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

Pull KVM updates from Paolo Bonzini:
 "ARM:
   - HYP mode stub supports kexec/kdump on 32-bit
   - improved PMU support
   - virtual interrupt controller performance improvements
   - support for userspace virtual interrupt controller (slower, but
     necessary for KVM on the weird Broadcom SoCs used by the Raspberry
     Pi 3)

  MIPS:
   - basic support for hardware virtualization (ImgTec P5600/P6600/I6400
     and Cavium Octeon III)

  PPC:
   - in-kernel acceleration for VFIO

  s390:
   - support for guests without storage keys
   - adapter interruption suppression

  x86:
   - usual range of nVMX improvements, notably nested EPT support for
     accessed and dirty bits
   - emulation of CPL3 CPUID faulting

  generic:
   - first part of VCPU thread request API
   - kvm_stat improvements"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (227 commits)
  kvm: nVMX: Don't validate disabled secondary controls
  KVM: put back #ifndef CONFIG_S390 around kvm_vcpu_kick
  Revert "KVM: Support vCPU-based gfn->hva cache"
  tools/kvm: fix top level makefile
  KVM: x86: don't hold kvm->lock in KVM_SET_GSI_ROUTING
  KVM: Documentation: remove VM mmap documentation
  kvm: nVMX: Remove superfluous VMX instruction fault checks
  KVM: x86: fix emulation of RSM and IRET instructions
  KVM: mark requests that need synchronization
  KVM: return if kvm_vcpu_wake_up() did wake up the VCPU
  KVM: add explicit barrier to kvm_vcpu_kick
  KVM: perform a wake_up in kvm_make_all_cpus_request
  KVM: mark requests that do not need a wakeup
  KVM: remove #ifndef CONFIG_S390 around kvm_vcpu_wake_up
  KVM: x86: always use kvm_make_request instead of set_bit
  KVM: add kvm_{test,clear}_request to replace {test,clear}_bit
  s390: kvm: Cpu model support for msa6, msa7 and msa8
  KVM: x86: remove irq disablement around KVM_SET_CLOCK/KVM_GET_CLOCK
  kvm: better MWAIT emulation for guests
  KVM: x86: virtualize cpuid faulting
  ...

13 files changed, 540 insertions, 369 deletions

diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index 35d7100e0815..5976609ef27c 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -184,28 +184,47 @@ bool kvm_timer_should_fire(struct arch_timer_context *timer_ctx)
 	return cval <= now;
 }
 
+/*
+ * Reflect the timer output level into the kvm_run structure
+ */
+void kvm_timer_update_run(struct kvm_vcpu *vcpu)
+{
+	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
+	struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);
+	struct kvm_sync_regs *regs = &vcpu->run->s.regs;
+
+	/* 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)
+		regs->device_irq_level |= KVM_ARM_DEV_EL1_VTIMER;
+	if (ptimer->irq.level)
+		regs->device_irq_level |= KVM_ARM_DEV_EL1_PTIMER;
+}
+
 static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level,
 				 struct arch_timer_context *timer_ctx)
 {
 	int ret;
 
-	BUG_ON(!vgic_initialized(vcpu->kvm));
-
 	timer_ctx->active_cleared_last = false;
 	timer_ctx->irq.level = new_level;
 	trace_kvm_timer_update_irq(vcpu->vcpu_id, timer_ctx->irq.irq,
 				   timer_ctx->irq.level);
 
-	ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id, timer_ctx->irq.irq,
-				  timer_ctx->irq.level);
-	WARN_ON(ret);
+	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);
+		WARN_ON(ret);
+	}
 }
 
 /*
  * Check if there was a change in the timer state (should we raise or lower
  * the line level to the GIC).
  */
-static int kvm_timer_update_state(struct kvm_vcpu *vcpu)
+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);
@@ -217,16 +236,14 @@ static int kvm_timer_update_state(struct kvm_vcpu *vcpu)
 	 * because the guest would never see the interrupt.  Instead wait
 	 * until we call this function from kvm_timer_flush_hwstate.
 	 */
-	if (!vgic_initialized(vcpu->kvm) || !timer->enabled)
-		return -ENODEV;
+	if (unlikely(!timer->enabled))
+		return;
 
 	if (kvm_timer_should_fire(vtimer) != vtimer->irq.level)
 		kvm_timer_update_irq(vcpu, !vtimer->irq.level, vtimer);
 
 	if (kvm_timer_should_fire(ptimer) != ptimer->irq.level)
 		kvm_timer_update_irq(vcpu, !ptimer->irq.level, ptimer);
-
-	return 0;
 }
 
 /* Schedule the background timer for the emulated timer. */
@@ -286,25 +303,12 @@ void kvm_timer_unschedule(struct kvm_vcpu *vcpu)
 	timer_disarm(timer);
 }
 
-/**
- * kvm_timer_flush_hwstate - prepare to move the virt timer to the cpu
- * @vcpu: The vcpu pointer
- *
- * Check if the virtual timer has expired while we were running in the host,
- * and inject an interrupt if that was the case.
- */
-void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu)
+static void kvm_timer_flush_hwstate_vgic(struct kvm_vcpu *vcpu)
 {
 	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
 	bool phys_active;
 	int ret;
 
-	if (kvm_timer_update_state(vcpu))
-		return;
-
-	/* Set the background timer for the physical timer emulation. */
-	kvm_timer_emulate(vcpu, vcpu_ptimer(vcpu));
-
 	/*
 	* If we enter the guest with the virtual input level to the VGIC
 	* asserted, then we have already told the VGIC what we need to, and
@@ -356,11 +360,72 @@ void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu)
 	vtimer->active_cleared_last = !phys_active;
 }
 
+bool kvm_timer_should_notify_user(struct kvm_vcpu *vcpu)
+{
+	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
+	struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);
+	struct kvm_sync_regs *sregs = &vcpu->run->s.regs;
+	bool vlevel, plevel;
+
+	if (likely(irqchip_in_kernel(vcpu->kvm)))
+		return false;
+
+	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;
+}
+
+static void kvm_timer_flush_hwstate_user(struct kvm_vcpu *vcpu)
+{
+	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
+
+	/*
+	 * To prevent continuously exiting from the guest, we mask the
+	 * physical interrupt such that the guest can make forward progress.
+	 * Once we detect the output level being deasserted, we unmask the
+	 * interrupt again so that we exit from the guest when the timer
+	 * fires.
+	*/
+	if (vtimer->irq.level)
+		disable_percpu_irq(host_vtimer_irq);
+	else
+		enable_percpu_irq(host_vtimer_irq, 0);
+}
+
+/**
+ * kvm_timer_flush_hwstate - prepare timers before running the vcpu
+ * @vcpu: The vcpu pointer
+ *
+ * Check if the virtual timer has expired while we were running in the host,
+ * and inject an interrupt if that was the case, making sure the timer is
+ * masked or disabled on the host so that we keep executing.  Also schedule a
+ * software timer for the physical timer if it is enabled.
+ */
+void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu)
+{
+	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
+
+	if (unlikely(!timer->enabled))
+		return;
+
+	kvm_timer_update_state(vcpu);
+
+	/* Set the background timer for the physical timer emulation. */
+	kvm_timer_emulate(vcpu, vcpu_ptimer(vcpu));
+
+	if (unlikely(!irqchip_in_kernel(vcpu->kvm)))
+		kvm_timer_flush_hwstate_user(vcpu);
+	else
+		kvm_timer_flush_hwstate_vgic(vcpu);
+}
+
 /**
  * kvm_timer_sync_hwstate - sync timer state from cpu
  * @vcpu: The vcpu pointer
  *
- * Check if the virtual timer has expired while we were running in the guest,
+ * 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)
@@ -560,6 +625,13 @@ int kvm_timer_enable(struct kvm_vcpu *vcpu)
 	if (timer->enabled)
 		return 0;
 
+	/* Without a VGIC we do not map virtual IRQs to physical IRQs */
+	if (!irqchip_in_kernel(vcpu->kvm))
+		goto no_vgic;
+
+	if (!vgic_initialized(vcpu->kvm))
+		return -ENODEV;
+
 	/*
 	 * Find the physical IRQ number corresponding to the host_vtimer_irq
 	 */
@@ -583,8 +655,8 @@ int kvm_timer_enable(struct kvm_vcpu *vcpu)
 	if (ret)
 		return ret;
 
