1 files changed, 119 insertions, 44 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 04c5d96b1d67..51ccfe08e32f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -434,12 +434,14 @@ void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr)
 }
 EXPORT_SYMBOL_GPL(kvm_requeue_exception);
 
-void kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err)
+int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err)
 {
 	if (err)
 		kvm_inject_gp(vcpu, 0);
 	else
-		kvm_x86_ops->skip_emulated_instruction(vcpu);
+		return kvm_skip_emulated_instruction(vcpu);
+
+	return 1;
 }
 EXPORT_SYMBOL_GPL(kvm_complete_insn_gp);
 
@@ -573,7 +575,7 @@ out:
 }
 EXPORT_SYMBOL_GPL(load_pdptrs);
 
-static bool pdptrs_changed(struct kvm_vcpu *vcpu)
+bool pdptrs_changed(struct kvm_vcpu *vcpu)
 {
 	u64 pdpte[ARRAY_SIZE(vcpu->arch.walk_mmu->pdptrs)];
 	bool changed = true;
@@ -599,6 +601,7 @@ out:
 
 	return changed;
 }
+EXPORT_SYMBOL_GPL(pdptrs_changed);
 
 int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 {
@@ -1128,8 +1131,8 @@ struct pvclock_gtod_data {
 
 	struct { /* extract of a clocksource struct */
 		int vclock_mode;
-		cycle_t	cycle_last;
-		cycle_t	mask;
+		u64	cycle_last;
+		u64	mask;
 		u32	mult;
 		u32	shift;
 	} clock;
@@ -1569,9 +1572,9 @@ static inline void adjust_tsc_offset_host(struct kvm_vcpu *vcpu, s64 adjustment)
 
 #ifdef CONFIG_X86_64
 
-static cycle_t read_tsc(void)
+static u64 read_tsc(void)
 {
-	cycle_t ret = (cycle_t)rdtsc_ordered();
+	u64 ret = (u64)rdtsc_ordered();
 	u64 last = pvclock_gtod_data.clock.cycle_last;
 
 	if (likely(ret >= last))
@@ -1589,7 +1592,7 @@ static cycle_t read_tsc(void)
 	return last;
 }
 
-static inline u64 vgettsc(cycle_t *cycle_now)
+static inline u64 vgettsc(u64 *cycle_now)
 {
 	long v;
 	struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
@@ -1600,7 +1603,7 @@ static inline u64 vgettsc(cycle_t *cycle_now)
 	return v * gtod->clock.mult;
 }
 
-static int do_monotonic_boot(s64 *t, cycle_t *cycle_now)
+static int do_monotonic_boot(s64 *t, u64 *cycle_now)
 {
 	struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
 	unsigned long seq;
@@ -1621,7 +1624,7 @@ static int do_monotonic_boot(s64 *t, cycle_t *cycle_now)
 }
 
 /* returns true if host is using tsc clocksource */
-static bool kvm_get_time_and_clockread(s64 *kernel_ns, cycle_t *cycle_now)
+static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *cycle_now)
 {
 	/* checked again under seqlock below */
 	if (pvclock_gtod_data.clock.vclock_mode != VCLOCK_TSC)
@@ -2071,6 +2074,8 @@ static void record_steal_time(struct kvm_vcpu *vcpu)
 		&vcpu->arch.st.steal, sizeof(struct kvm_steal_time))))
 		return;
 
+	vcpu->arch.st.steal.preempted = 0;
+
 	if (vcpu->arch.st.steal.version & 1)
 		vcpu->arch.st.steal.version += 1;  /* first time write, random junk */
 
@@ -2176,7 +2181,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		break;
 	case MSR_KVM_SYSTEM_TIME_NEW:
 	case MSR_KVM_SYSTEM_TIME: {
-		u64 gpa_offset;
 		struct kvm_arch *ka = &vcpu->kvm->arch;
 
 		kvmclock_reset(vcpu);
@@ -2198,8 +2202,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (!(data & 1))
 			break;
 
-		gpa_offset = data & ~(PAGE_MASK | 1);
-
 		if (kvm_gfn_to_hva_cache_init(vcpu->kvm,
 		     &vcpu->arch.pv_time, data & ~1ULL,
 		     sizeof(struct pvclock_vcpu_time_info)))
@@ -2294,7 +2296,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (kvm_pmu_is_valid_msr(vcpu, msr))
 			return kvm_pmu_set_msr(vcpu, msr_info);
 		if (!ignore_msrs) {
-			vcpu_unimpl(vcpu, "unhandled wrmsr: 0x%x data 0x%llx\n",
+			vcpu_debug_ratelimited(vcpu, "unhandled wrmsr: 0x%x data 0x%llx\n",
 				    msr, data);
 			return 1;
 		} else {
@@ -2506,7 +2508,8 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (kvm_pmu_is_valid_msr(vcpu, msr_info->index))
 			return kvm_pmu_get_msr(vcpu, msr_info->index, &msr_info->data);
 		if (!ignore_msrs) {
-			vcpu_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr_info->index);
+			vcpu_debug_ratelimited(vcpu, "unhandled rdmsr: 0x%x\n",
+					       msr_info->index);
 			return 1;
 		} else {
 			vcpu_unimpl(vcpu, "ignored rdmsr: 0x%x\n", msr_info->index);
@@ -2810,7 +2813,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		}
 		if (kvm_lapic_hv_timer_in_use(vcpu) &&
 				kvm_x86_ops->set_hv_timer(vcpu,
-					kvm_get_lapic_tscdeadline_msr(vcpu)))
+					kvm_get_lapic_target_expiration_tsc(vcpu)))
 			kvm_lapic_switch_to_sw_timer(vcpu);
 		/*
 		 * On a host with synchronized TSC, there is no need to update
@@ -2826,8 +2829,39 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu);
 }
 
