virtio: Add platform bus driver for memory mapped virtio device

This patch, based on virtio PCI driver, adds support for memory
mapped (platform) virtio device. This should allow environments
like qemu to use virtio-based block & network devices even on
platforms without PCI support.

One can define and register a platform device which resources
will describe memory mapped control registers and "mailbox"
interrupt. Such device can be also instantiated using the Device
Tree node with compatible property equal "virtio,mmio".

Cc: Anthony Liguori <aliguori@us.ibm.com>
Cc: Michael S.Tsirkin <mst@redhat.com>
Signed-off-by: Pawel Moll <pawel.moll@arm.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>

Documentation/devicetree/bindings/virtio/mmio.txt

+* virtio memory mapped device
+
+See http://ozlabs.org/~rusty/virtio-spec/ for more details.
+
+Required properties:
+
+- compatible:	"virtio,mmio" compatibility string
+- reg:		control registers base address and size including configuration space
+- interrupts:	interrupt generated by the device
+
+Example:
+
+	virtio_block@3000 {
+		compatible = "virtio,mmio";
+		reg = <0x3000 0x100>;
+		interrupts = <41>;
+	}

drivers/virtio/Kconfig

@@ -35,4 +35,15 @@ config VIRTIO_BALLOON
 
 	 If unsure, say M.
 
+ config VIRTIO_MMIO
+ 	tristate "Platform bus driver for memory mapped virtio devices (EXPERIMENTAL)"
+ 	depends on EXPERIMENTAL
+ 	select VIRTIO
+ 	select VIRTIO_RING
+ 	---help---
+ 	 This drivers provides support for memory mapped virtio
+	 platform device driver.
+
+ 	 If unsure, say N.
+
 endmenu

drivers/virtio/Makefile

 obj-$(CONFIG_VIRTIO) += virtio.o
 obj-$(CONFIG_VIRTIO_RING) += virtio_ring.o
+obj-$(CONFIG_VIRTIO_MMIO) += virtio_mmio.o
 obj-$(CONFIG_VIRTIO_PCI) += virtio_pci.o
 obj-$(CONFIG_VIRTIO_BALLOON) += virtio_balloon.o

