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

Pull KVM updates from Paolo Bonzini:
 "Small update for KVM:

  ARM:
   - lazy context-switching of FPSIMD registers on arm64
   - "split" regions for vGIC redistributor

  s390:
   - cleanups for nested
   - clock handling
   - crypto
   - storage keys
   - control register bits

  x86:
   - many bugfixes
   - implement more Hyper-V super powers
   - implement lapic_timer_advance_ns even when the LAPIC timer is
     emulated using the processor's VMX preemption timer.
   - two security-related bugfixes at the top of the branch"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (79 commits)
  kvm: fix typo in flag name
  kvm: x86: use correct privilege level for sgdt/sidt/fxsave/fxrstor access
  KVM: x86: pass kvm_vcpu to kvm_read_guest_virt and kvm_write_guest_virt_system
  KVM: x86: introduce linear_{read,write}_system
  kvm: nVMX: Enforce cpl=0 for VMX instructions
  kvm: nVMX: Add support for "VMWRITE to any supported field"
  kvm: nVMX: Restrict VMX capability MSR changes
  KVM: VMX: Optimize tscdeadline timer latency
  KVM: docs: nVMX: Remove known limitations as they do not exist now
  KVM: docs: mmu: KVM support exposing SLAT to guests
  kvm: no need to check return value of debugfs_create functions
  kvm: Make VM ioctl do valloc for some archs
  kvm: Change return type to vm_fault_t
  KVM: docs: mmu: Fix link to NPT presentation from KVM Forum 2008
  kvm: x86: Amend the KVM_GET_SUPPORTED_CPUID API documentation
  KVM: x86: hyperv: declare KVM_CAP_HYPERV_TLBFLUSH capability
  KVM: x86: hyperv: simplistic HVCALL_FLUSH_VIRTUAL_ADDRESS_{LIST,SPACE}_EX implementation
  KVM: x86: hyperv: simplistic HVCALL_FLUSH_VIRTUAL_ADDRESS_{LIST,SPACE} implementation
  KVM: introduce kvm_make_vcpus_request_mask() API
  KVM: x86: hyperv: do rep check for each hypercall separately
  ...

9 files changed, 404 insertions, 141 deletions

diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index cca7e065a075..72143cfaf6ec 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -54,3 +54,6 @@ config HAVE_KVM_IRQ_BYPASS
 
 config HAVE_KVM_VCPU_ASYNC_IOCTL
        bool
+
+config HAVE_KVM_VCPU_RUN_PID_CHANGE
+       bool
diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c
index 2d9b4795edb2..04e554cae3a2 100644
--- a/virt/kvm/arm/arm.c
+++ b/virt/kvm/arm/arm.c
@@ -16,6 +16,7 @@
  * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
  */
 
+#include <linux/bug.h>
 #include <linux/cpu_pm.h>
 #include <linux/errno.h>
 #include <linux/err.h>
@@ -41,6 +42,7 @@
 #include <asm/mman.h>
 #include <asm/tlbflush.h>
 #include <asm/cacheflush.h>
+#include <asm/cpufeature.h>
 #include <asm/virt.h>
 #include <asm/kvm_arm.h>
 #include <asm/kvm_asm.h>
@@ -163,7 +165,7 @@ int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
+vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
 {
 	return VM_FAULT_SIGBUS;
 }
@@ -249,6 +251,21 @@ long kvm_arch_dev_ioctl(struct file *filp,
 	return -EINVAL;
 }
 
+struct kvm *kvm_arch_alloc_vm(void)
+{
+	if (!has_vhe())
+		return kzalloc(sizeof(struct kvm), GFP_KERNEL);
+
+	return vzalloc(sizeof(struct kvm));
+}
+
+void kvm_arch_free_vm(struct kvm *kvm)
+{
+	if (!has_vhe())
+		kfree(kvm);
+	else
+		vfree(kvm);
+}
 
 struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
 {
@@ -290,7 +307,6 @@ out:
 
 void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 {
-	kvm_vgic_vcpu_early_init(vcpu);
 }
 
 void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
@@ -363,10 +379,12 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	kvm_vgic_load(vcpu);
 	kvm_timer_vcpu_load(vcpu);
 	kvm_vcpu_load_sysregs(vcpu);
+	kvm_arch_vcpu_load_fp(vcpu);
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
+	kvm_arch_vcpu_put_fp(vcpu);
 	kvm_vcpu_put_sysregs(vcpu);
 	kvm_timer_vcpu_put(vcpu);
 	kvm_vgic_put(vcpu);
@@ -678,9 +696,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		 */
 		preempt_disable();
 
