xillybus: Move out of staging

This driver has been functional and stable throughout the year it has spent
in the staging area. It has been patched for minor bugs, coding style issues
and improvements during this period.

This is the second submission of this move-out, after making several style
improvements, as suggested by Dan Carpenter.

Signed-off-by: Eli Billauer <eli.billauer@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

6 files changed, 2718 insertions, 0 deletions

diff --git a/drivers/char/xillybus/Kconfig b/drivers/char/xillybus/Kconfig
new file mode 100644
index 000000000000..b53bdf12da0d
--- /dev/null
+++ b/drivers/char/xillybus/Kconfig
@@ -0,0 +1,33 @@
+#
+# Xillybus devices
+#
+
+config XILLYBUS
+	tristate "Xillybus generic FPGA interface"
+	depends on PCI || (OF_ADDRESS && OF_IRQ)
+	select CRC32
+	help
+	  Xillybus is a generic interface for peripherals designed on
+	  programmable logic (FPGA). The driver probes the hardware for
+	  its capabilities, and creates device files accordingly.
+
+	  If unsure, say N.
+
+if XILLYBUS
+
+config XILLYBUS_PCIE
+	tristate "Xillybus over PCIe"
+	depends on PCI_MSI
+	help
+	  Set to M if you want Xillybus to use PCI Express for communicating
+	  with the FPGA.
+
+config XILLYBUS_OF
+	tristate "Xillybus over Device Tree"
+	depends on OF_ADDRESS && OF_IRQ
+	help
+	  Set to M if you want Xillybus to find its resources from the
+	  Open Firmware Flattened Device Tree. If the target is an embedded
+	  system, say M.
+
+endif # if XILLYBUS
diff --git a/drivers/char/xillybus/Makefile b/drivers/char/xillybus/Makefile
new file mode 100644
index 000000000000..b68b7ebfd381
--- /dev/null
+++ b/drivers/char/xillybus/Makefile
@@ -0,0 +1,7 @@
+#
+# Makefile for Xillybus driver
+#
+
+obj-$(CONFIG_XILLYBUS)		+= xillybus_core.o
+obj-$(CONFIG_XILLYBUS_PCIE)	+= xillybus_pcie.o
+obj-$(CONFIG_XILLYBUS_OF)	+= xillybus_of.o
diff --git a/drivers/char/xillybus/xillybus.h b/drivers/char/xillybus/xillybus.h
new file mode 100644
index 000000000000..b9a9eb6d4f72
--- /dev/null
+++ b/drivers/char/xillybus/xillybus.h
@@ -0,0 +1,160 @@
+/*
+ * linux/drivers/misc/xillybus.h
+ *
+ * Copyright 2011 Xillybus Ltd, http://xillybus.com
+ *
+ * Header file for the Xillybus FPGA/host framework.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the smems of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ */
+
+#ifndef __XILLYBUS_H
+#define __XILLYBUS_H
+
+#include <linux/list.h>
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/interrupt.h>
+#include <linux/sched.h>
+#include <linux/cdev.h>
+#include <linux/spinlock.h>
+#include <linux/mutex.h>
+#include <linux/workqueue.h>
+
+struct xilly_endpoint_hardware;
+
+struct xilly_buffer {
+	void *addr;
+	dma_addr_t dma_addr;
+	int end_offset; /* Counting elements, not bytes */
+};
+
+struct xilly_idt_handle {
+	unsigned char *chandesc;
+	unsigned char *idt;
+	int entries;
+};
+
+/*
+ * Read-write confusion: wr_* and rd_* notation sticks to FPGA view, so
+ * wr_* buffers are those consumed by read(), since the FPGA writes to them
+ * and vice versa.
