Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm fixes from Paolo Bonzini:
 "Fixes for ARM and x86, the latter especially for old processors
  without two-dimensional paging (EPT/NPT)"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  kvm: mmu: fix is_tdp_mmu_check when the TDP MMU is not in use
  KVM: SVM: Update cr3_lm_rsvd_bits for AMD SEV guests
  KVM: x86: Introduce cr3_lm_rsvd_bits in kvm_vcpu_arch
  KVM: x86: clflushopt should be treated as a no-op by emulation
  KVM: arm64: Handle SCXTNUM_ELx traps
  KVM: arm64: Unify trap handlers injecting an UNDEF
  KVM: arm64: Allow setting of ID_AA64PFR0_EL1.CSV2 from userspace

Author: torvalds

arch/arm64/include/asm/kvm_host.h

@@ -118,6 +118,8 @@ struct kvm_arch {
 	 */
 	unsigned long *pmu_filter;
 	unsigned int pmuver;
+
+	u8 pfr0_csv2;
 };
 
 struct kvm_vcpu_fault_info {

arch/arm64/include/asm/sysreg.h

@@ -372,6 +372,8 @@
 #define SYS_CONTEXTIDR_EL1		sys_reg(3, 0, 13, 0, 1)
 #define SYS_TPIDR_EL1			sys_reg(3, 0, 13, 0, 4)
 
+#define SYS_SCXTNUM_EL1			sys_reg(3, 0, 13, 0, 7)
+
 #define SYS_CNTKCTL_EL1			sys_reg(3, 0, 14, 1, 0)
 
 #define SYS_CCSIDR_EL1			sys_reg(3, 1, 0, 0, 0)
@@ -404,6 +406,8 @@
 #define SYS_TPIDR_EL0			sys_reg(3, 3, 13, 0, 2)
 #define SYS_TPIDRRO_EL0			sys_reg(3, 3, 13, 0, 3)
 
+#define SYS_SCXTNUM_EL0			sys_reg(3, 3, 13, 0, 7)
+
 /* Definitions for system register interface to AMU for ARMv8.4 onwards */
 #define SYS_AM_EL0(crm, op2)		sys_reg(3, 3, 13, (crm), (op2))
 #define SYS_AMCR_EL0			SYS_AM_EL0(2, 0)

arch/arm64/kvm/arm.c

@@ -102,6 +102,20 @@ static int kvm_arm_default_max_vcpus(void)
 	return vgic_present ? kvm_vgic_get_max_vcpus() : KVM_MAX_VCPUS;
 }
 
+static void set_default_csv2(struct kvm *kvm)
+{
+	/*
+	 * The default is to expose CSV2 == 1 if the HW isn't affected.
+	 * Although this is a per-CPU feature, we make it global because
+	 * asymmetric systems are just a nuisance.
+	 *
+	 * Userspace can override this as long as it doesn't promise
+	 * the impossible.
+	 */
+	if (arm64_get_spectre_v2_state() == SPECTRE_UNAFFECTED)
+		kvm->arch.pfr0_csv2 = 1;
+}
+
 /**
  * kvm_arch_init_vm - initializes a VM data structure
  * @kvm:	pointer to the KVM struct
@@ -127,6 +141,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	/* The maximum number of VCPUs is limited by the host's GIC model */
 	kvm->arch.max_vcpus = kvm_arm_default_max_vcpus();
 
+	set_default_csv2(kvm);
+
 	return ret;
 out_free_stage2_pgd:
 	kvm_free_stage2_pgd(&kvm->arch.mmu);

arch/arm64/kvm/sys_regs.c

@@ -1038,42 +1038,34 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	{ SYS_DESC(SYS_PMEVTYPERn_EL0(n)),					\
 	  access_pmu_evtyper, reset_unknown, (PMEVTYPER0_EL0 + n), }
 
-static bool access_amu(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
-			     const struct sys_reg_desc *r)
+static bool undef_access(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			 const struct sys_reg_desc *r)
 {
 	kvm_inject_undefined(vcpu);
 
