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

Pull KVM updates from Paolo Bonzini:
 "First round of KVM updates for 3.14; PPC parts will come next week.

  Nothing major here, just bugfixes all over the place.  The most
  interesting part is the ARM guys' virtualized interrupt controller
  overhaul, which lets userspace get/set the state and thus enables
  migration of ARM VMs"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (67 commits)
  kvm: make KVM_MMU_AUDIT help text more readable
  KVM: s390: Fix memory access error detection
  KVM: nVMX: Update guest activity state field on L2 exits
  KVM: nVMX: Fix nested_run_pending on activity state HLT
  KVM: nVMX: Clean up handling of VMX-related MSRs
  KVM: nVMX: Add tracepoints for nested_vmexit and nested_vmexit_inject
  KVM: nVMX: Pass vmexit parameters to nested_vmx_vmexit
  KVM: nVMX: Leave VMX mode on clearing of feature control MSR
  KVM: VMX: Fix DR6 update on #DB exception
  KVM: SVM: Fix reading of DR6
  KVM: x86: Sync DR7 on KVM_SET_DEBUGREGS
  add support for Hyper-V reference time counter
  KVM: remove useless write to vcpu->hv_clock.tsc_timestamp
  KVM: x86: fix tsc catchup issue with tsc scaling
  KVM: x86: limit PIT timer frequency
  KVM: x86: handle invalid root_hpa everywhere
  kvm: Provide kvm_vcpu_eligible_for_directed_yield() stub
  kvm: vfio: silence GCC warning
  KVM: ARM: Remove duplicate include
  arm/arm64: KVM: relax the requirements of VMA alignment for THP
  ...

6 files changed, 617 insertions, 91 deletions

diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index c2e1ef4604e8..5081e809821f 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -182,6 +182,40 @@ static void kvm_timer_init_interrupt(void *info)
 	enable_percpu_irq(host_vtimer_irq, 0);
 }
 
+int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value)
+{
+	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
+
+	switch (regid) {
+	case KVM_REG_ARM_TIMER_CTL:
+		timer->cntv_ctl = value;
+		break;
+	case KVM_REG_ARM_TIMER_CNT:
+		vcpu->kvm->arch.timer.cntvoff = kvm_phys_timer_read() - value;
+		break;
+	case KVM_REG_ARM_TIMER_CVAL:
+		timer->cntv_cval = value;
+		break;
+	default:
+		return -1;
+	}
+	return 0;
+}
+
+u64 kvm_arm_timer_get_reg(struct kvm_vcpu *vcpu, u64 regid)
+{
+	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
+
+	switch (regid) {
+	case KVM_REG_ARM_TIMER_CTL:
+		return timer->cntv_ctl;
+	case KVM_REG_ARM_TIMER_CNT:
+		return kvm_phys_timer_read() - vcpu->kvm->arch.timer.cntvoff;
+	case KVM_REG_ARM_TIMER_CVAL:
+		return timer->cntv_cval;
+	}
+	return (u64)-1;
+}
 
 static int kvm_timer_cpu_notify(struct notifier_block *self,
 				unsigned long action, void *cpu)
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index 685fc72fc751..be456ce264d0 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -71,6 +71,10 @@
 #define VGIC_ADDR_UNDEF		(-1)
 #define IS_VGIC_ADDR_UNDEF(_x)  ((_x) == VGIC_ADDR_UNDEF)
 
+#define PRODUCT_ID_KVM		0x4b	/* ASCII code K */
+#define IMPLEMENTER_ARM		0x43b
+#define GICC_ARCH_VERSION_V2	0x2
+
 /* Physical address of vgic virtual cpu interface */
 static phys_addr_t vgic_vcpu_base;
 
@@ -312,7 +316,7 @@ static bool handle_mmio_misc(struct kvm_vcpu *vcpu,
 	u32 word_offset = offset & 3;
 
 	switch (offset & ~3) {
-	case 0:			/* CTLR */
+	case 0:			/* GICD_CTLR */
 		reg = vcpu->kvm->arch.vgic.enabled;
 		vgic_reg_access(mmio, &reg, word_offset,
 				ACCESS_READ_VALUE | ACCESS_WRITE_VALUE);
@@ -323,15 +327,15 @@ static bool handle_mmio_misc(struct kvm_vcpu *vcpu,
 		}
 		break;
 
-	case 4:			/* TYPER */
+	case 4:			/* GICD_TYPER */
 		reg  = (atomic_read(&vcpu->kvm->online_vcpus) - 1) << 5;
 		reg |= (VGIC_NR_IRQS >> 5) - 1;
 		vgic_reg_access(mmio, &reg, word_offset,
 				ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED);
 		break;
 
-	case 8:			/* IIDR */
-		reg = 0x4B00043B;
+	case 8:			/* GICD_IIDR */
+		reg = (PRODUCT_ID_KVM << 24) | (IMPLEMENTER_ARM << 0);
 		vgic_reg_access(mmio, &reg, word_offset,
 				ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED);
 		break;
@@ -589,6 +593,156 @@ static bool handle_mmio_sgi_reg(struct kvm_vcpu *vcpu,
 	return false;
 }
 
