arm64: perf: Add cap_user_time_short

This completes the ARM64 cap_user_time support.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Leo Yan <leo.yan@linaro.org>
Link: https://lore.kernel.org/r/20200716051130.4359-7-leo.yan@linaro.org
Signed-off-by: Will Deacon <will@kernel.org>

Author: Peter Zijlstra

arch/arm64/kernel/perf_event.c

@@ -1177,6 +1177,7 @@ void arch_perf_update_userpage(struct perf_event *event,
 
 	userpg->cap_user_time = 0;
 	userpg->cap_user_time_zero = 0;
+	userpg->cap_user_time_short = 0;
 
 	do {
 		rd = sched_clock_read_begin(&seq);
@@ -1187,13 +1188,13 @@ void arch_perf_update_userpage(struct perf_event *event,
 		userpg->time_mult = rd->mult;
 		userpg->time_shift = rd->shift;
 		userpg->time_zero = rd->epoch_ns;
+		userpg->time_cycles = rd->epoch_cyc;
+		userpg->time_mask = rd->sched_clock_mask;
 
 		/*
-		 * This isn't strictly correct, the ARM64 counter can be
-		 * 'short' and then we get funnies when it wraps. The correct
-		 * thing would be to extend the perf ABI with a cycle and mask
-		 * value, but because wrapping on ARM64 is very rare in
-		 * practise this 'works'.
+		 * Subtract the cycle base, such that software that
+		 * doesn't know about cap_user_time_short still 'works'
+		 * assuming no wraps.
 		 */
 		ns = mul_u64_u32_shr(rd->epoch_cyc, rd->mult, rd->shift);
 		userpg->time_zero -= ns;
@@ -1219,4 +1220,5 @@ void arch_perf_update_userpage(struct perf_event *event,
 	 */
 	userpg->cap_user_time = 1;
 	userpg->cap_user_time_zero = 1;
+	userpg->cap_user_time_short = 1;
 }