+static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu)
+{
+	if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
+		return;
+
+	vcpu->arch.st.steal.preempted = 1;
+
+	kvm_write_guest_offset_cached(vcpu->kvm, &vcpu->arch.st.stime,
+			&vcpu->arch.st.steal.preempted,
+			offsetof(struct kvm_steal_time, preempted),
+			sizeof(vcpu->arch.st.steal.preempted));
+}
+
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
+	int idx;
+	/*
+	 * Disable page faults because we're in atomic context here.
+	 * kvm_write_guest_offset_cached() would call might_fault()
+	 * that relies on pagefault_disable() to tell if there's a
+	 * bug. NOTE: the write to guest memory may not go through if
+	 * during postcopy live migration or if there's heavy guest
+	 * paging.
+	 */
+	pagefault_disable();
+	/*
+	 * kvm_memslots() will be called by
+	 * kvm_write_guest_offset_cached() so take the srcu lock.
+	 */
+	idx = srcu_read_lock(&vcpu->kvm->srcu);
+	kvm_steal_time_set_preempted(vcpu);
+	srcu_read_unlock(&vcpu->kvm->srcu, idx);
+	pagefault_enable();
 	kvm_x86_ops->vcpu_put(vcpu);
 	kvm_put_guest_fpu(vcpu);
 	vcpu->arch.last_host_tsc = rdtsc();
@@ -4816,7 +4850,7 @@ static void emulator_invlpg(struct x86_emulate_ctxt *ctxt, ulong address)
 	kvm_mmu_invlpg(emul_to_vcpu(ctxt), address);
 }
 
-int kvm_emulate_wbinvd_noskip(struct kvm_vcpu *vcpu)
+static int kvm_emulate_wbinvd_noskip(struct kvm_vcpu *vcpu)
 {
 	if (!need_emulate_wbinvd(vcpu))
 		return X86EMUL_CONTINUE;
@@ -4836,8 +4870,8 @@ int kvm_emulate_wbinvd_noskip(struct kvm_vcpu *vcpu)
 
 int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu)
 {
-	kvm_x86_ops->skip_emulated_instruction(vcpu);
-	return kvm_emulate_wbinvd_noskip(vcpu);
+	kvm_emulate_wbinvd_noskip(vcpu);
+	return kvm_skip_emulated_instruction(vcpu);
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_wbinvd);
 
@@ -5081,11 +5115,6 @@ static void emulator_get_fpu(struct x86_emulate_ctxt *ctxt)
 {
 	preempt_disable();
 	kvm_load_guest_fpu(emul_to_vcpu(ctxt));
-	/*
-	 * CR0.TS may reference the host fpu state, not the guest fpu state,
-	 * so it may be clear at this point.
-	 */
-	clts();
 }
 
 static void emulator_put_fpu(struct x86_emulate_ctxt *ctxt)
@@ -5440,7 +5469,6 @@ static void kvm_vcpu_check_singlestep(struct kvm_vcpu *vcpu, unsigned long rflag
 			kvm_run->exit_reason = KVM_EXIT_DEBUG;
 			*r = EMULATE_USER_EXIT;
 		} else {
-			vcpu->arch.emulate_ctxt.eflags &= ~X86_EFLAGS_TF;
 			/*
 			 * "Certain debug exceptions may clear bit 0-3.  The
 			 * remaining contents of the DR6 register are never
@@ -5453,6 +5481,17 @@ static void kvm_vcpu_check_singlestep(struct kvm_vcpu *vcpu, unsigned long rflag
 	}
 }
 
+int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu)
+{
+	unsigned long rflags = kvm_x86_ops->get_rflags(vcpu);
+	int r = EMULATE_DONE;
+
+	kvm_x86_ops->skip_emulated_instruction(vcpu);
+	kvm_vcpu_check_singlestep(vcpu, rflags, &r);
+	return r == EMULATE_DONE;
+}
+EXPORT_SYMBOL_GPL(kvm_skip_emulated_instruction);
+
 static bool kvm_vcpu_check_breakpoint(struct kvm_vcpu *vcpu, int *r)
 {
 	if (unlikely(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) &&
@@ -5638,6 +5677,49 @@ int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port)
 }
 EXPORT_SYMBOL_GPL(kvm_fast_pio_out);
 