drivers/virtio/virtio_mmio.c

+/*
+ * Virtio memory mapped device driver
+ *
+ * Copyright 2011, ARM Ltd.
+ *
+ * This module allows virtio devices to be used over a virtual, memory mapped
+ * platform device.
+ *
+ * Registers layout (all 32-bit wide):
+ *
+ * offset d. name             description
+ * ------ -- ---------------- -----------------
+ *
+ * 0x000  R  MagicValue       Magic value "virt"
+ * 0x004  R  Version          Device version (current max. 1)
+ * 0x008  R  DeviceID         Virtio device ID
+ * 0x00c  R  VendorID         Virtio vendor ID
+ *
+ * 0x010  R  HostFeatures     Features supported by the host
+ * 0x014  W  HostFeaturesSel  Set of host features to access via HostFeatures
+ *
+ * 0x020  W  GuestFeatures    Features activated by the guest
+ * 0x024  W  GuestFeaturesSel Set of activated features to set via GuestFeatures
+ * 0x028  W  GuestPageSize    Size of guest's memory page in bytes
+ *
+ * 0x030  W  QueueSel         Queue selector
+ * 0x034  R  QueueNumMax      Maximum size of the currently selected queue
+ * 0x038  W  QueueNum         Queue size for the currently selected queue
+ * 0x03c  W  QueueAlign       Used Ring alignment for the current queue
+ * 0x040  RW QueuePFN         PFN for the currently selected queue
+ *
+ * 0x050  W  QueueNotify      Queue notifier
+ * 0x060  R  InterruptStatus  Interrupt status register
+ * 0x060  W  InterruptACK     Interrupt acknowledge register
+ * 0x070  RW Status           Device status register
+ *
+ * 0x100+ RW                  Device-specific configuration space
+ *
+ * Based on Virtio PCI driver by Anthony Liguori, copyright IBM Corp. 2007
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+
+#include <linux/highmem.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/virtio.h>
+#include <linux/virtio_config.h>
+#include <linux/virtio_mmio.h>
+#include <linux/virtio_ring.h>
+
+
+
+/* The alignment to use between consumer and producer parts of vring.
+ * Currently hardcoded to the page size. */
+#define VIRTIO_MMIO_VRING_ALIGN		PAGE_SIZE
+
+
+
+#define to_virtio_mmio_device(_plat_dev) \
+	container_of(_plat_dev, struct virtio_mmio_device, vdev)
+
+struct virtio_mmio_device {
+	struct virtio_device vdev;
+	struct platform_device *pdev;
+
+	void __iomem *base;
+	unsigned long version;
+
+	/* a list of queues so we can dispatch IRQs */
+	spinlock_t lock;
+	struct list_head virtqueues;
+};
+
+struct virtio_mmio_vq_info {
+	/* the actual virtqueue */
+	struct virtqueue *vq;
+
+	/* the number of entries in the queue */
+	unsigned int num;
+
+	/* the index of the queue */
+	int queue_index;
+
+	/* the virtual address of the ring queue */
+	void *queue;
+
+	/* the list node for the virtqueues list */
+	struct list_head node;
+};
+
+
+
+/* Configuration interface */
+
+static u32 vm_get_features(struct virtio_device *vdev)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+
+	/* TODO: Features > 32 bits */
+	writel(0, vm_dev->base + VIRTIO_MMIO_HOST_FEATURES_SEL);
+
+	return readl(vm_dev->base + VIRTIO_MMIO_HOST_FEATURES);
+}
+
+static void vm_finalize_features(struct virtio_device *vdev)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+	int i;
+
+	/* Give virtio_ring a chance to accept features. */
+	vring_transport_features(vdev);
+
+	for (i = 0; i < ARRAY_SIZE(vdev->features); i++) {
+		writel(i, vm_dev->base + VIRTIO_MMIO_GUEST_FEATURES_SET);
+		writel(vdev->features[i],
+				vm_dev->base + VIRTIO_MMIO_GUEST_FEATURES);
+	}
+}
+
+static void vm_get(struct virtio_device *vdev, unsigned offset,
+		   void *buf, unsigned len)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+	u8 *ptr = buf;
+	int i;
+
+	for (i = 0; i < len; i++)
+		ptr[i] = readb(vm_dev->base + VIRTIO_MMIO_CONFIG + offset + i);
+}
+
+static void vm_set(struct virtio_device *vdev, unsigned offset,
+		   const void *buf, unsigned len)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+	const u8 *ptr = buf;
+	int i;
+
+	for (i = 0; i < len; i++)
+		writeb(ptr[i], vm_dev->base + VIRTIO_MMIO_CONFIG + offset + i);
+}
+
+static u8 vm_get_status(struct virtio_device *vdev)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+
+	return readl(vm_dev->base + VIRTIO_MMIO_STATUS) & 0xff;
+}
+