+no_vgic:
 	timer->enabled = 1;
-
 	return 0;
 }
 
diff --git a/virt/kvm/arm/hyp/vgic-v2-sr.c b/virt/kvm/arm/hyp/vgic-v2-sr.c
index c8aeb7b91ec8..a3f18d362366 100644
--- a/virt/kvm/arm/hyp/vgic-v2-sr.c
+++ b/virt/kvm/arm/hyp/vgic-v2-sr.c
@@ -22,49 +22,6 @@
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_hyp.h>
 
-static void __hyp_text save_maint_int_state(struct kvm_vcpu *vcpu,
-					    void __iomem *base)
-{
-	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
-	int nr_lr = (kern_hyp_va(&kvm_vgic_global_state))->nr_lr;
-	u32 eisr0, eisr1;
-	int i;
-	bool expect_mi;
-
-	expect_mi = !!(cpu_if->vgic_hcr & GICH_HCR_UIE);
-
-	for (i = 0; i < nr_lr; i++) {
-		if (!(vcpu->arch.vgic_cpu.live_lrs & (1UL << i)))
-				continue;
-
-		expect_mi |= (!(cpu_if->vgic_lr[i] & GICH_LR_HW) &&
-			      (cpu_if->vgic_lr[i] & GICH_LR_EOI));
-	}
-
-	if (expect_mi) {
-		cpu_if->vgic_misr = readl_relaxed(base + GICH_MISR);
-
-		if (cpu_if->vgic_misr & GICH_MISR_EOI) {
-			eisr0  = readl_relaxed(base + GICH_EISR0);
-			if (unlikely(nr_lr > 32))
-				eisr1  = readl_relaxed(base + GICH_EISR1);
-			else
-				eisr1 = 0;
-		} else {
-			eisr0 = eisr1 = 0;
-		}
-	} else {
-		cpu_if->vgic_misr = 0;
-		eisr0 = eisr1 = 0;
-	}
-
-#ifdef CONFIG_CPU_BIG_ENDIAN
-	cpu_if->vgic_eisr = ((u64)eisr0 << 32) | eisr1;
-#else
-	cpu_if->vgic_eisr = ((u64)eisr1 << 32) | eisr0;
-#endif
-}
-
 static void __hyp_text save_elrsr(struct kvm_vcpu *vcpu, void __iomem *base)
 {
 	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
@@ -87,13 +44,10 @@ static void __hyp_text save_elrsr(struct kvm_vcpu *vcpu, void __iomem *base)
 static void __hyp_text save_lrs(struct kvm_vcpu *vcpu, void __iomem *base)
 {
 	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
-	int nr_lr = (kern_hyp_va(&kvm_vgic_global_state))->nr_lr;
 	int i;
+	u64 used_lrs = vcpu->arch.vgic_cpu.used_lrs;
 
-	for (i = 0; i < nr_lr; i++) {
-		if (!(vcpu->arch.vgic_cpu.live_lrs & (1UL << i)))
-			continue;
-
+	for (i = 0; i < used_lrs; i++) {
 		if (cpu_if->vgic_elrsr & (1UL << i))
 			cpu_if->vgic_lr[i] &= ~GICH_LR_STATE;
 		else
@@ -110,26 +64,20 @@ void __hyp_text __vgic_v2_save_state(struct kvm_vcpu *vcpu)
 	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
 	struct vgic_dist *vgic = &kvm->arch.vgic;
 	void __iomem *base = kern_hyp_va(vgic->vctrl_base);
+	u64 used_lrs = vcpu->arch.vgic_cpu.used_lrs;
 
 	if (!base)
 		return;
 
-	cpu_if->vgic_vmcr = readl_relaxed(base + GICH_VMCR);
-
-	if (vcpu->arch.vgic_cpu.live_lrs) {
+	if (used_lrs) {
 		cpu_if->vgic_apr = readl_relaxed(base + GICH_APR);
 
-		save_maint_int_state(vcpu, base);
 		save_elrsr(vcpu, base);
 		save_lrs(vcpu, base);
 
 		writel_relaxed(0, base + GICH_HCR);
-
-		vcpu->arch.vgic_cpu.live_lrs = 0;
 	} else {
-		cpu_if->vgic_eisr = 0;
 		cpu_if->vgic_elrsr = ~0UL;
-		cpu_if->vgic_misr = 0;
 		cpu_if->vgic_apr = 0;
 	}
 }
@@ -141,32 +89,20 @@ void __hyp_text __vgic_v2_restore_state(struct kvm_vcpu *vcpu)
 	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
 	struct vgic_dist *vgic = &kvm->arch.vgic;
 	void __iomem *base = kern_hyp_va(vgic->vctrl_base);
-	int nr_lr = (kern_hyp_va(&kvm_vgic_global_state))->nr_lr;
 	int i;
-	u64 live_lrs = 0;
+	u64 used_lrs = vcpu->arch.vgic_cpu.used_lrs;
 
 	if (!base)
 		return;
 
-
-	for (i = 0; i < nr_lr; i++)
-		if (cpu_if->vgic_lr[i] & GICH_LR_STATE)
-			live_lrs |= 1UL << i;
-
-	if (live_lrs) {
+	if (used_lrs) {
 		writel_relaxed(cpu_if->vgic_hcr, base + GICH_HCR);
 		writel_relaxed(cpu_if->vgic_apr, base + GICH_APR);
-		for (i = 0; i < nr_lr; i++) {
-			if (!(live_lrs & (1UL << i)))
-				continue;
-
+		for (i = 0; i < used_lrs; i++) {
 			writel_relaxed(cpu_if->vgic_lr[i],
 				       base + GICH_LR0 + (i * 4));
 		}
 	}
-
-	writel_relaxed(cpu_if->vgic_vmcr, base + GICH_VMCR);
-	vcpu->arch.vgic_cpu.live_lrs = live_lrs;
 }
 
 #ifdef CONFIG_ARM64
diff --git a/virt/kvm/arm/hyp/vgic-v3-sr.c b/virt/kvm/arm/hyp/vgic-v3-sr.c
index 3947095cc0a1..bce6037cf01d 100644
--- a/virt/kvm/arm/hyp/vgic-v3-sr.c
+++ b/virt/kvm/arm/hyp/vgic-v3-sr.c
@@ -118,66 +118,32 @@ static void __hyp_text __gic_v3_set_lr(u64 val, int lr)
 	}
 }
 
-static void __hyp_text save_maint_int_state(struct kvm_vcpu *vcpu, int nr_lr)
-{
-	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
-	int i;
-	bool expect_mi;
-
-	expect_mi = !!(cpu_if->vgic_hcr & ICH_HCR_UIE);
-
-	for (i = 0; i < nr_lr; i++) {
-		if (!(vcpu->arch.vgic_cpu.live_lrs & (1UL << i)))
-				continue;
-
-		expect_mi |= (!(cpu_if->vgic_lr[i] & ICH_LR_HW) &&
-			      (cpu_if->vgic_lr[i] & ICH_LR_EOI));
-	}
-
-	if (expect_mi) {
-		cpu_if->vgic_misr  = read_gicreg(ICH_MISR_EL2);
-
-		if (cpu_if->vgic_misr & ICH_MISR_EOI)
-			cpu_if->vgic_eisr = read_gicreg(ICH_EISR_EL2);
-		else
-			cpu_if->vgic_eisr = 0;
-	} else {
-		cpu_if->vgic_misr = 0;
-		cpu_if->vgic_eisr = 0;
-	}
-}
-
 void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
+	u64 used_lrs = vcpu->arch.vgic_cpu.used_lrs;
 	u64 val;
 
 	/*
 	 * Make sure stores to the GIC via the memory mapped interface
 	 * are now visible to the system register interface.
 	 */
-	if (!cpu_if->vgic_sre)
+	if (!cpu_if->vgic_sre) {
 		dsb(st);
+		cpu_if->vgic_vmcr = read_gicreg(ICH_VMCR_EL2);
+	}
 
