1 files changed, 33 insertions, 8 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index a781dec1cd0b..c49a2585ff7d 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -3,6 +3,8 @@
 
 #include <uapi/linux/sched.h>
 
+#include <linux/sched/prio.h>
+
 
 struct sched_param {
         int sched_priority;
@@ -1077,6 +1079,7 @@ struct sched_entity {
 #endif
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
+        int                     depth;
         struct sched_entity     *parent;
         /* rq on which this entity is (to be) queued: */
         struct cfs_rq           *cfs_rq;
@@ -1470,9 +1473,10 @@ struct task_struct {
         unsigned int numa_scan_period;
         unsigned int numa_scan_period_max;
         int numa_preferred_nid;
-        int numa_migrate_deferred;
         unsigned long numa_migrate_retry;
         u64 node_stamp;                 /* migration stamp  */
+        u64 last_task_numa_placement;
+        u64 last_sum_exec_runtime;
         struct callback_head numa_work;
 
         struct list_head numa_entry;
@@ -1483,15 +1487,22 @@ struct task_struct {
          * Scheduling placement decisions are made based on the these counts.
          * The values remain static for the duration of a PTE scan
          */
-        unsigned long *numa_faults;
+        unsigned long *numa_faults_memory;
         unsigned long total_numa_faults;
 
         /*
          * numa_faults_buffer records faults per node during the current
-         * scan window. When the scan completes, the counts in numa_faults
-         * decay and these values are copied.
+         * scan window. When the scan completes, the counts in
+         * numa_faults_memory decay and these values are copied.
+         */
+        unsigned long *numa_faults_buffer_memory;
+
+        /*
+         * Track the nodes the process was running on when a NUMA hinting
+         * fault was incurred.
          */
-        unsigned long *numa_faults_buffer;
+        unsigned long *numa_faults_cpu;
+        unsigned long *numa_faults_buffer_cpu;
 
         /*
          * numa_faults_locality tracks if faults recorded during the last
@@ -1596,8 +1607,8 @@ extern void task_numa_fault(int last_node, int node, int pages, int flags);
 extern pid_t task_numa_group_id(struct task_struct *p);
 extern void set_numabalancing_state(bool enabled);
 extern void task_numa_free(struct task_struct *p);
-
-extern unsigned int sysctl_numa_balancing_migrate_deferred;
+extern bool should_numa_migrate_memory(struct task_struct *p, struct page *page,
+                                        int src_nid, int dst_cpu);
 #else
 static inline void task_numa_fault(int last_node, int node, int pages,
                                    int flags)
@@ -1613,6 +1624,11 @@ static inline void set_numabalancing_state(bool enabled)
 static inline void task_numa_free(struct task_struct *p)
 {
 }
+static inline bool should_numa_migrate_memory(struct task_struct *p,
+                                struct page *page, int src_nid, int dst_cpu)
+{
+        return true;
+}
 #endif
 
 static inline struct pid *task_pid(struct task_struct *task)
@@ -2080,7 +2096,16 @@ static inline void sched_autogroup_exit(struct signal_struct *sig) { }
 extern bool yield_to(struct task_struct *p, bool preempt);
 extern void set_user_nice(struct task_struct *p, long nice);
 extern int task_prio(const struct task_struct *p);
-extern int task_nice(const struct task_struct *p);
+/**
+ * task_nice - return the nice value of a given task.
+ * @p: the task in question.
+ *
+ * Return: The nice value [ -20 ... 0 ... 19 ].
+ */
+static inline int task_nice(const struct task_struct *p)
+{
+        return PRIO_TO_NICE((p)->static_prio);
+}
 extern int can_nice(const struct task_struct *p, const int nice);
 extern int task_curr(const struct task_struct *p);
 extern int idle_cpu(int cpu);