KVM: PPC: Book3S HV P9: Avoid SPR scoreboard stalls

Avoid interleaving mfSPR and mtSPR to reduce SPR scoreboard stalls.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20211123095231.1036501-26-npiggin@gmail.com

arch/powerpc/kvm/book3s_hv.c

@@ -4321,10 +4321,6 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 
 	store_spr_state(vcpu);
 
-	timer_rearm_host_dec(*tb);
-
-	restore_p9_host_os_sprs(vcpu, &host_os_sprs);
-
 	store_fp_state(&vcpu->arch.fp);
 #ifdef CONFIG_ALTIVEC
 	store_vr_state(&vcpu->arch.vr);
@@ -4339,6 +4335,10 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 
 	switch_pmu_to_host(vcpu, &host_os_sprs);
 
+	timer_rearm_host_dec(*tb);
+
+	restore_p9_host_os_sprs(vcpu, &host_os_sprs);
+
 	vc->entry_exit_map = 0x101;
 	vc->in_guest = 0;
 

arch/powerpc/kvm/book3s_hv_p9_entry.c

@@ -228,6 +228,9 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
 		host_dawrx1 = mfspr(SPRN_DAWRX1);
 	}
 
+	local_paca->kvm_hstate.host_purr = mfspr(SPRN_PURR);
+	local_paca->kvm_hstate.host_spurr = mfspr(SPRN_SPURR);
+
 	if (vc->tb_offset) {
 		u64 new_tb = *tb + vc->tb_offset;
 		mtspr(SPRN_TBU40, new_tb);
@@ -244,8 +247,6 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
 	mtspr(SPRN_DPDES, vc->dpdes);
 	mtspr(SPRN_VTB, vc->vtb);
 
-	local_paca->kvm_hstate.host_purr = mfspr(SPRN_PURR);
-	local_paca->kvm_hstate.host_spurr = mfspr(SPRN_SPURR);
 	mtspr(SPRN_PURR, vcpu->arch.purr);
 	mtspr(SPRN_SPURR, vcpu->arch.spurr);
 
@@ -448,10 +449,8 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
 	/* Advance host PURR/SPURR by the amount used by guest */
 	purr = mfspr(SPRN_PURR);
 	spurr = mfspr(SPRN_SPURR);
-	mtspr(SPRN_PURR, local_paca->kvm_hstate.host_purr +
-	      purr - vcpu->arch.purr);
-	mtspr(SPRN_SPURR, local_paca->kvm_hstate.host_spurr +
-	      spurr - vcpu->arch.spurr);
+	local_paca->kvm_hstate.host_purr += purr - vcpu->arch.purr;
+	local_paca->kvm_hstate.host_spurr += spurr - vcpu->arch.spurr;
 	vcpu->arch.purr = purr;
 	vcpu->arch.spurr = spurr;
 
@@ -464,6 +463,9 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
 	vcpu->arch.shregs.sprg2 = mfspr(SPRN_SPRG2);
 	vcpu->arch.shregs.sprg3 = mfspr(SPRN_SPRG3);
 
+	vc->dpdes = mfspr(SPRN_DPDES);
+	vc->vtb = mfspr(SPRN_VTB);
+
 	dec = mfspr(SPRN_DEC);
 	if (!(lpcr & LPCR_LD)) /* Sign extend if not using large decrementer */
 		dec = (s32) dec;
@@ -481,6 +483,9 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
 		vc->tb_offset_applied = 0;
 	}
 
+	mtspr(SPRN_PURR, local_paca->kvm_hstate.host_purr);
+	mtspr(SPRN_SPURR, local_paca->kvm_hstate.host_spurr);
+
 	/* Preserve PSSCR[FAKE_SUSPEND] until we've called kvmppc_save_tm_hv */
 	mtspr(SPRN_PSSCR, host_psscr |
 	      (local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG));
@@ -509,8 +514,6 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
 	if (cpu_has_feature(CPU_FTR_ARCH_31))
 		asm volatile(PPC_CP_ABORT);
 
-	vc->dpdes = mfspr(SPRN_DPDES);
-	vc->vtb = mfspr(SPRN_VTB);
 	mtspr(SPRN_DPDES, 0);
 	if (vc->pcr)
 		mtspr(SPRN_PCR, PCR_MASK);