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

Pull kvm fixes from Paolo Bonzini:
 "x86:

   - Miscellaneous bugfixes

   - A small cleanup for the new workqueue code

   - Documentation syntax fix

  RISC-V:

   - Remove hgatp zeroing in kvm_arch_vcpu_put()

   - Fix alignment of the guest_hang() in KVM selftest

   - Fix PTE A and D bits in KVM selftest

   - Missing #include in vcpu_fp.c

  ARM:

   - Some PSCI fixes after introducing PSCIv1.1 and SYSTEM_RESET2

   - Fix the MMU write-lock not being taken on THP split

   - Fix mixed-width VM handling

   - Fix potential UAF when debugfs registration fails

   - Various selftest updates for all of the above"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (24 commits)
  KVM: x86: hyper-v: Avoid writing to TSC page without an active vCPU
  KVM: SVM: Do not activate AVIC for SEV-enabled guest
  Documentation: KVM: Add SPDX-License-Identifier tag
  selftests: kvm: add tsc_scaling_sync to .gitignore
  RISC-V: KVM: include missing hwcap.h into vcpu_fp
  KVM: selftests: riscv: Fix alignment of the guest_hang() function
  KVM: selftests: riscv: Set PTE A and D bits in VS-stage page table
  RISC-V: KVM: Don't clear hgatp CSR in kvm_arch_vcpu_put()
  selftests: KVM: Free the GIC FD when cleaning up in arch_timer
  selftests: KVM: Don't leak GIC FD across dirty log test iterations
  KVM: Don't create VM debugfs files outside of the VM directory
  KVM: selftests: get-reg-list: Add KVM_REG_ARM_FW_REG(3)
  KVM: avoid NULL pointer dereference in kvm_dirty_ring_push
  KVM: arm64: selftests: Introduce vcpu_width_config
  KVM: arm64: mixed-width check should be skipped for uninitialized vCPUs
  KVM: arm64: vgic: Remove unnecessary type castings
  KVM: arm64: Don't split hugepages outside of MMU write lock
  KVM: arm64: Drop unneeded minor version check from PSCI v1.x handler
  KVM: arm64: Actually prevent SMC64 SYSTEM_RESET2 from AArch32
  KVM: arm64: Generally disallow SMC64 for AArch32 guests
  ...

Documentation/virt/kvm/api.rst

@@ -6190,6 +6190,7 @@ Valid values for 'type' are:
 			unsigned long args[6];
 			unsigned long ret[2];
 		} riscv_sbi;
+
 If exit reason is KVM_EXIT_RISCV_SBI then it indicates that the VCPU has
 done a SBI call which is not handled by KVM RISC-V kernel module. The details
 of the SBI call are available in 'riscv_sbi' member of kvm_run structure. The

Documentation/virt/kvm/vcpu-requests.rst

+.. SPDX-License-Identifier: GPL-2.0
+
 =================
 KVM VCPU Requests
 =================

Documentation/virt/kvm/x86/amd-memory-encryption.rst

+.. SPDX-License-Identifier: GPL-2.0
+
 ======================================
 Secure Encrypted Virtualization (SEV)
 ======================================

Documentation/virt/kvm/x86/errata.rst

+.. SPDX-License-Identifier: GPL-2.0
 
 =======================================
 Known limitations of CPU virtualization
@@ -36,4 +37,3 @@ Nested virtualization features
 ------------------------------
 
 TBD
-

Documentation/virt/kvm/x86/running-nested-guests.rst

+.. SPDX-License-Identifier: GPL-2.0
+
 ==============================
 Running nested guests with KVM
 ==============================

arch/arm64/include/asm/kvm_emulate.h

@@ -43,10 +43,22 @@ void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr);
 
 void kvm_vcpu_wfi(struct kvm_vcpu *vcpu);
 
+#if defined(__KVM_VHE_HYPERVISOR__) || defined(__KVM_NVHE_HYPERVISOR__)
 static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu)
 {
 	return !(vcpu->arch.hcr_el2 & HCR_RW);
 }
+#else
+static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+
+	WARN_ON_ONCE(!test_bit(KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED,
+			       &kvm->arch.flags));
+
+	return test_bit(KVM_ARCH_FLAG_EL1_32BIT, &kvm->arch.flags);
+}
+#endif
 
 static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
 {
@@ -72,15 +84,14 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
 		vcpu->arch.hcr_el2 |= HCR_TVM;
 	}
 
-	if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features))
+	if (vcpu_el1_is_32bit(vcpu))
 		vcpu->arch.hcr_el2 &= ~HCR_RW;
-
-	/*
-	 * TID3: trap feature register accesses that we virtualise.
-	 * For now this is conditional, since no AArch32 feature regs
-	 * are currently virtualised.
-	 */
-	if (!vcpu_el1_is_32bit(vcpu))
+	else
+		/*
+		 * TID3: trap feature register accesses that we virtualise.
+		 * For now this is conditional, since no AArch32 feature regs
+		 * are currently virtualised.
+		 */
 		vcpu->arch.hcr_el2 |= HCR_TID3;
 
 	if (cpus_have_const_cap(ARM64_MISMATCHED_CACHE_TYPE) ||

arch/arm64/include/asm/kvm_host.h

@@ -127,6 +127,16 @@ struct kvm_arch {
 #define KVM_ARCH_FLAG_MTE_ENABLED			1
 	/* At least one vCPU has ran in the VM */
 #define KVM_ARCH_FLAG_HAS_RAN_ONCE			2
+	/*
+	 * The following two bits are used to indicate the guest's EL1
+	 * register width configuration. A value of KVM_ARCH_FLAG_EL1_32BIT
+	 * bit is valid only when KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED is set.
+	 * Otherwise, the guest's EL1 register width has not yet been
+	 * determined yet.
+	 */
+#define KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED		3
+#define KVM_ARCH_FLAG_EL1_32BIT				4
+
 	unsigned long flags;
 
