3 files changed, 94 insertions, 1 deletions

diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 04c308413a5d..67e1bbf83695 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -443,6 +443,93 @@ TRACE_EVENT(sched_process_hang,
 );
 #endif /* CONFIG_DETECT_HUNG_TASK */
 
+DECLARE_EVENT_CLASS(sched_move_task_template,
+
+        TP_PROTO(struct task_struct *tsk, int src_cpu, int dst_cpu),
+
+        TP_ARGS(tsk, src_cpu, dst_cpu),
+
+        TP_STRUCT__entry(
+                __field( pid_t, pid                     )
+                __field( pid_t, tgid                    )
+                __field( pid_t, ngid                    )
+                __field( int,   src_cpu                 )
+                __field( int,   src_nid                 )
+                __field( int,   dst_cpu                 )
+                __field( int,   dst_nid                 )
+        ),
+
+        TP_fast_assign(
+                __entry->pid            = task_pid_nr(tsk);
+                __entry->tgid           = task_tgid_nr(tsk);
+                __entry->ngid           = task_numa_group_id(tsk);
+                __entry->src_cpu        = src_cpu;
+                __entry->src_nid        = cpu_to_node(src_cpu);
+                __entry->dst_cpu        = dst_cpu;
+                __entry->dst_nid        = cpu_to_node(dst_cpu);
+        ),
+
+        TP_printk("pid=%d tgid=%d ngid=%d src_cpu=%d src_nid=%d dst_cpu=%d dst_nid=%d",
+                        __entry->pid, __entry->tgid, __entry->ngid,
+                        __entry->src_cpu, __entry->src_nid,
+                        __entry->dst_cpu, __entry->dst_nid)
+);
+
+/*
+ * Tracks migration of tasks from one runqueue to another. Can be used to
+ * detect if automatic NUMA balancing is bouncing between nodes
+ */
+DEFINE_EVENT(sched_move_task_template, sched_move_numa,
+        TP_PROTO(struct task_struct *tsk, int src_cpu, int dst_cpu),
+
+        TP_ARGS(tsk, src_cpu, dst_cpu)
+);
+
+DEFINE_EVENT(sched_move_task_template, sched_stick_numa,
+        TP_PROTO(struct task_struct *tsk, int src_cpu, int dst_cpu),
+
+        TP_ARGS(tsk, src_cpu, dst_cpu)
+);
+
+TRACE_EVENT(sched_swap_numa,
+
+        TP_PROTO(struct task_struct *src_tsk, int src_cpu,
+                 struct task_struct *dst_tsk, int dst_cpu),
+
+        TP_ARGS(src_tsk, src_cpu, dst_tsk, dst_cpu),
+
+        TP_STRUCT__entry(
+                __field( pid_t, src_pid                 )
+                __field( pid_t, src_tgid                )
+                __field( pid_t, src_ngid                )
+                __field( int,   src_cpu                 )
+                __field( int,   src_nid                 )
+                __field( pid_t, dst_pid                 )
+                __field( pid_t, dst_tgid                )
+                __field( pid_t, dst_ngid                )
+                __field( int,   dst_cpu                 )
+                __field( int,   dst_nid                 )
+        ),
+
+        TP_fast_assign(
+                __entry->src_pid        = task_pid_nr(src_tsk);
+                __entry->src_tgid       = task_tgid_nr(src_tsk);
+                __entry->src_ngid       = task_numa_group_id(src_tsk);
+                __entry->src_cpu        = src_cpu;
+                __entry->src_nid        = cpu_to_node(src_cpu);
+                __entry->dst_pid        = task_pid_nr(dst_tsk);
+                __entry->dst_tgid       = task_tgid_nr(dst_tsk);
+                __entry->dst_ngid       = task_numa_group_id(dst_tsk);
+                __entry->dst_cpu        = dst_cpu;
+                __entry->dst_nid        = cpu_to_node(dst_cpu);
+        ),
+
+        TP_printk("src_pid=%d src_tgid=%d src_ngid=%d src_cpu=%d src_nid=%d dst_pid=%d dst_tgid=%d dst_ngid=%d dst_cpu=%d dst_nid=%d",
+                        __entry->src_pid, __entry->src_tgid, __entry->src_ngid,
+                        __entry->src_cpu, __entry->src_nid,
+                        __entry->dst_pid, __entry->dst_tgid, __entry->dst_ngid,
+                        __entry->dst_cpu, __entry->dst_nid)
+);
 #endif /* _TRACE_SCHED_H */
 
 /* This part must be outside protection */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 36c951b7eef8..5ae36cc11fe5 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1108,6 +1108,7 @@ int migrate_swap(struct task_struct *cur, struct task_struct *p)
         if (!cpumask_test_cpu(arg.src_cpu, tsk_cpus_allowed(arg.dst_task)))
                 goto out;
 
+        trace_sched_swap_numa(cur, arg.src_cpu, p, arg.dst_cpu);
         ret = stop_two_cpus(arg.dst_cpu, arg.src_cpu, migrate_swap_stop, &arg);
 
 out:
@@ -4603,6 +4604,7 @@ int migrate_task_to(struct task_struct *p, int target_cpu)
 
         /* TODO: This is not properly updating schedstats */
 
+        trace_sched_move_numa(p, curr_cpu, target_cpu);
         return stop_one_cpu(curr_cpu, migration_cpu_stop, &arg);
 }
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index b24b6cfde9aa..867b0a4b0893 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1250,11 +1250,15 @@ static int task_numa_migrate(struct task_struct *p)
         p->numa_scan_period = task_scan_min(p);
 
         if (env.best_task == NULL) {
-                int ret = migrate_task_to(p, env.best_cpu);
+                ret = migrate_task_to(p, env.best_cpu);
+                if (ret != 0)
+                        trace_sched_stick_numa(p, env.src_cpu, env.best_cpu);
                 return ret;
         }
 
         ret = migrate_swap(p, env.best_task);
+        if (ret != 0)
+                trace_sched_stick_numa(p, env.src_cpu, task_cpu(env.best_task));
         put_task_struct(env.best_task);
         return ret;
 }