-		/* Flush FP/SIMD state that can't survive guest entry/exit */
-		kvm_fpsimd_flush_cpu_state();
-
 		kvm_pmu_flush_hwstate(vcpu);
 
 		local_irq_disable();
@@ -778,6 +793,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		if (static_branch_unlikely(&userspace_irqchip_in_use))
 			kvm_timer_sync_hwstate(vcpu);
 
+		kvm_arch_vcpu_ctxsync_fp(vcpu);
+
 		/*
 		 * We may have taken a host interrupt in HYP mode (ie
 		 * while executing the guest). This interrupt is still
@@ -1574,6 +1591,11 @@ int kvm_arch_init(void *opaque)
 		return -ENODEV;
 	}
 
+	if (!kvm_arch_check_sve_has_vhe()) {
+		kvm_pr_unimpl("SVE system without VHE unsupported.  Broken cpu?");
+		return -ENODEV;
+	}
+
 	for_each_online_cpu(cpu) {
 		smp_call_function_single(cpu, check_kvm_target_cpu, &ret, 1);
 		if (ret < 0) {
diff --git a/virt/kvm/arm/vgic/vgic-debug.c b/virt/kvm/arm/vgic/vgic-debug.c
index 4ffc0b5e6105..c589d4c2b478 100644
--- a/virt/kvm/arm/vgic/vgic-debug.c
+++ b/virt/kvm/arm/vgic/vgic-debug.c
@@ -264,21 +264,12 @@ static const struct file_operations vgic_debug_fops = {
 	.release = seq_release
 };
 
-int vgic_debug_init(struct kvm *kvm)
+void vgic_debug_init(struct kvm *kvm)
 {
-	if (!kvm->debugfs_dentry)
-		return -ENOENT;
-
-	if (!debugfs_create_file("vgic-state", 0444,
-				 kvm->debugfs_dentry,
-				 kvm,
-				 &vgic_debug_fops))
-		return -ENOMEM;
-
-	return 0;
+	debugfs_create_file("vgic-state", 0444, kvm->debugfs_dentry, kvm,
+			    &vgic_debug_fops);
 }
 
-int vgic_debug_destroy(struct kvm *kvm)
+void vgic_debug_destroy(struct kvm *kvm)
 {
-	return 0;
 }
diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c
index e07156c30323..2673efce65f3 100644
--- a/virt/kvm/arm/vgic/vgic-init.c
+++ b/virt/kvm/arm/vgic/vgic-init.c
@@ -44,7 +44,7 @@
  *
  * CPU Interface:
  *
- * - kvm_vgic_vcpu_early_init(): initialization of static data that
+ * - kvm_vgic_vcpu_init(): initialization of static data that
  *   doesn't depend on any sizing information or emulation type. No
  *   allocation is allowed there.
  */
@@ -67,46 +67,6 @@ void kvm_vgic_early_init(struct kvm *kvm)
 	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 */
 
 /**
@@ -167,8 +127,11 @@ int kvm_vgic_create(struct kvm *kvm, u32 type)
 	kvm->arch.vgic.vgic_model = type;
 
 	kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF;
-	kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF;
-	kvm->arch.vgic.vgic_redist_base = VGIC_ADDR_UNDEF;
+
+	if (type == KVM_DEV_TYPE_ARM_VGIC_V2)
+		kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF;
+	else
+		INIT_LIST_HEAD(&kvm->arch.vgic.rd_regions);
 
 out_unlock:
 	for (; vcpu_lock_idx >= 0; vcpu_lock_idx--) {
@@ -221,13 +184,50 @@ static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis)
 }
 
 /**
- * kvm_vgic_vcpu_init() - Register VCPU-specific KVM iodevs
+ * kvm_vgic_vcpu_init() - Initialize static VGIC VCPU data
+ * structures and register VCPU-specific KVM iodevs
+ *
  * @vcpu: pointer to the VCPU being created and initialized
+ *
+ * Only do initialization, but do not actually enable the
+ * VGIC CPU interface
  */
 int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
 {
-	int ret = 0;
+	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+	int ret = 0;
+	int i;
+
+	vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF;
+	vgic_cpu->sgi_iodev.base_addr = VGIC_ADDR_UNDEF;
+
+	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 (!irqchip_in_kernel(vcpu->kvm))
 		return 0;
@@ -303,13 +303,23 @@ out:
 static void kvm_vgic_dist_destroy(struct kvm *kvm)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
+	struct vgic_redist_region *rdreg, *next;
 
 	dist->ready = false;
 	dist->initialized = false;
 
 	kfree(dist->spis);
+	dist->spis = NULL;
 	dist->nr_spis = 0;
 