 	/*

arch/arm64/kvm/mmu.c

@@ -1079,7 +1079,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	gfn_t gfn;
 	kvm_pfn_t pfn;
 	bool logging_active = memslot_is_logging(memslot);
-	bool logging_perm_fault = false;
+	bool use_read_lock = false;
 	unsigned long fault_level = kvm_vcpu_trap_get_fault_level(vcpu);
 	unsigned long vma_pagesize, fault_granule;
 	enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R;
@@ -1114,7 +1114,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	if (logging_active) {
 		force_pte = true;
 		vma_shift = PAGE_SHIFT;
-		logging_perm_fault = (fault_status == FSC_PERM && write_fault);
+		use_read_lock = (fault_status == FSC_PERM && write_fault &&
+				 fault_granule == PAGE_SIZE);
 	} else {
 		vma_shift = get_vma_page_shift(vma, hva);
 	}
@@ -1218,7 +1219,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * logging dirty logging, only acquire read lock for permission
 	 * relaxation.
 	 */
-	if (logging_perm_fault)
+	if (use_read_lock)
 		read_lock(&kvm->mmu_lock);
 	else
 		write_lock(&kvm->mmu_lock);
@@ -1268,6 +1269,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	if (fault_status == FSC_PERM && vma_pagesize == fault_granule) {
 		ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot);
 	} else {
+		WARN_ONCE(use_read_lock, "Attempted stage-2 map outside of write lock\n");
+
 		ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize,
 					     __pfn_to_phys(pfn), prot,
 					     memcache);
@@ -1280,7 +1283,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	}
 
 out_unlock:
-	if (logging_perm_fault)
+	if (use_read_lock)
 		read_unlock(&kvm->mmu_lock);
 	else
 		write_unlock(&kvm->mmu_lock);

arch/arm64/kvm/psci.c

@@ -215,15 +215,11 @@ static void kvm_psci_narrow_to_32bit(struct kvm_vcpu *vcpu)
 
 static unsigned long kvm_psci_check_allowed_function(struct kvm_vcpu *vcpu, u32 fn)
 {
-	switch(fn) {
-	case PSCI_0_2_FN64_CPU_SUSPEND:
-	case PSCI_0_2_FN64_CPU_ON:
-	case PSCI_0_2_FN64_AFFINITY_INFO:
-		/* Disallow these functions for 32bit guests */
-		if (vcpu_mode_is_32bit(vcpu))
-			return PSCI_RET_NOT_SUPPORTED;
-		break;
-	}
+	/*
+	 * Prevent 32 bit guests from calling 64 bit PSCI functions.
+	 */
+	if ((fn & PSCI_0_2_64BIT) && vcpu_mode_is_32bit(vcpu))
+		return PSCI_RET_NOT_SUPPORTED;
 
 	return 0;
 }
@@ -235,10 +231,6 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 	unsigned long val;
 	int ret = 1;
 
-	val = kvm_psci_check_allowed_function(vcpu, psci_fn);
-	if (val)
-		goto out;
-
 	switch (psci_fn) {
 	case PSCI_0_2_FN_PSCI_VERSION:
 		/*
@@ -306,7 +298,6 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 		break;
 	}
 
-out:
 	smccc_set_retval(vcpu, val, 0, 0, 0);
 	return ret;
 }
@@ -318,9 +309,6 @@ static int kvm_psci_1_x_call(struct kvm_vcpu *vcpu, u32 minor)
 	unsigned long val;
 	int ret = 1;
 
-	if (minor > 1)
-		return -EINVAL;
-
 	switch(psci_fn) {
 	case PSCI_0_2_FN_PSCI_VERSION:
 		val = minor == 0 ? KVM_ARM_PSCI_1_0 : KVM_ARM_PSCI_1_1;
@@ -426,6 +414,15 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
  */
 int kvm_psci_call(struct kvm_vcpu *vcpu)
 {
+	u32 psci_fn = smccc_get_function(vcpu);
+	unsigned long val;
+
+	val = kvm_psci_check_allowed_function(vcpu, psci_fn);
+	if (val) {
+		smccc_set_retval(vcpu, val, 0, 0, 0);
+		return 1;
+	}
+
 	switch (kvm_psci_version(vcpu)) {
 	case KVM_ARM_PSCI_1_1:
 		return kvm_psci_1_x_call(vcpu, 1);

