[23/29] KVM: TDX: Finalize VM initialization

Commit Message

Paolo Bonzini Feb. 26, 2025, 7:55 p.m. UTC

From: Isaku Yamahata <[e-mail]>

Add a new VM-scoped KVM_MEMORY_ENCRYPT_OP IOCTL subcommand,
KVM_TDX_FINALIZE_VM, to perform TD Measurement Finalization.

Documentation for the API is added in another patch:
"Documentation/virt/kvm: Document on Trust Domain Extensions(TDX)"

For the purpose of attestation, a measurement must be made of the TDX VM
initial state. This is referred to as TD Measurement Finalization, and
uses SEAMCALL TDH.MR.FINALIZE, after which:
1. The VMM adding TD private pages with arbitrary content is no longer
   allowed
2. The TDX VM is runnable

Co-developed-by: Adrian Hunter <[e-mail]>
Signed-off-by: Adrian Hunter <[e-mail]>
Signed-off-by: Isaku Yamahata <[e-mail]>
Signed-off-by: Rick Edgecombe <[e-mail]>
Message-ID: <[e-mail]>
Signed-off-by: Paolo Bonzini <[e-mail]>
---
 arch/x86/include/uapi/asm/kvm.h |  1 +
 arch/x86/kvm/vmx/tdx.c          | 78 +++++++++++++++++++++++++++++----
 arch/x86/kvm/vmx/tdx.h          |  3 ++
 3 files changed, 74 insertions(+), 8 deletions(-)

Patch

diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index ee1b517351a3..89cc7a18ef45 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -933,6 +933,7 @@  enum kvm_tdx_cmd_id {
 	KVM_TDX_INIT_VM,
 	KVM_TDX_INIT_VCPU,
 	KVM_TDX_INIT_MEM_REGION,
+	KVM_TDX_FINALIZE_VM,
 	KVM_TDX_GET_CPUID,
 
 	KVM_TDX_CMD_NR_MAX,
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index 12f3433d062d..246f924ae6f6 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -557,6 +557,29 @@  static int tdx_mem_page_aug(struct kvm *kvm, gfn_t gfn,
 	return 0;
 }
 
+/*
+ * KVM_TDX_INIT_MEM_REGION calls kvm_gmem_populate() to map guest pages; the
+ * callback tdx_gmem_post_populate() then maps pages into private memory.
+ * through the a seamcall TDH.MEM.PAGE.ADD().  The SEAMCALL also requires the
+ * private EPT structures for the page to have been built before, which is
+ * done via kvm_tdp_map_page(). nr_premapped counts the number of pages that
+ * were added to the EPT structures but not added with TDH.MEM.PAGE.ADD().
+ * The counter has to be zero on KVM_TDX_FINALIZE_VM, to ensure that there
+ * are no half-initialized shared EPT pages.
+ */
+static int tdx_mem_page_record_premap_cnt(struct kvm *kvm, gfn_t gfn,
+					  enum pg_level level, kvm_pfn_t pfn)
+{
+	struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
+
+	if (KVM_BUG_ON(kvm->arch.pre_fault_allowed, kvm))
+		return -EINVAL;
+
+	/* nr_premapped will be decreased when tdh_mem_page_add() is called. */
+	atomic64_inc(&kvm_tdx->nr_premapped);
+	return 0;
+}
+
 int tdx_sept_set_private_spte(struct kvm *kvm, gfn_t gfn,
 			      enum pg_level level, kvm_pfn_t pfn)
 {
@@ -577,14 +600,15 @@  int tdx_sept_set_private_spte(struct kvm *kvm, gfn_t gfn,
 	 */
 	get_page(page);
 
+	/*
+	 * Read 'pre_fault_allowed' before 'kvm_tdx->state'; see matching
+	 * barrier in tdx_td_finalize().
+	 */
+	smp_rmb();
 	if (likely(kvm_tdx->state == TD_STATE_RUNNABLE))
 		return tdx_mem_page_aug(kvm, gfn, level, page);
 
