On Thu, Jul 12, 2018 at 01:29:40PM -0400, Johannes Weiner wrote:

+static bool psi_update_stats(struct psi_group *group)
+{

+	for_each_online_cpu(cpu) {
+		struct psi_group_cpu *groupc = per_cpu_ptr(group->cpus, cpu);
+		unsigned long nonidle;
+
+		if (!groupc->nonidle_time)
+			continue;
+
+		nonidle = nsecs_to_jiffies(groupc->nonidle_time);
+		groupc->nonidle_time = 0;
+		nonidle_total += nonidle;
+
+		for (r = 0; r < NR_PSI_RESOURCES; r++) {
+			struct psi_resource *res = &groupc->res[r];
+
+			some[r] += (res->times[0] + res->times[1]) * nonidle;
+			full[r] += res->times[1] * nonidle;
+
+			/* It's racy, but we can tolerate some error */
+			res->times[0] = 0;
+			res->times[1] = 0;
+		}
+	}

An alternative for this, that also allows that ondemand update, but
without spamming the rq->lock would be something like:

struct psi_group_cpu {
	u32 tasks[3];
	u32 cpu_state : 2;
	u32 mem_state : 2;
	u32 io_state  : 2;
	u32 :0;

	u64 last_update_time;

	u32 nonidle;
	u32 full[2];
	u32 some[3];
} ____cacheline_aligned_in_smp;

/* Allocate _2_ copies */
DEFINE_PER_CPU_ALIGNED_SHARED(struct psi_group_cpu[2], psi_cpus);

struct psi_group global_psi = {
	.cpus = &psi_cpus[0],
};


	u64 sums[6] = { 0, };

	for_each_possible_cpu(cpu) {
		struct psi_group_cpu *pgc = per_cpu_ptr(group->cpus, cpu);
		u32 *active, *shadow;

		active = &pgc[0].nonidle;
		shadow = &pgc[1].nonidle;

		/*
		 * Compare the active count to the shadow count
		 * if different, compute the delta and update the shadow
		 * copy.
		 * This only writes to the shadow copy (separate line)
		 * and leaves the active a read-only access.
		 */
		for (i = 0; i < 6; i++) {
			u32 old = READ_ONCE(shadow[i]);
			u32 new = READ_ONCE(active[i]);

			delta = (new - old);
			if (!delta) {
				if (!i)
					goto next;
				continue;
			}

			WRITE_ONCE(shadow[i], new);

			sums[i] += delta;
		}
next:		;
	}