+ */
+
+struct xilly_channel {
+	struct xilly_endpoint *endpoint;
+	int chan_num;
+	int log2_element_size;
+	int seekable;
+
+	struct xilly_buffer **wr_buffers; /* FPGA writes, driver reads! */
+	int num_wr_buffers;
+	unsigned int wr_buf_size; /* In bytes */
+	int wr_fpga_buf_idx;
+	int wr_host_buf_idx;
+	int wr_host_buf_pos;
+	int wr_empty;
+	int wr_ready; /* Significant only when wr_empty == 1 */
+	int wr_sleepy;
+	int wr_eof;
+	int wr_hangup;
+	spinlock_t wr_spinlock;
+	struct mutex wr_mutex;
+	wait_queue_head_t wr_wait;
+	wait_queue_head_t wr_ready_wait;
+	int wr_ref_count;
+	int wr_synchronous;
+	int wr_allow_partial;
+	int wr_exclusive_open;
+	int wr_supports_nonempty;
+
+	struct xilly_buffer **rd_buffers; /* FPGA reads, driver writes! */
+	int num_rd_buffers;
+	unsigned int rd_buf_size; /* In bytes */
+	int rd_fpga_buf_idx;
+	int rd_host_buf_pos;
+	int rd_host_buf_idx;
+	int rd_full;
+	spinlock_t rd_spinlock;
+	struct mutex rd_mutex;
+	wait_queue_head_t rd_wait;
+	int rd_ref_count;
+	int rd_allow_partial;
+	int rd_synchronous;
+	int rd_exclusive_open;
+	struct delayed_work rd_workitem;
+	unsigned char rd_leftovers[4];
+};
+
+struct xilly_endpoint {
+	/*
+	 * One of pdev and dev is always NULL, and the other is a valid
+	 * pointer, depending on the type of device
+	 */
+	struct pci_dev *pdev;
+	struct device *dev;
+	struct xilly_endpoint_hardware *ephw;
+
+	struct list_head ep_list;
+	int dma_using_dac; /* =1 if 64-bit DMA is used, =0 otherwise. */
+	__iomem void *registers;
+	int fatal_error;
+
+	struct mutex register_mutex;
+	wait_queue_head_t ep_wait;
+
+	/* Channels and message handling */
+	struct cdev cdev;
+
+	int major;
+	int lowest_minor; /* Highest minor = lowest_minor + num_channels - 1 */
+
+	int num_channels; /* EXCLUDING message buffer */
+	struct xilly_channel **channels;
+	int msg_counter;
+	int failed_messages;
+	int idtlen;
+
+	u32 *msgbuf_addr;
+	dma_addr_t msgbuf_dma_addr;
+	unsigned int msg_buf_size;
+};
+
+struct xilly_endpoint_hardware {
+	struct module *owner;
+	void (*hw_sync_sgl_for_cpu)(struct xilly_endpoint *,
+				    dma_addr_t,
+				    size_t,
+				    int);
+	void (*hw_sync_sgl_for_device)(struct xilly_endpoint *,
+				       dma_addr_t,
+				       size_t,
+				       int);
+	int (*map_single)(struct xilly_endpoint *,
+			  void *,
+			  size_t,
+			  int,
+			  dma_addr_t *);
+};
+
+struct xilly_mapping {
+	void *device;
+	dma_addr_t dma_addr;
+	size_t size;
+	int direction;
+};
+
+irqreturn_t xillybus_isr(int irq, void *data);
+
+struct xilly_endpoint *xillybus_init_endpoint(struct pci_dev *pdev,
+					      struct device *dev,
+					      struct xilly_endpoint_hardware
+					      *ephw);
+
+int xillybus_endpoint_discovery(struct xilly_endpoint *endpoint);
+
+void xillybus_endpoint_remove(struct xilly_endpoint *endpoint);
+
+#endif /* __XILLYBUS_H */
diff --git a/drivers/char/xillybus/xillybus_core.c b/drivers/char/xillybus/xillybus_core.c
new file mode 100644
index 000000000000..b827fa095f1b
--- /dev/null
+++ b/drivers/char/xillybus/xillybus_core.c
@@ -0,0 +1,2103 @@
+/*
+ * linux/drivers/misc/xillybus_core.c
+ *
+ * Copyright 2011 Xillybus Ltd, http://xillybus.com
+ *
+ * Driver for the Xillybus FPGA/host framework.
+ *
+ * This driver interfaces with a special IP core in an FPGA, setting up
+ * a pipe between a hardware FIFO in the programmable logic and a device
+ * file in the host. The number of such pipes and their attributes are
+ * set up on the logic. This driver detects these automatically and
+ * creates the device files accordingly.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the smems of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ */
+
+#include <linux/list.h>
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/io.h>
+#include <linux/dma-mapping.h>
+#include <linux/interrupt.h>
+#include <linux/sched.h>
+#include <linux/fs.h>
+#include <linux/cdev.h>
+#include <linux/spinlock.h>
+#include <linux/mutex.h>
+#include <linux/crc32.h>
+#include <linux/poll.h>
+#include <linux/delay.h>
+#include <linux/slab.h>
+#include <linux/workqueue.h>
+#include "xillybus.h"
+
+MODULE_DESCRIPTION("Xillybus core functions");
+MODULE_AUTHOR("Eli Billauer, Xillybus Ltd.");
+MODULE_VERSION("1.07");
+MODULE_ALIAS("xillybus_core");
+MODULE_LICENSE("GPL v2");
+
+/* General timeout is 100 ms, rx timeout is 10 ms */
+#define XILLY_RX_TIMEOUT (10*HZ/1000)
+#define XILLY_TIMEOUT (100*HZ/1000)
+
+#define fpga_msg_ctrl_reg              0x0008
+#define fpga_dma_control_reg           0x0020
+#define fpga_dma_bufno_reg             0x0024
+#define fpga_dma_bufaddr_lowaddr_reg   0x0028
+#define fpga_dma_bufaddr_highaddr_reg  0x002c
+#define fpga_buf_ctrl_reg              0x0030
+#define fpga_buf_offset_reg            0x0034
+#define fpga_endian_reg                0x0040
+
+#define XILLYMSG_OPCODE_RELEASEBUF 1
+#define XILLYMSG_OPCODE_QUIESCEACK 2
+#define XILLYMSG_OPCODE_FIFOEOF 3
+#define XILLYMSG_OPCODE_FATAL_ERROR 4
+#define XILLYMSG_OPCODE_NONEMPTY 5
+
+static const char xillyname[] = "xillybus";
+
+static struct class *xillybus_class;
+
+/*
+ * ep_list_lock is the last lock to be taken; No other lock requests are
+ * allowed while holding it. It merely protects list_of_endpoints, and not
+ * the endpoints listed in it.
