Merge remote-tracking branch 'kvmarm/misc-5.5' into kvmarm/next

arch/arm/include/asm/kvm_emulate.h

@@ -95,12 +95,12 @@ static inline unsigned long *vcpu_hcr(const struct kvm_vcpu *vcpu)
 	return (unsigned long *)&vcpu->arch.hcr;
 }
 
-static inline void vcpu_clear_wfe_traps(struct kvm_vcpu *vcpu)
+static inline void vcpu_clear_wfx_traps(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.hcr &= ~HCR_TWE;
 }
 
-static inline void vcpu_set_wfe_traps(struct kvm_vcpu *vcpu)
+static inline void vcpu_set_wfx_traps(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.hcr |= HCR_TWE;
 }

arch/arm/kvm/guest.c

@@ -21,6 +21,10 @@
 #define VCPU_STAT(x) { #x, offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU }
 
 struct kvm_stats_debugfs_item debugfs_entries[] = {
+	VCPU_STAT(halt_successful_poll),
+	VCPU_STAT(halt_attempted_poll),
+	VCPU_STAT(halt_poll_invalid),
+	VCPU_STAT(halt_wakeup),
 	VCPU_STAT(hvc_exit_stat),
 	VCPU_STAT(wfe_exit_stat),
 	VCPU_STAT(wfi_exit_stat),

arch/arm64/include/asm/kvm_arm.h

@@ -61,7 +61,6 @@
  * RW:		64bit by default, can be overridden for 32bit VMs
  * TAC:		Trap ACTLR
  * TSC:		Trap SMC
- * TVM:		Trap VM ops (until M+C set in SCTLR_EL1)
  * TSW:		Trap cache operations by set/way
  * TWE:		Trap WFE
  * TWI:		Trap WFI
@@ -74,7 +73,7 @@
  * SWIO:	Turn set/way invalidates into set/way clean+invalidate
  */
 #define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \
-			 HCR_TVM | HCR_BSU_IS | HCR_FB | HCR_TAC | \
+			 HCR_BSU_IS | HCR_FB | HCR_TAC | \
 			 HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW | HCR_TLOR | \
 			 HCR_FMO | HCR_IMO)
 #define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF)

arch/arm64/include/asm/kvm_emulate.h

@@ -53,8 +53,18 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
 		/* trap error record accesses */
 		vcpu->arch.hcr_el2 |= HCR_TERR;
 	}
-	if (cpus_have_const_cap(ARM64_HAS_STAGE2_FWB))
+
+	if (cpus_have_const_cap(ARM64_HAS_STAGE2_FWB)) {
 		vcpu->arch.hcr_el2 |= HCR_FWB;
+	} else {
+		/*
+		 * For non-FWB CPUs, we trap VM ops (HCR_EL2.TVM) until M+C
+		 * get set in SCTLR_EL1 such that we can detect when the guest
+		 * MMU gets turned on and do the necessary cache maintenance
+		 * then.
+		 */
+		vcpu->arch.hcr_el2 |= HCR_TVM;
+	}
 
 	if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features))
 		vcpu->arch.hcr_el2 &= ~HCR_RW;
@@ -77,14 +87,19 @@ static inline unsigned long *vcpu_hcr(struct kvm_vcpu *vcpu)
 	return (unsigned long *)&vcpu->arch.hcr_el2;
 }
 
-static inline void vcpu_clear_wfe_traps(struct kvm_vcpu *vcpu)
+static inline void vcpu_clear_wfx_traps(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.hcr_el2 &= ~HCR_TWE;
+	if (atomic_read(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vlpi_count))
+		vcpu->arch.hcr_el2 &= ~HCR_TWI;
+	else
+		vcpu->arch.hcr_el2 |= HCR_TWI;
 }
 
-static inline void vcpu_set_wfe_traps(struct kvm_vcpu *vcpu)
+static inline void vcpu_set_wfx_traps(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.hcr_el2 |= HCR_TWE;
+	vcpu->arch.hcr_el2 |= HCR_TWI;
 }
 
 static inline void vcpu_ptrauth_enable(struct kvm_vcpu *vcpu)

arch/arm64/kvm/guest.c

@@ -34,6 +34,10 @@
 #define VCPU_STAT(x) { #x, offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU }
 
 struct kvm_stats_debugfs_item debugfs_entries[] = {
+	VCPU_STAT(halt_successful_poll),
+	VCPU_STAT(halt_attempted_poll),
+	VCPU_STAT(halt_poll_invalid),
+	VCPU_STAT(halt_wakeup),
 	VCPU_STAT(hvc_exit_stat),
 	VCPU_STAT(wfe_exit_stat),
 	VCPU_STAT(wfi_exit_stat),

drivers/irqchip/irq-gic-v4.c

@@ -141,12 +141,17 @@ static int its_send_vpe_cmd(struct its_vpe *vpe, struct its_cmd_info *info)
 int its_schedule_vpe(struct its_vpe *vpe, bool on)
 {
 	struct its_cmd_info info;
+	int ret;
 
