sched/numa: Report a NUMA task group ID

It is desirable to model from userspace how the scheduler groups tasks
over time. This patch adds an ID to the numa_group and reports it via
/proc/PID/status.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-45-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>

fs/proc/array.c

@@ -183,6 +183,7 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
 	seq_printf(m,
 		"State:\t%s\n"
 		"Tgid:\t%d\n"
+		"Ngid:\t%d\n"
 		"Pid:\t%d\n"
 		"PPid:\t%d\n"
 		"TracerPid:\t%d\n"
@@ -190,6 +191,7 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
 		"Gid:\t%d\t%d\t%d\t%d\n",
 		get_task_state(p),
 		task_tgid_nr_ns(p, ns),
+		task_numa_group_id(p),
 		pid_nr_ns(pid, ns),
 		ppid, tpid,
 		from_kuid_munged(user_ns, cred->uid),

include/linux/sched.h

@@ -1452,12 +1452,17 @@ struct task_struct {
 
 #ifdef CONFIG_NUMA_BALANCING
 extern void task_numa_fault(int last_node, int node, int pages, bool migrated);
+extern pid_t task_numa_group_id(struct task_struct *p);
 extern void set_numabalancing_state(bool enabled);
 #else
 static inline void task_numa_fault(int last_node, int node, int pages,
 				   bool migrated)
 {
 }
+static inline pid_t task_numa_group_id(struct task_struct *p)
+{
+	return 0;
+}
 static inline void set_numabalancing_state(bool enabled)
 {
 }

kernel/sched/fair.c

@@ -893,12 +893,18 @@ struct numa_group {
 
 	spinlock_t lock; /* nr_tasks, tasks */
 	int nr_tasks;
+	pid_t gid;
 	struct list_head task_list;
 
 	struct rcu_head rcu;
 	atomic_long_t faults[0];
 };
 
+pid_t task_numa_group_id(struct task_struct *p)
+{
+	return p->numa_group ? p->numa_group->gid : 0;
+}
+
 static inline int task_faults_idx(int nid, int priv)
 {
 	return 2 * nid + priv;
@@ -1265,6 +1271,7 @@ static void task_numa_group(struct task_struct *p, int cpupid)
 		atomic_set(&grp->refcount, 1);
 		spin_lock_init(&grp->lock);
 		INIT_LIST_HEAD(&grp->task_list);
+		grp->gid = p->pid;
 
 		for (i = 0; i < 2*nr_node_ids; i++)
 			atomic_long_set(&grp->faults[i], p->numa_faults[i]);