KVM: x86: Use reserved_gpa_bits to calculate reserved PxE bits

Use reserved_gpa_bits, which accounts for exceptions to the maxphyaddr
rule, e.g. SEV's C-bit, for the page {table,directory,etc...} entry (PxE)
reserved bits checks.  For SEV, the C-bit is ignored by hardware when
walking pages tables, e.g. the APM states:

  Note that while the guest may choose to set the C-bit explicitly on
  instruction pages and page table addresses, the value of this bit is a
  don't-care in such situations as hardware always performs these as
  private accesses.

Such behavior is expected to hold true for other features that repurpose
GPA bits, e.g. KVM could theoretically emulate SME or MKTME, which both
allow non-zero repurposed bits in the page tables.  Conceptually, KVM
should apply reserved GPA checks universally, and any features that do
not adhere to the basic rule should be explicitly handled, i.e. if a GPA
bit is repurposed but not allowed in page tables for whatever reason.

Refactor __reset_rsvds_bits_mask() to take the pre-generated reserved
bits mask, and opportunistically clean up its code, e.g. to align lines
and comments.

Practically speaking, this is change is a likely a glorified nop given
the current KVM code base.  SEV's C-bit is the only repurposed GPA bit,
and KVM doesn't support shadowing encrypted page tables (which is
theoretically possible via SEV debug APIs).

Cc: Rick Edgecombe <rick.p.edgecombe@intel.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210204000117.3303214-9-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 50 insertions, 54 deletions

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index e8bfff9acd5e..d462db3bc742 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3985,20 +3985,27 @@ static inline bool is_last_gpte(struct kvm_mmu *mmu,
 static void
 __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 			struct rsvd_bits_validate *rsvd_check,
-			int maxphyaddr, int level, bool nx, bool gbpages,
+			u64 pa_bits_rsvd, int level, bool nx, bool gbpages,
 			bool pse, bool amd)
 {
-	u64 exb_bit_rsvd = 0;
 	u64 gbpages_bit_rsvd = 0;
 	u64 nonleaf_bit8_rsvd = 0;
+	u64 high_bits_rsvd;
 
 	rsvd_check->bad_mt_xwr = 0;
 
-	if (!nx)
-		exb_bit_rsvd = rsvd_bits(63, 63);
 	if (!gbpages)
 		gbpages_bit_rsvd = rsvd_bits(7, 7);
 
