sched/numa: Use {cpu, pid} to create task groups for shared faults

While parallel applications tend to align their data on the cache
boundary, they tend not to align on the page or THP boundary.
Consequently tasks that partition their data can still "false-share"
pages presenting a problem for optimal NUMA placement.

This patch uses NUMA hinting faults to chain tasks together into
numa_groups. As well as storing the NID a task was running on when
accessing a page a truncated representation of the faulting PID is
stored. If subsequent faults are from different PIDs it is reasonable
to assume that those two tasks share a page and are candidates for
being grouped together. Note that this patch makes no scheduling
decisions based on the grouping information.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
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>
Link: http://lkml.kernel.org/r/1381141781-10992-44-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>

3 files changed, 160 insertions, 13 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 1fe59da280e3..51092d5cc64c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1733,6 +1733,9 @@ static void __sched_fork(struct task_struct *p)
 	p->numa_work.next = &p->numa_work;
 	p->numa_faults = NULL;
 	p->numa_faults_buffer = NULL;
+
+	INIT_LIST_HEAD(&p->numa_entry);
+	p->numa_group = NULL;
 #endif /* CONFIG_NUMA_BALANCING */
 }
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index dbe0f628efa3..85565053a6ed 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -888,6 +888,17 @@ static unsigned int task_scan_max(struct task_struct *p)
  */
 unsigned int sysctl_numa_balancing_settle_count __read_mostly = 4;
 
+struct numa_group {
+	atomic_t refcount;
+
+	spinlock_t lock; /* nr_tasks, tasks */
+	int nr_tasks;
+	struct list_head task_list;
+
+	struct rcu_head rcu;
+	atomic_long_t faults[0];
+};
+
 static inline int task_faults_idx(int nid, int priv)
 {
 	return 2 * nid + priv;
@@ -1182,7 +1193,10 @@ static void task_numa_placement(struct task_struct *p)
 		int priv, i;
 
 		for (priv = 0; priv < 2; priv++) {
+			long diff;
+
 			i = task_faults_idx(nid, priv);
+			diff = -p->numa_faults[i];
 
 			/* Decay existing window, copy faults since last scan */
 			p->numa_faults[i] >>= 1;
@@ -1190,6 +1204,11 @@ static void task_numa_placement(struct task_struct *p)
 			p->numa_faults_buffer[i] = 0;
 
 			faults += p->numa_faults[i];
+			diff += p->numa_faults[i];
+			if (p->numa_group) {
+				/* safe because we can only change our own group */
+				atomic_long_add(diff, &p->numa_group->faults[i]);
+			}
 		}
 
 		if (faults > max_faults) {
@@ -1207,6 +1226,131 @@ static void task_numa_placement(struct task_struct *p)
 	}
 }
 
