KVM: PPC: Book3S HV P9: Use host timer accounting to avoid decrementer read

There is no need to save away the host DEC value, as it is derived
from the host timer subsystem which maintains the next timer time,
so it can be restored from there.
Signed-off-by: NNicholas Piggin <npiggin@gmail.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20211123095231.1036501-5-npiggin@gmail.com

arch/powerpc/include/asm/time.h

@@ -111,6 +111,11 @@ static inline unsigned long test_irq_work_pending(void)
 
 DECLARE_PER_CPU(u64, decrementers_next_tb);
 
+static inline u64 timer_get_next_tb(void)
+{
+	return __this_cpu_read(decrementers_next_tb);
+}
+
 /* Convert timebase ticks to nanoseconds */
 unsigned long long tb_to_ns(unsigned long long tb_ticks);
 

arch/powerpc/kernel/time.c

@@ -107,6 +107,7 @@ struct clock_event_device decrementer_clockevent = {
 EXPORT_SYMBOL(decrementer_clockevent);
 
 DEFINE_PER_CPU(u64, decrementers_next_tb);
+EXPORT_SYMBOL_GPL(decrementers_next_tb);
 static DEFINE_PER_CPU(struct clock_event_device, decrementers);
 
 #define XSEC_PER_SEC (1024*1024)

arch/powerpc/kvm/book3s_hv.c

@@ -3873,18 +3873,17 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
 	struct p9_host_os_sprs host_os_sprs;
 	s64 dec;
-	u64 tb;
+	u64 tb, next_timer;
 	int trap, save_pmu;
 
 	WARN_ON_ONCE(vcpu->arch.ceded);
 
-	dec = mfspr(SPRN_DEC);
 	tb = mftb();
-	if (dec < 0)
+	next_timer = timer_get_next_tb();
+	if (tb >= next_timer)
 		return BOOK3S_INTERRUPT_HV_DECREMENTER;
-	local_paca->kvm_hstate.dec_expires = dec + tb;
-	if (local_paca->kvm_hstate.dec_expires < time_limit)
-		time_limit = local_paca->kvm_hstate.dec_expires;
+	if (next_timer < time_limit)
+		time_limit = next_timer;
 
 	save_p9_host_os_sprs(&host_os_sprs);
 
@@ -4063,7 +4062,8 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 	vc->entry_exit_map = 0x101;
 	vc->in_guest = 0;
 
-	set_dec(local_paca->kvm_hstate.dec_expires - mftb());
+	next_timer = timer_get_next_tb();
+	set_dec(next_timer - mftb());
 	/* We may have raced with new irq work */
 	if (test_irq_work_pending())
 		set_dec(1);