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

Pull KVM updates from Paolo Bonzini:
 "PPC:
   - Better machine check handling for HV KVM
   - Ability to support guests with threads=2, 4 or 8 on POWER9
   - Fix for a race that could cause delayed recognition of signals
   - Fix for a bug where POWER9 guests could sleep with interrupts pending.

  ARM:
   - VCPU request overhaul
   - allow timer and PMU to have their interrupt number selected from userspace
   - workaround for Cavium erratum 30115
   - handling of memory poisonning
   - the usual crop of fixes and cleanups

  s390:
   - initial machine check forwarding
   - migration support for the CMMA page hinting information
   - cleanups and fixes

  x86:
   - nested VMX bugfixes and improvements
   - more reliable NMI window detection on AMD
   - APIC timer optimizations

  Generic:
   - VCPU request overhaul + documentation of common code patterns
   - kvm_stat improvements"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (124 commits)
  Update my email address
  kvm: vmx: allow host to access guest MSR_IA32_BNDCFGS
  x86: kvm: mmu: use ept a/d in vmcs02 iff used in vmcs12
  kvm: x86: mmu: allow A/D bits to be disabled in an mmu
  x86: kvm: mmu: make spte mmio mask more explicit
  x86: kvm: mmu: dead code thanks to access tracking
  KVM: PPC: Book3S: Fix typo in XICS-on-XIVE state saving code
  KVM: PPC: Book3S HV: Close race with testing for signals on guest entry
  KVM: PPC: Book3S HV: Simplify dynamic micro-threading code
  KVM: x86: remove ignored type attribute
  KVM: LAPIC: Fix lapic timer injection delay
  KVM: lapic: reorganize restart_apic_timer
  KVM: lapic: reorganize start_hv_timer
  kvm: nVMX: Check memory operand to INVVPID
  KVM: s390: Inject machine check into the nested guest
  KVM: s390: Inject machine check into the guest
  tools/kvm_stat: add new interactive command 'b'
  tools/kvm_stat: add new command line switch '-i'
  tools/kvm_stat: fix error on interactive command 'g'
  KVM: SVM: suppress unnecessary NMI singlestep on GIF=0 and nested exit
  ...

virt/kvm/arm/aarch32.c

@@ -60,7 +60,7 @@ static const unsigned short cc_map[16] = {
 /*
  * Check if a trapped instruction should have been executed or not.
  */
-bool kvm_condition_valid32(const struct kvm_vcpu *vcpu)
+bool __hyp_text kvm_condition_valid32(const struct kvm_vcpu *vcpu)
 {
 	unsigned long cpsr;
 	u32 cpsr_cond;

virt/kvm/arm/arch_timer.c

@@ -21,6 +21,7 @@
 #include <linux/kvm_host.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
+#include <linux/uaccess.h>
 
 #include <clocksource/arm_arch_timer.h>
 #include <asm/arch_timer.h>
@@ -35,6 +36,16 @@ static struct timecounter *timecounter;
 static unsigned int host_vtimer_irq;
 static u32 host_vtimer_irq_flags;
 
+static const struct kvm_irq_level default_ptimer_irq = {
+	.irq	= 30,
+	.level	= 1,
+};
+
+static const struct kvm_irq_level default_vtimer_irq = {
+	.irq	= 27,
+	.level	= 1,
+};
+
 void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu)
 {
 	vcpu_vtimer(vcpu)->active_cleared_last = false;
@@ -95,7 +106,7 @@ static void kvm_timer_inject_irq_work(struct work_struct *work)
 	 * If the vcpu is blocked we want to wake it up so that it will see
 	 * the timer has expired when entering the guest.
 	 */
-	kvm_vcpu_kick(vcpu);
+	kvm_vcpu_wake_up(vcpu);
 }
 
 static u64 kvm_timer_compute_delta(struct arch_timer_context *timer_ctx)
@@ -215,7 +226,8 @@ static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level,
 	if (likely(irqchip_in_kernel(vcpu->kvm))) {
 		ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id,
 					  timer_ctx->irq.irq,
-					  timer_ctx->irq.level);
+					  timer_ctx->irq.level,
+					  timer_ctx);
 		WARN_ON(ret);
 	}
 }
@@ -445,22 +457,11 @@ void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu)
 	kvm_timer_update_state(vcpu);
 }
 
-int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu,
-			 const struct kvm_irq_level *virt_irq,
-			 const struct kvm_irq_level *phys_irq)
+int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu)
 {
 	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
 	struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);
 
-	/*
-	 * The vcpu timer irq number cannot be determined in
-	 * kvm_timer_vcpu_init() because it is called much before
-	 * kvm_vcpu_set_target(). To handle this, we determine
-	 * vcpu timer irq number when the vcpu is reset.
-	 */
-	vtimer->irq.irq = virt_irq->irq;
-	ptimer->irq.irq = phys_irq->irq;
-
 	/*
 	 * The bits in CNTV_CTL are architecturally reset to UNKNOWN for ARMv8
 	 * and to 0 for ARMv7.  We provide an implementation that always
@@ -496,6 +497,8 @@ static void update_vtimer_cntvoff(struct kvm_vcpu *vcpu, u64 cntvoff)
 void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu)
 {
 	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
+	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
+	struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);
 
 	/* Synchronize cntvoff across all vtimers of a VM. */
 	update_vtimer_cntvoff(vcpu, kvm_phys_timer_read());
@@ -504,6 +507,9 @@ void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu)
 	INIT_WORK(&timer->expired, kvm_timer_inject_irq_work);
 	hrtimer_init(&timer->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
 	timer->timer.function = kvm_timer_expire;
+
+	vtimer->irq.irq = default_vtimer_irq.irq;
+	ptimer->irq.irq = default_ptimer_irq.irq;
 }
 
 static void kvm_timer_init_interrupt(void *info)
@@ -613,6 +619,30 @@ void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu)
 	kvm_vgic_unmap_phys_irq(vcpu, vtimer->irq.irq);
 }
 