+#define LR_CPUID(lr)	\
+	(((lr) & GICH_LR_PHYSID_CPUID) >> GICH_LR_PHYSID_CPUID_SHIFT)
+#define LR_IRQID(lr)	\
+	((lr) & GICH_LR_VIRTUALID)
+
+static void vgic_retire_lr(int lr_nr, int irq, struct vgic_cpu *vgic_cpu)
+{
+	clear_bit(lr_nr, vgic_cpu->lr_used);
+	vgic_cpu->vgic_lr[lr_nr] &= ~GICH_LR_STATE;
+	vgic_cpu->vgic_irq_lr_map[irq] = LR_EMPTY;
+}
+
+/**
+ * vgic_unqueue_irqs - move pending IRQs from LRs to the distributor
+ * @vgic_cpu: Pointer to the vgic_cpu struct holding the LRs
+ *
+ * Move any pending IRQs that have already been assigned to LRs back to the
+ * emulated distributor state so that the complete emulated state can be read
+ * from the main emulation structures without investigating the LRs.
+ *
+ * Note that IRQs in the active state in the LRs get their pending state moved
+ * to the distributor but the active state stays in the LRs, because we don't
+ * track the active state on the distributor side.
+ */
+static void vgic_unqueue_irqs(struct kvm_vcpu *vcpu)
+{
+	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+	int vcpu_id = vcpu->vcpu_id;
+	int i, irq, source_cpu;
+	u32 *lr;
+
+	for_each_set_bit(i, vgic_cpu->lr_used, vgic_cpu->nr_lr) {
+		lr = &vgic_cpu->vgic_lr[i];
+		irq = LR_IRQID(*lr);
+		source_cpu = LR_CPUID(*lr);
+
+		/*
+		 * There are three options for the state bits:
+		 *
+		 * 01: pending
+		 * 10: active
+		 * 11: pending and active
+		 *
+		 * If the LR holds only an active interrupt (not pending) then
+		 * just leave it alone.
+		 */
+		if ((*lr & GICH_LR_STATE) == GICH_LR_ACTIVE_BIT)
+			continue;
+
+		/*
+		 * Reestablish the pending state on the distributor and the
+		 * CPU interface.  It may have already been pending, but that
+		 * is fine, then we are only setting a few bits that were
+		 * already set.
+		 */
+		vgic_dist_irq_set(vcpu, irq);
+		if (irq < VGIC_NR_SGIS)
+			dist->irq_sgi_sources[vcpu_id][irq] |= 1 << source_cpu;
+		*lr &= ~GICH_LR_PENDING_BIT;
+
+		/*
+		 * If there's no state left on the LR (it could still be
+		 * active), then the LR does not hold any useful info and can
+		 * be marked as free for other use.
+		 */
+		if (!(*lr & GICH_LR_STATE))
+			vgic_retire_lr(i, irq, vgic_cpu);
+
+		/* Finally update the VGIC state. */
+		vgic_update_state(vcpu->kvm);
+	}
+}
+
+/* Handle reads of GICD_CPENDSGIRn and GICD_SPENDSGIRn */
+static bool read_set_clear_sgi_pend_reg(struct kvm_vcpu *vcpu,
+					struct kvm_exit_mmio *mmio,
+					phys_addr_t offset)
+{
+	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+	int sgi;
+	int min_sgi = (offset & ~0x3) * 4;
+	int max_sgi = min_sgi + 3;
+	int vcpu_id = vcpu->vcpu_id;
+	u32 reg = 0;
+
+	/* Copy source SGIs from distributor side */
+	for (sgi = min_sgi; sgi <= max_sgi; sgi++) {
+		int shift = 8 * (sgi - min_sgi);
+		reg |= (u32)dist->irq_sgi_sources[vcpu_id][sgi] << shift;
+	}
+
+	mmio_data_write(mmio, ~0, reg);
+	return false;
+}
+
+static bool write_set_clear_sgi_pend_reg(struct kvm_vcpu *vcpu,
+					 struct kvm_exit_mmio *mmio,
+					 phys_addr_t offset, bool set)
+{
+	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+	int sgi;
+	int min_sgi = (offset & ~0x3) * 4;
+	int max_sgi = min_sgi + 3;
+	int vcpu_id = vcpu->vcpu_id;
+	u32 reg;
+	bool updated = false;
+
+	reg = mmio_data_read(mmio, ~0);
+
+	/* Clear pending SGIs on the distributor */
+	for (sgi = min_sgi; sgi <= max_sgi; sgi++) {
+		u8 mask = reg >> (8 * (sgi - min_sgi));
+		if (set) {
+			if ((dist->irq_sgi_sources[vcpu_id][sgi] & mask) != mask)
+				updated = true;
+			dist->irq_sgi_sources[vcpu_id][sgi] |= mask;
+		} else {
+			if (dist->irq_sgi_sources[vcpu_id][sgi] & mask)
+				updated = true;
+			dist->irq_sgi_sources[vcpu_id][sgi] &= ~mask;
+		}
+	}
+
+	if (updated)
+		vgic_update_state(vcpu->kvm);
+
+	return updated;
+}
+
+static bool handle_mmio_sgi_set(struct kvm_vcpu *vcpu,
+				struct kvm_exit_mmio *mmio,
+				phys_addr_t offset)
+{
+	if (!mmio->is_write)
+		return read_set_clear_sgi_pend_reg(vcpu, mmio, offset);
+	else
+		return write_set_clear_sgi_pend_reg(vcpu, mmio, offset, true);
+}
+
+static bool handle_mmio_sgi_clear(struct kvm_vcpu *vcpu,
+				  struct kvm_exit_mmio *mmio,
+				  phys_addr_t offset)
+{
+	if (!mmio->is_write)
+		return read_set_clear_sgi_pend_reg(vcpu, mmio, offset);
+	else
+		return write_set_clear_sgi_pend_reg(vcpu, mmio, offset, false);
+}
+
 /*
  * I would have liked to use the kvm_bus_io_*() API instead, but it
  * cannot cope with banked registers (only the VM pointer is passed
@@ -602,7 +756,7 @@ struct mmio_range {
 			    phys_addr_t offset);
 };
 