+	if (kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) {
+		list_for_each_entry_safe(rdreg, next, &dist->rd_regions, list) {
+			list_del(&rdreg->list);
+			kfree(rdreg);
+		}
+		INIT_LIST_HEAD(&dist->rd_regions);
+	}
+
 	if (vgic_supports_direct_msis(kvm))
 		vgic_v4_teardown(kvm);
 }
diff --git a/virt/kvm/arm/vgic/vgic-kvm-device.c b/virt/kvm/arm/vgic/vgic-kvm-device.c
index 10ae6f394b71..6ada2432e37c 100644
--- a/virt/kvm/arm/vgic/vgic-kvm-device.c
+++ b/virt/kvm/arm/vgic/vgic-kvm-device.c
@@ -66,6 +66,7 @@ int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write)
 	int r = 0;
 	struct vgic_dist *vgic = &kvm->arch.vgic;
 	phys_addr_t *addr_ptr, alignment;
+	u64 undef_value = VGIC_ADDR_UNDEF;
 
 	mutex_lock(&kvm->lock);
 	switch (type) {
@@ -84,16 +85,61 @@ int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write)
 		addr_ptr = &vgic->vgic_dist_base;
 		alignment = SZ_64K;
 		break;
-	case KVM_VGIC_V3_ADDR_TYPE_REDIST:
+	case KVM_VGIC_V3_ADDR_TYPE_REDIST: {
+		struct vgic_redist_region *rdreg;
+
 		r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V3);
 		if (r)
 			break;
 		if (write) {
-			r = vgic_v3_set_redist_base(kvm, *addr);
+			r = vgic_v3_set_redist_base(kvm, 0, *addr, 0);
 			goto out;
 		}
-		addr_ptr = &vgic->vgic_redist_base;
+		rdreg = list_first_entry(&vgic->rd_regions,
+					 struct vgic_redist_region, list);
+		if (!rdreg)
+			addr_ptr = &undef_value;
+		else
+			addr_ptr = &rdreg->base;
 		break;
+	}
+	case KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION:
+	{
+		struct vgic_redist_region *rdreg;
+		u8 index;
+
+		r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V3);
+		if (r)
+			break;
+
+		index = *addr & KVM_VGIC_V3_RDIST_INDEX_MASK;
+
+		if (write) {
+			gpa_t base = *addr & KVM_VGIC_V3_RDIST_BASE_MASK;
+			u32 count = (*addr & KVM_VGIC_V3_RDIST_COUNT_MASK)
+					>> KVM_VGIC_V3_RDIST_COUNT_SHIFT;
+			u8 flags = (*addr & KVM_VGIC_V3_RDIST_FLAGS_MASK)
+					>> KVM_VGIC_V3_RDIST_FLAGS_SHIFT;
+
+			if (!count || flags)
+				r = -EINVAL;
+			else
+				r = vgic_v3_set_redist_base(kvm, index,
+							    base, count);
+			goto out;
+		}
+
+		rdreg = vgic_v3_rdist_region_from_index(kvm, index);
+		if (!rdreg) {
+			r = -ENOENT;
+			goto out;
+		}
+
+		*addr = index;
+		*addr |= rdreg->base;
+		*addr |= (u64)rdreg->count << KVM_VGIC_V3_RDIST_COUNT_SHIFT;
+		goto out;
+	}
 	default:
 		r = -ENODEV;
 	}
@@ -665,6 +711,7 @@ static int vgic_v3_has_attr(struct kvm_device *dev,
 		switch (attr->attr) {
 		case KVM_VGIC_V3_ADDR_TYPE_DIST:
 		case KVM_VGIC_V3_ADDR_TYPE_REDIST:
+		case KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION:
 			return 0;
 		}
 		break;
diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c
index 671fe81f8e1d..287784095b5b 100644
--- a/virt/kvm/arm/vgic/vgic-mmio-v3.c
+++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c
@@ -184,12 +184,17 @@ static unsigned long vgic_mmio_read_v3r_typer(struct kvm_vcpu *vcpu,
 					      gpa_t addr, unsigned int len)
 {
 	unsigned long mpidr = kvm_vcpu_get_mpidr_aff(vcpu);
+	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+	struct vgic_redist_region *rdreg = vgic_cpu->rdreg;
 	int target_vcpu_id = vcpu->vcpu_id;
+	gpa_t last_rdist_typer = rdreg->base + GICR_TYPER +
+			(rdreg->free_index - 1) * KVM_VGIC_V3_REDIST_SIZE;
 	u64 value;
 