arch/arm64/kvm/reset.c

@@ -181,27 +181,51 @@ static int kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-static bool vcpu_allowed_register_width(struct kvm_vcpu *vcpu)
+/**
+ * kvm_set_vm_width() - set the register width for the guest
+ * @vcpu: Pointer to the vcpu being configured
+ *
+ * Set both KVM_ARCH_FLAG_EL1_32BIT and KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED
+ * in the VM flags based on the vcpu's requested register width, the HW
+ * capabilities and other options (such as MTE).
+ * When REG_WIDTH_CONFIGURED is already set, the vcpu settings must be
+ * consistent with the value of the FLAG_EL1_32BIT bit in the flags.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+static int kvm_set_vm_width(struct kvm_vcpu *vcpu)
 {
-	struct kvm_vcpu *tmp;
+	struct kvm *kvm = vcpu->kvm;
 	bool is32bit;
-	unsigned long i;
 
 	is32bit = vcpu_has_feature(vcpu, KVM_ARM_VCPU_EL1_32BIT);
+
+	lockdep_assert_held(&kvm->lock);
+
+	if (test_bit(KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED, &kvm->arch.flags)) {
+		/*
+		 * The guest's register width is already configured.
+		 * Make sure that the vcpu is consistent with it.
+		 */
+		if (is32bit == test_bit(KVM_ARCH_FLAG_EL1_32BIT, &kvm->arch.flags))
+			return 0;
+
+		return -EINVAL;
+	}
+
 	if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1) && is32bit)
-		return false;
+		return -EINVAL;
 
 	/* MTE is incompatible with AArch32 */
-	if (kvm_has_mte(vcpu->kvm) && is32bit)
-		return false;
+	if (kvm_has_mte(kvm) && is32bit)
+		return -EINVAL;
 
-	/* Check that the vcpus are either all 32bit or all 64bit */
-	kvm_for_each_vcpu(i, tmp, vcpu->kvm) {
-		if (vcpu_has_feature(tmp, KVM_ARM_VCPU_EL1_32BIT) != is32bit)
-			return false;
-	}
+	if (is32bit)
+		set_bit(KVM_ARCH_FLAG_EL1_32BIT, &kvm->arch.flags);
 
-	return true;
+	set_bit(KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED, &kvm->arch.flags);
+
+	return 0;
 }
 
 /**
@@ -230,10 +254,16 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 	u32 pstate;
 
 	mutex_lock(&vcpu->kvm->lock);
-	reset_state = vcpu->arch.reset_state;
-	WRITE_ONCE(vcpu->arch.reset_state.reset, false);
+	ret = kvm_set_vm_width(vcpu);
+	if (!ret) {
+		reset_state = vcpu->arch.reset_state;
+		WRITE_ONCE(vcpu->arch.reset_state.reset, false);
+	}
 	mutex_unlock(&vcpu->kvm->lock);
 
+	if (ret)
+		return ret;
+
 	/* Reset PMU outside of the non-preemptible section */
 	kvm_pmu_vcpu_reset(vcpu);
 
@@ -260,14 +290,9 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 		}
 	}
 
-	if (!vcpu_allowed_register_width(vcpu)) {
-		ret = -EINVAL;
-		goto out;
-	}
-
 	switch (vcpu->arch.target) {
 	default:
-		if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) {
+		if (vcpu_el1_is_32bit(vcpu)) {
 			pstate = VCPU_RESET_PSTATE_SVC;
 		} else {
 			pstate = VCPU_RESET_PSTATE_EL1;

arch/arm64/kvm/vgic/vgic-debug.c

@@ -82,7 +82,7 @@ static bool end_of_vgic(struct vgic_state_iter *iter)
 
 static void *vgic_debug_start(struct seq_file *s, loff_t *pos)
 {
-	struct kvm *kvm = (struct kvm *)s->private;
+	struct kvm *kvm = s->private;
 	struct vgic_state_iter *iter;
 
 	mutex_lock(&kvm->lock);
@@ -110,7 +110,7 @@ static void *vgic_debug_start(struct seq_file *s, loff_t *pos)
 
 static void *vgic_debug_next(struct seq_file *s, void *v, loff_t *pos)
 {
-	struct kvm *kvm = (struct kvm *)s->private;
+	struct kvm *kvm = s->private;
 	struct vgic_state_iter *iter = kvm->arch.vgic.iter;
 
 	++*pos;
@@ -122,7 +122,7 @@ static void *vgic_debug_next(struct seq_file *s, void *v, loff_t *pos)
 
 static void vgic_debug_stop(struct seq_file *s, void *v)
 {
-	struct kvm *kvm = (struct kvm *)s->private;
+	struct kvm *kvm = s->private;
 	struct vgic_state_iter *iter;
 
 	/*
@@ -229,8 +229,8 @@ static void print_irq_state(struct seq_file *s, struct vgic_irq *irq,
 
 static int vgic_debug_show(struct seq_file *s, void *v)
 {
-	struct kvm *kvm = (struct kvm *)s->private;
-	struct vgic_state_iter *iter = (struct vgic_state_iter *)v;
+	struct kvm *kvm = s->private;
+	struct vgic_state_iter *iter = v;
 	struct vgic_irq *irq;
 	struct kvm_vcpu *vcpu = NULL;
 	unsigned long flags;

arch/arm64/kvm/vgic/vgic-its.c

@@ -2143,7 +2143,7 @@ static int vgic_its_save_ite(struct vgic_its *its, struct its_device *dev,
 static int vgic_its_restore_ite(struct vgic_its *its, u32 event_id,
 				void *ptr, void *opaque)
 {
-	struct its_device *dev = (struct its_device *)opaque;
+	struct its_device *dev = opaque;
 	struct its_collection *collection;
 	struct kvm *kvm = its->dev->kvm;
 	struct kvm_vcpu *vcpu = NULL;

arch/riscv/kvm/vcpu.c

@@ -653,8 +653,6 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 				     vcpu->arch.isa);
 	kvm_riscv_vcpu_host_fp_restore(&vcpu->arch.host_context);
 
