@@ 1,44 0,0 @@
-From 183b8ec38f1ec6c1f8419375303bf1d09a2b8369 Mon Sep 17 00:00:00 2001
-From: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
-Date: Fri, 10 Sep 2021 18:18:14 -0700
-Subject: [PATCH 1/6] x86/sched: Decrease further the priorities of SMT
- siblings
-
-When scheduling, it is better to prefer a separate physical core rather
-than the SMT sibling of a high priority core. The existing formula to
-compute priorities takes such fact in consideration. There may exist,
-however, combinations of priorities (i.e., maximum frequencies) in which
-the priority of high-numbered SMT siblings of high-priority cores collides
-with the priority of low-numbered SMT siblings of low-priority cores.
-
-Consider for instance an SMT2 system with CPUs [0, 1] with priority 60 and
-[2, 3] with priority 30(CPUs in brackets are SMT siblings. In such a case,
-the resulting priorities would be [120, 60], [60, 30]. Thus, to ensure
-that CPU2 has higher priority than CPU1, divide the raw priority by the
-squared SMT iterator. The resulting priorities are [120, 30]. [60, 15].
-
-Originally-by: Len Brown <len.brown@intel.com>
-Signed-off-by: Len Brown <len.brown@intel.com>
-Signed-off-by: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
-Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
-Link: https://lkml.kernel.org/r/20210911011819.12184-2-ricardo.neri-calderon@linux.intel.com
----
- arch/x86/kernel/itmt.c | 2 +-
- 1 file changed, 1 insertion(+), 1 deletion(-)
-
-diff --git a/arch/x86/kernel/itmt.c b/arch/x86/kernel/itmt.c
-index 1afbdd1dd777..9ff480e94511 100644
---- a/arch/x86/kernel/itmt.c
-+++ b/arch/x86/kernel/itmt.c
-@@ -198,7 +198,7 @@ void sched_set_itmt_core_prio(int prio, int core_cpu)
- 		 * of the priority chain and only used when
- 		 * all other high priority cpus are out of capacity.
- 		 */
--		smt_prio = prio * smp_num_siblings / i;
-+		smt_prio = prio * smp_num_siblings / (i * i);
- 		per_cpu(sched_core_priority, cpu) = smt_prio;
- 		i++;
- 	}
--- 
-2.33.1
-


@@ 1,93 0,0 @@
-From 16d364ba6ef2aa59b409df70682770f3ed23f7c0 Mon Sep 17 00:00:00 2001
-From: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
-Date: Fri, 10 Sep 2021 18:18:15 -0700
-Subject: [PATCH 2/6] sched/topology: Introduce sched_group::flags
-
-There exist situations in which the load balance needs to know the
-properties of the CPUs in a scheduling group. When using asymmetric
-packing, for instance, the load balancer needs to know not only the
-state of dst_cpu but also of its SMT siblings, if any.
-
-Use the flags of the child scheduling domains to initialize scheduling
-group flags. This will reflect the properties of the CPUs in the
-group.
-
-A subsequent changeset will make use of these new flags. No functional
-changes are introduced.
-
-Originally-by: Peter Zijlstra (Intel) <peterz@infradead.org>
-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/20210911011819.12184-3-ricardo.neri-calderon@linux.intel.com
----
- kernel/sched/sched.h    |  1 +
- kernel/sched/topology.c | 21 ++++++++++++++++++---
- 2 files changed, 19 insertions(+), 3 deletions(-)
-
-diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
-index 198058bb54d7..e5c4d4ddd83a 100644
---- a/kernel/sched/sched.h
-+++ b/kernel/sched/sched.h
-@@ -1808,6 +1808,7 @@ struct sched_group {
- 	unsigned int		group_weight;
- 	struct sched_group_capacity *sgc;
- 	int			asym_prefer_cpu;	/* CPU of highest priority in group */
-+	int			flags;
- 
- 	/*
- 	 * The CPUs this group covers.
-diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
-index 4e8698e62f07..c56faae461d9 100644
---- a/kernel/sched/topology.c
-+++ b/kernel/sched/topology.c
-@@ -716,8 +716,20 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
- 		tmp = sd;
- 		sd = sd->parent;
- 		destroy_sched_domain(tmp);
--		if (sd)
-+		if (sd) {
-+			struct sched_group *sg = sd->groups;
-+
-+			/*
-+			 * sched groups hold the flags of the child sched
-+			 * domain for convenience. Clear such flags since
-+			 * the child is being destroyed.
-+			 */
-+			do {
-+				sg->flags = 0;
-+			} while (sg != sd->groups);
-+
- 			sd->child = NULL;
-+		}
- 	}
- 
- 	for (tmp = sd; tmp; tmp = tmp->parent)
-@@ -916,10 +928,12 @@ build_group_from_child_sched_domain(struct sched_domain *sd, int cpu)
- 		return NULL;
- 
- 	sg_span = sched_group_span(sg);
--	if (sd->child)
-+	if (sd->child) {
- 		cpumask_copy(sg_span, sched_domain_span(sd->child));
--	else
-+		sg->flags = sd->child->flags;
-+	} else {
- 		cpumask_copy(sg_span, sched_domain_span(sd));
-+	}
- 
- 	atomic_inc(&sg->ref);
- 	return sg;
-@@ -1169,6 +1183,7 @@ static struct sched_group *get_group(int cpu, struct sd_data *sdd)
- 	if (child) {
- 		cpumask_copy(sched_group_span(sg), sched_domain_span(child));
- 		cpumask_copy(group_balance_mask(sg), sched_group_span(sg));
-+		sg->flags = child->flags;
- 	} else {
- 		cpumask_set_cpu(cpu, sched_group_span(sg));
- 		cpumask_set_cpu(cpu, group_balance_mask(sg));
--- 
-2.33.1
-


