Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Message-Id: <20190314130706.061994422@infradead.org>
User-Agent: quilt/0.65
Date:   Thu, 14 Mar 2019 14:01:20 +0100
From:   Peter Zijlstra <peterz@infradead.org>
To:     mingo@kernel.org, eranian@google.com, jolsa@redhat.com
Cc:     linux-kernel@vger.kernel.org, tonyj@suse.com,
        nelson.dsouza@intel.com, peterz@infradead.org
Subject: [RFC][PATCH 7/8] perf/x86: Optimize x86_schedule_events()
References: <20190314130113.919278615@infradead.org>
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

Now that cpuc->event_constraint[] is retained, we can avoid calling
get_event_constraints() over and over again.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 arch/x86/events/core.c       |   25 +++++++++++++++++++++----
 arch/x86/events/intel/core.c |    3 ++-
 2 files changed, 23 insertions(+), 5 deletions(-)

--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -844,6 +844,12 @@ int perf_assign_events(struct event_cons
 }
 EXPORT_SYMBOL_GPL(perf_assign_events);
 
+static inline bool is_ht_workaround_active(struct cpu_hw_events *cpuc)
+{
+	return is_ht_workaround_enabled() && !cpuc->is_fake &&
+	       READ_ONCE(cpuc->excl_cntrs->exclusive_present);
+}
+
 int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 {
 	struct event_constraint *c;
@@ -858,8 +864,20 @@ int x86_schedule_events(struct cpu_hw_ev
 		x86_pmu.start_scheduling(cpuc);
 
 	for (i = 0, wmin = X86_PMC_IDX_MAX, wmax = 0; i < n; i++) {
-		c = x86_pmu.get_event_constraints(cpuc, i, cpuc->event_list[i]);
-		cpuc->event_constraint[i] = c;
+		c = cpuc->event_constraint[i];
+
+		/*
+		 * Request constraints for new events; or for those events that
+		 * have a dynamic constraint due to the HT workaround -- for
+		 * those the constraint can change due to scheduling activity
+		 * on the other sibling.
+		 */
+		if (!c || ((c->flags & PERF_X86_EVENT_DYNAMIC) &&
+			   is_ht_workaround_active(cpuc))) {
+
+			c = x86_pmu.get_event_constraints(cpuc, i, cpuc->event_list[i]);
+			cpuc->event_constraint[i] = c;
+		}
 
 		wmin = min(wmin, c->weight);
 		wmax = max(wmax, c->weight);
@@ -903,8 +921,7 @@ int x86_schedule_events(struct cpu_hw_ev
 		 * N/2 counters can be used. This helps with events with
 		 * specific counter constraints.
 		 */
-		if (is_ht_workaround_enabled() && !cpuc->is_fake &&
-		    READ_ONCE(cpuc->excl_cntrs->exclusive_present))
+		if (is_ht_workaround_active(cpuc))
 			gpmax /= 2;
 
 		unsched = perf_assign_events(cpuc->event_constraint, n, wmin,
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2945,7 +2945,8 @@ intel_get_event_constraints(struct cpu_h
 	 * - dynamic constraint: handled by intel_get_excl_constraints()
 	 */
 	c2 = __intel_get_event_constraints(cpuc, idx, event);
-	if (c1 && (c1->flags & PERF_X86_EVENT_DYNAMIC)) {
+	if (c1) {
+	        WARN_ON_ONCE(!(c1->flags & PERF_X86_EVENT_DYNAMIC));
 		bitmap_copy(c1->idxmsk, c2->idxmsk, X86_PMC_IDX_MAX);
 		c1->weight = c2->weight;
 		c2 = c1;