-	cpu_if->vgic_vmcr  = read_gicreg(ICH_VMCR_EL2);
-
-	if (vcpu->arch.vgic_cpu.live_lrs) {
+	if (used_lrs) {
 		int i;
-		u32 max_lr_idx, nr_pri_bits;
+		u32 nr_pri_bits;
 
 		cpu_if->vgic_elrsr = read_gicreg(ICH_ELSR_EL2);
 
 		write_gicreg(0, ICH_HCR_EL2);
 		val = read_gicreg(ICH_VTR_EL2);
-		max_lr_idx = vtr_to_max_lr_idx(val);
 		nr_pri_bits = vtr_to_nr_pri_bits(val);
 
-		save_maint_int_state(vcpu, max_lr_idx + 1);
-
-		for (i = 0; i <= max_lr_idx; i++) {
-			if (!(vcpu->arch.vgic_cpu.live_lrs & (1UL << i)))
-				continue;
-
+		for (i = 0; i < used_lrs; i++) {
 			if (cpu_if->vgic_elrsr & (1 << i))
 				cpu_if->vgic_lr[i] &= ~ICH_LR_STATE;
 			else
@@ -205,11 +171,7 @@ void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu)
 		default:
 			cpu_if->vgic_ap1r[0] = read_gicreg(ICH_AP1R0_EL2);
 		}
-
-		vcpu->arch.vgic_cpu.live_lrs = 0;
 	} else {
-		cpu_if->vgic_misr  = 0;
-		cpu_if->vgic_eisr  = 0;
 		cpu_if->vgic_elrsr = 0xffff;
 		cpu_if->vgic_ap0r[0] = 0;
 		cpu_if->vgic_ap0r[1] = 0;
@@ -234,9 +196,9 @@ void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu)
 void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
+	u64 used_lrs = vcpu->arch.vgic_cpu.used_lrs;
 	u64 val;
-	u32 max_lr_idx, nr_pri_bits;
-	u16 live_lrs = 0;
+	u32 nr_pri_bits;
 	int i;
 
 	/*
@@ -245,25 +207,19 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
 	 * delivered as a FIQ to the guest, with potentially fatal
 	 * consequences. So we must make sure that ICC_SRE_EL1 has
 	 * been actually programmed with the value we want before
-	 * starting to mess with the rest of the GIC.
+	 * starting to mess with the rest of the GIC, and VMCR_EL2 in
+	 * particular.
 	 */
 	if (!cpu_if->vgic_sre) {
 		write_gicreg(0, ICC_SRE_EL1);
 		isb();
+		write_gicreg(cpu_if->vgic_vmcr, ICH_VMCR_EL2);
 	}
 
 	val = read_gicreg(ICH_VTR_EL2);
-	max_lr_idx = vtr_to_max_lr_idx(val);
 	nr_pri_bits = vtr_to_nr_pri_bits(val);
 
-	for (i = 0; i <= max_lr_idx; i++) {
-		if (cpu_if->vgic_lr[i] & ICH_LR_STATE)
-			live_lrs |= (1 << i);
-	}
-
-	write_gicreg(cpu_if->vgic_vmcr, ICH_VMCR_EL2);
-
-	if (live_lrs) {
+	if (used_lrs) {
 		write_gicreg(cpu_if->vgic_hcr, ICH_HCR_EL2);
 
 		switch (nr_pri_bits) {
@@ -286,12 +242,8 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
 			write_gicreg(cpu_if->vgic_ap1r[0], ICH_AP1R0_EL2);
 		}
 
-		for (i = 0; i <= max_lr_idx; i++) {
-			if (!(live_lrs & (1 << i)))
-				continue;
-
+		for (i = 0; i < used_lrs; i++)
 			__gic_v3_set_lr(cpu_if->vgic_lr[i], i);
-		}
 	}
 
 	/*
@@ -303,7 +255,6 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
 		isb();
 		dsb(sy);
 	}
-	vcpu->arch.vgic_cpu.live_lrs = live_lrs;
 
 	/*
 	 * Prevent the guest from touching the GIC system registers if
@@ -326,3 +277,13 @@ u64 __hyp_text __vgic_v3_get_ich_vtr_el2(void)
 {
 	return read_gicreg(ICH_VTR_EL2);
 }
+
+u64 __hyp_text __vgic_v3_read_vmcr(void)
+{
+	return read_gicreg(ICH_VMCR_EL2);
+}
+
+void __hyp_text __vgic_v3_write_vmcr(u32 vmcr)
+{
+	write_gicreg(vmcr, ICH_VMCR_EL2);
+}
diff --git a/virt/kvm/arm/pmu.c b/virt/kvm/arm/pmu.c
index 69ccce308458..4b43e7f3b158 100644
--- a/virt/kvm/arm/pmu.c
+++ b/virt/kvm/arm/pmu.c
@@ -230,13 +230,44 @@ static void kvm_pmu_update_state(struct kvm_vcpu *vcpu)
 		return;
 
 	overflow = !!kvm_pmu_overflow_status(vcpu);
-	if (pmu->irq_level != overflow) {
-		pmu->irq_level = overflow;
-		kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id,
-				    pmu->irq_num, overflow);
+	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);
 	}
 }
 
+bool kvm_pmu_should_notify_user(struct kvm_vcpu *vcpu)
+{
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+	struct kvm_sync_regs *sregs = &vcpu->run->s.regs;
+	bool run_level = sregs->device_irq_level & KVM_ARM_DEV_PMU;
+
+	if (likely(irqchip_in_kernel(vcpu->kvm)))
+		return false;
+
+	return pmu->irq_level != run_level;
+}
+
+/*
+ * Reflect the PMU overflow interrupt output level into the kvm_run structure
+ */
+void kvm_pmu_update_run(struct kvm_vcpu *vcpu)
+{
+	struct kvm_sync_regs *regs = &vcpu->run->s.regs;
+
+	/* Populate the timer bitmap for user space */
+	regs->device_irq_level &= ~KVM_ARM_DEV_PMU;
+	if (vcpu->arch.pmu.irq_level)
+		regs->device_irq_level |= KVM_ARM_DEV_PMU;
+}
+
 /**
  * kvm_pmu_flush_hwstate - flush pmu state to cpu
  * @vcpu: The vcpu pointer
diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c
index 702f8108608d..25fd1b942c11 100644
--- a/virt/kvm/arm/vgic/vgic-init.c
+++ b/virt/kvm/arm/vgic/vgic-init.c
@@ -24,7 +24,12 @@
 
 /*
  * Initialization rules: there are multiple stages to the vgic
- * initialization, both for the distributor and the CPU interfaces.
+ * initialization, both for the distributor and the CPU interfaces.  The basic
+ * idea is that even though the VGIC is not functional or not requested from
+ * user space, the critical path of the run loop can still call VGIC functions
+ * that just won't do anything, without them having to check additional
+ * initialization flags to ensure they don't look at uninitialized data
+ * structures.
  *
  * Distributor:
  *
@@ -39,23 +44,67 @@
  *
  * CPU Interface:
  *
- * - kvm_vgic_cpu_early_init(): initialization of static data that
+ * - kvm_vgic_vcpu_early_init(): initialization of static data that
  *   doesn't depend on any sizing information or emulation type. No
  *   allocation is allowed there.
  */
 
 /* EARLY INIT */
 
-/*
- * Those 2 functions should not be needed anymore but they
- * still are called from arm.c
+/**
+ * kvm_vgic_early_init() - Initialize static VGIC VCPU data structures
+ * @kvm: The VM whose VGIC districutor should be initialized
+ *
+ * Only do initialization of static structures that don't require any
+ * allocation or sizing information from userspace.  vgic_init() called
+ * kvm_vgic_dist_init() which takes care of the rest.
  */
 void kvm_vgic_early_init(struct kvm *kvm)
 {
+	struct vgic_dist *dist = &kvm->arch.vgic;
+
+	INIT_LIST_HEAD(&dist->lpi_list_head);
+	spin_lock_init(&dist->lpi_list_lock);
 }
 