-static const struct mmio_range vgic_ranges[] = {
+static const struct mmio_range vgic_dist_ranges[] = {
 	{
 		.base		= GIC_DIST_CTRL,
 		.len		= 12,
@@ -663,20 +817,29 @@ static const struct mmio_range vgic_ranges[] = {
 		.len		= 4,
 		.handle_mmio	= handle_mmio_sgi_reg,
 	},
+	{
+		.base		= GIC_DIST_SGI_PENDING_CLEAR,
+		.len		= VGIC_NR_SGIS,
+		.handle_mmio	= handle_mmio_sgi_clear,
+	},
+	{
+		.base		= GIC_DIST_SGI_PENDING_SET,
+		.len		= VGIC_NR_SGIS,
+		.handle_mmio	= handle_mmio_sgi_set,
+	},
 	{}
 };
 
 static const
 struct mmio_range *find_matching_range(const struct mmio_range *ranges,
 				       struct kvm_exit_mmio *mmio,
-				       phys_addr_t base)
+				       phys_addr_t offset)
 {
 	const struct mmio_range *r = ranges;
-	phys_addr_t addr = mmio->phys_addr - base;
 
 	while (r->len) {
-		if (addr >= r->base &&
-		    (addr + mmio->len) <= (r->base + r->len))
+		if (offset >= r->base &&
+		    (offset + mmio->len) <= (r->base + r->len))
 			return r;
 		r++;
 	}
@@ -713,7 +876,8 @@ bool vgic_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		return true;
 	}
 
-	range = find_matching_range(vgic_ranges, mmio, base);
+	offset = mmio->phys_addr - base;
+	range = find_matching_range(vgic_dist_ranges, mmio, offset);
 	if (unlikely(!range || !range->handle_mmio)) {
 		pr_warn("Unhandled access %d %08llx %d\n",
 			mmio->is_write, mmio->phys_addr, mmio->len);
@@ -824,8 +988,6 @@ static void vgic_update_state(struct kvm *kvm)
 	}
 }
 
-#define LR_CPUID(lr)	\
-	(((lr) & GICH_LR_PHYSID_CPUID) >> GICH_LR_PHYSID_CPUID_SHIFT)
 #define MK_LR_PEND(src, irq)	\
 	(GICH_LR_PENDING_BIT | ((src) << GICH_LR_PHYSID_CPUID_SHIFT) | (irq))
 
@@ -847,9 +1009,7 @@ static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu)
 		int irq = vgic_cpu->vgic_lr[lr] & GICH_LR_VIRTUALID;
 
 		if (!vgic_irq_is_enabled(vcpu, irq)) {
-			vgic_cpu->vgic_irq_lr_map[irq] = LR_EMPTY;
-			clear_bit(lr, vgic_cpu->lr_used);
-			vgic_cpu->vgic_lr[lr] &= ~GICH_LR_STATE;
+			vgic_retire_lr(lr, irq, vgic_cpu);
 			if (vgic_irq_is_active(vcpu, irq))
 				vgic_irq_clear_active(vcpu, irq);
 		}
@@ -1243,15 +1403,19 @@ static irqreturn_t vgic_maintenance_handler(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
+/**
+ * kvm_vgic_vcpu_init - Initialize per-vcpu VGIC state
+ * @vcpu: pointer to the vcpu struct
+ *
+ * Initialize the vgic_cpu struct and vgic_dist struct fields pertaining to
+ * this vcpu and enable the VGIC for this VCPU
+ */
 int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
 	int i;
 
-	if (!irqchip_in_kernel(vcpu->kvm))
-		return 0;
-
 	if (vcpu->vcpu_id >= VGIC_MAX_CPUS)
 		return -EBUSY;
 
