2 files changed, 386 insertions, 83 deletions

diff --git a/drivers/fpga/fpga-mgr.c b/drivers/fpga/fpga-mgr.c
index f0a69d3e60a5..86d2cb203533 100644
--- a/drivers/fpga/fpga-mgr.c
+++ b/drivers/fpga/fpga-mgr.c
@@ -25,16 +25,106 @@
 #include <linux/of.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
+#include <linux/scatterlist.h>
+#include <linux/highmem.h>
 
 static DEFINE_IDA(fpga_mgr_ida);
 static struct class *fpga_mgr_class;
 
+/*
+ * Call the low level driver's write_init function.  This will do the
+ * device-specific things to get the FPGA into the state where it is ready to
+ * receive an FPGA image. The low level driver only gets to see the first
+ * initial_header_size bytes in the buffer.
+ */
+static int fpga_mgr_write_init_buf(struct fpga_manager *mgr,
+				   struct fpga_image_info *info,
+				   const char *buf, size_t count)
+{
+	int ret;
+
+	mgr->state = FPGA_MGR_STATE_WRITE_INIT;
+	if (!mgr->mops->initial_header_size)
+		ret = mgr->mops->write_init(mgr, info, NULL, 0);
+	else
+		ret = mgr->mops->write_init(
+		    mgr, info, buf, min(mgr->mops->initial_header_size, count));
+
+	if (ret) {
+		dev_err(&mgr->dev, "Error preparing FPGA for writing\n");
+		mgr->state = FPGA_MGR_STATE_WRITE_INIT_ERR;
+		return ret;
+	}
+
+	return 0;
+}
+
+static int fpga_mgr_write_init_sg(struct fpga_manager *mgr,
+				  struct fpga_image_info *info,
+				  struct sg_table *sgt)
+{
+	struct sg_mapping_iter miter;
+	size_t len;
+	char *buf;
+	int ret;
+
+	if (!mgr->mops->initial_header_size)
+		return fpga_mgr_write_init_buf(mgr, info, NULL, 0);
+
+	/*
+	 * First try to use miter to map the first fragment to access the
+	 * header, this is the typical path.
+	 */
+	sg_miter_start(&miter, sgt->sgl, sgt->nents, SG_MITER_FROM_SG);
+	if (sg_miter_next(&miter) &&
+	    miter.length >= mgr->mops->initial_header_size) {
+		ret = fpga_mgr_write_init_buf(mgr, info, miter.addr,
+					      miter.length);
+		sg_miter_stop(&miter);
+		return ret;
+	}
+	sg_miter_stop(&miter);
+
+	/* Otherwise copy the fragments into temporary memory. */
+	buf = kmalloc(mgr->mops->initial_header_size, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	len = sg_copy_to_buffer(sgt->sgl, sgt->nents, buf,
+				mgr->mops->initial_header_size);
+	ret = fpga_mgr_write_init_buf(mgr, info, buf, len);
+
+	kfree(buf);
+
+	return ret;
+}
+
+/*
+ * After all the FPGA image has been written, do the device specific steps to
+ * finish and set the FPGA into operating mode.
+ */
+static int fpga_mgr_write_complete(struct fpga_manager *mgr,
+				   struct fpga_image_info *info)
+{
+	int ret;
+
+	mgr->state = FPGA_MGR_STATE_WRITE_COMPLETE;
+	ret = mgr->mops->write_complete(mgr, info);
+	if (ret) {
+		dev_err(&mgr->dev, "Error after writing image data to FPGA\n");
+		mgr->state = FPGA_MGR_STATE_WRITE_COMPLETE_ERR;
+		return ret;
+	}
+	mgr->state = FPGA_MGR_STATE_OPERATING;
+
+	return 0;
+}
+
 /**
- * fpga_mgr_buf_load - load fpga from image in buffer
+ * fpga_mgr_buf_load_sg - load fpga from image in buffer from a scatter list
  * @mgr:	fpga manager
  * @info:	fpga image specific information
- * @buf:	buffer contain fpga image
- * @count:	byte count of buf
+ * @sgt:	scatterlist table
  *
  * Step the low level fpga manager through the device-specific steps of getting
  * an FPGA ready to be configured, writing the image to it, then doing whatever
@@ -42,54 +132,139 @@ static struct class *fpga_mgr_class;
  * mgr pointer from of_fpga_mgr_get() or fpga_mgr_get() and checked that it is
  * not an error code.
  *
+ * This is the preferred entry point for FPGA programming, it does not require
+ * any contiguous kernel memory.
+ *
  * Return: 0 on success, negative error code otherwise.
  */
-int fpga_mgr_buf_load(struct fpga_manager *mgr, struct fpga_image_info *info,
-		      const char *buf, size_t count)
+int fpga_mgr_buf_load_sg(struct fpga_manager *mgr, struct fpga_image_info *info,
+			 struct sg_table *sgt)
 {
-	struct device *dev = &mgr->dev;
 	int ret;
 