@@ 1,36 0,0 @@
-From 6025643596895695956c27119c6b0bfa40d8035b Mon Sep 17 00:00:00 2001
-From: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
-Date: Fri, 10 Sep 2021 18:18:16 -0700
-Subject: [PATCH 3/6] sched/fair: Optimize checking for group_asym_packing
-
-sched_asmy_prefer() always returns false when called on the local group. By
-checking local_group, we can avoid additional checks and invoking
-sched_asmy_prefer() when it is not needed. No functional changes are
-introduced.
-
-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/20210911011819.12184-4-ricardo.neri-calderon@linux.intel.com
----
- kernel/sched/fair.c | 2 +-
- 1 file changed, 1 insertion(+), 1 deletion(-)
-
-diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
-index 71b30ef31110..e050b1d92efe 100644
---- a/kernel/sched/fair.c
-+++ b/kernel/sched/fair.c
-@@ -8631,7 +8631,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
- 	}
- 
- 	/* Check if dst CPU is idle and preferred to this group */
--	if (env->sd->flags & SD_ASYM_PACKING &&
-+	if (!local_group && env->sd->flags & SD_ASYM_PACKING &&
- 	    env->idle != CPU_NOT_IDLE &&
- 	    sgs->sum_h_nr_running &&
- 	    sched_asym_prefer(env->dst_cpu, group->asym_prefer_cpu)) {
--- 
-2.33.1
-


@@ 1,57 0,0 @@
-From c0d14b57fe0c11b65ce8a1a4a58a48f3f324ca0f Mon Sep 17 00:00:00 2001
-From: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
-Date: Fri, 10 Sep 2021 18:18:17 -0700
-Subject: [PATCH 4/6] sched/fair: Provide update_sg_lb_stats() with sched
- domain statistics
-
-Before deciding to pull tasks when using asymmetric packing of tasks,
-on some architectures (e.g., x86) it is necessary to know not only the
-state of dst_cpu but also of its SMT siblings. The decision to classify
-a candidate busiest group as group_asym_packing is done in
-update_sg_lb_stats(). Give this function access to the scheduling domain
-statistics, which contains the statistics of the local group.
-
-Originally-by: Peter Zijlstra (Intel) <peterz@infradead.org>
-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/20210911011819.12184-5-ricardo.neri-calderon@linux.intel.com
----
- kernel/sched/fair.c | 5 +++--
- 1 file changed, 3 insertions(+), 2 deletions(-)
-
-diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
-index e050b1d92efe..2e8ef337c7d4 100644
---- a/kernel/sched/fair.c
-+++ b/kernel/sched/fair.c
-@@ -8579,6 +8579,7 @@ group_type group_classify(unsigned int imbalance_pct,
-  * @sg_status: Holds flag indicating the status of the sched_group
-  */
- static inline void update_sg_lb_stats(struct lb_env *env,
-+				      struct sd_lb_stats *sds,
- 				      struct sched_group *group,
- 				      struct sg_lb_stats *sgs,
- 				      int *sg_status)
-@@ -8587,7 +8588,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
- 
- 	memset(sgs, 0, sizeof(*sgs));
- 
--	local_group = cpumask_test_cpu(env->dst_cpu, sched_group_span(group));
-+	local_group = group == sds->local;
- 
- 	for_each_cpu_and(i, sched_group_span(group), env->cpus) {
- 		struct rq *rq = cpu_rq(i);
-@@ -9150,7 +9151,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
- 				update_group_capacity(env->sd, env->dst_cpu);
- 		}
- 
--		update_sg_lb_stats(env, sg, sgs, &sg_status);
-+		update_sg_lb_stats(env, sds, sg, sgs, &sg_status);
- 
- 		if (local_group)
- 			goto next_group;
--- 
-2.33.1
-