@@ -1383,10 +1547,22 @@ out:
 	return ret;
 }
 
+/**
+ * kvm_vgic_init - Initialize global VGIC state before running any VCPUs
+ * @kvm: pointer to the kvm struct
+ *
+ * Map the virtual CPU interface into the VM before running any VCPUs.  We
+ * can't do this at creation time, because user space must first set the
+ * virtual CPU interface address in the guest physical address space.  Also
+ * initialize the ITARGETSRn regs to 0 on the emulated distributor.
+ */
 int kvm_vgic_init(struct kvm *kvm)
 {
 	int ret = 0, i;
 
+	if (!irqchip_in_kernel(kvm))
+		return 0;
+
 	mutex_lock(&kvm->lock);
 
 	if (vgic_initialized(kvm))
@@ -1409,7 +1585,6 @@ int kvm_vgic_init(struct kvm *kvm)
 	for (i = VGIC_NR_PRIVATE_IRQS; i < VGIC_NR_IRQS; i += 4)
 		vgic_set_target_reg(kvm, 0, i);
 
-	kvm_timer_init(kvm);
 	kvm->arch.vgic.ready = true;
 out:
 	mutex_unlock(&kvm->lock);
@@ -1418,20 +1593,45 @@ out:
 
 int kvm_vgic_create(struct kvm *kvm)
 {
-	int ret = 0;
+	int i, vcpu_lock_idx = -1, ret = 0;
+	struct kvm_vcpu *vcpu;
 
 	mutex_lock(&kvm->lock);
 
-	if (atomic_read(&kvm->online_vcpus) || kvm->arch.vgic.vctrl_base) {
+	if (kvm->arch.vgic.vctrl_base) {
 		ret = -EEXIST;
 		goto out;
 	}
 
+	/*
+	 * Any time a vcpu is run, vcpu_load is called which tries to grab the
+	 * vcpu->mutex.  By grabbing the vcpu->mutex of all VCPUs we ensure
+	 * that no other VCPUs are run while we create the vgic.
+	 */
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		if (!mutex_trylock(&vcpu->mutex))
+			goto out_unlock;
+		vcpu_lock_idx = i;
+	}
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		if (vcpu->arch.has_run_once) {
+			ret = -EBUSY;
+			goto out_unlock;
+		}
+	}
+
 	spin_lock_init(&kvm->arch.vgic.lock);
 	kvm->arch.vgic.vctrl_base = vgic_vctrl_base;
 	kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF;
 	kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF;
 
+out_unlock:
+	for (; vcpu_lock_idx >= 0; vcpu_lock_idx--) {
+		vcpu = kvm_get_vcpu(kvm, vcpu_lock_idx);
+		mutex_unlock(&vcpu->mutex);
+	}
+
 out:
 	mutex_unlock(&kvm->lock);
 	return ret;
@@ -1455,6 +1655,12 @@ static int vgic_ioaddr_assign(struct kvm *kvm, phys_addr_t *ioaddr,
 {
 	int ret;
 
+	if (addr & ~KVM_PHYS_MASK)
+		return -E2BIG;
+
+	if (addr & (SZ_4K - 1))
+		return -EINVAL;
+
 	if (!IS_VGIC_ADDR_UNDEF(*ioaddr))
 		return -EEXIST;
 	if (addr + size < addr)
@@ -1467,26 +1673,41 @@ static int vgic_ioaddr_assign(struct kvm *kvm, phys_addr_t *ioaddr,
 	return ret;
 }
 
-int kvm_vgic_set_addr(struct kvm *kvm, unsigned long type, u64 addr)
+/**
+ * kvm_vgic_addr - set or get vgic VM base addresses
+ * @kvm:   pointer to the vm struct
+ * @type:  the VGIC addr type, one of KVM_VGIC_V2_ADDR_TYPE_XXX
+ * @addr:  pointer to address value
+ * @write: if true set the address in the VM address space, if false read the
+ *          address
+ *
+ * Set or get the vgic base addresses for the distributor and the virtual CPU
+ * interface in the VM physical address space.  These addresses are properties
+ * of the emulated core/SoC and therefore user space initially knows this
+ * information.
+ */
+int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write)
 {
 	int r = 0;
 	struct vgic_dist *vgic = &kvm->arch.vgic;
 
