Merge tag 'kvm-arm-for-v4.16' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm

KVM/ARM Changes for v4.16

The changes for this version include icache invalidation optimizations
(improving VM startup time), support for forwarded level-triggered
interrupts (improved performance for timers and passthrough platform
devices), a small fix for power-management notifiers, and some cosmetic
changes.

10 files changed, 368 insertions, 123 deletions

diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index f9555b1..fb6bd9b 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -97,15 +97,13 @@ static irqreturn_t kvm_arch_timer_handler(int irq, void *dev_id)
 		pr_warn_once("Spurious arch timer IRQ on non-VCPU thread\n");
 		return IRQ_NONE;
 	}
-	vtimer = vcpu_vtimer(vcpu);
 
-	if (!vtimer->irq.level) {
-		vtimer->cnt_ctl = read_sysreg_el0(cntv_ctl);
-		if (kvm_timer_irq_can_fire(vtimer))
-			kvm_timer_update_irq(vcpu, true, vtimer);
-	}
+	vtimer = vcpu_vtimer(vcpu);
+	if (kvm_timer_should_fire(vtimer))
+		kvm_timer_update_irq(vcpu, true, vtimer);
 
-	if (unlikely(!irqchip_in_kernel(vcpu->kvm)))
+	if (static_branch_unlikely(&userspace_irqchip_in_use) &&
+	    unlikely(!irqchip_in_kernel(vcpu->kvm)))
 		kvm_vtimer_update_mask_user(vcpu);
 
 	return IRQ_HANDLED;
@@ -231,6 +229,16 @@ static bool kvm_timer_should_fire(struct arch_timer_context *timer_ctx)
 {
 	u64 cval, now;
 
+	if (timer_ctx->loaded) {
+		u32 cnt_ctl;
+
+		/* Only the virtual timer can be loaded so far */
+		cnt_ctl = read_sysreg_el0(cntv_ctl);
+		return  (cnt_ctl & ARCH_TIMER_CTRL_ENABLE) &&
+		        (cnt_ctl & ARCH_TIMER_CTRL_IT_STAT) &&
+		       !(cnt_ctl & ARCH_TIMER_CTRL_IT_MASK);
+	}
+
 	if (!kvm_timer_irq_can_fire(timer_ctx))
 		return false;
 
@@ -245,15 +253,7 @@ bool kvm_timer_is_pending(struct kvm_vcpu *vcpu)
 	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
 	struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);
 
-	if (vtimer->irq.level || ptimer->irq.level)
-		return true;
-
-	/*
-	 * When this is called from withing the wait loop of kvm_vcpu_block(),
-	 * the software view of the timer state is up to date (timer->loaded
-	 * is false), and so we can simply check if the timer should fire now.
-	 */
-	if (!vtimer->loaded && kvm_timer_should_fire(vtimer))
+	if (kvm_timer_should_fire(vtimer))
 		return true;
 
 	return kvm_timer_should_fire(ptimer);
@@ -271,9 +271,9 @@ void kvm_timer_update_run(struct kvm_vcpu *vcpu)
 	/* Populate the device bitmap with the timer states */
 	regs->device_irq_level &= ~(KVM_ARM_DEV_EL1_VTIMER |
 				    KVM_ARM_DEV_EL1_PTIMER);
-	if (vtimer->irq.level)
+	if (kvm_timer_should_fire(vtimer))
 		regs->device_irq_level |= KVM_ARM_DEV_EL1_VTIMER;
-	if (ptimer->irq.level)
+	if (kvm_timer_should_fire(ptimer))
 		regs->device_irq_level |= KVM_ARM_DEV_EL1_PTIMER;
 }
 
@@ -286,7 +286,8 @@ static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level,
 	trace_kvm_timer_update_irq(vcpu->vcpu_id, timer_ctx->irq.irq,
 				   timer_ctx->irq.level);
 
-	if (likely(irqchip_in_kernel(vcpu->kvm))) {
+	if (!static_branch_unlikely(&userspace_irqchip_in_use) ||
+	    likely(irqchip_in_kernel(vcpu->kvm))) {
 		ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id,
 					  timer_ctx->irq.irq,
 					  timer_ctx->irq.level,
@@ -324,12 +325,20 @@ static void kvm_timer_update_state(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);
+	bool level;
 
 	if (unlikely(!timer->enabled))
 		return;
 