+/**
+ * kvm_vgic_vcpu_early_init() - Initialize static VGIC VCPU data structures
+ * @vcpu: The VCPU whose VGIC data structures whould be initialized
+ *
+ * Only do initialization, but do not actually enable the VGIC CPU interface
+ * yet.
+ */
 void kvm_vgic_vcpu_early_init(struct kvm_vcpu *vcpu)
 {
+	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+	int i;
+
+	INIT_LIST_HEAD(&vgic_cpu->ap_list_head);
+	spin_lock_init(&vgic_cpu->ap_list_lock);
+
+	/*
+	 * Enable and configure all SGIs to be edge-triggered and
+	 * configure all PPIs as level-triggered.
+	 */
+	for (i = 0; i < VGIC_NR_PRIVATE_IRQS; i++) {
+		struct vgic_irq *irq = &vgic_cpu->private_irqs[i];
+
+		INIT_LIST_HEAD(&irq->ap_list);
+		spin_lock_init(&irq->irq_lock);
+		irq->intid = i;
+		irq->vcpu = NULL;
+		irq->target_vcpu = vcpu;
+		irq->targets = 1U << vcpu->vcpu_id;
+		kref_init(&irq->refcount);
+		if (vgic_irq_is_sgi(i)) {
+			/* SGIs */
+			irq->enabled = 1;
+			irq->config = VGIC_CONFIG_EDGE;
+		} else {
+			/* PPIs */
+			irq->config = VGIC_CONFIG_LEVEL;
+		}
+	}
 }
 
 /* CREATION */
@@ -148,9 +197,6 @@ static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis)
 	struct kvm_vcpu *vcpu0 = kvm_get_vcpu(kvm, 0);
 	int i;
 
-	INIT_LIST_HEAD(&dist->lpi_list_head);
-	spin_lock_init(&dist->lpi_list_lock);
-
 	dist->spis = kcalloc(nr_spis, sizeof(struct vgic_irq), GFP_KERNEL);
 	if (!dist->spis)
 		return  -ENOMEM;
@@ -181,41 +227,11 @@ static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis)
 }
 
 /**
- * kvm_vgic_vcpu_init: initialize the vcpu data structures and
- * enable the VCPU interface
- * @vcpu: the VCPU which's VGIC should be initialized
+ * kvm_vgic_vcpu_init() - Enable the VCPU interface
+ * @vcpu: the VCPU which's VGIC should be enabled
  */
 static void kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
 {
-	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
-	int i;
-
-	INIT_LIST_HEAD(&vgic_cpu->ap_list_head);
-	spin_lock_init(&vgic_cpu->ap_list_lock);
-
-	/*
-	 * Enable and configure all SGIs to be edge-triggered and
-	 * configure all PPIs as level-triggered.
-	 */
-	for (i = 0; i < VGIC_NR_PRIVATE_IRQS; i++) {
-		struct vgic_irq *irq = &vgic_cpu->private_irqs[i];
-
-		INIT_LIST_HEAD(&irq->ap_list);
-		spin_lock_init(&irq->irq_lock);
-		irq->intid = i;
-		irq->vcpu = NULL;
-		irq->target_vcpu = vcpu;
-		irq->targets = 1U << vcpu->vcpu_id;
-		kref_init(&irq->refcount);
-		if (vgic_irq_is_sgi(i)) {
-			/* SGIs */
-			irq->enabled = 1;
-			irq->config = VGIC_CONFIG_EDGE;
-		} else {
-			/* PPIs */
-			irq->config = VGIC_CONFIG_LEVEL;
-		}
-	}
 	if (kvm_vgic_global_state.type == VGIC_V2)
 		vgic_v2_enable(vcpu);
 	else
@@ -262,6 +278,18 @@ int vgic_init(struct kvm *kvm)
 	vgic_debug_init(kvm);
 
 	dist->initialized = true;
+
+	/*
+	 * If we're initializing GICv2 on-demand when first running the VCPU
+	 * then we need to load the VGIC state onto the CPU.  We can detect
+	 * this easily by checking if we are in between vcpu_load and vcpu_put
+	 * when we just initialized the VGIC.
+	 */
+	preempt_disable();
+	vcpu = kvm_arm_get_running_vcpu();
+	if (vcpu)
+		kvm_vgic_load(vcpu);
+	preempt_enable();
 out:
 	return ret;
 }
diff --git a/virt/kvm/arm/vgic/vgic-v2.c b/virt/kvm/arm/vgic/vgic-v2.c
index b637d9c7afe3..a65757aab6d3 100644
--- a/virt/kvm/arm/vgic/vgic-v2.c
+++ b/virt/kvm/arm/vgic/vgic-v2.c
@@ -22,20 +22,6 @@
 
 #include "vgic.h"
 
-/*
- * Call this function to convert a u64 value to an unsigned long * bitmask
- * in a way that works on both 32-bit and 64-bit LE and BE platforms.
- *
- * Warning: Calling this function may modify *val.
- */
-static unsigned long *u64_to_bitmask(u64 *val)
-{
-#if defined(CONFIG_CPU_BIG_ENDIAN) && BITS_PER_LONG == 32
-	*val = (*val >> 32) | (*val << 32);
-#endif
-	return (unsigned long *)val;
-}
-
 static inline void vgic_v2_write_lr(int lr, u32 val)
 {
 	void __iomem *base = kvm_vgic_global_state.vctrl_base;
@@ -51,45 +37,17 @@ void vgic_v2_init_lrs(void)
 		vgic_v2_write_lr(i, 0);
 }
 
-void vgic_v2_process_maintenance(struct kvm_vcpu *vcpu)
+void vgic_v2_set_underflow(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v2_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v2;
 
-	if (cpuif->vgic_misr & GICH_MISR_EOI) {
-		u64 eisr = cpuif->vgic_eisr;
-		unsigned long *eisr_bmap = u64_to_bitmask(&eisr);
-		int lr;
-
-		for_each_set_bit(lr, eisr_bmap, kvm_vgic_global_state.nr_lr) {
-			u32 intid = cpuif->vgic_lr[lr] & GICH_LR_VIRTUALID;
-
-			WARN_ON(cpuif->vgic_lr[lr] & GICH_LR_STATE);
-
-			/* Only SPIs require notification */
-			if (vgic_valid_spi(vcpu->kvm, intid))
-				kvm_notify_acked_irq(vcpu->kvm, 0,
-						     intid - VGIC_NR_PRIVATE_IRQS);
-		}
-	}
-
-	/* check and disable underflow maintenance IRQ */
-	cpuif->vgic_hcr &= ~GICH_HCR_UIE;
-
-	/*
-	 * In the next iterations of the vcpu loop, if we sync the
-	 * vgic state after flushing it, but before entering the guest
-	 * (this happens for pending signals and vmid rollovers), then
-	 * make sure we don't pick up any old maintenance interrupts
-	 * here.
-	 */
-	cpuif->vgic_eisr = 0;
+	cpuif->vgic_hcr |= GICH_HCR_UIE;
 }
 
-void vgic_v2_set_underflow(struct kvm_vcpu *vcpu)
+static bool lr_signals_eoi_mi(u32 lr_val)
 {
-	struct vgic_v2_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v2;
-
-	cpuif->vgic_hcr |= GICH_HCR_UIE;
+	return !(lr_val & GICH_LR_STATE) && (lr_val & GICH_LR_EOI) &&
+	       !(lr_val & GICH_LR_HW);
 }
 
 /*
@@ -101,14 +59,22 @@ void vgic_v2_set_underflow(struct kvm_vcpu *vcpu)
  */
 void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu)
 {
-	struct vgic_v2_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v2;
+	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+	struct vgic_v2_cpu_if *cpuif = &vgic_cpu->vgic_v2;
 	int lr;
 
-	for (lr = 0; lr < vcpu->arch.vgic_cpu.used_lrs; lr++) {
+	cpuif->vgic_hcr &= ~GICH_HCR_UIE;
+
+	for (lr = 0; lr < vgic_cpu->used_lrs; lr++) {
 		u32 val = cpuif->vgic_lr[lr];
 		u32 intid = val & GICH_LR_VIRTUALID;
 		struct vgic_irq *irq;
 
+		/* Notify fds when the guest EOI'ed a level-triggered SPI */
+		if (lr_signals_eoi_mi(val) && vgic_valid_spi(vcpu->kvm, intid))
+			kvm_notify_acked_irq(vcpu->kvm, 0,
+					     intid - VGIC_NR_PRIVATE_IRQS);
+
 		irq = vgic_get_irq(vcpu->kvm, vcpu, intid);
 
 		spin_lock(&irq->irq_lock);
@@ -141,6 +107,8 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu)
 		spin_unlock(&irq->irq_lock);
 		vgic_put_irq(vcpu->kvm, irq);
 	}
+
+	vgic_cpu->used_lrs = 0;
 }
 
