Merge tag 'kvm-3.15-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm updates from Paolo Bonzini:
 "PPC and ARM do not have much going on this time.  Most of the cool
  stuff, instead, is in s390 and (after a few releases) x86.

  ARM has some caching fixes and PPC has transactional memory support in
  guests.  MIPS has some fixes, with more probably coming in 3.16 as
  QEMU will soon get support for MIPS KVM.

  For x86 there are optimizations for debug registers, which trigger on
  some Windows games, and other important fixes for Windows guests.  We
  now expose to the guest Broadwell instruction set extensions and also
  Intel MPX.  There's also a fix/workaround for OS X guests, nested
  virtualization features (preemption timer), and a couple kvmclock
  refinements.

  For s390, the main news is asynchronous page faults, together with
  improvements to IRQs (floating irqs and adapter irqs) that speed up
  virtio devices"

* tag 'kvm-3.15-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (96 commits)
  KVM: PPC: Book3S HV: Save/restore host PMU registers that are new in POWER8
  KVM: PPC: Book3S HV: Fix decrementer timeouts with non-zero TB offset
  KVM: PPC: Book3S HV: Don't use kvm_memslots() in real mode
  KVM: PPC: Book3S HV: Return ENODEV error rather than EIO
  KVM: PPC: Book3S: Trim top 4 bits of physical address in RTAS code
  KVM: PPC: Book3S HV: Add get/set_one_reg for new TM state
  KVM: PPC: Book3S HV: Add transactional memory support
  KVM: Specify byte order for KVM_EXIT_MMIO
  KVM: vmx: fix MPX detection
  KVM: PPC: Book3S HV: Fix KVM hang with CONFIG_KVM_XICS=n
  KVM: PPC: Book3S: Introduce hypervisor call H_GET_TCE
  KVM: PPC: Book3S HV: Fix incorrect userspace exit on ioeventfd write
  KVM: s390: clear local interrupts at cpu initial reset
  KVM: s390: Fix possible memory leak in SIGP functions
  KVM: s390: fix calculation of idle_mask array size
  KVM: s390: randomize sca address
  KVM: ioapic: reinject pending interrupts on KVM_SET_IRQCHIP
  KVM: Bump KVM_MAX_IRQ_ROUTES for s390
  KVM: s390: irq routing for adapter interrupts.
  KVM: s390: adapter interrupt sources
  ...

1 files changed, 119 insertions, 26 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 2b8578432d5b..d1c55f8722c6 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -595,13 +595,13 @@ static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
 
 int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 {
-	u64 xcr0;
+	u64 xcr0 = xcr;
+	u64 old_xcr0 = vcpu->arch.xcr0;
 	u64 valid_bits;
 
 	/* Only support XCR_XFEATURE_ENABLED_MASK(xcr0) now  */
 	if (index != XCR_XFEATURE_ENABLED_MASK)
 		return 1;
-	xcr0 = xcr;
 	if (!(xcr0 & XSTATE_FP))
 		return 1;
 	if ((xcr0 & XSTATE_YMM) && !(xcr0 & XSTATE_SSE))
@@ -616,8 +616,14 @@ int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 	if (xcr0 & ~valid_bits)
 		return 1;
 
+	if ((!(xcr0 & XSTATE_BNDREGS)) != (!(xcr0 & XSTATE_BNDCSR)))
+		return 1;
+
 	kvm_put_guest_xcr0(vcpu);
 	vcpu->arch.xcr0 = xcr0;
+
+	if ((xcr0 ^ old_xcr0) & XSTATE_EXTEND_MASK)
+		kvm_update_cpuid(vcpu);
 	return 0;
 }
 
@@ -753,7 +759,9 @@ static void kvm_update_dr7(struct kvm_vcpu *vcpu)
 	else
 		dr7 = vcpu->arch.dr7;
 	kvm_x86_ops->set_dr7(vcpu, dr7);
-	vcpu->arch.switch_db_regs = (dr7 & DR7_BP_EN_MASK);
+	vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_BP_ENABLED;
+	if (dr7 & DR7_BP_EN_MASK)
+		vcpu->arch.switch_db_regs |= KVM_DEBUGREG_BP_ENABLED;
 }
 
 static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val)
@@ -879,7 +887,7 @@ static u32 msrs_to_save[] = {
 	MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR,
 #endif
 	MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA,
-	MSR_IA32_FEATURE_CONTROL
+	MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS
 };
 
 static unsigned num_msrs_to_save;
@@ -1581,7 +1589,6 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 	/* 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;
-	vcpu->last_kernel_ns = kernel_ns;
 	vcpu->last_guest_tsc = tsc_timestamp;
 
 	/*
@@ -1623,14 +1630,21 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
  * the others.
  *
  * So in those cases, request a kvmclock update for all vcpus.
- * The worst case for a remote vcpu to update its kvmclock
- * is then bounded by maximum nohz sleep latency.
+ * We need to rate-limit these requests though, as they can
+ * considerably slow guests that have a large number of vcpus.
+ * The time for a remote vcpu to update its kvmclock is bound
+ * by the delay we use to rate-limit the updates.
  */
 