-	if (kvm_timer_should_fire(vtimer) != vtimer->irq.level)
-		kvm_timer_update_irq(vcpu, !vtimer->irq.level, vtimer);
+	/*
+	 * The vtimer virtual interrupt is a 'mapped' interrupt, meaning part
+	 * of its lifecycle is offloaded to the hardware, and we therefore may
+	 * not have lowered the irq.level value before having to signal a new
+	 * interrupt, but have to signal an interrupt every time the level is
+	 * asserted.
+	 */
+	level = kvm_timer_should_fire(vtimer);
+	kvm_timer_update_irq(vcpu, level, vtimer);
 
 	if (kvm_timer_should_fire(ptimer) != ptimer->irq.level)
 		kvm_timer_update_irq(vcpu, !ptimer->irq.level, ptimer);
@@ -337,6 +346,12 @@ static void kvm_timer_update_state(struct kvm_vcpu *vcpu)
 	phys_timer_emulate(vcpu);
 }
 
+static void __timer_snapshot_state(struct arch_timer_context *timer)
+{
+	timer->cnt_ctl = read_sysreg_el0(cntv_ctl);
+	timer->cnt_cval = read_sysreg_el0(cntv_cval);
+}
+
 static void vtimer_save_state(struct kvm_vcpu *vcpu)
 {
 	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
@@ -348,10 +363,8 @@ static void vtimer_save_state(struct kvm_vcpu *vcpu)
 	if (!vtimer->loaded)
 		goto out;
 
-	if (timer->enabled) {
-		vtimer->cnt_ctl = read_sysreg_el0(cntv_ctl);
-		vtimer->cnt_cval = read_sysreg_el0(cntv_cval);
-	}
+	if (timer->enabled)
+		__timer_snapshot_state(vtimer);
 
 	/* Disable the virtual timer */
 	write_sysreg_el0(0, cntv_ctl);
@@ -448,8 +461,7 @@ static void kvm_timer_vcpu_load_vgic(struct kvm_vcpu *vcpu)
 	bool phys_active;
 	int ret;
 
-	phys_active = vtimer->irq.level ||
-		      kvm_vgic_map_is_active(vcpu, vtimer->irq.irq);
+	phys_active = kvm_vgic_map_is_active(vcpu, vtimer->irq.irq);
 
 	ret = irq_set_irqchip_state(host_vtimer_irq,
 				    IRQCHIP_STATE_ACTIVE,
@@ -496,8 +508,8 @@ bool kvm_timer_should_notify_user(struct kvm_vcpu *vcpu)
 	vlevel = sregs->device_irq_level & KVM_ARM_DEV_EL1_VTIMER;
 	plevel = sregs->device_irq_level & KVM_ARM_DEV_EL1_PTIMER;
 
-	return vtimer->irq.level != vlevel ||
-	       ptimer->irq.level != plevel;
+	return kvm_timer_should_fire(vtimer) != vlevel ||
+	       kvm_timer_should_fire(ptimer) != plevel;
 }
 
 void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu)
@@ -529,54 +541,27 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu)
 	set_cntvoff(0);
 }
 
-static void unmask_vtimer_irq(struct kvm_vcpu *vcpu)
+/*
+ * With a userspace irqchip we have to check if the guest de-asserted the
+ * timer and if so, unmask the timer irq signal on the host interrupt
+ * controller to ensure that we see future timer signals.
+ */
+static void unmask_vtimer_irq_user(struct kvm_vcpu *vcpu)
 {
 	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
 
 	if (unlikely(!irqchip_in_kernel(vcpu->kvm))) {
-		kvm_vtimer_update_mask_user(vcpu);
-		return;
-	}
-
-	/*
-	 * If the guest disabled the timer without acking the interrupt, then
-	 * we must make sure the physical and virtual active states are in
-	 * sync by deactivating the physical interrupt, because otherwise we
-	 * wouldn't see the next timer interrupt in the host.
-	 */
-	if (!kvm_vgic_map_is_active(vcpu, vtimer->irq.irq)) {
-		int ret;
-		ret = irq_set_irqchip_state(host_vtimer_irq,
-					    IRQCHIP_STATE_ACTIVE,
-					    false);
-		WARN_ON(ret);
+		__timer_snapshot_state(vtimer);
+		if (!kvm_timer_should_fire(vtimer)) {
+			kvm_timer_update_irq(vcpu, false, vtimer);
+			kvm_vtimer_update_mask_user(vcpu);
+		}
 	}
 }
 
