Merge tag 'kvm-x86-fixes-6.19-rc1' of https://github.com/kvm-x86/linux into HEAD

KVM fixes for 6.19-rc1

 - Add a missing "break" to fix param parsing in the rseq selftest.

 - Apply runtime updates to the _current_ CPUID when userspace is setting
   CPUID, e.g. as part of vCPU hotplug, to fix a false positive and to avoid
   dropping the pending update.

 - Disallow toggling KVM_MEM_GUEST_MEMFD on an existing memslot, as it's not
   supported by KVM and leads to a use-after-free due to KVM failing to unbind
   the memslot from the previously-associated guest_memfd instance.

 - Harden against similar KVM_MEM_GUEST_MEMFD goofs, and prepare for supporting
   flags-only changes on KVM_MEM_GUEST_MEMFD memlslots, e.g. for dirty logging.

 - Set exit_code[63:32] to -1 (all 0xffs) when synthesizing a nested
   SVM_EXIT_ERR (a.k.a. VMEXIT_INVALID) #VMEXIT, as VMEXIT_INVALID is defined
   as -1ull (a 64-bit value).

 - Update SVI when activating APICv to fix a bug where a post-activation EOI
   for an in-service IRQ would effective be lost due to SVI being stale.

 - Immediately refresh APICv controls (if necessary) on a nested VM-Exit
   instead of deferring the update via KVM_REQ_APICV_UPDATE, as the request is
   effectively ignored because KVM thinks the vCPU already has the correct
   APICv settings.

Author: bonzini

arch/x86/kvm/cpuid.c

@@ -509,11 +509,18 @@ static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2,
 	u32 vcpu_caps[NR_KVM_CPU_CAPS];
 	int r;
 
+	/*
+	 * Apply pending runtime CPUID updates to the current CPUID entries to
+	 * avoid false positives due to mismatches on KVM-owned feature flags.
+	 */
+	if (vcpu->arch.cpuid_dynamic_bits_dirty)
+		kvm_update_cpuid_runtime(vcpu);
+
 	/*
 	 * Swap the existing (old) entries with the incoming (new) entries in
 	 * order to massage the new entries, e.g. to account for dynamic bits
-	 * that KVM controls, without clobbering the current guest CPUID, which
-	 * KVM needs to preserve in order to unwind on failure.
+	 * that KVM controls, without losing the current guest CPUID, which KVM
+	 * needs to preserve in order to unwind on failure.
 	 *
 	 * Similarly, save the vCPU's current cpu_caps so that the capabilities
 	 * can be updated alongside the CPUID entries when performing runtime

arch/x86/kvm/svm/nested.c

@@ -985,7 +985,7 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu)
 	if (!nested_vmcb_check_save(vcpu) ||
 	    !nested_vmcb_check_controls(vcpu)) {
 		vmcb12->control.exit_code    = SVM_EXIT_ERR;
-		vmcb12->control.exit_code_hi = 0;
+		vmcb12->control.exit_code_hi = -1u;
 		vmcb12->control.exit_info_1  = 0;
 		vmcb12->control.exit_info_2  = 0;
 		goto out;
@@ -1018,7 +1018,7 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu)
 	svm->soft_int_injected = false;
 
 	svm->vmcb->control.exit_code    = SVM_EXIT_ERR;
-	svm->vmcb->control.exit_code_hi = 0;
+	svm->vmcb->control.exit_code_hi = -1u;
 	svm->vmcb->control.exit_info_1  = 0;
 	svm->vmcb->control.exit_info_2  = 0;
 

arch/x86/kvm/svm/svm.c

@@ -2443,6 +2443,7 @@ static bool check_selective_cr0_intercepted(struct kvm_vcpu *vcpu,
 
 	if (cr0 ^ val) {
 		svm->vmcb->control.exit_code = SVM_EXIT_CR0_SEL_WRITE;
+		svm->vmcb->control.exit_code_hi = 0;
 		ret = (nested_svm_exit_handled(svm) == NESTED_EXIT_DONE);
 	}
 