-	if (addr & ~KVM_PHYS_MASK)
-		return -E2BIG;
-
-	if (addr & (SZ_4K - 1))
-		return -EINVAL;
-
 	mutex_lock(&kvm->lock);
 	switch (type) {
 	case KVM_VGIC_V2_ADDR_TYPE_DIST:
-		r = vgic_ioaddr_assign(kvm, &vgic->vgic_dist_base,
-				       addr, KVM_VGIC_V2_DIST_SIZE);
+		if (write) {
+			r = vgic_ioaddr_assign(kvm, &vgic->vgic_dist_base,
+					       *addr, KVM_VGIC_V2_DIST_SIZE);
+		} else {
+			*addr = vgic->vgic_dist_base;
+		}
 		break;
 	case KVM_VGIC_V2_ADDR_TYPE_CPU:
-		r = vgic_ioaddr_assign(kvm, &vgic->vgic_cpu_base,
-				       addr, KVM_VGIC_V2_CPU_SIZE);
+		if (write) {
+			r = vgic_ioaddr_assign(kvm, &vgic->vgic_cpu_base,
+					       *addr, KVM_VGIC_V2_CPU_SIZE);
+		} else {
+			*addr = vgic->vgic_cpu_base;
+		}
 		break;
 	default:
 		r = -ENODEV;
@@ -1495,3 +1716,302 @@ int kvm_vgic_set_addr(struct kvm *kvm, unsigned long type, u64 addr)
 	mutex_unlock(&kvm->lock);
 	return r;
 }
+
+static bool handle_cpu_mmio_misc(struct kvm_vcpu *vcpu,
+				 struct kvm_exit_mmio *mmio, phys_addr_t offset)
+{
+	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+	u32 reg, mask = 0, shift = 0;
+	bool updated = false;
+
+	switch (offset & ~0x3) {
+	case GIC_CPU_CTRL:
+		mask = GICH_VMCR_CTRL_MASK;
+		shift = GICH_VMCR_CTRL_SHIFT;
+		break;
+	case GIC_CPU_PRIMASK:
+		mask = GICH_VMCR_PRIMASK_MASK;
+		shift = GICH_VMCR_PRIMASK_SHIFT;
+		break;
+	case GIC_CPU_BINPOINT:
+		mask = GICH_VMCR_BINPOINT_MASK;
+		shift = GICH_VMCR_BINPOINT_SHIFT;
+		break;
+	case GIC_CPU_ALIAS_BINPOINT:
+		mask = GICH_VMCR_ALIAS_BINPOINT_MASK;
+		shift = GICH_VMCR_ALIAS_BINPOINT_SHIFT;
+		break;
+	}
+
+	if (!mmio->is_write) {
+		reg = (vgic_cpu->vgic_vmcr & mask) >> shift;
+		mmio_data_write(mmio, ~0, reg);
+	} else {
+		reg = mmio_data_read(mmio, ~0);
+		reg = (reg << shift) & mask;
+		if (reg != (vgic_cpu->vgic_vmcr & mask))
+			updated = true;
+		vgic_cpu->vgic_vmcr &= ~mask;
+		vgic_cpu->vgic_vmcr |= reg;
+	}
+	return updated;
+}
+
+static bool handle_mmio_abpr(struct kvm_vcpu *vcpu,
+			     struct kvm_exit_mmio *mmio, phys_addr_t offset)
+{
+	return handle_cpu_mmio_misc(vcpu, mmio, GIC_CPU_ALIAS_BINPOINT);
+}
+
+static bool handle_cpu_mmio_ident(struct kvm_vcpu *vcpu,
+				  struct kvm_exit_mmio *mmio,
+				  phys_addr_t offset)
+{
+	u32 reg;
+
+	if (mmio->is_write)
+		return false;
+
+	/* GICC_IIDR */
+	reg = (PRODUCT_ID_KVM << 20) |
+	      (GICC_ARCH_VERSION_V2 << 16) |
+	      (IMPLEMENTER_ARM << 0);
+	mmio_data_write(mmio, ~0, reg);
+	return false;
+}
+
+/*
+ * CPU Interface Register accesses - these are not accessed by the VM, but by
+ * user space for saving and restoring VGIC state.
+ */
+static const struct mmio_range vgic_cpu_ranges[] = {
+	{
+		.base		= GIC_CPU_CTRL,
+		.len		= 12,
+		.handle_mmio	= handle_cpu_mmio_misc,
+	},
+	{
+		.base		= GIC_CPU_ALIAS_BINPOINT,
+		.len		= 4,
+		.handle_mmio	= handle_mmio_abpr,
+	},
+	{
+		.base		= GIC_CPU_ACTIVEPRIO,
+		.len		= 16,
+		.handle_mmio	= handle_mmio_raz_wi,
+	},
+	{
+		.base		= GIC_CPU_IDENT,
+		.len		= 4,
+		.handle_mmio	= handle_cpu_mmio_ident,
+	},
+};
+
+static int vgic_attr_regs_access(struct kvm_device *dev,
+				 struct kvm_device_attr *attr,
+				 u32 *reg, bool is_write)
+{
+	const struct mmio_range *r = NULL, *ranges;
+	phys_addr_t offset;
+	int ret, cpuid, c;
+	struct kvm_vcpu *vcpu, *tmp_vcpu;
+	struct vgic_dist *vgic;
+	struct kvm_exit_mmio mmio;
+
+	offset = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK;
+	cpuid = (attr->attr & KVM_DEV_ARM_VGIC_CPUID_MASK) >>
+		KVM_DEV_ARM_VGIC_CPUID_SHIFT;
+
+	mutex_lock(&dev->kvm->lock);
+
+	if (cpuid >= atomic_read(&dev->kvm->online_vcpus)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	vcpu = kvm_get_vcpu(dev->kvm, cpuid);
+	vgic = &dev->kvm->arch.vgic;
+
+	mmio.len = 4;
+	mmio.is_write = is_write;
+	if (is_write)
+		mmio_data_write(&mmio, ~0, *reg);
+	switch (attr->group) {
+	case KVM_DEV_ARM_VGIC_GRP_DIST_REGS:
+		mmio.phys_addr = vgic->vgic_dist_base + offset;
+		ranges = vgic_dist_ranges;
+		break;
+	case KVM_DEV_ARM_VGIC_GRP_CPU_REGS:
+		mmio.phys_addr = vgic->vgic_cpu_base + offset;
+		ranges = vgic_cpu_ranges;
+		break;
+	default:
+		BUG();
+	}
+	r = find_matching_range(ranges, &mmio, offset);