-/**
- * kvm_timer_sync_hwstate - sync timer state from cpu
- * @vcpu: The vcpu pointer
- *
- * Check if any of the timers have expired while we were running in the guest,
- * and inject an interrupt if that was the case.
- */
 void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu)
 {
-	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
-
-	/*
-	 * If we entered the guest with the vtimer output asserted we have to
-	 * check if the guest has modified the timer so that we should lower
-	 * the line at this point.
-	 */
-	if (vtimer->irq.level) {
-		vtimer->cnt_ctl = read_sysreg_el0(cntv_ctl);
-		vtimer->cnt_cval = read_sysreg_el0(cntv_cval);
-		if (!kvm_timer_should_fire(vtimer)) {
-			kvm_timer_update_irq(vcpu, false, vtimer);
-			unmask_vtimer_irq(vcpu);
-		}
-	}
+	unmask_vtimer_irq_user(vcpu);
 }
 
 int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu)
@@ -807,6 +792,19 @@ static bool timer_irqs_are_valid(struct kvm_vcpu *vcpu)
 	return true;
 }
 
+bool kvm_arch_timer_get_input_level(int vintid)
+{
+	struct kvm_vcpu *vcpu = kvm_arm_get_running_vcpu();
+	struct arch_timer_context *timer;
+
+	if (vintid == vcpu_vtimer(vcpu)->irq.irq)
+		timer = vcpu_vtimer(vcpu);
+	else
+		BUG(); /* We only map the vtimer so far */
+
+	return kvm_timer_should_fire(timer);
+}
+
 int kvm_timer_enable(struct kvm_vcpu *vcpu)
 {
 	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
@@ -828,7 +826,8 @@ int kvm_timer_enable(struct kvm_vcpu *vcpu)
 		return -EINVAL;
 	}
 
-	ret = kvm_vgic_map_phys_irq(vcpu, host_vtimer_irq, vtimer->irq.irq);
+	ret = kvm_vgic_map_phys_irq(vcpu, host_vtimer_irq, vtimer->irq.irq,
+				    kvm_arch_timer_get_input_level);
 	if (ret)
 		return ret;
 
diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c
index cd7d90c..92b95ae 100644
--- a/virt/kvm/arm/arm.c
+++ b/virt/kvm/arm/arm.c
@@ -71,17 +71,17 @@ static DEFINE_PER_CPU(unsigned char, kvm_arm_hardware_enabled);
 
 static void kvm_arm_set_running_vcpu(struct kvm_vcpu *vcpu)
 {
-	BUG_ON(preemptible());
 	__this_cpu_write(kvm_arm_running_vcpu, vcpu);
 }
 
+DEFINE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
+
 /**
  * kvm_arm_get_running_vcpu - get the vcpu running on the current CPU.
  * Must be called from non-preemptible context
  */
 struct kvm_vcpu *kvm_arm_get_running_vcpu(void)
 {
-	BUG_ON(preemptible());
 	return __this_cpu_read(kvm_arm_running_vcpu);
 }
 
@@ -295,6 +295,9 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 
 void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 {
+	if (vcpu->arch.has_run_once && unlikely(!irqchip_in_kernel(vcpu->kvm)))
+		static_branch_dec(&userspace_irqchip_in_use);
+
 	kvm_mmu_free_memory_caches(vcpu);
 	kvm_timer_vcpu_terminate(vcpu);
 	kvm_pmu_vcpu_destroy(vcpu);
@@ -532,14 +535,22 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
 
 	vcpu->arch.has_run_once = true;
 
-	/*
-	 * Map the VGIC hardware resources before running a vcpu the first
-	 * time on this VM.
-	 */
-	if (unlikely(irqchip_in_kernel(kvm) && !vgic_ready(kvm))) {
-		ret = kvm_vgic_map_resources(kvm);
-		if (ret)
-			return ret;
+	if (likely(irqchip_in_kernel(kvm))) {
+		/*
+		 * Map the VGIC hardware resources before running a vcpu the
+		 * first time on this VM.
+		 */
+		if (unlikely(!vgic_ready(kvm))) {
+			ret = kvm_vgic_map_resources(kvm);
+			if (ret)
+				return ret;
+		}
+	} else {
+		/*
+		 * Tell the rest of the code that there are userspace irqchip
+		 * VMs in the wild.
+		 */
+		static_branch_inc(&userspace_irqchip_in_use);
 	}
 
 	ret = kvm_timer_enable(vcpu);
@@ -680,19 +691,30 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		kvm_vgic_flush_hwstate(vcpu);
 