+	if (level == PT32E_ROOT_LEVEL)
+		high_bits_rsvd = pa_bits_rsvd & rsvd_bits(0, 62);
+	else
+		high_bits_rsvd = pa_bits_rsvd & rsvd_bits(0, 51);
+
+	/* Note, NX doesn't exist in PDPTEs, this is handled below. */
+	if (!nx)
+		high_bits_rsvd |= rsvd_bits(63, 63);
+
 	/*
 	 * Non-leaf PML4Es and PDPEs reserve bit 8 (which would be the G bit for
 	 * leaf entries) on AMD CPUs only.
@@ -4027,45 +4034,39 @@ __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 			rsvd_check->rsvd_bits_mask[1][1] = rsvd_bits(13, 21);
 		break;
 	case PT32E_ROOT_LEVEL:
-		rsvd_check->rsvd_bits_mask[0][2] =
-			rsvd_bits(maxphyaddr, 63) |
-			rsvd_bits(5, 8) | rsvd_bits(1, 2);	/* PDPTE */
-		rsvd_check->rsvd_bits_mask[0][1] = exb_bit_rsvd |
-			rsvd_bits(maxphyaddr, 62);	/* PDE */
-		rsvd_check->rsvd_bits_mask[0][0] = exb_bit_rsvd |
-			rsvd_bits(maxphyaddr, 62); 	/* PTE */
-		rsvd_check->rsvd_bits_mask[1][1] = exb_bit_rsvd |
-			rsvd_bits(maxphyaddr, 62) |
-			rsvd_bits(13, 20);		/* large page */
+		rsvd_check->rsvd_bits_mask[0][2] = rsvd_bits(63, 63) |
+						   high_bits_rsvd |
+						   rsvd_bits(5, 8) |
+						   rsvd_bits(1, 2);	/* PDPTE */
+		rsvd_check->rsvd_bits_mask[0][1] = high_bits_rsvd;	/* PDE */
+		rsvd_check->rsvd_bits_mask[0][0] = high_bits_rsvd;	/* PTE */
+		rsvd_check->rsvd_bits_mask[1][1] = high_bits_rsvd |
+						   rsvd_bits(13, 20);	/* large page */
 		rsvd_check->rsvd_bits_mask[1][0] =
 			rsvd_check->rsvd_bits_mask[0][0];
 		break;
 	case PT64_ROOT_5LEVEL:
-		rsvd_check->rsvd_bits_mask[0][4] = exb_bit_rsvd |
-			nonleaf_bit8_rsvd | rsvd_bits(7, 7) |
-			rsvd_bits(maxphyaddr, 51);
+		rsvd_check->rsvd_bits_mask[0][4] = high_bits_rsvd |
+						   nonleaf_bit8_rsvd |
+						   rsvd_bits(7, 7);
 		rsvd_check->rsvd_bits_mask[1][4] =
 			rsvd_check->rsvd_bits_mask[0][4];
 		fallthrough;
 	case PT64_ROOT_4LEVEL:
-		rsvd_check->rsvd_bits_mask[0][3] = exb_bit_rsvd |
-			nonleaf_bit8_rsvd | rsvd_bits(7, 7) |
-			rsvd_bits(maxphyaddr, 51);
-		rsvd_check->rsvd_bits_mask[0][2] = exb_bit_rsvd |
-			gbpages_bit_rsvd |
-			rsvd_bits(maxphyaddr, 51);
-		rsvd_check->rsvd_bits_mask[0][1] = exb_bit_rsvd |
-			rsvd_bits(maxphyaddr, 51);
-		rsvd_check->rsvd_bits_mask[0][0] = exb_bit_rsvd |
-			rsvd_bits(maxphyaddr, 51);
+		rsvd_check->rsvd_bits_mask[0][3] = high_bits_rsvd |
+						   nonleaf_bit8_rsvd |
+						   rsvd_bits(7, 7);
+		rsvd_check->rsvd_bits_mask[0][2] = high_bits_rsvd |
+						   gbpages_bit_rsvd;
+		rsvd_check->rsvd_bits_mask[0][1] = high_bits_rsvd;
+		rsvd_check->rsvd_bits_mask[0][0] = high_bits_rsvd;
 		rsvd_check->rsvd_bits_mask[1][3] =
 			rsvd_check->rsvd_bits_mask[0][3];
-		rsvd_check->rsvd_bits_mask[1][2] = exb_bit_rsvd |
-			gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51) |
-			rsvd_bits(13, 29);
-		rsvd_check->rsvd_bits_mask[1][1] = exb_bit_rsvd |
-			rsvd_bits(maxphyaddr, 51) |
-			rsvd_bits(13, 20);		/* large page */
+		rsvd_check->rsvd_bits_mask[1][2] = high_bits_rsvd |
+						   gbpages_bit_rsvd |
+						   rsvd_bits(13, 29);
+		rsvd_check->rsvd_bits_mask[1][1] = high_bits_rsvd |
+						   rsvd_bits(13, 20); /* large page */
 		rsvd_check->rsvd_bits_mask[1][0] =
 			rsvd_check->rsvd_bits_mask[0][0];
 		break;
@@ -4076,8 +4077,8 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 				  struct kvm_mmu *context)
 {
 	__reset_rsvds_bits_mask(vcpu, &context->guest_rsvd_check,
-				cpuid_maxphyaddr(vcpu), context->root_level,
-				context->nx,
+				vcpu->arch.reserved_gpa_bits,
+				context->root_level, context->nx,
 				guest_cpuid_has(vcpu, X86_FEATURE_GBPAGES),
 				is_pse(vcpu),
 				guest_cpuid_is_amd_or_hygon(vcpu));
@@ -4085,27 +4086,22 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 
 static void
 __reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check,
-			    int maxphyaddr, bool execonly)
+			    u64 pa_bits_rsvd, bool execonly)
 {
+	u64 high_bits_rsvd = pa_bits_rsvd & rsvd_bits(0, 51);
 	u64 bad_mt_xwr;
 
