c43193995b0b1a9fb0ccb9d17568e3e2c89689c6689a9d7977f0aa04.patch

From fe8613546614bed3f089a1fce3411ada03620f5e Mon Sep 17 00:00:00 2001
From: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
Date: Fri, 10 Sep 2021 18:18:19 -0700
Subject: [PATCH] BACKPORT: FROMGIT: sched/fair: Consider SMT in ASYM_PACKING
 load balance

When deciding to pull tasks in ASYM_PACKING, it is necessary not only to
check for the idle state of the destination CPU, dst_cpu, but also of
its SMT siblings.

If dst_cpu is idle but its SMT siblings are busy, performance suffers
if it pulls tasks from a medium priority CPU that does not have SMT
siblings.

Implement asym_smt_can_pull_tasks() to inspect the state of the SMT
siblings of both dst_cpu and the CPUs in the candidate busiest group.

Signed-off-by: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Reviewed-by: Len Brown <len.brown@intel.com>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20210911011819.12184-7-ricardo.neri-calderon@linux.intel.com
Change-Id: Ib94f2ab5dd21ae7ceb81c800d9c6724948a28ea2

(cherry picked from commit eac6f3841f1dac7b6f43002056b63f44cc1f1543
git://git.kernel.org/pub/scm/linux/kernel/git/peterz/queue.git master)

Conflicts:
      kernel/sched/fair.c

Backport Notes:
      minor conflict due to code overlap in API static bool update_nohz_stats(struct rq *rq, bool force) and new function
      asym_smt_can_pull_tasks

      Added the below three lines:

             return false;
     #endif
     }

BUG=b:179699891
TEST=basic boot on brya and check /proc/sys/kernel/sched_itmt_enabled
     should be 1
TEST=spin N+1 threads where N = number of physical cores - expect
        N threads to run on N physical cores and the N+1st thread
        to run on an atom CPU

Signed-off-by: George D Sworo <george.d.sworo@intel.com>
Change-Id: I9b962caa959262eec8f960e40769e41761fa84c3
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/third_party/kernel/+/3174725
Reviewed-by: Alex Levin <levinale@google.com>
---
 kernel/sched/fair.c | 92 +++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 92 insertions(+)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -8604,10 +8604,96 @@ group_type group_classify(unsigned int imbalance_pct,
 	return group_has_spare;
 }
 
+/**
+ * asym_smt_can_pull_tasks - Check whether the load balancing CPU can pull tasks
+ * @dst_cpu:	Destination CPU of the load balancing
+ * @sds:	Load-balancing data with statistics of the local group
+ * @sgs:	Load-balancing statistics of the candidate busiest group
+ * @sg:		The candidate busiest group
+ *
+ * Check the state of the SMT siblings of both @sds::local and @sg and decide
+ * if @dst_cpu can pull tasks.
+ *
+ * If @dst_cpu does not have SMT siblings, it can pull tasks if two or more of
+ * the SMT siblings of @sg are busy. If only one CPU in @sg is busy, pull tasks
+ * only if @dst_cpu has higher priority.
+ *
+ * If both @dst_cpu and @sg have SMT siblings, and @sg has exactly one more
+ * busy CPU than @sds::local, let @dst_cpu pull tasks if it has higher priority.
+ * Bigger imbalances in the number of busy CPUs will be dealt with in
+ * update_sd_pick_busiest().
+ *
+ * If @sg does not have SMT siblings, only pull tasks if all of the SMT siblings
+ * of @dst_cpu are idle and @sg has lower priority.
+ */
+static bool asym_smt_can_pull_tasks(int dst_cpu, struct sd_lb_stats *sds,
+				    struct sg_lb_stats *sgs,
+				    struct sched_group *sg)
+{
+#ifdef CONFIG_SCHED_SMT
+	bool local_is_smt, sg_is_smt;
+	int sg_busy_cpus;
+
+	local_is_smt = sds->local->flags & SD_SHARE_CPUCAPACITY;
+	sg_is_smt = sg->flags & SD_SHARE_CPUCAPACITY;
+
+	sg_busy_cpus = sgs->group_weight - sgs->idle_cpus;
+
+	if (!local_is_smt) {
+		/*
+		 * If we are here, @dst_cpu is idle and does not have SMT
+		 * siblings. Pull tasks if candidate group has two or more
+		 * busy CPUs.
+		 */
+		if (sg_busy_cpus >= 2) /* implies sg_is_smt */
+			return true;
+
+		/*
+		 * @dst_cpu does not have SMT siblings. @sg may have SMT
+		 * siblings and only one is busy. In such case, @dst_cpu
+		 * can help if it has higher priority and is idle (i.e.,
+		 * it has no running tasks).
+		 */
+		return sched_asym_prefer(dst_cpu, sg->asym_prefer_cpu);
+	}
+
+	/* @dst_cpu has SMT siblings. */
+
+	if (sg_is_smt) {
+		int local_busy_cpus = sds->local->group_weight -
+				      sds->local_stat.idle_cpus;
+		int busy_cpus_delta = sg_busy_cpus - local_busy_cpus;
+
+		if (busy_cpus_delta == 1)
+			return sched_asym_prefer(dst_cpu, sg->asym_prefer_cpu);
+
+		return false;
+	}
+
+	/*
+	 * @sg does not have SMT siblings. Ensure that @sds::local does not end
+	 * up with more than one busy SMT sibling and only pull tasks if there
+	 * are not busy CPUs (i.e., no CPU has running tasks).
+	 */
+	if (!sds->local_stat.sum_nr_running)
+		return sched_asym_prefer(dst_cpu, sg->asym_prefer_cpu);
+
+	return false;
+#else
+	/* Always return false so that callers deal with non-SMT cases. */
+	return false;
+#endif
+}
+
 static inline bool
 sched_asym(struct lb_env *env, struct sd_lb_stats *sds,  struct sg_lb_stats *sgs,
 	   struct sched_group *group)
 {
+	/* Only do SMT checks if either local or candidate have SMT siblings */
+	if ((sds->local->flags & SD_SHARE_CPUCAPACITY) ||
+	    (group->flags & SD_SHARE_CPUCAPACITY))
+		return asym_smt_can_pull_tasks(env->dst_cpu, sds, sgs, group);
+
 	return sched_asym_prefer(env->dst_cpu, group->asym_prefer_cpu);
 }
 
@@ -9613,6 +9699,12 @@ static struct rq *find_busiest_queue(struct lb_env *env,
 		    nr_running == 1)
 			continue;
 
+		/* Make sure we only pull tasks from a CPU of lower priority */
+		if ((env->sd->flags & SD_ASYM_PACKING) &&
+		    sched_asym_prefer(i, env->dst_cpu) &&
+		    nr_running == 1)
+			continue;
+
 		switch (env->migration_type) {
 		case migrate_load:
 			/*
-- 
2.33.0.882.g93a45727a2-goog