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

Pull kvm updates from Paolo Bonzini:
 "RISCV:

   - Use common KVM implementation of MMU memory caches

   - SBI v0.2 support for Guest

   - Initial KVM selftests support

   - Fix to avoid spurious virtual interrupts after clearing hideleg CSR

   - Update email address for Anup and Atish

  ARM:

   - Simplification of the 'vcpu first run' by integrating it into KVM's
     'pid change' flow

   - Refactoring of the FP and SVE state tracking, also leading to a
     simpler state and less shared data between EL1 and EL2 in the nVHE
     case

   - Tidy up the header file usage for the nvhe hyp object

   - New HYP unsharing mechanism, finally allowing pages to be unmapped
     from the Stage-1 EL2 page-tables

   - Various pKVM cleanups around refcounting and sharing

   - A couple of vgic fixes for bugs that would trigger once the vcpu
     xarray rework is merged, but not sooner

   - Add minimal support for ARMv8.7's PMU extension

   - Rework kvm_pgtable initialisation ahead of the NV work

   - New selftest for IRQ injection

   - Teach selftests about the lack of default IPA space and page sizes

   - Expand sysreg selftest to deal with Pointer Authentication

   - The usual bunch of cleanups and doc update

  s390:

   - fix sigp sense/start/stop/inconsistency

   - cleanups

  x86:

   - Clean up some function prototypes more

   - improved gfn_to_pfn_cache with proper invalidation, used by Xen
     emulation

   - add KVM_IRQ_ROUTING_XEN_EVTCHN and event channel delivery

   - completely remove potential TOC/TOU races in nested SVM consistency
     checks

   - update some PMCs on emulated instructions

   - Intel AMX support (joint work between Thomas and Intel)

   - large MMU cleanups

   - module parameter to disable PMU virtualization

   - cleanup register cache

   - first part of halt handling cleanups

   - Hyper-V enlightened MSR bitmap support for nested hypervisors

  Generic:

   - clean up Makefiles

   - introduce CONFIG_HAVE_KVM_DIRTY_RING

   - optimize memslot lookup using a tree

   - optimize vCPU array usage by converting to xarray"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (268 commits)
  x86/fpu: Fix inline prefix warnings
  selftest: kvm: Add amx selftest
  selftest: kvm: Move struct kvm_x86_state to header
  selftest: kvm: Reorder vcpu_load_state steps for AMX
  kvm: x86: Disable interception for IA32_XFD on demand
  x86/fpu: Provide fpu_sync_guest_vmexit_xfd_state()
  kvm: selftests: Add support for KVM_CAP_XSAVE2
  kvm: x86: Add support for getting/setting expanded xstate buffer
  x86/fpu: Add uabi_size to guest_fpu
  kvm: x86: Add CPUID support for Intel AMX
  kvm: x86: Add XCR0 support for Intel AMX
  kvm: x86: Disable RDMSR interception of IA32_XFD_ERR
  kvm: x86: Emulate IA32_XFD_ERR for guest
  kvm: x86: Intercept #NM for saving IA32_XFD_ERR
  x86/fpu: Prepare xfd_err in struct fpu_guest
  kvm: x86: Add emulation for IA32_XFD
  x86/fpu: Provide fpu_update_guest_xfd() for IA32_XFD emulation
  kvm: x86: Enable dynamic xfeatures at KVM_SET_CPUID2
  x86/fpu: Provide fpu_enable_guest_xfd_features() for KVM
  x86/fpu: Add guest support to xfd_enable_feature()
  ...