+static inline int get_numa_group(struct numa_group *grp)
+{
+	return atomic_inc_not_zero(&grp->refcount);
+}
+
+static inline void put_numa_group(struct numa_group *grp)
+{
+	if (atomic_dec_and_test(&grp->refcount))
+		kfree_rcu(grp, rcu);
+}
+
+static void double_lock(spinlock_t *l1, spinlock_t *l2)
+{
+	if (l1 > l2)
+		swap(l1, l2);
+
+	spin_lock(l1);
+	spin_lock_nested(l2, SINGLE_DEPTH_NESTING);
+}
+
+static void task_numa_group(struct task_struct *p, int cpupid)
+{
+	struct numa_group *grp, *my_grp;
+	struct task_struct *tsk;
+	bool join = false;
+	int cpu = cpupid_to_cpu(cpupid);
+	int i;
+
+	if (unlikely(!p->numa_group)) {
+		unsigned int size = sizeof(struct numa_group) +
+				    2*nr_node_ids*sizeof(atomic_long_t);
+
+		grp = kzalloc(size, GFP_KERNEL | __GFP_NOWARN);
+		if (!grp)
+			return;
+
+		atomic_set(&grp->refcount, 1);
+		spin_lock_init(&grp->lock);
+		INIT_LIST_HEAD(&grp->task_list);
+
+		for (i = 0; i < 2*nr_node_ids; i++)
+			atomic_long_set(&grp->faults[i], p->numa_faults[i]);
+
+		list_add(&p->numa_entry, &grp->task_list);
+		grp->nr_tasks++;
+		rcu_assign_pointer(p->numa_group, grp);
+	}
+
+	rcu_read_lock();
+	tsk = ACCESS_ONCE(cpu_rq(cpu)->curr);
+
+	if (!cpupid_match_pid(tsk, cpupid))
+		goto unlock;
+
+	grp = rcu_dereference(tsk->numa_group);
+	if (!grp)
+		goto unlock;
+
+	my_grp = p->numa_group;
+	if (grp == my_grp)
+		goto unlock;
+
+	/*
+	 * Only join the other group if its bigger; if we're the bigger group,
+	 * the other task will join us.
+	 */
+	if (my_grp->nr_tasks > grp->nr_tasks)
+		goto unlock;
+
+	/*
+	 * Tie-break on the grp address.
+	 */
+	if (my_grp->nr_tasks == grp->nr_tasks && my_grp > grp)
+		goto unlock;
+
+	if (!get_numa_group(grp))
+		goto unlock;
+
+	join = true;
+
+unlock:
+	rcu_read_unlock();
+
+	if (!join)
+		return;
+
+	for (i = 0; i < 2*nr_node_ids; i++) {
+		atomic_long_sub(p->numa_faults[i], &my_grp->faults[i]);
+		atomic_long_add(p->numa_faults[i], &grp->faults[i]);
+	}
+
+	double_lock(&my_grp->lock, &grp->lock);
+
+	list_move(&p->numa_entry, &grp->task_list);
+	my_grp->nr_tasks--;
+	grp->nr_tasks++;
+
+	spin_unlock(&my_grp->lock);
+	spin_unlock(&grp->lock);
+
+	rcu_assign_pointer(p->numa_group, grp);
+
+	put_numa_group(my_grp);
+}
+
+void task_numa_free(struct task_struct *p)
+{
+	struct numa_group *grp = p->numa_group;
+	int i;
+
+	if (grp) {
+		for (i = 0; i < 2*nr_node_ids; i++)
+			atomic_long_sub(p->numa_faults[i], &grp->faults[i]);
+
+		spin_lock(&grp->lock);
+		list_del(&p->numa_entry);
+		grp->nr_tasks--;
+		spin_unlock(&grp->lock);
+		rcu_assign_pointer(p->numa_group, NULL);
+		put_numa_group(grp);
+	}
+
+	kfree(p->numa_faults);
+}
+
 /*
  * Got a PROT_NONE fault for a page on @node.
  */
@@ -1222,15 +1366,6 @@ void task_numa_fault(int last_cpupid, int node, int pages, bool migrated)
 	if (!p->mm)
 		return;
 
-	/*
-	 * First accesses are treated as private, otherwise consider accesses
-	 * to be private if the accessing pid has not changed
-	 */
-	if (!cpupid_pid_unset(last_cpupid))
-		priv = ((p->pid & LAST__PID_MASK) == cpupid_to_pid(last_cpupid));
-	else
-		priv = 1;
-
 	/* Allocate buffer to track faults on a per-node basis */
 	if (unlikely(!p->numa_faults)) {
 		int size = sizeof(*p->numa_faults) * 2 * nr_node_ids;
@@ -1245,6 +1380,18 @@ void task_numa_fault(int last_cpupid, int node, int pages, bool migrated)
 	}
 
 	/*
+	 * First accesses are treated as private, otherwise consider accesses
+	 * to be private if the accessing pid has not changed
+	 */
+	if (unlikely(last_cpupid == (-1 & LAST_CPUPID_MASK))) {
+		priv = 1;
+	} else {
+		priv = cpupid_match_pid(p, last_cpupid);
+		if (!priv)
+			task_numa_group(p, last_cpupid);
+	}
+
+	/*
 	 * If pages are properly placed (did not migrate) then scan slower.
 	 * This is reset periodically in case of phase changes
 	 */
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 691e96964dcc..8037b10a256f 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -559,10 +559,7 @@ static inline u64 rq_clock_task(struct rq *rq)
 #ifdef CONFIG_NUMA_BALANCING
 extern int migrate_task_to(struct task_struct *p, int cpu);
 extern int migrate_swap(struct task_struct *, struct task_struct *);
-static inline void task_numa_free(struct task_struct *p)
-{
-	kfree(p->numa_faults);
-}
+extern void task_numa_free(struct task_struct *p);
 #else /* CONFIG_NUMA_BALANCING */
 static inline void task_numa_free(struct task_struct *p)
 {