+static bool timer_irqs_are_valid(struct kvm_vcpu *vcpu)
+{
+	int vtimer_irq, ptimer_irq;
+	int i, ret;
+
+	vtimer_irq = vcpu_vtimer(vcpu)->irq.irq;
+	ret = kvm_vgic_set_owner(vcpu, vtimer_irq, vcpu_vtimer(vcpu));
+	if (ret)
+		return false;
+
+	ptimer_irq = vcpu_ptimer(vcpu)->irq.irq;
+	ret = kvm_vgic_set_owner(vcpu, ptimer_irq, vcpu_ptimer(vcpu));
+	if (ret)
+		return false;
+
+	kvm_for_each_vcpu(i, vcpu, vcpu->kvm) {
+		if (vcpu_vtimer(vcpu)->irq.irq != vtimer_irq ||
+		    vcpu_ptimer(vcpu)->irq.irq != ptimer_irq)
+			return false;
+	}
+
+	return true;
+}
+
 int kvm_timer_enable(struct kvm_vcpu *vcpu)
 {
 	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
@@ -632,6 +662,11 @@ int kvm_timer_enable(struct kvm_vcpu *vcpu)
 	if (!vgic_initialized(vcpu->kvm))
 		return -ENODEV;
 
+	if (!timer_irqs_are_valid(vcpu)) {
+		kvm_debug("incorrectly configured timer irqs\n");
+		return -EINVAL;
+	}
+
 	/*
 	 * Find the physical IRQ number corresponding to the host_vtimer_irq
 	 */
@@ -681,3 +716,79 @@ void kvm_timer_init_vhe(void)
 	val |= (CNTHCTL_EL1PCTEN << cnthctl_shift);
 	write_sysreg(val, cnthctl_el2);
 }
+
+static void set_timer_irqs(struct kvm *kvm, int vtimer_irq, int ptimer_irq)
+{
+	struct kvm_vcpu *vcpu;
+	int i;
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		vcpu_vtimer(vcpu)->irq.irq = vtimer_irq;
+		vcpu_ptimer(vcpu)->irq.irq = ptimer_irq;
+	}
+}
+
+int kvm_arm_timer_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
+{
+	int __user *uaddr = (int __user *)(long)attr->addr;
+	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
+	struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);
+	int irq;
+
+	if (!irqchip_in_kernel(vcpu->kvm))
+		return -EINVAL;
+
+	if (get_user(irq, uaddr))
+		return -EFAULT;
+
+	if (!(irq_is_ppi(irq)))
+		return -EINVAL;
+
+	if (vcpu->arch.timer_cpu.enabled)
+		return -EBUSY;
+
+	switch (attr->attr) {
+	case KVM_ARM_VCPU_TIMER_IRQ_VTIMER:
+		set_timer_irqs(vcpu->kvm, irq, ptimer->irq.irq);
+		break;
+	case KVM_ARM_VCPU_TIMER_IRQ_PTIMER:
+		set_timer_irqs(vcpu->kvm, vtimer->irq.irq, irq);
+		break;
+	default:
+		return -ENXIO;
+	}
+
+	return 0;
+}
+
+int kvm_arm_timer_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
+{
+	int __user *uaddr = (int __user *)(long)attr->addr;
+	struct arch_timer_context *timer;
+	int irq;
+
+	switch (attr->attr) {
+	case KVM_ARM_VCPU_TIMER_IRQ_VTIMER:
+		timer = vcpu_vtimer(vcpu);
+		break;
+	case KVM_ARM_VCPU_TIMER_IRQ_PTIMER:
+		timer = vcpu_ptimer(vcpu);
+		break;
+	default:
+		return -ENXIO;
+	}
+
+	irq = timer->irq.irq;
+	return put_user(irq, uaddr);
+}
+
+int kvm_arm_timer_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
+{
+	switch (attr->attr) {
+	case KVM_ARM_VCPU_TIMER_IRQ_VTIMER:
+	case KVM_ARM_VCPU_TIMER_IRQ_PTIMER:
+		return 0;
+	}
+
+	return -ENXIO;
+}

virt/kvm/arm/arm.c

@@ -368,6 +368,13 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 	kvm_timer_vcpu_put(vcpu);
 }
 
+static void vcpu_power_off(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.power_off = true;
+	kvm_make_request(KVM_REQ_SLEEP, vcpu);
+	kvm_vcpu_kick(vcpu);
+}
+
 int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
 				    struct kvm_mp_state *mp_state)
 {
@@ -387,7 +394,7 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 		vcpu->arch.power_off = false;
 		break;
 	case KVM_MP_STATE_STOPPED:
-		vcpu->arch.power_off = true;
+		vcpu_power_off(vcpu);
 		break;
 	default:
 		return -EINVAL;
@@ -520,6 +527,10 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
 	}
 
 	ret = kvm_timer_enable(vcpu);
+	if (ret)
+		return ret;
+
+	ret = kvm_arm_pmu_v3_enable(vcpu);
 
 	return ret;
 }
@@ -536,21 +547,7 @@ void kvm_arm_halt_guest(struct kvm *kvm)
 
 	kvm_for_each_vcpu(i, vcpu, kvm)
 		vcpu->arch.pause = true;
-	kvm_make_all_cpus_request(kvm, KVM_REQ_VCPU_EXIT);
-}
-
-void kvm_arm_halt_vcpu(struct kvm_vcpu *vcpu)
-{
-	vcpu->arch.pause = true;
-	kvm_vcpu_kick(vcpu);
-}
-
-void kvm_arm_resume_vcpu(struct kvm_vcpu *vcpu)
-{
-	struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu);
-
-	vcpu->arch.pause = false;
-	swake_up(wq);
+	kvm_make_all_cpus_request(kvm, KVM_REQ_SLEEP);
 }
 
 void kvm_arm_resume_guest(struct kvm *kvm)
@@ -558,16 +555,23 @@ void kvm_arm_resume_guest(struct kvm *kvm)
 	int i;
 	struct kvm_vcpu *vcpu;
 
-	kvm_for_each_vcpu(i, vcpu, kvm)
-		kvm_arm_resume_vcpu(vcpu);
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		vcpu->arch.pause = false;
+		swake_up(kvm_arch_vcpu_wq(vcpu));
+	}
 }
 
