1 files changed, 90 insertions, 58 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 099b851dabaf..d75bb97b983c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -136,10 +136,14 @@ EXPORT_SYMBOL_GPL(kvm_default_tsc_scaling_ratio);
 static u32 __read_mostly tsc_tolerance_ppm = 250;
 module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR);
 
-/* lapic timer advance (tscdeadline mode only) in nanoseconds */
-unsigned int __read_mostly lapic_timer_advance_ns = 1000;
+/*
+ * lapic timer advance (tscdeadline mode only) in nanoseconds.  '-1' enables
+ * adaptive tuning starting from default advancment of 1000ns.  '0' disables
+ * advancement entirely.  Any other value is used as-is and disables adaptive
+ * tuning, i.e. allows priveleged userspace to set an exact advancement time.
+ */
+static int __read_mostly lapic_timer_advance_ns = -1;
 module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR);
-EXPORT_SYMBOL_GPL(lapic_timer_advance_ns);
 
 static bool __read_mostly vector_hashing = true;
 module_param(vector_hashing, bool, S_IRUGO);
@@ -800,7 +804,7 @@ void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw)
 }
 EXPORT_SYMBOL_GPL(kvm_lmsw);
 
-static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu)
+void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu)
 {
 	if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) &&
 			!vcpu->guest_xcr0_loaded) {
@@ -810,8 +814,9 @@ static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu)
 		vcpu->guest_xcr0_loaded = 1;
 	}
 }
+EXPORT_SYMBOL_GPL(kvm_load_guest_xcr0);
 
-static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
+void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
 {
 	if (vcpu->guest_xcr0_loaded) {
 		if (vcpu->arch.xcr0 != host_xcr0)
@@ -819,6 +824,7 @@ static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
 		vcpu->guest_xcr0_loaded = 0;
 	}
 }
+EXPORT_SYMBOL_GPL(kvm_put_guest_xcr0);
 
 static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 {
@@ -3093,7 +3099,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		break;
 	case KVM_CAP_NESTED_STATE:
 		r = kvm_x86_ops->get_nested_state ?
-			kvm_x86_ops->get_nested_state(NULL, 0, 0) : 0;
+			kvm_x86_ops->get_nested_state(NULL, NULL, 0) : 0;
 		break;
 	default:
 		break;
@@ -3528,7 +3534,7 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
 	memset(&events->reserved, 0, sizeof(events->reserved));
 }
 
-static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags);
+static void kvm_smm_changed(struct kvm_vcpu *vcpu);
 
 static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 					      struct kvm_vcpu_events *events)
@@ -3588,12 +3594,13 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 		vcpu->arch.apic->sipi_vector = events->sipi_vector;
 
 	if (events->flags & KVM_VCPUEVENT_VALID_SMM) {
-		u32 hflags = vcpu->arch.hflags;
-		if (events->smi.smm)
-			hflags |= HF_SMM_MASK;
-		else
-			hflags &= ~HF_SMM_MASK;
-		kvm_set_hflags(vcpu, hflags);
+		if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) {
+			if (events->smi.smm)
+				vcpu->arch.hflags |= HF_SMM_MASK;
+			else
+				vcpu->arch.hflags &= ~HF_SMM_MASK;
+			kvm_smm_changed(vcpu);
+		}
 
 		vcpu->arch.smi_pending = events->smi.pending;
 
@@ -3674,15 +3681,15 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu)
 	 */
 	valid = xstate_bv & ~XFEATURE_MASK_FPSSE;
 	while (valid) {
-		u64 feature = valid & -valid;
-		int index = fls64(feature) - 1;
-		void *src = get_xsave_addr(xsave, feature);
+		u64 xfeature_mask = valid & -valid;
+		int xfeature_nr = fls64(xfeature_mask) - 1;
+		void *src = get_xsave_addr(xsave, xfeature_nr);
 
 		if (src) {
 			u32 size, offset, ecx, edx;
-			cpuid_count(XSTATE_CPUID, index,
+			cpuid_count(XSTATE_CPUID, xfeature_nr,
 				    &size, &offset, &ecx, &edx);
-			if (feature == XFEATURE_MASK_PKRU)
+			if (xfeature_nr == XFEATURE_PKRU)
 				memcpy(dest + offset, &vcpu->arch.pkru,
 				       sizeof(vcpu->arch.pkru));
 			else
@@ -3690,7 +3697,7 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu)
 