 	value = (u64)(mpidr & GENMASK(23, 0)) << 32;
 	value |= ((target_vcpu_id & 0xffff) << 8);
-	if (target_vcpu_id == atomic_read(&vcpu->kvm->online_vcpus) - 1)
+
+	if (addr == last_rdist_typer)
 		value |= GICR_TYPER_LAST;
 	if (vgic_has_its(vcpu->kvm))
 		value |= GICR_TYPER_PLPIS;
@@ -580,24 +585,32 @@ int vgic_register_redist_iodev(struct kvm_vcpu *vcpu)
 {
 	struct kvm *kvm = vcpu->kvm;
 	struct vgic_dist *vgic = &kvm->arch.vgic;
+	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 	struct vgic_io_device *rd_dev = &vcpu->arch.vgic_cpu.rd_iodev;
 	struct vgic_io_device *sgi_dev = &vcpu->arch.vgic_cpu.sgi_iodev;
+	struct vgic_redist_region *rdreg;
 	gpa_t rd_base, sgi_base;
 	int ret;
 
+	if (!IS_VGIC_ADDR_UNDEF(vgic_cpu->rd_iodev.base_addr))
+		return 0;
+
 	/*
 	 * We may be creating VCPUs before having set the base address for the
 	 * redistributor region, in which case we will come back to this
 	 * function for all VCPUs when the base address is set.  Just return
 	 * without doing any work for now.
 	 */
-	if (IS_VGIC_ADDR_UNDEF(vgic->vgic_redist_base))
+	rdreg = vgic_v3_rdist_free_slot(&vgic->rd_regions);
+	if (!rdreg)
 		return 0;
 
 	if (!vgic_v3_check_base(kvm))
 		return -EINVAL;
 
-	rd_base = vgic->vgic_redist_base + vgic->vgic_redist_free_offset;
+	vgic_cpu->rdreg = rdreg;
+
+	rd_base = rdreg->base + rdreg->free_index * KVM_VGIC_V3_REDIST_SIZE;
 	sgi_base = rd_base + SZ_64K;
 
 	kvm_iodevice_init(&rd_dev->dev, &kvm_io_gic_ops);
@@ -631,7 +644,7 @@ int vgic_register_redist_iodev(struct kvm_vcpu *vcpu)
 		goto out;
 	}
 
-	vgic->vgic_redist_free_offset += 2 * SZ_64K;
+	rdreg->free_index++;
 out:
 	mutex_unlock(&kvm->slots_lock);
 	return ret;
@@ -670,23 +683,96 @@ static int vgic_register_all_redist_iodevs(struct kvm *kvm)
 	return ret;
 }
 
-int vgic_v3_set_redist_base(struct kvm *kvm, u64 addr)
+/**
+ * vgic_v3_insert_redist_region - Insert a new redistributor region
+ *
+ * Performs various checks before inserting the rdist region in the list.
+ * Those tests depend on whether the size of the rdist region is known
+ * (ie. count != 0). The list is sorted by rdist region index.
+ *
+ * @kvm: kvm handle
+ * @index: redist region index
+ * @base: base of the new rdist region
+ * @count: number of redistributors the region is made of (0 in the old style
+ * single region, whose size is induced from the number of vcpus)
+ *
+ * Return 0 on success, < 0 otherwise
+ */
+static int vgic_v3_insert_redist_region(struct kvm *kvm, uint32_t index,
+					gpa_t base, uint32_t count)
 {
-	struct vgic_dist *vgic = &kvm->arch.vgic;
+	struct vgic_dist *d = &kvm->arch.vgic;
+	struct vgic_redist_region *rdreg;
+	struct list_head *rd_regions = &d->rd_regions;
+	size_t size = count * KVM_VGIC_V3_REDIST_SIZE;
 	int ret;
 
-	/* vgic_check_ioaddr makes sure we don't do this twice */
-	ret = vgic_check_ioaddr(kvm, &vgic->vgic_redist_base, addr, SZ_64K);
-	if (ret)
-		return ret;
+	/* single rdist region already set ?*/
+	if (!count && !list_empty(rd_regions))
+		return -EINVAL;
 