@@ -4617,6 +4618,7 @@ static int svm_check_intercept(struct kvm_vcpu *vcpu,
 	if (static_cpu_has(X86_FEATURE_NRIPS))
 		vmcb->control.next_rip  = info->next_rip;
 	vmcb->control.exit_code = icpt_info.exit_code;
+	vmcb->control.exit_code_hi = 0;
 	vmexit = nested_svm_exit_handled(svm);
 
 	ret = (vmexit == NESTED_EXIT_DONE) ? X86EMUL_INTERCEPTED

arch/x86/kvm/svm/svm.h

@@ -761,9 +761,10 @@ int nested_svm_vmexit(struct vcpu_svm *svm);
 
 static inline int nested_svm_simple_vmexit(struct vcpu_svm *svm, u32 exit_code)
 {
-	svm->vmcb->control.exit_code   = exit_code;
-	svm->vmcb->control.exit_info_1 = 0;
-	svm->vmcb->control.exit_info_2 = 0;
+	svm->vmcb->control.exit_code	= exit_code;
+	svm->vmcb->control.exit_code_hi	= 0;
+	svm->vmcb->control.exit_info_1	= 0;
+	svm->vmcb->control.exit_info_2	= 0;
 	return nested_svm_vmexit(svm);
 }
 

arch/x86/kvm/vmx/nested.c

@@ -19,6 +19,7 @@
 #include "trace.h"
 #include "vmx.h"
 #include "smm.h"
+#include "x86_ops.h"
 
 static bool __read_mostly enable_shadow_vmcs = 1;
 module_param_named(enable_shadow_vmcs, enable_shadow_vmcs, bool, S_IRUGO);
@@ -5165,7 +5166,7 @@ void __nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 
 	if (vmx->nested.update_vmcs01_apicv_status) {
 		vmx->nested.update_vmcs01_apicv_status = false;
-		kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu);
+		vmx_refresh_apicv_exec_ctrl(vcpu);
 	}
 
 	if (vmx->nested.update_vmcs01_hwapic_isr) {

arch/x86/kvm/vmx/vmx.c

@@ -6937,15 +6937,6 @@ void vmx_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr)
 	 * VM-Exit, otherwise L1 with run with a stale SVI.
 	 */
 	if (is_guest_mode(vcpu)) {
-		/*
-		 * KVM is supposed to forward intercepted L2 EOIs to L1 if VID
-		 * is enabled in vmcs12; as above, the EOIs affect L2's vAPIC.
-		 * Note, userspace can stuff state while L2 is active; assert
-		 * that VID is disabled if and only if the vCPU is in KVM_RUN
-		 * to avoid false positives if userspace is setting APIC state.
-		 */
-		WARN_ON_ONCE(vcpu->wants_to_run &&
-			     nested_cpu_has_vid(get_vmcs12(vcpu)));
 		to_vmx(vcpu)->nested.update_vmcs01_hwapic_isr = true;
 		return;
 	}

arch/x86/kvm/x86.c

@@ -10886,9 +10886,16 @@ void __kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu)
 	 * pending. At the same time, KVM_REQ_EVENT may not be set as APICv was
 	 * still active when the interrupt got accepted. Make sure
 	 * kvm_check_and_inject_events() is called to check for that.
+	 *
+	 * Update SVI when APICv gets enabled, otherwise SVI won't reflect the
+	 * highest bit in vISR and the next accelerated EOI in the guest won't
+	 * be virtualized correctly (the CPU uses SVI to determine which vISR
+	 * vector to clear).
 	 */
 	if (!apic->apicv_active)
 		kvm_make_request(KVM_REQ_EVENT, vcpu);
+	else
+		kvm_apic_update_hwapic_isr(vcpu);
 