 		/*
-		 * If we have a singal pending, or need to notify a userspace
-		 * irqchip about timer or PMU level changes, then we exit (and
-		 * update the timer level state in kvm_timer_update_run
-		 * below).
+		 * Exit if we have a signal pending so that we can deliver the
+		 * signal to user space.
 		 */
-		if (signal_pending(current) ||
-		    kvm_timer_should_notify_user(vcpu) ||
-		    kvm_pmu_should_notify_user(vcpu)) {
+		if (signal_pending(current)) {
 			ret = -EINTR;
 			run->exit_reason = KVM_EXIT_INTR;
 		}
 
 		/*
+		 * If we're using a userspace irqchip, then check if we need
+		 * to tell a userspace irqchip about timer or PMU level
+		 * changes and if so, exit to userspace (the actual level
+		 * state gets updated in kvm_timer_update_run and
+		 * kvm_pmu_update_run below).
+		 */
+		if (static_branch_unlikely(&userspace_irqchip_in_use)) {
+			if (kvm_timer_should_notify_user(vcpu) ||
+			    kvm_pmu_should_notify_user(vcpu)) {
+				ret = -EINTR;
+				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
@@ -704,7 +726,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		    kvm_request_pending(vcpu)) {
 			vcpu->mode = OUTSIDE_GUEST_MODE;
 			kvm_pmu_sync_hwstate(vcpu);
-			kvm_timer_sync_hwstate(vcpu);
+			if (static_branch_unlikely(&userspace_irqchip_in_use))
+				kvm_timer_sync_hwstate(vcpu);
 			kvm_vgic_sync_hwstate(vcpu);
 			local_irq_enable();
 			preempt_enable();
@@ -748,7 +771,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		 * we don't want vtimer interrupts to race with syncing the
 		 * timer virtual interrupt state.
 		 */
-		kvm_timer_sync_hwstate(vcpu);
+		if (static_branch_unlikely(&userspace_irqchip_in_use))
+			kvm_timer_sync_hwstate(vcpu);
 
 		/*
 		 * We may have taken a host interrupt in HYP mode (ie
@@ -1277,6 +1301,7 @@ static int hyp_init_cpu_pm_notifier(struct notifier_block *self,
 			cpu_hyp_reset();
 
 		return NOTIFY_OK;
+	case CPU_PM_ENTER_FAILED:
 	case CPU_PM_EXIT:
 		if (__this_cpu_read(kvm_arm_hardware_enabled))
 			/* The hardware was enabled before suspend. */
diff --git a/virt/kvm/arm/hyp/vgic-v2-sr.c b/virt/kvm/arm/hyp/vgic-v2-sr.c
index d7fd46f..4fe6e79 100644
--- a/virt/kvm/arm/hyp/vgic-v2-sr.c
+++ b/virt/kvm/arm/hyp/vgic-v2-sr.c
@@ -21,6 +21,7 @@
 
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
 
 static void __hyp_text save_elrsr(struct kvm_vcpu *vcpu, void __iomem *base)
 {
diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c
index b36945d..a1ea43f 100644
--- a/virt/kvm/arm/mmu.c
+++ b/virt/kvm/arm/mmu.c
@@ -926,6 +926,25 @@ static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache
 	return 0;
 }
 
+static bool stage2_is_exec(struct kvm *kvm, phys_addr_t addr)
+{
+	pmd_t *pmdp;
+	pte_t *ptep;
+
+	pmdp = stage2_get_pmd(kvm, NULL, addr);
+	if (!pmdp || pmd_none(*pmdp) || !pmd_present(*pmdp))
+		return false;
+
+	if (pmd_thp_or_huge(*pmdp))
+		return kvm_s2pmd_exec(pmdp);
+
+	ptep = pte_offset_kernel(pmdp, addr);
+	if (!ptep || pte_none(*ptep) || !pte_present(*ptep))
+		return false;
+
+	return kvm_s2pte_exec(ptep);
+}
+
 static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
 			  phys_addr_t addr, const pte_t *new_pte,
 			  unsigned long flags)
@@ -1257,10 +1276,14 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
 	kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask);
 }
 