1 files changed, 74 insertions, 54 deletions

diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index f026fd01bf7b..a4a0063df456 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -146,7 +146,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	if (ret)
 		return ret;
 
-	ret = create_hyp_mappings(kvm, kvm + 1, PAGE_HYP);
+	ret = kvm_share_hyp(kvm, kvm + 1);
 	if (ret)
 		goto out_free_stage2_pgd;
 
@@ -175,19 +175,13 @@ vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
  */
 void kvm_arch_destroy_vm(struct kvm *kvm)
 {
-	int i;
-
 	bitmap_free(kvm->arch.pmu_filter);
 
 	kvm_vgic_destroy(kvm);
 
-	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
-		if (kvm->vcpus[i]) {
-			kvm_vcpu_destroy(kvm->vcpus[i]);
-			kvm->vcpus[i] = NULL;
-		}
-	}
-	atomic_set(&kvm->online_vcpus, 0);
+	kvm_destroy_vcpus(kvm);
+
+	kvm_unshare_hyp(kvm, kvm + 1);
 }
 
 int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
@@ -342,7 +336,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	if (err)
 		return err;
 
-	return create_hyp_mappings(vcpu, vcpu + 1, PAGE_HYP);
+	return kvm_share_hyp(vcpu, vcpu + 1);
 }
 
 void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
@@ -351,7 +345,7 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
-	if (vcpu->arch.has_run_once && unlikely(!irqchip_in_kernel(vcpu->kvm)))
+	if (vcpu_has_run_once(vcpu) && unlikely(!irqchip_in_kernel(vcpu->kvm)))
 		static_branch_dec(&userspace_irqchip_in_use);
 
 	kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache);
@@ -368,27 +362,12 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 
 void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
 {
-	/*
-	 * If we're about to block (most likely because we've just hit a
-	 * WFI), we need to sync back the state of the GIC CPU interface
-	 * so that we have the latest PMR and group enables. This ensures
-	 * that kvm_arch_vcpu_runnable has up-to-date data to decide
-	 * whether we have pending interrupts.
-	 *
-	 * For the same reason, we want to tell GICv4 that we need
-	 * doorbells to be signalled, should an interrupt become pending.
-	 */
-	preempt_disable();
-	kvm_vgic_vmcr_sync(vcpu);
-	vgic_v4_put(vcpu, true);
-	preempt_enable();
+
 }
 
 void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu)
 {
-	preempt_disable();
-	vgic_v4_load(vcpu);
-	preempt_enable();
+
 }
 
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
@@ -591,18 +570,33 @@ static void update_vmid(struct kvm_vmid *vmid)
 	spin_unlock(&kvm_vmid_lock);
 }
 
-static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
+static int kvm_vcpu_initialized(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.target >= 0;
+}
+
+/*
+ * Handle both the initialisation that is being done when the vcpu is
+ * run for the first time, as well as the updates that must be
+ * performed each time we get a new thread dealing with this vcpu.
+ */
+int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
 {
 	struct kvm *kvm = vcpu->kvm;
-	int ret = 0;
+	int ret;
 
-	if (likely(vcpu->arch.has_run_once))
-		return 0;
+	if (!kvm_vcpu_initialized(vcpu))
+		return -ENOEXEC;
 
 	if (!kvm_arm_vcpu_is_finalized(vcpu))
 		return -EPERM;
 
-	vcpu->arch.has_run_once = true;
+	ret = kvm_arch_vcpu_run_map_fp(vcpu);
+	if (ret)
+		return ret;
+
+	if (likely(vcpu_has_run_once(vcpu)))
+		return 0;
 
 	kvm_arm_vcpu_init_debug(vcpu);
 
@@ -614,12 +608,6 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
 		ret = kvm_vgic_map_resources(kvm);
 		if (ret)
 			return ret;
-	} else {
-		/*
-		 * Tell the rest of the code that there are userspace irqchip
-		 * VMs in the wild.
-		 */
-		static_branch_inc(&userspace_irqchip_in_use);
 	}
 
 	ret = kvm_timer_enable(vcpu);
@@ -627,6 +615,16 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
 		return ret;
 
 	ret = kvm_arm_pmu_v3_enable(vcpu);
+	if (ret)
+		return ret;
+
+	if (!irqchip_in_kernel(kvm)) {
+		/*
+		 * Tell the rest of the code that there are userspace irqchip
+		 * VMs in the wild.
+		 */
+		static_branch_inc(&userspace_irqchip_in_use);
+	}
 