-static void vcpu_sleep(struct kvm_vcpu *vcpu)
+static void vcpu_req_sleep(struct kvm_vcpu *vcpu)
 {
 	struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu);
 
 	swait_event_interruptible(*wq, ((!vcpu->arch.power_off) &&
 				       (!vcpu->arch.pause)));
+
+	if (vcpu->arch.power_off || vcpu->arch.pause) {
+		/* Awaken to handle a signal, request we sleep again later. */
+		kvm_make_request(KVM_REQ_SLEEP, vcpu);
+	}
 }
 
 static int kvm_vcpu_initialized(struct kvm_vcpu *vcpu)
@@ -575,6 +579,20 @@ static int kvm_vcpu_initialized(struct kvm_vcpu *vcpu)
 	return vcpu->arch.target >= 0;
 }
 
+static void check_vcpu_requests(struct kvm_vcpu *vcpu)
+{
+	if (kvm_request_pending(vcpu)) {
+		if (kvm_check_request(KVM_REQ_SLEEP, vcpu))
+			vcpu_req_sleep(vcpu);
+
+		/*
+		 * Clear IRQ_PENDING requests that were made to guarantee
+		 * that a VCPU sees new virtual interrupts.
+		 */
+		kvm_check_request(KVM_REQ_IRQ_PENDING, vcpu);
+	}
+}
+
 /**
  * kvm_arch_vcpu_ioctl_run - the main VCPU run function to execute guest code
  * @vcpu:	The VCPU pointer
@@ -620,8 +638,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 		update_vttbr(vcpu->kvm);
 
-		if (vcpu->arch.power_off || vcpu->arch.pause)
-			vcpu_sleep(vcpu);
+		check_vcpu_requests(vcpu);
 
 		/*
 		 * Preparing the interrupts to be injected also
@@ -650,8 +667,17 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 			run->exit_reason = KVM_EXIT_INTR;
 		}
 
+		/*
+		 * Ensure we set mode to IN_GUEST_MODE after we disable
+		 * interrupts and before the final VCPU requests check.
+		 * See the comment in kvm_vcpu_exiting_guest_mode() and
+		 * Documentation/virtual/kvm/vcpu-requests.rst
+		 */
+		smp_store_mb(vcpu->mode, IN_GUEST_MODE);
+
 		if (ret <= 0 || need_new_vmid_gen(vcpu->kvm) ||
-			vcpu->arch.power_off || vcpu->arch.pause) {
+		    kvm_request_pending(vcpu)) {
+			vcpu->mode = OUTSIDE_GUEST_MODE;
 			local_irq_enable();
 			kvm_pmu_sync_hwstate(vcpu);
 			kvm_timer_sync_hwstate(vcpu);
@@ -667,7 +693,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		 */
 		trace_kvm_entry(*vcpu_pc(vcpu));
 		guest_enter_irqoff();
-		vcpu->mode = IN_GUEST_MODE;
 
 		ret = kvm_call_hyp(__kvm_vcpu_run, vcpu);
 
@@ -756,6 +781,7 @@ static int vcpu_interrupt_line(struct kvm_vcpu *vcpu, int number, bool level)
 	 * trigger a world-switch round on the running physical CPU to set the
 	 * virtual IRQ/FIQ fields in the HCR appropriately.
 	 */
+	kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu);
 	kvm_vcpu_kick(vcpu);
 
 	return 0;
@@ -806,7 +832,7 @@ int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level,
 		if (irq_num < VGIC_NR_SGIS || irq_num >= VGIC_NR_PRIVATE_IRQS)
 			return -EINVAL;
 
-		return kvm_vgic_inject_irq(kvm, vcpu->vcpu_id, irq_num, level);
+		return kvm_vgic_inject_irq(kvm, vcpu->vcpu_id, irq_num, level, NULL);
 	case KVM_ARM_IRQ_TYPE_SPI:
 		if (!irqchip_in_kernel(kvm))
 			return -ENXIO;
@@ -814,7 +840,7 @@ int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level,
 		if (irq_num < VGIC_NR_PRIVATE_IRQS)
 			return -EINVAL;
 
-		return kvm_vgic_inject_irq(kvm, 0, irq_num, level);
+		return kvm_vgic_inject_irq(kvm, 0, irq_num, level, NULL);
 	}
 
 	return -EINVAL;
@@ -884,7 +910,7 @@ static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu,
 	 * Handle the "start in power-off" case.
 	 */
 	if (test_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features))
-		vcpu->arch.power_off = true;
+		vcpu_power_off(vcpu);
 	else
 		vcpu->arch.power_off = false;
 
@@ -1115,9 +1141,6 @@ static void cpu_init_hyp_mode(void *dummy)
 	__cpu_init_hyp_mode(pgd_ptr, hyp_stack_ptr, vector_ptr);
 	__cpu_init_stage2();
 
-	if (is_kernel_in_hyp_mode())
-		kvm_timer_init_vhe();
-
 	kvm_arm_init_debug();
 }
 
@@ -1137,6 +1160,7 @@ static void cpu_hyp_reinit(void)
 		 * event was cancelled before the CPU was reset.
 		 */
 		__cpu_init_stage2();
+		kvm_timer_init_vhe();
 	} else {
 		cpu_init_hyp_mode(NULL);
 	}

virt/kvm/arm/mmu.c

@@ -20,6 +20,7 @@
 #include <linux/kvm_host.h>
 #include <linux/io.h>
 #include <linux/hugetlb.h>
+#include <linux/sched/signal.h>
 #include <trace/events/kvm.h>
 #include <asm/pgalloc.h>
 #include <asm/cacheflush.h>
@@ -1262,6 +1263,24 @@ static void coherent_cache_guest_page(struct kvm_vcpu *vcpu, kvm_pfn_t pfn,
 	__coherent_cache_guest_page(vcpu, pfn, size);
 }
 