-static void coherent_cache_guest_page(struct kvm_vcpu *vcpu, kvm_pfn_t pfn,
-				      unsigned long size)
+static void clean_dcache_guest_page(kvm_pfn_t pfn, unsigned long size)
 {
-	__coherent_cache_guest_page(vcpu, pfn, size);
+	__clean_dcache_guest_page(pfn, size);
+}
+
+static void invalidate_icache_guest_page(kvm_pfn_t pfn, unsigned long size)
+{
+	__invalidate_icache_guest_page(pfn, size);
 }
 
 static void kvm_send_hwpoison_signal(unsigned long address,
@@ -1286,7 +1309,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 			  unsigned long fault_status)
 {
 	int ret;
-	bool write_fault, writable, hugetlb = false, force_pte = false;
+	bool write_fault, exec_fault, writable, hugetlb = false, force_pte = false;
 	unsigned long mmu_seq;
 	gfn_t gfn = fault_ipa >> PAGE_SHIFT;
 	struct kvm *kvm = vcpu->kvm;
@@ -1298,7 +1321,10 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	unsigned long flags = 0;
 
 	write_fault = kvm_is_write_fault(vcpu);
-	if (fault_status == FSC_PERM && !write_fault) {
+	exec_fault = kvm_vcpu_trap_is_iabt(vcpu);
+	VM_BUG_ON(write_fault && exec_fault);
+
+	if (fault_status == FSC_PERM && !write_fault && !exec_fault) {
 		kvm_err("Unexpected L2 read permission error\n");
 		return -EFAULT;
 	}
@@ -1391,7 +1417,19 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 			new_pmd = kvm_s2pmd_mkwrite(new_pmd);
 			kvm_set_pfn_dirty(pfn);
 		}
-		coherent_cache_guest_page(vcpu, pfn, PMD_SIZE);
+
+		if (fault_status != FSC_PERM)
+			clean_dcache_guest_page(pfn, PMD_SIZE);
+
+		if (exec_fault) {
+			new_pmd = kvm_s2pmd_mkexec(new_pmd);
+			invalidate_icache_guest_page(pfn, PMD_SIZE);
+		} else if (fault_status == FSC_PERM) {
+			/* Preserve execute if XN was already cleared */
+			if (stage2_is_exec(kvm, fault_ipa))
+				new_pmd = kvm_s2pmd_mkexec(new_pmd);
+		}
+
 		ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd);
 	} else {
 		pte_t new_pte = pfn_pte(pfn, mem_type);
@@ -1401,7 +1439,19 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 			kvm_set_pfn_dirty(pfn);
 			mark_page_dirty(kvm, gfn);
 		}
-		coherent_cache_guest_page(vcpu, pfn, PAGE_SIZE);
+
+		if (fault_status != FSC_PERM)
+			clean_dcache_guest_page(pfn, PAGE_SIZE);
+
+		if (exec_fault) {
+			new_pte = kvm_s2pte_mkexec(new_pte);
+			invalidate_icache_guest_page(pfn, PAGE_SIZE);
+		} else if (fault_status == FSC_PERM) {
+			/* Preserve execute if XN was already cleared */
+			if (stage2_is_exec(kvm, fault_ipa))
+				new_pte = kvm_s2pte_mkexec(new_pte);
+		}
+
 		ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte, flags);
 	}
 
diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c
index 8e633bd..4650953 100644
--- a/virt/kvm/arm/vgic/vgic-its.c
+++ b/virt/kvm/arm/vgic/vgic-its.c
@@ -1034,10 +1034,8 @@ static int vgic_its_cmd_handle_mapd(struct kvm *kvm, struct vgic_its *its,
 
 	device = vgic_its_alloc_device(its, device_id, itt_addr,
 				       num_eventid_bits);
-	if (IS_ERR(device))
-		return PTR_ERR(device);
 
-	return 0;
+	return PTR_ERR_OR_ZERO(device);
 }
 
 /*
diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c
index deb51ee..83d82bd 100644
--- a/virt/kvm/arm/vgic/vgic-mmio.c
+++ b/virt/kvm/arm/vgic/vgic-mmio.c
@@ -16,6 +16,7 @@
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
 #include <kvm/iodev.h>
+#include <kvm/arm_arch_timer.h>
 #include <kvm/arm_vgic.h>
 
 #include "vgic.h"
@@ -122,10 +123,43 @@ unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu,
 	return value;
 }
 