+static void vm_set_status(struct virtio_device *vdev, u8 status)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+
+	/* We should never be setting status to 0. */
+	BUG_ON(status == 0);
+
+	writel(status, vm_dev->base + VIRTIO_MMIO_STATUS);
+}
+
+static void vm_reset(struct virtio_device *vdev)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+
+	/* 0 status means a reset. */
+	writel(0, vm_dev->base + VIRTIO_MMIO_STATUS);
+}
+
+
+
+/* Transport interface */
+
+/* the notify function used when creating a virt queue */
+static void vm_notify(struct virtqueue *vq)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vq->vdev);
+	struct virtio_mmio_vq_info *info = vq->priv;
+
+	/* We write the queue's selector into the notification register to
+	 * signal the other end */
+	writel(info->queue_index, vm_dev->base + VIRTIO_MMIO_QUEUE_NOTIFY);
+}
+
+/* Notify all virtqueues on an interrupt. */
+static irqreturn_t vm_interrupt(int irq, void *opaque)
+{
+	struct virtio_mmio_device *vm_dev = opaque;
+	struct virtio_mmio_vq_info *info;
+	struct virtio_driver *vdrv = container_of(vm_dev->vdev.dev.driver,
+			struct virtio_driver, driver);
+	unsigned long status;
+	unsigned long flags;
+	irqreturn_t ret = IRQ_NONE;
+
+	/* Read and acknowledge interrupts */
+	status = readl(vm_dev->base + VIRTIO_MMIO_INTERRUPT_STATUS);
+	writel(status, vm_dev->base + VIRTIO_MMIO_INTERRUPT_ACK);
+
+	if (unlikely(status & VIRTIO_MMIO_INT_CONFIG)
+			&& vdrv && vdrv->config_changed) {
+		vdrv->config_changed(&vm_dev->vdev);
+		ret = IRQ_HANDLED;
+	}
+
+	if (likely(status & VIRTIO_MMIO_INT_VRING)) {
+		spin_lock_irqsave(&vm_dev->lock, flags);
+		list_for_each_entry(info, &vm_dev->virtqueues, node)
+			ret |= vring_interrupt(irq, info->vq);
+		spin_unlock_irqrestore(&vm_dev->lock, flags);
+	}
+
+	return ret;
+}
+
+
+
+static void vm_del_vq(struct virtqueue *vq)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vq->vdev);
+	struct virtio_mmio_vq_info *info = vq->priv;
+	unsigned long flags, size;
+
+	spin_lock_irqsave(&vm_dev->lock, flags);
+	list_del(&info->node);
+	spin_unlock_irqrestore(&vm_dev->lock, flags);
+
+	vring_del_virtqueue(vq);
+
+	/* Select and deactivate the queue */
+	writel(info->queue_index, vm_dev->base + VIRTIO_MMIO_QUEUE_SEL);
+	writel(0, vm_dev->base + VIRTIO_MMIO_QUEUE_PFN);
+
+	size = PAGE_ALIGN(vring_size(info->num, VIRTIO_MMIO_VRING_ALIGN));
+	free_pages_exact(info->queue, size);
+	kfree(info);
+}
+
+static void vm_del_vqs(struct virtio_device *vdev)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+	struct virtqueue *vq, *n;
+
+	list_for_each_entry_safe(vq, n, &vdev->vqs, list)
+		vm_del_vq(vq);
+
+	free_irq(platform_get_irq(vm_dev->pdev, 0), vm_dev);
+}
+
+
+
+static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned index,
+				  void (*callback)(struct virtqueue *vq),
+				  const char *name)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+	struct virtio_mmio_vq_info *info;
+	struct virtqueue *vq;
+	unsigned long flags, size;
+	int err;
+
+	/* Select the queue we're interested in */
+	writel(index, vm_dev->base + VIRTIO_MMIO_QUEUE_SEL);
+
+	/* Queue shouldn't already be set up. */
+	if (readl(vm_dev->base + VIRTIO_MMIO_QUEUE_PFN)) {
+		err = -ENOENT;
+		goto error_available;
+	}
+
+	/* Allocate and fill out our active queue description */
+	info = kmalloc(sizeof(*info), GFP_KERNEL);
+	if (!info) {
+		err = -ENOMEM;
+		goto error_kmalloc;
+	}
+	info->queue_index = index;
+
+	/* Allocate pages for the queue - start with a queue as big as
+	 * possible (limited by maximum size allowed by device), drop down
+	 * to a minimal size, just big enough to fit descriptor table
+	 * and two rings (which makes it "alignment_size * 2")
+	 */
+	info->num = readl(vm_dev->base + VIRTIO_MMIO_QUEUE_NUM_MAX);
+	while (1) {
+		size = PAGE_ALIGN(vring_size(info->num,
+				VIRTIO_MMIO_VRING_ALIGN));
+		/* Already smallest possible allocation? */
+		if (size <= VIRTIO_MMIO_VRING_ALIGN * 2) {
+			err = -ENOMEM;
+			goto error_alloc_pages;
+		}
+
+		info->queue = alloc_pages_exact(size, GFP_KERNEL | __GFP_ZERO);
+		if (info->queue)
+			break;
+
+		info->num /= 2;
+	}
+
+	/* Activate the queue */
+	writel(info->num, vm_dev->base + VIRTIO_MMIO_QUEUE_NUM);
+	writel(VIRTIO_MMIO_VRING_ALIGN,
+			vm_dev->base + VIRTIO_MMIO_QUEUE_ALIGN);
