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

Pull KVM updates from Paolo Bonzini:
 "ARM:
   - support for SVE and Pointer Authentication in guests
   - PMU improvements

  POWER:
   - support for direct access to the POWER9 XIVE interrupt controller
   - memory and performance optimizations

  x86:
   - support for accessing memory not backed by struct page
   - fixes and refactoring

  Generic:
   - dirty page tracking improvements"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (155 commits)
  kvm: fix compilation on aarch64
  Revert "KVM: nVMX: Expose RDPMC-exiting only when guest supports PMU"
  kvm: x86: Fix L1TF mitigation for shadow MMU
  KVM: nVMX: Disable intercept for FS/GS base MSRs in vmcs02 when possible
  KVM: PPC: Book3S: Remove useless checks in 'release' method of KVM device
  KVM: PPC: Book3S HV: XIVE: Fix spelling mistake "acessing" -> "accessing"
  KVM: PPC: Book3S HV: Make sure to load LPID for radix VCPUs
  kvm: nVMX: Set nested_run_pending in vmx_set_nested_state after checks complete
  tests: kvm: Add tests for KVM_SET_NESTED_STATE
  KVM: nVMX: KVM_SET_NESTED_STATE - Tear down old EVMCS state before setting new state
  tests: kvm: Add tests for KVM_CAP_MAX_VCPUS and KVM_CAP_MAX_CPU_ID
  tests: kvm: Add tests to .gitignore
  KVM: Introduce KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2
  KVM: Fix kvm_clear_dirty_log_protect off-by-(minus-)one
  KVM: Fix the bitmap range to copy during clear dirty
  KVM: arm64: Fix ptrauth ID register masking logic
  KVM: x86: use direct accessors for RIP and RSP
  KVM: VMX: Use accessors for GPRs outside of dedicated caching logic
  KVM: x86: Omit caching logic for always-available GPRs
  kvm, x86: Properly check whether a pfn is an MMIO or not
  ...

3 files changed, 131 insertions, 18 deletions

diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index ea434ddc8499..aad9284c043a 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -57,3 +57,6 @@ config HAVE_KVM_VCPU_ASYNC_IOCTL
 
 config HAVE_KVM_VCPU_RUN_PID_CHANGE
        bool
+
+config HAVE_KVM_NO_POLL
+       bool
diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c
index f412ebc90610..90cedebaeb94 100644
--- a/virt/kvm/arm/arm.c
+++ b/virt/kvm/arm/arm.c
@@ -56,7 +56,7 @@
 __asm__(".arch_extension	virt");
 #endif
 
-DEFINE_PER_CPU(kvm_cpu_context_t, kvm_host_cpu_state);
+DEFINE_PER_CPU(kvm_host_data_t, kvm_host_data);
 static DEFINE_PER_CPU(unsigned long, kvm_arm_hyp_stack_page);
 
 /* Per-CPU variable containing the currently running vcpu. */
@@ -224,9 +224,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_MAX_VCPUS:
 		r = KVM_MAX_VCPUS;
 		break;
-	case KVM_CAP_NR_MEMSLOTS:
-		r = KVM_USER_MEM_SLOTS;
-		break;
 	case KVM_CAP_MSI_DEVID:
 		if (!kvm)
 			r = -EINVAL;
@@ -360,8 +357,10 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	int *last_ran;
+	kvm_host_data_t *cpu_data;
 
 	last_ran = this_cpu_ptr(vcpu->kvm->arch.last_vcpu_ran);
+	cpu_data = this_cpu_ptr(&kvm_host_data);
 
 	/*
 	 * We might get preempted before the vCPU actually runs, but
@@ -373,18 +372,21 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	}
 
 	vcpu->cpu = cpu;
-	vcpu->arch.host_cpu_context = this_cpu_ptr(&kvm_host_cpu_state);
+	vcpu->arch.host_cpu_context = &cpu_data->host_ctxt;
 
 	kvm_arm_set_running_vcpu(vcpu);
 	kvm_vgic_load(vcpu);
 	kvm_timer_vcpu_load(vcpu);
 	kvm_vcpu_load_sysregs(vcpu);
 	kvm_arch_vcpu_load_fp(vcpu);
+	kvm_vcpu_pmu_restore_guest(vcpu);
 
 	if (single_task_running())
 		vcpu_clear_wfe_traps(vcpu);
 	else
 		vcpu_set_wfe_traps(vcpu);
+
+	vcpu_ptrauth_setup_lazy(vcpu);
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
@@ -393,6 +395,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 	kvm_vcpu_put_sysregs(vcpu);
 	kvm_timer_vcpu_put(vcpu);
 	kvm_vgic_put(vcpu);
+	kvm_vcpu_pmu_restore_host(vcpu);
 
 	vcpu->cpu = -1;
 
@@ -545,6 +548,9 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
 	if (likely(vcpu->arch.has_run_once))
 		return 0;
 
