KVM: PPC: Book3S HV P9: Improve mtmsrd scheduling by delaying MSR[EE] disable

Moving the mtmsrd after the host SPRs are saved and before the guest
SPRs start to be loaded can prevent an SPR scoreboard stall (because
the mtmsrd is L=1 type which does not cause context synchronisation.

This is also now more convenient to combined with the mtmsrd L=0
instruction to enable facilities just below, but that is not done yet.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20211123095231.1036501-21-npiggin@gmail.com

arch/powerpc/kvm/book3s_hv.c

@@ -4169,6 +4169,18 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 
 	save_p9_host_os_sprs(&host_os_sprs);
 
+	/*
+	 * This could be combined with MSR[RI] clearing, but that expands
+	 * the unrecoverable window. It would be better to cover unrecoverable
+	 * with KVM bad interrupt handling rather than use MSR[RI] at all.
+	 *
+	 * Much more difficult and less worthwhile to combine with IR/DR
+	 * disable.
+	 */
+	hard_irq_disable();
+	if (lazy_irq_pending())
+		return 0;
+
 	/* MSR bits may have been cleared by context switch */
 	msr = 0;
 	if (IS_ENABLED(CONFIG_PPC_FPU))
@@ -4680,6 +4692,7 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
 	struct kvmppc_vcore *vc;
 	struct kvm *kvm = vcpu->kvm;
 	struct kvm_nested_guest *nested = vcpu->arch.nested;
+	unsigned long flags;
 
 	trace_kvmppc_run_vcpu_enter(vcpu);
 
@@ -4723,11 +4736,11 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
 	if (kvm_is_radix(kvm))
 		kvmppc_prepare_radix_vcpu(vcpu, pcpu);
 
-	local_irq_disable();
-	hard_irq_disable();
+	/* flags save not required, but irq_pmu has no disable/enable API */
+	powerpc_local_irq_pmu_save(flags);
 	if (signal_pending(current))
 		goto sigpend;
-	if (lazy_irq_pending() || need_resched() || !kvm->arch.mmu_ready)
+	if (need_resched() || !kvm->arch.mmu_ready)
 		goto out;
 
 	if (!nested) {
@@ -4795,7 +4808,7 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
 	}
 	vtime_account_guest_exit();
 
-	local_irq_enable();
+	powerpc_local_irq_pmu_restore(flags);
 
 	cpumask_clear_cpu(pcpu, &kvm->arch.cpu_in_guest);
 
@@ -4853,7 +4866,7 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
 	run->exit_reason = KVM_EXIT_INTR;
 	vcpu->arch.ret = -EINTR;
  out:
-	local_irq_enable();
+	powerpc_local_irq_pmu_restore(flags);
 	preempt_enable();
 	goto done;
 }