KVM: x86: Fix CR3 reserved bits

According to Intel specifications, PAE and non-PAE does not have any reserved
bits.  In long-mode, regardless to PCIDE, only the high bits (above the
physical address) are reserved.

Signed-off-by: Nadav Amit <namit@cs.technion.ac.il>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

arch/x86/include/asm/kvm_host.h

@@ -50,11 +50,7 @@
 			  | X86_CR0_ET | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM \
 			  | X86_CR0_NW | X86_CR0_CD | X86_CR0_PG))
 
-#define CR3_PAE_RESERVED_BITS ((X86_CR3_PWT | X86_CR3_PCD) - 1)
-#define CR3_NONPAE_RESERVED_BITS ((PAGE_SIZE-1) & ~(X86_CR3_PWT | X86_CR3_PCD))
-#define CR3_PCID_ENABLED_RESERVED_BITS 0xFFFFFF0000000000ULL
-#define CR3_L_MODE_RESERVED_BITS (CR3_NONPAE_RESERVED_BITS |	\
-				  0xFFFFFF0000000000ULL)
+#define CR3_L_MODE_RESERVED_BITS 0xFFFFFF0000000000ULL
 #define CR4_RESERVED_BITS                                               \
 	(~(unsigned long)(X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE\
 			  | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE     \

arch/x86/kvm/emulate.c

@@ -3388,10 +3388,6 @@ static int check_cr_write(struct x86_emulate_ctxt *ctxt)
 		ctxt->ops->get_msr(ctxt, MSR_EFER, &efer);
 		if (efer & EFER_LMA)
 			rsvd = CR3_L_MODE_RESERVED_BITS;
-		else if (ctxt->ops->get_cr(ctxt, 4) & X86_CR4_PAE)
-			rsvd = CR3_PAE_RESERVED_BITS;
-		else if (ctxt->ops->get_cr(ctxt, 0) & X86_CR0_PG)
-			rsvd = CR3_NONPAE_RESERVED_BITS;
 
 		if (new_val & rsvd)
 			return emulate_gp(ctxt, 0);

arch/x86/kvm/x86.c

@@ -701,26 +701,11 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 		return 0;
 	}
 
-	if (is_long_mode(vcpu)) {
-		if (kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE)) {
-			if (cr3 & CR3_PCID_ENABLED_RESERVED_BITS)
-				return 1;
-		} else
-			if (cr3 & CR3_L_MODE_RESERVED_BITS)
-				return 1;
-	} else {
-		if (is_pae(vcpu)) {
-			if (cr3 & CR3_PAE_RESERVED_BITS)
-				return 1;
-			if (is_paging(vcpu) &&
-			    !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))
-				return 1;
-		}
-		/*
-		 * We don't check reserved bits in nonpae mode, because
-		 * this isn't enforced, and VMware depends on this.
-		 */
-	}
+	if (is_long_mode(vcpu) && (cr3 & CR3_L_MODE_RESERVED_BITS))
+		return 1;
+	if (is_pae(vcpu) && is_paging(vcpu) &&
+	    !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))
+		return 1;
 
 	vcpu->arch.cr3 = cr3;
 	__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);