Merge tag 'kvmarm-fixes-6.12-2' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 fixes for 6.12, take #2

- Fix the guest view of the ID registers, making the relevant fields
  writable from userspace (affecting ID_AA64DFR0_EL1 and ID_AA64PFR1_EL1)

- Correcly expose S1PIE to guests, fixing a regression introduced
  in 6.12-rc1 with the S1POE support

- Fix the recycling of stage-2 shadow MMUs by tracking the context
  (are we allowed to block or not) as well as the recycling state

- Address a couple of issues with the vgic when userspace misconfigures
  the emulation, resulting in various splats. Headaches courtesy
  of our Syzkaller friends

Author: bonzini

arch/arm64/include/asm/kvm_host.h

@@ -51,6 +51,7 @@
 #define KVM_REQ_RELOAD_PMU	KVM_ARCH_REQ(5)
 #define KVM_REQ_SUSPEND		KVM_ARCH_REQ(6)
 #define KVM_REQ_RESYNC_PMU_EL0	KVM_ARCH_REQ(7)
+#define KVM_REQ_NESTED_S2_UNMAP	KVM_ARCH_REQ(8)
 
 #define KVM_DIRTY_LOG_MANUAL_CAPS   (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
 				     KVM_DIRTY_LOG_INITIALLY_SET)
@@ -211,6 +212,12 @@ struct kvm_s2_mmu {
 	 */
 	bool	nested_stage2_enabled;
 
+	/*
+	 * true when this MMU needs to be unmapped before being used for a new
+	 * purpose.
+	 */
+	bool	pending_unmap;
+
 	/*
 	 *  0: Nobody is currently using this, check vttbr for validity
 	 * >0: Somebody is actively using this.

arch/arm64/include/asm/kvm_mmu.h

@@ -166,7 +166,8 @@ int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
 int create_hyp_stack(phys_addr_t phys_addr, unsigned long *haddr);
 void __init free_hyp_pgds(void);
 
-void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size);
+void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start,
+			    u64 size, bool may_block);
 void kvm_stage2_flush_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end);
 void kvm_stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end);
 

arch/arm64/include/asm/kvm_nested.h

@@ -78,6 +78,8 @@ extern void kvm_s2_mmu_iterate_by_vmid(struct kvm *kvm, u16 vmid,
 extern void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu);
 extern void kvm_vcpu_put_hw_mmu(struct kvm_vcpu *vcpu);
 
+extern void check_nested_vcpu_requests(struct kvm_vcpu *vcpu);
+
 struct kvm_s2_trans {
 	phys_addr_t output;
 	unsigned long block_size;
@@ -124,7 +126,7 @@ extern int kvm_s2_handle_perm_fault(struct kvm_vcpu *vcpu,
 				    struct kvm_s2_trans *trans);
 extern int kvm_inject_s2_fault(struct kvm_vcpu *vcpu, u64 esr_el2);
 extern void kvm_nested_s2_wp(struct kvm *kvm);
-extern void kvm_nested_s2_unmap(struct kvm *kvm);
+extern void kvm_nested_s2_unmap(struct kvm *kvm, bool may_block);
 extern void kvm_nested_s2_flush(struct kvm *kvm);
 
 unsigned long compute_tlb_inval_range(struct kvm_s2_mmu *mmu, u64 val);

arch/arm64/kvm/arm.c

@@ -997,6 +997,9 @@ static int kvm_vcpu_suspend(struct kvm_vcpu *vcpu)
 static int check_vcpu_requests(struct kvm_vcpu *vcpu)
 {
 	if (kvm_request_pending(vcpu)) {
+		if (kvm_check_request(KVM_REQ_VM_DEAD, vcpu))
+			return -EIO;
+
 		if (kvm_check_request(KVM_REQ_SLEEP, vcpu))
 			kvm_vcpu_sleep(vcpu);
 