+static void kvm_send_hwpoison_signal(unsigned long address,
+				     struct vm_area_struct *vma)
+{
+	siginfo_t info;
+
+	info.si_signo   = SIGBUS;
+	info.si_errno   = 0;
+	info.si_code    = BUS_MCEERR_AR;
+	info.si_addr    = (void __user *)address;
+
+	if (is_vm_hugetlb_page(vma))
+		info.si_addr_lsb = huge_page_shift(hstate_vma(vma));
+	else
+		info.si_addr_lsb = PAGE_SHIFT;
+
+	send_sig_info(SIGBUS, &info, current);
+}
+
 static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 			  struct kvm_memory_slot *memslot, unsigned long hva,
 			  unsigned long fault_status)
@@ -1331,6 +1350,10 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	smp_rmb();
 
 	pfn = gfn_to_pfn_prot(kvm, gfn, write_fault, &writable);
+	if (pfn == KVM_PFN_ERR_HWPOISON) {
+		kvm_send_hwpoison_signal(hva, vma);
+		return 0;
+	}
 	if (is_error_noslot_pfn(pfn))
 		return -EFAULT;
 

virt/kvm/arm/pmu.c

@@ -203,6 +203,24 @@ static u64 kvm_pmu_overflow_status(struct kvm_vcpu *vcpu)
 	return reg;
 }
 
+static void kvm_pmu_check_overflow(struct kvm_vcpu *vcpu)
+{
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+	bool overflow = !!kvm_pmu_overflow_status(vcpu);
+
+	if (pmu->irq_level == overflow)
+		return;
+
+	pmu->irq_level = overflow;
+
+	if (likely(irqchip_in_kernel(vcpu->kvm))) {
+		int ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id,
+					      pmu->irq_num, overflow,
+					      &vcpu->arch.pmu);
+		WARN_ON(ret);
+	}
+}
+
 /**
  * kvm_pmu_overflow_set - set PMU overflow interrupt
  * @vcpu: The vcpu pointer
@@ -210,37 +228,18 @@ static u64 kvm_pmu_overflow_status(struct kvm_vcpu *vcpu)
  */
 void kvm_pmu_overflow_set(struct kvm_vcpu *vcpu, u64 val)
 {
-	u64 reg;
-
 	if (val == 0)
 		return;
 
 	vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= val;
-	reg = kvm_pmu_overflow_status(vcpu);
-	if (reg != 0)
-		kvm_vcpu_kick(vcpu);
+	kvm_pmu_check_overflow(vcpu);
 }
 
 static void kvm_pmu_update_state(struct kvm_vcpu *vcpu)
 {
-	struct kvm_pmu *pmu = &vcpu->arch.pmu;
-	bool overflow;
-
 	if (!kvm_arm_pmu_v3_ready(vcpu))
 		return;
-
-	overflow = !!kvm_pmu_overflow_status(vcpu);
-	if (pmu->irq_level == overflow)
-		return;
-
-	pmu->irq_level = overflow;
-
-	if (likely(irqchip_in_kernel(vcpu->kvm))) {
-		int ret;
-		ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id,
-					  pmu->irq_num, overflow);
-		WARN_ON(ret);
-	}
+	kvm_pmu_check_overflow(vcpu);
 }
 
 bool kvm_pmu_should_notify_user(struct kvm_vcpu *vcpu)
@@ -451,25 +450,32 @@ bool kvm_arm_support_pmu_v3(void)
 	return (perf_num_counters() > 0);
 }
 
-static int kvm_arm_pmu_v3_init(struct kvm_vcpu *vcpu)
+int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu)
 {
-	if (!kvm_arm_support_pmu_v3())
-		return -ENODEV;
+	if (!vcpu->arch.pmu.created)
+		return 0;
 
 	/*
-	 * We currently require an in-kernel VGIC to use the PMU emulation,
-	 * because we do not support forwarding PMU overflow interrupts to
-	 * userspace yet.
+	 * A valid interrupt configuration for the PMU is either to have a
+	 * properly configured interrupt number and using an in-kernel
+	 * irqchip, or to not have an in-kernel GIC and not set an IRQ.
 	 */
-	if (!irqchip_in_kernel(vcpu->kvm) || !vgic_initialized(vcpu->kvm))
-		return -ENODEV;
+	if (irqchip_in_kernel(vcpu->kvm)) {
+		int irq = vcpu->arch.pmu.irq_num;
+		if (!kvm_arm_pmu_irq_initialized(vcpu))
+			return -EINVAL;
 
-	if (!test_bit(KVM_ARM_VCPU_PMU_V3, vcpu->arch.features) ||
-	    !kvm_arm_pmu_irq_initialized(vcpu))
-		return -ENXIO;
-
-	if (kvm_arm_pmu_v3_ready(vcpu))
-		return -EBUSY;
+		/*
+		 * If we are using an in-kernel vgic, at this point we know
+		 * the vgic will be initialized, so we can check the PMU irq
+		 * number against the dimensions of the vgic and make sure
+		 * it's valid.
+		 */
+		if (!irq_is_ppi(irq) && !vgic_valid_spi(vcpu->kvm, irq))
+			return -EINVAL;
+	} else if (kvm_arm_pmu_irq_initialized(vcpu)) {
+		   return -EINVAL;
+	}
 
 	kvm_pmu_vcpu_reset(vcpu);
 	vcpu->arch.pmu.ready = true;
@@ -477,7 +483,40 @@ static int kvm_arm_pmu_v3_init(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-#define irq_is_ppi(irq) ((irq) >= VGIC_NR_SGIS && (irq) < VGIC_NR_PRIVATE_IRQS)
+static int kvm_arm_pmu_v3_init(struct kvm_vcpu *vcpu)
+{
+	if (!kvm_arm_support_pmu_v3())
+		return -ENODEV;
+
+	if (!test_bit(KVM_ARM_VCPU_PMU_V3, vcpu->arch.features))
+		return -ENXIO;
+
+	if (vcpu->arch.pmu.created)
+		return -EBUSY;
+
+	if (irqchip_in_kernel(vcpu->kvm)) {
+		int ret;
+
+		/*
+		 * If using the PMU with an in-kernel virtual GIC
+		 * implementation, we require the GIC to be already
+		 * initialized when initializing the PMU.
+		 */
+		if (!vgic_initialized(vcpu->kvm))
+			return -ENODEV;
+
+		if (!kvm_arm_pmu_irq_initialized(vcpu))
+			return -ENXIO;
+
+		ret = kvm_vgic_set_owner(vcpu, vcpu->arch.pmu.irq_num,
+					 &vcpu->arch.pmu);
+		if (ret)
+			return ret;
+	}
+
+	vcpu->arch.pmu.created = true;
+	return 0;
+}
 