+	if (!kvm_arm_vcpu_is_finalized(vcpu))
+		return -EPERM;
+
 	vcpu->arch.has_run_once = true;
 
 	if (likely(irqchip_in_kernel(kvm))) {
@@ -1121,6 +1127,10 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		if (unlikely(!kvm_vcpu_initialized(vcpu)))
 			break;
 
+		r = -EPERM;
+		if (!kvm_arm_vcpu_is_finalized(vcpu))
+			break;
+
 		r = -EFAULT;
 		if (copy_from_user(&reg_list, user_list, sizeof(reg_list)))
 			break;
@@ -1174,6 +1184,17 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 
 		return kvm_arm_vcpu_set_events(vcpu, &events);
 	}
+	case KVM_ARM_VCPU_FINALIZE: {
+		int what;
+
+		if (!kvm_vcpu_initialized(vcpu))
+			return -ENOEXEC;
+
+		if (get_user(what, (const int __user *)argp))
+			return -EFAULT;
+
+		return kvm_arm_vcpu_finalize(vcpu, what);
+	}
 	default:
 		r = -EINVAL;
 	}
@@ -1554,11 +1575,11 @@ static int init_hyp_mode(void)
 	}
 
 	for_each_possible_cpu(cpu) {
-		kvm_cpu_context_t *cpu_ctxt;
+		kvm_host_data_t *cpu_data;
 
-		cpu_ctxt = per_cpu_ptr(&kvm_host_cpu_state, cpu);
-		kvm_init_host_cpu_context(cpu_ctxt, cpu);
-		err = create_hyp_mappings(cpu_ctxt, cpu_ctxt + 1, PAGE_HYP);
+		cpu_data = per_cpu_ptr(&kvm_host_data, cpu);
+		kvm_init_host_cpu_context(&cpu_data->host_ctxt, cpu);
+		err = create_hyp_mappings(cpu_data, cpu_data + 1, PAGE_HYP);
 
 		if (err) {
 			kvm_err("Cannot map host CPU state: %d\n", err);
@@ -1669,6 +1690,10 @@ int kvm_arch_init(void *opaque)
 	if (err)
 		return err;
 
+	err = kvm_arm_init_sve();
+	if (err)
+		return err;
+
 	if (!in_hyp_mode) {
 		err = init_hyp_mode();
 		if (err)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 5fb0f1656a96..f0d13d9d125d 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -51,9 +51,9 @@
 #include <linux/slab.h>
 #include <linux/sort.h>
 #include <linux/bsearch.h>
+#include <linux/io.h>
 
 #include <asm/processor.h>
-#include <asm/io.h>
 #include <asm/ioctl.h>
 #include <linux/uaccess.h>
 #include <asm/pgtable.h>
@@ -1135,11 +1135,11 @@ EXPORT_SYMBOL_GPL(kvm_get_dirty_log);
 
 #ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
 /**
- * kvm_get_dirty_log_protect - get a snapshot of dirty pages, and if any pages
+ * kvm_get_dirty_log_protect - get a snapshot of dirty pages
  *	and reenable dirty page tracking for the corresponding pages.
  * @kvm:	pointer to kvm instance
  * @log:	slot id and address to which we copy the log
- * @is_dirty:	flag set if any page is dirty
+ * @flush:	true if TLB flush is needed by caller
  *
  * We need to keep it in mind that VCPU threads can write to the bitmap
  * concurrently. So, to avoid losing track of dirty pages we keep the
@@ -1224,6 +1224,7 @@ EXPORT_SYMBOL_GPL(kvm_get_dirty_log_protect);
  *	and reenable dirty page tracking for the corresponding pages.
  * @kvm:	pointer to kvm instance
  * @log:	slot id and address from which to fetch the bitmap of dirty pages
+ * @flush:	true if TLB flush is needed by caller
  */
 int kvm_clear_dirty_log_protect(struct kvm *kvm,
 				struct kvm_clear_dirty_log *log, bool *flush)
@@ -1251,7 +1252,7 @@ int kvm_clear_dirty_log_protect(struct kvm *kvm,
 	if (!dirty_bitmap)
 		return -ENOENT;
 
-	n = kvm_dirty_bitmap_bytes(memslot);
+	n = ALIGN(log->num_pages, BITS_PER_LONG) / 8;
 
 	if (log->first_page > memslot->npages ||
 	    log->num_pages > memslot->npages - log->first_page ||
@@ -1264,8 +1265,8 @@ int kvm_clear_dirty_log_protect(struct kvm *kvm,
 		return -EFAULT;
 
 	spin_lock(&kvm->mmu_lock);
-	for (offset = log->first_page,
-	     i = offset / BITS_PER_LONG, n = log->num_pages / BITS_PER_LONG; n--;
+	for (offset = log->first_page, i = offset / BITS_PER_LONG,
+		 n = DIV_ROUND_UP(log->num_pages, BITS_PER_LONG); n--;
 	     i++, offset += BITS_PER_LONG) {
 		unsigned long mask = *dirty_bitmap_buffer++;
 		atomic_long_t *p = (atomic_long_t *) &dirty_bitmap[i];
@@ -1742,6 +1743,70 @@ struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn)
 }
 EXPORT_SYMBOL_GPL(gfn_to_page);
 