+ */
+
+static LIST_HEAD(list_of_endpoints);
+static struct mutex ep_list_lock;
+static struct workqueue_struct *xillybus_wq;
+
+/*
+ * Locking scheme: Mutexes protect invocations of character device methods.
+ * If both locks are taken, wr_mutex is taken first, rd_mutex second.
+ *
+ * wr_spinlock protects wr_*_buf_idx, wr_empty, wr_sleepy, wr_ready and the
+ * buffers' end_offset fields against changes made by IRQ handler (and in
+ * theory, other file request handlers, but the mutex handles that). Nothing
+ * else.
+ * They are held for short direct memory manipulations. Needless to say,
+ * no mutex locking is allowed when a spinlock is held.
+ *
+ * rd_spinlock does the same with rd_*_buf_idx, rd_empty and end_offset.
+ *
+ * register_mutex is endpoint-specific, and is held when non-atomic
+ * register operations are performed. wr_mutex and rd_mutex may be
+ * held when register_mutex is taken, but none of the spinlocks. Note that
+ * register_mutex doesn't protect against sporadic buf_ctrl_reg writes
+ * which are unrelated to buf_offset_reg, since they are harmless.
+ *
+ * Blocking on the wait queues is allowed with mutexes held, but not with
+ * spinlocks.
+ *
+ * Only interruptible blocking is allowed on mutexes and wait queues.
+ *
+ * All in all, the locking order goes (with skips allowed, of course):
+ * wr_mutex -> rd_mutex -> register_mutex -> wr_spinlock -> rd_spinlock
+ */
+
+static void malformed_message(struct xilly_endpoint *endpoint, u32 *buf)
+{
+	int opcode;
+	int msg_channel, msg_bufno, msg_data, msg_dir;
+
+	opcode = (buf[0] >> 24) & 0xff;
+	msg_dir = buf[0] & 1;
+	msg_channel = (buf[0] >> 1) & 0x7ff;
+	msg_bufno = (buf[0] >> 12) & 0x3ff;
+	msg_data = buf[1] & 0xfffffff;
+
+	dev_warn(endpoint->dev,
+		 "Malformed message (skipping): opcode=%d, channel=%03x, dir=%d, bufno=%03x, data=%07x\n",
+		 opcode, msg_channel, msg_dir, msg_bufno, msg_data);
+}
+
+/*
+ * xillybus_isr assumes the interrupt is allocated exclusively to it,
+ * which is the natural case MSI and several other hardware-oriented
+ * interrupts. Sharing is not allowed.
+ */
+
+irqreturn_t xillybus_isr(int irq, void *data)
+{
+	struct xilly_endpoint *ep = data;
+	u32 *buf;
+	unsigned int buf_size;
+	int i;
+	int opcode;
+	unsigned int msg_channel, msg_bufno, msg_data, msg_dir;
+	struct xilly_channel *channel;
+
+	buf = ep->msgbuf_addr;
+	buf_size = ep->msg_buf_size/sizeof(u32);
+
+	ep->ephw->hw_sync_sgl_for_cpu(ep,
+				      ep->msgbuf_dma_addr,
+				      ep->msg_buf_size,
+				      DMA_FROM_DEVICE);
+
+	for (i = 0; i < buf_size; i += 2) {
+		if (((buf[i+1] >> 28) & 0xf) != ep->msg_counter) {
+			malformed_message(ep, &buf[i]);
+			dev_warn(ep->dev,
+				 "Sending a NACK on counter %x (instead of %x) on entry %d\n",
+				 ((buf[i+1] >> 28) & 0xf),
+				 ep->msg_counter,
+				 i/2);
+
+			if (++ep->failed_messages > 10) {
+				dev_err(ep->dev,
+					"Lost sync with interrupt messages. Stopping.\n");
+			} else {
+				ep->ephw->hw_sync_sgl_for_device(
+					ep,
+					ep->msgbuf_dma_addr,
+					ep->msg_buf_size,
+					DMA_FROM_DEVICE);
+
+				iowrite32(0x01,  /* Message NACK */
+					  ep->registers + fpga_msg_ctrl_reg);
+			}
+			return IRQ_HANDLED;
+		} else if (buf[i] & (1 << 22)) /* Last message */
+			break;
+	}
+
+	if (i >= buf_size) {
+		dev_err(ep->dev, "Bad interrupt message. Stopping.\n");
+		return IRQ_HANDLED;
+	}
+
+	buf_size = i + 2;
+
+	for (i = 0; i < buf_size; i += 2) { /* Scan through messages */
+		opcode = (buf[i] >> 24) & 0xff;
