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

Pull KVM fixes from Radim Krčmář:
 "PPC:

   - Close a hole which could possibly lead to the host timebase getting
     out of sync.

   - Three fixes relating to PTEs and TLB entries for radix guests.

   - Fix a bug which could lead to an interrupt never getting delivered
     to the guest, if it is pending for a guest vCPU when the vCPU gets
     offlined.

  s390:

   - Fix false negatives in VSIE validity check (Cc stable)

  x86:

   - Fix time drift of VMX preemption timer when a guest uses LAPIC
     timer in periodic mode (Cc stable)

   - Unconditionally expose CPUID.IA32_ARCH_CAPABILITIES to allow
     migration from hosts that don't need retpoline mitigation (Cc
     stable)

   - Fix guest crashes on reboot by properly coupling CR4.OSXSAVE and
     CPUID.OSXSAVE (Cc stable)

   - Report correct RIP after Hyper-V hypercall #UD (introduced in
     -rc6)"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: x86: fix #UD address of failed Hyper-V hypercalls
  kvm: x86: IA32_ARCH_CAPABILITIES is always supported
  KVM: x86: Update cpuid properly when CR4.OSXAVE or CR4.PKE is changed
  x86/kvm: fix LAPIC timer drift when guest uses periodic mode
  KVM: s390: vsie: fix < 8k check for the itdba
  KVM: PPC: Book 3S HV: Do ptesync in radix guest exit path
  KVM: PPC: Book3S HV: XIVE: Resend re-routed interrupts on CPU priority change
  KVM: PPC: Book3S HV: Make radix clear pte when unmapping
  KVM: PPC: Book3S HV: Make radix use correct tlbie sequence in kvmppc_radix_tlbie_page
  KVM: PPC: Book3S HV: Snapshot timebase offset on guest entry

4 files changed, 38 insertions, 19 deletions

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index ced851169730..9bffb5228f31 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -495,6 +495,11 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 				entry->ecx &= ~F(PKU);
 			entry->edx &= kvm_cpuid_7_0_edx_x86_features;
 			cpuid_mask(&entry->edx, CPUID_7_EDX);
+			/*
+			 * We emulate ARCH_CAPABILITIES in software even
+			 * if the host doesn't support it.
+			 */
+			entry->edx |= F(ARCH_CAPABILITIES);
 		} else {
 			entry->ebx = 0;
 			entry->ecx = 0;
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 5708e951a5c6..46ff64da44ca 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1260,14 +1260,18 @@ static void kvm_hv_hypercall_set_result(struct kvm_vcpu *vcpu, u64 result)
 	}
 }
 
-static int kvm_hv_hypercall_complete_userspace(struct kvm_vcpu *vcpu)
+static int kvm_hv_hypercall_complete(struct kvm_vcpu *vcpu, u64 result)
 {
-	struct kvm_run *run = vcpu->run;
-
-	kvm_hv_hypercall_set_result(vcpu, run->hyperv.u.hcall.result);
+	kvm_hv_hypercall_set_result(vcpu, result);
+	++vcpu->stat.hypercalls;
 	return kvm_skip_emulated_instruction(vcpu);
 }
 
+static int kvm_hv_hypercall_complete_userspace(struct kvm_vcpu *vcpu)
+{
+	return kvm_hv_hypercall_complete(vcpu, vcpu->run->hyperv.u.hcall.result);
+}
+
 static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, bool fast, u64 param)
 {
 	struct eventfd_ctx *eventfd;
@@ -1350,7 +1354,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 	/* Hypercall continuation is not supported yet */
 	if (rep_cnt || rep_idx) {
 		ret = HV_STATUS_INVALID_HYPERCALL_CODE;
-		goto set_result;
+		goto out;
 	}
 
 	switch (code) {
@@ -1381,9 +1385,8 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 		break;
 	}
 
-set_result:
-	kvm_hv_hypercall_set_result(vcpu, ret);
-	return 1;
+out:
+	return kvm_hv_hypercall_complete(vcpu, ret);
 }
 
 void kvm_hv_init_vm(struct kvm *kvm)
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index b74c9c1405b9..3773c4625114 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1522,11 +1522,23 @@ static bool set_target_expiration(struct kvm_lapic *apic)
 
 static void advance_periodic_target_expiration(struct kvm_lapic *apic)
 {
-	apic->lapic_timer.tscdeadline +=
-		nsec_to_cycles(apic->vcpu, apic->lapic_timer.period);
+	ktime_t now = ktime_get();
+	u64 tscl = rdtsc();
+	ktime_t delta;
+
+	/*
+	 * Synchronize both deadlines to the same time source or
+	 * differences in the periods (caused by differences in the
+	 * underlying clocks or numerical approximation errors) will
+	 * cause the two to drift apart over time as the errors
+	 * accumulate.
+	 */
 	apic->lapic_timer.target_expiration =
 		ktime_add_ns(apic->lapic_timer.target_expiration,
 				apic->lapic_timer.period);
+	delta = ktime_sub(apic->lapic_timer.target_expiration, now);
+	apic->lapic_timer.tscdeadline = kvm_read_l1_tsc(apic->vcpu, tscl) +
+		nsec_to_cycles(apic->vcpu, delta);
 }
 
 static void start_sw_period(struct kvm_lapic *apic)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 22a183aac1c6..71e7cda6d014 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6671,11 +6671,8 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 	unsigned long nr, a0, a1, a2, a3, ret;
 	int op_64_bit;
 
-	if (kvm_hv_hypercall_enabled(vcpu->kvm)) {
-		if (!kvm_hv_hypercall(vcpu))
-			return 0;
-		goto out;
-	}
+	if (kvm_hv_hypercall_enabled(vcpu->kvm))
+		return kvm_hv_hypercall(vcpu);
 
 	nr = kvm_register_read(vcpu, VCPU_REGS_RAX);
 	a0 = kvm_register_read(vcpu, VCPU_REGS_RBX);
@@ -6696,7 +6693,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 
 	if (kvm_x86_ops->get_cpl(vcpu) != 0) {
 		ret = -KVM_EPERM;
-		goto out_error;
+		goto out;
 	}
 
 	switch (nr) {
@@ -6716,12 +6713,11 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 		ret = -KVM_ENOSYS;
 		break;
 	}
-out_error:
+out:
 	if (!op_64_bit)
 		ret = (u32)ret;
 	kvm_register_write(vcpu, VCPU_REGS_RAX, ret);
 
-out:
 	++vcpu->stat.hypercalls;
 	return kvm_skip_emulated_instruction(vcpu);
 }
@@ -7980,6 +7976,7 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 {
 	struct msr_data apic_base_msr;
 	int mmu_reset_needed = 0;
+	int cpuid_update_needed = 0;
 	int pending_vec, max_bits, idx;
 	struct desc_ptr dt;
 	int ret = -EINVAL;
@@ -8018,8 +8015,10 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 	vcpu->arch.cr0 = sregs->cr0;
 
 	mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4;
+	cpuid_update_needed |= ((kvm_read_cr4(vcpu) ^ sregs->cr4) &
+				(X86_CR4_OSXSAVE | X86_CR4_PKE));
 	kvm_x86_ops->set_cr4(vcpu, sregs->cr4);
-	if (sregs->cr4 & (X86_CR4_OSXSAVE | X86_CR4_PKE))
+	if (cpuid_update_needed)
 		kvm_update_cpuid(vcpu);
 
 	idx = srcu_read_lock(&vcpu->kvm->srcu);