KVM: x86: Support KVM VMs sharing SEV context

Add a capability for userspace to mirror SEV encryption context from
one vm to another. On our side, this is intended to support a
Migration Helper vCPU, but it can also be used generically to support
other in-guest workloads scheduled by the host. The intention is for
the primary guest and the mirror to have nearly identical memslots.

The primary benefits of this are that:
1) The VMs do not share KVM contexts (think APIC/MSRs/etc), so they
can't accidentally clobber each other.
2) The VMs can have different memory-views, which is necessary for post-copy
migration (the migration vCPUs on the target need to read and write to
pages, when the primary guest would VMEXIT).

This does not change the threat model for AMD SEV. Any memory involved
is still owned by the primary guest and its initial state is still
attested to through the normal SEV_LAUNCH_* flows. If userspace wanted
to circumvent SEV, they could achieve the same effect by simply attaching
a vCPU to the primary VM.
This patch deliberately leaves userspace in charge of the memslots for the
mirror, as it already has the power to mess with them in the primary guest.

This patch does not support SEV-ES (much less SNP), as it does not
handle handing off attested VMSAs to the mirror.

For additional context, we need a Migration Helper because SEV PSP
migration is far too slow for our live migration on its own. Using
an in-guest migrator lets us speed this up significantly.

Signed-off-by: Nathan Tempelman <natet@google.com>
Message-Id: <20210408223214.2582277-1-natet@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

9 files changed, 126 insertions, 2 deletions

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 414b7fe1cf7b..fd4a84911355 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -6207,6 +6207,22 @@ KVM_RUN_BUS_LOCK flag is used to distinguish between them.
 This capability can be used to check / enable 2nd DAWR feature provided
 by POWER10 processor.
 
+7.24 KVM_CAP_VM_COPY_ENC_CONTEXT_FROM
+-------------------------------------
+
+Architectures: x86 SEV enabled
+Type: vm
+Parameters: args[0] is the fd of the source vm
+Returns: 0 on success; ENOTTY on error
+
+This capability enables userspace to copy encryption context from the vm
+indicated by the fd to the vm this is called on.
+
+This is intended to support in-guest workloads scheduled by the host. This
+allows the in-guest workload to maintain its own NPTs and keeps the two vms
+from accidentally clobbering each other with interrupts and the like (separate
+APIC/MSRs/etc).
+
 7.25 KVM_CAP_SGX_ATTRIBUTE
 ----------------------
 
@@ -6749,4 +6765,4 @@ in the kernel based fast path. If they can not be handled by the kernel,
 they will get passed on to user space. So user space still has to have
 an implementation for these despite the in kernel acceleration.
 
-This capability is always enabled.
\ No newline at end of file
+This capability is always enabled.
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index c5c96386cc76..6e195f7df4f0 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1349,6 +1349,7 @@ struct kvm_x86_ops {
 	int (*mem_enc_op)(struct kvm *kvm, void __user *argp);
 	int (*mem_enc_reg_region)(struct kvm *kvm, struct kvm_enc_region *argp);
 	int (*mem_enc_unreg_region)(struct kvm *kvm, struct kvm_enc_region *argp);
+	int (*vm_copy_enc_context_from)(struct kvm *kvm, unsigned int source_fd);
 
 	int (*get_msr_feature)(struct kvm_msr_entry *entry);
 
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index bb4bf5ffb104..4bf79dbc3eeb 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -66,6 +66,11 @@ static int sev_flush_asids(void)
 	return ret;
 }
 
+static inline bool is_mirroring_enc_context(struct kvm *kvm)
+{
+	return !!to_kvm_svm(kvm)->sev_info.enc_context_owner;
+}
+
 /* Must be called with the sev_bitmap_lock held */
 static bool __sev_recycle_asids(int min_asid, int max_asid)
 {
@@ -1122,6 +1127,12 @@ int svm_mem_enc_op(struct kvm *kvm, void __user *argp)
 
 	mutex_lock(&kvm->lock);
 
+	/* enc_context_owner handles all memory enc operations */
+	if (is_mirroring_enc_context(kvm)) {
+		r = -EINVAL;
+		goto out;
+	}
+
 	switch (sev_cmd.id) {
 	case KVM_SEV_ES_INIT:
 		if (!sev_es) {
@@ -1185,6 +1196,10 @@ int svm_register_enc_region(struct kvm *kvm,
 	if (!sev_guest(kvm))
 		return -ENOTTY;
 
+	/* If kvm is mirroring encryption context it isn't responsible for it */
+	if (is_mirroring_enc_context(kvm))
+		return -EINVAL;
+
 	if (range->addr > ULONG_MAX || range->size > ULONG_MAX)
 		return -EINVAL;
 
@@ -1251,6 +1266,10 @@ int svm_unregister_enc_region(struct kvm *kvm,
 	struct enc_region *region;
 	int ret;
 