+/*
+ * This function will return the VCPU that performed the MMIO access and
+ * trapped from within the VM, and will return NULL if this is a userspace
+ * access.
+ *
+ * We can disable preemption locally around accessing the per-CPU variable,
+ * and use the resolved vcpu pointer after enabling preemption again, because
+ * even if the current thread is migrated to another CPU, reading the per-CPU
+ * value later will give us the same value as we update the per-CPU variable
+ * in the preempt notifier handlers.
+ */
+static struct kvm_vcpu *vgic_get_mmio_requester_vcpu(void)
+{
+	struct kvm_vcpu *vcpu;
+
+	preempt_disable();
+	vcpu = kvm_arm_get_running_vcpu();
+	preempt_enable();
+	return vcpu;
+}
+
+/* Must be called with irq->irq_lock held */
+static void vgic_hw_irq_spending(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
+				 bool is_uaccess)
+{
+	if (is_uaccess)
+		return;
+
+	irq->pending_latch = true;
+	vgic_irq_set_phys_active(irq, true);
+}
+
 void vgic_mmio_write_spending(struct kvm_vcpu *vcpu,
 			      gpa_t addr, unsigned int len,
 			      unsigned long val)
 {
+	bool is_uaccess = !vgic_get_mmio_requester_vcpu();
 	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
 	int i;
 	unsigned long flags;
@@ -134,17 +168,45 @@ void vgic_mmio_write_spending(struct kvm_vcpu *vcpu,
 		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
 
 		spin_lock_irqsave(&irq->irq_lock, flags);
-		irq->pending_latch = true;
-
+		if (irq->hw)
+			vgic_hw_irq_spending(vcpu, irq, is_uaccess);
+		else
+			irq->pending_latch = true;
 		vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
 		vgic_put_irq(vcpu->kvm, irq);
 	}
 }
 
+/* Must be called with irq->irq_lock held */
+static void vgic_hw_irq_cpending(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
+				 bool is_uaccess)
+{
+	if (is_uaccess)
+		return;
+
+	irq->pending_latch = false;
+
+	/*
+	 * We don't want the guest to effectively mask the physical
+	 * interrupt by doing a write to SPENDR followed by a write to
+	 * CPENDR for HW interrupts, so we clear the active state on
+	 * the physical side if the virtual interrupt is not active.
+	 * This may lead to taking an additional interrupt on the
+	 * host, but that should not be a problem as the worst that
+	 * can happen is an additional vgic injection.  We also clear
+	 * the pending state to maintain proper semantics for edge HW
+	 * interrupts.
+	 */
+	vgic_irq_set_phys_pending(irq, false);
+	if (!irq->active)
+		vgic_irq_set_phys_active(irq, false);
+}
+
 void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu,
 			      gpa_t addr, unsigned int len,
 			      unsigned long val)
 {
+	bool is_uaccess = !vgic_get_mmio_requester_vcpu();
 	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
 	int i;
 	unsigned long flags;
@@ -154,7 +216,10 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu,
 
 		spin_lock_irqsave(&irq->irq_lock, flags);
 
-		irq->pending_latch = false;
+		if (irq->hw)
+			vgic_hw_irq_cpending(vcpu, irq, is_uaccess);
+		else
+			irq->pending_latch = false;
 
 		spin_unlock_irqrestore(&irq->irq_lock, flags);
 		vgic_put_irq(vcpu->kvm, irq);
@@ -181,27 +246,24 @@ unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu,
 	return value;
 }
 
+/* Must be called with irq->irq_lock held */
+static void vgic_hw_irq_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
+				      bool active, bool is_uaccess)
+{
+	if (is_uaccess)
+		return;
+
+	irq->active = active;
+	vgic_irq_set_phys_active(irq, active);
+}
+
 static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
-				    bool new_active_state)
+				    bool active)
 {
-	struct kvm_vcpu *requester_vcpu;
 	unsigned long flags;
-	spin_lock_irqsave(&irq->irq_lock, flags);
+	struct kvm_vcpu *requester_vcpu = vgic_get_mmio_requester_vcpu();
 
-	/*
-	 * The vcpu parameter here can mean multiple things depending on how
-	 * this function is called; when handling a trap from the kernel it
-	 * depends on the GIC version, and these functions are also called as
-	 * part of save/restore from userspace.
-	 *
-	 * Therefore, we have to figure out the requester in a reliable way.
-	 *
-	 * When accessing VGIC state from user space, the requester_vcpu is
-	 * NULL, which is fine, because we guarantee that no VCPUs are running
-	 * when accessing VGIC state from user space so irq->vcpu->cpu is
-	 * always -1.
-	 */
-	requester_vcpu = kvm_arm_get_running_vcpu();
+	spin_lock_irqsave(&irq->irq_lock, flags);
 
