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

Pull kvm fixes from Paolo Bonzini:
 "x86 host:

   - Expose KVM_CAP_ENABLE_CAP since it is supported

   - Disable KVM_HC_CLOCK_PAIRING in TSC catchup mode

   - Ensure async page fault token is nonzero

   - Fix lockdep false negative

   - Fix FPU migration regression from the AMX changes

  x86 guest:

   - Don't use PV TLB/IPI/yield on uniprocessor guests

  PPC:

   - reserve capability id (topic branch for ppc/kvm)"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: x86: nSVM: disallow userspace setting of MSR_AMD64_TSC_RATIO to non default value when tsc scaling disabled
  KVM: x86/mmu: make apf token non-zero to fix bug
  KVM: PPC: reserve capability 210 for KVM_CAP_PPC_AIL_MODE_3
  x86/kvm: Don't use pv tlb/ipi/sched_yield if on 1 vCPU
  x86/kvm: Fix compilation warning in non-x86_64 builds
  x86/kvm/fpu: Remove kvm_vcpu_arch.guest_supported_xcr0
  x86/kvm/fpu: Limit guest user_xfeatures to supported bits of XCR0
  kvm: x86: Disable KVM_HC_CLOCK_PAIRING if tsc is in always catchup mode
  KVM: Fix lockdep false negative during host resume
  KVM: x86: Add KVM_CAP_ENABLE_CAP to x86

Documentation/virt/kvm/api.rst

@@ -1394,7 +1394,7 @@ documentation when it pops into existence).
 -------------------
 
 :Capability: KVM_CAP_ENABLE_CAP
-:Architectures: mips, ppc, s390
+:Architectures: mips, ppc, s390, x86
 :Type: vcpu ioctl
 :Parameters: struct kvm_enable_cap (in)
 :Returns: 0 on success; -1 on error
@@ -6997,6 +6997,20 @@ indicated by the fd to the VM this is called on.
 This is intended to support intra-host migration of VMs between userspace VMMs,
 upgrading the VMM process without interrupting the guest.
 
+7.30 KVM_CAP_PPC_AIL_MODE_3
+-------------------------------
+
+:Capability: KVM_CAP_PPC_AIL_MODE_3
+:Architectures: ppc
+:Type: vm
+
+This capability indicates that the kernel supports the mode 3 setting for the
+"Address Translation Mode on Interrupt" aka "Alternate Interrupt Location"
+resource that is controlled with the H_SET_MODE hypercall.
+
+This capability allows a guest kernel to use a better-performance mode for
+handling interrupts and system calls.
+
 8. Other capabilities.
 ======================
 

arch/x86/include/asm/kvm_host.h

@@ -703,7 +703,6 @@ struct kvm_vcpu_arch {
 	struct fpu_guest guest_fpu;
 
 	u64 xcr0;
-	u64 guest_supported_xcr0;
 
 	struct kvm_pio_request pio;
 	void *pio_data;

arch/x86/kernel/fpu/xstate.c

@@ -1558,7 +1558,10 @@ static int fpstate_realloc(u64 xfeatures, unsigned int ksize,
 		fpregs_restore_userregs();
 
 	newfps->xfeatures = curfps->xfeatures | xfeatures;
-	newfps->user_xfeatures = curfps->user_xfeatures | xfeatures;
+
+	if (!guest_fpu)
+		newfps->user_xfeatures = curfps->user_xfeatures | xfeatures;
+
 	newfps->xfd = curfps->xfd & ~xfeatures;
 