 /*
  * For one VM the interrupt type must be same for each vcpu.
@@ -512,6 +551,9 @@ int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
 		int __user *uaddr = (int __user *)(long)attr->addr;
 		int irq;
 
+		if (!irqchip_in_kernel(vcpu->kvm))
+			return -EINVAL;
+
 		if (!test_bit(KVM_ARM_VCPU_PMU_V3, vcpu->arch.features))
 			return -ENODEV;
 
@@ -519,7 +561,7 @@ int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
 			return -EFAULT;
 
 		/* The PMU overflow interrupt can be a PPI or a valid SPI. */
-		if (!(irq_is_ppi(irq) || vgic_valid_spi(vcpu->kvm, irq)))
+		if (!(irq_is_ppi(irq) || irq_is_spi(irq)))
 			return -EINVAL;
 
 		if (!pmu_irq_is_valid(vcpu->kvm, irq))
@@ -546,6 +588,9 @@ int kvm_arm_pmu_v3_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
 		int __user *uaddr = (int __user *)(long)attr->addr;
 		int irq;
 
+		if (!irqchip_in_kernel(vcpu->kvm))
+			return -EINVAL;
+
 		if (!test_bit(KVM_ARM_VCPU_PMU_V3, vcpu->arch.features))
 			return -ENODEV;
 

virt/kvm/arm/psci.c

@@ -57,6 +57,7 @@ static unsigned long kvm_psci_vcpu_suspend(struct kvm_vcpu *vcpu)
 	 * for KVM will preserve the register state.
 	 */
 	kvm_vcpu_block(vcpu);
+	kvm_clear_request(KVM_REQ_UNHALT, vcpu);
 
 	return PSCI_RET_SUCCESS;
 }
@@ -64,6 +65,8 @@ static unsigned long kvm_psci_vcpu_suspend(struct kvm_vcpu *vcpu)
 static void kvm_psci_vcpu_off(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.power_off = true;
+	kvm_make_request(KVM_REQ_SLEEP, vcpu);
+	kvm_vcpu_kick(vcpu);
 }
 
 static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
@@ -178,10 +181,9 @@ static void kvm_prepare_system_event(struct kvm_vcpu *vcpu, u32 type)
 	 * after this call is handled and before the VCPUs have been
 	 * re-initialized.
 	 */
-	kvm_for_each_vcpu(i, tmp, vcpu->kvm) {
+	kvm_for_each_vcpu(i, tmp, vcpu->kvm)
 		tmp->arch.power_off = true;
-		kvm_vcpu_kick(tmp);
-	}
+	kvm_make_all_cpus_request(vcpu->kvm, KVM_REQ_SLEEP);
 
 	memset(&vcpu->run->system_event, 0, sizeof(vcpu->run->system_event));
 	vcpu->run->system_event.type = type;

virt/kvm/arm/vgic/vgic-irqfd.c

@@ -34,7 +34,7 @@ static int vgic_irqfd_set_irq(struct kvm_kernel_irq_routing_entry *e,
 
 	if (!vgic_valid_spi(kvm, spi_id))
 		return -EINVAL;
-	return kvm_vgic_inject_irq(kvm, 0, spi_id, level);
+	return kvm_vgic_inject_irq(kvm, 0, spi_id, level, NULL);
 }
 
 /**

virt/kvm/arm/vgic/vgic-mmio-v2.c

@@ -308,34 +308,36 @@ static const struct vgic_register_region vgic_v2_dist_registers[] = {
 		vgic_mmio_read_v2_misc, vgic_mmio_write_v2_misc, 12,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_IGROUP,
-		vgic_mmio_read_rao, vgic_mmio_write_wi, 1,
+		vgic_mmio_read_rao, vgic_mmio_write_wi, NULL, NULL, 1,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ENABLE_SET,
-		vgic_mmio_read_enable, vgic_mmio_write_senable, 1,
+		vgic_mmio_read_enable, vgic_mmio_write_senable, NULL, NULL, 1,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ENABLE_CLEAR,
-		vgic_mmio_read_enable, vgic_mmio_write_cenable, 1,
+		vgic_mmio_read_enable, vgic_mmio_write_cenable, NULL, NULL, 1,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PENDING_SET,
-		vgic_mmio_read_pending, vgic_mmio_write_spending, 1,
+		vgic_mmio_read_pending, vgic_mmio_write_spending, NULL, NULL, 1,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PENDING_CLEAR,
-		vgic_mmio_read_pending, vgic_mmio_write_cpending, 1,
+		vgic_mmio_read_pending, vgic_mmio_write_cpending, NULL, NULL, 1,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ACTIVE_SET,
-		vgic_mmio_read_active, vgic_mmio_write_sactive, 1,
+		vgic_mmio_read_active, vgic_mmio_write_sactive,
+		NULL, vgic_mmio_uaccess_write_sactive, 1,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ACTIVE_CLEAR,
-		vgic_mmio_read_active, vgic_mmio_write_cactive, 1,
+		vgic_mmio_read_active, vgic_mmio_write_cactive,
+		NULL, vgic_mmio_uaccess_write_cactive, 1,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PRI,
-		vgic_mmio_read_priority, vgic_mmio_write_priority, 8,
-		VGIC_ACCESS_32bit | VGIC_ACCESS_8bit),
+		vgic_mmio_read_priority, vgic_mmio_write_priority, NULL, NULL,
+		8, VGIC_ACCESS_32bit | VGIC_ACCESS_8bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_TARGET,
-		vgic_mmio_read_target, vgic_mmio_write_target, 8,
+		vgic_mmio_read_target, vgic_mmio_write_target, NULL, NULL, 8,
 		VGIC_ACCESS_32bit | VGIC_ACCESS_8bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_CONFIG,
-		vgic_mmio_read_config, vgic_mmio_write_config, 2,
+		vgic_mmio_read_config, vgic_mmio_write_config, NULL, NULL, 2,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_LENGTH(GIC_DIST_SOFTINT,
 		vgic_mmio_read_raz, vgic_mmio_write_sgir, 4,