@@ -1031,6 +1034,8 @@ static int check_vcpu_requests(struct kvm_vcpu *vcpu)
 
 		if (kvm_dirty_ring_check_request(vcpu))
 			return 0;
+
+		check_nested_vcpu_requests(vcpu);
 	}
 
 	return 1;

arch/arm64/kvm/hypercalls.c

@@ -317,7 +317,7 @@ int kvm_smccc_call_handler(struct kvm_vcpu *vcpu)
 				 * to the guest, and hide SSBS so that the
 				 * guest stays protected.
 				 */
-				if (cpus_have_final_cap(ARM64_SSBS))
+				if (kvm_has_feat(vcpu->kvm, ID_AA64PFR1_EL1, SSBS, IMP))
 					break;
 				fallthrough;
 			case SPECTRE_UNAFFECTED:
@@ -428,7 +428,7 @@ int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
  * Convert the workaround level into an easy-to-compare number, where higher
  * values mean better protection.
  */
-static int get_kernel_wa_level(u64 regid)
+static int get_kernel_wa_level(struct kvm_vcpu *vcpu, u64 regid)
 {
 	switch (regid) {
 	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
@@ -449,7 +449,7 @@ static int get_kernel_wa_level(u64 regid)
 			 * don't have any FW mitigation if SSBS is there at
 			 * all times.
 			 */
-			if (cpus_have_final_cap(ARM64_SSBS))
+			if (kvm_has_feat(vcpu->kvm, ID_AA64PFR1_EL1, SSBS, IMP))
 				return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL;
 			fallthrough;
 		case SPECTRE_UNAFFECTED:
@@ -486,7 +486,7 @@ int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
 	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2:
 	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3:
-		val = get_kernel_wa_level(reg->id) & KVM_REG_FEATURE_LEVEL_MASK;
+		val = get_kernel_wa_level(vcpu, reg->id) & KVM_REG_FEATURE_LEVEL_MASK;
 		break;
 	case KVM_REG_ARM_STD_BMAP:
 		val = READ_ONCE(smccc_feat->std_bmap);
@@ -588,7 +588,7 @@ int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 		if (val & ~KVM_REG_FEATURE_LEVEL_MASK)
 			return -EINVAL;
 
-		if (get_kernel_wa_level(reg->id) < val)
+		if (get_kernel_wa_level(vcpu, reg->id) < val)
 			return -EINVAL;
 
 		return 0;
@@ -624,7 +624,7 @@ int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 		 * We can deal with NOT_AVAIL on NOT_REQUIRED, but not the
 		 * other way around.
 		 */
-		if (get_kernel_wa_level(reg->id) < wa_level)
+		if (get_kernel_wa_level(vcpu, reg->id) < wa_level)
 			return -EINVAL;
 
 		return 0;

arch/arm64/kvm/mmu.c

@@ -328,9 +328,10 @@ static void __unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64
 				   may_block));
 }
 
-void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size)
+void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start,
+			    u64 size, bool may_block)
 {
-	__unmap_stage2_range(mmu, start, size, true);
+	__unmap_stage2_range(mmu, start, size, may_block);
 }
 
 void kvm_stage2_flush_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end)
@@ -1015,7 +1016,7 @@ static void stage2_unmap_memslot(struct kvm *kvm,
 
 		if (!(vma->vm_flags & VM_PFNMAP)) {
 			gpa_t gpa = addr + (vm_start - memslot->userspace_addr);
-			kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, vm_end - vm_start);
+			kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, vm_end - vm_start, true);
 		}
 		hva = vm_end;
 	} while (hva < reg_end);
@@ -1042,7 +1043,7 @@ void stage2_unmap_vm(struct kvm *kvm)
 	kvm_for_each_memslot(memslot, bkt, slots)
 		stage2_unmap_memslot(kvm, memslot);
 
-	kvm_nested_s2_unmap(kvm);
+	kvm_nested_s2_unmap(kvm, true);
 
 	write_unlock(&kvm->mmu_lock);
 	mmap_read_unlock(current->mm);
@@ -1912,7 +1913,7 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
 			     (range->end - range->start) << PAGE_SHIFT,
 			     range->may_block);
 
-	kvm_nested_s2_unmap(kvm);
+	kvm_nested_s2_unmap(kvm, range->may_block);
 	return false;
 }
 
@@ -2179,8 +2180,8 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 	phys_addr_t size = slot->npages << PAGE_SHIFT;
 
 	write_lock(&kvm->mmu_lock);
-	kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, size);
-	kvm_nested_s2_unmap(kvm);
+	kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, size, true);
+	kvm_nested_s2_unmap(kvm, true);
 	write_unlock(&kvm->mmu_lock);
 }
 

arch/arm64/kvm/nested.c

@@ -632,9 +632,9 @@ static struct kvm_s2_mmu *get_s2_mmu_nested(struct kvm_vcpu *vcpu)
 	/* Set the scene for the next search */
 	kvm->arch.nested_mmus_next = (i + 1) % kvm->arch.nested_mmus_size;
 