-	/*
-	 * Call the low level driver's write_init function.  This will do the
-	 * device-specific things to get the FPGA into the state where it is
-	 * ready to receive an FPGA image. The low level driver only gets to
-	 * see the first initial_header_size bytes in the buffer.
-	 */
-	mgr->state = FPGA_MGR_STATE_WRITE_INIT;
-	ret = mgr->mops->write_init(mgr, info, buf,
-				    min(mgr->mops->initial_header_size, count));
+	ret = fpga_mgr_write_init_sg(mgr, info, sgt);
+	if (ret)
+		return ret;
+
+	/* Write the FPGA image to the FPGA. */
+	mgr->state = FPGA_MGR_STATE_WRITE;
+	if (mgr->mops->write_sg) {
+		ret = mgr->mops->write_sg(mgr, sgt);
+	} else {
+		struct sg_mapping_iter miter;
+
+		sg_miter_start(&miter, sgt->sgl, sgt->nents, SG_MITER_FROM_SG);
+		while (sg_miter_next(&miter)) {
+			ret = mgr->mops->write(mgr, miter.addr, miter.length);
+			if (ret)
+				break;
+		}
+		sg_miter_stop(&miter);
+	}
+
 	if (ret) {
-		dev_err(dev, "Error preparing FPGA for writing\n");
-		mgr->state = FPGA_MGR_STATE_WRITE_INIT_ERR;
+		dev_err(&mgr->dev, "Error while writing image data to FPGA\n");
+		mgr->state = FPGA_MGR_STATE_WRITE_ERR;
 		return ret;
 	}
 
+	return fpga_mgr_write_complete(mgr, info);
+}
+EXPORT_SYMBOL_GPL(fpga_mgr_buf_load_sg);
+
+static int fpga_mgr_buf_load_mapped(struct fpga_manager *mgr,
+				    struct fpga_image_info *info,
+				    const char *buf, size_t count)
+{
+	int ret;
+
+	ret = fpga_mgr_write_init_buf(mgr, info, buf, count);
+	if (ret)
+		return ret;
+
 	/*
 	 * Write the FPGA image to the FPGA.
 	 */
 	mgr->state = FPGA_MGR_STATE_WRITE;
 	ret = mgr->mops->write(mgr, buf, count);
 	if (ret) {
-		dev_err(dev, "Error while writing image data to FPGA\n");
+		dev_err(&mgr->dev, "Error while writing image data to FPGA\n");
 		mgr->state = FPGA_MGR_STATE_WRITE_ERR;
 		return ret;
 	}
 