-	vgic->vgic_redist_base = addr;
-	if (!vgic_v3_check_base(kvm)) {
-		vgic->vgic_redist_base = VGIC_ADDR_UNDEF;
+	/* cross the end of memory ? */
+	if (base + size < base)
 		return -EINVAL;
+
+	if (list_empty(rd_regions)) {
+		if (index != 0)
+			return -EINVAL;
+	} else {
+		rdreg = list_last_entry(rd_regions,
+					struct vgic_redist_region, list);
+		if (index != rdreg->index + 1)
+			return -EINVAL;
+
+		/* Cannot add an explicitly sized regions after legacy region */
+		if (!rdreg->count)
+			return -EINVAL;
 	}
 
 	/*
+	 * For legacy single-region redistributor regions (!count),
+	 * check that the redistributor region does not overlap with the
+	 * distributor's address space.
+	 */
+	if (!count && !IS_VGIC_ADDR_UNDEF(d->vgic_dist_base) &&
+		vgic_dist_overlap(kvm, base, size))
+		return -EINVAL;
+
+	/* collision with any other rdist region? */
+	if (vgic_v3_rdist_overlap(kvm, base, size))
+		return -EINVAL;
+
+	rdreg = kzalloc(sizeof(*rdreg), GFP_KERNEL);
+	if (!rdreg)
+		return -ENOMEM;
+
+	rdreg->base = VGIC_ADDR_UNDEF;
+
+	ret = vgic_check_ioaddr(kvm, &rdreg->base, base, SZ_64K);
+	if (ret)
+		goto free;
+
+	rdreg->base = base;
+	rdreg->count = count;
+	rdreg->free_index = 0;
+	rdreg->index = index;
+
+	list_add_tail(&rdreg->list, rd_regions);
+	return 0;
+free:
+	kfree(rdreg);
+	return ret;
+}
+
+int vgic_v3_set_redist_base(struct kvm *kvm, u32 index, u64 addr, u32 count)
+{
+	int ret;
+
+	ret = vgic_v3_insert_redist_region(kvm, index, addr, count);
+	if (ret)
+		return ret;
+
+	/*
 	 * Register iodevs for each existing VCPU.  Adding more VCPUs
 	 * afterwards will register the iodevs when needed.
 	 */
diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c
index bdcf8e7a6161..ff7dc890941a 100644
--- a/virt/kvm/arm/vgic/vgic-v3.c
+++ b/virt/kvm/arm/vgic/vgic-v3.c
@@ -419,6 +419,29 @@ int vgic_v3_save_pending_tables(struct kvm *kvm)
 	return 0;
 }
 
+/**
+ * vgic_v3_rdist_overlap - check if a region overlaps with any
+ * existing redistributor region
+ *
+ * @kvm: kvm handle
+ * @base: base of the region
+ * @size: size of region
+ *
+ * Return: true if there is an overlap
+ */
+bool vgic_v3_rdist_overlap(struct kvm *kvm, gpa_t base, size_t size)
+{
+	struct vgic_dist *d = &kvm->arch.vgic;
+	struct vgic_redist_region *rdreg;
+
+	list_for_each_entry(rdreg, &d->rd_regions, list) {
+		if ((base + size > rdreg->base) &&
+			(base < rdreg->base + vgic_v3_rd_region_size(kvm, rdreg)))
+			return true;
+	}
+	return false;
+}
+
 /*
  * Check for overlapping regions and for regions crossing the end of memory
  * for base addresses which have already been set.
@@ -426,41 +449,83 @@ int vgic_v3_save_pending_tables(struct kvm *kvm)
 bool vgic_v3_check_base(struct kvm *kvm)
 {
 	struct vgic_dist *d = &kvm->arch.vgic;
-	gpa_t redist_size = KVM_VGIC_V3_REDIST_SIZE;
-
-	redist_size *= atomic_read(&kvm->online_vcpus);
+	struct vgic_redist_region *rdreg;
 
 	if (!IS_VGIC_ADDR_UNDEF(d->vgic_dist_base) &&
 	    d->vgic_dist_base + KVM_VGIC_V3_DIST_SIZE < d->vgic_dist_base)
 		return false;
 