 	/*
 	 * If this virtual IRQ was written into a list register, we
@@ -213,14 +275,23 @@ static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
 	 * vgic_change_active_prepare)  and still has to sync back this IRQ,
 	 * so we release and re-acquire the spin_lock to let the other thread
 	 * sync back the IRQ.
+	 *
+	 * When accessing VGIC state from user space, requester_vcpu is
+	 * NULL, which is fine, because we guarantee that no VCPUs are running
+	 * when accessing VGIC state from user space so irq->vcpu->cpu is
+	 * always -1.
 	 */
 	while (irq->vcpu && /* IRQ may have state in an LR somewhere */
 	       irq->vcpu != requester_vcpu && /* Current thread is not the VCPU thread */
 	       irq->vcpu->cpu != -1) /* VCPU thread is running */
 		cond_resched_lock(&irq->irq_lock);
 
-	irq->active = new_active_state;
-	if (new_active_state)
+	if (irq->hw)
+		vgic_hw_irq_change_active(vcpu, irq, active, !requester_vcpu);
+	else
+		irq->active = active;
+
+	if (irq->active)
 		vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
 	else
 		spin_unlock_irqrestore(&irq->irq_lock, flags);
diff --git a/virt/kvm/arm/vgic/vgic-v2.c b/virt/kvm/arm/vgic/vgic-v2.c
index 8089710..c32d7b9 100644
--- a/virt/kvm/arm/vgic/vgic-v2.c
+++ b/virt/kvm/arm/vgic/vgic-v2.c
@@ -105,6 +105,26 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu)
 				irq->pending_latch = false;
 		}
 
+		/*
+		 * Level-triggered mapped IRQs are special because we only
+		 * observe rising edges as input to the VGIC.
+		 *
+		 * If the guest never acked the interrupt we have to sample
+		 * the physical line and set the line level, because the
+		 * device state could have changed or we simply need to
+		 * process the still pending interrupt later.
+		 *
+		 * If this causes us to lower the level, we have to also clear
+		 * the physical active state, since we will otherwise never be
+		 * told when the interrupt becomes asserted again.
+		 */
+		if (vgic_irq_is_mapped_level(irq) && (val & GICH_LR_PENDING_BIT)) {
+			irq->line_level = vgic_get_phys_line_level(irq);
+
+			if (!irq->line_level)
+				vgic_irq_set_phys_active(irq, false);
+		}
+
 		spin_unlock_irqrestore(&irq->irq_lock, flags);
 		vgic_put_irq(vcpu->kvm, irq);
 	}
@@ -162,6 +182,15 @@ void vgic_v2_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr)
 			val |= GICH_LR_EOI;
 	}
 
+	/*
+	 * Level-triggered mapped IRQs are special because we only observe
+	 * rising edges as input to the VGIC.  We therefore lower the line
+	 * level here, so that we can take new virtual IRQs.  See
+	 * vgic_v2_fold_lr_state for more info.
+	 */
+	if (vgic_irq_is_mapped_level(irq) && (val & GICH_LR_PENDING_BIT))
+		irq->line_level = false;
+
 	/* The GICv2 LR only holds five bits of priority. */
 	val |= (irq->priority >> 3) << GICH_LR_PRIORITY_SHIFT;
 
diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c
index f47e848..6b32941 100644
--- a/virt/kvm/arm/vgic/vgic-v3.c
+++ b/virt/kvm/arm/vgic/vgic-v3.c
@@ -96,6 +96,26 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
 				irq->pending_latch = false;
 		}
 
+		/*
+		 * Level-triggered mapped IRQs are special because we only
+		 * observe rising edges as input to the VGIC.
+		 *
+		 * If the guest never acked the interrupt we have to sample
+		 * the physical line and set the line level, because the
+		 * device state could have changed or we simply need to
+		 * process the still pending interrupt later.
+		 *
+		 * If this causes us to lower the level, we have to also clear
+		 * the physical active state, since we will otherwise never be
+		 * told when the interrupt becomes asserted again.
+		 */
+		if (vgic_irq_is_mapped_level(irq) && (val & ICH_LR_PENDING_BIT)) {
+			irq->line_level = vgic_get_phys_line_level(irq);
+
+			if (!irq->line_level)
+				vgic_irq_set_phys_active(irq, false);
+		}
+
 		spin_unlock_irqrestore(&irq->irq_lock, flags);
 		vgic_put_irq(vcpu->kvm, irq);
 	}
@@ -146,6 +166,15 @@ void vgic_v3_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr)
 	}
 