@@ 1,68 0,0 @@
-From aafc917a3c31dcc76cb0279cd7617dda11b15f2a Mon Sep 17 00:00:00 2001
-From: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
-Date: Fri, 10 Sep 2021 18:18:18 -0700
-Subject: [PATCH 5/6] sched/fair: Carve out logic to mark a group for
- asymmetric packing
-
-Create a separate function, sched_asym(). A subsequent changeset will
-introduce logic to deal with SMT in conjunction with asmymmetric
-packing. Such logic will need the statistics of the scheduling
-group provided as argument. Update them before calling sched_asym().
-
-Co-developed-by: Peter Zijlstra (Intel) <peterz@infradead.org>
-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/20210911011819.12184-6-ricardo.neri-calderon@linux.intel.com
----
- kernel/sched/fair.c | 20 +++++++++++++-------
- 1 file changed, 13 insertions(+), 7 deletions(-)
-
-diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
-index 2e8ef337c7d4..1c8b5fa58c23 100644
---- a/kernel/sched/fair.c
-+++ b/kernel/sched/fair.c
-@@ -8571,6 +8571,13 @@ group_type group_classify(unsigned int imbalance_pct,
- 	return group_has_spare;
- }
- 
-+static inline bool
-+sched_asym(struct lb_env *env, struct sd_lb_stats *sds,  struct sg_lb_stats *sgs,
-+	   struct sched_group *group)
-+{
-+	return sched_asym_prefer(env->dst_cpu, group->asym_prefer_cpu);
-+}
-+
- /**
-  * update_sg_lb_stats - Update sched_group's statistics for load balancing.
-  * @env: The load balancing environment.
-@@ -8631,18 +8638,17 @@ static inline void update_sg_lb_stats(struct lb_env *env,
- 		}
- 	}
- 
-+	sgs->group_capacity = group->sgc->capacity;
-+
-+	sgs->group_weight = group->group_weight;
-+
- 	/* Check if dst CPU is idle and preferred to this group */
- 	if (!local_group && env->sd->flags & SD_ASYM_PACKING &&
--	    env->idle != CPU_NOT_IDLE &&
--	    sgs->sum_h_nr_running &&
--	    sched_asym_prefer(env->dst_cpu, group->asym_prefer_cpu)) {
-+	    env->idle != CPU_NOT_IDLE && sgs->sum_h_nr_running &&
-+	    sched_asym(env, sds, sgs, group)) {
- 		sgs->group_asym_packing = 1;
- 	}
- 
--	sgs->group_capacity = group->sgc->capacity;
--
--	sgs->group_weight = group->group_weight;
--
- 	sgs->group_type = group_classify(env->sd->imbalance_pct, group, sgs);
- 
- 	/* Computing avg_load makes sense only when group is overloaded */
--- 
-2.33.1
-


@@ 1,143 0,0 @@
-From 4006a72bdd93b1ffedc2bd8646dee18c822a2c26 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 6/6] 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
----
- kernel/sched/fair.c | 92 +++++++++++++++++++++++++++++++++++++++++++++
- 1 file changed, 92 insertions(+)
-
-diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
-index 1c8b5fa58c23..c50ae23013dc 100644
---- a/kernel/sched/fair.c
-+++ b/kernel/sched/fair.c
-@@ -8571,10 +8571,96 @@ 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);
- }
- 
-@@ -9580,6 +9666,12 @@ 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:
- 			/*
--- 
-2.33.1
-