-	/* Clear the old state */
+	/* Make sure we don't forget to do the laundry */
 	if (kvm_s2_mmu_valid(s2_mmu))
-		kvm_stage2_unmap_range(s2_mmu, 0, kvm_phys_size(s2_mmu));
+		s2_mmu->pending_unmap = true;
 
 	/*
 	 * The virtual VMID (modulo CnP) will be used as a key when matching
@@ -650,6 +650,16 @@ static struct kvm_s2_mmu *get_s2_mmu_nested(struct kvm_vcpu *vcpu)
 
 out:
 	atomic_inc(&s2_mmu->refcnt);
+
+	/*
+	 * Set the vCPU request to perform an unmap, even if the pending unmap
+	 * originates from another vCPU. This guarantees that the MMU has been
+	 * completely unmapped before any vCPU actually uses it, and allows
+	 * multiple vCPUs to lend a hand with completing the unmap.
+	 */
+	if (s2_mmu->pending_unmap)
+		kvm_make_request(KVM_REQ_NESTED_S2_UNMAP, vcpu);
+
 	return s2_mmu;
 }
 
@@ -663,6 +673,13 @@ void kvm_init_nested_s2_mmu(struct kvm_s2_mmu *mmu)
 
 void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu)
 {
+	/*
+	 * The vCPU kept its reference on the MMU after the last put, keep
+	 * rolling with it.
+	 */
+	if (vcpu->arch.hw_mmu)
+		return;
+
 	if (is_hyp_ctxt(vcpu)) {
 		vcpu->arch.hw_mmu = &vcpu->kvm->arch.mmu;
 	} else {
@@ -674,10 +691,18 @@ void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu)
 
 void kvm_vcpu_put_hw_mmu(struct kvm_vcpu *vcpu)
 {
-	if (kvm_is_nested_s2_mmu(vcpu->kvm, vcpu->arch.hw_mmu)) {
+	/*
+	 * Keep a reference on the associated stage-2 MMU if the vCPU is
+	 * scheduling out and not in WFI emulation, suggesting it is likely to
+	 * reuse the MMU sometime soon.
+	 */
+	if (vcpu->scheduled_out && !vcpu_get_flag(vcpu, IN_WFI))
+		return;
+
+	if (kvm_is_nested_s2_mmu(vcpu->kvm, vcpu->arch.hw_mmu))
 		atomic_dec(&vcpu->arch.hw_mmu->refcnt);
-		vcpu->arch.hw_mmu = NULL;
-	}
+
+	vcpu->arch.hw_mmu = NULL;
 }
 
 /*
@@ -730,7 +755,7 @@ void kvm_nested_s2_wp(struct kvm *kvm)
 	}
 }
 
-void kvm_nested_s2_unmap(struct kvm *kvm)
+void kvm_nested_s2_unmap(struct kvm *kvm, bool may_block)
 {
 	int i;
 
@@ -740,7 +765,7 @@ void kvm_nested_s2_unmap(struct kvm *kvm)
 		struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
 
 		if (kvm_s2_mmu_valid(mmu))
-			kvm_stage2_unmap_range(mmu, 0, kvm_phys_size(mmu));
+			kvm_stage2_unmap_range(mmu, 0, kvm_phys_size(mmu), may_block);
 	}
 }
 
@@ -1184,3 +1209,17 @@ int kvm_init_nv_sysregs(struct kvm *kvm)
 
 	return 0;
 }
+
+void check_nested_vcpu_requests(struct kvm_vcpu *vcpu)
+{
+	if (kvm_check_request(KVM_REQ_NESTED_S2_UNMAP, vcpu)) {
+		struct kvm_s2_mmu *mmu = vcpu->arch.hw_mmu;
+
+		write_lock(&vcpu->kvm->mmu_lock);
+		if (mmu->pending_unmap) {
+			kvm_stage2_unmap_range(mmu, 0, kvm_phys_size(mmu), true);
+			mmu->pending_unmap = false;
+		}
+		write_unlock(&vcpu->kvm->mmu_lock);
+	}
+}