-static void kvm_gen_kvmclock_update(struct kvm_vcpu *v)
+#define KVMCLOCK_UPDATE_DELAY msecs_to_jiffies(100)
+
+static void kvmclock_update_fn(struct work_struct *work)
 {
 	int i;
-	struct kvm *kvm = v->kvm;
+	struct delayed_work *dwork = to_delayed_work(work);
+	struct kvm_arch *ka = container_of(dwork, struct kvm_arch,
+					   kvmclock_update_work);
+	struct kvm *kvm = container_of(ka, struct kvm, arch);
 	struct kvm_vcpu *vcpu;
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
@@ -1639,6 +1653,29 @@ static void kvm_gen_kvmclock_update(struct kvm_vcpu *v)
 	}
 }
 
+static void kvm_gen_kvmclock_update(struct kvm_vcpu *v)
+{
+	struct kvm *kvm = v->kvm;
+
+	set_bit(KVM_REQ_CLOCK_UPDATE, &v->requests);
+	schedule_delayed_work(&kvm->arch.kvmclock_update_work,
+					KVMCLOCK_UPDATE_DELAY);
+}
+
+#define KVMCLOCK_SYNC_PERIOD (300 * HZ)
+
+static void kvmclock_sync_fn(struct work_struct *work)
+{
+	struct delayed_work *dwork = to_delayed_work(work);
+	struct kvm_arch *ka = container_of(dwork, struct kvm_arch,
+					   kvmclock_sync_work);
+	struct kvm *kvm = container_of(ka, struct kvm, arch);
+
+	schedule_delayed_work(&kvm->arch.kvmclock_update_work, 0);
+	schedule_delayed_work(&kvm->arch.kvmclock_sync_work,
+					KVMCLOCK_SYNC_PERIOD);
+}
+
 static bool msr_mtrr_valid(unsigned msr)
 {
 	switch (msr) {
@@ -2323,9 +2360,12 @@ static int get_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	case HV_X64_MSR_VP_INDEX: {
 		int r;
 		struct kvm_vcpu *v;
-		kvm_for_each_vcpu(r, v, vcpu->kvm)
-			if (v == vcpu)
+		kvm_for_each_vcpu(r, v, vcpu->kvm) {
+			if (v == vcpu) {
 				data = r;
+				break;
+			}
+		}
 		break;
 	}
 	case HV_X64_MSR_EOI:
@@ -2617,6 +2657,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_KVMCLOCK_CTRL:
 	case KVM_CAP_READONLY_MEM:
 	case KVM_CAP_HYPERV_TIME:
+	case KVM_CAP_IOAPIC_POLARITY_IGNORED:
 #ifdef CONFIG_KVM_DEVICE_ASSIGNMENT
 	case KVM_CAP_ASSIGN_DEV_IRQ:
 	case KVM_CAP_PCI_2_3:
@@ -3043,9 +3084,7 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
 		 * CPUID leaf 0xD, index 0, EDX:EAX.  This is for compatibility
 		 * with old userspace.
 		 */
-		if (xstate_bv & ~KVM_SUPPORTED_XCR0)
-			return -EINVAL;
-		if (xstate_bv & ~host_xcr0)
+		if (xstate_bv & ~kvm_supported_xcr0())
 			return -EINVAL;
 		memcpy(&vcpu->arch.guest_fpu.state->xsave,
 			guest_xsave->region, vcpu->arch.guest_xstate_size);
@@ -3898,6 +3937,23 @@ static void kvm_init_msr_list(void)
 	for (i = j = KVM_SAVE_MSRS_BEGIN; i < ARRAY_SIZE(msrs_to_save); i++) {
 		if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0)
 			continue;
+
+		/*
+		 * Even MSRs that are valid in the host may not be exposed
+		 * to the guests in some cases.  We could work around this
+		 * in VMX with the generic MSR save/load machinery, but it
+		 * is not really worthwhile since it will really only
+		 * happen with nested virtualization.
+		 */
+		switch (msrs_to_save[i]) {
+		case MSR_IA32_BNDCFGS:
+			if (!kvm_x86_ops->mpx_supported())
+				continue;
+			break;
+		default:
+			break;
+		}
+
 		if (j < i)
 			msrs_to_save[j] = msrs_to_save[i];
 		j++;
@@ -4394,6 +4450,7 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt,
 	if (!exchanged)
 		return X86EMUL_CMPXCHG_FAILED;
 
+	mark_page_dirty(vcpu->kvm, gpa >> PAGE_SHIFT);
 	kvm_mmu_pte_write(vcpu, gpa, new, bytes);
 
 	return X86EMUL_CONTINUE;
@@ -5537,9 +5594,10 @@ int kvm_arch_init(void *opaque)
 		goto out_free_percpu;
 
 	kvm_set_mmio_spte_mask();
-	kvm_init_msr_list();
 
 	kvm_x86_ops = ops;
+	kvm_init_msr_list();
+
 	kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK,
 			PT_DIRTY_MASK, PT64_NX_MASK, 0);
 
@@ -5782,8 +5840,10 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu)
 	kvm_x86_ops->update_cr8_intercept(vcpu, tpr, max_irr);
 }
 