virt/kvm/arm/vgic/vgic-mmio-v3.c

@@ -456,11 +456,13 @@ static const struct vgic_register_region vgic_v3_dist_registers[] = {
 		vgic_mmio_read_raz, vgic_mmio_write_wi, 1,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ISACTIVER,
-		vgic_mmio_read_active, vgic_mmio_write_sactive, NULL, NULL, 1,
+		vgic_mmio_read_active, vgic_mmio_write_sactive,
+		NULL, vgic_mmio_uaccess_write_sactive, 1,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ICACTIVER,
-		vgic_mmio_read_active, vgic_mmio_write_cactive, NULL, NULL, 1,
-		VGIC_ACCESS_32bit),
+		vgic_mmio_read_active, vgic_mmio_write_cactive,
+		NULL, vgic_mmio_uaccess_write_cactive,
+		1, VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_IPRIORITYR,
 		vgic_mmio_read_priority, vgic_mmio_write_priority, NULL, NULL,
 		8, VGIC_ACCESS_32bit | VGIC_ACCESS_8bit),
@@ -526,12 +528,14 @@ static const struct vgic_register_region vgic_v3_sgibase_registers[] = {
 		vgic_mmio_read_pending, vgic_mmio_write_cpending,
 		vgic_mmio_read_raz, vgic_mmio_write_wi, 4,
 		VGIC_ACCESS_32bit),
-	REGISTER_DESC_WITH_LENGTH(GICR_ISACTIVER0,
-		vgic_mmio_read_active, vgic_mmio_write_sactive, 4,
-		VGIC_ACCESS_32bit),
-	REGISTER_DESC_WITH_LENGTH(GICR_ICACTIVER0,
-		vgic_mmio_read_active, vgic_mmio_write_cactive, 4,
-		VGIC_ACCESS_32bit),
+	REGISTER_DESC_WITH_LENGTH_UACCESS(GICR_ISACTIVER0,
+		vgic_mmio_read_active, vgic_mmio_write_sactive,
+		NULL, vgic_mmio_uaccess_write_sactive,
+		4, VGIC_ACCESS_32bit),
+	REGISTER_DESC_WITH_LENGTH_UACCESS(GICR_ICACTIVER0,
+		vgic_mmio_read_active, vgic_mmio_write_cactive,
+		NULL, vgic_mmio_uaccess_write_cactive,
+		4, VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_LENGTH(GICR_IPRIORITYR0,
 		vgic_mmio_read_priority, vgic_mmio_write_priority, 32,
 		VGIC_ACCESS_32bit | VGIC_ACCESS_8bit),

virt/kvm/arm/vgic/vgic-mmio.c

@@ -231,40 +231,72 @@ static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
  * be migrated while we don't hold the IRQ locks and we don't want to be
  * chasing moving targets.
  *
- * For private interrupts, we only have to make sure the single and only VCPU
- * that can potentially queue the IRQ is stopped.
+ * For private interrupts we don't have to do anything because userspace
+ * accesses to the VGIC state already require all VCPUs to be stopped, and
+ * only the VCPU itself can modify its private interrupts active state, which
+ * guarantees that the VCPU is not running.
  */
 static void vgic_change_active_prepare(struct kvm_vcpu *vcpu, u32 intid)
 {
-	if (intid < VGIC_NR_PRIVATE_IRQS)
-		kvm_arm_halt_vcpu(vcpu);
-	else
+	if (intid > VGIC_NR_PRIVATE_IRQS)
 		kvm_arm_halt_guest(vcpu->kvm);
 }
 
 /* See vgic_change_active_prepare */
 static void vgic_change_active_finish(struct kvm_vcpu *vcpu, u32 intid)
 {
-	if (intid < VGIC_NR_PRIVATE_IRQS)
-		kvm_arm_resume_vcpu(vcpu);
-	else
+	if (intid > VGIC_NR_PRIVATE_IRQS)
 		kvm_arm_resume_guest(vcpu->kvm);
 }
 
+static void __vgic_mmio_write_cactive(struct kvm_vcpu *vcpu,
+				      gpa_t addr, unsigned int len,
+				      unsigned long val)
+{
+	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
+	int i;
+
+	for_each_set_bit(i, &val, len * 8) {
+		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
+		vgic_mmio_change_active(vcpu, irq, false);
+		vgic_put_irq(vcpu->kvm, irq);
+	}
+}
+
 void vgic_mmio_write_cactive(struct kvm_vcpu *vcpu,
 			     gpa_t addr, unsigned int len,
 			     unsigned long val)
 {
 	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
+
+	mutex_lock(&vcpu->kvm->lock);
+	vgic_change_active_prepare(vcpu, intid);
+
+	__vgic_mmio_write_cactive(vcpu, addr, len, val);
+
+	vgic_change_active_finish(vcpu, intid);
+	mutex_unlock(&vcpu->kvm->lock);
+}
+
+void vgic_mmio_uaccess_write_cactive(struct kvm_vcpu *vcpu,
+				     gpa_t addr, unsigned int len,
+				     unsigned long val)
+{
+	__vgic_mmio_write_cactive(vcpu, addr, len, val);
+}
+
+static void __vgic_mmio_write_sactive(struct kvm_vcpu *vcpu,
+				      gpa_t addr, unsigned int len,
+				      unsigned long val)
+{
+	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
 	int i;
 
-	vgic_change_active_prepare(vcpu, intid);
 	for_each_set_bit(i, &val, len * 8) {
 		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
-		vgic_mmio_change_active(vcpu, irq, false);
+		vgic_mmio_change_active(vcpu, irq, true);
 		vgic_put_irq(vcpu->kvm, irq);
 	}
-	vgic_change_active_finish(vcpu, intid);
 }
 
 void vgic_mmio_write_sactive(struct kvm_vcpu *vcpu,
@@ -272,15 +304,21 @@ void vgic_mmio_write_sactive(struct kvm_vcpu *vcpu,
 			     unsigned long val)
 {
 	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
-	int i;
 