-	csr_write(CSR_HGATP, 0);
-
 	csr->vsstatus = csr_read(CSR_VSSTATUS);
 	csr->vsie = csr_read(CSR_VSIE);
 	csr->vstvec = csr_read(CSR_VSTVEC);

arch/riscv/kvm/vcpu_fp.c

@@ -11,6 +11,7 @@
 #include <linux/err.h>
 #include <linux/kvm_host.h>
 #include <linux/uaccess.h>
+#include <asm/hwcap.h>
 
 #ifdef CONFIG_FPU
 void kvm_riscv_vcpu_fp_reset(struct kvm_vcpu *vcpu)

arch/x86/include/asm/kvm_host.h

@@ -974,12 +974,10 @@ enum hv_tsc_page_status {
 	HV_TSC_PAGE_UNSET = 0,
 	/* TSC page MSR was written by the guest, update pending */
 	HV_TSC_PAGE_GUEST_CHANGED,
-	/* TSC page MSR was written by KVM userspace, update pending */
+	/* TSC page update was triggered from the host side */
 	HV_TSC_PAGE_HOST_CHANGED,
 	/* TSC page was properly set up and is currently active  */
 	HV_TSC_PAGE_SET,
-	/* TSC page is currently being updated and therefore is inactive */
-	HV_TSC_PAGE_UPDATING,
 	/* TSC page was set up with an inaccessible GPA */
 	HV_TSC_PAGE_BROKEN,
 };
@@ -1052,6 +1050,7 @@ enum kvm_apicv_inhibit {
 	APICV_INHIBIT_REASON_X2APIC,
 	APICV_INHIBIT_REASON_BLOCKIRQ,
 	APICV_INHIBIT_REASON_ABSENT,
+	APICV_INHIBIT_REASON_SEV,
 };
 
 struct kvm_arch {
@@ -1585,8 +1584,9 @@ static inline int kvm_arch_flush_remote_tlb(struct kvm *kvm)
 #define kvm_arch_pmi_in_guest(vcpu) \
 	((vcpu) && (vcpu)->arch.handling_intr_from_guest)
 
-int kvm_mmu_module_init(void);
-void kvm_mmu_module_exit(void);
+void kvm_mmu_x86_module_init(void);
+int kvm_mmu_vendor_module_init(void);
+void kvm_mmu_vendor_module_exit(void);
 
 void kvm_mmu_destroy(struct kvm_vcpu *vcpu);
 int kvm_mmu_create(struct kvm_vcpu *vcpu);

arch/x86/kvm/hyperv.c

@@ -1135,11 +1135,13 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm,
 	BUILD_BUG_ON(sizeof(tsc_seq) != sizeof(hv->tsc_ref.tsc_sequence));
 	BUILD_BUG_ON(offsetof(struct ms_hyperv_tsc_page, tsc_sequence) != 0);
 
+	mutex_lock(&hv->hv_lock);
+
 	if (hv->hv_tsc_page_status == HV_TSC_PAGE_BROKEN ||
+	    hv->hv_tsc_page_status == HV_TSC_PAGE_SET ||
 	    hv->hv_tsc_page_status == HV_TSC_PAGE_UNSET)
-		return;
+		goto out_unlock;
 
-	mutex_lock(&hv->hv_lock);
 	if (!(hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE))
 		goto out_unlock;
 
@@ -1201,45 +1203,19 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm,
 	mutex_unlock(&hv->hv_lock);
 }
 
-void kvm_hv_invalidate_tsc_page(struct kvm *kvm)
+void kvm_hv_request_tsc_page_update(struct kvm *kvm)
 {
 	struct kvm_hv *hv = to_kvm_hv(kvm);
-	u64 gfn;
-	int idx;
-
-	if (hv->hv_tsc_page_status == HV_TSC_PAGE_BROKEN ||
-	    hv->hv_tsc_page_status == HV_TSC_PAGE_UNSET ||
-	    tsc_page_update_unsafe(hv))
-		return;
 
 	mutex_lock(&hv->hv_lock);
 
-	if (!(hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE))
-		goto out_unlock;
-
-	/* Preserve HV_TSC_PAGE_GUEST_CHANGED/HV_TSC_PAGE_HOST_CHANGED states */
-	if (hv->hv_tsc_page_status == HV_TSC_PAGE_SET)
-		hv->hv_tsc_page_status = HV_TSC_PAGE_UPDATING;
+	if (hv->hv_tsc_page_status == HV_TSC_PAGE_SET &&
+	    !tsc_page_update_unsafe(hv))
+		hv->hv_tsc_page_status = HV_TSC_PAGE_HOST_CHANGED;
 
