Merge tag 'kvmarm-fixes-7.0-3' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 fixes for 7.0, take #3

- Correctly handle deeactivation of out-of-LRs interrupts by
  starting the EOIcount deactivation walk *after* the last irq
  that made it into an LR. This avoids deactivating irqs that
  are in the LRs and that the vcpu hasn't deactivated yet.

- Avoid calling into the stubs to probe for ICH_VTR_EL2.TDS when
  pKVM is already enabled -- not only thhis isn't possible (pKVM
  will reject the call), but it is also useless: this can only
  happen for a CPU that has already booted once, and the capability
  will not change.

Author: bonzini

arch/arm64/include/asm/kvm_host.h

@@ -784,6 +784,9 @@ struct kvm_host_data {
 	/* Number of debug breakpoints/watchpoints for this CPU (minus 1) */
 	unsigned int debug_brps;
 	unsigned int debug_wrps;
+
+	/* Last vgic_irq part of the AP list recorded in an LR */
+	struct vgic_irq *last_lr_irq;
 };
 
 struct kvm_host_psci_config {

arch/arm64/kernel/cpufeature.c

@@ -2345,6 +2345,15 @@ static bool can_trap_icv_dir_el1(const struct arm64_cpu_capabilities *entry,
 	    !is_midr_in_range_list(has_vgic_v3))
 		return false;
 
+	/*
+	 * pKVM prevents late onlining of CPUs. This means that whatever
+	 * state the capability is in after deprivilege cannot be affected
+	 * by a new CPU booting -- this is garanteed to be a CPU we have
+	 * already seen, and the cap is therefore unchanged.
+	 */
+	if (system_capabilities_finalized() && is_protected_kvm_enabled())
+		return cpus_have_final_cap(ARM64_HAS_ICH_HCR_EL2_TDIR);
+
 	if (is_kernel_in_hyp_mode())
 		res.a1 = read_sysreg_s(SYS_ICH_VTR_EL2);
 	else

arch/arm64/kvm/vgic/vgic-v2.c

@@ -115,15 +115,15 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu)
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 	struct vgic_v2_cpu_if *cpuif = &vgic_cpu->vgic_v2;
 	u32 eoicount = FIELD_GET(GICH_HCR_EOICOUNT, cpuif->vgic_hcr);
-	struct vgic_irq *irq;
+	struct vgic_irq *irq = *host_data_ptr(last_lr_irq);
 
 	DEBUG_SPINLOCK_BUG_ON(!irqs_disabled());
 
 	for (int lr = 0; lr < vgic_cpu->vgic_v2.used_lrs; lr++)
 		vgic_v2_fold_lr(vcpu, cpuif->vgic_lr[lr]);
 
 	/* See the GICv3 equivalent for the EOIcount handling rationale */
-	list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) {
+	list_for_each_entry_continue(irq, &vgic_cpu->ap_list_head, ap_list) {
 		u32 lr;
 
 		if (!eoicount) {

arch/arm64/kvm/vgic/vgic-v3.c

@@ -148,7 +148,7 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 	struct vgic_v3_cpu_if *cpuif = &vgic_cpu->vgic_v3;
 	u32 eoicount = FIELD_GET(ICH_HCR_EL2_EOIcount, cpuif->vgic_hcr);
-	struct vgic_irq *irq;
+	struct vgic_irq *irq = *host_data_ptr(last_lr_irq);
 
 	DEBUG_SPINLOCK_BUG_ON(!irqs_disabled());
 
@@ -158,12 +158,12 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
 	/*
 	 * EOIMode=0: use EOIcount to emulate deactivation. We are
 	 * guaranteed to deactivate in reverse order of the activation, so
-	 * just pick one active interrupt after the other in the ap_list,
-	 * and replay the deactivation as if the CPU was doing it. We also
-	 * rely on priority drop to have taken place, and the list to be
-	 * sorted by priority.
+	 * just pick one active interrupt after the other in the tail part
+	 * of the ap_list, past the LRs, and replay the deactivation as if
+	 * the CPU was doing it. We also rely on priority drop to have taken
+	 * place, and the list to be sorted by priority.
 	 */
-	list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) {
+	list_for_each_entry_continue(irq, &vgic_cpu->ap_list_head, ap_list) {
 		u64 lr;
 
 		/*

arch/arm64/kvm/vgic/vgic.c

@@ -814,6 +814,9 @@ static void vgic_prune_ap_list(struct kvm_vcpu *vcpu)
 
 static inline void vgic_fold_lr_state(struct kvm_vcpu *vcpu)
 {
+	if (!*host_data_ptr(last_lr_irq))
+		return;
+
 	if (kvm_vgic_global_state.type == VGIC_V2)
 		vgic_v2_fold_lr_state(vcpu);
 	else
@@ -960,10 +963,13 @@ static void vgic_flush_lr_state(struct kvm_vcpu *vcpu)
 	if (irqs_outside_lrs(&als))
 		vgic_sort_ap_list(vcpu);
 
+	*host_data_ptr(last_lr_irq) = NULL;
+
 	list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) {
 		scoped_guard(raw_spinlock,  &irq->irq_lock) {
 			if (likely(vgic_target_oracle(irq) == vcpu)) {
 				vgic_populate_lr(vcpu, irq, count++);
+				*host_data_ptr(last_lr_irq) = irq;
 			}
 		}