 	WARN_ON(preemptible());
 
 	info.cmd_type = on ? SCHEDULE_VPE : DESCHEDULE_VPE;
 
-	return its_send_vpe_cmd(vpe, &info);
+	ret = its_send_vpe_cmd(vpe, &info);
+	if (!ret)
+		vpe->resident = on;
+
+	return ret;
 }
 
 int its_invall_vpe(struct its_vpe *vpe)

include/kvm/arm_vgic.h

@@ -240,7 +240,7 @@ struct vgic_dist {
 	 * Contains the attributes and gpa of the LPI configuration table.
 	 * Since we report GICR_TYPER.CommonLPIAff as 0b00, we can share
 	 * one address across all redistributors.
-	 * GICv3 spec: 6.1.2 "LPI Configuration tables"
+	 * GICv3 spec: IHI 0069E 6.1.1 "LPI Configuration tables"
 	 */
 	u64			propbaser;
 
@@ -378,8 +378,6 @@ static inline int kvm_vgic_get_max_vcpus(void)
 	return kvm_vgic_global_state.max_gic_vcpus;
 }
 
-int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi);
-
 /**
  * kvm_vgic_setup_default_irq_routing:
  * Setup a default flat gsi routing table mapping all SPIs
@@ -396,7 +394,7 @@ int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int irq,
 int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int irq,
 				 struct kvm_kernel_irq_routing_entry *irq_entry);
 
-void kvm_vgic_v4_enable_doorbell(struct kvm_vcpu *vcpu);
+int vgic_v4_load(struct kvm_vcpu *vcpu);
-void kvm_vgic_v4_disable_doorbell(struct kvm_vcpu *vcpu);
+int vgic_v4_put(struct kvm_vcpu *vcpu, bool need_db);
 
 #endif /* __KVM_ARM_VGIC_H */

include/linux/irqchip/arm-gic-v4.h

@@ -32,9 +32,13 @@ struct its_vm {
 struct its_vpe {
 	struct page 		*vpt_page;
 	struct its_vm		*its_vm;
+	/* per-vPE VLPI tracking */
+	atomic_t		vlpi_count;
 	/* Doorbell interrupt */
 	int			irq;
 	irq_hw_number_t		vpe_db_lpi;
+	/* VPE resident */
+	bool			resident;
 	/* VPE proxy mapping */
 	int			vpe_proxy_event;
 	/*

virt/kvm/arm/arch_timer.c

@@ -80,7 +80,7 @@ static inline bool userspace_irqchip(struct kvm *kvm)
 static void soft_timer_start(struct hrtimer *hrt, u64 ns)
 {
 	hrtimer_start(hrt, ktime_add_ns(ktime_get(), ns),
-		      HRTIMER_MODE_ABS);
+		      HRTIMER_MODE_ABS_HARD);
 }
 
 static void soft_timer_cancel(struct hrtimer *hrt)
@@ -697,11 +697,11 @@ void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu)
 	update_vtimer_cntvoff(vcpu, kvm_phys_timer_read());
 	ptimer->cntvoff = 0;
 
-	hrtimer_init(&timer->bg_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+	hrtimer_init(&timer->bg_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
 	timer->bg_timer.function = kvm_bg_timer_expire;
 
-	hrtimer_init(&vtimer->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+	hrtimer_init(&vtimer->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
-	hrtimer_init(&ptimer->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+	hrtimer_init(&ptimer->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
 	vtimer->hrtimer.function = kvm_hrtimer_expire;
 	ptimer->hrtimer.function = kvm_hrtimer_expire;
 

virt/kvm/arm/arm.c

@@ -348,20 +348,24 @@ void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
 	/*
 	 * If we're about to block (most likely because we've just hit a
 	 * WFI), we need to sync back the state of the GIC CPU interface
-	 * so that we have the lastest PMR and group enables. This ensures
+	 * so that we have the latest PMR and group enables. This ensures
 	 * that kvm_arch_vcpu_runnable has up-to-date data to decide
 	 * whether we have pending interrupts.
+	 *
+	 * For the same reason, we want to tell GICv4 that we need
+	 * doorbells to be signalled, should an interrupt become pending.
 	 */
 	preempt_disable();
 	kvm_vgic_vmcr_sync(vcpu);
+	vgic_v4_put(vcpu, true);
 	preempt_enable();
-
-	kvm_vgic_v4_enable_doorbell(vcpu);
 }
 
 void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu)
 {
-	kvm_vgic_v4_disable_doorbell(vcpu);
+	preempt_disable();
+	vgic_v4_load(vcpu);
+	preempt_enable();
 }
 