-	if (!IS_VGIC_ADDR_UNDEF(d->vgic_redist_base) &&
-	    d->vgic_redist_base + redist_size < d->vgic_redist_base)
-		return false;
+	list_for_each_entry(rdreg, &d->rd_regions, list) {
+		if (rdreg->base + vgic_v3_rd_region_size(kvm, rdreg) <
+			rdreg->base)
+			return false;
+	}
 
-	/* Both base addresses must be set to check if they overlap */
-	if (IS_VGIC_ADDR_UNDEF(d->vgic_dist_base) ||
-	    IS_VGIC_ADDR_UNDEF(d->vgic_redist_base))
+	if (IS_VGIC_ADDR_UNDEF(d->vgic_dist_base))
 		return true;
 
-	if (d->vgic_dist_base + KVM_VGIC_V3_DIST_SIZE <= d->vgic_redist_base)
-		return true;
-	if (d->vgic_redist_base + redist_size <= d->vgic_dist_base)
-		return true;
+	return !vgic_v3_rdist_overlap(kvm, d->vgic_dist_base,
+				      KVM_VGIC_V3_DIST_SIZE);
+}
 
-	return false;
+/**
+ * vgic_v3_rdist_free_slot - Look up registered rdist regions and identify one
+ * which has free space to put a new rdist region.
+ *
+ * @rd_regions: redistributor region list head
+ *
+ * A redistributor regions maps n redistributors, n = region size / (2 x 64kB).
+ * Stride between redistributors is 0 and regions are filled in the index order.
+ *
+ * Return: the redist region handle, if any, that has space to map a new rdist
+ * region.
+ */
+struct vgic_redist_region *vgic_v3_rdist_free_slot(struct list_head *rd_regions)
+{
+	struct vgic_redist_region *rdreg;
+
+	list_for_each_entry(rdreg, rd_regions, list) {
+		if (!vgic_v3_redist_region_full(rdreg))
+			return rdreg;
+	}
+	return NULL;
 }
 
+struct vgic_redist_region *vgic_v3_rdist_region_from_index(struct kvm *kvm,
+							   u32 index)
+{
+	struct list_head *rd_regions = &kvm->arch.vgic.rd_regions;
+	struct vgic_redist_region *rdreg;
+
+	list_for_each_entry(rdreg, rd_regions, list) {
+		if (rdreg->index == index)
+			return rdreg;
+	}
+	return NULL;
+}
+
+
 int vgic_v3_map_resources(struct kvm *kvm)
 {
-	int ret = 0;
 	struct vgic_dist *dist = &kvm->arch.vgic;
+	struct kvm_vcpu *vcpu;
+	int ret = 0;
+	int c;
 
 	if (vgic_ready(kvm))
 		goto out;
 
-	if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base) ||
-	    IS_VGIC_ADDR_UNDEF(dist->vgic_redist_base)) {
+	kvm_for_each_vcpu(c, vcpu, kvm) {
+		struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+
+		if (IS_VGIC_ADDR_UNDEF(vgic_cpu->rd_iodev.base_addr)) {
+			kvm_debug("vcpu %d redistributor base not set\n", c);
+			ret = -ENXIO;
+			goto out;
+		}
+	}
+
+	if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base)) {
 		kvm_err("Need to set vgic distributor addresses first\n");
 		ret = -ENXIO;
 		goto out;
diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h
index 32c25d42c93f..ead00b2072b2 100644
--- a/virt/kvm/arm/vgic/vgic.h
+++ b/virt/kvm/arm/vgic/vgic.h
@@ -96,6 +96,13 @@
 /* we only support 64 kB translation table page size */
 #define KVM_ITS_L1E_ADDR_MASK		GENMASK_ULL(51, 16)
 
+#define KVM_VGIC_V3_RDIST_INDEX_MASK	GENMASK_ULL(11, 0)
+#define KVM_VGIC_V3_RDIST_FLAGS_MASK	GENMASK_ULL(15, 12)
+#define KVM_VGIC_V3_RDIST_FLAGS_SHIFT	12
+#define KVM_VGIC_V3_RDIST_BASE_MASK	GENMASK_ULL(51, 16)
+#define KVM_VGIC_V3_RDIST_COUNT_MASK	GENMASK_ULL(63, 52)
+#define KVM_VGIC_V3_RDIST_COUNT_SHIFT	52
+
 /* Requires the irq_lock to be held by the caller. */
 static inline bool irq_is_pending(struct vgic_irq *irq)
 {
@@ -215,7 +222,7 @@ int vgic_v3_probe(const struct gic_kvm_info *info);
 int vgic_v3_map_resources(struct kvm *kvm);
 int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq);
 int vgic_v3_save_pending_tables(struct kvm *kvm);
-int vgic_v3_set_redist_base(struct kvm *kvm, u64 addr);
+int vgic_v3_set_redist_base(struct kvm *kvm, u32 index, u64 addr, u32 count);
 int vgic_register_redist_iodev(struct kvm_vcpu *vcpu);
 bool vgic_v3_check_base(struct kvm *kvm);
 