+	return fpga_mgr_write_complete(mgr, info);
+}
+
+/**
+ * fpga_mgr_buf_load - load fpga from image in buffer
+ * @mgr:	fpga manager
+ * @flags:	flags setting fpga confuration modes
+ * @buf:	buffer contain fpga image
+ * @count:	byte count of buf
+ *
+ * Step the low level fpga manager through the device-specific steps of getting
+ * an FPGA ready to be configured, writing the image to it, then doing whatever
+ * post-configuration steps necessary.  This code assumes the caller got the
+ * mgr pointer from of_fpga_mgr_get() and checked that it is not an error code.
+ *
+ * Return: 0 on success, negative error code otherwise.
+ */
+int fpga_mgr_buf_load(struct fpga_manager *mgr, struct fpga_image_info *info,
+		      const char *buf, size_t count)
+{
+	struct page **pages;
+	struct sg_table sgt;
+	const void *p;
+	int nr_pages;
+	int index;
+	int rc;
+
 	/*
-	 * After all the FPGA image has been written, do the device specific
-	 * steps to finish and set the FPGA into operating mode.
+	 * This is just a fast path if the caller has already created a
+	 * contiguous kernel buffer and the driver doesn't require SG, non-SG
+	 * drivers will still work on the slow path.
 	 */
-	mgr->state = FPGA_MGR_STATE_WRITE_COMPLETE;
-	ret = mgr->mops->write_complete(mgr, info);
-	if (ret) {
-		dev_err(dev, "Error after writing image data to FPGA\n");
-		mgr->state = FPGA_MGR_STATE_WRITE_COMPLETE_ERR;
-		return ret;
+	if (mgr->mops->write)
+		return fpga_mgr_buf_load_mapped(mgr, info, buf, count);
+
+	/*
+	 * Convert the linear kernel pointer into a sg_table of pages for use
+	 * by the driver.
+	 */
+	nr_pages = DIV_ROUND_UP((unsigned long)buf + count, PAGE_SIZE) -
+		   (unsigned long)buf / PAGE_SIZE;
+	pages = kmalloc_array(nr_pages, sizeof(struct page *), GFP_KERNEL);
+	if (!pages)
+		return -ENOMEM;
+
+	p = buf - offset_in_page(buf);
+	for (index = 0; index < nr_pages; index++) {
+		if (is_vmalloc_addr(p))
+			pages[index] = vmalloc_to_page(p);
+		else
+			pages[index] = kmap_to_page((void *)p);
+		if (!pages[index]) {
+			kfree(pages);
+			return -EFAULT;
+		}
+		p += PAGE_SIZE;
 	}
-	mgr->state = FPGA_MGR_STATE_OPERATING;
 
-	return 0;
+	/*
+	 * The temporary pages list is used to code share the merging algorithm
+	 * in sg_alloc_table_from_pages
+	 */
+	rc = sg_alloc_table_from_pages(&sgt, pages, index, offset_in_page(buf),
+				       count, GFP_KERNEL);
+	kfree(pages);
+	if (rc)
+		return rc;
+
+	rc = fpga_mgr_buf_load_sg(mgr, info, &sgt);
+	sg_free_table(&sgt);
+
+	return rc;
 }
 EXPORT_SYMBOL_GPL(fpga_mgr_buf_load);
 
@@ -291,8 +466,9 @@ int fpga_mgr_register(struct device *dev, const char *name,
 	struct fpga_manager *mgr;
 	int id, ret;
 
-	if (!mops || !mops->write_init || !mops->write ||
-	    !mops->write_complete || !mops->state) {
+	if (!mops || !mops->write_complete || !mops->state ||
+	    !mops->write_init || (!mops->write && !mops->write_sg) ||
+	    (mops->write && mops->write_sg)) {
 		dev_err(dev, "Attempt to register without fpga_manager_ops\n");
 		return -EINVAL;
 	}
diff --git a/drivers/fpga/zynq-fpga.c b/drivers/fpga/zynq-fpga.c
index 1812bf7614e1..34cb98139442 100644
--- a/drivers/fpga/zynq-fpga.c
+++ b/drivers/fpga/zynq-fpga.c
@@ -30,6 +30,7 @@
 #include <linux/pm.h>
 #include <linux/regmap.h>
 #include <linux/string.h>
+#include <linux/scatterlist.h>
 
 /* Offsets into SLCR regmap */
 
@@ -80,6 +81,7 @@
 
 /* FPGA init status */
 #define STATUS_DMA_Q_F			BIT(31)
+#define STATUS_DMA_Q_E			BIT(30)
 #define STATUS_PCFG_INIT_MASK		BIT(4)
 
