tracing/filters: Further optimise scalar vs cpumask comparison

Per the previous commits, we now only enter do_filter_scalar_cpumask() with
a mask of weight greater than one. Optimise the equality checks.

Link: https://lkml.kernel.org/r/[e-mail]

Cc: Masami Hiramatsu <[e-mail]>
Cc: Jonathan Corbet <[e-mail]>
Cc: Juri Lelli <[e-mail]>
Cc: Daniel Bristot de Oliveira <[e-mail]>
Cc: Marcelo Tosatti <[e-mail]>
Cc: Leonardo Bras <[e-mail]>
Cc: Frederic Weisbecker <[e-mail]>
Suggested-by: Steven Rostedt <[e-mail]>
Signed-off-by: Valentin Schneider <[e-mail]>
Signed-off-by: Steven Rostedt (Google) <[e-mail]>

kernel/trace/trace_events_filter.c

···
 static inline int
 do_filter_scalar_cpumask(int op, unsigned int cpu, const struct cpumask *mask)
 {
+	/*
+	 * Per the weight-of-one cpumask optimisations, the mask passed in this
+	 * function has a weight >= 2, so it is never equal to a single scalar.
+	 */
+	switch (op) {
+	case OP_EQ:
+		return false;
+	case OP_NE:
+		return true;
+	case OP_BAND:
+		return cpumask_test_cpu(cpu, mask);
+	default:
+		return 0;
+	}
+}
+
+static inline int
+do_filter_cpumask_scalar(int op, const struct cpumask *mask, unsigned int cpu)
+{
 	switch (op) {
 	case OP_EQ:
 		return cpumask_test_cpu(cpu, mask) &&
···
 	const struct cpumask *mask = (event + loc);
 	unsigned int cpu = pred->val;
 
-	/*
-	 * This inverts the usual usage of the function (field is first element,
-	 * user parameter is second), but that's fine because the (scalar, mask)
-	 * operations used are symmetric.
-	 */
-	return do_filter_scalar_cpumask(pred->op, cpu, mask);
+	return do_filter_cpumask_scalar(pred->op, mask, cpu);
 }
 
 /* Filter predicate for COMM. */