+	/* If kvm is mirroring encryption context it isn't responsible for it */
+	if (is_mirroring_enc_context(kvm))
+		return -EINVAL;
+
 	mutex_lock(&kvm->lock);
 
 	if (!sev_guest(kvm)) {
@@ -1281,6 +1300,71 @@ failed:
 	return ret;
 }
 
+int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd)
+{
+	struct file *source_kvm_file;
+	struct kvm *source_kvm;
+	struct kvm_sev_info *mirror_sev;
+	unsigned int asid;
+	int ret;
+
+	source_kvm_file = fget(source_fd);
+	if (!file_is_kvm(source_kvm_file)) {
+		ret = -EBADF;
+		goto e_source_put;
+	}
+
+	source_kvm = source_kvm_file->private_data;
+	mutex_lock(&source_kvm->lock);
+
+	if (!sev_guest(source_kvm)) {
+		ret = -EINVAL;
+		goto e_source_unlock;
+	}
+
+	/* Mirrors of mirrors should work, but let's not get silly */
+	if (is_mirroring_enc_context(source_kvm) || source_kvm == kvm) {
+		ret = -EINVAL;
+		goto e_source_unlock;
+	}
+
+	asid = to_kvm_svm(source_kvm)->sev_info.asid;
+
+	/*
+	 * The mirror kvm holds an enc_context_owner ref so its asid can't
+	 * disappear until we're done with it
+	 */
+	kvm_get_kvm(source_kvm);
+
+	fput(source_kvm_file);
+	mutex_unlock(&source_kvm->lock);
+	mutex_lock(&kvm->lock);
+
+	if (sev_guest(kvm)) {
+		ret = -EINVAL;
+		goto e_mirror_unlock;
+	}
+
+	/* Set enc_context_owner and copy its encryption context over */
+	mirror_sev = &to_kvm_svm(kvm)->sev_info;
+	mirror_sev->enc_context_owner = source_kvm;
+	mirror_sev->asid = asid;
+	mirror_sev->active = true;
+
+	mutex_unlock(&kvm->lock);
+	return 0;
+
+e_mirror_unlock:
+	mutex_unlock(&kvm->lock);
+	kvm_put_kvm(source_kvm);
+	return ret;
+e_source_unlock:
+	mutex_unlock(&source_kvm->lock);
+e_source_put:
+	fput(source_kvm_file);
+	return ret;
+}
+
 void sev_vm_destroy(struct kvm *kvm)
 {
 	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
@@ -1290,6 +1374,12 @@ void sev_vm_destroy(struct kvm *kvm)
 	if (!sev_guest(kvm))
 		return;
 
+	/* If this is a mirror_kvm release the enc_context_owner and skip sev cleanup */
+	if (is_mirroring_enc_context(kvm)) {
+		kvm_put_kvm(sev->enc_context_owner);
+		return;
+	}
+
 	mutex_lock(&kvm->lock);
 
 	/*
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 86e42d42637e..cd8c333ed2dc 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4589,6 +4589,8 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.mem_enc_reg_region = svm_register_enc_region,
 	.mem_enc_unreg_region = svm_unregister_enc_region,
 
+	.vm_copy_enc_context_from = svm_vm_copy_asid_from,
+
 	.can_emulate_instruction = svm_can_emulate_instruction,
 
 	.apic_init_signal_blocked = svm_apic_init_signal_blocked,
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 7deb7a057004..454da1c1d9b7 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -68,6 +68,7 @@ struct kvm_sev_info {
 	unsigned long pages_locked; /* Number of pages locked */
 	struct list_head regions_list;  /* List of registered regions */
 	u64 ap_jump_table;	/* SEV-ES AP Jump Table address */
+	struct kvm *enc_context_owner; /* Owner of copied encryption context */
 };
 
 struct kvm_svm {
@@ -580,6 +581,7 @@ int svm_register_enc_region(struct kvm *kvm,
 			    struct kvm_enc_region *range);
 int svm_unregister_enc_region(struct kvm *kvm,
 			      struct kvm_enc_region *range);
+int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd);
 void pre_sev_run(struct vcpu_svm *svm, int cpu);
 void __init sev_hardware_setup(void);
 void sev_hardware_teardown(void);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index d4cdab15238b..a5eeca55810f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3808,6 +3808,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 #ifdef CONFIG_X86_SGX_KVM
 	case KVM_CAP_SGX_ATTRIBUTE:
 #endif
+	case KVM_CAP_VM_COPY_ENC_CONTEXT_FROM:
 		r = 1;
 		break;
 	case KVM_CAP_SET_GUEST_DEBUG2:
@@ -4714,7 +4715,6 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 			kvm_update_pv_runtime(vcpu);
 
 		return 0;
-
 	default:
 		return -EINVAL;
 	}
@@ -5413,6 +5413,11 @@ split_irqchip_unlock:
 		break;
 	}
 #endif
+	case KVM_CAP_VM_COPY_ENC_CONTEXT_FROM:
+		r = -EINVAL;
+		if (kvm_x86_ops.vm_copy_enc_context_from)
+			r = kvm_x86_ops.vm_copy_enc_context_from(kvm, cap->args[0]);
+		return r;
 	default:
 		r = -EINVAL;
 		break;
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 82b066db37cb..c306b4c3674e 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -654,6 +654,7 @@ void kvm_exit(void);
 
 void kvm_get_kvm(struct kvm *kvm);
 void kvm_put_kvm(struct kvm *kvm);
+bool file_is_kvm(struct file *file);
 void kvm_put_kvm_no_destroy(struct kvm *kvm);
 
 static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id)
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 162b7e044c8b..37f0a329da6a 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1080,6 +1080,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_PPC_DAWR1 194
 #define KVM_CAP_SET_GUEST_DEBUG2 195
 #define KVM_CAP_SGX_ATTRIBUTE 196
+#define KVM_CAP_VM_COPY_ENC_CONTEXT_FROM 197
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 545a28387c33..48c1e4842908 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -4197,6 +4197,12 @@ static struct file_operations kvm_vm_fops = {
 	KVM_COMPAT(kvm_vm_compat_ioctl),
 };
 
+bool file_is_kvm(struct file *file)
+{
+	return file && file->f_op == &kvm_vm_fops;
+}
+EXPORT_SYMBOL_GPL(file_is_kvm);
+
 static int kvm_dev_ioctl_create_vm(unsigned long type)
 {
 	int r;