 /* Interrupt Status/Mask Register Bit definitions */
@@ -89,7 +91,7 @@
 #define IXR_D_P_DONE_MASK		BIT(12)
  /* FPGA programmed */
 #define IXR_PCFG_DONE_MASK		BIT(2)
-#define IXR_ERROR_FLAGS_MASK		0x00F0F860
+#define IXR_ERROR_FLAGS_MASK		0x00F0C860
 #define IXR_ALL_MASK			0xF8F7F87F
 
 /* Miscellaneous constant values */
@@ -98,12 +100,16 @@
 #define DMA_INVALID_ADDRESS		GENMASK(31, 0)
 /* Used to unlock the dev */
 #define UNLOCK_MASK			0x757bdf0d
-/* Timeout for DMA to complete */
-#define DMA_DONE_TIMEOUT		msecs_to_jiffies(1000)
 /* Timeout for polling reset bits */
 #define INIT_POLL_TIMEOUT		2500000
 /* Delay for polling reset bits */
 #define INIT_POLL_DELAY			20
+/* Signal this is the last DMA transfer, wait for the AXI and PCAP before
+ * interrupting
+ */
+#define DMA_SRC_LAST_TRANSFER		1
+/* Timeout for DMA completion */
+#define DMA_TIMEOUT_MS			5000
 
 /* Masks for controlling stuff in SLCR */
 /* Disable all Level shifters */
@@ -124,6 +130,11 @@ struct zynq_fpga_priv {
 	void __iomem *io_base;
 	struct regmap *slcr;
 
+	spinlock_t dma_lock;
+	unsigned int dma_elm;
+	unsigned int dma_nelms;
+	struct scatterlist *cur_sg;
+
 	struct completion dma_done;
 };
 
@@ -143,37 +154,104 @@ static inline u32 zynq_fpga_read(const struct zynq_fpga_priv *priv,
 	readl_poll_timeout(priv->io_base + addr, val, cond, sleep_us, \
 			   timeout_us)
 
-static void zynq_fpga_mask_irqs(struct zynq_fpga_priv *priv)
+/* Cause the specified irq mask bits to generate IRQs */
+static inline void zynq_fpga_set_irq(struct zynq_fpga_priv *priv, u32 enable)
 {
-	u32 intr_mask;
-
-	intr_mask = zynq_fpga_read(priv, INT_MASK_OFFSET);
-	zynq_fpga_write(priv, INT_MASK_OFFSET,
-			intr_mask | IXR_DMA_DONE_MASK | IXR_ERROR_FLAGS_MASK);
+	zynq_fpga_write(priv, INT_MASK_OFFSET, ~enable);
 }
 
-static void zynq_fpga_unmask_irqs(struct zynq_fpga_priv *priv)
+/* Must be called with dma_lock held */
+static void zynq_step_dma(struct zynq_fpga_priv *priv)
 {
-	u32 intr_mask;
+	u32 addr;
+	u32 len;
+	bool first;
+
+	first = priv->dma_elm == 0;
+	while (priv->cur_sg) {
+		/* Feed the DMA queue until it is full. */
+		if (zynq_fpga_read(priv, STATUS_OFFSET) & STATUS_DMA_Q_F)
+			break;
+
+		addr = sg_dma_address(priv->cur_sg);
+		len = sg_dma_len(priv->cur_sg);
+		if (priv->dma_elm + 1 == priv->dma_nelms) {
+			/* The last transfer waits for the PCAP to finish too,
+			 * notice this also changes the irq_mask to ignore
+			 * IXR_DMA_DONE_MASK which ensures we do not trigger
+			 * the completion too early.
+			 */
+			addr |= DMA_SRC_LAST_TRANSFER;
+			priv->cur_sg = NULL;
+		} else {
+			priv->cur_sg = sg_next(priv->cur_sg);
+			priv->dma_elm++;
+		}
 