-	gfn = hv->hv_tsc_page >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT;
-
-	hv->tsc_ref.tsc_sequence = 0;
-
-	/*
-	 * Take the srcu lock as memslots will be accessed to check the gfn
-	 * cache generation against the memslots generation.
-	 */
-	idx = srcu_read_lock(&kvm->srcu);
-	if (kvm_write_guest(kvm, gfn_to_gpa(gfn),
-			    &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence)))
-		hv->hv_tsc_page_status = HV_TSC_PAGE_BROKEN;
-	srcu_read_unlock(&kvm->srcu, idx);
-
-out_unlock:
 	mutex_unlock(&hv->hv_lock);
 }
 
-
 static bool hv_check_msr_access(struct kvm_vcpu_hv *hv_vcpu, u32 msr)
 {
 	if (!hv_vcpu->enforce_cpuid)

arch/x86/kvm/hyperv.h

@@ -137,7 +137,7 @@ void kvm_hv_process_stimers(struct kvm_vcpu *vcpu);
 
 void kvm_hv_setup_tsc_page(struct kvm *kvm,
 			   struct pvclock_vcpu_time_info *hv_clock);
-void kvm_hv_invalidate_tsc_page(struct kvm *kvm);
+void kvm_hv_request_tsc_page_update(struct kvm *kvm);
 
 void kvm_hv_init_vm(struct kvm *kvm);
 void kvm_hv_destroy_vm(struct kvm *kvm);

arch/x86/kvm/mmu/mmu.c

@@ -6237,12 +6237,24 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp)
 	return 0;
 }
 
-int kvm_mmu_module_init(void)
+/*
+ * nx_huge_pages needs to be resolved to true/false when kvm.ko is loaded, as
+ * its default value of -1 is technically undefined behavior for a boolean.
+ */
+void kvm_mmu_x86_module_init(void)
 {
-	int ret = -ENOMEM;
-
 	if (nx_huge_pages == -1)
 		__set_nx_huge_pages(get_nx_auto_mode());
+}
+
+/*
+ * The bulk of the MMU initialization is deferred until the vendor module is
+ * loaded as many of the masks/values may be modified by VMX or SVM, i.e. need
+ * to be reset when a potentially different vendor module is loaded.
+ */
+int kvm_mmu_vendor_module_init(void)
+{
+	int ret = -ENOMEM;
 
 	/*
 	 * MMU roles use union aliasing which is, generally speaking, an
@@ -6290,7 +6302,7 @@ void kvm_mmu_destroy(struct kvm_vcpu *vcpu)
 	mmu_free_memory_caches(vcpu);
 }
 
-void kvm_mmu_module_exit(void)
+void kvm_mmu_vendor_module_exit(void)
 {
 	mmu_destroy_caches();
 	percpu_counter_destroy(&kvm_total_used_mmu_pages);

arch/x86/kvm/mmu/tdp_mmu.c

@@ -51,7 +51,7 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm)
 	if (!kvm->arch.tdp_mmu_enabled)
 		return;
 
-	flush_workqueue(kvm->arch.tdp_mmu_zap_wq);
+	/* Also waits for any queued work items.  */
 	destroy_workqueue(kvm->arch.tdp_mmu_zap_wq);
 
 	WARN_ON(!list_empty(&kvm->arch.tdp_mmu_pages));

arch/x86/kvm/svm/avic.c

@@ -837,7 +837,8 @@ bool avic_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason)
 			  BIT(APICV_INHIBIT_REASON_IRQWIN) |
 			  BIT(APICV_INHIBIT_REASON_PIT_REINJ) |
 			  BIT(APICV_INHIBIT_REASON_X2APIC) |
-			  BIT(APICV_INHIBIT_REASON_BLOCKIRQ);
+			  BIT(APICV_INHIBIT_REASON_BLOCKIRQ) |
+			  BIT(APICV_INHIBIT_REASON_SEV);
 
 	return supported & BIT(reason);
 }

arch/x86/kvm/svm/sev.c

@@ -260,6 +260,8 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	INIT_LIST_HEAD(&sev->regions_list);
 	INIT_LIST_HEAD(&sev->mirror_vms);
 
+	kvm_set_apicv_inhibit(kvm, APICV_INHIBIT_REASON_SEV);
+
 	return 0;
 
 e_free:
@@ -465,6 +467,7 @@ static void sev_clflush_pages(struct page *pages[], unsigned long npages)
 		page_virtual = kmap_atomic(pages[i]);
 		clflush_cache_range(page_virtual, PAGE_SIZE);
 		kunmap_atomic(page_virtual);
+		cond_resched();
 	}
 }
 

arch/x86/kvm/x86.c

@@ -2901,7 +2901,7 @@ static void kvm_end_pvclock_update(struct kvm *kvm)
 
 static void kvm_update_masterclock(struct kvm *kvm)
 {
-	kvm_hv_invalidate_tsc_page(kvm);
+	kvm_hv_request_tsc_page_update(kvm);
 	kvm_start_pvclock_update(kvm);
 	pvclock_update_vm_gtod_copy(kvm);
 	kvm_end_pvclock_update(kvm);
@@ -3113,8 +3113,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 				       offsetof(struct compat_vcpu_info, time));
 	if (vcpu->xen.vcpu_time_info_set)
 		kvm_setup_pvclock_page(v, &vcpu->xen.vcpu_time_info_cache, 0);
-	if (!v->vcpu_idx)
-		kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock);
+	kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock);
 	return 0;
 }
 
