kvm: Add VFIO device

So far we've succeeded at making KVM and VFIO mostly unaware of each
other, but areas are cropping up where a connection beyond eventfds
and irqfds needs to be made.  This patch introduces a KVM-VFIO device
that is meant to be a gateway for such interaction.  The user creates
the device and can add and remove VFIO groups to it via file
descriptors.  When a group is added, KVM verifies the group is valid
and gets a reference to it via the VFIO external user interface.
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Documentation/virtual/kvm/devices/vfio.txt

+VFIO virtual device
+===================
+
+Device types supported:
+  KVM_DEV_TYPE_VFIO
+
+Only one VFIO instance may be created per VM.  The created device
+tracks VFIO groups in use by the VM and features of those groups
+important to the correctness and acceleration of the VM.  As groups
+are enabled and disabled for use by the VM, KVM should be updated
+about their presence.  When registered with KVM, a reference to the
+VFIO-group is held by KVM.
+
+Groups:
+  KVM_DEV_VFIO_GROUP
+
+KVM_DEV_VFIO_GROUP attributes:
+  KVM_DEV_VFIO_GROUP_ADD: Add a VFIO group to VFIO-KVM device tracking
+  KVM_DEV_VFIO_GROUP_DEL: Remove a VFIO group from VFIO-KVM device tracking
+
+For each, kvm_device_attr.addr points to an int32_t file descriptor
+for the VFIO group.

arch/x86/kvm/Kconfig

@@ -38,6 +38,7 @@ config KVM
 	select PERF_EVENTS
 	select HAVE_KVM_MSI
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
+	select KVM_VFIO
 	---help---
 	  Support hosting fully virtualized guest machines using hardware
 	  virtualization extensions.  You will need a fairly recent

arch/x86/kvm/Makefile

@@ -9,7 +9,7 @@ KVM := ../../../virt/kvm
 
 kvm-y			+= $(KVM)/kvm_main.o $(KVM)/ioapic.o \
 				$(KVM)/coalesced_mmio.o $(KVM)/irq_comm.o \
-				$(KVM)/eventfd.o $(KVM)/irqchip.o
+				$(KVM)/eventfd.o $(KVM)/irqchip.o $(KVM)/vfio.o
 kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT)	+= $(KVM)/assigned-dev.o $(KVM)/iommu.o
 kvm-$(CONFIG_KVM_ASYNC_PF)	+= $(KVM)/async_pf.o
 

include/linux/kvm_host.h

@@ -1058,6 +1058,7 @@ struct kvm_device *kvm_device_from_filp(struct file *filp);
 
 extern struct kvm_device_ops kvm_mpic_ops;
 extern struct kvm_device_ops kvm_xics_ops;
+extern struct kvm_device_ops kvm_vfio_ops;
 
 #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
 

include/uapi/linux/kvm.h

@@ -845,6 +845,10 @@ struct kvm_device_attr {
 #define KVM_DEV_TYPE_FSL_MPIC_20	1
 #define KVM_DEV_TYPE_FSL_MPIC_42	2
 #define KVM_DEV_TYPE_XICS		3
+#define KVM_DEV_TYPE_VFIO		4
+#define  KVM_DEV_VFIO_GROUP			1
+#define   KVM_DEV_VFIO_GROUP_ADD			1
+#define   KVM_DEV_VFIO_GROUP_DEL			2
 
 /*
  * ioctls for VM fds

virt/kvm/Kconfig

@@ -27,3 +27,6 @@ config HAVE_KVM_MSI
 
 config HAVE_KVM_CPU_RELAX_INTERCEPT
        bool
+
+config KVM_VFIO
+       bool

virt/kvm/kvm_main.c

@@ -2270,6 +2270,11 @@ static int kvm_ioctl_create_device(struct kvm *kvm,
 	case KVM_DEV_TYPE_XICS:
 		ops = &kvm_xics_ops;
 		break;
+#endif
+#ifdef CONFIG_KVM_VFIO
+	case KVM_DEV_TYPE_VFIO:
+		ops = &kvm_vfio_ops;
+		break;
 #endif
 	default:
 		return -ENODEV;