@@ -243,8 +250,8 @@ void vgic_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr);
 int vgic_lazy_init(struct kvm *kvm);
 int vgic_init(struct kvm *kvm);
 
-int vgic_debug_init(struct kvm *kvm);
-int vgic_debug_destroy(struct kvm *kvm);
+void vgic_debug_init(struct kvm *kvm);
+void vgic_debug_destroy(struct kvm *kvm);
 
 bool lock_all_vcpus(struct kvm *kvm);
 void unlock_all_vcpus(struct kvm *kvm);
@@ -265,6 +272,39 @@ static inline int vgic_v3_max_apr_idx(struct kvm_vcpu *vcpu)
 	}
 }
 
+static inline bool
+vgic_v3_redist_region_full(struct vgic_redist_region *region)
+{
+	if (!region->count)
+		return false;
+
+	return (region->free_index >= region->count);
+}
+
+struct vgic_redist_region *vgic_v3_rdist_free_slot(struct list_head *rdregs);
+
+static inline size_t
+vgic_v3_rd_region_size(struct kvm *kvm, struct vgic_redist_region *rdreg)
+{
+	if (!rdreg->count)
+		return atomic_read(&kvm->online_vcpus) * KVM_VGIC_V3_REDIST_SIZE;
+	else
+		return rdreg->count * KVM_VGIC_V3_REDIST_SIZE;
+}
+
+struct vgic_redist_region *vgic_v3_rdist_region_from_index(struct kvm *kvm,
+							   u32 index);
+
+bool vgic_v3_rdist_overlap(struct kvm *kvm, gpa_t base, size_t size);
+
+static inline bool vgic_dist_overlap(struct kvm *kvm, gpa_t base, size_t size)
+{
+	struct vgic_dist *d = &kvm->arch.vgic;
+
+	return (base + size > d->vgic_dist_base) &&
+		(base < d->vgic_dist_base + KVM_VGIC_V3_DIST_SIZE);
+}
+
 int vgic_its_resolve_lpi(struct kvm *kvm, struct vgic_its *its,
 			 u32 devid, u32 eventid, struct vgic_irq **irq);
 struct vgic_its *vgic_msi_to_its(struct kvm *kvm, struct kvm_msi *msi);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index c7b2e927f699..aa7da1d8ece2 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -203,29 +203,47 @@ static inline bool kvm_kick_many_cpus(const struct cpumask *cpus, bool wait)
 	return true;
 }
 
-bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req)
+bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req,
+				 unsigned long *vcpu_bitmap, cpumask_var_t tmp)
 {
 	int i, cpu, me;
-	cpumask_var_t cpus;
-	bool called;
 	struct kvm_vcpu *vcpu;
-
-	zalloc_cpumask_var(&cpus, GFP_ATOMIC);
+	bool called;
 
 	me = get_cpu();
+
 	kvm_for_each_vcpu(i, vcpu, kvm) {
+		if (!test_bit(i, vcpu_bitmap))
+			continue;
+
 		kvm_make_request(req, vcpu);
 		cpu = vcpu->cpu;
 
 		if (!(req & KVM_REQUEST_NO_WAKEUP) && kvm_vcpu_wake_up(vcpu))
 			continue;
 
-		if (cpus != NULL && cpu != -1 && cpu != me &&
+		if (tmp != NULL && cpu != -1 && cpu != me &&
 		    kvm_request_needs_ipi(vcpu, req))
-			__cpumask_set_cpu(cpu, cpus);
+			__cpumask_set_cpu(cpu, tmp);
 	}
-	called = kvm_kick_many_cpus(cpus, !!(req & KVM_REQUEST_WAIT));
+
+	called = kvm_kick_many_cpus(tmp, !!(req & KVM_REQUEST_WAIT));
 	put_cpu();
+
+	return called;
+}
+
+bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req)
+{
+	cpumask_var_t cpus;
+	bool called;
+	static unsigned long vcpu_bitmap[BITS_TO_LONGS(KVM_MAX_VCPUS)]
+		= {[0 ... BITS_TO_LONGS(KVM_MAX_VCPUS)-1] = ULONG_MAX};
+
+	zalloc_cpumask_var(&cpus, GFP_ATOMIC);
+
+	called = kvm_make_vcpus_request_mask(kvm, req, vcpu_bitmap, cpus);
+
 	free_cpumask_var(cpus);
 	return called;
 }
@@ -572,10 +590,7 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd)
 		return 0;
 