+
+	if (unlikely(!r || !r->handle_mmio)) {
+		ret = -ENXIO;
+		goto out;
+	}
+
+
+	spin_lock(&vgic->lock);
+
+	/*
+	 * Ensure that no other VCPU is running by checking the vcpu->cpu
+	 * field.  If no other VPCUs are running we can safely access the VGIC
+	 * state, because even if another VPU is run after this point, that
+	 * VCPU will not touch the vgic state, because it will block on
+	 * getting the vgic->lock in kvm_vgic_sync_hwstate().
+	 */
+	kvm_for_each_vcpu(c, tmp_vcpu, dev->kvm) {
+		if (unlikely(tmp_vcpu->cpu != -1)) {
+			ret = -EBUSY;
+			goto out_vgic_unlock;
+		}
+	}
+
+	/*
+	 * Move all pending IRQs from the LRs on all VCPUs so the pending
+	 * state can be properly represented in the register state accessible
+	 * through this API.
+	 */
+	kvm_for_each_vcpu(c, tmp_vcpu, dev->kvm)
+		vgic_unqueue_irqs(tmp_vcpu);
+
+	offset -= r->base;
+	r->handle_mmio(vcpu, &mmio, offset);
+
+	if (!is_write)
+		*reg = mmio_data_read(&mmio, ~0);
+
+	ret = 0;
+out_vgic_unlock:
+	spin_unlock(&vgic->lock);
+out:
+	mutex_unlock(&dev->kvm->lock);
+	return ret;
+}
+
+static int vgic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
+{
+	int r;
+
+	switch (attr->group) {
+	case KVM_DEV_ARM_VGIC_GRP_ADDR: {
+		u64 __user *uaddr = (u64 __user *)(long)attr->addr;
+		u64 addr;
+		unsigned long type = (unsigned long)attr->attr;
+
+		if (copy_from_user(&addr, uaddr, sizeof(addr)))
+			return -EFAULT;
+
+		r = kvm_vgic_addr(dev->kvm, type, &addr, true);
+		return (r == -ENODEV) ? -ENXIO : r;
+	}
+
+	case KVM_DEV_ARM_VGIC_GRP_DIST_REGS:
+	case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: {
+		u32 __user *uaddr = (u32 __user *)(long)attr->addr;
+		u32 reg;
+
+		if (get_user(reg, uaddr))
+			return -EFAULT;
+
+		return vgic_attr_regs_access(dev, attr, &reg, true);
+	}
+
+	}
+
+	return -ENXIO;
+}
+
+static int vgic_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
+{
+	int r = -ENXIO;
+
+	switch (attr->group) {
+	case KVM_DEV_ARM_VGIC_GRP_ADDR: {
+		u64 __user *uaddr = (u64 __user *)(long)attr->addr;
+		u64 addr;
+		unsigned long type = (unsigned long)attr->attr;
+
+		r = kvm_vgic_addr(dev->kvm, type, &addr, false);
+		if (r)
+			return (r == -ENODEV) ? -ENXIO : r;
+
+		if (copy_to_user(uaddr, &addr, sizeof(addr)))
+			return -EFAULT;
+		break;
+	}
+
+	case KVM_DEV_ARM_VGIC_GRP_DIST_REGS:
+	case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: {
+		u32 __user *uaddr = (u32 __user *)(long)attr->addr;
+		u32 reg = 0;
+
+		r = vgic_attr_regs_access(dev, attr, &reg, false);
+		if (r)
+			return r;
+		r = put_user(reg, uaddr);
+		break;
+	}
+
+	}
+
+	return r;
+}
+
+static int vgic_has_attr_regs(const struct mmio_range *ranges,
+			      phys_addr_t offset)
+{
+	struct kvm_exit_mmio dev_attr_mmio;
+
+	dev_attr_mmio.len = 4;
+	if (find_matching_range(ranges, &dev_attr_mmio, offset))
+		return 0;
+	else
+		return -ENXIO;
+}
+
+static int vgic_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
+{
+	phys_addr_t offset;
+
+	switch (attr->group) {
+	case KVM_DEV_ARM_VGIC_GRP_ADDR:
+		switch (attr->attr) {
+		case KVM_VGIC_V2_ADDR_TYPE_DIST:
+		case KVM_VGIC_V2_ADDR_TYPE_CPU:
+			return 0;
+		}
+		break;
+	case KVM_DEV_ARM_VGIC_GRP_DIST_REGS:
+		offset = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK;
+		return vgic_has_attr_regs(vgic_dist_ranges, offset);
+	case KVM_DEV_ARM_VGIC_GRP_CPU_REGS:
+		offset = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK;
+		return vgic_has_attr_regs(vgic_cpu_ranges, offset);
+	}
+	return -ENXIO;
+}
+
+static void vgic_destroy(struct kvm_device *dev)
+{
+	kfree(dev);
+}
+
+static int vgic_create(struct kvm_device *dev, u32 type)
+{
+	return kvm_vgic_create(dev->kvm);
+}
+
+struct kvm_device_ops kvm_arm_vgic_v2_ops = {
+	.name = "kvm-arm-vgic",
+	.create = vgic_create,
+	.destroy = vgic_destroy,
+	.set_attr = vgic_set_attr,
+	.get_attr = vgic_get_attr,
+	.has_attr = vgic_has_attr,
+};
diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c
index 2d682977ce82..ce9ed99ad7dc 100644
--- a/virt/kvm/ioapic.c
+++ b/virt/kvm/ioapic.c
@@ -520,7 +520,7 @@ static int ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len,
 	return 0;
 }
 