 	/* Do the final updates within the locked region */

arch/x86/kernel/kvm.c

@@ -462,19 +462,22 @@ static bool pv_tlb_flush_supported(void)
 {
 	return (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
 		!kvm_para_has_hint(KVM_HINTS_REALTIME) &&
-		kvm_para_has_feature(KVM_FEATURE_STEAL_TIME));
+		kvm_para_has_feature(KVM_FEATURE_STEAL_TIME) &&
+		(num_possible_cpus() != 1));
 }
 
 static bool pv_ipi_supported(void)
 {
-	return kvm_para_has_feature(KVM_FEATURE_PV_SEND_IPI);
+	return (kvm_para_has_feature(KVM_FEATURE_PV_SEND_IPI) &&
+	       (num_possible_cpus() != 1));
 }
 
 static bool pv_sched_yield_supported(void)
 {
 	return (kvm_para_has_feature(KVM_FEATURE_PV_SCHED_YIELD) &&
 		!kvm_para_has_hint(KVM_HINTS_REALTIME) &&
-	    kvm_para_has_feature(KVM_FEATURE_STEAL_TIME));
+	    kvm_para_has_feature(KVM_FEATURE_STEAL_TIME) &&
+	    (num_possible_cpus() != 1));
 }
 
 #define KVM_IPI_CLUSTER_SIZE	(2 * BITS_PER_LONG)

arch/x86/kvm/cpuid.c

@@ -282,6 +282,7 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	struct kvm_cpuid_entry2 *best;
+	u64 guest_supported_xcr0;
 
 	best = kvm_find_cpuid_entry(vcpu, 1, 0);
 	if (best && apic) {
@@ -293,9 +294,11 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 		kvm_apic_set_version(vcpu);
 	}
 
-	vcpu->arch.guest_supported_xcr0 =
+	guest_supported_xcr0 =
 		cpuid_get_supported_xcr0(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent);
 
+	vcpu->arch.guest_fpu.fpstate->user_xfeatures = guest_supported_xcr0;
+
 	kvm_update_pv_runtime(vcpu);
 
 	vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);

arch/x86/kvm/mmu/mmu.c

@@ -3889,12 +3889,23 @@ static void shadow_page_table_clear_flood(struct kvm_vcpu *vcpu, gva_t addr)
 	walk_shadow_page_lockless_end(vcpu);
 }
 
+static u32 alloc_apf_token(struct kvm_vcpu *vcpu)
+{
+	/* make sure the token value is not 0 */
+	u32 id = vcpu->arch.apf.id;
+
+	if (id << 12 == 0)
+		vcpu->arch.apf.id = 1;
+
+	return (vcpu->arch.apf.id++ << 12) | vcpu->vcpu_id;
+}
+
 static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 				    gfn_t gfn)
 {
 	struct kvm_arch_async_pf arch;
 
-	arch.token = (vcpu->arch.apf.id++ << 12) | vcpu->vcpu_id;
+	arch.token = alloc_apf_token(vcpu);
 	arch.gfn = gfn;
 	arch.direct_map = vcpu->arch.mmu->direct_map;
 	arch.cr3 = vcpu->arch.mmu->get_guest_pgd(vcpu);

arch/x86/kvm/svm/svm.c

@@ -2693,8 +2693,23 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	u64 data = msr->data;
 	switch (ecx) {
 	case MSR_AMD64_TSC_RATIO:
-		if (!msr->host_initiated && !svm->tsc_scaling_enabled)
-			return 1;
+
+		if (!svm->tsc_scaling_enabled) {
+
+			if (!msr->host_initiated)
+				return 1;
+			/*
+			 * In case TSC scaling is not enabled, always
+			 * leave this MSR at the default value.
+			 *
+			 * Due to bug in qemu 6.2.0, it would try to set
+			 * this msr to 0 if tsc scaling is not enabled.
+			 * Ignore this value as well.
+			 */
+			if (data != 0 && data != svm->tsc_ratio_msr)
+				return 1;
+			break;
+		}
 
 		if (data & TSC_RATIO_RSVD)
 			return 1;

arch/x86/kvm/x86.c

@@ -984,6 +984,18 @@ void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_load_host_xsave_state);
 