 	snprintf(dir_name, sizeof(dir_name), "%d-%d", task_pid_nr(current), fd);
-	kvm->debugfs_dentry = debugfs_create_dir(dir_name,
-						 kvm_debugfs_dir);
-	if (!kvm->debugfs_dentry)
-		return -ENOMEM;
+	kvm->debugfs_dentry = debugfs_create_dir(dir_name, kvm_debugfs_dir);
 
 	kvm->debugfs_stat_data = kcalloc(kvm_debugfs_num_entries,
 					 sizeof(*kvm->debugfs_stat_data),
@@ -591,11 +606,8 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd)
 		stat_data->kvm = kvm;
 		stat_data->offset = p->offset;
 		kvm->debugfs_stat_data[p - debugfs_entries] = stat_data;
-		if (!debugfs_create_file(p->name, 0644,
-					 kvm->debugfs_dentry,
-					 stat_data,
-					 stat_fops_per_vm[p->kind]))
-			return -ENOMEM;
+		debugfs_create_file(p->name, 0644, kvm->debugfs_dentry,
+				    stat_data, stat_fops_per_vm[p->kind]);
 	}
 	return 0;
 }
@@ -2340,7 +2352,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode)
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_on_spin);
 
-static int kvm_vcpu_fault(struct vm_fault *vmf)
+static vm_fault_t kvm_vcpu_fault(struct vm_fault *vmf)
 {
 	struct kvm_vcpu *vcpu = vmf->vma->vm_file->private_data;
 	struct page *page;
@@ -2550,8 +2562,13 @@ static long kvm_vcpu_ioctl(struct file *filp,
 		oldpid = rcu_access_pointer(vcpu->pid);
 		if (unlikely(oldpid != current->pids[PIDTYPE_PID].pid)) {
 			/* The thread running this VCPU changed. */
-			struct pid *newpid = get_task_pid(current, PIDTYPE_PID);
+			struct pid *newpid;
+
+			r = kvm_arch_vcpu_run_pid_change(vcpu);
+			if (r)
+				break;
 
+			newpid = get_task_pid(current, PIDTYPE_PID);
 			rcu_assign_pointer(vcpu->pid, newpid);
 			if (oldpid)
 				synchronize_rcu();
@@ -3896,29 +3913,18 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm)
 	kfree(env);
 }
 
-static int kvm_init_debug(void)
+static void kvm_init_debug(void)
 {
-	int r = -EEXIST;
 	struct kvm_stats_debugfs_item *p;
 
 	kvm_debugfs_dir = debugfs_create_dir("kvm", NULL);
-	if (kvm_debugfs_dir == NULL)
-		goto out;
 
 	kvm_debugfs_num_entries = 0;
 	for (p = debugfs_entries; p->name; ++p, kvm_debugfs_num_entries++) {
-		if (!debugfs_create_file(p->name, 0644, kvm_debugfs_dir,
-					 (void *)(long)p->offset,
-					 stat_fops[p->kind]))
-			goto out_dir;
+		debugfs_create_file(p->name, 0644, kvm_debugfs_dir,
+				    (void *)(long)p->offset,
+				    stat_fops[p->kind]);
 	}
-
-	return 0;
-
-out_dir:
-	debugfs_remove_recursive(kvm_debugfs_dir);
-out:
-	return r;
 }
 
 static int kvm_suspend(void)
@@ -4046,20 +4052,13 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 	kvm_preempt_ops.sched_in = kvm_sched_in;
 	kvm_preempt_ops.sched_out = kvm_sched_out;
 
-	r = kvm_init_debug();
-	if (r) {
-		pr_err("kvm: create debugfs files failed\n");
-		goto out_undebugfs;
-	}
+	kvm_init_debug();
 
 	r = kvm_vfio_ops_init();
 	WARN_ON(r);
 
 	return 0;
 
-out_undebugfs:
-	unregister_syscore_ops(&kvm_syscore_ops);
-	misc_deregister(&kvm_dev);
 out_unreg:
 	kvm_async_pf_deinit();
 out_free: