KVM: X86: Introduce KVM_HC_MAP_GPA_RANGE hypercall

This hypercall is used by the SEV guest to notify a change in the page
encryption status to the hypervisor. The hypercall should be invoked
only when the encryption attribute is changed from encrypted -> decrypted
and vice versa. By default all guest pages are considered encrypted.

The hypercall exits to userspace to manage the guest shared regions and
integrate with the userspace VMM's migration code.

Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Borislav Petkov <bp@suse.de>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: x86@kernel.org
Cc: kvm@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Reviewed-by: Steve Rutherford <srutherford@google.com>
Signed-off-by: Brijesh Singh <brijesh.singh@amd.com>
Signed-off-by: Ashish Kalra <ashish.kalra@amd.com>
Co-developed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Co-developed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <90778988e1ee01926ff9cac447aacb745f954c8c.1623174621.git.ashish.kalra@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Documentation/virt/kvm/api.rst

@@ -6950,3 +6950,22 @@ guest according to the bits Hyper-V CPUID feature leaves. Otherwise, all
 currently implmented Hyper-V features are provided unconditionally when
 Hyper-V identification is set in the HYPERV_CPUID_INTERFACE (0x40000001)
 leaf.
+
+8.34 KVM_CAP_EXIT_HYPERCALL
+---------------------------
+
+:Capability: KVM_CAP_EXIT_HYPERCALL
+:Architectures: x86
+:Type: vm
+
+This capability, if enabled, will cause KVM to exit to userspace
+with KVM_EXIT_HYPERCALL exit reason to process some hypercalls.
+
+Calling KVM_CHECK_EXTENSION for this capability will return a bitmask
+of hypercalls that can be configured to exit to userspace.
+Right now, the only such hypercall is KVM_HC_MAP_GPA_RANGE.
+
+The argument to KVM_ENABLE_CAP is also a bitmask, and must be a subset
+of the result of KVM_CHECK_EXTENSION.  KVM will forward to userspace
+the hypercalls whose corresponding bit is in the argument, and return
+ENOSYS for the others.

Documentation/virt/kvm/cpuid.rst

@@ -96,6 +96,13 @@ KVM_FEATURE_MSI_EXT_DEST_ID        15          guest checks this feature bit
                                                before using extended destination
                                                ID bits in MSI address bits 11-5.
 
+KVM_FEATURE_HC_MAP_GPA_RANGE       16          guest checks this feature bit before
+                                               using the map gpa range hypercall
+                                               to notify the page state change
+
+KVM_FEATURE_MIGRATION_CONTROL      17          guest checks this feature bit before
+                                               using MSR_KVM_MIGRATION_CONTROL
+
 KVM_FEATURE_CLOCKSOURCE_STABLE_BIT 24          host will warn if no guest-side
                                                per-cpu warps are expected in
                                                kvmclock

Documentation/virt/kvm/hypercalls.rst

@@ -169,3 +169,24 @@ a0: destination APIC ID
 
 :Usage example: When sending a call-function IPI-many to vCPUs, yield if
 	        any of the IPI target vCPUs was preempted.
+
+8. KVM_HC_MAP_GPA_RANGE
+-------------------------
+:Architecture: x86
+:Status: active
+:Purpose: Request KVM to map a GPA range with the specified attributes.
+
+a0: the guest physical address of the start page
+a1: the number of (4kb) pages (must be contiguous in GPA space)
+a2: attributes
+
+    Where 'attributes' :
+        * bits  3:0 - preferred page size encoding 0 = 4kb, 1 = 2mb, 2 = 1gb, etc...
+        * bit     4 - plaintext = 0, encrypted = 1
+        * bits 63:5 - reserved (must be zero)
+
+**Implementation note**: this hypercall is implemented in userspace via
+the KVM_CAP_EXIT_HYPERCALL capability. Userspace must enable that capability
+before advertising KVM_FEATURE_HC_MAP_GPA_RANGE in the guest CPUID.  In
+addition, if the guest supports KVM_FEATURE_MIGRATION_CONTROL, userspace
+must also set up an MSR filter to process writes to MSR_KVM_MIGRATION_CONTROL.

Documentation/virt/kvm/msr.rst

@@ -376,3 +376,16 @@ data:
 	write '1' to bit 0 of the MSR, this causes the host to re-scan its queue
 	and check if there are more notifications pending. The MSR is available
 	if KVM_FEATURE_ASYNC_PF_INT is present in CPUID.
+
+MSR_KVM_MIGRATION_CONTROL:
+        0x4b564d08
+
+data:
+        This MSR is available if KVM_FEATURE_MIGRATION_CONTROL is present in
+        CPUID.  Bit 0 represents whether live migration of the guest is allowed.
+
+        When a guest is started, bit 0 will be 0 if the guest has encrypted
+        memory and 1 if the guest does not have encrypted memory.  If the
+        guest is communicating page encryption status to the host using the
+        ``KVM_HC_MAP_GPA_RANGE`` hypercall, it can set bit 0 in this MSR to
+        allow live migration of the guest.

arch/x86/include/asm/kvm_host.h

@@ -1087,6 +1087,8 @@ struct kvm_arch {
 	u32 user_space_msr_mask;
 	struct kvm_x86_msr_filter __rcu *msr_filter;
 
+	u32 hypercall_exit_enabled;
+
 	/* Guest can access the SGX PROVISIONKEY. */
 	bool sgx_provisioning_allowed;
 

arch/x86/include/uapi/asm/kvm_para.h

@@ -33,6 +33,8 @@
 #define KVM_FEATURE_PV_SCHED_YIELD	13
 #define KVM_FEATURE_ASYNC_PF_INT	14
 #define KVM_FEATURE_MSI_EXT_DEST_ID	15
+#define KVM_FEATURE_HC_MAP_GPA_RANGE	16
+#define KVM_FEATURE_MIGRATION_CONTROL	17
 
 #define KVM_HINTS_REALTIME      0
 
@@ -54,6 +56,7 @@
 #define MSR_KVM_POLL_CONTROL	0x4b564d05
 #define MSR_KVM_ASYNC_PF_INT	0x4b564d06
 #define MSR_KVM_ASYNC_PF_ACK	0x4b564d07
+#define MSR_KVM_MIGRATION_CONTROL	0x4b564d08
 
 struct kvm_steal_time {
 	__u64 steal;
@@ -90,6 +93,16 @@ struct kvm_clock_pairing {
 /* MSR_KVM_ASYNC_PF_INT */
 #define KVM_ASYNC_PF_VEC_MASK			GENMASK(7, 0)
 
+/* MSR_KVM_MIGRATION_CONTROL */
+#define KVM_MIGRATION_READY		(1 << 0)
+
+/* KVM_HC_MAP_GPA_RANGE */
+#define KVM_MAP_GPA_RANGE_PAGE_SZ_4K	0
+#define KVM_MAP_GPA_RANGE_PAGE_SZ_2M	(1 << 0)
+#define KVM_MAP_GPA_RANGE_PAGE_SZ_1G	(1 << 1)
+#define KVM_MAP_GPA_RANGE_ENC_STAT(n)	(n << 4)
+#define KVM_MAP_GPA_RANGE_ENCRYPTED	KVM_MAP_GPA_RANGE_ENC_STAT(1)
+#define KVM_MAP_GPA_RANGE_DECRYPTED	KVM_MAP_GPA_RANGE_ENC_STAT(0)
 
 /* Operations for KVM_HC_MMU_OP */
 #define KVM_MMU_OP_WRITE_PTE            1

arch/x86/kvm/x86.c

@@ -103,6 +103,8 @@ static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE);
 
 static u64 __read_mostly cr4_reserved_bits = CR4_RESERVED_BITS;
 
+#define KVM_EXIT_HYPERCALL_VALID_MASK (1 << KVM_HC_MAP_GPA_RANGE)
+
 #define KVM_X2APIC_API_VALID_FLAGS (KVM_X2APIC_API_USE_32BIT_IDS | \
                                     KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK)
 
@@ -3996,6 +3998,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_SREGS2:
 		r = 1;
 		break;
+	case KVM_CAP_EXIT_HYPERCALL:
+		r = KVM_EXIT_HYPERCALL_VALID_MASK;
+		break;
 	case KVM_CAP_SET_GUEST_DEBUG2:
 		return KVM_GUESTDBG_VALID_MASK;
 #ifdef CONFIG_KVM_XEN
@@ -5622,6 +5627,14 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 		if (kvm_x86_ops.vm_copy_enc_context_from)
 			r = kvm_x86_ops.vm_copy_enc_context_from(kvm, cap->args[0]);
 		return r;
+	case KVM_CAP_EXIT_HYPERCALL:
+		if (cap->args[0] & ~KVM_EXIT_HYPERCALL_VALID_MASK) {
+			r = -EINVAL;
+			break;
+		}
+		kvm->arch.hypercall_exit_enabled = cap->args[0];
+		r = 0;
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -8548,6 +8561,17 @@ static void kvm_sched_yield(struct kvm_vcpu *vcpu, unsigned long dest_id)
 	return;
 }
 
+static int complete_hypercall_exit(struct kvm_vcpu *vcpu)
+{
+	u64 ret = vcpu->run->hypercall.ret;
+
+	if (!is_64_bit_mode(vcpu))
+		ret = (u32)ret;
+	kvm_rax_write(vcpu, ret);
+	++vcpu->stat.hypercalls;
+	return kvm_skip_emulated_instruction(vcpu);
+}
+
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 {
 	unsigned long nr, a0, a1, a2, a3, ret;
@@ -8613,6 +8637,28 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 		kvm_sched_yield(vcpu, a0);
 		ret = 0;
 		break;
+	case KVM_HC_MAP_GPA_RANGE: {
+		u64 gpa = a0, npages = a1, attrs = a2;
+
+		ret = -KVM_ENOSYS;
+		if (!(vcpu->kvm->arch.hypercall_exit_enabled & (1 << KVM_HC_MAP_GPA_RANGE)))
+			break;
+
+		if (!PAGE_ALIGNED(gpa) || !npages ||
+		    gpa_to_gfn(gpa) + npages <= gpa_to_gfn(gpa)) {
+			ret = -KVM_EINVAL;
+			break;
+		}
+
+		vcpu->run->exit_reason        = KVM_EXIT_HYPERCALL;
+		vcpu->run->hypercall.nr       = KVM_HC_MAP_GPA_RANGE;
+		vcpu->run->hypercall.args[0]  = gpa;
+		vcpu->run->hypercall.args[1]  = npages;
+		vcpu->run->hypercall.args[2]  = attrs;
+		vcpu->run->hypercall.longmode = op_64_bit;
+		vcpu->arch.complete_userspace_io = complete_hypercall_exit;
+		return 0;
+	}
 	default:
 		ret = -KVM_ENOSYS;
 		break;

include/uapi/linux/kvm.h

@@ -1085,6 +1085,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_PTP_KVM 198
 #define KVM_CAP_HYPERV_ENFORCE_CPUID 199
 #define KVM_CAP_SREGS2 200
+#define KVM_CAP_EXIT_HYPERCALL 201
 
 #ifdef KVM_CAP_IRQ_ROUTING
 

include/uapi/linux/kvm_para.h

@@ -29,6 +29,7 @@
 #define KVM_HC_CLOCK_PAIRING		9
 #define KVM_HC_SEND_IPI		10
 #define KVM_HC_SCHED_YIELD		11
+#define KVM_HC_MAP_GPA_RANGE		12
 
 /*
  * hypercalls use architecture specific