 out:
 	preempt_enable();

tools/testing/selftests/kvm/rseq_test.c

@@ -215,6 +215,7 @@ int main(int argc, char *argv[])
 		switch (opt) {
 		case 'u':
 			skip_sanity_check = true;
+			break;
 		case 'l':
 			latency = atoi_paranoid(optarg);
 			break;

tools/testing/selftests/kvm/x86/cpuid_test.c

@@ -155,13 +155,28 @@ struct kvm_cpuid2 *vcpu_alloc_cpuid(struct kvm_vm *vm, vm_vaddr_t *p_gva, struct
 static void set_cpuid_after_run(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *ent;
+	struct kvm_sregs sregs;
 	int rc;
 	u32 eax, ebx, x;
 
 	/* Setting unmodified CPUID is allowed */
 	rc = __vcpu_set_cpuid(vcpu);
 	TEST_ASSERT(!rc, "Setting unmodified CPUID after KVM_RUN failed: %d", rc);
 
+	/*
+	 * Toggle CR4 bits that affect dynamic CPUID feature flags to verify
+	 * setting unmodified CPUID succeeds with runtime CPUID updates.
+	 */
+	vcpu_sregs_get(vcpu, &sregs);
+	if (kvm_cpu_has(X86_FEATURE_XSAVE))
+		sregs.cr4 ^= X86_CR4_OSXSAVE;
+	if (kvm_cpu_has(X86_FEATURE_PKU))
+		sregs.cr4 ^= X86_CR4_PKE;
+	vcpu_sregs_set(vcpu, &sregs);
+
+	rc = __vcpu_set_cpuid(vcpu);
+	TEST_ASSERT(!rc, "Setting unmodified CPUID after KVM_RUN failed: %d", rc);
+
 	/* Changing CPU features is forbidden */
 	ent = vcpu_get_cpuid_entry(vcpu, 0x7);
 	ebx = ent->ebx;

virt/kvm/kvm_main.c

@@ -1749,6 +1749,12 @@ static void kvm_commit_memory_region(struct kvm *kvm,
 		kvm_free_memslot(kvm, old);
 		break;
 	case KVM_MR_MOVE:
+		/*
+		 * Moving a guest_memfd memslot isn't supported, and will never
+		 * be supported.
+		 */
+		WARN_ON_ONCE(old->flags & KVM_MEM_GUEST_MEMFD);
+		fallthrough;
 	case KVM_MR_FLAGS_ONLY:
 		/*
 		 * Free the dirty bitmap as needed; the below check encompasses
@@ -1757,6 +1763,15 @@ static void kvm_commit_memory_region(struct kvm *kvm,
 		if (old->dirty_bitmap && !new->dirty_bitmap)
 			kvm_destroy_dirty_bitmap(old);
 
+		/*
+		 * Unbind the guest_memfd instance as needed; the @new slot has
+		 * already created its own binding.  TODO: Drop the WARN when
+		 * dirty logging guest_memfd memslots is supported.  Until then,
+		 * flags-only changes on guest_memfd slots should be impossible.
+		 */
+		if (WARN_ON_ONCE(old->flags & KVM_MEM_GUEST_MEMFD))
+			kvm_gmem_unbind(old);
+
 		/*
 		 * The final quirk.  Free the detached, old slot, but only its
 		 * memory, not any metadata.  Metadata, including arch specific
@@ -2086,7 +2101,7 @@ static int kvm_set_memory_region(struct kvm *kvm,
 			return -EINVAL;
 		if ((mem->userspace_addr != old->userspace_addr) ||
 		    (npages != old->npages) ||
-		    ((mem->flags ^ old->flags) & KVM_MEM_READONLY))
+		    ((mem->flags ^ old->flags) & (KVM_MEM_READONLY | KVM_MEM_GUEST_MEMFD)))
 			return -EINVAL;
 
 		if (base_gfn != old->base_gfn)