summaryrefslogtreecommitdiff
path: root/virt/kvm
diff options
context:
space:
mode:
Diffstat (limited to 'virt/kvm')
-rw-r--r--virt/kvm/Kconfig3
-rw-r--r--virt/kvm/iommu.c22
-rw-r--r--virt/kvm/kvm_main.c40
-rw-r--r--virt/kvm/vfio.c264
4 files changed, 304 insertions, 25 deletions
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index 779262f59e25..fbe1a48bd629 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -27,3 +27,6 @@ config HAVE_KVM_MSI
config HAVE_KVM_CPU_RELAX_INTERCEPT
bool
+
+config KVM_VFIO
+ bool
diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c
index a3b14109049b..c7d9ce122529 100644
--- a/virt/kvm/iommu.c
+++ b/virt/kvm/iommu.c
@@ -79,7 +79,7 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
flags = IOMMU_READ;
if (!(slot->flags & KVM_MEM_READONLY))
flags |= IOMMU_WRITE;
- if (kvm->arch.iommu_flags & KVM_IOMMU_CACHE_COHERENCY)
+ if (!kvm->arch.iommu_noncoherent)
flags |= IOMMU_CACHE;
@@ -140,6 +140,9 @@ static int kvm_iommu_map_memslots(struct kvm *kvm)
struct kvm_memslots *slots;
struct kvm_memory_slot *memslot;
+ if (kvm->arch.iommu_noncoherent)
+ kvm_arch_register_noncoherent_dma(kvm);
+
idx = srcu_read_lock(&kvm->srcu);
slots = kvm_memslots(kvm);
@@ -158,7 +161,8 @@ int kvm_assign_device(struct kvm *kvm,
{
struct pci_dev *pdev = NULL;
struct iommu_domain *domain = kvm->arch.iommu_domain;
- int r, last_flags;
+ int r;
+ bool noncoherent;
/* check if iommu exists and in use */
if (!domain)
@@ -174,15 +178,13 @@ int kvm_assign_device(struct kvm *kvm,
return r;
}
- last_flags = kvm->arch.iommu_flags;
- if (iommu_domain_has_cap(kvm->arch.iommu_domain,
- IOMMU_CAP_CACHE_COHERENCY))
- kvm->arch.iommu_flags |= KVM_IOMMU_CACHE_COHERENCY;
+ noncoherent = !iommu_domain_has_cap(kvm->arch.iommu_domain,
+ IOMMU_CAP_CACHE_COHERENCY);
/* Check if need to update IOMMU page table for guest memory */
- if ((last_flags ^ kvm->arch.iommu_flags) ==
- KVM_IOMMU_CACHE_COHERENCY) {
+ if (noncoherent != kvm->arch.iommu_noncoherent) {
kvm_iommu_unmap_memslots(kvm);
+ kvm->arch.iommu_noncoherent = noncoherent;
r = kvm_iommu_map_memslots(kvm);
if (r)
goto out_unmap;
@@ -328,6 +330,9 @@ static int kvm_iommu_unmap_memslots(struct kvm *kvm)
srcu_read_unlock(&kvm->srcu, idx);
+ if (kvm->arch.iommu_noncoherent)
+ kvm_arch_unregister_noncoherent_dma(kvm);
+
return 0;
}
@@ -342,6 +347,7 @@ int kvm_iommu_unmap_guest(struct kvm *kvm)
mutex_lock(&kvm->slots_lock);
kvm_iommu_unmap_memslots(kvm);
kvm->arch.iommu_domain = NULL;
+ kvm->arch.iommu_noncoherent = false;
mutex_unlock(&kvm->slots_lock);
iommu_domain_free(domain);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 0932c3b64155..7a317a7f9025 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -874,21 +874,6 @@ int __kvm_set_memory_region(struct kvm *kvm,
goto out_free;
}
- /*
- * IOMMU mapping: New slots need to be mapped. Old slots need to be
- * un-mapped and re-mapped if their base changes. Since base change
- * unmapping is handled above with slot deletion, mapping alone is
- * needed here. Anything else the iommu might care about for existing
- * slots (size changes, userspace addr changes and read-only flag
- * changes) is disallowed above, so any other attribute changes getting
- * here can be skipped.