-	intr_mask = zynq_fpga_read(priv, INT_MASK_OFFSET);
-	zynq_fpga_write(priv, INT_MASK_OFFSET,
-			intr_mask
-			& ~(IXR_D_P_DONE_MASK | IXR_ERROR_FLAGS_MASK));
+		zynq_fpga_write(priv, DMA_SRC_ADDR_OFFSET, addr);
+		zynq_fpga_write(priv, DMA_DST_ADDR_OFFSET, DMA_INVALID_ADDRESS);
+		zynq_fpga_write(priv, DMA_SRC_LEN_OFFSET, len / 4);
+		zynq_fpga_write(priv, DMA_DEST_LEN_OFFSET, 0);
+	}
+
+	/* Once the first transfer is queued we can turn on the ISR, future
+	 * calls to zynq_step_dma will happen from the ISR context. The
+	 * dma_lock spinlock guarentees this handover is done coherently, the
+	 * ISR enable is put at the end to avoid another CPU spinning in the
+	 * ISR on this lock.
+	 */
+	if (first && priv->cur_sg) {
+		zynq_fpga_set_irq(priv,
+				  IXR_DMA_DONE_MASK | IXR_ERROR_FLAGS_MASK);
+	} else if (!priv->cur_sg) {
+		/* The last transfer changes to DMA & PCAP mode since we do
+		 * not want to continue until everything has been flushed into
+		 * the PCAP.
+		 */
+		zynq_fpga_set_irq(priv,
+				  IXR_D_P_DONE_MASK | IXR_ERROR_FLAGS_MASK);
+	}
 }
 
 static irqreturn_t zynq_fpga_isr(int irq, void *data)
 {
 	struct zynq_fpga_priv *priv = data;
+	u32 intr_status;
 
-	/* disable DMA and error IRQs */
-	zynq_fpga_mask_irqs(priv);
+	/* If anything other than DMA completion is reported stop and hand
+	 * control back to zynq_fpga_ops_write, something went wrong,
+	 * otherwise progress the DMA.
+	 */
+	spin_lock(&priv->dma_lock);
+	intr_status = zynq_fpga_read(priv, INT_STS_OFFSET);
+	if (!(intr_status & IXR_ERROR_FLAGS_MASK) &&
+	    (intr_status & IXR_DMA_DONE_MASK) && priv->cur_sg) {
+		zynq_fpga_write(priv, INT_STS_OFFSET, IXR_DMA_DONE_MASK);
+		zynq_step_dma(priv);
+		spin_unlock(&priv->dma_lock);
+		return IRQ_HANDLED;
+	}
+	spin_unlock(&priv->dma_lock);
 
+	zynq_fpga_set_irq(priv, 0);
 	complete(&priv->dma_done);
 
 	return IRQ_HANDLED;
 }
 
+/* Sanity check the proposed bitstream. It must start with the sync word in
+ * the correct byte order, and be dword aligned. The input is a Xilinx .bin
+ * file with every 32 bit quantity swapped.
+ */
+static bool zynq_fpga_has_sync(const u8 *buf, size_t count)
+{
+	for (; count >= 4; buf += 4, count -= 4)
+		if (buf[0] == 0x66 && buf[1] == 0x55 && buf[2] == 0x99 &&
+		    buf[3] == 0xaa)
+			return true;
+	return false;
+}
+
 static int zynq_fpga_ops_write_init(struct fpga_manager *mgr,
 				    struct fpga_image_info *info,
 				    const char *buf, size_t count)
@@ -190,6 +268,13 @@ static int zynq_fpga_ops_write_init(struct fpga_manager *mgr,
 
 	/* don't globally reset PL if we're doing partial reconfig */
 	if (!(info->flags & FPGA_MGR_PARTIAL_RECONFIG)) {
+		if (!zynq_fpga_has_sync(buf, count)) {
+			dev_err(&mgr->dev,
+				"Invalid bitstream, could not find a sync word. Bitstream must be a byte swapped .bin file\n");
+			err = -EINVAL;
+			goto out_err;
+		}
+
 		/* assert AXI interface resets */
 		regmap_write(priv->slcr, SLCR_FPGA_RST_CTRL_OFFSET,
 			     FPGA_RST_ALL_MASK);
@@ -259,10 +344,11 @@ static int zynq_fpga_ops_write_init(struct fpga_manager *mgr,
 	zynq_fpga_write(priv, CTRL_OFFSET,
 			(CTRL_PCAP_PR_MASK | CTRL_PCAP_MODE_MASK | ctrl));
 