 	return false;
 }
 
 /* Macro to expand the AMU counter and type registers*/
-#define AMU_AMEVCNTR0_EL0(n) { SYS_DESC(SYS_AMEVCNTR0_EL0(n)), access_amu }
-#define AMU_AMEVTYPER0_EL0(n) { SYS_DESC(SYS_AMEVTYPER0_EL0(n)), access_amu }
-#define AMU_AMEVCNTR1_EL0(n) { SYS_DESC(SYS_AMEVCNTR1_EL0(n)), access_amu }
-#define AMU_AMEVTYPER1_EL0(n) { SYS_DESC(SYS_AMEVTYPER1_EL0(n)), access_amu }
-
-static bool trap_ptrauth(struct kvm_vcpu *vcpu,
-			 struct sys_reg_params *p,
-			 const struct sys_reg_desc *rd)
-{
-	/*
-	 * If we land here, that is because we didn't fixup the access on exit
-	 * by allowing the PtrAuth sysregs. The only way this happens is when
-	 * the guest does not have PtrAuth support enabled.
-	 */
-	kvm_inject_undefined(vcpu);
-
-	return false;
-}
+#define AMU_AMEVCNTR0_EL0(n) { SYS_DESC(SYS_AMEVCNTR0_EL0(n)), undef_access }
+#define AMU_AMEVTYPER0_EL0(n) { SYS_DESC(SYS_AMEVTYPER0_EL0(n)), undef_access }
+#define AMU_AMEVCNTR1_EL0(n) { SYS_DESC(SYS_AMEVCNTR1_EL0(n)), undef_access }
+#define AMU_AMEVTYPER1_EL0(n) { SYS_DESC(SYS_AMEVTYPER1_EL0(n)), undef_access }
 
 static unsigned int ptrauth_visibility(const struct kvm_vcpu *vcpu,
 			const struct sys_reg_desc *rd)
 {
 	return vcpu_has_ptrauth(vcpu) ? 0 : REG_HIDDEN;
 }
 
+/*
+ * If we land here on a PtrAuth access, that is because we didn't
+ * fixup the access on exit by allowing the PtrAuth sysregs. The only
+ * way this happens is when the guest does not have PtrAuth support
+ * enabled.
+ */
 #define __PTRAUTH_KEY(k)						\
-	{ SYS_DESC(SYS_## k), trap_ptrauth, reset_unknown, k,		\
+	{ SYS_DESC(SYS_## k), undef_access, reset_unknown, k,		\
 	.visibility = ptrauth_visibility}
 
 #define PTRAUTH_KEY(k)							\
@@ -1128,9 +1120,8 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu,
 		if (!vcpu_has_sve(vcpu))
 			val &= ~(0xfUL << ID_AA64PFR0_SVE_SHIFT);
 		val &= ~(0xfUL << ID_AA64PFR0_AMU_SHIFT);
-		if (!(val & (0xfUL << ID_AA64PFR0_CSV2_SHIFT)) &&
-		    arm64_get_spectre_v2_state() == SPECTRE_UNAFFECTED)
-			val |= (1UL << ID_AA64PFR0_CSV2_SHIFT);
+		val &= ~(0xfUL << ID_AA64PFR0_CSV2_SHIFT);
+		val |= ((u64)vcpu->kvm->arch.pfr0_csv2 << ID_AA64PFR0_CSV2_SHIFT);
 	} else if (id == SYS_ID_AA64PFR1_EL1) {
 		val &= ~(0xfUL << ID_AA64PFR1_MTE_SHIFT);
 	} else if (id == SYS_ID_AA64ISAR1_EL1 && !vcpu_has_ptrauth(vcpu)) {
@@ -1213,6 +1204,40 @@ static unsigned int sve_visibility(const struct kvm_vcpu *vcpu,
 	return REG_HIDDEN;
 }
 
+static int set_id_aa64pfr0_el1(struct kvm_vcpu *vcpu,
+			       const struct sys_reg_desc *rd,
+			       const struct kvm_one_reg *reg, void __user *uaddr)
+{
+	const u64 id = sys_reg_to_index(rd);
+	int err;
+	u64 val;
+	u8 csv2;
+
+	err = reg_from_user(&val, uaddr, id);
+	if (err)
+		return err;
+
+	/*
+	 * Allow AA64PFR0_EL1.CSV2 to be set from userspace as long as
+	 * it doesn't promise more than what is actually provided (the
+	 * guest could otherwise be covered in ectoplasmic residue).
+	 */
+	csv2 = cpuid_feature_extract_unsigned_field(val, ID_AA64PFR0_CSV2_SHIFT);
+	if (csv2 > 1 ||
+	    (csv2 && arm64_get_spectre_v2_state() != SPECTRE_UNAFFECTED))
+		return -EINVAL;
+
+	/* We can only differ with CSV2, and anything else is an error */
+	val ^= read_id_reg(vcpu, rd, false);
+	val &= ~(0xFUL << ID_AA64PFR0_CSV2_SHIFT);
+	if (val)
+		return -EINVAL;
+
+	vcpu->kvm->arch.pfr0_csv2 = csv2;
+
+	return 0;
+}
+
 /*
  * cpufeature ID register user accessors
  *
@@ -1341,13 +1366,6 @@ static bool access_ccsidr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	return true;
 }
 
