ipq806x: Add support for IPQ806x chip family

Patches are generated using the "format-patch" command from the
following location:
*https://www.codeaurora.org/cgit/quic/kernel/galak-msm/log/?h=apq_ipq_base
*rev=0771849495b4128cac2faf7d49c85c729fc48b20
Patches numbered 76/77/102/103 have already been integrated in 3.14.12,
so they're not in this list.

All these patches are either integrated are pending integration into
kernel.org, therefore these patches should go away once the kernel
gets upgraded to 3.16.

Support is currently limited to AP148 board but can be extended to other
platforms in the future.

These changes do not cover ethernet connectivity.

Signed-off-by: Mathieu Olivari <mathieu@codeaurora.org>

git-svn-id: svn://svn.openwrt.org/openwrt/trunk@42334 3c298f89-4303-0410-b956-a3cf2f4a3e73

1 files changed, 495 insertions, 0 deletions

diff --git a/target/linux/ipq806x/patches/0179-spi-qup-Add-DMA-capabilities.patch b/target/linux/ipq806x/patches/0179-spi-qup-Add-DMA-capabilities.patch
new file mode 100644
index 0000000000..c35aeb17b3
--- /dev/null
+++ b/target/linux/ipq806x/patches/0179-spi-qup-Add-DMA-capabilities.patch
@@ -0,0 +1,495 @@
+From 8322bafdcee1d7eaf15540ff013415bff1eacb28 Mon Sep 17 00:00:00 2001
+From: Andy Gross <agross@codeaurora.org>
+Date: Thu, 26 Jun 2014 10:50:24 -0500
+Subject: [PATCH 179/182] spi: qup: Add DMA capabilities
+
+This patch adds DMA capabilities to the spi-qup driver.  If DMA channels are
+present, the QUP will use DMA instead of block mode for transfers to/from SPI
+peripherals for transactions larger greater than the length of a block.
+
+Signed-off-by: Andy Gross <agross@codeaurora.org>
+---
+ drivers/spi/spi-qup.c |  361 ++++++++++++++++++++++++++++++++++++++++++++++---
+ 1 file changed, 340 insertions(+), 21 deletions(-)
+
+diff --git a/drivers/spi/spi-qup.c b/drivers/spi/spi-qup.c
+index c137226..28754ae 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_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
+@@ -143,6 +147,14 @@ struct spi_qup {
+ 	int			tx_bytes;
+ 	int			rx_bytes;
+ 	int			qup_v1;
++	int			use_dma;
++
++	struct dma_chan		*rx_chan;
++	struct dma_slave_config	rx_conf;
++	struct dma_chan		*tx_chan;
++	struct dma_slave_config tx_conf;
++	void *dummy;
++	atomic_t		dma_outstanding;
+ };
+ 
+ 
+@@ -266,6 +278,221 @@ static void spi_qup_fifo_write(struct spi_qup *controller,
+ 	}
+ }
+ 
++static void qup_dma_callback(void *data)
++{
++	struct spi_qup *controller = data;
++
++	if (atomic_dec_and_test(&controller->dma_outstanding))
++		complete(&controller->done);
++}
++
++static int spi_qup_do_dma(struct spi_qup *controller, struct spi_transfer *xfer)
++{
++	struct dma_async_tx_descriptor *rxd, *txd;
++	dma_cookie_t rx_cookie, tx_cookie;
++	u32 xfer_len, rx_align = 0, tx_align = 0, n_words;
++	struct scatterlist tx_sg[2], rx_sg[2];
++	int ret = 0;
++	u32 bytes_to_xfer = xfer->len;
++	u32 offset = 0;
++	u32 rx_nents = 0, tx_nents = 0;
++	dma_addr_t rx_dma = 0, tx_dma = 0, rx_dummy_dma = 0, tx_dummy_dma = 0;
++
++
++	if (xfer->rx_buf) {
++		rx_dma = dma_map_single(controller->dev, xfer->rx_buf,
++			xfer->len, DMA_FROM_DEVICE);
++
++		if (dma_mapping_error(controller->dev, rx_dma)) {
++			ret = -ENOMEM;
++			return ret;
++		}
++
++		/* check to see if we need dummy buffer for leftover bytes */
++		rx_align = xfer->len % controller->in_blk_sz;
++		if (rx_align) {
++			rx_dummy_dma = dma_map_single(controller->dev,
++				controller->dummy, controller->in_fifo_sz,