-	/* check that we have room in the command queue */
+	/* We expect that the command queue is empty right now. */
 	status = zynq_fpga_read(priv, STATUS_OFFSET);
-	if (status & STATUS_DMA_Q_F) {
-		dev_err(&mgr->dev, "DMA command queue full\n");
+	if ((status & STATUS_DMA_Q_F) ||
+	    (status & STATUS_DMA_Q_E) != STATUS_DMA_Q_E) {
+		dev_err(&mgr->dev, "DMA command queue not right\n");
 		err = -EBUSY;
 		goto out_err;
 	}
@@ -281,26 +367,36 @@ out_err:
 	return err;
 }
 
-static int zynq_fpga_ops_write(struct fpga_manager *mgr,
-			       const char *buf, size_t count)
+static int zynq_fpga_ops_write(struct fpga_manager *mgr, struct sg_table *sgt)
 {
 	struct zynq_fpga_priv *priv;
+	const char *why;
 	int err;
-	char *kbuf;
-	size_t in_count;
-	dma_addr_t dma_addr;
-	u32 transfer_length;
 	u32 intr_status;
+	unsigned long timeout;
+	unsigned long flags;
+	struct scatterlist *sg;
+	int i;
 
-	in_count = count;
 	priv = mgr->priv;
 
-	kbuf =
-	    dma_alloc_coherent(mgr->dev.parent, count, &dma_addr, GFP_KERNEL);
-	if (!kbuf)
-		return -ENOMEM;
+	/* The hardware can only DMA multiples of 4 bytes, and it requires the
+	 * starting addresses to be aligned to 64 bits (UG585 pg 212).
+	 */
+	for_each_sg(sgt->sgl, sg, sgt->nents, i) {
+		if ((sg->offset % 8) || (sg->length % 4)) {
+			dev_err(&mgr->dev,
+			    "Invalid bitstream, chunks must be aligned\n");
+			return -EINVAL;
+		}
+	}
 
-	memcpy(kbuf, buf, count);
+	priv->dma_nelms =
+	    dma_map_sg(mgr->dev.parent, sgt->sgl, sgt->nents, DMA_TO_DEVICE);
+	if (priv->dma_nelms == 0) {
+		dev_err(&mgr->dev, "Unable to DMA map (TO_DEVICE)\n");
+		return -ENOMEM;
+	}
 
 	/* enable clock */
 	err = clk_enable(priv->clk);
@@ -308,38 +404,67 @@ static int zynq_fpga_ops_write(struct fpga_manager *mgr,
 		goto out_free;
 
 	zynq_fpga_write(priv, INT_STS_OFFSET, IXR_ALL_MASK);
-
 	reinit_completion(&priv->dma_done);
 
-	/* enable DMA and error IRQs */
-	zynq_fpga_unmask_irqs(priv);
+	/* zynq_step_dma will turn on interrupts */
+	spin_lock_irqsave(&priv->dma_lock, flags);
+	priv->dma_elm = 0;
+	priv->cur_sg = sgt->sgl;
+	zynq_step_dma(priv);
+	spin_unlock_irqrestore(&priv->dma_lock, flags);
 
-	/* the +1 in the src addr is used to hold off on DMA_DONE IRQ
-	 * until both AXI and PCAP are done ...
-	 */
-	zynq_fpga_write(priv, DMA_SRC_ADDR_OFFSET, (u32)(dma_addr) + 1);
-	zynq_fpga_write(priv, DMA_DST_ADDR_OFFSET, (u32)DMA_INVALID_ADDRESS);
+	timeout = wait_for_completion_timeout(&priv->dma_done,
+					      msecs_to_jiffies(DMA_TIMEOUT_MS));
 
-	/* convert #bytes to #words */
-	transfer_length = (count + 3) / 4;
+	spin_lock_irqsave(&priv->dma_lock, flags);
+	zynq_fpga_set_irq(priv, 0);
+	priv->cur_sg = NULL;
+	spin_unlock_irqrestore(&priv->dma_lock, flags);
 
