7 files changed, 52 insertions, 5 deletions
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index f6b048902d6c..3ba3e6da13a6 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -150,6 +150,7 @@ struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset,
 struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset,
 					struct cgroup_subsys_state **dst_cssp);
 
+void cgroup_enable_task_cg_lists(void);
 void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags,
 			 struct css_task_iter *it);
 struct task_struct *css_task_iter_next(struct css_task_iter *it);
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 934633a05d20..04c20de66afc 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -40,14 +40,14 @@ static inline bool cpusets_enabled(void)
 
 static inline void cpuset_inc(void)
 {
-	static_branch_inc(&cpusets_pre_enable_key);
-	static_branch_inc(&cpusets_enabled_key);
+	static_branch_inc_cpuslocked(&cpusets_pre_enable_key);
+	static_branch_inc_cpuslocked(&cpusets_enabled_key);
 }
 
 static inline void cpuset_dec(void)
 {
-	static_branch_dec(&cpusets_enabled_key);
-	static_branch_dec(&cpusets_pre_enable_key);
+	static_branch_dec_cpuslocked(&cpusets_enabled_key);
+	static_branch_dec_cpuslocked(&cpusets_pre_enable_key);
 }
 
 extern int cpuset_init(void);
@@ -55,6 +55,8 @@ extern void cpuset_init_smp(void);
 extern void cpuset_force_rebuild(void);
 extern void cpuset_update_active_cpus(void);
 extern void cpuset_wait_for_hotplug(void);
+extern void cpuset_read_lock(void);
+extern void cpuset_read_unlock(void);
 extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask);
 extern void cpuset_cpus_allowed_fallback(struct task_struct *p);
 extern nodemask_t cpuset_mems_allowed(struct task_struct *p);
@@ -176,6 +178,9 @@ static inline void cpuset_update_active_cpus(void)
 
 static inline void cpuset_wait_for_hotplug(void) { }
 
+static inline void cpuset_read_lock(void) { }
+static inline void cpuset_read_unlock(void) { }
+
 static inline void cpuset_cpus_allowed(struct task_struct *p,
 				       struct cpumask *mask)
 {
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 6947516a2d3e..f0edee94834a 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -295,6 +295,11 @@ enum uclamp_id {
 	UCLAMP_CNT
 };
 
+#ifdef CONFIG_SMP
+extern struct root_domain def_root_domain;
+extern struct mutex sched_domains_mutex;
+#endif
+
 struct sched_info {
 #ifdef CONFIG_SCHED_INFO
 	/* Cumulative counters: */
diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h
index 0cb034331cbb..1aff00b65f3c 100644
--- a/include/linux/sched/deadline.h
+++ b/include/linux/sched/deadline.h
@@ -24,3 +24,11 @@ static inline bool dl_time_before(u64 a, u64 b)
 {
 	return (s64)(a - b) < 0;
 }
+
+#ifdef CONFIG_SMP
+
+struct root_domain;
+extern void dl_add_task_root_domain(struct task_struct *p);
+extern void dl_clear_root_domain(struct root_domain *rd);
+
+#endif /* CONFIG_SMP */
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 0497091e40c1..3d90ed8f75f0 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -105,7 +105,11 @@ extern void sched_exec(void);
 #define sched_exec()   {}
 #endif
 
-#define get_task_struct(tsk) do { refcount_inc(&(tsk)->usage); } while(0)
+static inline struct task_struct *get_task_struct(struct task_struct *t)
+{
+	refcount_inc(&t->usage);
+	return t;
+}
 
 extern void __put_task_struct(struct task_struct *t);
 
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 7863bb62d2ab..f341163fedc9 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -150,6 +150,10 @@ static inline struct cpumask *sched_domain_span(struct sched_domain *sd)
 	return to_cpumask(sd->span);
 }
 
+extern void partition_sched_domains_locked(int ndoms_new,
+					   cpumask_var_t doms_new[],
+					   struct sched_domain_attr *dattr_new);
+
 extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 				    struct sched_domain_attr *dattr_new);
 
@@ -195,6 +199,12 @@ extern void set_sched_topology(struct sched_domain_topology_level *tl);
 struct sched_domain_attr;
 
 static inline void
+partition_sched_domains_locked(int ndoms_new, cpumask_var_t doms_new[],
+			       struct sched_domain_attr *dattr_new)
+{
+}
+
+static inline void
 partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 			struct sched_domain_attr *dattr_new)
 {
diff --git a/include/linux/topology.h b/include/linux/topology.h
index 47a3e3c08036..579522ec446c 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -59,6 +59,20 @@ int arch_update_cpu_topology(void);
  */
 #define RECLAIM_DISTANCE 30
 #endif
+
+/*
+ * The following tunable allows platforms to override the default node
+ * reclaim distance (RECLAIM_DISTANCE) if remote memory accesses are
+ * sufficiently fast that the default value actually hurts
+ * performance.
+ *
+ * AMD EPYC machines use this because even though the 2-hop distance
+ * is 32 (3.2x slower than a local memory access) performance actually
+ * *improves* if allowed to reclaim memory and load balance tasks
+ * between NUMA nodes 2-hops apart.
+ */
+extern int __read_mostly node_reclaim_distance;
+
 #ifndef PENALTY_FOR_NODE_WITH_CPUS
 #define PENALTY_FOR_NODE_WITH_CPUS	(1)
 #endif