-static void inject_pending_event(struct kvm_vcpu *vcpu)
+static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
 {
+	int r;
+
 	/* try to reinject previous events if any */
 	if (vcpu->arch.exception.pending) {
 		trace_kvm_inj_exception(vcpu->arch.exception.nr,
@@ -5793,17 +5853,23 @@ static void inject_pending_event(struct kvm_vcpu *vcpu)
 					  vcpu->arch.exception.has_error_code,
 					  vcpu->arch.exception.error_code,
 					  vcpu->arch.exception.reinject);
-		return;
+		return 0;
 	}
 
 	if (vcpu->arch.nmi_injected) {
 		kvm_x86_ops->set_nmi(vcpu);
-		return;
+		return 0;
 	}
 
 	if (vcpu->arch.interrupt.pending) {
 		kvm_x86_ops->set_irq(vcpu);
-		return;
+		return 0;
+	}
+
+	if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) {
+		r = kvm_x86_ops->check_nested_events(vcpu, req_int_win);
+		if (r != 0)
+			return r;
 	}
 
 	/* try to inject new event if pending */
@@ -5820,6 +5886,7 @@ static void inject_pending_event(struct kvm_vcpu *vcpu)
 			kvm_x86_ops->set_irq(vcpu);
 		}
 	}
+	return 0;
 }
 
 static void process_nmi(struct kvm_vcpu *vcpu)
@@ -5924,15 +5991,13 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			goto out;
 		}
 
-		inject_pending_event(vcpu);
-
+		if (inject_pending_event(vcpu, req_int_win) != 0)
+			req_immediate_exit = true;
 		/* enable NMI/IRQ window open exits if needed */
-		if (vcpu->arch.nmi_pending)
-			req_immediate_exit =
-				kvm_x86_ops->enable_nmi_window(vcpu) != 0;
+		else if (vcpu->arch.nmi_pending)
+			kvm_x86_ops->enable_nmi_window(vcpu);
 		else if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win)
-			req_immediate_exit =
-				kvm_x86_ops->enable_irq_window(vcpu) != 0;
+			kvm_x86_ops->enable_irq_window(vcpu);
 
 		if (kvm_lapic_enabled(vcpu)) {
 			/*
@@ -5992,12 +6057,28 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		set_debugreg(vcpu->arch.eff_db[1], 1);
 		set_debugreg(vcpu->arch.eff_db[2], 2);
 		set_debugreg(vcpu->arch.eff_db[3], 3);
+		set_debugreg(vcpu->arch.dr6, 6);
 	}
 
 	trace_kvm_entry(vcpu->vcpu_id);
 	kvm_x86_ops->run(vcpu);
 
 	/*
+	 * Do this here before restoring debug registers on the host.  And
+	 * since we do this before handling the vmexit, a DR access vmexit
+	 * can (a) read the correct value of the debug registers, (b) set
+	 * KVM_DEBUGREG_WONT_EXIT again.
+	 */
+	if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) {
+		int i;
+
+		WARN_ON(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP);
+		kvm_x86_ops->sync_dirty_debug_regs(vcpu);
+		for (i = 0; i < KVM_NR_DB_REGS; i++)
+			vcpu->arch.eff_db[i] = vcpu->arch.db[i];
+	}
+
+	/*
 	 * If the guest has used debug registers, at least dr7
 	 * will be disabled while returning to the host.
 	 * If we don't have active breakpoints in the host, we don't
@@ -6711,6 +6792,7 @@ int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 {
 	int r;
 	struct msr_data msr;
+	struct kvm *kvm = vcpu->kvm;
 
 	r = vcpu_load(vcpu);
 	if (r)
@@ -6721,6 +6803,9 @@ int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 	kvm_write_tsc(vcpu, &msr);
 	vcpu_put(vcpu);
 
+	schedule_delayed_work(&kvm->arch.kvmclock_sync_work,
+					KVMCLOCK_SYNC_PERIOD);
+
 	return r;
 }
 
@@ -7013,6 +7098,9 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 
 	pvclock_update_vm_gtod_copy(kvm);
 
+	INIT_DELAYED_WORK(&kvm->arch.kvmclock_update_work, kvmclock_update_fn);
+	INIT_DELAYED_WORK(&kvm->arch.kvmclock_sync_work, kvmclock_sync_fn);
+
 	return 0;
 }
 
@@ -7050,6 +7138,8 @@ static void kvm_free_vcpus(struct kvm *kvm)
 
 void kvm_arch_sync_events(struct kvm *kvm)
 {
+	cancel_delayed_work_sync(&kvm->arch.kvmclock_sync_work);
+	cancel_delayed_work_sync(&kvm->arch.kvmclock_update_work);
 	kvm_free_all_assigned_devices(kvm);
 	kvm_free_pit(kvm);
 }
@@ -7248,6 +7338,9 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 {
+	if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events)
+		kvm_x86_ops->check_nested_events(vcpu, false);
+
 	return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE &&
 		!vcpu->arch.apf.halted)
 		|| !list_empty_careful(&vcpu->async_pf.done)