For SEV-ES to work with intra host migration the VMSAs, GHCB metadata,
and other SEV-ES info needs to be preserved along with the guest's
memory.
Signed-off-by: Peter Gonda <[email protected]>
Reviewed-by: Marc Orr <[email protected]>
Cc: Marc Orr <[email protected]>
Cc: Paolo Bonzini <[email protected]>
Cc: Sean Christopherson <[email protected]>
Cc: David Rientjes <[email protected]>
Cc: Dr. David Alan Gilbert <[email protected]>
Cc: Brijesh Singh <[email protected]>
Cc: Vitaly Kuznetsov <[email protected]>
Cc: Wanpeng Li <[email protected]>
Cc: Jim Mattson <[email protected]>
Cc: Joerg Roedel <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Borislav Petkov <[email protected]>
Cc: "H. Peter Anvin" <[email protected]>
Cc: [email protected]
Cc: [email protected]
---
arch/x86/kvm/svm/sev.c | 62 ++++++++++++++++++++++++++++++++++++++++--
1 file changed, 60 insertions(+), 2 deletions(-)
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 8db666a362d4..fac21a82e4de 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -1545,6 +1545,59 @@ static void migrate_info_from(struct kvm_sev_info *dst,
list_replace_init(&src->regions_list, &dst->regions_list);
}
+static int migrate_vmsa_from(struct kvm *dst, struct kvm *src)
+{
+ int i, num_vcpus;
+ struct kvm_vcpu *dst_vcpu, *src_vcpu;
+ struct vcpu_svm *dst_svm, *src_svm;
+
+ num_vcpus = atomic_read(&dst->online_vcpus);
+ if (num_vcpus != atomic_read(&src->online_vcpus)) {
+ pr_warn_ratelimited(
+ "Source and target VMs must have same number of vCPUs.\n");
+ return -EINVAL;
+ }
+
+ for (i = 0; i < num_vcpus; ++i) {
+ src_vcpu = src->vcpus[i];
+ if (!src_vcpu->arch.guest_state_protected) {
+ pr_warn_ratelimited(
+ "Source ES VM vCPUs must have protected state.\n");
+ return -EINVAL;
+ }
+ }
+
+ for (i = 0; i < num_vcpus; ++i) {
+ src_vcpu = src->vcpus[i];
+ src_svm = to_svm(src_vcpu);
+ dst_vcpu = dst->vcpus[i];
+ dst_svm = to_svm(dst_vcpu);
+
+ /*
+ * Copy VMSA and GHCB fields from the source to the destination.
+ * Clear them on the source to prevent the VM running and
+ * changing the state of the VMSA/GHCB unexpectedly.
+ */
+ dst_vcpu->vcpu_id = src_vcpu->vcpu_id;
+ dst_svm->vmsa = src_svm->vmsa;
+ src_svm->vmsa = NULL;
+ dst_svm->ghcb = src_svm->ghcb;
+ src_svm->ghcb = NULL;
+ dst_svm->vmcb->control.ghcb_gpa =
+ src_svm->vmcb->control.ghcb_gpa;
+ src_svm->vmcb->control.ghcb_gpa = 0;
+ dst_svm->ghcb_sa = src_svm->ghcb_sa;
+ src_svm->ghcb_sa = NULL;
+ dst_svm->ghcb_sa_len = src_svm->ghcb_sa_len;
+ src_svm->ghcb_sa_len = 0;
+ dst_svm->ghcb_sa_sync = src_svm->ghcb_sa_sync;
+ src_svm->ghcb_sa_sync = false;
+ dst_svm->ghcb_sa_free = src_svm->ghcb_sa_free;
+ src_svm->ghcb_sa_free = false;
+ }
+ return 0;
+}
+
int svm_vm_migrate_from(struct kvm *kvm, unsigned int source_fd)
{
struct kvm_sev_info *dst_sev = &to_kvm_svm(kvm)->sev_info;
@@ -1556,7 +1609,7 @@ int svm_vm_migrate_from(struct kvm *kvm, unsigned int source_fd)
if (ret)
return ret;
- if (!sev_guest(kvm) || sev_es_guest(kvm)) {
+ if (!sev_guest(kvm)) {
ret = -EINVAL;
pr_warn_ratelimited("VM must be SEV enabled to migrate to.\n");
goto out_unlock;
@@ -1582,13 +1635,18 @@ int svm_vm_migrate_from(struct kvm *kvm, unsigned int source_fd)
if (ret)
goto out_fput;
- if (!sev_guest(source_kvm) || sev_es_guest(source_kvm)) {
+ if (!sev_guest(source_kvm)) {
ret = -EINVAL;
pr_warn_ratelimited(
"Source VM must be SEV enabled to migrate from.\n");
goto out_source;
}
+ if (sev_es_guest(kvm)) {
+ ret = migrate_vmsa_from(kvm, source_kvm);
+ if (ret)
+ goto out_source;
+ }
migrate_info_from(dst_sev, &to_kvm_svm(source_kvm)->sev_info);
ret = 0;
--
2.33.0.153.gba50c8fa24-goog
On Thu, Sep 02, 2021, Peter Gonda wrote:
> diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
> index 8db666a362d4..fac21a82e4de 100644
> --- a/arch/x86/kvm/svm/sev.c
> +++ b/arch/x86/kvm/svm/sev.c
> @@ -1545,6 +1545,59 @@ static void migrate_info_from(struct kvm_sev_info *dst,
> list_replace_init(&src->regions_list, &dst->regions_list);
> }
>
> +static int migrate_vmsa_from(struct kvm *dst, struct kvm *src)
> +{
> + int i, num_vcpus;
> + struct kvm_vcpu *dst_vcpu, *src_vcpu;
> + struct vcpu_svm *dst_svm, *src_svm;
> +
> + num_vcpus = atomic_read(&dst->online_vcpus);
> + if (num_vcpus != atomic_read(&src->online_vcpus)) {
> + pr_warn_ratelimited(
> + "Source and target VMs must have same number of vCPUs.\n");
Same comments about not logging the why.