-	zynq_fpga_write(priv, DMA_SRC_LEN_OFFSET, transfer_length);
-	zynq_fpga_write(priv, DMA_DEST_LEN_OFFSET, 0);
+	intr_status = zynq_fpga_read(priv, INT_STS_OFFSET);
+	zynq_fpga_write(priv, INT_STS_OFFSET, IXR_ALL_MASK);
 
-	wait_for_completion(&priv->dma_done);
+	/* There doesn't seem to be a way to force cancel any DMA, so if
+	 * something went wrong we are relying on the hardware to have halted
+	 * the DMA before we get here, if there was we could use
+	 * wait_for_completion_interruptible too.
+	 */
 
-	intr_status = zynq_fpga_read(priv, INT_STS_OFFSET);
-	zynq_fpga_write(priv, INT_STS_OFFSET, intr_status);
+	if (intr_status & IXR_ERROR_FLAGS_MASK) {
+		why = "DMA reported error";
+		err = -EIO;
+		goto out_report;
+	}
 
-	if (!((intr_status & IXR_D_P_DONE_MASK) == IXR_D_P_DONE_MASK)) {
-		dev_err(&mgr->dev, "Error configuring FPGA\n");
-		err = -EFAULT;
+	if (priv->cur_sg ||
+	    !((intr_status & IXR_D_P_DONE_MASK) == IXR_D_P_DONE_MASK)) {
+		if (timeout == 0)
+			why = "DMA timed out";
+		else
+			why = "DMA did not complete";
+		err = -EIO;
+		goto out_report;
 	}
 
+	err = 0;
+	goto out_clk;
+
+out_report:
+	dev_err(&mgr->dev,
+		"%s: INT_STS:0x%x CTRL:0x%x LOCK:0x%x INT_MASK:0x%x STATUS:0x%x MCTRL:0x%x\n",
+		why,
+		intr_status,
+		zynq_fpga_read(priv, CTRL_OFFSET),
+		zynq_fpga_read(priv, LOCK_OFFSET),
+		zynq_fpga_read(priv, INT_MASK_OFFSET),
+		zynq_fpga_read(priv, STATUS_OFFSET),
+		zynq_fpga_read(priv, MCTRL_OFFSET));
+
+out_clk:
 	clk_disable(priv->clk);
 
 out_free:
-	dma_free_coherent(mgr->dev.parent, count, kbuf, dma_addr);
+	dma_unmap_sg(mgr->dev.parent, sgt->sgl, sgt->nents, DMA_TO_DEVICE);
 	return err;
 }
 
@@ -400,9 +525,10 @@ static enum fpga_mgr_states zynq_fpga_ops_state(struct fpga_manager *mgr)
 }
 
 static const struct fpga_manager_ops zynq_fpga_ops = {
+	.initial_header_size = 128,
 	.state = zynq_fpga_ops_state,
 	.write_init = zynq_fpga_ops_write_init,
-	.write = zynq_fpga_ops_write,
+	.write_sg = zynq_fpga_ops_write,
 	.write_complete = zynq_fpga_ops_write_complete,
 };
 
@@ -416,6 +542,7 @@ static int zynq_fpga_probe(struct platform_device *pdev)
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
+	spin_lock_init(&priv->dma_lock);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	priv->io_base = devm_ioremap_resource(dev, res);
@@ -452,7 +579,7 @@ static int zynq_fpga_probe(struct platform_device *pdev)
 	/* unlock the device */
 	zynq_fpga_write(priv, UNLOCK_OFFSET, UNLOCK_MASK);
 
-	zynq_fpga_write(priv, INT_MASK_OFFSET, 0xFFFFFFFF);
+	zynq_fpga_set_irq(priv, 0);
 	zynq_fpga_write(priv, INT_STS_OFFSET, IXR_ALL_MASK);
 	err = devm_request_irq(dev, priv->irq, zynq_fpga_isr, 0, dev_name(dev),
 			       priv);