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, 25 insertions, 4 deletions

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index a983a16163b1..dcd60b39e794 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -376,7 +376,8 @@ void kvm_recalculate_apic_map(struct kvm *kvm)
 	struct kvm_vcpu *vcpu;
 	unsigned long i;
 	u32 max_id = 255; /* enough space for any xAPIC ID */
-	bool xapic_id_mismatch = false;
+	bool xapic_id_mismatch;
+	int r;
 
 	/* Read kvm->arch.apic_map_dirty before kvm->arch.apic_map.  */
 	if (atomic_read_acquire(&kvm->arch.apic_map_dirty) == CLEAN)
@@ -386,9 +387,14 @@ void kvm_recalculate_apic_map(struct kvm *kvm)
 		  "Dirty APIC map without an in-kernel local APIC");
 
 	mutex_lock(&kvm->arch.apic_map_lock);
+
+retry:
 	/*
-	 * Read kvm->arch.apic_map_dirty before kvm->arch.apic_map
-	 * (if clean) or the APIC registers (if dirty).
+	 * Read kvm->arch.apic_map_dirty before kvm->arch.apic_map (if clean)
+	 * or the APIC registers (if dirty).  Note, on retry the map may have
+	 * not yet been marked dirty by whatever task changed a vCPU's x2APIC
+	 * ID, i.e. the map may still show up as in-progress.  In that case
+	 * this task still needs to retry and complete its calculation.
 	 */
 	if (atomic_cmpxchg_acquire(&kvm->arch.apic_map_dirty,
 				   DIRTY, UPDATE_IN_PROGRESS) == CLEAN) {
@@ -397,6 +403,15 @@ void kvm_recalculate_apic_map(struct kvm *kvm)
 		return;
 	}
 
+	/*
+	 * Reset the mismatch flag between attempts so that KVM does the right
+	 * thing if a vCPU changes its xAPIC ID, but do NOT reset max_id, i.e.
+	 * keep max_id strictly increasing.  Disallowing max_id from shrinking
+	 * ensures KVM won't get stuck in an infinite loop, e.g. if the vCPU
+	 * with the highest x2APIC ID is toggling its APIC on and off.
+	 */
+	xapic_id_mismatch = false;
+
 	kvm_for_each_vcpu(i, vcpu, kvm)
 		if (kvm_apic_present(vcpu))
 			max_id = max(max_id, kvm_x2apic_id(vcpu->arch.apic));
@@ -415,9 +430,15 @@ void kvm_recalculate_apic_map(struct kvm *kvm)
 		if (!kvm_apic_present(vcpu))
 			continue;
 
-		if (kvm_recalculate_phys_map(new, vcpu, &xapic_id_mismatch)) {
+		r = kvm_recalculate_phys_map(new, vcpu, &xapic_id_mismatch);
+		if (r) {
 			kvfree(new);
 			new = NULL;
+			if (r == -E2BIG) {
+				cond_resched();
+				goto retry;
+			}
+
 			goto out;
 		}