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
@@ -412,9 +416,9 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		kvm_make_request(KVM_REQ_RECORD_STEAL, vcpu);
 
 	if (single_task_running())
-		vcpu_clear_wfe_traps(vcpu);
+		vcpu_clear_wfx_traps(vcpu);
 	else
-		vcpu_set_wfe_traps(vcpu);
+		vcpu_set_wfx_traps(vcpu);
 
 	vcpu_ptrauth_setup_lazy(vcpu);
 }

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

@@ -203,6 +203,7 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
 
 	INIT_LIST_HEAD(&vgic_cpu->ap_list_head);
 	raw_spin_lock_init(&vgic_cpu->ap_list_lock);
+	atomic_set(&vgic_cpu->vgic_v3.its_vpe.vlpi_count, 0);
 
 	/*
 	 * Enable and configure all SGIs to be edge-triggered and

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

@@ -360,7 +360,10 @@ static int update_affinity(struct vgic_irq *irq, struct kvm_vcpu *vcpu)
 		if (ret)
 			return ret;
 
+		if (map.vpe)
+			atomic_dec(&map.vpe->vlpi_count);
 		map.vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe;
+		atomic_inc(&map.vpe->vlpi_count);
 
 		ret = its_map_vlpi(irq->host_irq, &map);
 	}

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

@@ -357,14 +357,14 @@ retry:
 }
 
 /**
- * vgic_its_save_pending_tables - Save the pending tables into guest RAM
+ * vgic_v3_save_pending_tables - Save the pending tables into guest RAM
  * kvm lock and all vcpu lock must be held
  */
 int vgic_v3_save_pending_tables(struct kvm *kvm)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
-	int last_byte_offset = -1;
 	struct vgic_irq *irq;
+	gpa_t last_ptr = ~(gpa_t)0;
 	int ret;
 	u8 val;
 
@@ -384,11 +384,11 @@ int vgic_v3_save_pending_tables(struct kvm *kvm)
 		bit_nr = irq->intid % BITS_PER_BYTE;
 		ptr = pendbase + byte_offset;
 
-		if (byte_offset != last_byte_offset) {
+		if (ptr != last_ptr) {
 			ret = kvm_read_guest_lock(kvm, ptr, &val, 1);
 			if (ret)
 				return ret;
-			last_byte_offset = byte_offset;
+			last_ptr = ptr;
 		}
 
 		stored = val & (1U << bit_nr);
@@ -664,6 +664,8 @@ void vgic_v3_load(struct kvm_vcpu *vcpu)
 
 	if (has_vhe())
 		__vgic_v3_activate_traps(vcpu);
+
+	WARN_ON(vgic_v4_load(vcpu));
 }
 
 void vgic_v3_vmcr_sync(struct kvm_vcpu *vcpu)
@@ -676,6 +678,8 @@ void vgic_v3_vmcr_sync(struct kvm_vcpu *vcpu)
 
 void vgic_v3_put(struct kvm_vcpu *vcpu)
 {
+	WARN_ON(vgic_v4_put(vcpu, false));
+
 	vgic_v3_vmcr_sync(vcpu);
 
 	kvm_call_hyp(__vgic_v3_save_aprs, vcpu);

virt/kvm/arm/vgic/vgic-v4.c

@@ -85,6 +85,10 @@ static irqreturn_t vgic_v4_doorbell_handler(int irq, void *info)
 {
 	struct kvm_vcpu *vcpu = info;
 
+	/* We got the message, no need to fire again */
+	if (!irqd_irq_disabled(&irq_to_desc(irq)->irq_data))
+		disable_irq_nosync(irq);
+
 	vcpu->arch.vgic_cpu.vgic_v3.its_vpe.pending_last = true;
 	kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu);
 	kvm_vcpu_kick(vcpu);
@@ -192,20 +196,30 @@ void vgic_v4_teardown(struct kvm *kvm)
 	its_vm->vpes = NULL;
 }
 
-int vgic_v4_sync_hwstate(struct kvm_vcpu *vcpu)
+int vgic_v4_put(struct kvm_vcpu *vcpu, bool need_db)
 {
-	if (!vgic_supports_direct_msis(vcpu->kvm))
+	struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe;
+	struct irq_desc *desc = irq_to_desc(vpe->irq);
+
+	if (!vgic_supports_direct_msis(vcpu->kvm) || !vpe->resident)
 		return 0;
 
-	return its_schedule_vpe(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe, false);
+	/*
+	 * If blocking, a doorbell is required. Undo the nested
+	 * disable_irq() calls...
+	 */
+	while (need_db && irqd_irq_disabled(&desc->irq_data))
+		enable_irq(vpe->irq);
+
+	return its_schedule_vpe(vpe, false);
 }
 