-	/*
-	 * TODO: KVM_TDX_INIT_MEM_REGION support to populate before finalize
-	 * comes here for the initial memory.
-	 */
-	return -EOPNOTSUPP;
+	return tdx_mem_page_record_premap_cnt(kvm, gfn, level, pfn);
 }
 
 static int tdx_sept_drop_private_spte(struct kvm *kvm, gfn_t gfn,
@@ -615,10 +639,12 @@  static int tdx_sept_drop_private_spte(struct kvm *kvm, gfn_t gfn,
 	if (unlikely(kvm_tdx->state != TD_STATE_RUNNABLE &&
 		     err == (TDX_EPT_WALK_FAILED | TDX_OPERAND_ID_RCX))) {
 		/*
-		 * This page was mapped with KVM_MAP_MEMORY, but
-		 * KVM_TDX_INIT_MEM_REGION is not issued yet.
+		 * Page is mapped by KVM_TDX_INIT_MEM_REGION, but hasn't called
+		 * tdh_mem_page_add().
 		 */
-		if (!is_last_spte(entry, level) || !(entry & VMX_EPT_RWX_MASK)) {
+		if ((!is_last_spte(entry, level) || !(entry & VMX_EPT_RWX_MASK)) &&
+		    !KVM_BUG_ON(!atomic64_read(&kvm_tdx->nr_premapped), kvm)) {
+			atomic64_dec(&kvm_tdx->nr_premapped);
 			tdx_unpin(kvm, page);
 			return 0;
 		}
@@ -1365,6 +1391,36 @@  void tdx_flush_tlb_all(struct kvm_vcpu *vcpu)
 	ept_sync_global();
 }
 
+static int tdx_td_finalize(struct kvm *kvm, struct kvm_tdx_cmd *cmd)
+{
+	struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
+
+	guard(mutex)(&kvm->slots_lock);
+
+	if (!is_hkid_assigned(kvm_tdx) || kvm_tdx->state == TD_STATE_RUNNABLE)
+		return -EINVAL;
+	/*
+	 * Pages are pending for KVM_TDX_INIT_MEM_REGION to issue
+	 * TDH.MEM.PAGE.ADD().
+	 */
+	if (atomic64_read(&kvm_tdx->nr_premapped))
+		return -EINVAL;
+
+	cmd->hw_error = tdh_mr_finalize(&kvm_tdx->td);
+	if (tdx_operand_busy(cmd->hw_error))
+		return -EBUSY;
+	if (KVM_BUG_ON(cmd->hw_error, kvm)) {
+		pr_tdx_error(TDH_MR_FINALIZE, cmd->hw_error);
+		return -EIO;
+	}
+
+	kvm_tdx->state = TD_STATE_RUNNABLE;
+	/* TD_STATE_RUNNABLE must be set before 'pre_fault_allowed' */
+	smp_wmb();
+	kvm->arch.pre_fault_allowed = true;
+	return 0;
+}
+
 int tdx_vm_ioctl(struct kvm *kvm, void __user *argp)
 {
 	struct kvm_tdx_cmd tdx_cmd;
@@ -1389,6 +1445,9 @@  int tdx_vm_ioctl(struct kvm *kvm, void __user *argp)
 	case KVM_TDX_INIT_VM:
 		r = tdx_td_init(kvm, &tdx_cmd);
 		break;
+	case KVM_TDX_FINALIZE_VM:
+		r = tdx_td_finalize(kvm, &tdx_cmd);
+		break;
 	default:
 		r = -EINVAL;
 		goto out;
@@ -1656,6 +1715,9 @@  static int tdx_gmem_post_populate(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn,
 		goto out;
 	}
 
+	if (!KVM_BUG_ON(!atomic64_read(&kvm_tdx->nr_premapped), kvm))
+		atomic64_dec(&kvm_tdx->nr_premapped);
+
 	if (arg->flags & KVM_TDX_MEASURE_MEMORY_REGION) {
 		for (i = 0; i < PAGE_SIZE; i += TDX_EXTENDMR_CHUNKSIZE) {
 			err = tdh_mr_extend(&kvm_tdx->td, gpa + i, &entry,
diff --git a/arch/x86/kvm/vmx/tdx.h b/arch/x86/kvm/vmx/tdx.h
index 77d693dfcb08..b71f8e9643e4 100644
--- a/arch/x86/kvm/vmx/tdx.h
+++ b/arch/x86/kvm/vmx/tdx.h
@@ -31,6 +31,9 @@  struct kvm_tdx {
 	u64 tsc_offset;
 
 	struct tdx_td td;
+
+	/* For KVM_TDX_INIT_MEM_REGION. */
+	atomic64_t nr_premapped;
 };
 
 /* TDX module vCPU states */