- */
- if ((change == KVM_MR_CREATE) || (change == KVM_MR_MOVE)) {
- r = kvm_iommu_map_pages(kvm, &new);
- if (r)
- goto out_slots;
- }
-
/* actual memory is freed via old in kvm_free_physmem_slot below */
if (change == KVM_MR_DELETE) {
new.dirty_bitmap = NULL;
@@ -902,6 +887,20 @@ int __kvm_set_memory_region(struct kvm *kvm,
kvm_free_physmem_slot(kvm, &old, &new);
kfree(old_memslots);
+ /*
+ * IOMMU mapping: New slots need to be mapped. Old slots need to be
+ * un-mapped and re-mapped if their base changes. Since base change
+ * unmapping is handled above with slot deletion, mapping alone is
+ * needed here. Anything else the iommu might care about for existing
+ * slots (size changes, userspace addr changes and read-only flag
+ * changes) is disallowed above, so any other attribute changes getting
+ * here can be skipped.
+ */
+ if ((change == KVM_MR_CREATE) || (change == KVM_MR_MOVE)) {
+ r = kvm_iommu_map_pages(kvm, &new);
+ return r;
+ }
+
return 0;
out_slots:
@@ -1067,10 +1066,12 @@ EXPORT_SYMBOL_GPL(gfn_to_hva);
unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable)
{
struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn);
- if (writable)
+ unsigned long hva = __gfn_to_hva_many(slot, gfn, NULL, false);
+
+ if (!kvm_is_error_hva(hva) && writable)
*writable = !memslot_is_readonly(slot);
- return __gfn_to_hva_many(gfn_to_memslot(kvm, gfn), gfn, NULL, false);
+ return hva;
}
static int kvm_read_hva(void *data, void __user *hva, int len)
@@ -2274,6 +2275,11 @@ static int kvm_ioctl_create_device(struct kvm *kvm,
ops = &kvm_xics_ops;
break;
#endif
+#ifdef CONFIG_KVM_VFIO
+ case KVM_DEV_TYPE_VFIO:
+ ops = &kvm_vfio_ops;
+ break;
+#endif
default:
return -ENODEV;
}
diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c
new file mode 100644
index 000000000000..ca4260e35037
--- /dev/null
+++ b/virt/kvm/vfio.c
@@ -0,0 +1,264 @@
+/*
+ * 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;
+ bool noncoherent;
+};
+
+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);
+}
+
+/*
+ * Groups can use the same or different IOMMU domains. If the same then
+ * adding a new group may change the coherency of groups we've previously
+ * been told about. We don't want to care about any of that so we retest
+ * each group and bail as soon as we find one that's noncoherent. This
+ * means we only ever [un]register_noncoherent_dma once for the whole device.
+ */
+static void kvm_vfio_update_coherency(struct kvm_device *dev)
+{
+ struct kvm_vfio *kv = dev->private;
+ bool noncoherent = false;
+ struct kvm_vfio_group *kvg;
+
+ mutex_lock(&kv->lock);
+
+ list_for_each_entry(kvg, &kv->group_list, node) {
+ /*
+ * TODO: We need an interface to check the coherency of
+ * the IOMMU domain this group is using. For now, assume
+ * it's always noncoherent.
+ */
+ noncoherent = true;
+ break;
+ }
+
+ if (noncoherent != kv->noncoherent) {
+ kv->noncoherent = noncoherent;
+
+ if (kv->noncoherent)
+ kvm_arch_register_noncoherent_dma(dev->kvm);
+ else
+ kvm_arch_unregister_noncoherent_dma(dev->kvm);
+ }
+
+ mutex_unlock(&kv->lock);
+}
+
+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);
+
+ kvm_vfio_update_coherency(dev);
+
+ 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);
+
+ kvm_vfio_update_coherency(dev);
+
+ 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);
+ }
+
+ kvm_vfio_update_coherency(dev);
+
+ 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,
+};