-int vgic_v4_flush_hwstate(struct kvm_vcpu *vcpu)
+int vgic_v4_load(struct kvm_vcpu *vcpu)
 {
-	int irq = vcpu->arch.vgic_cpu.vgic_v3.its_vpe.irq;
+	struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe;
 	int err;
 
-	if (!vgic_supports_direct_msis(vcpu->kvm))
+	if (!vgic_supports_direct_msis(vcpu->kvm) || vpe->resident)
 		return 0;
 
 	/*
@@ -214,11 +228,14 @@ int vgic_v4_flush_hwstate(struct kvm_vcpu *vcpu)
 	 * doc in drivers/irqchip/irq-gic-v4.c to understand how this
 	 * turns into a VMOVP command at the ITS level.
 	 */
-	err = irq_set_affinity(irq, cpumask_of(smp_processor_id()));
+	err = irq_set_affinity(vpe->irq, cpumask_of(smp_processor_id()));
 	if (err)
 		return err;
 
-	err = its_schedule_vpe(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe, true);
+	/* Disabled the doorbell, as we're about to enter the guest */
+	disable_irq_nosync(vpe->irq);
+
+	err = its_schedule_vpe(vpe, true);
 	if (err)
 		return err;
 
@@ -226,9 +243,7 @@ int vgic_v4_flush_hwstate(struct kvm_vcpu *vcpu)
 	 * Now that the VPE is resident, let's get rid of a potential
 	 * doorbell interrupt that would still be pending.
 	 */
-	err = irq_set_irqchip_state(irq, IRQCHIP_STATE_PENDING, false);
+	return irq_set_irqchip_state(vpe->irq, IRQCHIP_STATE_PENDING, false);
-
-	return err;
 }
 
 static struct vgic_its *vgic_get_its(struct kvm *kvm,
@@ -266,7 +281,7 @@ int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int virq,
 
 	mutex_lock(&its->its_lock);
 
-	/* Perform then actual DevID/EventID -> LPI translation. */
+	/* Perform the actual DevID/EventID -> LPI translation. */
 	ret = vgic_its_resolve_lpi(kvm, its, irq_entry->msi.devid,
 				   irq_entry->msi.data, &irq);
 	if (ret)
@@ -294,6 +309,7 @@ int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int virq,
 
 	irq->hw		= true;
 	irq->host_irq	= virq;
+	atomic_inc(&map.vpe->vlpi_count);
 
 out:
 	mutex_unlock(&its->its_lock);
@@ -327,6 +343,7 @@ int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int virq,
 
 	WARN_ON(!(irq->hw && irq->host_irq == virq));
 	if (irq->hw) {
+		atomic_dec(&irq->target_vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vlpi_count);
 		irq->hw = false;
 		ret = its_unmap_vlpi(virq);
 	}
@@ -335,21 +352,3 @@ out:
 	mutex_unlock(&its->its_lock);
 	return ret;
 }
-
-void kvm_vgic_v4_enable_doorbell(struct kvm_vcpu *vcpu)
-{
-	if (vgic_supports_direct_msis(vcpu->kvm)) {
-		int irq = vcpu->arch.vgic_cpu.vgic_v3.its_vpe.irq;
-		if (irq)
-			enable_irq(irq);
-	}
-}
-
-void kvm_vgic_v4_disable_doorbell(struct kvm_vcpu *vcpu)
-{
-	if (vgic_supports_direct_msis(vcpu->kvm)) {
-		int irq = vcpu->arch.vgic_cpu.vgic_v3.its_vpe.irq;
-		if (irq)
-			disable_irq(irq);
-	}
-}

virt/kvm/arm/vgic/vgic.c

@@ -857,8 +857,6 @@ void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 
-	WARN_ON(vgic_v4_sync_hwstate(vcpu));
-
 	/* An empty ap_list_head implies used_lrs == 0 */
 	if (list_empty(&vcpu->arch.vgic_cpu.ap_list_head))
 		return;
@@ -882,8 +880,6 @@ static inline void vgic_restore_state(struct kvm_vcpu *vcpu)
 /* Flush our emulation state into the GIC hardware before entering the guest. */
 void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
 {
-	WARN_ON(vgic_v4_flush_hwstate(vcpu));
-
 	/*
 	 * If there are no virtual interrupts active or pending for this
 	 * VCPU, then there is no work to do and we can bail out without

virt/kvm/arm/vgic/vgic.h

@@ -316,7 +316,5 @@ void vgic_its_invalidate_cache(struct kvm *kvm);
 bool vgic_supports_direct_msis(struct kvm *kvm);
 int vgic_v4_init(struct kvm *kvm);
 void vgic_v4_teardown(struct kvm *kvm);
-int vgic_v4_sync_hwstate(struct kvm_vcpu *vcpu);
-int vgic_v4_flush_hwstate(struct kvm_vcpu *vcpu);
 
 #endif