 	/*
+	 * Level-triggered mapped IRQs are special because we only observe
+	 * rising edges as input to the VGIC.  We therefore lower the line
+	 * level here, so that we can take new virtual IRQs.  See
+	 * vgic_v3_fold_lr_state for more info.
+	 */
+	if (vgic_irq_is_mapped_level(irq) && (val & ICH_LR_PENDING_BIT))
+		irq->line_level = false;
+
+	/*
 	 * We currently only support Group1 interrupts, which is a
 	 * known defect. This needs to be addressed at some point.
 	 */
diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c
index ecb8e25..c7c5ef1 100644
--- a/virt/kvm/arm/vgic/vgic.c
+++ b/virt/kvm/arm/vgic/vgic.c
@@ -144,6 +144,38 @@ void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq)
 	kfree(irq);
 }
 
+void vgic_irq_set_phys_pending(struct vgic_irq *irq, bool pending)
+{
+	WARN_ON(irq_set_irqchip_state(irq->host_irq,
+				      IRQCHIP_STATE_PENDING,
+				      pending));
+}
+
+bool vgic_get_phys_line_level(struct vgic_irq *irq)
+{
+	bool line_level;
+
+	BUG_ON(!irq->hw);
+
+	if (irq->get_input_level)
+		return irq->get_input_level(irq->intid);
+
+	WARN_ON(irq_get_irqchip_state(irq->host_irq,
+				      IRQCHIP_STATE_PENDING,
+				      &line_level));
+	return line_level;
+}
+
+/* Set/Clear the physical active state */
+void vgic_irq_set_phys_active(struct vgic_irq *irq, bool active)
+{
+
+	BUG_ON(!irq->hw);
+	WARN_ON(irq_set_irqchip_state(irq->host_irq,
+				      IRQCHIP_STATE_ACTIVE,
+				      active));
+}
+
 /**
  * kvm_vgic_target_oracle - compute the target vcpu for an irq
  *
@@ -413,7 +445,8 @@ int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int intid,
 
 /* @irq->irq_lock must be held */
 static int kvm_vgic_map_irq(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
-			    unsigned int host_irq)
+			    unsigned int host_irq,
+			    bool (*get_input_level)(int vindid))
 {
 	struct irq_desc *desc;
 	struct irq_data *data;
@@ -433,6 +466,7 @@ static int kvm_vgic_map_irq(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
 	irq->hw = true;
 	irq->host_irq = host_irq;
 	irq->hwintid = data->hwirq;
+	irq->get_input_level = get_input_level;
 	return 0;
 }
 
@@ -441,10 +475,11 @@ static inline void kvm_vgic_unmap_irq(struct vgic_irq *irq)
 {
 	irq->hw = false;
 	irq->hwintid = 0;
+	irq->get_input_level = NULL;
 }
 
 int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, unsigned int host_irq,
-			  u32 vintid)
+			  u32 vintid, bool (*get_input_level)(int vindid))
 {
 	struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, vintid);
 	unsigned long flags;
@@ -453,7 +488,7 @@ int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, unsigned int host_irq,
 	BUG_ON(!irq);
 
 	spin_lock_irqsave(&irq->irq_lock, flags);
-	ret = kvm_vgic_map_irq(vcpu, irq, host_irq);
+	ret = kvm_vgic_map_irq(vcpu, irq, host_irq, get_input_level);
 	spin_unlock_irqrestore(&irq->irq_lock, flags);
 	vgic_put_irq(vcpu->kvm, irq);
 
diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h
index efbcf8f..12c37b8 100644
--- a/virt/kvm/arm/vgic/vgic.h
+++ b/virt/kvm/arm/vgic/vgic.h
@@ -104,6 +104,11 @@ static inline bool irq_is_pending(struct vgic_irq *irq)
 		return irq->pending_latch || irq->line_level;
 }
 
+static inline bool vgic_irq_is_mapped_level(struct vgic_irq *irq)
+{
+	return irq->config == VGIC_CONFIG_LEVEL && irq->hw;
+}
+
 /*
  * This struct provides an intermediate representation of the fields contained
  * in the GICH_VMCR and ICH_VMCR registers, such that code exporting the GIC
@@ -140,6 +145,9 @@ vgic_get_mmio_region(struct kvm_vcpu *vcpu, struct vgic_io_device *iodev,
 struct vgic_irq *vgic_get_irq(struct kvm *kvm, struct kvm_vcpu *vcpu,
 			      u32 intid);
 void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq);
+bool vgic_get_phys_line_level(struct vgic_irq *irq);
+void vgic_irq_set_phys_pending(struct vgic_irq *irq, bool pending);
+void vgic_irq_set_phys_active(struct vgic_irq *irq, bool active);
 bool vgic_queue_irq_unlock(struct kvm *kvm, struct vgic_irq *irq,
 			   unsigned long flags);
 void vgic_kick_vcpus(struct kvm *kvm);