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

Pull KVM updates from Paolo Bonzini:
 "First round of KVM updates for 3.14; PPC parts will come next week.

  Nothing major here, just bugfixes all over the place.  The most
  interesting part is the ARM guys' virtualized interrupt controller
  overhaul, which lets userspace get/set the state and thus enables
  migration of ARM VMs"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (67 commits)
  kvm: make KVM_MMU_AUDIT help text more readable
  KVM: s390: Fix memory access error detection
  KVM: nVMX: Update guest activity state field on L2 exits
  KVM: nVMX: Fix nested_run_pending on activity state HLT
  KVM: nVMX: Clean up handling of VMX-related MSRs
  KVM: nVMX: Add tracepoints for nested_vmexit and nested_vmexit_inject
  KVM: nVMX: Pass vmexit parameters to nested_vmx_vmexit
  KVM: nVMX: Leave VMX mode on clearing of feature control MSR
  KVM: VMX: Fix DR6 update on #DB exception
  KVM: SVM: Fix reading of DR6
  KVM: x86: Sync DR7 on KVM_SET_DEBUGREGS
  add support for Hyper-V reference time counter
  KVM: remove useless write to vcpu->hv_clock.tsc_timestamp
  KVM: x86: fix tsc catchup issue with tsc scaling
  KVM: x86: limit PIT timer frequency
  KVM: x86: handle invalid root_hpa everywhere
  kvm: Provide kvm_vcpu_eligible_for_directed_yield() stub
  kvm: vfio: silence GCC warning
  KVM: ARM: Remove duplicate include
  arm/arm64: KVM: relax the requirements of VMA alignment for THP
  ...

1 files changed, 55 insertions, 46 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 5d004da1e35d..0c76f7cfdb32 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -94,6 +94,9 @@ EXPORT_SYMBOL_GPL(kvm_x86_ops);
 static bool ignore_msrs = 0;
 module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR);
 
+unsigned int min_timer_period_us = 500;
+module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR);
+
 bool kvm_has_tsc_control;
 EXPORT_SYMBOL_GPL(kvm_has_tsc_control);
 u32  kvm_max_guest_tsc_khz;
@@ -719,6 +722,12 @@ unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_get_cr8);
 
+static void kvm_update_dr6(struct kvm_vcpu *vcpu)
+{
+	if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP))
+		kvm_x86_ops->set_dr6(vcpu, vcpu->arch.dr6);
+}
+
 static void kvm_update_dr7(struct kvm_vcpu *vcpu)
 {
 	unsigned long dr7;
@@ -747,6 +756,7 @@ static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val)
 		if (val & 0xffffffff00000000ULL)
 			return -1; /* #GP */
 		vcpu->arch.dr6 = (val & DR6_VOLATILE) | DR6_FIXED_1;
+		kvm_update_dr6(vcpu);
 		break;
 	case 5:
 		if (kvm_read_cr4_bits(vcpu, X86_CR4_DE))
@@ -788,7 +798,10 @@ static int _kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val)
 			return 1;
 		/* fall through */
 	case 6:
-		*val = vcpu->arch.dr6;
+		if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
+			*val = vcpu->arch.dr6;
+		else
+			*val = kvm_x86_ops->get_dr6(vcpu);
 		break;
 	case 5:
 		if (kvm_read_cr4_bits(vcpu, X86_CR4_DE))
@@ -836,11 +849,12 @@ EXPORT_SYMBOL_GPL(kvm_rdpmc);
  * kvm-specific. Those are put in the beginning of the list.
  */
 
-#define KVM_SAVE_MSRS_BEGIN	10
+#define KVM_SAVE_MSRS_BEGIN	12
 static u32 msrs_to_save[] = {
 	MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
 	MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW,
 	HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,
+	HV_X64_MSR_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC,
 	HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME,
 	MSR_KVM_PV_EOI_EN,
 	MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
@@ -1275,8 +1289,6 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	kvm->arch.last_tsc_write = data;
 	kvm->arch.last_tsc_khz = vcpu->arch.virtual_tsc_khz;
 
-	/* Reset of TSC must disable overshoot protection below */
-	vcpu->arch.hv_clock.tsc_timestamp = 0;
 	vcpu->arch.last_guest_tsc = data;
 
 	/* Keep track of which generation this VCPU has synchronized to */
@@ -1484,7 +1496,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 	unsigned long flags, this_tsc_khz;
 	struct kvm_vcpu_arch *vcpu = &v->arch;
 	struct kvm_arch *ka = &v->kvm->arch;
-	s64 kernel_ns, max_kernel_ns;
+	s64 kernel_ns;
 	u64 tsc_timestamp, host_tsc;
 	struct pvclock_vcpu_time_info guest_hv_clock;
 	u8 pvclock_flags;
@@ -1543,37 +1555,6 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 	if (!vcpu->pv_time_enabled)
 		return 0;
 