@@ -6241,7 +6240,7 @@ static int kvm_vm_ioctl_set_clock(struct kvm *kvm, void __user *argp)
 	if (data.flags & ~KVM_CLOCK_VALID_FLAGS)
 		return -EINVAL;
 
-	kvm_hv_invalidate_tsc_page(kvm);
+	kvm_hv_request_tsc_page_update(kvm);
 	kvm_start_pvclock_update(kvm);
 	pvclock_update_vm_gtod_copy(kvm);
 
@@ -8926,7 +8925,7 @@ int kvm_arch_init(void *opaque)
 	}
 	kvm_nr_uret_msrs = 0;
 
-	r = kvm_mmu_module_init();
+	r = kvm_mmu_vendor_module_init();
 	if (r)
 		goto out_free_percpu;
 
@@ -8974,7 +8973,7 @@ void kvm_arch_exit(void)
 	cancel_work_sync(&pvclock_gtod_work);
 #endif
 	kvm_x86_ops.hardware_enable = NULL;
-	kvm_mmu_module_exit();
+	kvm_mmu_vendor_module_exit();
 	free_percpu(user_return_msrs);
 	kmem_cache_destroy(x86_emulator_cache);
 #ifdef CONFIG_KVM_XEN
@@ -12986,3 +12985,19 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_enter);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_exit);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_enter);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_exit);
+
+static int __init kvm_x86_init(void)
+{
+	kvm_mmu_x86_module_init();
+	return 0;
+}
+module_init(kvm_x86_init);
+
+static void __exit kvm_x86_exit(void)
+{
+	/*
+	 * If module_init() is implemented, module_exit() must also be
+	 * implemented to allow module unload.
+	 */
+}
+module_exit(kvm_x86_exit);

tools/testing/selftests/kvm/.gitignore

@@ -3,6 +3,7 @@
 /aarch64/debug-exceptions
 /aarch64/get-reg-list
 /aarch64/psci_cpu_on_test
+/aarch64/vcpu_width_config
 /aarch64/vgic_init
 /aarch64/vgic_irq
 /s390x/memop
@@ -33,6 +34,7 @@
 /x86_64/state_test
 /x86_64/svm_vmcall_test
 /x86_64/svm_int_ctl_test
+/x86_64/tsc_scaling_sync
 /x86_64/sync_regs_test
 /x86_64/tsc_msrs_test
 /x86_64/userspace_io_test

tools/testing/selftests/kvm/Makefile

@@ -106,6 +106,7 @@ TEST_GEN_PROGS_aarch64 += aarch64/arch_timer
 TEST_GEN_PROGS_aarch64 += aarch64/debug-exceptions
 TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list
 TEST_GEN_PROGS_aarch64 += aarch64/psci_cpu_on_test
+TEST_GEN_PROGS_aarch64 += aarch64/vcpu_width_config
 TEST_GEN_PROGS_aarch64 += aarch64/vgic_init
 TEST_GEN_PROGS_aarch64 += aarch64/vgic_irq
 TEST_GEN_PROGS_aarch64 += demand_paging_test

tools/testing/selftests/kvm/aarch64/arch_timer.c

@@ -362,11 +362,12 @@ static void test_init_timer_irq(struct kvm_vm *vm)
 	pr_debug("ptimer_irq: %d; vtimer_irq: %d\n", ptimer_irq, vtimer_irq);
 }
 
+static int gic_fd;
+
 static struct kvm_vm *test_vm_create(void)
 {
 	struct kvm_vm *vm;
 	unsigned int i;
-	int ret;
 	int nr_vcpus = test_args.nr_vcpus;
 
 	vm = vm_create_default_with_vcpus(nr_vcpus, 0, 0, guest_code, NULL);
@@ -383,8 +384,8 @@ static struct kvm_vm *test_vm_create(void)
 
 	ucall_init(vm, NULL);
 	test_init_timer_irq(vm);
-	ret = vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA);
-	if (ret < 0) {
+	gic_fd = vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA);
+	if (gic_fd < 0) {
 		print_skip("Failed to create vgic-v3");
 		exit(KSFT_SKIP);
 	}
@@ -395,6 +396,12 @@ static struct kvm_vm *test_vm_create(void)
 	return vm;
 }
 
+static void test_vm_cleanup(struct kvm_vm *vm)
+{
+	close(gic_fd);
+	kvm_vm_free(vm);
+}
+
 static void test_print_help(char *name)
 {
 	pr_info("Usage: %s [-h] [-n nr_vcpus] [-i iterations] [-p timer_period_ms]\n",
@@ -478,7 +485,7 @@ int main(int argc, char *argv[])
 
 	vm = test_vm_create();
 	test_run(vm);
-	kvm_vm_free(vm);
+	test_vm_cleanup(vm);
 
 	return 0;
 }

tools/testing/selftests/kvm/aarch64/get-reg-list.c

@@ -503,8 +503,13 @@ static void run_test(struct vcpu_config *c)
 		++missing_regs;
 
 	if (new_regs || missing_regs) {
+		n = 0;
+		for_each_reg_filtered(i)
+			++n;
+
 		printf("%s: Number blessed registers: %5lld\n", config_name(c), blessed_n);
-		printf("%s: Number registers:         %5lld\n", config_name(c), reg_list->n);
+		printf("%s: Number registers:         %5lld (includes %lld filtered registers)\n",
+		       config_name(c), reg_list->n, reg_list->n - n);
 	}
 