+	mutex_lock(&vcpu->kvm->lock);
 	vgic_change_active_prepare(vcpu, intid);
-	for_each_set_bit(i, &val, len * 8) {
-		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
-		vgic_mmio_change_active(vcpu, irq, true);
-		vgic_put_irq(vcpu->kvm, irq);
-	}
+
+	__vgic_mmio_write_sactive(vcpu, addr, len, val);
+
 	vgic_change_active_finish(vcpu, intid);
+	mutex_unlock(&vcpu->kvm->lock);
+}
+
+void vgic_mmio_uaccess_write_sactive(struct kvm_vcpu *vcpu,
+				     gpa_t addr, unsigned int len,
+				     unsigned long val)
+{
+	__vgic_mmio_write_sactive(vcpu, addr, len, val);
 }
 
 unsigned long vgic_mmio_read_priority(struct kvm_vcpu *vcpu,

virt/kvm/arm/vgic/vgic-mmio.h

@@ -75,7 +75,7 @@ extern struct kvm_io_device_ops kvm_io_gic_ops;
  * The _WITH_LENGTH version instantiates registers with a fixed length
  * and is mutually exclusive with the _PER_IRQ version.
  */
-#define REGISTER_DESC_WITH_BITS_PER_IRQ(off, rd, wr, bpi, acc)		\
+#define REGISTER_DESC_WITH_BITS_PER_IRQ(off, rd, wr, ur, uw, bpi, acc)	\
 	{								\
 		.reg_offset = off,					\
 		.bits_per_irq = bpi,					\
@@ -83,6 +83,8 @@ extern struct kvm_io_device_ops kvm_io_gic_ops;
 		.access_flags = acc,					\
 		.read = rd,						\
 		.write = wr,						\
+		.uaccess_read = ur,					\
+		.uaccess_write = uw,					\
 	}
 
 #define REGISTER_DESC_WITH_LENGTH(off, rd, wr, length, acc)		\
@@ -165,6 +167,14 @@ void vgic_mmio_write_sactive(struct kvm_vcpu *vcpu,
 			     gpa_t addr, unsigned int len,
 			     unsigned long val);
 
+void vgic_mmio_uaccess_write_cactive(struct kvm_vcpu *vcpu,
+				     gpa_t addr, unsigned int len,
+				     unsigned long val);
+
+void vgic_mmio_uaccess_write_sactive(struct kvm_vcpu *vcpu,
+				     gpa_t addr, unsigned int len,
+				     unsigned long val);
+
 unsigned long vgic_mmio_read_priority(struct kvm_vcpu *vcpu,
 				      gpa_t addr, unsigned int len);
 

virt/kvm/arm/vgic/vgic-v3.c

@@ -21,6 +21,10 @@
 
 #include "vgic.h"
 
+static bool group0_trap;
+static bool group1_trap;
+static bool common_trap;
+
 void vgic_v3_set_underflow(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v3_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v3;
@@ -258,6 +262,12 @@ void vgic_v3_enable(struct kvm_vcpu *vcpu)
 
 	/* Get the show on the road... */
 	vgic_v3->vgic_hcr = ICH_HCR_EN;
+	if (group0_trap)
+		vgic_v3->vgic_hcr |= ICH_HCR_TALL0;
+	if (group1_trap)
+		vgic_v3->vgic_hcr |= ICH_HCR_TALL1;
+	if (common_trap)
+		vgic_v3->vgic_hcr |= ICH_HCR_TC;
 }
 
 int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq)
@@ -429,6 +439,26 @@ out:
 	return ret;
 }
 
+DEFINE_STATIC_KEY_FALSE(vgic_v3_cpuif_trap);
+
+static int __init early_group0_trap_cfg(char *buf)
+{
+	return strtobool(buf, &group0_trap);
+}
+early_param("kvm-arm.vgic_v3_group0_trap", early_group0_trap_cfg);
+
+static int __init early_group1_trap_cfg(char *buf)
+{
+	return strtobool(buf, &group1_trap);
+}
+early_param("kvm-arm.vgic_v3_group1_trap", early_group1_trap_cfg);
+
+static int __init early_common_trap_cfg(char *buf)
+{
+	return strtobool(buf, &common_trap);
+}
+early_param("kvm-arm.vgic_v3_common_trap", early_common_trap_cfg);
+
 /**
  * vgic_v3_probe - probe for a GICv3 compatible interrupt controller in DT
  * @node:	pointer to the DT node
@@ -480,6 +510,21 @@ int vgic_v3_probe(const struct gic_kvm_info *info)
 	if (kvm_vgic_global_state.vcpu_base == 0)
 		kvm_info("disabling GICv2 emulation\n");
 
+#ifdef CONFIG_ARM64
+	if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_30115)) {
+		group0_trap = true;
+		group1_trap = true;
+	}
+#endif
+
+	if (group0_trap || group1_trap || common_trap) {
+		kvm_info("GICv3 sysreg trapping enabled ([%s%s%s], reduced performance)\n",
+			 group0_trap ? "G0" : "",
+			 group1_trap ? "G1" : "",
+			 common_trap ? "C"  : "");
+		static_branch_enable(&vgic_v3_cpuif_trap);
+	}
+
 	kvm_vgic_global_state.vctrl_base = NULL;
 	kvm_vgic_global_state.type = VGIC_V3;
 	kvm_vgic_global_state.max_gic_vcpus = VGIC_V3_MAX_CPUS;

virt/kvm/arm/vgic/vgic.c

@@ -35,11 +35,12 @@ struct vgic_global kvm_vgic_global_state __ro_after_init = {
 
 /*
  * Locking order is always:
- * its->cmd_lock (mutex)
- *   its->its_lock (mutex)
- *     vgic_cpu->ap_list_lock
- *       kvm->lpi_list_lock
- *         vgic_irq->irq_lock
+ * kvm->lock (mutex)
+ *   its->cmd_lock (mutex)
+ *     its->its_lock (mutex)
+ *       vgic_cpu->ap_list_lock
+ *         kvm->lpi_list_lock
+ *           vgic_irq->irq_lock
  *
  * If you need to take multiple locks, always take the upper lock first,
  * then the lower ones, e.g. first take the its_lock, then the irq_lock.
@@ -234,10 +235,14 @@ static void vgic_sort_ap_list(struct kvm_vcpu *vcpu)
 