 		}
 
-		valid -= feature;
+		valid -= xfeature_mask;
 	}
 }
 
@@ -3717,22 +3724,22 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src)
 	 */
 	valid = xstate_bv & ~XFEATURE_MASK_FPSSE;
 	while (valid) {
-		u64 feature = valid & -valid;
-		int index = fls64(feature) - 1;
-		void *dest = get_xsave_addr(xsave, feature);
+		u64 xfeature_mask = valid & -valid;
+		int xfeature_nr = fls64(xfeature_mask) - 1;
+		void *dest = get_xsave_addr(xsave, xfeature_nr);
 
 		if (dest) {
 			u32 size, offset, ecx, edx;
-			cpuid_count(XSTATE_CPUID, index,
+			cpuid_count(XSTATE_CPUID, xfeature_nr,
 				    &size, &offset, &ecx, &edx);
-			if (feature == XFEATURE_MASK_PKRU)
+			if (xfeature_nr == XFEATURE_PKRU)
 				memcpy(&vcpu->arch.pkru, src + offset,
 				       sizeof(vcpu->arch.pkru));
 			else
 				memcpy(dest, src + offset, size);
 		}
 
-		valid -= feature;
+		valid -= xfeature_mask;
 	}
 }
 
@@ -4270,7 +4277,7 @@ static int kvm_vm_ioctl_set_identity_map_addr(struct kvm *kvm,
 }
 
 static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm,
-					  u32 kvm_nr_mmu_pages)
+					 unsigned long kvm_nr_mmu_pages)
 {
 	if (kvm_nr_mmu_pages < KVM_MIN_ALLOC_MMU_PAGES)
 		return -EINVAL;
@@ -4284,7 +4291,7 @@ static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm,
 	return 0;
 }
 
-static int kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm)
+static unsigned long kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm)
 {
 	return kvm->arch.n_max_mmu_pages;
 }
@@ -5958,12 +5965,18 @@ static unsigned emulator_get_hflags(struct x86_emulate_ctxt *ctxt)
 
 static void emulator_set_hflags(struct x86_emulate_ctxt *ctxt, unsigned emul_flags)
 {
-	kvm_set_hflags(emul_to_vcpu(ctxt), emul_flags);
+	emul_to_vcpu(ctxt)->arch.hflags = emul_flags;
+}
+
+static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt,
+				  const char *smstate)
+{
+	return kvm_x86_ops->pre_leave_smm(emul_to_vcpu(ctxt), smstate);
 }
 
-static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt, u64 smbase)
+static void emulator_post_leave_smm(struct x86_emulate_ctxt *ctxt)
 {
-	return kvm_x86_ops->pre_leave_smm(emul_to_vcpu(ctxt), smbase);
+	kvm_smm_changed(emul_to_vcpu(ctxt));
 }
 
 static const struct x86_emulate_ops emulate_ops = {
@@ -6006,6 +6019,7 @@ static const struct x86_emulate_ops emulate_ops = {
 	.get_hflags          = emulator_get_hflags,
 	.set_hflags          = emulator_set_hflags,
 	.pre_leave_smm       = emulator_pre_leave_smm,
+	.post_leave_smm      = emulator_post_leave_smm,
 };
 
 static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask)
@@ -6247,16 +6261,6 @@ static void kvm_smm_changed(struct kvm_vcpu *vcpu)
 	kvm_mmu_reset_context(vcpu);
 }
 
-static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags)
-{
-	unsigned changed = vcpu->arch.hflags ^ emul_flags;
-
-	vcpu->arch.hflags = emul_flags;
-
-	if (changed & HF_SMM_MASK)
-		kvm_smm_changed(vcpu);
-}
-
 static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7,
 				unsigned long *db)
 {
@@ -6535,6 +6539,12 @@ int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu,
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_instruction_from_buffer);
 
+static int complete_fast_pio_out_port_0x7e(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.pio.count = 0;
+	return 1;
+}
+
 static int complete_fast_pio_out(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.pio.count = 0;
@@ -6551,12 +6561,23 @@ static int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size,
 	unsigned long val = kvm_register_read(vcpu, VCPU_REGS_RAX);
 	int ret = emulator_pio_out_emulated(&vcpu->arch.emulate_ctxt,
 					    size, port, &val, 1);
+	if (ret)
+		return ret;
 
-	if (!ret) {
+	/*
+	 * Workaround userspace that relies on old KVM behavior of %rip being
+	 * incremented prior to exiting to userspace to handle "OUT 0x7e".
+	 */
+	if (port == 0x7e &&
+	    kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_OUT_7E_INC_RIP)) {
+		vcpu->arch.complete_userspace_io =
+			complete_fast_pio_out_port_0x7e;
+		kvm_skip_emulated_instruction(vcpu);
+	} else {
 		vcpu->arch.pio.linear_rip = kvm_get_linear_rip(vcpu);
 		vcpu->arch.complete_userspace_io = complete_fast_pio_out;
 	}
-	return ret;
+	return 0;
 }
 
 static int complete_fast_pio_in(struct kvm_vcpu *vcpu)
@@ -7441,9 +7462,9 @@ static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, char *buf)
 	put_smstate(u32, buf, 0x7ef8, vcpu->arch.smbase);
 }
 