> + return -EINVAL;
> + }
> +
> + for (i = 0; i < num_vcpus; ++i)
> + src_vcpu = src->vcpus[i];
This can be:
kvm_for_each_vcpu(i, src_vcpu, src) {
if (!src_vcpu->arch.guest_state_protected)
return -EINVAL;
}
> + if (!src_vcpu->arch.guest_state_protected) {
> + pr_warn_ratelimited(
> + "Source ES VM vCPUs must have protected state.\n");
> + return -EINVAL;
> + }
> + }
> +
> + for (i = 0; i < num_vcpus; ++i) {
And again here,
kvm_for_each_vcpu(i, src_vcpu, src) {
src_svm = to_svm(src_vcpu);
> + src_vcpu = src->vcpus[i];
> + src_svm = to_svm(src_vcpu);
> + dst_vcpu = dst->vcpus[i];
Probably a good idea to use kvm_get_vcpu(), even though dst->lock is held. If
nothing else, using kvm_get_vcpu() may save some merge pain as there's a proposal
to switch vcpus to an xarray.
> + dst_svm = to_svm(dst_vcpu);
> +
> + /*
> + * Copy VMSA and GHCB fields from the source to the destination.
> + * Clear them on the source to prevent the VM running and
As brought up in the prior patch, clearing the fields might ensure future KVM_RUNs
fail, but it doesn't prevent the VM from running _now_. And with vcpu->mutext
held, I think a more appropriate comment would be:
/*
* Transfer VMSA and GHCB state to the destination. Nullify and
* clear source fields as appropriate, the state now belongs to
* the destination.
*/
> + * changing the state of the VMSA/GHCB unexpectedly.
> + */
> + dst_vcpu->vcpu_id = src_vcpu->vcpu_id;
> + dst_svm->vmsa = src_svm->vmsa;
> + src_svm->vmsa = NULL;
> + dst_svm->ghcb = src_svm->ghcb;
> + src_svm->ghcb = NULL;
> + dst_svm->vmcb->control.ghcb_gpa =
> + src_svm->vmcb->control.ghcb_gpa;
Let this poke out, an 83 char line isn't the end of the world, and not having
the interrupt makes the code more readable overall.
> + src_svm->vmcb->control.ghcb_gpa = 0;
Nit, '0' isn't an invalid GPA. The reset value would be more appropriate, though
I would just leave this alone.
> + dst_svm->ghcb_sa = src_svm->ghcb_sa;
> + src_svm->ghcb_sa = NULL;
> + dst_svm->ghcb_sa_len = src_svm->ghcb_sa_len;
> + src_svm->ghcb_sa_len = 0;
> + dst_svm->ghcb_sa_sync = src_svm->ghcb_sa_sync;
> + src_svm->ghcb_sa_sync = false;
> + dst_svm->ghcb_sa_free = src_svm->ghcb_sa_free;
> + src_svm->ghcb_sa_free = false;
> + }
> + return 0;
> +}
On Fri, Sep 10, 2021, Sean Christopherson wrote:
> On Thu, Sep 02, 2021, Peter Gonda wrote:
> > diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
> > index 8db666a362d4..fac21a82e4de 100644
> > --- a/arch/x86/kvm/svm/sev.c
> > +++ b/arch/x86/kvm/svm/sev.c
> > @@ -1545,6 +1545,59 @@ static void migrate_info_from(struct kvm_sev_info *dst,
> > list_replace_init(&src->regions_list, &dst->regions_list);
> > }
> >
> > +static int migrate_vmsa_from(struct kvm *dst, struct kvm *src)
Better to call this sev_es_migrate_from()...
> > +{
> > + int i, num_vcpus;
> > + struct kvm_vcpu *dst_vcpu, *src_vcpu;
> > + struct vcpu_svm *dst_svm, *src_svm;
> > +
...because this should also clear kvm->es_active. KVM_SEV_INIT isn't problematic
(as currently written) because the common sev_guest_init() explicitly writes es_active,
but I think a clever userspace could get an SEV ASID into an "ES" guest via
KVM_CAP_VM_COPY_ENC_CONTEXT_FROM, which requires its dst to be !SEV and thus
doesn't touch es_active.
Huh, that's a bug, svm_vm_copy_asid_from() should explicitly disallow copying the
ASID from an SEV-ES guest. I'll send a patch for that.
Last thought, it's probably worth renaming migrate_info_from() to sev_migrate_from()
to pair with sev_es_migrate_from().