Merge tag 'kvm-x86-misc-6.12' of https://github.com/kvm-x86/linux into HEAD

KVM x86 misc changes for 6.12

 - Advertise AVX10.1 to userspace (effectively prep work for the "real" AVX10
   functionality that is on the horizon).

 - Rework common MSR handling code to suppress errors on userspace accesses to
   unsupported-but-advertised MSRs.  This will allow removing (almost?) all of
   KVM's exemptions for userspace access to MSRs that shouldn't exist based on
   the vCPU model (the actual cleanup is non-trivial future work).

 - Rework KVM's handling of x2APIC ICR, again, because AMD (x2AVIC) splits the
   64-bit value into the legacy ICR and ICR2 storage, whereas Intel (APICv)
   stores the entire 64-bit value a the ICR offset.

 - Fix a bug where KVM would fail to exit to userspace if one was triggered by
   a fastpath exit handler.

 - Add fastpath handling of HLT VM-Exit to expedite re-entering the guest when
   there's already a pending wake event at the time of the exit.

 - Finally fix the RSM vs. nested VM-Enter WARN by forcing the vCPU out of
   guest mode prior to signalling SHUTDOWN (architecturally, the SHUTDOWN is
   supposed to hit L1, not L2).

1 files changed, 29 insertions, 15 deletions

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 6b804ec3d1dc..c1062e8c3f50 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -2825,17 +2825,17 @@ static int efer_trap(struct kvm_vcpu *vcpu)
 	return kvm_complete_insn_gp(vcpu, ret);
 }
 
-static int svm_get_msr_feature(struct kvm_msr_entry *msr)
+static int svm_get_feature_msr(u32 msr, u64 *data)
 {
-	msr->data = 0;
+	*data = 0;
 
-	switch (msr->index) {
+	switch (msr) {
 	case MSR_AMD64_DE_CFG:
 		if (cpu_feature_enabled(X86_FEATURE_LFENCE_RDTSC))
-			msr->data |= MSR_AMD64_DE_CFG_LFENCE_SERIALIZE;
+			*data |= MSR_AMD64_DE_CFG_LFENCE_SERIALIZE;
 		break;
 	default:
-		return KVM_MSR_RET_INVALID;
+		return KVM_MSR_RET_UNSUPPORTED;
 	}
 
 	return 0;
@@ -3191,18 +3191,21 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 		kvm_pr_unimpl_wrmsr(vcpu, ecx, data);
 		break;
 	case MSR_AMD64_DE_CFG: {
-		struct kvm_msr_entry msr_entry;
+		u64 supported_de_cfg;
 
-		msr_entry.index = msr->index;
-		if (svm_get_msr_feature(&msr_entry))
+		if (svm_get_feature_msr(ecx, &supported_de_cfg))
 			return 1;
 
-		/* Check the supported bits */
-		if (data & ~msr_entry.data)
+		if (data & ~supported_de_cfg)
 			return 1;
 
-		/* Don't allow the guest to change a bit, #GP */
-		if (!msr->host_initiated && (data ^ msr_entry.data))
+		/*
+		 * Don't let the guest change the host-programmed value.  The
+		 * MSR is very model specific, i.e. contains multiple bits that
+		 * are completely unknown to KVM, and the one bit known to KVM
+		 * is simply a reflection of hardware capabilities.
+		 */
+		if (!msr->host_initiated && data != svm->msr_decfg)
 			return 1;
 
 		svm->msr_decfg = data;
@@ -4156,12 +4159,21 @@ static int svm_vcpu_pre_run(struct kvm_vcpu *vcpu)
 
 static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu)
 {
+	struct vcpu_svm *svm = to_svm(vcpu);
+
 	if (is_guest_mode(vcpu))
 		return EXIT_FASTPATH_NONE;
 
-	if (to_svm(vcpu)->vmcb->control.exit_code == SVM_EXIT_MSR &&
-	    to_svm(vcpu)->vmcb->control.exit_info_1)
+	switch (svm->vmcb->control.exit_code) {
+	case SVM_EXIT_MSR:
+		if (!svm->vmcb->control.exit_info_1)
+			break;
 		return handle_fastpath_set_msr_irqoff(vcpu);
+	case SVM_EXIT_HLT:
+		return handle_fastpath_hlt(vcpu);
+	default:
+		break;
+	}
 
 	return EXIT_FASTPATH_NONE;
 }
@@ -5012,7 +5024,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.vcpu_unblocking = avic_vcpu_unblocking,
 
 	.update_exception_bitmap = svm_update_exception_bitmap,
-	.get_msr_feature = svm_get_msr_feature,
+	.get_feature_msr = svm_get_feature_msr,
 	.get_msr = svm_get_msr,
 	.set_msr = svm_set_msr,
 	.get_segment_base = svm_get_segment_base,
@@ -5063,6 +5075,8 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.enable_nmi_window = svm_enable_nmi_window,
 	.enable_irq_window = svm_enable_irq_window,
 	.update_cr8_intercept = svm_update_cr8_intercept,
+
+	.x2apic_icr_is_split = true,
 	.set_virtual_apic_mode = avic_refresh_virtual_apic_mode,
 	.refresh_apicv_exec_ctrl = avic_refresh_apicv_exec_ctrl,
 	.apicv_post_state_restore = avic_apicv_post_state_restore,