 	if (new_regs) {
@@ -683,9 +688,10 @@ static __u64 base_regs[] = {
 	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[4]),
 	KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.fpsr),
 	KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.fpcr),
-	KVM_REG_ARM_FW_REG(0),
-	KVM_REG_ARM_FW_REG(1),
-	KVM_REG_ARM_FW_REG(2),
+	KVM_REG_ARM_FW_REG(0),		/* KVM_REG_ARM_PSCI_VERSION */
+	KVM_REG_ARM_FW_REG(1),		/* KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1 */
+	KVM_REG_ARM_FW_REG(2),		/* KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2 */
+	KVM_REG_ARM_FW_REG(3),		/* KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3 */
 	ARM64_SYS_REG(3, 3, 14, 3, 1),	/* CNTV_CTL_EL0 */
 	ARM64_SYS_REG(3, 3, 14, 3, 2),	/* CNTV_CVAL_EL0 */
 	ARM64_SYS_REG(3, 3, 14, 0, 2),

tools/testing/selftests/kvm/aarch64/vcpu_width_config.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * vcpu_width_config - Test KVM_ARM_VCPU_INIT() with KVM_ARM_VCPU_EL1_32BIT.
+ *
+ * Copyright (c) 2022 Google LLC.
+ *
+ * This is a test that ensures that non-mixed-width vCPUs (all 64bit vCPUs
+ * or all 32bit vcPUs) can be configured and mixed-width vCPUs cannot be
+ * configured.
+ */
+
+#include "kvm_util.h"
+#include "processor.h"
+#include "test_util.h"
+
+
+/*
+ * Add a vCPU, run KVM_ARM_VCPU_INIT with @init1, and then
+ * add another vCPU, and run KVM_ARM_VCPU_INIT with @init2.
+ */
+static int add_init_2vcpus(struct kvm_vcpu_init *init1,
+			   struct kvm_vcpu_init *init2)
+{
+	struct kvm_vm *vm;
+	int ret;
+
+	vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR);
+
+	vm_vcpu_add(vm, 0);
+	ret = _vcpu_ioctl(vm, 0, KVM_ARM_VCPU_INIT, init1);
+	if (ret)
+		goto free_exit;
+
+	vm_vcpu_add(vm, 1);
+	ret = _vcpu_ioctl(vm, 1, KVM_ARM_VCPU_INIT, init2);
+
+free_exit:
+	kvm_vm_free(vm);
+	return ret;
+}
+
+/*
+ * Add two vCPUs, then run KVM_ARM_VCPU_INIT for one vCPU with @init1,
+ * and run KVM_ARM_VCPU_INIT for another vCPU with @init2.
+ */
+static int add_2vcpus_init_2vcpus(struct kvm_vcpu_init *init1,
+				  struct kvm_vcpu_init *init2)
+{
+	struct kvm_vm *vm;
+	int ret;
+
+	vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR);
+
+	vm_vcpu_add(vm, 0);
+	vm_vcpu_add(vm, 1);
+
+	ret = _vcpu_ioctl(vm, 0, KVM_ARM_VCPU_INIT, init1);
+	if (ret)
+		goto free_exit;
+
+	ret = _vcpu_ioctl(vm, 1, KVM_ARM_VCPU_INIT, init2);
+
+free_exit:
+	kvm_vm_free(vm);
+	return ret;
+}
+
+/*
+ * Tests that two 64bit vCPUs can be configured, two 32bit vCPUs can be
+ * configured, and two mixed-width vCPUs cannot be configured.
+ * Each of those three cases, configure vCPUs in two different orders.
+ * The one is running KVM_CREATE_VCPU for 2 vCPUs, and then running
+ * KVM_ARM_VCPU_INIT for them.
+ * The other is running KVM_CREATE_VCPU and KVM_ARM_VCPU_INIT for a vCPU,
+ * and then run those commands for another vCPU.
+ */
+int main(void)
+{
+	struct kvm_vcpu_init init1, init2;
+	struct kvm_vm *vm;
+	int ret;
+
+	if (!kvm_check_cap(KVM_CAP_ARM_EL1_32BIT)) {
+		print_skip("KVM_CAP_ARM_EL1_32BIT is not supported");
+		exit(KSFT_SKIP);
+	}
+
+	/* Get the preferred target type and copy that to init2 for later use */
+	vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR);
+	vm_ioctl(vm, KVM_ARM_PREFERRED_TARGET, &init1);
+	kvm_vm_free(vm);
+	init2 = init1;
+
+	/* Test with 64bit vCPUs */
+	ret = add_init_2vcpus(&init1, &init1);
+	TEST_ASSERT(ret == 0,
+		    "Configuring 64bit EL1 vCPUs failed unexpectedly");
+	ret = add_2vcpus_init_2vcpus(&init1, &init1);
+	TEST_ASSERT(ret == 0,
+		    "Configuring 64bit EL1 vCPUs failed unexpectedly");
+
+	/* Test with 32bit vCPUs */
+	init1.features[0] = (1 << KVM_ARM_VCPU_EL1_32BIT);
+	ret = add_init_2vcpus(&init1, &init1);
+	TEST_ASSERT(ret == 0,
+		    "Configuring 32bit EL1 vCPUs failed unexpectedly");
+	ret = add_2vcpus_init_2vcpus(&init1, &init1);
+	TEST_ASSERT(ret == 0,
+		    "Configuring 32bit EL1 vCPUs failed unexpectedly");
+
+	/* Test with mixed-width vCPUs  */
+	init1.features[0] = 0;
+	init2.features[0] = (1 << KVM_ARM_VCPU_EL1_32BIT);
+	ret = add_init_2vcpus(&init1, &init2);
+	TEST_ASSERT(ret != 0,
+		    "Configuring mixed-width vCPUs worked unexpectedly");
+	ret = add_2vcpus_init_2vcpus(&init1, &init2);
+	TEST_ASSERT(ret != 0,
+		    "Configuring mixed-width vCPUs worked unexpectedly");
+
+	return 0;
+}

