KVM: PPC: Book3S HV P9: Optimise hash guest SLB saving

slbmfee/slbmfev instructions are very expensive, moreso than a regular
mfspr instruction, so minimising them significantly improves hash guest
exit performance. The slbmfev is only required if slbmfee found a valid
SLB entry.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20211123095231.1036501-47-npiggin@gmail.com

arch/powerpc/kvm/book3s_hv_p9_entry.c

@@ -487,10 +487,22 @@ static void __accumulate_time(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator
 #define accumulate_time(vcpu, next) do {} while (0)
 #endif
 
-static inline void mfslb(unsigned int idx, u64 *slbee, u64 *slbev)
+static inline u64 mfslbv(unsigned int idx)
 {
-	asm volatile("slbmfev  %0,%1" : "=r" (*slbev) : "r" (idx));
-	asm volatile("slbmfee  %0,%1" : "=r" (*slbee) : "r" (idx));
+	u64 slbev;
+
+	asm volatile("slbmfev  %0,%1" : "=r" (slbev) : "r" (idx));
+
+	return slbev;
+}
+
+static inline u64 mfslbe(unsigned int idx)
+{
+	u64 slbee;
+
+	asm volatile("slbmfee  %0,%1" : "=r" (slbee) : "r" (idx));
+
+	return slbee;
 }
 
 static inline void mtslb(u64 slbee, u64 slbev)
@@ -620,8 +632,10 @@ static void save_clear_guest_mmu(struct kvm *kvm, struct kvm_vcpu *vcpu)
 		 */
 		for (i = 0; i < vcpu->arch.slb_nr; i++) {
 			u64 slbee, slbev;
-			mfslb(i, &slbee, &slbev);
+
+			slbee = mfslbe(i);
 			if (slbee & SLB_ESID_V) {
+				slbev = mfslbv(i);
 				vcpu->arch.slb[nr].orige = slbee | i;
 				vcpu->arch.slb[nr].origv = slbev;
 				nr++;