-static bool access_mte_regs(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
-			    const struct sys_reg_desc *r)
-{
-	kvm_inject_undefined(vcpu);
-	return false;
-}
-
 /* sys_reg_desc initialiser for known cpufeature ID registers */
 #define ID_SANITISED(name) {			\
 	SYS_DESC(SYS_##name),			\
@@ -1472,7 +1490,8 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 
 	/* AArch64 ID registers */
 	/* CRm=4 */
-	ID_SANITISED(ID_AA64PFR0_EL1),
+	{ SYS_DESC(SYS_ID_AA64PFR0_EL1), .access = access_id_reg,
+	  .get_user = get_id_reg, .set_user = set_id_aa64pfr0_el1, },
 	ID_SANITISED(ID_AA64PFR1_EL1),
 	ID_UNALLOCATED(4,2),
 	ID_UNALLOCATED(4,3),
@@ -1515,8 +1534,8 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_ACTLR_EL1), access_actlr, reset_actlr, ACTLR_EL1 },
 	{ SYS_DESC(SYS_CPACR_EL1), NULL, reset_val, CPACR_EL1, 0 },
 
-	{ SYS_DESC(SYS_RGSR_EL1), access_mte_regs },
-	{ SYS_DESC(SYS_GCR_EL1), access_mte_regs },
+	{ SYS_DESC(SYS_RGSR_EL1), undef_access },
+	{ SYS_DESC(SYS_GCR_EL1), undef_access },
 
 	{ SYS_DESC(SYS_ZCR_EL1), NULL, reset_val, ZCR_EL1, 0, .visibility = sve_visibility },
 	{ SYS_DESC(SYS_TTBR0_EL1), access_vm_reg, reset_unknown, TTBR0_EL1 },
@@ -1542,8 +1561,8 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_ERXMISC0_EL1), trap_raz_wi },
 	{ SYS_DESC(SYS_ERXMISC1_EL1), trap_raz_wi },
 
-	{ SYS_DESC(SYS_TFSR_EL1), access_mte_regs },
-	{ SYS_DESC(SYS_TFSRE0_EL1), access_mte_regs },
+	{ SYS_DESC(SYS_TFSR_EL1), undef_access },
+	{ SYS_DESC(SYS_TFSRE0_EL1), undef_access },
 
 	{ SYS_DESC(SYS_FAR_EL1), access_vm_reg, reset_unknown, FAR_EL1 },
 	{ SYS_DESC(SYS_PAR_EL1), NULL, reset_unknown, PAR_EL1 },
@@ -1579,6 +1598,8 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_CONTEXTIDR_EL1), access_vm_reg, reset_val, CONTEXTIDR_EL1, 0 },
 	{ SYS_DESC(SYS_TPIDR_EL1), NULL, reset_unknown, TPIDR_EL1 },
 
+	{ SYS_DESC(SYS_SCXTNUM_EL1), undef_access },
+
 	{ SYS_DESC(SYS_CNTKCTL_EL1), NULL, reset_val, CNTKCTL_EL1, 0},
 
 	{ SYS_DESC(SYS_CCSIDR_EL1), access_ccsidr },
@@ -1607,14 +1628,16 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_TPIDR_EL0), NULL, reset_unknown, TPIDR_EL0 },
 	{ SYS_DESC(SYS_TPIDRRO_EL0), NULL, reset_unknown, TPIDRRO_EL0 },
 
-	{ SYS_DESC(SYS_AMCR_EL0), access_amu },
-	{ SYS_DESC(SYS_AMCFGR_EL0), access_amu },
-	{ SYS_DESC(SYS_AMCGCR_EL0), access_amu },
-	{ SYS_DESC(SYS_AMUSERENR_EL0), access_amu },
-	{ SYS_DESC(SYS_AMCNTENCLR0_EL0), access_amu },
-	{ SYS_DESC(SYS_AMCNTENSET0_EL0), access_amu },
-	{ SYS_DESC(SYS_AMCNTENCLR1_EL0), access_amu },
-	{ SYS_DESC(SYS_AMCNTENSET1_EL0), access_amu },
+	{ SYS_DESC(SYS_SCXTNUM_EL0), undef_access },
+
+	{ SYS_DESC(SYS_AMCR_EL0), undef_access },
+	{ SYS_DESC(SYS_AMCFGR_EL0), undef_access },
+	{ SYS_DESC(SYS_AMCGCR_EL0), undef_access },
+	{ SYS_DESC(SYS_AMUSERENR_EL0), undef_access },
+	{ SYS_DESC(SYS_AMCNTENCLR0_EL0), undef_access },
+	{ SYS_DESC(SYS_AMCNTENSET0_EL0), undef_access },
+	{ SYS_DESC(SYS_AMCNTENCLR1_EL0), undef_access },
+	{ SYS_DESC(SYS_AMCNTENSET1_EL0), undef_access },
 	AMU_AMEVCNTR0_EL0(0),
 	AMU_AMEVCNTR0_EL0(1),
 	AMU_AMEVCNTR0_EL0(2),