-	rsvd_check->rsvd_bits_mask[0][4] =
-		rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 7);
-	rsvd_check->rsvd_bits_mask[0][3] =
-		rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 7);
-	rsvd_check->rsvd_bits_mask[0][2] =
-		rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 6);
-	rsvd_check->rsvd_bits_mask[0][1] =
-		rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 6);
-	rsvd_check->rsvd_bits_mask[0][0] = rsvd_bits(maxphyaddr, 51);
+	rsvd_check->rsvd_bits_mask[0][4] = high_bits_rsvd | rsvd_bits(3, 7);
+	rsvd_check->rsvd_bits_mask[0][3] = high_bits_rsvd | rsvd_bits(3, 7);
+	rsvd_check->rsvd_bits_mask[0][2] = high_bits_rsvd | rsvd_bits(3, 6);
+	rsvd_check->rsvd_bits_mask[0][1] = high_bits_rsvd | rsvd_bits(3, 6);
+	rsvd_check->rsvd_bits_mask[0][0] = high_bits_rsvd;
 
 	/* large page */
 	rsvd_check->rsvd_bits_mask[1][4] = rsvd_check->rsvd_bits_mask[0][4];
 	rsvd_check->rsvd_bits_mask[1][3] = rsvd_check->rsvd_bits_mask[0][3];
-	rsvd_check->rsvd_bits_mask[1][2] =
-		rsvd_bits(maxphyaddr, 51) | rsvd_bits(12, 29);
-	rsvd_check->rsvd_bits_mask[1][1] =
-		rsvd_bits(maxphyaddr, 51) | rsvd_bits(12, 20);
+	rsvd_check->rsvd_bits_mask[1][2] = high_bits_rsvd | rsvd_bits(12, 29);
+	rsvd_check->rsvd_bits_mask[1][1] = high_bits_rsvd | rsvd_bits(12, 20);
 	rsvd_check->rsvd_bits_mask[1][0] = rsvd_check->rsvd_bits_mask[0][0];
 
 	bad_mt_xwr = 0xFFull << (2 * 8);	/* bits 3..5 must not be 2 */
@@ -4124,7 +4120,7 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
 		struct kvm_mmu *context, bool execonly)
 {
 	__reset_rsvds_bits_mask_ept(&context->guest_rsvd_check,
-				    cpuid_maxphyaddr(vcpu), execonly);
+				    vcpu->arch.reserved_gpa_bits, execonly);
 }
 
 /*
@@ -4146,7 +4142,7 @@ reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
 	 */
 	shadow_zero_check = &context->shadow_zero_check;
 	__reset_rsvds_bits_mask(vcpu, shadow_zero_check,
-				shadow_phys_bits,
+				rsvd_bits(shadow_phys_bits, 63),
 				context->shadow_root_level, uses_nx,
 				guest_cpuid_has(vcpu, X86_FEATURE_GBPAGES),
 				is_pse(vcpu), true);
@@ -4183,13 +4179,13 @@ reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu,
 
 	if (boot_cpu_is_amd())
 		__reset_rsvds_bits_mask(vcpu, shadow_zero_check,
-					shadow_phys_bits,
+					rsvd_bits(shadow_phys_bits, 63),
 					context->shadow_root_level, false,
 					boot_cpu_has(X86_FEATURE_GBPAGES),
 					true, true);
 	else
 		__reset_rsvds_bits_mask_ept(shadow_zero_check,
-					    shadow_phys_bits,
+					    rsvd_bits(shadow_phys_bits, 63),
 					    false);
 
 	if (!shadow_me_mask)
@@ -4210,7 +4206,7 @@ reset_ept_shadow_zero_bits_mask(struct kvm_vcpu *vcpu,
 				struct kvm_mmu *context, bool execonly)
 {
 	__reset_rsvds_bits_mask_ept(&context->shadow_zero_check,
-				    shadow_phys_bits, execonly);
+				    rsvd_bits(shadow_phys_bits, 63), execonly);
 }
 
 #define BYTE_MASK(access) \