++				DMA_FROM_DEVICE);
++
++			if (dma_mapping_error(controller->dev, rx_dummy_dma)) {
++				ret = -ENOMEM;
++				goto err_map_rx_dummy;
++			}
++		}
++	}
++
++	if (xfer->tx_buf) {
++		tx_dma = dma_map_single(controller->dev,
++			(void *)xfer->tx_buf, xfer->len, DMA_TO_DEVICE);
++
++		if (dma_mapping_error(controller->dev, tx_dma)) {
++			ret = -ENOMEM;
++			goto err_map_tx;
++		}
++
++		/* check to see if we need dummy buffer for leftover bytes */
++		tx_align = xfer->len % controller->out_blk_sz;
++		if (tx_align) {
++			memcpy(controller->dummy + SZ_1K,
++				xfer->tx_buf + xfer->len - tx_align,
++				tx_align);
++			memset(controller->dummy + SZ_1K + tx_align, 0,
++				controller->out_blk_sz - tx_align);
++
++			tx_dummy_dma = dma_map_single(controller->dev,
++				controller->dummy + SZ_1K,
++				controller->out_blk_sz, DMA_TO_DEVICE);
++
++			if (dma_mapping_error(controller->dev, tx_dummy_dma)) {
++				ret = -ENOMEM;
++				goto err_map_tx_dummy;
++			}
++		}
++	}
++
++	atomic_set(&controller->dma_outstanding, 0);
++
++	while (bytes_to_xfer > 0) {
++		xfer_len = min_t(u32, bytes_to_xfer, SPI_MAX_XFER);
++		n_words = DIV_ROUND_UP(xfer_len, controller->w_size);
++
++		/* write out current word count to controller */
++		writel_relaxed(n_words, controller->base + QUP_MX_INPUT_CNT);
++		writel_relaxed(n_words, controller->base + QUP_MX_OUTPUT_CNT);
++
++		reinit_completion(&controller->done);
++
++		if (xfer->tx_buf) {
++			/* recalc align for each transaction */
++			tx_align = xfer_len % controller->out_blk_sz;
++
++			if (tx_align)
++				tx_nents = 2;
++			else
++				tx_nents = 1;
++
++			/* initialize scatterlists */
++			sg_init_table(tx_sg, tx_nents);
++			sg_dma_len(&tx_sg[0]) = xfer_len - tx_align;
++			sg_dma_address(&tx_sg[0]) = tx_dma + offset;
++
++			/* account for non block size transfer */
++			if (tx_align) {
++				sg_dma_len(&tx_sg[1]) = controller->out_blk_sz;
++				sg_dma_address(&tx_sg[1]) = tx_dummy_dma;
++			}
++
++			txd = dmaengine_prep_slave_sg(controller->tx_chan,
++					tx_sg, tx_nents, DMA_MEM_TO_DEV, 0);
++			if (!txd) {
++				ret = -ENOMEM;
++				goto err_unmap;
++			}
++
++			atomic_inc(&controller->dma_outstanding);
++
++			txd->callback = qup_dma_callback;
++			txd->callback_param = controller;
++
++			tx_cookie = dmaengine_submit(txd);
++
++			dma_async_issue_pending(controller->tx_chan);
++		}
++
++		if (xfer->rx_buf) {
++			/* recalc align for each transaction */
++			rx_align = xfer_len % controller->in_blk_sz;
++
++			if (rx_align)
++				rx_nents = 2;
++			else
++				rx_nents = 1;
++
++			/* initialize scatterlists */
++			sg_init_table(rx_sg, rx_nents);
++			sg_dma_address(&rx_sg[0]) = rx_dma + offset;
++			sg_dma_len(&rx_sg[0]) = xfer_len - rx_align;
++
++			/* account for non block size transfer */
++			if (rx_align) {
++				sg_dma_len(&rx_sg[1]) = controller->in_blk_sz;
++				sg_dma_address(&rx_sg[1]) = rx_dummy_dma;
++			}
++
++			rxd = dmaengine_prep_slave_sg(controller->rx_chan,
++					rx_sg, rx_nents, DMA_DEV_TO_MEM, 0);
++			if (!rxd) {
++				ret = -ENOMEM;
++				goto err_unmap;
++			}
++
++			atomic_inc(&controller->dma_outstanding);
++
++			rxd->callback = qup_dma_callback;
++			rxd->callback_param = controller;
++
++			rx_cookie = dmaengine_submit(rxd);
++
++			dma_async_issue_pending(controller->rx_chan);
++		}
++
++		if (spi_qup_set_state(controller, QUP_STATE_RUN)) {
++			dev_warn(controller->dev, "cannot set EXECUTE state\n");