+	writel(virt_to_phys(info->queue) >> PAGE_SHIFT,
+			vm_dev->base + VIRTIO_MMIO_QUEUE_PFN);
+
+	/* Create the vring */
+	vq = vring_new_virtqueue(info->num, VIRTIO_MMIO_VRING_ALIGN,
+				 vdev, info->queue, vm_notify, callback, name);
+	if (!vq) {
+		err = -ENOMEM;
+		goto error_new_virtqueue;
+	}
+
+	vq->priv = info;
+	info->vq = vq;
+
+	spin_lock_irqsave(&vm_dev->lock, flags);
+	list_add(&info->node, &vm_dev->virtqueues);
+	spin_unlock_irqrestore(&vm_dev->lock, flags);
+
+	return vq;
+
+error_new_virtqueue:
+	writel(0, vm_dev->base + VIRTIO_MMIO_QUEUE_PFN);
+	free_pages_exact(info->queue, size);
+error_alloc_pages:
+	kfree(info);
+error_kmalloc:
+error_available:
+	return ERR_PTR(err);
+}
+
+static int vm_find_vqs(struct virtio_device *vdev, unsigned nvqs,
+		       struct virtqueue *vqs[],
+		       vq_callback_t *callbacks[],
+		       const char *names[])
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+	unsigned int irq = platform_get_irq(vm_dev->pdev, 0);
+	int i, err;
+
+	err = request_irq(irq, vm_interrupt, IRQF_SHARED,
+			dev_name(&vdev->dev), vm_dev);
+	if (err)
+		return err;
+
+	for (i = 0; i < nvqs; ++i) {
+		vqs[i] = vm_setup_vq(vdev, i, callbacks[i], names[i]);
+		if (IS_ERR(vqs[i])) {
+			vm_del_vqs(vdev);
+			return PTR_ERR(vqs[i]);
+		}
+	}
+
+	return 0;
+}
+
+
+
+static struct virtio_config_ops virtio_mmio_config_ops = {
+	.get		= vm_get,
+	.set		= vm_set,
+	.get_status	= vm_get_status,
+	.set_status	= vm_set_status,
+	.reset		= vm_reset,
+	.find_vqs	= vm_find_vqs,
+	.del_vqs	= vm_del_vqs,
+	.get_features	= vm_get_features,
+	.finalize_features = vm_finalize_features,
+};
+
+
+
+/* Platform device */
+
+static int __devinit virtio_mmio_probe(struct platform_device *pdev)
+{
+	struct virtio_mmio_device *vm_dev;
+	struct resource *mem;
+	unsigned long magic;
+
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!mem)
+		return -EINVAL;
+
+	if (!devm_request_mem_region(&pdev->dev, mem->start,
+			resource_size(mem), pdev->name))
+		return -EBUSY;
+
+	vm_dev = devm_kzalloc(&pdev->dev, sizeof(*vm_dev), GFP_KERNEL);
+	if (!vm_dev)
+		return  -ENOMEM;
+
+	vm_dev->vdev.dev.parent = &pdev->dev;
+	vm_dev->vdev.config = &virtio_mmio_config_ops;
+	vm_dev->pdev = pdev;
+	INIT_LIST_HEAD(&vm_dev->virtqueues);
+	spin_lock_init(&vm_dev->lock);
+
+	vm_dev->base = devm_ioremap(&pdev->dev, mem->start, resource_size(mem));
+	if (vm_dev->base == NULL)
+		return -EFAULT;
+
+	/* Check magic value */
+	magic = readl(vm_dev->base + VIRTIO_MMIO_MAGIC_VALUE);
+	if (memcmp(&magic, "virt", 4) != 0) {
+		dev_warn(&pdev->dev, "Wrong magic value 0x%08lx!\n", magic);
+		return -ENODEV;
+	}
+
+	/* Check device version */
+	vm_dev->version = readl(vm_dev->base + VIRTIO_MMIO_VERSION);
+	if (vm_dev->version != 1) {
+		dev_err(&pdev->dev, "Version %ld not supported!\n",
+				vm_dev->version);
+		return -ENXIO;
+	}
+
+	vm_dev->vdev.id.device = readl(vm_dev->base + VIRTIO_MMIO_DEVICE_ID);
+	vm_dev->vdev.id.vendor = readl(vm_dev->base + VIRTIO_MMIO_VENDOR_ID);
+
+	writel(PAGE_SIZE, vm_dev->base + VIRTIO_MMIO_GUEST_PAGE_SIZE);
+
+	platform_set_drvdata(pdev, vm_dev);
+
+	return register_virtio_device(&vm_dev->vdev);
+}
+
+static int __devexit virtio_mmio_remove(struct platform_device *pdev)
+{
+	struct virtio_mmio_device *vm_dev = platform_get_drvdata(pdev);
+
+	unregister_virtio_device(&vm_dev->vdev);
+
+	return 0;
+}
+
+
+
+/* Platform driver */
+
+static struct of_device_id virtio_mmio_match[] = {
+	{ .compatible = "virtio,mmio", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, virtio_mmio_match);
+
+static struct platform_driver virtio_mmio_driver = {
+	.probe		= virtio_mmio_probe,
+	.remove		= __devexit_p(virtio_mmio_remove),
+	.driver		= {
+		.name	= "virtio-mmio",
+		.owner	= THIS_MODULE,
+		.of_match_table	= virtio_mmio_match,
+	},
+};
+
+static int __init virtio_mmio_init(void)
+{
+	return platform_driver_register(&virtio_mmio_driver);
+}
+
+static void __exit virtio_mmio_exit(void)
+{
+	platform_driver_unregister(&virtio_mmio_driver);
+}
+
+module_init(virtio_mmio_init);
+module_exit(virtio_mmio_exit);
+
+MODULE_AUTHOR("Pawel Moll <pawel.moll@arm.com>");
+MODULE_DESCRIPTION("Platform bus driver for memory mapped virtio devices");
+MODULE_LICENSE("GPL");