-	/*
-	 * Time as measured by the TSC may go backwards when resetting the base
-	 * tsc_timestamp.  The reason for this is that the TSC resolution is
-	 * higher than the resolution of the other clock scales.  Thus, many
-	 * possible measurments of the TSC correspond to one measurement of any
-	 * other clock, and so a spread of values is possible.  This is not a
-	 * problem for the computation of the nanosecond clock; with TSC rates
-	 * around 1GHZ, there can only be a few cycles which correspond to one
-	 * nanosecond value, and any path through this code will inevitably
-	 * take longer than that.  However, with the kernel_ns value itself,
-	 * the precision may be much lower, down to HZ granularity.  If the
-	 * first sampling of TSC against kernel_ns ends in the low part of the
-	 * range, and the second in the high end of the range, we can get:
-	 *
-	 * (TSC - offset_low) * S + kns_old > (TSC - offset_high) * S + kns_new
-	 *
-	 * As the sampling errors potentially range in the thousands of cycles,
-	 * it is possible such a time value has already been observed by the
-	 * guest.  To protect against this, we must compute the system time as
-	 * observed by the guest and ensure the new system time is greater.
-	 */
-	max_kernel_ns = 0;
-	if (vcpu->hv_clock.tsc_timestamp) {
-		max_kernel_ns = vcpu->last_guest_tsc -
-				vcpu->hv_clock.tsc_timestamp;
-		max_kernel_ns = pvclock_scale_delta(max_kernel_ns,
-				    vcpu->hv_clock.tsc_to_system_mul,
-				    vcpu->hv_clock.tsc_shift);
-		max_kernel_ns += vcpu->last_kernel_ns;
-	}
-
 	if (unlikely(vcpu->hw_tsc_khz != this_tsc_khz)) {
 		kvm_get_time_scale(NSEC_PER_SEC / 1000, this_tsc_khz,
 				   &vcpu->hv_clock.tsc_shift,
@@ -1581,14 +1562,6 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 		vcpu->hw_tsc_khz = this_tsc_khz;
 	}
 
-	/* with a master <monotonic time, tsc value> tuple,
-	 * pvclock clock reads always increase at the (scaled) rate
-	 * of guest TSC - no need to deal with sampling errors.
-	 */
-	if (!use_master_clock) {
-		if (max_kernel_ns > kernel_ns)
-			kernel_ns = max_kernel_ns;
-	}
 	/* With all the info we got, fill in the values */
 	vcpu->hv_clock.tsc_timestamp = tsc_timestamp;
 	vcpu->hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset;
@@ -1826,6 +1799,8 @@ static bool kvm_hv_msr_partition_wide(u32 msr)
 	switch (msr) {
 	case HV_X64_MSR_GUEST_OS_ID:
 	case HV_X64_MSR_HYPERCALL:
+	case HV_X64_MSR_REFERENCE_TSC:
+	case HV_X64_MSR_TIME_REF_COUNT:
 		r = true;
 		break;
 	}
@@ -1867,6 +1842,20 @@ static int set_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 		kvm->arch.hv_hypercall = data;
 		break;
 	}
+	case HV_X64_MSR_REFERENCE_TSC: {
+		u64 gfn;
+		HV_REFERENCE_TSC_PAGE tsc_ref;
+		memset(&tsc_ref, 0, sizeof(tsc_ref));
+		kvm->arch.hv_tsc_page = data;
+		if (!(data & HV_X64_MSR_TSC_REFERENCE_ENABLE))
+			break;
+		gfn = data >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT;
+		if (kvm_write_guest(kvm, data,
+			&tsc_ref, sizeof(tsc_ref)))
+			return 1;
+		mark_page_dirty(kvm, gfn);
+		break;
+	}
 	default:
 		vcpu_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x "
 			    "data 0x%llx\n", msr, data);
@@ -2291,6 +2280,14 @@ static int get_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	case HV_X64_MSR_HYPERCALL:
 		data = kvm->arch.hv_hypercall;
 		break;
+	case HV_X64_MSR_TIME_REF_COUNT: {
+		data =
+		     div_u64(get_kernel_ns() + kvm->arch.kvmclock_offset, 100);
+		break;
+	}
+	case HV_X64_MSR_REFERENCE_TSC:
+		data = kvm->arch.hv_tsc_page;
+		break;
 	default:
 		vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
 		return 1;
@@ -2604,6 +2601,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 #ifdef CONFIG_KVM_DEVICE_ASSIGNMENT
 	case KVM_CAP_ASSIGN_DEV_IRQ:
 	case KVM_CAP_PCI_2_3:
+	case KVM_CAP_HYPERV_TIME:
 #endif
 		r = 1;
 		break;
@@ -2972,8 +2970,11 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 static void kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu,
 					     struct kvm_debugregs *dbgregs)
 {
+	unsigned long val;
+
 	memcpy(dbgregs->db, vcpu->arch.db, sizeof(vcpu->arch.db));
-	dbgregs->dr6 = vcpu->arch.dr6;
+	_kvm_get_dr(vcpu, 6, &val);
+	dbgregs->dr6 = val;
 	dbgregs->dr7 = vcpu->arch.dr7;
 	dbgregs->flags = 0;
 	memset(&dbgregs->reserved, 0, sizeof(dbgregs->reserved));
@@ -2987,7 +2988,9 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
 
 	memcpy(vcpu->arch.db, dbgregs->db, sizeof(vcpu->arch.db));
 	vcpu->arch.dr6 = dbgregs->dr6;
+	kvm_update_dr6(vcpu);
 	vcpu->arch.dr7 = dbgregs->dr7;
+	kvm_update_dr7(vcpu);
 
 	return 0;
 }
@@ -5834,6 +5837,11 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
 	kvm_apic_update_tmr(vcpu, tmr);
 }
 
+/*
+ * Returns 1 to let __vcpu_run() continue the guest execution loop without
+ * exiting to the userspace.  Otherwise, the value will be returned to the
+ * userspace.
+ */
 static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 {
 	int r;
@@ -6089,7 +6097,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 		}
 		if (need_resched()) {
 			srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
-			kvm_resched(vcpu);
+			cond_resched();
 			vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
 		}
 	}
@@ -6717,6 +6725,7 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu)
 
 	memset(vcpu->arch.db, 0, sizeof(vcpu->arch.db));
 	vcpu->arch.dr6 = DR6_FIXED_1;
+	kvm_update_dr6(vcpu);
 	vcpu->arch.dr7 = DR7_FIXED_1;
 	kvm_update_dr7(vcpu);