virt/kvm/vfio.c

+/*
+ * VFIO-KVM bridge pseudo device
+ *
+ * Copyright (C) 2013 Red Hat, Inc.  All rights reserved.
+ *     Author: Alex Williamson <alex.williamson@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/errno.h>
+#include <linux/file.h>
+#include <linux/kvm_host.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/vfio.h>
+
+struct kvm_vfio_group {
+	struct list_head node;
+	struct vfio_group *vfio_group;
+};
+
+struct kvm_vfio {
+	struct list_head group_list;
+	struct mutex lock;
+};
+
+static struct vfio_group *kvm_vfio_group_get_external_user(struct file *filep)
+{
+	struct vfio_group *vfio_group;
+	struct vfio_group *(*fn)(struct file *);
+
+	fn = symbol_get(vfio_group_get_external_user);
+	if (!fn)
+		return ERR_PTR(-EINVAL);
+
+	vfio_group = fn(filep);
+
+	symbol_put(vfio_group_get_external_user);
+
+	return vfio_group;
+}
+
+static void kvm_vfio_group_put_external_user(struct vfio_group *vfio_group)
+{
+	void (*fn)(struct vfio_group *);
+
+	fn = symbol_get(vfio_group_put_external_user);
+	if (!fn)
+		return;
+
+	fn(vfio_group);
+
+	symbol_put(vfio_group_put_external_user);
+}
+
+static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
+{
+	struct kvm_vfio *kv = dev->private;
+	struct vfio_group *vfio_group;
+	struct kvm_vfio_group *kvg;
+	void __user *argp = (void __user *)arg;
+	struct fd f;
+	int32_t fd;
+	int ret;
+
+	switch (attr) {
+	case KVM_DEV_VFIO_GROUP_ADD:
+		if (get_user(fd, (int32_t __user *)argp))
+			return -EFAULT;
+
+		f = fdget(fd);
+		if (!f.file)
+			return -EBADF;
+
+		vfio_group = kvm_vfio_group_get_external_user(f.file);
+		fdput(f);
+
+		if (IS_ERR(vfio_group))
+			return PTR_ERR(vfio_group);
+
+		mutex_lock(&kv->lock);
+
+		list_for_each_entry(kvg, &kv->group_list, node) {
+			if (kvg->vfio_group == vfio_group) {
+				mutex_unlock(&kv->lock);
+				kvm_vfio_group_put_external_user(vfio_group);
+				return -EEXIST;
+			}
+		}
+
+		kvg = kzalloc(sizeof(*kvg), GFP_KERNEL);
+		if (!kvg) {
+			mutex_unlock(&kv->lock);
+			kvm_vfio_group_put_external_user(vfio_group);
+			return -ENOMEM;
+		}
+
+		list_add_tail(&kvg->node, &kv->group_list);
+		kvg->vfio_group = vfio_group;
+
+		mutex_unlock(&kv->lock);
+
+		return 0;
+
+	case KVM_DEV_VFIO_GROUP_DEL:
+		if (get_user(fd, (int32_t __user *)argp))
+			return -EFAULT;
+
+		f = fdget(fd);
+		if (!f.file)
+			return -EBADF;
+
+		vfio_group = kvm_vfio_group_get_external_user(f.file);
+		fdput(f);
+
+		if (IS_ERR(vfio_group))
+			return PTR_ERR(vfio_group);
+
+		ret = -ENOENT;
+
+		mutex_lock(&kv->lock);
+
+		list_for_each_entry(kvg, &kv->group_list, node) {
+			if (kvg->vfio_group != vfio_group)
+				continue;
+
+			list_del(&kvg->node);
+			kvm_vfio_group_put_external_user(kvg->vfio_group);
+			kfree(kvg);
+			ret = 0;
+			break;
+		}
+
+		mutex_unlock(&kv->lock);
+
+		kvm_vfio_group_put_external_user(vfio_group);
+
+		return ret;
+	}
+
+	return -ENXIO;
+}
+
+static int kvm_vfio_set_attr(struct kvm_device *dev,
+			     struct kvm_device_attr *attr)
+{
+	switch (attr->group) {
+	case KVM_DEV_VFIO_GROUP:
+		return kvm_vfio_set_group(dev, attr->attr, attr->addr);
+	}
+
+	return -ENXIO;
+}
+
+static int kvm_vfio_has_attr(struct kvm_device *dev,
+			     struct kvm_device_attr *attr)
+{
+	switch (attr->group) {
+	case KVM_DEV_VFIO_GROUP:
+		switch (attr->attr) {
+		case KVM_DEV_VFIO_GROUP_ADD:
+		case KVM_DEV_VFIO_GROUP_DEL:
+			return 0;
+		}
+
+		break;
+	}
+
+	return -ENXIO;
+}
+
+static void kvm_vfio_destroy(struct kvm_device *dev)
+{
+	struct kvm_vfio *kv = dev->private;
+	struct kvm_vfio_group *kvg, *tmp;
+
+	list_for_each_entry_safe(kvg, tmp, &kv->group_list, node) {
+		kvm_vfio_group_put_external_user(kvg->vfio_group);
+		list_del(&kvg->node);
+		kfree(kvg);
+	}
+
+	kfree(kv);
+	kfree(dev); /* alloc by kvm_ioctl_create_device, free by .destroy */
+}
+
+static int kvm_vfio_create(struct kvm_device *dev, u32 type)
+{
+	struct kvm_device *tmp;
+	struct kvm_vfio *kv;
+
+	/* Only one VFIO "device" per VM */
+	list_for_each_entry(tmp, &dev->kvm->devices, vm_node)
+		if (tmp->ops == &kvm_vfio_ops)
+			return -EBUSY;
+
+	kv = kzalloc(sizeof(*kv), GFP_KERNEL);
+	if (!kv)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&kv->group_list);
+	mutex_init(&kv->lock);
+
+	dev->private = kv;
+
+	return 0;
+}
+
+struct kvm_device_ops kvm_vfio_ops = {
+	.name = "kvm-vfio",
+	.create = kvm_vfio_create,
+	.destroy = kvm_vfio_destroy,
+	.set_attr = kvm_vfio_set_attr,
+	.has_attr = kvm_vfio_has_attr,
+};