 /*
@@ -199,6 +167,7 @@ void vgic_v2_clear_lr(struct kvm_vcpu *vcpu, int lr)
 
 void vgic_v2_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
 {
+	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
 	u32 vmcr;
 
 	vmcr  = (vmcrp->ctlr << GICH_VMCR_CTRL_SHIFT) & GICH_VMCR_CTRL_MASK;
@@ -209,12 +178,15 @@ void vgic_v2_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
 	vmcr |= ((vmcrp->pmr >> GICV_PMR_PRIORITY_SHIFT) <<
 		 GICH_VMCR_PRIMASK_SHIFT) & GICH_VMCR_PRIMASK_MASK;
 
-	vcpu->arch.vgic_cpu.vgic_v2.vgic_vmcr = vmcr;
+	cpu_if->vgic_vmcr = vmcr;
 }
 
 void vgic_v2_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
 {
-	u32 vmcr = vcpu->arch.vgic_cpu.vgic_v2.vgic_vmcr;
+	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
+	u32 vmcr;
+
+	vmcr = cpu_if->vgic_vmcr;
 
 	vmcrp->ctlr = (vmcr & GICH_VMCR_CTRL_MASK) >>
 			GICH_VMCR_CTRL_SHIFT;
@@ -390,3 +362,19 @@ out:
 
 	return ret;
 }
+
+void vgic_v2_load(struct kvm_vcpu *vcpu)
+{
+	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
+	struct vgic_dist *vgic = &vcpu->kvm->arch.vgic;
+
+	writel_relaxed(cpu_if->vgic_vmcr, vgic->vctrl_base + GICH_VMCR);
+}
+
+void vgic_v2_put(struct kvm_vcpu *vcpu)
+{
+	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
+	struct vgic_dist *vgic = &vcpu->kvm->arch.vgic;
+
+	cpu_if->vgic_vmcr = readl_relaxed(vgic->vctrl_base + GICH_VMCR);
+}
diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c
index be0f4c3e0142..df1503650300 100644
--- a/virt/kvm/arm/vgic/vgic-v3.c
+++ b/virt/kvm/arm/vgic/vgic-v3.c
@@ -21,59 +21,29 @@
 
 #include "vgic.h"
 
-void vgic_v3_process_maintenance(struct kvm_vcpu *vcpu)
+void vgic_v3_set_underflow(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v3_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v3;
-	u32 model = vcpu->kvm->arch.vgic.vgic_model;
-
-	if (cpuif->vgic_misr & ICH_MISR_EOI) {
-		unsigned long eisr_bmap = cpuif->vgic_eisr;
-		int lr;
-
-		for_each_set_bit(lr, &eisr_bmap, kvm_vgic_global_state.nr_lr) {
-			u32 intid;
-			u64 val = cpuif->vgic_lr[lr];
-
-			if (model == KVM_DEV_TYPE_ARM_VGIC_V3)
-				intid = val & ICH_LR_VIRTUAL_ID_MASK;
-			else
-				intid = val & GICH_LR_VIRTUALID;
-
-			WARN_ON(cpuif->vgic_lr[lr] & ICH_LR_STATE);
-
-			/* Only SPIs require notification */
-			if (vgic_valid_spi(vcpu->kvm, intid))
-				kvm_notify_acked_irq(vcpu->kvm, 0,
-						     intid - VGIC_NR_PRIVATE_IRQS);
-		}
-
-		/*
-		 * In the next iterations of the vcpu loop, if we sync
-		 * the vgic state after flushing it, but before
-		 * entering the guest (this happens for pending
-		 * signals and vmid rollovers), then make sure we
-		 * don't pick up any old maintenance interrupts here.
-		 */
-		cpuif->vgic_eisr = 0;
-	}
 
-	cpuif->vgic_hcr &= ~ICH_HCR_UIE;
+	cpuif->vgic_hcr |= ICH_HCR_UIE;
 }
 
-void vgic_v3_set_underflow(struct kvm_vcpu *vcpu)
+static bool lr_signals_eoi_mi(u64 lr_val)
 {
-	struct vgic_v3_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v3;
-
-	cpuif->vgic_hcr |= ICH_HCR_UIE;
+	return !(lr_val & ICH_LR_STATE) && (lr_val & ICH_LR_EOI) &&
+	       !(lr_val & ICH_LR_HW);
 }
 
 void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
 {
-	struct vgic_v3_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v3;
+	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+	struct vgic_v3_cpu_if *cpuif = &vgic_cpu->vgic_v3;
 	u32 model = vcpu->kvm->arch.vgic.vgic_model;
 	int lr;
 
-	for (lr = 0; lr < vcpu->arch.vgic_cpu.used_lrs; lr++) {
+	cpuif->vgic_hcr &= ~ICH_HCR_UIE;
+
+	for (lr = 0; lr < vgic_cpu->used_lrs; lr++) {
 		u64 val = cpuif->vgic_lr[lr];
 		u32 intid;
 		struct vgic_irq *irq;
@@ -82,6 +52,12 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
 			intid = val & ICH_LR_VIRTUAL_ID_MASK;
 		else
 			intid = val & GICH_LR_VIRTUALID;
+
+		/* Notify fds when the guest EOI'ed a level-triggered IRQ */
+		if (lr_signals_eoi_mi(val) && vgic_valid_spi(vcpu->kvm, intid))
+			kvm_notify_acked_irq(vcpu->kvm, 0,
+					     intid - VGIC_NR_PRIVATE_IRQS);
+
 		irq = vgic_get_irq(vcpu->kvm, vcpu, intid);
 		if (!irq)	/* An LPI could have been unmapped. */
 			continue;
@@ -117,6 +93,8 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
 		spin_unlock(&irq->irq_lock);
 		vgic_put_irq(vcpu->kvm, irq);
 	}
+
+	vgic_cpu->used_lrs = 0;
 }
 
 /* Requires the irq to be locked already */
@@ -173,6 +151,7 @@ void vgic_v3_clear_lr(struct kvm_vcpu *vcpu, int lr)
 
 void vgic_v3_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
 {
+	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
 	u32 vmcr;
 
 	/*
@@ -188,12 +167,15 @@ void vgic_v3_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
 	vmcr |= (vmcrp->grpen0 << ICH_VMCR_ENG0_SHIFT) & ICH_VMCR_ENG0_MASK;
 	vmcr |= (vmcrp->grpen1 << ICH_VMCR_ENG1_SHIFT) & ICH_VMCR_ENG1_MASK;
 
-	vcpu->arch.vgic_cpu.vgic_v3.vgic_vmcr = vmcr;
+	cpu_if->vgic_vmcr = vmcr;
 }
 
 void vgic_v3_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
 {
-	u32 vmcr = vcpu->arch.vgic_cpu.vgic_v3.vgic_vmcr;
+	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
+	u32 vmcr;
+
+	vmcr = cpu_if->vgic_vmcr;
 
 	/*
 	 * Ignore the FIQen bit, because GIC emulation always implies
@@ -386,3 +368,24 @@ int vgic_v3_probe(const struct gic_kvm_info *info)
 
 	return 0;
 }
+
+void vgic_v3_load(struct kvm_vcpu *vcpu)
+{
+	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
+
+	/*
+	 * If dealing with a GICv2 emulation on GICv3, VMCR_EL2.VFIQen
+	 * is dependent on ICC_SRE_EL1.SRE, and we have to perform the
+	 * VMCR_EL2 save/restore in the world switch.
+	 */
+	if (likely(cpu_if->vgic_sre))
+		kvm_call_hyp(__vgic_v3_write_vmcr, cpu_if->vgic_vmcr);
+}
+
+void vgic_v3_put(struct kvm_vcpu *vcpu)
+{
+	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
+
+	if (likely(cpu_if->vgic_sre))
+		cpu_if->vgic_vmcr = kvm_call_hyp(__vgic_v3_read_vmcr);
+}
diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c
index 7713d96e85b7..4346bc7d08dc 100644
--- a/virt/kvm/arm/vgic/vgic.c
+++ b/virt/kvm/arm/vgic/vgic.c
@@ -529,14 +529,6 @@ retry:
 	spin_unlock(&vgic_cpu->ap_list_lock);
 }
 