+
+		msg_dir = buf[i] & 1;
+		msg_channel = (buf[i] >> 1) & 0x7ff;
+		msg_bufno = (buf[i] >> 12) & 0x3ff;
+		msg_data = buf[i+1] & 0xfffffff;
+
+		switch (opcode) {
+		case XILLYMSG_OPCODE_RELEASEBUF:
+			if ((msg_channel > ep->num_channels) ||
+			    (msg_channel == 0)) {
+				malformed_message(ep, &buf[i]);
+				break;
+			}
+
+			channel = ep->channels[msg_channel];
+
+			if (msg_dir) { /* Write channel */
+				if (msg_bufno >= channel->num_wr_buffers) {
+					malformed_message(ep, &buf[i]);
+					break;
+				}
+				spin_lock(&channel->wr_spinlock);
+				channel->wr_buffers[msg_bufno]->end_offset =
+					msg_data;
+				channel->wr_fpga_buf_idx = msg_bufno;
+				channel->wr_empty = 0;
+				channel->wr_sleepy = 0;
+				spin_unlock(&channel->wr_spinlock);
+
+				wake_up_interruptible(&channel->wr_wait);
+
+			} else {
+				/* Read channel */
+
+				if (msg_bufno >= channel->num_rd_buffers) {
+					malformed_message(ep, &buf[i]);
+					break;
+				}
+
+				spin_lock(&channel->rd_spinlock);
+				channel->rd_fpga_buf_idx = msg_bufno;
+				channel->rd_full = 0;
+				spin_unlock(&channel->rd_spinlock);
+
+				wake_up_interruptible(&channel->rd_wait);
+				if (!channel->rd_synchronous)
+					queue_delayed_work(
+						xillybus_wq,
+						&channel->rd_workitem,
+						XILLY_RX_TIMEOUT);
+			}
+
+			break;
+		case XILLYMSG_OPCODE_NONEMPTY:
+			if ((msg_channel > ep->num_channels) ||
+			    (msg_channel == 0) || (!msg_dir) ||
+			    !ep->channels[msg_channel]->wr_supports_nonempty) {
+				malformed_message(ep, &buf[i]);
+				break;
+			}
+
+			channel = ep->channels[msg_channel];
+
+			if (msg_bufno >= channel->num_wr_buffers) {
+				malformed_message(ep, &buf[i]);
+				break;
+			}
+			spin_lock(&channel->wr_spinlock);
+			if (msg_bufno == channel->wr_host_buf_idx)
+				channel->wr_ready = 1;
+			spin_unlock(&channel->wr_spinlock);
+
+			wake_up_interruptible(&channel->wr_ready_wait);
+
+			break;
+		case XILLYMSG_OPCODE_QUIESCEACK:
+			ep->idtlen = msg_data;
+			wake_up_interruptible(&ep->ep_wait);
+
+			break;
+		case XILLYMSG_OPCODE_FIFOEOF:
+			if ((msg_channel > ep->num_channels) ||
+			    (msg_channel == 0) || (!msg_dir) ||
+			    !ep->channels[msg_channel]->num_wr_buffers) {
+				malformed_message(ep, &buf[i]);
+				break;
+			}
+			channel = ep->channels[msg_channel];
+			spin_lock(&channel->wr_spinlock);
+			channel->wr_eof = msg_bufno;
+			channel->wr_sleepy = 0;
+
+			channel->wr_hangup = channel->wr_empty &&
+				(channel->wr_host_buf_idx == msg_bufno);
+
+			spin_unlock(&channel->wr_spinlock);
+
+			wake_up_interruptible(&channel->wr_wait);
+
+			break;
+		case XILLYMSG_OPCODE_FATAL_ERROR:
+			ep->fatal_error = 1;
+			wake_up_interruptible(&ep->ep_wait); /* For select() */
+			dev_err(ep->dev,
+				"FPGA reported a fatal error. This means that the low-level communication with the device has failed. This hardware problem is most likely unrelated to Xillybus (neither kernel module nor FPGA core), but reports are still welcome. All I/O is aborted.\n");
+			break;
+		default:
+			malformed_message(ep, &buf[i]);
+			break;
+		}
+	}
+
+	ep->ephw->hw_sync_sgl_for_device(ep,
+					 ep->msgbuf_dma_addr,
+					 ep->msg_buf_size,
+					 DMA_FROM_DEVICE);
+
+	ep->msg_counter = (ep->msg_counter + 1) & 0xf;
+	ep->failed_messages = 0;
+	iowrite32(0x03, ep->registers + fpga_msg_ctrl_reg); /* Message ACK */
+
+	return IRQ_HANDLED;
+}
+EXPORT_SYMBOL(xillybus_isr);
+
+/*
+ * A few trivial memory management functions.
