Merge tag 'kvm-x86-misc-6.6' of https://github.com/kvm-x86/linux into HEAD

KVM x86 changes for 6.6:

 - Misc cleanups

 - Retry APIC optimized recalculation if a vCPU is added/enabled

 - Overhaul emergency reboot code to bring SVM up to par with VMX, tie the
   "emergency disabling" behavior to KVM actually being loaded, and move all of
   the logic within KVM

 - Fix user triggerable WARNs in SVM where KVM incorrectly assumes the TSC
   ratio MSR can diverge from the default iff TSC scaling is enabled, and clean
   up related code

 - Add a framework to allow "caching" feature flags so that KVM can check if
   the guest can use a feature without needing to search guest CPUID

1 files changed, 39 insertions, 1 deletions

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index d3432687c9e6..0544e30b4946 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -11,6 +11,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/kvm_host.h>
+#include "linux/lockdep.h"
 #include <linux/export.h>
 #include <linux/vmalloc.h>
 #include <linux/uaccess.h>
@@ -84,6 +85,18 @@ static inline struct kvm_cpuid_entry2 *cpuid_entry2_find(
 	struct kvm_cpuid_entry2 *e;
 	int i;
 
+	/*
+	 * KVM has a semi-arbitrary rule that querying the guest's CPUID model
+	 * with IRQs disabled is disallowed.  The CPUID model can legitimately
+	 * have over one hundred entries, i.e. the lookup is slow, and IRQs are
+	 * typically disabled in KVM only when KVM is in a performance critical
+	 * path, e.g. the core VM-Enter/VM-Exit run loop.  Nothing will break
+	 * if this rule is violated, this assertion is purely to flag potential
+	 * performance issues.  If this fires, consider moving the lookup out
+	 * of the hotpath, e.g. by caching information during CPUID updates.
+	 */
+	lockdep_assert_irqs_enabled();
+
 	for (i = 0; i < nent; i++) {
 		e = &entries[i];
 
@@ -312,6 +325,27 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	struct kvm_cpuid_entry2 *best;
+	bool allow_gbpages;
+
+	BUILD_BUG_ON(KVM_NR_GOVERNED_FEATURES > KVM_MAX_NR_GOVERNED_FEATURES);
+	bitmap_zero(vcpu->arch.governed_features.enabled,
+		    KVM_MAX_NR_GOVERNED_FEATURES);
+
+	/*
+	 * If TDP is enabled, let the guest use GBPAGES if they're supported in
+	 * hardware.  The hardware page walker doesn't let KVM disable GBPAGES,
+	 * i.e. won't treat them as reserved, and KVM doesn't redo the GVA->GPA
+	 * walk for performance and complexity reasons.  Not to mention KVM
+	 * _can't_ solve the problem because GVA->GPA walks aren't visible to
+	 * KVM once a TDP translation is installed.  Mimic hardware behavior so
+	 * that KVM's is at least consistent, i.e. doesn't randomly inject #PF.
+	 * If TDP is disabled, honor *only* guest CPUID as KVM has full control
+	 * and can install smaller shadow pages if the host lacks 1GiB support.
+	 */
+	allow_gbpages = tdp_enabled ? boot_cpu_has(X86_FEATURE_GBPAGES) :
+				      guest_cpuid_has(vcpu, X86_FEATURE_GBPAGES);
+	if (allow_gbpages)
+		kvm_governed_feature_set(vcpu, X86_FEATURE_GBPAGES);
 
 	best = kvm_find_cpuid_entry(vcpu, 1);
 	if (best && apic) {
@@ -647,7 +681,8 @@ void kvm_set_cpu_caps(void)
 	);
 
 	kvm_cpu_cap_init_kvm_defined(CPUID_7_1_EDX,
-		F(AVX_VNNI_INT8) | F(AVX_NE_CONVERT) | F(PREFETCHITI)
+		F(AVX_VNNI_INT8) | F(AVX_NE_CONVERT) | F(PREFETCHITI) |
+		F(AMX_COMPLEX)
 	);
 
 	kvm_cpu_cap_mask(CPUID_D_1_EAX,
@@ -1154,6 +1189,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 		cpuid_entry_override(entry, CPUID_8000_0001_EDX);
 		cpuid_entry_override(entry, CPUID_8000_0001_ECX);
 		break;
+	case 0x80000005:
+		/*  Pass host L1 cache and TLB info. */
+		break;
 	case 0x80000006:
 		/* Drop reserved bits, pass host L2 cache and TLB info. */
 		entry->edx &= ~GENMASK(17, 16);