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

Pull KVM updates from Paolo Bonzini:
 "First batch of KVM changes for 4.4.

  s390:
     A bunch of fixes and optimizations for interrupt and time handling.

  PPC:
     Mostly bug fixes.

  ARM:
     No big features, but many small fixes and prerequisites including:

      - a number of fixes for the arch-timer

      - introducing proper level-triggered semantics for the arch-timers

      - a series of patches to synchronously halt a guest (prerequisite
        for IRQ forwarding)

      - some tracepoint improvements

      - a tweak for the EL2 panic handlers

      - some more VGIC cleanups getting rid of redundant state

  x86:
     Quite a few changes:

      - support for VT-d posted interrupts (i.e. PCI devices can inject
        interrupts directly into vCPUs).  This introduces a new
        component (in virt/lib/) that connects VFIO and KVM together.
        The same infrastructure will be used for ARM interrupt
        forwarding as well.

      - more Hyper-V features, though the main one Hyper-V synthetic
        interrupt controller will have to wait for 4.5.  These will let
        KVM expose Hyper-V devices.

      - nested virtualization now supports VPID (same as PCID but for
        vCPUs) which makes it quite a bit faster

      - for future hardware that supports NVDIMM, there is support for
        clflushopt, clwb, pcommit

      - support for "split irqchip", i.e.  LAPIC in kernel +
        IOAPIC/PIC/PIT in userspace, which reduces the attack surface of
        the hypervisor

      - obligatory smattering of SMM fixes

      - on the guest side, stable scheduler clock support was rewritten
        to not require help from the hypervisor"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (123 commits)
  KVM: VMX: Fix commit which broke PML
  KVM: x86: obey KVM_X86_QUIRK_CD_NW_CLEARED in kvm_set_cr0()
  KVM: x86: allow RSM from 64-bit mode
  KVM: VMX: fix SMEP and SMAP without EPT
  KVM: x86: move kvm_set_irq_inatomic to legacy device assignment
  KVM: device assignment: remove pointless #ifdefs
  KVM: x86: merge kvm_arch_set_irq with kvm_set_msi_inatomic
  KVM: x86: zero apic_arb_prio on reset
  drivers/hv: share Hyper-V SynIC constants with userspace
  KVM: x86: handle SMBASE as physical address in RSM
  KVM: x86: add read_phys to x86_emulate_ops
  KVM: x86: removing unused variable
  KVM: don't pointlessly leave KVM_COMPAT=y in non-KVM configs
  KVM: arm/arm64: Merge vgic_set_lr() and vgic_sync_lr_elrsr()
  KVM: arm/arm64: Clean up vgic_retire_lr() and surroundings
  KVM: arm/arm64: Optimize away redundant LR tracking
  KVM: s390: use simple switch statement as multiplexer
  KVM: s390: drop useless newline in debugging data
  KVM: s390: SCA must not cross page boundaries
  KVM: arm: Do not indent the arguments of DECLARE_BITMAP
  ...

6 files changed, 98 insertions, 25 deletions

diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h
index d995821f1698..dc641ddf0784 100644
--- a/arch/arm/include/asm/kvm_arm.h
+++ b/arch/arm/include/asm/kvm_arm.h
@@ -218,4 +218,24 @@
 #define HSR_DABT_CM		(1U << 8)
 #define HSR_DABT_EA		(1U << 9)
 
+#define kvm_arm_exception_type	\
+	{0, "RESET" }, 		\
+	{1, "UNDEFINED" },	\
+	{2, "SOFTWARE" },	\
+	{3, "PREF_ABORT" },	\
+	{4, "DATA_ABORT" },	\
+	{5, "IRQ" },		\
+	{6, "FIQ" },		\
+	{7, "HVC" }
+
+#define HSRECN(x) { HSR_EC_##x, #x }
+
+#define kvm_arm_exception_class \
+	HSRECN(UNKNOWN), HSRECN(WFI), HSRECN(CP15_32), HSRECN(CP15_64), \
+	HSRECN(CP14_MR), HSRECN(CP14_LS), HSRECN(CP_0_13), HSRECN(CP10_ID), \
+	HSRECN(JAZELLE), HSRECN(BXJ), HSRECN(CP14_64), HSRECN(SVC_HYP), \
+	HSRECN(HVC), HSRECN(SMC), HSRECN(IABT), HSRECN(IABT_HYP), \
+	HSRECN(DABT), HSRECN(DABT_HYP)
+
+
 #endif /* __ARM_KVM_ARM_H__ */
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index c4072d9f32c7..6692982c9b57 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -126,7 +126,10 @@ struct kvm_vcpu_arch {
 	 * here.
 	 */
 
-	/* Don't run the guest on this vcpu */
+	/* vcpu power-off state */
+	bool power_off;
+
+	 /* Don't run the guest (internal implementation need) */
 	bool pause;
 
 	/* IO related fields */
diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig
index 356970f3b25e..95a000515e43 100644
--- a/arch/arm/kvm/Kconfig
+++ b/arch/arm/kvm/Kconfig
@@ -46,4 +46,6 @@ config KVM_ARM_HOST
 	---help---
 	  Provides host support for ARM processors.
 