 	/*
 	 * Initialize traps for protected VMs.
@@ -646,7 +644,7 @@ bool kvm_arch_intc_initialized(struct kvm *kvm)
 
 void kvm_arm_halt_guest(struct kvm *kvm)
 {
-	int i;
+	unsigned long i;
 	struct kvm_vcpu *vcpu;
 
 	kvm_for_each_vcpu(i, vcpu, kvm)
@@ -656,12 +654,12 @@ void kvm_arm_halt_guest(struct kvm *kvm)
 
 void kvm_arm_resume_guest(struct kvm *kvm)
 {
-	int i;
+	unsigned long i;
 	struct kvm_vcpu *vcpu;
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
 		vcpu->arch.pause = false;
-		rcuwait_wake_up(kvm_arch_vcpu_get_wait(vcpu));
+		__kvm_vcpu_wake_up(vcpu);
 	}
 }
 
@@ -686,9 +684,37 @@ static void vcpu_req_sleep(struct kvm_vcpu *vcpu)
 	smp_rmb();
 }
 
-static int kvm_vcpu_initialized(struct kvm_vcpu *vcpu)
+/**
+ * kvm_vcpu_wfi - emulate Wait-For-Interrupt behavior
+ * @vcpu:	The VCPU pointer
+ *
+ * Suspend execution of a vCPU until a valid wake event is detected, i.e. until
+ * the vCPU is runnable.  The vCPU may or may not be scheduled out, depending
+ * on when a wake event arrives, e.g. there may already be a pending wake event.
+ */
+void kvm_vcpu_wfi(struct kvm_vcpu *vcpu)
 {
-	return vcpu->arch.target >= 0;
+	/*
+	 * Sync back the state of the GIC CPU interface so that we have
+	 * the latest PMR and group enables. This ensures that
+	 * kvm_arch_vcpu_runnable has up-to-date data to decide whether
+	 * we have pending interrupts, e.g. when determining if the
+	 * vCPU should block.
+	 *
+	 * For the same reason, we want to tell GICv4 that we need
+	 * doorbells to be signalled, should an interrupt become pending.
+	 */
+	preempt_disable();
+	kvm_vgic_vmcr_sync(vcpu);
+	vgic_v4_put(vcpu, true);
+	preempt_enable();
+
+	kvm_vcpu_halt(vcpu);
+	kvm_clear_request(KVM_REQ_UNHALT, vcpu);
+
+	preempt_disable();
+	vgic_v4_load(vcpu);
+	preempt_enable();
 }
 
 static void check_vcpu_requests(struct kvm_vcpu *vcpu)
@@ -786,13 +812,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 	struct kvm_run *run = vcpu->run;
 	int ret;
 
-	if (unlikely(!kvm_vcpu_initialized(vcpu)))
-		return -ENOEXEC;
-
-	ret = kvm_vcpu_first_run_init(vcpu);
-	if (ret)
-		return ret;
-
 	if (run->exit_reason == KVM_EXIT_MMIO) {
 		ret = kvm_handle_mmio_return(vcpu);
 		if (ret)
@@ -856,6 +875,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		}
 
 		kvm_arm_setup_debug(vcpu);
+		kvm_arch_vcpu_ctxflush_fp(vcpu);
 
 		/**************************************************************
 		 * Enter the guest
@@ -1130,7 +1150,7 @@ static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu,
 	 * need to invalidate the I-cache though, as FWB does *not*
 	 * imply CTR_EL0.DIC.
 	 */
-	if (vcpu->arch.has_run_once) {
+	if (vcpu_has_run_once(vcpu)) {
 		if (!cpus_have_final_cap(ARM64_HAS_STAGE2_FWB))
 			stage2_unmap_vm(vcpu->kvm);
 		else
@@ -2043,7 +2063,7 @@ static int finalize_hyp_mode(void)
 struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr)
 {
 	struct kvm_vcpu *vcpu;
-	int i;
+	unsigned long i;
 
 	mpidr &= MPIDR_HWID_BITMASK;
 	kvm_for_each_vcpu(i, vcpu, kvm) {