tools/testing/selftests/kvm/dirty_log_perf_test.c

@@ -18,11 +18,40 @@
 #include "test_util.h"
 #include "perf_test_util.h"
 #include "guest_modes.h"
+
 #ifdef __aarch64__
 #include "aarch64/vgic.h"
 
 #define GICD_BASE_GPA			0x8000000ULL
 #define GICR_BASE_GPA			0x80A0000ULL
+
+static int gic_fd;
+
+static void arch_setup_vm(struct kvm_vm *vm, unsigned int nr_vcpus)
+{
+	/*
+	 * The test can still run even if hardware does not support GICv3, as it
+	 * is only an optimization to reduce guest exits.
+	 */
+	gic_fd = vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA);
+}
+
+static void arch_cleanup_vm(struct kvm_vm *vm)
+{
+	if (gic_fd > 0)
+		close(gic_fd);
+}
+
+#else /* __aarch64__ */
+
+static void arch_setup_vm(struct kvm_vm *vm, unsigned int nr_vcpus)
+{
+}
+
+static void arch_cleanup_vm(struct kvm_vm *vm)
+{
+}
+
 #endif
 
 /* How many host loops to run by default (one KVM_GET_DIRTY_LOG for each loop)*/
@@ -206,9 +235,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 		vm_enable_cap(vm, &cap);
 	}
 
-#ifdef __aarch64__
-	vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA);
-#endif
+	arch_setup_vm(vm, nr_vcpus);
 
 	/* Start the iterations */
 	iteration = 0;
@@ -302,6 +329,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	}
 
 	free_bitmaps(bitmaps, p->slots);
+	arch_cleanup_vm(vm);
 	perf_test_destroy_vm(vm);
 }
 

tools/testing/selftests/kvm/include/riscv/processor.h

@@ -101,7 +101,9 @@ static inline void set_reg(struct kvm_vm *vm, uint32_t vcpuid, uint64_t id,
 #define PGTBL_PTE_WRITE_SHIFT			2
 #define PGTBL_PTE_READ_MASK			0x0000000000000002ULL
 #define PGTBL_PTE_READ_SHIFT			1
-#define PGTBL_PTE_PERM_MASK			(PGTBL_PTE_EXECUTE_MASK | \
+#define PGTBL_PTE_PERM_MASK			(PGTBL_PTE_ACCESSED_MASK | \
+						 PGTBL_PTE_DIRTY_MASK | \
+						 PGTBL_PTE_EXECUTE_MASK | \
 						 PGTBL_PTE_WRITE_MASK | \
 						 PGTBL_PTE_READ_MASK)
 #define PGTBL_PTE_VALID_MASK			0x0000000000000001ULL

tools/testing/selftests/kvm/lib/riscv/processor.c

@@ -268,7 +268,7 @@ void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent)
 		core.regs.t3, core.regs.t4, core.regs.t5, core.regs.t6);
 }
 
-static void guest_hang(void)
+static void __aligned(16) guest_hang(void)
 {
 	while (1)
 		;

virt/kvm/kvm_main.c

@@ -434,8 +434,8 @@ static void kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
 
 static void kvm_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
-	kvm_dirty_ring_free(&vcpu->dirty_ring);
 	kvm_arch_vcpu_destroy(vcpu);
+	kvm_dirty_ring_free(&vcpu->dirty_ring);
 
 	/*
 	 * No need for rcu_read_lock as VCPU_RUN is the only place that changes
@@ -932,7 +932,7 @@ static void kvm_destroy_vm_debugfs(struct kvm *kvm)
 	int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc +
 				      kvm_vcpu_stats_header.num_desc;
 
-	if (!kvm->debugfs_dentry)
+	if (IS_ERR(kvm->debugfs_dentry))
 		return;
 
 	debugfs_remove_recursive(kvm->debugfs_dentry);
@@ -955,6 +955,12 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd)
 	int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc +
 				      kvm_vcpu_stats_header.num_desc;
 
+	/*
+	 * Force subsequent debugfs file creations to fail if the VM directory
+	 * is not created.
+	 */
+	kvm->debugfs_dentry = ERR_PTR(-ENOENT);
+
 	if (!debugfs_initialized())
 		return 0;
 
@@ -5479,7 +5485,7 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm)
 	}
 	add_uevent_var(env, "PID=%d", kvm->userspace_pid);
 
-	if (kvm->debugfs_dentry) {
+	if (!IS_ERR(kvm->debugfs_dentry)) {
 		char *tmp, *p = kmalloc(PATH_MAX, GFP_KERNEL_ACCOUNT);
 
 		if (p) {