+source drivers/vhost/Kconfig
+
 endif # VIRTUALIZATION
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 78b286994577..eab83b2435b8 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -271,6 +271,16 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 	return kvm_timer_should_fire(vcpu);
 }
 
+void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
+{
+	kvm_timer_schedule(vcpu);
+}
+
+void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu)
+{
+	kvm_timer_unschedule(vcpu);
+}
+
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 {
 	/* Force users to call KVM_ARM_VCPU_INIT */
@@ -308,7 +318,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
 				    struct kvm_mp_state *mp_state)
 {
-	if (vcpu->arch.pause)
+	if (vcpu->arch.power_off)
 		mp_state->mp_state = KVM_MP_STATE_STOPPED;
 	else
 		mp_state->mp_state = KVM_MP_STATE_RUNNABLE;
@@ -321,10 +331,10 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 {
 	switch (mp_state->mp_state) {
 	case KVM_MP_STATE_RUNNABLE:
-		vcpu->arch.pause = false;
+		vcpu->arch.power_off = false;
 		break;
 	case KVM_MP_STATE_STOPPED:
-		vcpu->arch.pause = true;
+		vcpu->arch.power_off = true;
 		break;
 	default:
 		return -EINVAL;
@@ -342,7 +352,8 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
  */
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
 {
-	return !!v->arch.irq_lines || kvm_vgic_vcpu_pending_irq(v);
+	return ((!!v->arch.irq_lines || kvm_vgic_vcpu_pending_irq(v))
+		&& !v->arch.power_off && !v->arch.pause);
 }
 
 /* Just ensure a guest exit from a particular CPU */
@@ -468,11 +479,38 @@ bool kvm_arch_intc_initialized(struct kvm *kvm)
 	return vgic_initialized(kvm);
 }
 
-static void vcpu_pause(struct kvm_vcpu *vcpu)
+static void kvm_arm_halt_guest(struct kvm *kvm) __maybe_unused;
+static void kvm_arm_resume_guest(struct kvm *kvm) __maybe_unused;
+
+static void kvm_arm_halt_guest(struct kvm *kvm)
+{
+	int i;
+	struct kvm_vcpu *vcpu;
+
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		vcpu->arch.pause = true;
+	force_vm_exit(cpu_all_mask);
+}
+
+static void kvm_arm_resume_guest(struct kvm *kvm)
+{
+	int i;
+	struct kvm_vcpu *vcpu;
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		wait_queue_head_t *wq = kvm_arch_vcpu_wq(vcpu);
+
+		vcpu->arch.pause = false;
+		wake_up_interruptible(wq);
+	}
+}
+
+static void vcpu_sleep(struct kvm_vcpu *vcpu)
 {
 	wait_queue_head_t *wq = kvm_arch_vcpu_wq(vcpu);
 
-	wait_event_interruptible(*wq, !vcpu->arch.pause);
+	wait_event_interruptible(*wq, ((!vcpu->arch.power_off) &&
+				       (!vcpu->arch.pause)));
 }
 
 static int kvm_vcpu_initialized(struct kvm_vcpu *vcpu)
@@ -522,8 +560,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 		update_vttbr(vcpu->kvm);
 
-		if (vcpu->arch.pause)
-			vcpu_pause(vcpu);
+		if (vcpu->arch.power_off || vcpu->arch.pause)
+			vcpu_sleep(vcpu);
 
 		/*
 		 * Disarming the background timer must be done in a
@@ -549,11 +587,12 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 			run->exit_reason = KVM_EXIT_INTR;
 		}
 
-		if (ret <= 0 || need_new_vmid_gen(vcpu->kvm)) {
+		if (ret <= 0 || need_new_vmid_gen(vcpu->kvm) ||
+			vcpu->arch.power_off || vcpu->arch.pause) {
 			local_irq_enable();
+			kvm_timer_sync_hwstate(vcpu);
 			kvm_vgic_sync_hwstate(vcpu);
 			preempt_enable();
-			kvm_timer_sync_hwstate(vcpu);
 			continue;
 		}
 