+static int complete_fast_pio_in(struct kvm_vcpu *vcpu)
+{
+	unsigned long val;
+
+	/* We should only ever be called with arch.pio.count equal to 1 */
+	BUG_ON(vcpu->arch.pio.count != 1);
+
+	/* For size less than 4 we merge, else we zero extend */
+	val = (vcpu->arch.pio.size < 4) ? kvm_register_read(vcpu, VCPU_REGS_RAX)
+					: 0;
+
+	/*
+	 * Since vcpu->arch.pio.count == 1 let emulator_pio_in_emulated perform
+	 * the copy and tracing
+	 */
+	emulator_pio_in_emulated(&vcpu->arch.emulate_ctxt, vcpu->arch.pio.size,
+				 vcpu->arch.pio.port, &val, 1);
+	kvm_register_write(vcpu, VCPU_REGS_RAX, val);
+
+	return 1;
+}
+
+int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size, unsigned short port)
+{
+	unsigned long val;
+	int ret;
+
+	/* For size less than 4 we merge, else we zero extend */
+	val = (size < 4) ? kvm_register_read(vcpu, VCPU_REGS_RAX) : 0;
+
+	ret = emulator_pio_in_emulated(&vcpu->arch.emulate_ctxt, size, port,
+				       &val, 1);
+	if (ret) {
+		kvm_register_write(vcpu, VCPU_REGS_RAX, val);
+		return ret;
+	}
+
+	vcpu->arch.complete_userspace_io = complete_fast_pio_in;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_fast_pio_in);
+
 static int kvmclock_cpu_down_prep(unsigned int cpu)
 {
 	__this_cpu_write(cpu_tsc_khz, 0);
@@ -5773,7 +5855,7 @@ static void kvm_timer_init(void)
 	}
 	pr_debug("kvm: max_tsc_khz = %ld\n", max_tsc_khz);
 
-	cpuhp_setup_state(CPUHP_AP_X86_KVM_CLK_ONLINE, "AP_X86_KVM_CLK_ONLINE",
+	cpuhp_setup_state(CPUHP_AP_X86_KVM_CLK_ONLINE, "x86/kvm/clk:online",
 			  kvmclock_cpu_online, kvmclock_cpu_down_prep);
 }
 
@@ -5987,8 +6069,12 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_halt);
 
 int kvm_emulate_halt(struct kvm_vcpu *vcpu)
 {
-	kvm_x86_ops->skip_emulated_instruction(vcpu);
-	return kvm_vcpu_halt(vcpu);
+	int ret = kvm_skip_emulated_instruction(vcpu);
+	/*
+	 * TODO: we might be squashing a GUESTDBG_SINGLESTEP-triggered
+	 * KVM_EXIT_DEBUG here.
+	 */
+	return kvm_vcpu_halt(vcpu) && ret;
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_halt);
 
@@ -6019,9 +6105,9 @@ void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu)
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 {
 	unsigned long nr, a0, a1, a2, a3, ret;
-	int op_64_bit, r = 1;
+	int op_64_bit, r;
 
-	kvm_x86_ops->skip_emulated_instruction(vcpu);
+	r = kvm_skip_emulated_instruction(vcpu);
 
 	if (kvm_hv_hypercall_enabled(vcpu->kvm))
 		return kvm_hv_hypercall(vcpu);
@@ -7407,25 +7493,13 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 
 void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 {
-	if (!vcpu->guest_fpu_loaded) {
-		vcpu->fpu_counter = 0;
+	if (!vcpu->guest_fpu_loaded)
 		return;
-	}
 
 	vcpu->guest_fpu_loaded = 0;
 	copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu);
 	__kernel_fpu_end();
 	++vcpu->stat.fpu_reload;
-	/*
-	 * If using eager FPU mode, or if the guest is a frequent user
-	 * of the FPU, just leave the FPU active for next time.
-	 * Every 255 times fpu_counter rolls over to 0; a guest that uses
-	 * the FPU in bursts will revert to loading it on demand.
-	 */
-	if (!use_eager_fpu()) {
-		if (++vcpu->fpu_counter < 5)
-			kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu);
-	}
 	trace_kvm_fpu(0);
 }
 
@@ -7824,6 +7898,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 
 	raw_spin_lock_init(&kvm->arch.tsc_write_lock);
 	mutex_init(&kvm->arch.apic_map_lock);
+	mutex_init(&kvm->arch.hyperv.hv_lock);
 	spin_lock_init(&kvm->arch.pvclock_gtod_sync_lock);
 
 	kvm->arch.kvmclock_offset = -ktime_get_boot_ns();
@@ -8176,7 +8251,7 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm)
 void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 				   struct kvm_memory_slot *slot)
 {
-	kvm_mmu_invalidate_zap_all_pages(kvm);
+	kvm_page_track_flush_slot(kvm, slot);
 }
 
 static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)