+ * NOTE: These functions are used only on probe and remove, and therefore
+ * no locks are applied!
+ */
+
+static void xillybus_autoflush(struct work_struct *work);
+
+struct xilly_alloc_state {
+	void *salami;
+	int left_of_salami;
+	int nbuffer;
+	enum dma_data_direction direction;
+	u32 regdirection;
+};
+
+static int xilly_get_dma_buffers(struct xilly_endpoint *ep,
+				 struct xilly_alloc_state *s,
+				 struct xilly_buffer **buffers,
+				 int bufnum, int bytebufsize)
+{
+	int i, rc;
+	dma_addr_t dma_addr;
+	struct device *dev = ep->dev;
+	struct xilly_buffer *this_buffer = NULL; /* Init to silence warning */
+
+	if (buffers) { /* Not the message buffer */
+		this_buffer = devm_kcalloc(dev, bufnum,
+					   sizeof(struct xilly_buffer),
+					   GFP_KERNEL);
+		if (!this_buffer)
+			return -ENOMEM;
+	}
+
+	for (i = 0; i < bufnum; i++) {
+		/*
+		 * Buffers are expected in descending size order, so there
+		 * is either enough space for this buffer or none at all.
+		 */
+
+		if ((s->left_of_salami < bytebufsize) &&
+		    (s->left_of_salami > 0)) {
+			dev_err(ep->dev,
+				"Corrupt buffer allocation in IDT. Aborting.\n");
+			return -ENODEV;
+		}
+
+		if (s->left_of_salami == 0) {
+			int allocorder, allocsize;
+
+			allocsize = PAGE_SIZE;
+			allocorder = 0;
+			while (bytebufsize > allocsize) {
+				allocsize *= 2;
+				allocorder++;
+			}
+
+			s->salami = (void *) devm_get_free_pages(
+				dev,
+				GFP_KERNEL | __GFP_DMA32 | __GFP_ZERO,
+				allocorder);
+			if (!s->salami)
+				return -ENOMEM;
+
+			s->left_of_salami = allocsize;
+		}
+
+		rc = ep->ephw->map_single(ep, s->salami,
+					  bytebufsize, s->direction,
+					  &dma_addr);
+		if (rc)
+			return rc;
+
+		iowrite32((u32) (dma_addr & 0xffffffff),
+			  ep->registers + fpga_dma_bufaddr_lowaddr_reg);
+		iowrite32(((u32) ((((u64) dma_addr) >> 32) & 0xffffffff)),
+			  ep->registers + fpga_dma_bufaddr_highaddr_reg);
+
+		if (buffers) { /* Not the message buffer */
+			this_buffer->addr = s->salami;
+			this_buffer->dma_addr = dma_addr;
+			buffers[i] = this_buffer++;
+
+			iowrite32(s->regdirection | s->nbuffer++,
+				  ep->registers + fpga_dma_bufno_reg);
+		} else {
+			ep->msgbuf_addr = s->salami;
+			ep->msgbuf_dma_addr = dma_addr;
+			ep->msg_buf_size = bytebufsize;
+
+			iowrite32(s->regdirection,
+				  ep->registers + fpga_dma_bufno_reg);
+		}
+
+		s->left_of_salami -= bytebufsize;
+		s->salami += bytebufsize;
+	}
+	return 0;
+}
+
+static int xilly_setupchannels(struct xilly_endpoint *ep,
+			       unsigned char *chandesc,
+			       int entries)
+{
+	struct device *dev = ep->dev;
+	int i, entry, rc;
+	struct xilly_channel *channel;
+	int channelnum, bufnum, bufsize, format, is_writebuf;
+	int bytebufsize;
+	int synchronous, allowpartial, exclusive_open, seekable;
+	int supports_nonempty;
+	int msg_buf_done = 0;
+
+	struct xilly_alloc_state rd_alloc = {
+		.salami = NULL,
+		.left_of_salami = 0,
+		.nbuffer = 1,
+		.direction = DMA_TO_DEVICE,
+		.regdirection = 0,
+	};
+
+	struct xilly_alloc_state wr_alloc = {
+		.salami = NULL,
+		.left_of_salami = 0,
+		.nbuffer = 1,
+		.direction = DMA_FROM_DEVICE,
+		.regdirection = 0x80000000,
+	};
+
+	channel = devm_kcalloc(dev, ep->num_channels,
+			       sizeof(struct xilly_channel), GFP_KERNEL);
+	if (!channel)
+		return -ENOMEM;
+
+	ep->channels = devm_kcalloc(dev, ep->num_channels + 1,
+				    sizeof(struct xilly_channel *),
+				    GFP_KERNEL);
+	if (!ep->channels)
+		return -ENOMEM;
+
+	ep->channels[0] = NULL; /* Channel 0 is message buf. */
+
+	/* Initialize all channels with defaults */
+
+	for (i = 1; i <= ep->num_channels; i++) {
+		channel->wr_buffers = NULL;
+		channel->rd_buffers = NULL;
+		channel->num_wr_buffers = 0;