@@ -596,14 +635,19 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		 * guest time.
 		 */
 		kvm_guest_exit();
-		trace_kvm_exit(kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu));
+		trace_kvm_exit(ret, kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu));
+
+		/*
+		 * We must sync the timer state before the vgic state so that
+		 * the vgic can properly sample the updated state of the
+		 * interrupt line.
+		 */
+		kvm_timer_sync_hwstate(vcpu);
 
 		kvm_vgic_sync_hwstate(vcpu);
 
 		preempt_enable();
 
-		kvm_timer_sync_hwstate(vcpu);
-
 		ret = handle_exit(vcpu, run, ret);
 	}
 
@@ -765,12 +809,12 @@ static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu,
 	vcpu_reset_hcr(vcpu);
 
 	/*
-	 * Handle the "start in power-off" case by marking the VCPU as paused.
+	 * Handle the "start in power-off" case.
 	 */
 	if (test_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features))
-		vcpu->arch.pause = true;
+		vcpu->arch.power_off = true;
 	else
-		vcpu->arch.pause = false;
+		vcpu->arch.power_off = false;
 
 	return 0;
 }
diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c
index ad6f6424f1d1..0b556968a6da 100644
--- a/arch/arm/kvm/psci.c
+++ b/arch/arm/kvm/psci.c
@@ -63,7 +63,7 @@ static unsigned long kvm_psci_vcpu_suspend(struct kvm_vcpu *vcpu)
 
 static void kvm_psci_vcpu_off(struct kvm_vcpu *vcpu)
 {
-	vcpu->arch.pause = true;
+	vcpu->arch.power_off = true;
 }
 
 static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
@@ -87,7 +87,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 	 */
 	if (!vcpu)
 		return PSCI_RET_INVALID_PARAMS;
-	if (!vcpu->arch.pause) {
+	if (!vcpu->arch.power_off) {
 		if (kvm_psci_version(source_vcpu) != KVM_ARM_PSCI_0_1)
 			return PSCI_RET_ALREADY_ON;
 		else
@@ -115,7 +115,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 	 * the general puspose registers are undefined upon CPU_ON.
 	 */
 	*vcpu_reg(vcpu, 0) = context_id;
-	vcpu->arch.pause = false;
+	vcpu->arch.power_off = false;
 	smp_mb();		/* Make sure the above is visible */
 
 	wq = kvm_arch_vcpu_wq(vcpu);
@@ -153,7 +153,7 @@ static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu)
 		mpidr = kvm_vcpu_get_mpidr_aff(tmp);
 		if ((mpidr & target_affinity_mask) == target_affinity) {
 			matching_cpus++;
-			if (!tmp->arch.pause)
+			if (!tmp->arch.power_off)
 				return PSCI_0_2_AFFINITY_LEVEL_ON;
 		}
 	}
@@ -179,7 +179,7 @@ static void kvm_prepare_system_event(struct kvm_vcpu *vcpu, u32 type)
 	 * re-initialized.
 	 */
 	kvm_for_each_vcpu(i, tmp, vcpu->kvm) {
-		tmp->arch.pause = true;
+		tmp->arch.power_off = true;
 		kvm_vcpu_kick(tmp);
 	}
 
diff --git a/arch/arm/kvm/trace.h b/arch/arm/kvm/trace.h
index 0ec35392d208..c25a88598eb0 100644
--- a/arch/arm/kvm/trace.h
+++ b/arch/arm/kvm/trace.h
@@ -25,21 +25,25 @@ TRACE_EVENT(kvm_entry,
 );
 
 TRACE_EVENT(kvm_exit,
-	TP_PROTO(unsigned int exit_reason, unsigned long vcpu_pc),
-	TP_ARGS(exit_reason, vcpu_pc),
+	TP_PROTO(int idx, unsigned int exit_reason, unsigned long vcpu_pc),
+	TP_ARGS(idx, exit_reason, vcpu_pc),
 
 	TP_STRUCT__entry(
+		__field(	int,		idx		)
 		__field(	unsigned int,	exit_reason	)
 		__field(	unsigned long,	vcpu_pc		)
 	),
 
 	TP_fast_assign(
+		__entry->idx			= idx;
 		__entry->exit_reason		= exit_reason;
 		__entry->vcpu_pc		= vcpu_pc;
 	),
 
-	TP_printk("HSR_EC: 0x%04x, PC: 0x%08lx",
+	TP_printk("%s: HSR_EC: 0x%04x (%s), PC: 0x%08lx",
+		  __print_symbolic(__entry->idx, kvm_arm_exception_type),
 		  __entry->exit_reason,
+		  __print_symbolic(__entry->exit_reason, kvm_arm_exception_class),
 		  __entry->vcpu_pc)
 );