 /*
  * Only valid injection if changing level for level-triggered IRQs or for a
- * rising edge.
+ * rising edge, and in-kernel connected IRQ lines can only be controlled by
+ * their owner.
  */
-static bool vgic_validate_injection(struct vgic_irq *irq, bool level)
+static bool vgic_validate_injection(struct vgic_irq *irq, bool level, void *owner)
 {
+	if (irq->owner != owner)
+		return false;
+
 	switch (irq->config) {
 	case VGIC_CONFIG_LEVEL:
 		return irq->line_level != level;
@@ -285,8 +290,10 @@ retry:
 		 * won't see this one until it exits for some other
 		 * reason.
 		 */
-		if (vcpu)
+		if (vcpu) {
+			kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu);
 			kvm_vcpu_kick(vcpu);
+		}
 		return false;
 	}
 
@@ -332,6 +339,7 @@ retry:
 	spin_unlock(&irq->irq_lock);
 	spin_unlock(&vcpu->arch.vgic_cpu.ap_list_lock);
 
+	kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu);
 	kvm_vcpu_kick(vcpu);
 
 	return true;
@@ -346,13 +354,16 @@ retry:
  *			      false: to ignore the call
  *	     Level-sensitive  true:  raise the input signal
  *			      false: lower the input signal
+ * @owner:   The opaque pointer to the owner of the IRQ being raised to verify
+ *           that the caller is allowed to inject this IRQ.  Userspace
+ *           injections will have owner == NULL.
  *
  * The VGIC is not concerned with devices being active-LOW or active-HIGH for
  * level-sensitive interrupts.  You can think of the level parameter as 1
  * being HIGH and 0 being LOW and all devices being active-HIGH.
  */
 int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int intid,
-			bool level)
+			bool level, void *owner)
 {
 	struct kvm_vcpu *vcpu;
 	struct vgic_irq *irq;
@@ -374,7 +385,7 @@ int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int intid,
 
 	spin_lock(&irq->irq_lock);
 
-	if (!vgic_validate_injection(irq, level)) {
+	if (!vgic_validate_injection(irq, level, owner)) {
 		/* Nothing to see here, move along... */
 		spin_unlock(&irq->irq_lock);
 		vgic_put_irq(kvm, irq);
@@ -430,6 +441,39 @@ int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int virt_irq)
 	return 0;
 }
 
+/**
+ * kvm_vgic_set_owner - Set the owner of an interrupt for a VM
+ *
+ * @vcpu:   Pointer to the VCPU (used for PPIs)
+ * @intid:  The virtual INTID identifying the interrupt (PPI or SPI)
+ * @owner:  Opaque pointer to the owner
+ *
+ * Returns 0 if intid is not already used by another in-kernel device and the
+ * owner is set, otherwise returns an error code.
+ */
+int kvm_vgic_set_owner(struct kvm_vcpu *vcpu, unsigned int intid, void *owner)
+{
+	struct vgic_irq *irq;
+	int ret = 0;
+
+	if (!vgic_initialized(vcpu->kvm))
+		return -EAGAIN;
+
+	/* SGIs and LPIs cannot be wired up to any device */
+	if (!irq_is_ppi(intid) && !vgic_valid_spi(vcpu->kvm, intid))
+		return -EINVAL;
+
+	irq = vgic_get_irq(vcpu->kvm, vcpu, intid);
+	spin_lock(&irq->irq_lock);
+	if (irq->owner && irq->owner != owner)
+		ret = -EEXIST;
+	else
+		irq->owner = owner;
+	spin_unlock(&irq->irq_lock);
+
+	return ret;
+}
+
 /**
  * vgic_prune_ap_list - Remove non-relevant interrupts from the list
  *
@@ -721,8 +765,10 @@ void vgic_kick_vcpus(struct kvm *kvm)
 	 * a good kick...
 	 */
 	kvm_for_each_vcpu(c, vcpu, kvm) {
-		if (kvm_vgic_vcpu_pending_irq(vcpu))
+		if (kvm_vgic_vcpu_pending_irq(vcpu)) {
+			kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu);
 			kvm_vcpu_kick(vcpu);
+		}
 	}
 }
 

virt/kvm/kvm_main.c

@@ -73,17 +73,17 @@ MODULE_LICENSE("GPL");
 
 /* Architectures should define their poll value according to the halt latency */
 unsigned int halt_poll_ns = KVM_HALT_POLL_NS_DEFAULT;
-module_param(halt_poll_ns, uint, S_IRUGO | S_IWUSR);
+module_param(halt_poll_ns, uint, 0644);
 EXPORT_SYMBOL_GPL(halt_poll_ns);
 
 /* Default doubles per-vcpu halt_poll_ns. */
 unsigned int halt_poll_ns_grow = 2;
-module_param(halt_poll_ns_grow, uint, S_IRUGO | S_IWUSR);
+module_param(halt_poll_ns_grow, uint, 0644);
 EXPORT_SYMBOL_GPL(halt_poll_ns_grow);
 
 /* Default resets per-vcpu halt_poll_ns . */
 unsigned int halt_poll_ns_shrink;
-module_param(halt_poll_ns_shrink, uint, S_IRUGO | S_IWUSR);
+module_param(halt_poll_ns_shrink, uint, 0644);
 EXPORT_SYMBOL_GPL(halt_poll_ns_shrink);
 
 /*
@@ -3191,6 +3191,12 @@ static int kvm_dev_ioctl_create_vm(unsigned long type)
 		return PTR_ERR(file);
 	}
 
+	/*
+	 * Don't call kvm_put_kvm anymore at this point; file->f_op is
+	 * already set, with ->release() being kvm_vm_release().  In error
+	 * cases it will be called by the final fput(file) and will take
+	 * care of doing kvm_put_kvm(kvm).
+	 */
 	if (kvm_create_vm_debugfs(kvm, r) < 0) {
 		put_unused_fd(r);
 		fput(file);