KVM: PPC: Book3S HV P9: Reduce mftb per guest entry/exit

mftb is serialising (dispatch next-to-complete) so it is heavy weight
for a mfspr. Avoid reading it multiple times in the entry or exit paths.
A small number of cycles delay to timers is tolerable.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Reviewed-by: Fabiano Rosas <farosas@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20211123095231.1036501-7-npiggin@gmail.com

arch/powerpc/kvm/book3s_hv.c

@@ -3940,7 +3940,7 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 	 *
 	 * XXX: Another day's problem.
 	 */
-	mtspr(SPRN_DEC, vcpu->arch.dec_expires - mftb());
+	mtspr(SPRN_DEC, vcpu->arch.dec_expires - tb);
 
 	if (kvmhv_on_pseries()) {
 		/*
@@ -4063,7 +4063,7 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 	vc->in_guest = 0;
 
 	next_timer = timer_get_next_tb();
-	set_dec(next_timer - mftb());
+	set_dec(next_timer - tb);
 	/* We may have raced with new irq work */
 	if (test_irq_work_pending())
 		set_dec(1);

arch/powerpc/kvm/book3s_hv_p9_entry.c

@@ -203,7 +203,8 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
 	unsigned long host_dawr1;
 	unsigned long host_dawrx1;
 
-	hdec = time_limit - mftb();
+	tb = mftb();
+	hdec = time_limit - tb;
 	if (hdec < 0)
 		return BOOK3S_INTERRUPT_HV_DECREMENTER;
 
@@ -215,7 +216,7 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
 	vcpu->arch.ceded = 0;
 
 	if (vc->tb_offset) {
-		u64 new_tb = mftb() + vc->tb_offset;
+		u64 new_tb = tb + vc->tb_offset;
 		mtspr(SPRN_TBU40, new_tb);
 		tb = mftb();
 		if ((tb & 0xffffff) < (new_tb & 0xffffff))