+static int __kvm_map_gfn(struct kvm_memory_slot *slot, gfn_t gfn,
+			 struct kvm_host_map *map)
+{
+	kvm_pfn_t pfn;
+	void *hva = NULL;
+	struct page *page = KVM_UNMAPPED_PAGE;
+
+	if (!map)
+		return -EINVAL;
+
+	pfn = gfn_to_pfn_memslot(slot, gfn);
+	if (is_error_noslot_pfn(pfn))
+		return -EINVAL;
+
+	if (pfn_valid(pfn)) {
+		page = pfn_to_page(pfn);
+		hva = kmap(page);
+	} else {
+		hva = memremap(pfn_to_hpa(pfn), PAGE_SIZE, MEMREMAP_WB);
+	}
+
+	if (!hva)
+		return -EFAULT;
+
+	map->page = page;
+	map->hva = hva;
+	map->pfn = pfn;
+	map->gfn = gfn;
+
+	return 0;
+}
+
+int kvm_vcpu_map(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map)
+{
+	return __kvm_map_gfn(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn, map);
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_map);
+
+void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map,
+		    bool dirty)
+{
+	if (!map)
+		return;
+
+	if (!map->hva)
+		return;
+
+	if (map->page)
+		kunmap(map->page);
+	else
+		memunmap(map->hva);
+
+	if (dirty) {
+		kvm_vcpu_mark_page_dirty(vcpu, map->gfn);
+		kvm_release_pfn_dirty(map->pfn);
+	} else {
+		kvm_release_pfn_clean(map->pfn);
+	}
+
+	map->hva = NULL;
+	map->page = NULL;
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_unmap);
+
 struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn)
 {
 	kvm_pfn_t pfn;
@@ -2255,7 +2320,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 	u64 block_ns;
 
 	start = cur = ktime_get();
-	if (vcpu->halt_poll_ns) {
+	if (vcpu->halt_poll_ns && !kvm_arch_no_poll(vcpu)) {
 		ktime_t stop = ktime_add_ns(ktime_get(), vcpu->halt_poll_ns);
 
 		++vcpu->stat.halt_attempted_poll;
@@ -2886,6 +2951,16 @@ out:
 }
 #endif
 
+static int kvm_device_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+	struct kvm_device *dev = filp->private_data;
+
+	if (dev->ops->mmap)
+		return dev->ops->mmap(dev, vma);
+
+	return -ENODEV;
+}
+
 static int kvm_device_ioctl_attr(struct kvm_device *dev,
 				 int (*accessor)(struct kvm_device *dev,
 						 struct kvm_device_attr *attr),
@@ -2930,6 +3005,13 @@ static int kvm_device_release(struct inode *inode, struct file *filp)
 	struct kvm_device *dev = filp->private_data;
 	struct kvm *kvm = dev->kvm;
 
+	if (dev->ops->release) {
+		mutex_lock(&kvm->lock);
+		list_del(&dev->vm_node);
+		dev->ops->release(dev);
+		mutex_unlock(&kvm->lock);
+	}
+
 	kvm_put_kvm(kvm);
 	return 0;
 }
@@ -2938,6 +3020,7 @@ static const struct file_operations kvm_device_fops = {
 	.unlocked_ioctl = kvm_device_ioctl,
 	.release = kvm_device_release,
 	KVM_COMPAT(kvm_device_ioctl),
+	.mmap = kvm_device_mmap,
 };
 
 struct kvm_device *kvm_device_from_filp(struct file *filp)
@@ -3046,7 +3129,7 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 	case KVM_CAP_CHECK_EXTENSION_VM:
 	case KVM_CAP_ENABLE_CAP_VM:
 #ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
-	case KVM_CAP_MANUAL_DIRTY_LOG_PROTECT:
+	case KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2:
 #endif
 		return 1;
 #ifdef CONFIG_KVM_MMIO
@@ -3065,6 +3148,8 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 #endif
 	case KVM_CAP_MAX_VCPU_ID:
 		return KVM_MAX_VCPU_ID;
+	case KVM_CAP_NR_MEMSLOTS:
+		return KVM_USER_MEM_SLOTS;
 	default:
 		break;
 	}
@@ -3082,7 +3167,7 @@ static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm,
 {
 	switch (cap->cap) {
 #ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
-	case KVM_CAP_MANUAL_DIRTY_LOG_PROTECT:
+	case KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2:
 		if (cap->flags || (cap->args[0] & ~1))
 			return -EINVAL;
 		kvm->manual_dirty_log_protect = cap->args[0];