+		channel->num_rd_buffers = 0;
+		channel->wr_fpga_buf_idx = -1;
+		channel->wr_host_buf_idx = 0;
+		channel->wr_host_buf_pos = 0;
+		channel->wr_empty = 1;
+		channel->wr_ready = 0;
+		channel->wr_sleepy = 1;
+		channel->rd_fpga_buf_idx = 0;
+		channel->rd_host_buf_idx = 0;
+		channel->rd_host_buf_pos = 0;
+		channel->rd_full = 0;
+		channel->wr_ref_count = 0;
+		channel->rd_ref_count = 0;
+
+		spin_lock_init(&channel->wr_spinlock);
+		spin_lock_init(&channel->rd_spinlock);
+		mutex_init(&channel->wr_mutex);
+		mutex_init(&channel->rd_mutex);
+		init_waitqueue_head(&channel->rd_wait);
+		init_waitqueue_head(&channel->wr_wait);
+		init_waitqueue_head(&channel->wr_ready_wait);
+
+		INIT_DELAYED_WORK(&channel->rd_workitem, xillybus_autoflush);
+
+		channel->endpoint = ep;
+		channel->chan_num = i;
+
+		channel->log2_element_size = 0;
+
+		ep->channels[i] = channel++;
+	}
+
+	for (entry = 0; entry < entries; entry++, chandesc += 4) {
+		struct xilly_buffer **buffers = NULL;
+
+		is_writebuf = chandesc[0] & 0x01;
+		channelnum = (chandesc[0] >> 1) | ((chandesc[1] & 0x0f) << 7);
+		format = (chandesc[1] >> 4) & 0x03;
+		allowpartial = (chandesc[1] >> 6) & 0x01;
+		synchronous = (chandesc[1] >> 7) & 0x01;
+		bufsize = 1 << (chandesc[2] & 0x1f);
+		bufnum = 1 << (chandesc[3] & 0x0f);
+		exclusive_open = (chandesc[2] >> 7) & 0x01;
+		seekable = (chandesc[2] >> 6) & 0x01;
+		supports_nonempty = (chandesc[2] >> 5) & 0x01;
+
+		if ((channelnum > ep->num_channels) ||
+		    ((channelnum == 0) && !is_writebuf)) {
+			dev_err(ep->dev,
+				"IDT requests channel out of range. Aborting.\n");
+			return -ENODEV;
+		}
+
+		channel = ep->channels[channelnum]; /* NULL for msg channel */
+
+		if (!is_writebuf || channelnum > 0) {
+			channel->log2_element_size = ((format > 2) ?
+						      2 : format);
+
+			bytebufsize = channel->rd_buf_size = bufsize *
+				(1 << channel->log2_element_size);
+
+			buffers = devm_kcalloc(dev, bufnum,
+					       sizeof(struct xilly_buffer *),
+					       GFP_KERNEL);
+			if (!buffers)
+				return -ENOMEM;
+		} else {
+			bytebufsize = bufsize << 2;
+		}
+
+		if (!is_writebuf) {
+			channel->num_rd_buffers = bufnum;
+			channel->rd_allow_partial = allowpartial;
+			channel->rd_synchronous = synchronous;
+			channel->rd_exclusive_open = exclusive_open;
+			channel->seekable = seekable;
+
+			channel->rd_buffers = buffers;
+			rc = xilly_get_dma_buffers(ep, &rd_alloc, buffers,
+						   bufnum, bytebufsize);
+		} else if (channelnum > 0) {
+			channel->num_wr_buffers = bufnum;
+
+			channel->seekable = seekable;
+			channel->wr_supports_nonempty = supports_nonempty;
+
+			channel->wr_allow_partial = allowpartial;
+			channel->wr_synchronous = synchronous;
+			channel->wr_exclusive_open = exclusive_open;
+
+			channel->wr_buffers = buffers;
+			rc = xilly_get_dma_buffers(ep, &wr_alloc, buffers,
+						   bufnum, bytebufsize);
+		} else {
+			rc = xilly_get_dma_buffers(ep, &wr_alloc, NULL,
+						   bufnum, bytebufsize);
+			msg_buf_done++;
+		}
+
+		if (rc)
+			return -ENOMEM;
+	}
+
+	if (!msg_buf_done) {
+		dev_err(ep->dev,
+			"Corrupt IDT: No message buffer. Aborting.\n");
+		return -ENODEV;
+	}
+	return 0;
+}
+
+static int xilly_scan_idt(struct xilly_endpoint *endpoint,
+			  struct xilly_idt_handle *idt_handle)
+{
+	int count = 0;
+	unsigned char *idt = endpoint->channels[1]->wr_buffers[0]->addr;
+	unsigned char *end_of_idt = idt + endpoint->idtlen - 4;
+	unsigned char *scan;
+	int len;
+
+	scan = idt;
+	idt_handle->idt = idt;
+
+	scan++; /* Skip version number */
+
+	while ((scan <= end_of_idt) && *scan) {
+		while ((scan <= end_of_idt) && *scan++)
+			/* Do nothing, just scan thru string */;
+		count++;
+	}
+
+	scan++;
+
+	if (scan > end_of_idt) {
+		dev_err(endpoint->dev,
+			"IDT device name list overflow. Aborting.\n");
+		return -ENODEV;
+	}
+	idt_handle->chandesc = scan;
+
+	len = endpoint->idtlen - (3 + ((int) (scan - idt)));
+
+	if (len & 0x03) {
+		dev_err(endpoint->dev,
+			"Corrupt IDT device name list. Aborting.\n");
+		return -ENODEV;
+	}
+
+	idt_handle->entries = len >> 2;
+	endpoint->num_channels = count;
+
+	return 0;
+}
+
+static int xilly_obtain_idt(struct xilly_endpoint *endpoint)
+{
+	struct xilly_channel *channel;
+	unsigned char *version;
+	long t;
+
+	channel = endpoint->channels[1]; /* This should be generated ad-hoc */
+
+	channel->wr_sleepy = 1;
+
+	iowrite32(1 |
+		  (3 << 24), /* Opcode 3 for channel 0 = Send IDT */
+		  endpoint->registers + fpga_buf_ctrl_reg);
+
+	t = wait_event_interruptible_timeout(channel->wr_wait,
+					     (!channel->wr_sleepy),
+					     XILLY_TIMEOUT);
+
+	if (t <= 0) {
+		dev_err(endpoint->dev, "Failed to obtain IDT. Aborting.\n");
+
+		if (endpoint->fatal_error)
+			return -EIO;
+
+		return -ENODEV;
+	}
+
+	endpoint->ephw->hw_sync_sgl_for_cpu(
+		channel->endpoint,
+		channel->wr_buffers[0]->dma_addr,
+		channel->wr_buf_size,
+		DMA_FROM_DEVICE);
+
+	if (channel->wr_buffers[0]->end_offset != endpoint->idtlen) {
+		dev_err(endpoint->dev,
+			"IDT length mismatch (%d != %d). Aborting.\n",
+			channel->wr_buffers[0]->end_offset, endpoint->idtlen);
+		return -ENODEV;
+	}
+
+	if (crc32_le(~0, channel->wr_buffers[0]->addr,
+		     endpoint->idtlen+1) != 0) {
+		dev_err(endpoint->dev, "IDT failed CRC check. Aborting.\n");
+		return -ENODEV;
+	}
+
+	version = channel->wr_buffers[0]->addr;
+
+	/* Check version number. Accept anything below 0x82 for now. */
+	if (*version > 0x82) {
+		dev_err(endpoint->dev,
+			"No support for IDT version 0x%02x. Maybe the xillybus driver needs an upgarde. Aborting.\n",
+			*version);
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static ssize_t xillybus_read(struct file *filp, char __user *userbuf,
+			     size_t count, loff_t *f_pos)
+{
+	ssize_t rc;
+	unsigned long flags;
+	int bytes_done = 0;
+	int no_time_left = 0;
+	long deadline, left_to_sleep;
+	struct xilly_channel *channel = filp->private_data;
+
+	int empty, reached_eof, exhausted, ready;
+	/* Initializations are there only to silence warnings */
+
+	int howmany = 0, bufpos = 0, bufidx = 0, bufferdone = 0;
+	int waiting_bufidx;
+
+	if (channel->endpoint->fatal_error)
+		return -EIO;
+
+	deadline = jiffies + 1 + XILLY_RX_TIMEOUT;
+
+	rc = mutex_lock_interruptible(&channel->wr_mutex);
+	if (rc)
+		return rc;
+
+	while (1) { /* Note that we may drop mutex within this loop */
+		int bytes_to_do = count - bytes_done;
+
+		spin_lock_irqsave(&channel->wr_spinlock, flags);
+
+		empty = channel->wr_empty;
+		ready = !empty || channel->wr_ready;
+
+		if (!empty) {
+			bufidx = channel->wr_host_buf_idx;
+			bufpos = channel->wr_host_buf_pos;
+			howmany = ((channel->wr_buffers[bufidx]->end_offset
+				    + 1) << channel->log2_element_size)
+				- bufpos;
+
+			/* Update wr_host_* to its post-operation state */
+			if (howmany > bytes_to_do) {
+				bufferdone = 0;
+
+				howmany = bytes_to_do;
+				channel->wr_host_buf_pos += howmany;
+			} else {
+				bufferdone = 1;
+
+				channel->wr_host_buf_pos = 0;
+
+				if (bufidx == channel->wr_fpga_buf_idx) {
+					channel->wr_empty = 1;
+					channel->wr_sleepy = 1;
+					channel->wr_ready = 0;
+				}
+
+				if (bufidx >= (channel->num_wr_buffers - 1))
+					channel->wr_host_buf_idx = 0;
+				else
+					channel->wr_host_buf_idx++;
+			}
+		}
+
+		/*
+		 * Marking our situation after the possible changes above,
+		 * for use after releasing the spinlock.
+		 *
+		 * empty = empty before change
+		 * exhasted = empty after possible change
+		 */
+
+		reached_eof = channel->wr_empty &&
+			(channel->wr_host_buf_idx == channel->wr_eof);
+		channel->wr_hangup = reached_eof;
+		exhausted = channel->wr_empty;
+		waiting_bufidx = channel->wr_host_buf_idx;
+
+		spin_unlock_irqrestore(&channel->wr_spinlock, flags);
+
+		if (!empty) { /* Go on, now without the spinlock */
+
+			if (bufpos == 0) /* Position zero means it's virgin */
+				channel->endpoint->ephw->hw_sync_sgl_for_cpu(
+					channel->endpoint,
+					channel->wr_buffers[bufidx]->dma_addr,
+					channel->wr_buf_size,
+					DMA_FROM_DEVICE);
+
+			if (copy_to_user(
+				    userbuf,
+				    channel->wr_buffers[bufidx]->addr
+				    + bufpos, howmany))
+				rc = -EFAULT;
+
+			userbuf += howmany;
+			bytes_done += howmany;
+
+			if (bufferdone) {
+				channel->endpoint->ephw->hw_sync_sgl_for_device(
+					channel->endpoint,
+					channel->wr_buffers[bufidx]->dma_addr,
+					channel->wr_buf_size,
+					DMA_FROM_DEVICE);
+
+				/*
+				 * Tell FPGA the buffer is done with. It's an
+				 * atomic operation to the FPGA, so what
+				 * happens with other channels doesn't matter,
+				 * and the certain channel is protected with
+				 * the channel-specific mutex.
+				 */
+
+				iowrite32(1 | (channel->chan_num << 1) |
+					  (bufidx << 12),
+					  channel->endpoint->registers +
+					  fpga_buf_ctrl_reg);
+			}
+
+			if (rc) {
+				mutex_unlock(&channel->wr_mutex);
+				return rc;
+			}
+		}
+
+		/* This includes a zero-count return = EOF */
+		if ((bytes_done >= count) || reached_eof)
+			break;
+
+		if (!exhausted)
+			continue; /* More in RAM buffer(s)? Just go on. */
+
+		if ((bytes_done > 0) &&
+		    (no_time_left ||
+		     (channel->wr_synchronous && channel->wr_allow_partial)))
+			break;
+
+		/*
+		 * Nonblocking read: The "ready" flag tells us that the FPGA
+		 * has data to send. In non-blocking mode, if it isn't on,
+		 * just return. But if there is, we jump directly to the point
+		 * where we ask for the FPGA to send all it has, and wait
+		 * until that data arrives. So in a sense, we *do* block in
+		 * nonblocking mode, but only for a very short time.
+		 */
+
+		if (!no_time_left && (filp->f_flags & O_NONBLOCK)) {
+			if (bytes_done > 0)
+				break;
+
+			if (ready)
+				goto desperate;
+
+			rc = -EAGAIN;
+			break;
+		}
+
+		if (!no_time_left || (bytes_done > 0)) {
+			/*
+			 * Note that in case of an element-misaligned read
+			 * request, offsetlimit will include the last element,
+			 * which will be partially read from.
+			 */
+			int offsetlimit = ((count - bytes_done) - 1) >>
+				channel->log2_element_size;
+			int buf_elements = channel->wr_buf_size >>
+				channel->log2_element_size;
+
+			/*
+			 * In synchronous mode, always send an offset limit.
+			 * Just don't send a value too big.
+			 */
+
+			if (channel->wr_synchronous) {
+				/* Don't request more than one buffer */
+				if (channel->wr_allow_partial &&
+				    (offsetlimit >= buf_elements))
+					offsetlimit = buf_elements - 1;
+
+				/* Don't request more than all buffers */
+				if (!channel->wr_allow_partial &&
+				    (offsetlimit >=
+				     (buf_elemen