-static inline void vgic_process_maintenance_interrupt(struct kvm_vcpu *vcpu)
-{
-	if (kvm_vgic_global_state.type == VGIC_V2)
-		vgic_v2_process_maintenance(vcpu);
-	else
-		vgic_v3_process_maintenance(vcpu);
-}
-
 static inline void vgic_fold_lr_state(struct kvm_vcpu *vcpu)
 {
 	if (kvm_vgic_global_state.type == VGIC_V2)
@@ -603,10 +595,8 @@ static void vgic_flush_lr_state(struct kvm_vcpu *vcpu)
 
 	DEBUG_SPINLOCK_BUG_ON(!spin_is_locked(&vgic_cpu->ap_list_lock));
 
-	if (compute_ap_list_depth(vcpu) > kvm_vgic_global_state.nr_lr) {
-		vgic_set_underflow(vcpu);
+	if (compute_ap_list_depth(vcpu) > kvm_vgic_global_state.nr_lr)
 		vgic_sort_ap_list(vcpu);
-	}
 
 	list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) {
 		spin_lock(&irq->irq_lock);
@@ -625,8 +615,12 @@ static void vgic_flush_lr_state(struct kvm_vcpu *vcpu)
 next:
 		spin_unlock(&irq->irq_lock);
 
-		if (count == kvm_vgic_global_state.nr_lr)
+		if (count == kvm_vgic_global_state.nr_lr) {
+			if (!list_is_last(&irq->ap_list,
+					  &vgic_cpu->ap_list_head))
+				vgic_set_underflow(vcpu);
 			break;
+		}
 	}
 
 	vcpu->arch.vgic_cpu.used_lrs = count;
@@ -639,18 +633,30 @@ next:
 /* Sync back the hardware VGIC state into our emulation after a guest's run. */
 void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
 {
-	if (unlikely(!vgic_initialized(vcpu->kvm)))
+	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+
+	/* An empty ap_list_head implies used_lrs == 0 */
+	if (list_empty(&vcpu->arch.vgic_cpu.ap_list_head))
 		return;
 
-	vgic_process_maintenance_interrupt(vcpu);
-	vgic_fold_lr_state(vcpu);
+	if (vgic_cpu->used_lrs)
+		vgic_fold_lr_state(vcpu);
 	vgic_prune_ap_list(vcpu);
 }
 
 /* Flush our emulation state into the GIC hardware before entering the guest. */
 void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
 {
-	if (unlikely(!vgic_initialized(vcpu->kvm)))
+	/*
+	 * 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
+	 * taking any lock.  There is a potential race with someone injecting
+	 * interrupts to the VCPU, but it is a benign race as the VCPU will
+	 * either observe the new interrupt before or after doing this check,
+	 * and introducing additional synchronization mechanism doesn't change
+	 * this.
+	 */
+	if (list_empty(&vcpu->arch.vgic_cpu.ap_list_head))
 		return;
 
 	spin_lock(&vcpu->arch.vgic_cpu.ap_list_lock);
@@ -658,6 +664,28 @@ void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
 	spin_unlock(&vcpu->arch.vgic_cpu.ap_list_lock);
 }
 
+void kvm_vgic_load(struct kvm_vcpu *vcpu)
+{
+	if (unlikely(!vgic_initialized(vcpu->kvm)))
+		return;
+
+	if (kvm_vgic_global_state.type == VGIC_V2)
+		vgic_v2_load(vcpu);
+	else
+		vgic_v3_load(vcpu);
+}
+
+void kvm_vgic_put(struct kvm_vcpu *vcpu)
+{
+	if (unlikely(!vgic_initialized(vcpu->kvm)))
+		return;
+
+	if (kvm_vgic_global_state.type == VGIC_V2)
+		vgic_v2_put(vcpu);
+	else
+		vgic_v3_put(vcpu);
+}
+
 int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h
index 6cf557e9f718..799fd651b260 100644
--- a/virt/kvm/arm/vgic/vgic.h
+++ b/virt/kvm/arm/vgic/vgic.h
@@ -119,7 +119,6 @@ void vgic_kick_vcpus(struct kvm *kvm);
 int vgic_check_ioaddr(struct kvm *kvm, phys_addr_t *ioaddr,
 		      phys_addr_t addr, phys_addr_t alignment);
 
-void vgic_v2_process_maintenance(struct kvm_vcpu *vcpu);
 void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu);
 void vgic_v2_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr);
 void vgic_v2_clear_lr(struct kvm_vcpu *vcpu, int lr);
@@ -138,6 +137,8 @@ int vgic_register_dist_iodev(struct kvm *kvm, gpa_t dist_base_address,
 			     enum vgic_type);
 
 void vgic_v2_init_lrs(void);
+void vgic_v2_load(struct kvm_vcpu *vcpu);
+void vgic_v2_put(struct kvm_vcpu *vcpu);
 
 static inline void vgic_get_irq_kref(struct vgic_irq *irq)
 {
@@ -147,7 +148,6 @@ static inline void vgic_get_irq_kref(struct vgic_irq *irq)
 	kref_get(&irq->refcount);
 }
 
-void vgic_v3_process_maintenance(struct kvm_vcpu *vcpu);
 void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu);
 void vgic_v3_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr);
 void vgic_v3_clear_lr(struct kvm_vcpu *vcpu, int lr);
@@ -159,6 +159,9 @@ int vgic_v3_probe(const struct gic_kvm_info *info);
 int vgic_v3_map_resources(struct kvm *kvm);
 int vgic_register_redist_iodevs(struct kvm *kvm, gpa_t dist_base_address);
 
+void vgic_v3_load(struct kvm_vcpu *vcpu);
+void vgic_v3_put(struct kvm_vcpu *vcpu);
+
 int vgic_register_its_iodevs(struct kvm *kvm);
 bool vgic_has_its(struct kvm *kvm);
 int kvm_vgic_register_its_device(void);
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 4d28a9ddbee0..a8d540398bbd 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -490,7 +490,7 @@ void kvm_register_irq_ack_notifier(struct kvm *kvm,
 	mutex_lock(&kvm->irq_lock);
 	hlist_add_head_rcu(&kian->link, &kvm->irq_ack_notifier_list);
 	mutex_unlock(&kvm->irq_lock);
-	kvm_vcpu_request_scan_ioapic(kvm);
+	kvm_arch_post_irq_ack_notifier_list_update(kvm);
 }
 
 void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
@@ -500,7 +500,7 @@ void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
 	hlist_del_init_rcu(&kian->link);
 	mutex_unlock(&kvm->irq_lock);
 	synchronize_srcu(&kvm->irq_srcu);
-	kvm_vcpu_request_scan_ioapic(kvm);
+	kvm_arch_post_irq_ack_notifier_list_update(kvm);
 }
 #endif
 
diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c
index 3bcc9990adf7..31e40c9e81df 100644
--- a/virt/kvm/irqchip.c
+++ b/virt/kvm/irqchip.c
@@ -142,8 +142,8 @@ static int setup_routing_entry(struct kvm *kvm,
 			       struct kvm_kernel_irq_routing_entry *e,
 			       const struct kvm_irq_routing_entry *ue)
 {
-	int r = -EINVAL;
 	struct kvm_kernel_irq_routing_entry *ei;
+	int r;
 
 	/*
 	 * Do not allow GSI to be mapped to the same irqchip more than once.
@@ -153,26 +153,30 @@ static int setup_routing_entry(struct kvm *kvm,
 		if (ei->type != KVM_IRQ_ROUTING_IRQCHIP ||
 		    ue->type != KVM_IRQ_ROUTING_IRQCHIP ||
 		    ue->u.irqchip.irqchip == ei->irqchip.irqchip)
-			return r;
+			return -EINVAL;
 
 	e->gsi = ue->gsi;
 	e->type = ue->type;
 	r = kvm_set_routing_entry(kvm, e, ue);
 	if (r)
-		goto out;
+		return r;
 	if (e->type == KVM_IRQ_ROUTING_IRQCHIP)
 		rt->chip[e->irqchip.irqchip][e->irqchip.pin] = e->gsi;
 
 	hlist_add_head(&e->link, &rt->map[e->gsi]);
-	r = 0;
-out:
-	return r;
+
+	return 0;
 }
 
 void __attribute__((weak)) kvm_arch_irq_routing_update(struct kvm *kvm)
 {
 }
 
+bool __weak kvm_arch_can_set_irq_routing(struct kvm *kvm)
+{
+	return true;
+}
+
 int kvm_set_irq_routing(struct kvm *kvm,
 			const struct kvm_irq_routing_entry *ue,
 			unsigned nr,
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 88257b311cb5..6e3b12c1925a 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -165,6 +165,24 @@ void vcpu_put(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(vcpu_put);
 