+static inline u64 kvm_guest_supported_xcr0(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.guest_fpu.fpstate->user_xfeatures;
+}
+
+#ifdef CONFIG_X86_64
+static inline u64 kvm_guest_supported_xfd(struct kvm_vcpu *vcpu)
+{
+	return kvm_guest_supported_xcr0(vcpu) & XFEATURE_MASK_USER_DYNAMIC;
+}
+#endif
+
 static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 {
 	u64 xcr0 = xcr;
@@ -1003,7 +1015,7 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 	 * saving.  However, xcr0 bit 0 is always set, even if the
 	 * emulated CPU does not support XSAVE (see kvm_vcpu_reset()).
 	 */
-	valid_bits = vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FP;
+	valid_bits = kvm_guest_supported_xcr0(vcpu) | XFEATURE_MASK_FP;
 	if (xcr0 & ~valid_bits)
 		return 1;
 
@@ -2351,10 +2363,12 @@ static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns)
 	return tsc;
 }
 
+#ifdef CONFIG_X86_64
 static inline int gtod_is_based_on_tsc(int mode)
 {
 	return mode == VDSO_CLOCKMODE_TSC || mode == VDSO_CLOCKMODE_HVCLOCK;
 }
+#endif
 
 static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu)
 {
@@ -3706,8 +3720,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		    !guest_cpuid_has(vcpu, X86_FEATURE_XFD))
 			return 1;
 
-		if (data & ~(XFEATURE_MASK_USER_DYNAMIC &
-			     vcpu->arch.guest_supported_xcr0))
+		if (data & ~kvm_guest_supported_xfd(vcpu))
 			return 1;
 
 		fpu_update_guest_xfd(&vcpu->arch.guest_fpu, data);
@@ -3717,8 +3730,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		    !guest_cpuid_has(vcpu, X86_FEATURE_XFD))
 			return 1;
 
-		if (data & ~(XFEATURE_MASK_USER_DYNAMIC &
-			     vcpu->arch.guest_supported_xcr0))
+		if (data & ~kvm_guest_supported_xfd(vcpu))
 			return 1;
 
 		vcpu->arch.guest_fpu.xfd_err = data;
@@ -4233,6 +4245,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_EXIT_ON_EMULATION_FAILURE:
 	case KVM_CAP_VCPU_ATTRIBUTES:
 	case KVM_CAP_SYS_ATTRIBUTES:
+	case KVM_CAP_ENABLE_CAP:
 		r = 1;
 		break;
 	case KVM_CAP_EXIT_HYPERCALL:
@@ -8942,6 +8955,13 @@ static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr,
 	if (clock_type != KVM_CLOCK_PAIRING_WALLCLOCK)
 		return -KVM_EOPNOTSUPP;
 
+	/*
+	 * When tsc is in permanent catchup mode guests won't be able to use
+	 * pvclock_read_retry loop to get consistent view of pvclock
+	 */
+	if (vcpu->arch.tsc_always_catchup)
+		return -KVM_EOPNOTSUPP;
+
 	if (!kvm_get_walltime_and_clockread(&ts, &cycle))
 		return -KVM_EOPNOTSUPP;
 

include/uapi/linux/kvm.h

@@ -1134,6 +1134,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_VM_GPA_BITS 207
 #define KVM_CAP_XSAVE2 208
 #define KVM_CAP_SYS_ATTRIBUTES 209
+#define KVM_CAP_PPC_AIL_MODE_3 210
 
 #ifdef KVM_CAP_IRQ_ROUTING
 

tools/include/uapi/linux/kvm.h

@@ -1134,6 +1134,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_VM_GPA_BITS 207
 #define KVM_CAP_XSAVE2 208
 #define KVM_CAP_SYS_ATTRIBUTES 209
+#define KVM_CAP_PPC_AIL_MODE_3 210
 
 #ifdef KVM_CAP_IRQ_ROUTING
 

virt/kvm/kvm_main.c

@@ -5528,9 +5528,7 @@ static int kvm_suspend(void)
 static void kvm_resume(void)
 {
 	if (kvm_usage_count) {
-#ifdef CONFIG_LOCKDEP
-		WARN_ON(lockdep_is_held(&kvm_count_lock));
-#endif
+		lockdep_assert_not_held(&kvm_count_lock);
 		hardware_enable_nolock(NULL);
 	}
 }