-void kvm_ioapic_reset(struct kvm_ioapic *ioapic)
+static void kvm_ioapic_reset(struct kvm_ioapic *ioapic)
 {
 	int i;
 
diff --git a/virt/kvm/ioapic.h b/virt/kvm/ioapic.h
index 615d8c995c3c..90d43e95dcf8 100644
--- a/virt/kvm/ioapic.h
+++ b/virt/kvm/ioapic.h
@@ -91,7 +91,6 @@ void kvm_ioapic_destroy(struct kvm *kvm);
 int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id,
 		       int level, bool line_status);
 void kvm_ioapic_clear_all(struct kvm_ioapic *ioapic, int irq_source_id);
-void kvm_ioapic_reset(struct kvm_ioapic *ioapic);
 int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
 		struct kvm_lapic_irq *irq, unsigned long *dest_map);
 int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 4f588bc94186..03a0381b1cb7 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -95,6 +95,12 @@ static int hardware_enable_all(void);
 static void hardware_disable_all(void);
 
 static void kvm_io_bus_destroy(struct kvm_io_bus *bus);
+static void update_memslots(struct kvm_memslots *slots,
+			    struct kvm_memory_slot *new, u64 last_generation);
+
+static void kvm_release_pfn_dirty(pfn_t pfn);
+static void mark_page_dirty_in_slot(struct kvm *kvm,
+				    struct kvm_memory_slot *memslot, gfn_t gfn);
 
 bool kvm_rebooting;
 EXPORT_SYMBOL_GPL(kvm_rebooting);
@@ -553,7 +559,7 @@ static void kvm_free_physmem_slot(struct kvm *kvm, struct kvm_memory_slot *free,
 	free->npages = 0;
 }
 
-void kvm_free_physmem(struct kvm *kvm)
+static void kvm_free_physmem(struct kvm *kvm)
 {
 	struct kvm_memslots *slots = kvm->memslots;
 	struct kvm_memory_slot *memslot;
@@ -675,8 +681,9 @@ static void sort_memslots(struct kvm_memslots *slots)
 		slots->id_to_index[slots->memslots[i].id] = i;
 }
 
-void update_memslots(struct kvm_memslots *slots, struct kvm_memory_slot *new,
-		     u64 last_generation)
+static void update_memslots(struct kvm_memslots *slots,
+			    struct kvm_memory_slot *new,
+			    u64 last_generation)
 {
 	if (new) {
 		int id = new->id;
@@ -924,8 +931,8 @@ int kvm_set_memory_region(struct kvm *kvm,
 }
 EXPORT_SYMBOL_GPL(kvm_set_memory_region);
 
-int kvm_vm_ioctl_set_memory_region(struct kvm *kvm,
-				   struct kvm_userspace_memory_region *mem)
+static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm,
+					  struct kvm_userspace_memory_region *mem)
 {
 	if (mem->slot >= KVM_USER_MEM_SLOTS)
 		return -EINVAL;
@@ -1047,7 +1054,7 @@ static unsigned long gfn_to_hva_many(struct kvm_memory_slot *slot, gfn_t gfn,
 }
 
 unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot,
-				 gfn_t gfn)
+					gfn_t gfn)
 {
 	return gfn_to_hva_many(slot, gfn, NULL);
 }
@@ -1387,18 +1394,11 @@ void kvm_release_page_dirty(struct page *page)
 }
 EXPORT_SYMBOL_GPL(kvm_release_page_dirty);
 