+/* TODO: merge with kvm_arch_vcpu_should_kick */
+static bool kvm_request_needs_ipi(struct kvm_vcpu *vcpu, unsigned req)
+{
+	int mode = kvm_vcpu_exiting_guest_mode(vcpu);
+
+	/*
+	 * We need to wait for the VCPU to reenable interrupts and get out of
+	 * READING_SHADOW_PAGE_TABLES mode.
+	 */
+	if (req & KVM_REQUEST_WAIT)
+		return mode != OUTSIDE_GUEST_MODE;
+
+	/*
+	 * Need to kick a running VCPU, but otherwise there is nothing to do.
+	 */
+	return mode == IN_GUEST_MODE;
+}
+
 static void ack_flush(void *_completed)
 {
 }
@@ -174,6 +192,7 @@ bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req)
 	int i, cpu, me;
 	cpumask_var_t cpus;
 	bool called = true;
+	bool wait = req & KVM_REQUEST_WAIT;
 	struct kvm_vcpu *vcpu;
 
 	zalloc_cpumask_var(&cpus, GFP_ATOMIC);
@@ -183,17 +202,17 @@ bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req)
 		kvm_make_request(req, vcpu);
 		cpu = vcpu->cpu;
 
-		/* Set ->requests bit before we read ->mode. */
-		smp_mb__after_atomic();
+		if (!(req & KVM_REQUEST_NO_WAKEUP) && kvm_vcpu_wake_up(vcpu))
+			continue;
 
 		if (cpus != NULL && cpu != -1 && cpu != me &&
-		      kvm_vcpu_exiting_guest_mode(vcpu) != OUTSIDE_GUEST_MODE)
+		    kvm_request_needs_ipi(vcpu, req))
 			cpumask_set_cpu(cpu, cpus);
 	}
 	if (unlikely(cpus == NULL))
-		smp_call_function_many(cpu_online_mask, ack_flush, NULL, 1);
+		smp_call_function_many(cpu_online_mask, ack_flush, NULL, wait);
 	else if (!cpumask_empty(cpus))
-		smp_call_function_many(cpus, ack_flush, NULL, 1);
+		smp_call_function_many(cpus, ack_flush, NULL, wait);
 	else
 		called = false;
 	put_cpu();
@@ -1019,8 +1038,6 @@ int __kvm_set_memory_region(struct kvm *kvm,
 
 		old_memslots = install_new_memslots(kvm, as_id, slots);
 
-		/* slot was deleted or moved, clear iommu mapping */
-		kvm_iommu_unmap_pages(kvm, &old);
 		/* From this point no new shadow pages pointing to a deleted,
 		 * or moved, memslot will be created.
 		 *
@@ -1055,21 +1072,6 @@ int __kvm_set_memory_region(struct kvm *kvm,
 
 	kvm_free_memslot(kvm, &old, &new);
 	kvfree(old_memslots);
-
-	/*
-	 * IOMMU mapping:  New slots need to be mapped.  Old slots need to be
-	 * un-mapped and re-mapped if their base changes.  Since base change
-	 * unmapping is handled above with slot deletion, mapping alone is
-	 * needed here.  Anything else the iommu might care about for existing
-	 * slots (size changes, userspace addr changes and read-only flag
-	 * changes) is disallowed above, so any other attribute changes getting
-	 * here can be skipped.
-	 */
-	if (as_id == 0 && (change == KVM_MR_CREATE || change == KVM_MR_MOVE)) {
-		r = kvm_iommu_map_pages(kvm, &new);
-		return r;
-	}
-
 	return 0;
 
 out_slots:
@@ -1973,18 +1975,18 @@ static int __kvm_gfn_to_hva_cache_init(struct kvm_memslots *slots,
 	return 0;
 }
 
-int kvm_vcpu_gfn_to_hva_cache_init(struct kvm_vcpu *vcpu, struct gfn_to_hva_cache *ghc,
+int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 			      gpa_t gpa, unsigned long len)
 {
-	struct kvm_memslots *slots = kvm_vcpu_memslots(vcpu);
+	struct kvm_memslots *slots = kvm_memslots(kvm);
 	return __kvm_gfn_to_hva_cache_init(slots, ghc, gpa, len);
 }
-EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_hva_cache_init);
+EXPORT_SYMBOL_GPL(kvm_gfn_to_hva_cache_init);
 
-int kvm_vcpu_write_guest_offset_cached(struct kvm_vcpu *vcpu, struct gfn_to_hva_cache *ghc,
-				       void *data, int offset, unsigned long len)
+int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
+			   void *data, int offset, unsigned long len)
 {
-	struct kvm_memslots *slots = kvm_vcpu_memslots(vcpu);
+	struct kvm_memslots *slots = kvm_memslots(kvm);
 	int r;
 	gpa_t gpa = ghc->gpa + offset;
 
@@ -1994,7 +1996,7 @@ int kvm_vcpu_write_guest_offset_cached(struct kvm_vcpu *vcpu, struct gfn_to_hva_
 		__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len);
 
 	if (unlikely(!ghc->memslot))
-		return kvm_vcpu_write_guest(vcpu, gpa, data, len);
+		return kvm_write_guest(kvm, gpa, data, len);
 
 	if (kvm_is_error_hva(ghc->hva))
 		return -EFAULT;
@@ -2006,19 +2008,19 @@ int kvm_vcpu_write_guest_offset_cached(struct kvm_vcpu *vcpu, struct gfn_to_hva_
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(kvm_vcpu_write_guest_offset_cached);
+EXPORT_SYMBOL_GPL(kvm_write_guest_offset_cached);
 
-int kvm_vcpu_write_guest_cached(struct kvm_vcpu *vcpu, struct gfn_to_hva_cache *ghc,
-			       void *data, unsigned long len)
+int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
+			   void *data, unsigned long len)
 {
-	return kvm_vcpu_write_guest_offset_cached(vcpu, ghc, data, 0, len);
+	return kvm_write_guest_offset_cached(kvm, ghc, data, 0, len);
 }
-EXPORT_SYMBOL_GPL(kvm_vcpu_write_guest_cached);
+EXPORT_SYMBOL_GPL(kvm_write_guest_cached);
 
-int kvm_vcpu_read_guest_cached(struct kvm_vcpu *vcpu, struct gfn_to_hva_cache *ghc,
-			       void *data, unsigned long len)
+int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
+			   void *data, unsigned long len)
 {
-	struct kvm_memslots *slots = kvm_vcpu_memslots(vcpu);
+	struct kvm_memslots *slots = kvm_memslots(kvm);
 	int r;
 
 	BUG_ON(len > ghc->len);
@@ -2027,7 +2029,7 @@ int kvm_vcpu_read_guest_cached(struct kvm_vcpu *vcpu, struct gfn_to_hva_cache *g
 		__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len);
 
 	if (unlikely(!ghc->memslot))
-		return kvm_vcpu_read_guest(vcpu, ghc->gpa, data, len);
+		return kvm_read_guest(kvm, ghc->gpa, data, len);
 
 	if (kvm_is_error_hva(ghc->hva))
 		return -EFAULT;
@@ -2038,7 +2040,7 @@ int kvm_vcpu_read_guest_cached(struct kvm_vcpu *vcpu, struct gfn_to_hva_cache *g
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(kvm_vcpu_read_guest_cached);
+EXPORT_SYMBOL_GPL(kvm_read_guest_cached);
 
 int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len)
 {
@@ -2212,8 +2214,7 @@ out:
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_block);
 
-#ifndef CONFIG_S390
-void kvm_vcpu_wake_up(struct kvm_vcpu *vcpu)
+bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu)
 {
 	struct swait_queue_head *wqp;
 
