[RFC][PATCH 5/8] perf/x86/intel: Optimize intel_get_excl_constraints()

[Peter Zijlstra]

Avoid the POPCNT by noting we can decrement the weight for each
cleared bit.

Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
---
 arch/x86/events/intel/core.c |   22 +++++++++++++---------
 1 file changed, 13 insertions(+), 9 deletions(-)

--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2838,7 +2838,7 @@ intel_get_excl_constraints(struct cpu_hw
 	struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
 	struct intel_excl_states *xlo;
 	int tid = cpuc->excl_thread_id;
-	int is_excl, i;
+	int is_excl, i, w;
 
 	/*
 	 * validating a group does not require
@@ -2894,36 +2894,40 @@ intel_get_excl_constraints(struct cpu_hw
 	 * SHARED   : sibling counter measuring non-exclusive event
 	 * UNUSED   : sibling counter unused
 	 */
+	w = c->weight;
 	for_each_set_bit(i, c->idxmsk, X86_PMC_IDX_MAX) {
 		/*
 		 * exclusive event in sibling counter
 		 * our corresponding counter cannot be used
 		 * regardless of our event
 		 */
-		if (xlo->state[i] == INTEL_EXCL_EXCLUSIVE)
+		if (xlo->state[i] == INTEL_EXCL_EXCLUSIVE) {
 			__clear_bit(i, c->idxmsk);
+			w--;
+			continue;
+		}
 		/*
 		 * if measuring an exclusive event, sibling
 		 * measuring non-exclusive, then counter cannot
 		 * be used
 		 */
-		if (is_excl && xlo->state[i] == INTEL_EXCL_SHARED)
+		if (is_excl && xlo->state[i] == INTEL_EXCL_SHARED) {
 			__clear_bit(i, c->idxmsk);
+			w--;
+			continue;
+		}
 	}
 
 	/*
-	 * recompute actual bit weight for scheduling algorithm
-	 */
-	c->weight = hweight64(c->idxmsk64);
-
-	/*
 	 * if we return an empty mask, then switch
 	 * back to static empty constraint to avoid
 	 * the cost of freeing later on
 	 */
-	if (c->weight == 0)
+	if (!w)
 		c = &emptyconstraint;
 
+	c->weight = w;
+
 	return c;
 }