include/linux/virtio_mmio.h

+/*
+ * Virtio platform device driver
+ *
+ * Copyright 2011, ARM Ltd.
+ *
+ * Based on Virtio PCI driver by Anthony Liguori, copyright IBM Corp. 2007
+ *
+ * This header is BSD licensed so anyone can use the definitions to implement
+ * compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ */
+
+#ifndef _LINUX_VIRTIO_MMIO_H
+#define _LINUX_VIRTIO_MMIO_H
+
+/*
+ * Control registers
+ */
+
+/* Magic value ("virt" string) - Read Only */
+#define VIRTIO_MMIO_MAGIC_VALUE		0x000
+
+/* Virtio device version - Read Only */
+#define VIRTIO_MMIO_VERSION		0x004
+
+/* Virtio device ID - Read Only */
+#define VIRTIO_MMIO_DEVICE_ID		0x008
+
+/* Virtio vendor ID - Read Only */
+#define VIRTIO_MMIO_VENDOR_ID		0x00c
+
+/* Bitmask of the features supported by the host
+ * (32 bits per set) - Read Only */
+#define VIRTIO_MMIO_HOST_FEATURES	0x010
+
+/* Host features set selector - Write Only */
+#define VIRTIO_MMIO_HOST_FEATURES_SEL	0x014
+
+/* Bitmask of features activated by the guest
+ * (32 bits per set) - Write Only */
+#define VIRTIO_MMIO_GUEST_FEATURES	0x020
+
+/* Activated features set selector - Write Only */
+#define VIRTIO_MMIO_GUEST_FEATURES_SET	0x024
+
+/* Guest's memory page size in bytes - Write Only */
+#define VIRTIO_MMIO_GUEST_PAGE_SIZE	0x028
+
+/* Queue selector - Write Only */
+#define VIRTIO_MMIO_QUEUE_SEL		0x030
+
+/* Maximum size of the currently selected queue - Read Only */
+#define VIRTIO_MMIO_QUEUE_NUM_MAX	0x034
+
+/* Queue size for the currently selected queue - Write Only */
+#define VIRTIO_MMIO_QUEUE_NUM		0x038
+
+/* Used Ring alignment for the currently selected queue - Write Only */
+#define VIRTIO_MMIO_QUEUE_ALIGN		0x03c
+
+/* Guest's PFN for the currently selected queue - Read Write */
+#define VIRTIO_MMIO_QUEUE_PFN		0x040
+
+/* Queue notifier - Write Only */
+#define VIRTIO_MMIO_QUEUE_NOTIFY	0x050
+
+/* Interrupt status - Read Only */
+#define VIRTIO_MMIO_INTERRUPT_STATUS	0x060
+
+/* Interrupt acknowledge - Write Only */
+#define VIRTIO_MMIO_INTERRUPT_ACK	0x064
+
+/* Device status register - Read Write */
+#define VIRTIO_MMIO_STATUS		0x070
+
+/* The config space is defined by each driver as
+ * the per-driver configuration space - Read Write */
+#define VIRTIO_MMIO_CONFIG		0x100
+
+
+
+/*
+ * Interrupt flags (re: interrupt status & acknowledge registers)
+ */
+
+#define VIRTIO_MMIO_INT_VRING		(1 << 0)
+#define VIRTIO_MMIO_INT_CONFIG		(1 << 1)
+
+#endif