+#ifdef CONFIG_X86_64
 static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf)
 {
-#ifdef CONFIG_X86_64
 	struct desc_ptr dt;
 	struct kvm_segment seg;
 	unsigned long val;
@@ -7493,10 +7514,8 @@ static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf)
 
 	for (i = 0; i < 6; i++)
 		enter_smm_save_seg_64(vcpu, buf, i);
-#else
-	WARN_ON_ONCE(1);
-#endif
 }
+#endif
 
 static void enter_smm(struct kvm_vcpu *vcpu)
 {
@@ -7507,9 +7526,11 @@ static void enter_smm(struct kvm_vcpu *vcpu)
 
 	trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, true);
 	memset(buf, 0, 512);
+#ifdef CONFIG_X86_64
 	if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
 		enter_smm_save_state_64(vcpu, buf);
 	else
+#endif
 		enter_smm_save_state_32(vcpu, buf);
 
 	/*
@@ -7567,8 +7588,10 @@ static void enter_smm(struct kvm_vcpu *vcpu)
 	kvm_set_segment(vcpu, &ds, VCPU_SREG_GS);
 	kvm_set_segment(vcpu, &ds, VCPU_SREG_SS);
 
+#ifdef CONFIG_X86_64
 	if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
 		kvm_x86_ops->set_efer(vcpu, 0);
+#endif
 
 	kvm_update_cpuid(vcpu);
 	kvm_mmu_reset_context(vcpu);
@@ -7865,18 +7888,21 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		goto cancel_injection;
 	}
 
-	kvm_load_guest_xcr0(vcpu);
-
 	if (req_immediate_exit) {
 		kvm_make_request(KVM_REQ_EVENT, vcpu);
 		kvm_x86_ops->request_immediate_exit(vcpu);
 	}
 
 	trace_kvm_entry(vcpu->vcpu_id);
-	if (lapic_timer_advance_ns)
+	if (lapic_in_kernel(vcpu) &&
+	    vcpu->arch.apic->lapic_timer.timer_advance_ns)
 		wait_lapic_expire(vcpu);
 	guest_enter_irqoff();
 
+	fpregs_assert_state_consistent();
+	if (test_thread_flag(TIF_NEED_FPU_LOAD))
+		switch_fpu_return();
+
 	if (unlikely(vcpu->arch.switch_db_regs)) {
 		set_debugreg(0, 7);
 		set_debugreg(vcpu->arch.eff_db[0], 0);
@@ -7919,8 +7945,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	vcpu->mode = OUTSIDE_GUEST_MODE;
 	smp_wmb();
 
-	kvm_put_guest_xcr0(vcpu);
-
 	kvm_before_interrupt(vcpu);
 	kvm_x86_ops->handle_external_intr(vcpu);
 	kvm_after_interrupt(vcpu);
@@ -8137,22 +8161,30 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
 /* Swap (qemu) user FPU context for the guest FPU context. */
 static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 {
-	preempt_disable();
+	fpregs_lock();
+
 	copy_fpregs_to_fpstate(&current->thread.fpu);
 	/* PKRU is separately restored in kvm_x86_ops->run.  */
 	__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu->state,
 				~XFEATURE_MASK_PKRU);
-	preempt_enable();
+
+	fpregs_mark_activate();
+	fpregs_unlock();
+
 	trace_kvm_fpu(1);
 }
 
 /* When vcpu_run ends, restore user space FPU context. */
 static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 {
-	preempt_disable();
+	fpregs_lock();
+
 	copy_fpregs_to_fpstate(vcpu->arch.guest_fpu);
 	copy_kernel_to_fpregs(&current->thread.fpu.state);
-	preempt_enable();
+
+	fpregs_mark_activate();
+	fpregs_unlock();
+
 	++vcpu->stat.fpu_reload;
 	trace_kvm_fpu(0);
 }
@@ -8850,11 +8882,11 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 		if (init_event)
 			kvm_put_guest_fpu(vcpu);
 		mpx_state_buffer = get_xsave_addr(&vcpu->arch.guest_fpu->state.xsave,
-					XFEATURE_MASK_BNDREGS);
+					XFEATURE_BNDREGS);
 		if (mpx_state_buffer)
 			memset(mpx_state_buffer, 0, sizeof(struct mpx_bndreg_state));
 		mpx_state_buffer = get_xsave_addr(&vcpu->arch.guest_fpu->state.xsave,
-					XFEATURE_MASK_BNDCSR);
+					XFEATURE_BNDCSR);
 		if (mpx_state_buffer)
 			memset(mpx_state_buffer, 0, sizeof(struct mpx_bndcsr));
 		if (init_event)
@@ -9063,7 +9095,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 
 	if (irqchip_in_kernel(vcpu->kvm)) {
 		vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(vcpu);
-		r = kvm_create_lapic(vcpu);
+		r = kvm_create_lapic(vcpu, lapic_timer_advance_ns);
 		if (r < 0)
 			goto fail_mmu_destroy;
 	} else