arch/x86/include/asm/kvm_host.h

@@ -639,6 +639,7 @@ struct kvm_vcpu_arch {
 	int cpuid_nent;
 	struct kvm_cpuid_entry2 *cpuid_entries;
 
+	unsigned long cr3_lm_rsvd_bits;
 	int maxphyaddr;
 	int max_tdp_level;
 

arch/x86/kvm/cpuid.c

@@ -178,6 +178,8 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 	vcpu->arch.cr4_guest_rsvd_bits =
 	    __cr4_reserved_bits(guest_cpuid_has, vcpu);
 
+	vcpu->arch.cr3_lm_rsvd_bits = rsvd_bits(cpuid_maxphyaddr(vcpu), 63);
+
 	/* Invoke the vendor callback only after the above state is updated. */
 	kvm_x86_ops.vcpu_after_set_cpuid(vcpu);
 }

arch/x86/kvm/emulate.c

@@ -4046,6 +4046,12 @@ static int em_clflush(struct x86_emulate_ctxt *ctxt)
 	return X86EMUL_CONTINUE;
 }
 
+static int em_clflushopt(struct x86_emulate_ctxt *ctxt)
+{
+	/* emulating clflushopt regardless of cpuid */
+	return X86EMUL_CONTINUE;
+}
+
 static int em_movsxd(struct x86_emulate_ctxt *ctxt)
 {
 	ctxt->dst.val = (s32) ctxt->src.val;
@@ -4585,7 +4591,7 @@ static const struct opcode group11[] = {
 };
 
 static const struct gprefix pfx_0f_ae_7 = {
-	I(SrcMem | ByteOp, em_clflush), N, N, N,
+	I(SrcMem | ByteOp, em_clflush), I(SrcMem | ByteOp, em_clflushopt), N, N,
 };
 
 static const struct group_dual group15 = { {

arch/x86/kvm/mmu/tdp_mmu.c

@@ -49,7 +49,14 @@ bool is_tdp_mmu_root(struct kvm *kvm, hpa_t hpa)
 {
 	struct kvm_mmu_page *sp;
 
+	if (!kvm->arch.tdp_mmu_enabled)
+		return false;
+	if (WARN_ON(!VALID_PAGE(hpa)))
+		return false;
+
 	sp = to_shadow_page(hpa);
+	if (WARN_ON(!sp))
+		return false;
 
 	return sp->tdp_mmu_page && sp->root_count;
 }

arch/x86/kvm/svm/svm.c

@@ -3741,6 +3741,7 @@ static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
 static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
+	struct kvm_cpuid_entry2 *best;
 
 	vcpu->arch.xsaves_enabled = guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
 				    boot_cpu_has(X86_FEATURE_XSAVE) &&
@@ -3753,6 +3754,13 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 	/* Check again if INVPCID interception if required */
 	svm_check_invpcid(svm);
 
+	/* For sev guests, the memory encryption bit is not reserved in CR3.  */
+	if (sev_guest(vcpu->kvm)) {
+		best = kvm_find_cpuid_entry(vcpu, 0x8000001F, 0);
+		if (best)
+			vcpu->arch.cr3_lm_rsvd_bits &= ~(1UL << (best->ebx & 0x3f));
+	}
+
 	if (!kvm_vcpu_apicv_active(vcpu))
 		return;
 

arch/x86/kvm/x86.c

@@ -1041,7 +1041,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 	}
 
 	if (is_long_mode(vcpu) &&
-	    (cr3 & rsvd_bits(cpuid_maxphyaddr(vcpu), 63)))
+	    (cr3 & vcpu->arch.cr3_lm_rsvd_bits))
 		return 1;
 	else if (is_pae_paging(vcpu) &&
 		 !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))