++			goto err_unmap;
++		}
++
++		if (!wait_for_completion_timeout(&controller->done,
++			msecs_to_jiffies(1000))) {
++			ret = -ETIMEDOUT;
++
++			/* clear out all the DMA transactions */
++			if (xfer->tx_buf)
++				dmaengine_terminate_all(controller->tx_chan);
++			if (xfer->rx_buf)
++				dmaengine_terminate_all(controller->rx_chan);
++
++			goto err_unmap;
++		}
++
++		if (rx_align)
++			memcpy(xfer->rx_buf + offset + xfer->len - rx_align,
++				controller->dummy, rx_align);
++
++		/* adjust remaining bytes to transfer */
++		bytes_to_xfer -= xfer_len;
++		offset += xfer_len;
++
++
++		/* reset mini-core state so we can program next transaction */
++		if (spi_qup_set_state(controller, QUP_STATE_RESET)) {
++			dev_err(controller->dev, "cannot set RESET state\n");
++			goto err_unmap;
++		}
++	}
++
++	ret = 0;
++
++err_unmap:
++	if (tx_align)
++		dma_unmap_single(controller->dev, tx_dummy_dma,
++			controller->out_fifo_sz, DMA_TO_DEVICE);
++err_map_tx_dummy:
++	if (xfer->tx_buf)
++		dma_unmap_single(controller->dev, tx_dma, xfer->len,
++			DMA_TO_DEVICE);
++err_map_tx:
++	if (rx_align)
++		dma_unmap_single(controller->dev, rx_dummy_dma,
++			controller->in_fifo_sz, DMA_FROM_DEVICE);
++err_map_rx_dummy:
++	if (xfer->rx_buf)
++		dma_unmap_single(controller->dev, rx_dma, xfer->len,
++			DMA_FROM_DEVICE);
++
++	return ret;
++}
++
+ static irqreturn_t spi_qup_qup_irq(int irq, void *dev_id)
+ {
+ 	struct spi_qup *controller = dev_id;
+@@ -315,11 +542,13 @@ 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;
+@@ -339,6 +568,8 @@ 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;
+ 	int ret, n_words, w_size;
++	size_t dma_align = dma_get_cache_alignment();
++	u32 dma_available = 0;
+ 
+ 	if (spi->mode & SPI_LOOP && xfer->len > controller->in_fifo_sz) {
+ 		dev_err(controller->dev, "too big size for loopback %d > %d\n",
+@@ -367,6 +598,13 @@ static int spi_qup_io_config(struct spi_device *spi, struct spi_transfer *xfer)
+ 	n_words = xfer->len / w_size;
+ 	controller->w_size = w_size;
+ 
++	if (controller->rx_chan &&
++		IS_ALIGNED((size_t)xfer->tx_buf, dma_align) &&
++		IS_ALIGNED((size_t)xfer->rx_buf, dma_align) &&
++		!is_vmalloc_addr(xfer->tx_buf) &&
++		!is_vmalloc_addr(xfer->rx_buf))
++		dma_available = 1;
++
+ 	if (n_words <= (controller->in_fifo_sz / sizeof(u32))) {
+ 		mode = QUP_IO_M_MODE_FIFO;
+ 		writel_relaxed(n_words, controller->base + QUP_MX_READ_CNT);
+@@ -374,19 +612,30 @@ static int spi_qup_io_config(struct spi_device *spi, struct spi_transfer *xfer)
+ 		/* must be zero for FIFO */
+ 		writel_relaxed(0, controller->base + QUP_MX_INPUT_CNT);
+ 		writel_relaxed(0, controller->base + QUP_MX_OUTPUT_CNT);
+-	} else {
++		controller->use_dma = 0;
++	} else if (!dma_available) {
+ 		mode = QUP_IO_M_MODE_BLOCK;
+ 		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);
++		controller->use_dma = 0;
++	} else {
++		mode = QUP_IO_M_MODE_DMOV;
++		writel_relaxed(0, controller->base + QUP_MX_READ_CNT);
++		writel_relaxed(0, controller->base + QUP_MX_WRITE_CNT);
++		controller->use_dma = 1;
+ 	}
+ 
+ 	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);
+ 
+@@ -419,11 +668,20 @@ 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);
++
+ 	return 0;
+ }
+ 
+@@ -452,26 +710,32 @@ 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(controller, xfer);
++	} else {
++		if (spi_qup_set_state(controller, QUP_STATE_RUN)) {
++			dev_warn(controller->dev, "cannot set RUN state\n");
++			goto exit;