-void kvm_release_pfn_dirty(pfn_t pfn)
+static void kvm_release_pfn_dirty(pfn_t pfn)
 {
 	kvm_set_pfn_dirty(pfn);
 	kvm_release_pfn_clean(pfn);
 }
-EXPORT_SYMBOL_GPL(kvm_release_pfn_dirty);
-
-void kvm_set_page_dirty(struct page *page)
-{
-	kvm_set_pfn_dirty(page_to_pfn(page));
-}
-EXPORT_SYMBOL_GPL(kvm_set_page_dirty);
 
 void kvm_set_pfn_dirty(pfn_t pfn)
 {
@@ -1640,8 +1640,9 @@ int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len)
 }
 EXPORT_SYMBOL_GPL(kvm_clear_guest);
 
-void mark_page_dirty_in_slot(struct kvm *kvm, struct kvm_memory_slot *memslot,
-			     gfn_t gfn)
+static void mark_page_dirty_in_slot(struct kvm *kvm,
+				    struct kvm_memory_slot *memslot,
+				    gfn_t gfn)
 {
 	if (memslot && memslot->dirty_bitmap) {
 		unsigned long rel_gfn = gfn - memslot->base_gfn;
@@ -1710,14 +1711,6 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
 EXPORT_SYMBOL_GPL(kvm_vcpu_kick);
 #endif /* !CONFIG_S390 */
 
-void kvm_resched(struct kvm_vcpu *vcpu)
-{
-	if (!need_resched())
-		return;
-	cond_resched();
-}
-EXPORT_SYMBOL_GPL(kvm_resched);
-
 bool kvm_vcpu_yield_to(struct kvm_vcpu *target)
 {
 	struct pid *pid;
@@ -1742,7 +1735,6 @@ bool kvm_vcpu_yield_to(struct kvm_vcpu *target)
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_yield_to);
 
-#ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
 /*
  * Helper that checks whether a VCPU is eligible for directed yield.
  * Most eligible candidate to yield is decided by following heuristics:
@@ -1765,8 +1757,9 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_yield_to);
  *  locking does not harm. It may result in trying to yield to  same VCPU, fail
  *  and continue with next VCPU and so on.
  */
-bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu)
+static bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu)
 {
+#ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
 	bool eligible;
 
 	eligible = !vcpu->spin_loop.in_spin_loop ||
@@ -1777,8 +1770,10 @@ bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu)
 		kvm_vcpu_set_dy_eligible(vcpu, !vcpu->spin_loop.dy_eligible);
 
 	return eligible;
-}
+#else
+	return true;
 #endif
+}
 
 void kvm_vcpu_on_spin(struct kvm_vcpu *me)
 {
@@ -2284,6 +2279,11 @@ static int kvm_ioctl_create_device(struct kvm *kvm,
 		ops = &kvm_vfio_ops;
 		break;
 #endif
+#ifdef CONFIG_KVM_ARM_VGIC
+	case KVM_DEV_TYPE_ARM_VGIC_V2:
+		ops = &kvm_arm_vgic_v2_ops;
+		break;
+#endif
 	default:
 		return -ENODEV;
 	}
@@ -2939,33 +2939,6 @@ int kvm_io_bus_read(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 	return r < 0 ? r : 0;
 }
 
-/* kvm_io_bus_read_cookie - called under kvm->slots_lock */
-int kvm_io_bus_read_cookie(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
-			   int len, void *val, long cookie)
-{
-	struct kvm_io_bus *bus;
-	struct kvm_io_range range;
-
-	range = (struct kvm_io_range) {
-		.addr = addr,
-		.len = len,
-	};
-
-	bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu);
-
-	/* First try the device referenced by cookie. */
-	if ((cookie >= 0) && (cookie < bus->dev_count) &&
-	    (kvm_io_bus_cmp(&range, &bus->range[cookie]) == 0))
-		if (!kvm_iodevice_read(bus->range[cookie].dev, addr, len,
-				       val))
-			return cookie;
-
-	/*
-	 * cookie contained garbage; fall back to search and return the
-	 * correct cookie value.
-	 */
-	return __kvm_io_bus_read(bus, &range, val);
-}
 
 /* Caller must hold slots_lock. */
 int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c
index ca4260e35037..b4f9507ae650 100644
--- a/virt/kvm/vfio.c
+++ b/virt/kvm/vfio.c
@@ -101,14 +101,14 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
 	struct kvm_vfio *kv = dev->private;
 	struct vfio_group *vfio_group;
 	struct kvm_vfio_group *kvg;
-	void __user *argp = (void __user *)arg;
+	int32_t __user *argp = (int32_t __user *)(unsigned long)arg;
 	struct fd f;
 	int32_t fd;
 	int ret;
 
 	switch (attr) {
 	case KVM_DEV_VFIO_GROUP_ADD:
-		if (get_user(fd, (int32_t __user *)argp))
+		if (get_user(fd, argp))
 			return -EFAULT;
 
 		f = fdget(fd);
@@ -148,7 +148,7 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
 		return 0;
 
 	case KVM_DEV_VFIO_GROUP_DEL:
-		if (get_user(fd, (int32_t __user *)argp))
+		if (get_user(fd, argp))
 			return -EFAULT;
 
 		f = fdget(fd);