@@ -2221,11 +2222,14 @@ void kvm_vcpu_wake_up(struct kvm_vcpu *vcpu)
 	if (swait_active(wqp)) {
 		swake_up(wqp);
 		++vcpu->stat.halt_wakeup;
+		return true;
 	}
 
+	return false;
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_wake_up);
 
+#ifndef CONFIG_S390
 /*
  * Kick a sleeping VCPU, or a guest VCPU in guest mode, into host kernel mode.
  */
@@ -2234,7 +2238,9 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
 	int me;
 	int cpu = vcpu->cpu;
 
-	kvm_vcpu_wake_up(vcpu);
+	if (kvm_vcpu_wake_up(vcpu))
+		return;
+
 	me = get_cpu();
 	if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu))
 		if (kvm_arch_vcpu_should_kick(vcpu))
@@ -2366,7 +2372,7 @@ static int kvm_vcpu_fault(struct vm_fault *vmf)
 	else if (vmf->pgoff == KVM_PIO_PAGE_OFFSET)
 		page = virt_to_page(vcpu->arch.pio_data);
 #endif
-#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
+#ifdef CONFIG_KVM_MMIO
 	else if (vmf->pgoff == KVM_COALESCED_MMIO_PAGE_OFFSET)
 		page = virt_to_page(vcpu->kvm->coalesced_mmio_ring);
 #endif
@@ -2935,6 +2941,10 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 	case KVM_CAP_IOEVENTFD_ANY_LENGTH:
 	case KVM_CAP_CHECK_EXTENSION_VM:
 		return 1;
+#ifdef CONFIG_KVM_MMIO
+	case KVM_CAP_COALESCED_MMIO:
+		return KVM_COALESCED_MMIO_PAGE_OFFSET;
+#endif
 #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
 	case KVM_CAP_IRQ_ROUTING:
 		return KVM_MAX_IRQ_ROUTES;
@@ -2984,7 +2994,7 @@ static long kvm_vm_ioctl(struct file *filp,
 		r = kvm_vm_ioctl_get_dirty_log(kvm, &log);
 		break;
 	}
-#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
+#ifdef CONFIG_KVM_MMIO
 	case KVM_REGISTER_COALESCED_MMIO: {
 		struct kvm_coalesced_mmio_zone zone;
 
@@ -3067,6 +3077,8 @@ static long kvm_vm_ioctl(struct file *filp,
 		if (copy_from_user(&routing, argp, sizeof(routing)))
 			goto out;
 		r = -EINVAL;
+		if (!kvm_arch_can_set_irq_routing(kvm))
+			goto out;
 		if (routing.nr > KVM_MAX_IRQ_ROUTES)
 			goto out;
 		if (routing.flags)
@@ -3176,7 +3188,7 @@ static int kvm_dev_ioctl_create_vm(unsigned long type)
 	kvm = kvm_create_vm(type);
 	if (IS_ERR(kvm))
 		return PTR_ERR(kvm);
-#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
+#ifdef CONFIG_KVM_MMIO
 	r = kvm_coalesced_mmio_init(kvm);
 	if (r < 0) {
 		kvm_put_kvm(kvm);
@@ -3229,7 +3241,7 @@ static long kvm_dev_ioctl(struct file *filp,
 #ifdef CONFIG_X86
 		r += PAGE_SIZE;    /* pio data page */
 #endif
-#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
+#ifdef CONFIG_KVM_MMIO
 		r += PAGE_SIZE;    /* coalesced mmio ring page */
 #endif
 		break;
diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c
index d32f239eb471..37d9118fd84b 100644
--- a/virt/kvm/vfio.c
+++ b/virt/kvm/vfio.c
@@ -20,6 +20,10 @@
 #include <linux/vfio.h>
 #include "vfio.h"
 
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+#include <asm/kvm_ppc.h>
+#endif
+
 struct kvm_vfio_group {
 	struct list_head node;
 	struct vfio_group *vfio_group;
@@ -89,6 +93,47 @@ static bool kvm_vfio_group_is_coherent(struct vfio_group *vfio_group)
 	return ret > 0;
 }
 
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+static int kvm_vfio_external_user_iommu_id(struct vfio_group *vfio_group)
+{
+	int (*fn)(struct vfio_group *);
+	int ret = -EINVAL;
+
+	fn = symbol_get(vfio_external_user_iommu_id);
+	if (!fn)
+		return ret;
+
+	ret = fn(vfio_group);
+
+	symbol_put(vfio_external_user_iommu_id);
+
+	return ret;
+}
+
+static struct iommu_group *kvm_vfio_group_get_iommu_group(
+		struct vfio_group *group)
+{
+	int group_id = kvm_vfio_external_user_iommu_id(group);
+
+	if (group_id < 0)
+		return NULL;
+
+	return iommu_group_get_by_id(group_id);
+}
+
+static void kvm_spapr_tce_release_vfio_group(struct kvm *kvm,
+		struct vfio_group *vfio_group)
+{
+	struct iommu_group *grp = kvm_vfio_group_get_iommu_group(vfio_group);
+
+	if (WARN_ON_ONCE(!grp))
+		return;
+
+	kvm_spapr_tce_release_iommu_group(kvm, grp);
+	iommu_group_put(grp);
+}
+#endif
+
 /*
  * Groups can use the same or different IOMMU domains.  If the same then
  * adding a new group may change the coherency of groups we've previously
@@ -211,6 +256,9 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
 
 		mutex_unlock(&kv->lock);
 
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+		kvm_spapr_tce_release_vfio_group(dev->kvm, vfio_group);
+#endif
 		kvm_vfio_group_set_kvm(vfio_group, NULL);
 
 		kvm_vfio_group_put_external_user(vfio_group);
@@ -218,6 +266,57 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
 		kvm_vfio_update_coherency(dev);
 
 		return ret;
+
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+	case KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE: {
+		struct kvm_vfio_spapr_tce param;
+		struct kvm_vfio *kv = dev->private;
+		struct vfio_group *vfio_group;
+		struct kvm_vfio_group *kvg;
+		struct fd f;
+		struct iommu_group *grp;
+
+		if (copy_from_user(&param, (void __user *)arg,
+				sizeof(struct kvm_vfio_spapr_tce)))
+			return -EFAULT;
+
+		f = fdget(param.groupfd);
+		if (!f.file)
+			return -EBADF;
+
+		vfio_group = kvm_vfio_group_get_external_user(f.file);
+		fdput(f);
+
+		if (IS_ERR(vfio_group))
+			return PTR_ERR(vfio_group);
+
+		grp = kvm_vfio_group_get_iommu_group(vfio_group);
+		if (WARN_ON_ONCE(!grp)) {
+			kvm_vfio_group_put_external_user(vfio_group);
+			return -EIO;
+		}
+
+		ret = -ENOENT;
+
+		mutex_lock(&kv->lock);
+
+		list_for_each_entry(kvg, &kv->group_list, node) {
+			if (kvg->vfio_group != vfio_group)
+				continue;
+
+			ret = kvm_spapr_tce_attach_iommu_group(dev->kvm,
+					param.tablefd, grp);
+			break;
+		}
+
+		mutex_unlock(&kv->lock);
+
+		iommu_group_put(grp);
+		kvm_vfio_group_put_external_user(vfio_group);
+
+		return ret;
+	}
+#endif /* CONFIG_SPAPR_TCE_IOMMU */
 	}
 
 	return -ENXIO;
@@ -242,6 +341,9 @@ static int kvm_vfio_has_attr(struct kvm_device *dev,
 		switch (attr->attr) {
 		case KVM_DEV_VFIO_GROUP_ADD:
 		case KVM_DEV_VFIO_GROUP_DEL:
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+		case KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE:
+#endif
 			return 0;
 		}
 
@@ -257,6 +359,9 @@ static void kvm_vfio_destroy(struct kvm_device *dev)
 	struct kvm_vfio_group *kvg, *tmp;
 
 	list_for_each_entry_safe(kvg, tmp, &kv->group_list, node) {
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+		kvm_spapr_tce_release_vfio_group(dev->kvm, kvg->vfio_group);
+#endif
 		kvm_vfio_group_set_kvm(kvg->vfio_group, NULL);
 		kvm_vfio_group_put_external_user(kvg->vfio_group);
 		list_del(&kvg->node);