++		}
+ 
+-	if (spi_qup_set_state(controller, QUP_STATE_PAUSE)) {
+-		dev_warn(controller->dev, "cannot set PAUSE state\n");
+-		goto exit;
+-	}
++		if (spi_qup_set_state(controller, QUP_STATE_PAUSE)) {
++			dev_warn(controller->dev, "cannot set PAUSE state\n");
++			goto exit;
++		}
+ 
+-	spi_qup_fifo_write(controller, xfer);
++		spi_qup_fifo_write(controller, xfer);
+ 
+-	if (spi_qup_set_state(controller, QUP_STATE_RUN)) {
+-		dev_warn(controller->dev, "cannot set EXECUTE state\n");
+-		goto exit;
+-	}
++		if (spi_qup_set_state(controller, QUP_STATE_RUN)) {
++			dev_warn(controller->dev, "cannot set EXECUTE state\n");
++			goto exit;
++		}
+ 
+-	if (!wait_for_completion_timeout(&controller->done, timeout))
+-		ret = -ETIMEDOUT;
++		if (!ret && !wait_for_completion_timeout(&controller->done,
++				timeout))
++			ret = -ETIMEDOUT;
++	}
+ exit:
++
+ 	spi_qup_set_state(controller, QUP_STATE_RESET);
+ 	spin_lock_irqsave(&controller->lock, flags);
+ 	controller->xfer = NULL;
+@@ -553,6 +817,7 @@ 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();
+ 
+ 	platform_set_drvdata(pdev, master);
+ 
+@@ -612,6 +877,55 @@ static int spi_qup_probe(struct platform_device *pdev)
+ 	writel_relaxed(SPI_ERROR_CLK_UNDER_RUN | SPI_ERROR_CLK_OVER_RUN,
+ 		       base + SPI_ERROR_FLAGS_EN);
+ 
++	/* allocate dma resources, if available */
++	controller->rx_chan = dma_request_slave_channel(&pdev->dev, "rx");
++	if (controller->rx_chan) {
++		controller->tx_chan =
++			dma_request_slave_channel(&pdev->dev, "tx");
++
++		if (!controller->tx_chan) {
++			dev_err(&pdev->dev, "Failed to allocate dma tx chan");
++			dma_release_channel(controller->rx_chan);
++		}
++
++		/* set DMA parameters */
++		controller->rx_conf.device_fc = 1;
++		controller->rx_conf.src_addr = res->start + QUP_INPUT_FIFO;
++		controller->rx_conf.src_maxburst = controller->in_blk_sz;
++
++		controller->tx_conf.device_fc = 1;
++		controller->tx_conf.dst_addr = res->start + QUP_OUTPUT_FIFO;
++		controller->tx_conf.dst_maxburst = controller->out_blk_sz;
++
++		if (dmaengine_slave_config(controller->rx_chan,
++				&controller->rx_conf)) {
++			dev_err(&pdev->dev, "failed to configure RX channel\n");
++
++			dma_release_channel(controller->rx_chan);
++			dma_release_channel(controller->tx_chan);
++			controller->tx_chan = NULL;
++			controller->rx_chan = NULL;
++		} else if (dmaengine_slave_config(controller->tx_chan,
++				&controller->tx_conf)) {
++			dev_err(&pdev->dev, "failed to configure TX channel\n");
++
++			dma_release_channel(controller->rx_chan);
++			dma_release_channel(controller->tx_chan);
++			controller->tx_chan = NULL;
++			controller->rx_chan = NULL;
++		}
++
++		controller->dummy = devm_kmalloc(controller->dev, PAGE_SIZE,
++			GFP_KERNEL);
++
++		if (!controller->dummy) {
++			dma_release_channel(controller->rx_chan);
++			dma_release_channel(controller->tx_chan);
++			controller->tx_chan = NULL;
++			controller->rx_chan = NULL;
++		}
++	}
++
+ 	/* if earlier version of the QUP, disable INPUT_OVERRUN */
+ 	if (controller->qup_v1)
+ 		writel_relaxed(QUP_ERROR_OUTPUT_OVER_RUN |
+@@ -730,6 +1044,11 @@ static int spi_qup_remove(struct platform_device *pdev)
+ 	if (ret)
+ 		return ret;
+ 
++	if (controller->rx_chan)
++		dma_release_channel(controller->rx_chan);
++	if (controller->tx_chan)
++		dma_release_channel(controller->tx_chan);
++
+ 	clk_disable_unprepare(controller->cclk);
+ 	clk_disable_unprepare(controller->iclk);
+ 
+-- 
+1.7.10.4
+