mm: numa: Add fault driven placement and migration

NOTE: This patch is based on "sched, numa, mm: Add fault driven
	placement and migration policy" but as it throws away all the policy
	to just leave a basic foundation I had to drop the signed-offs-by.

This patch creates a bare-bones method for setting PTEs pte_numa in the
context of the scheduler that when faulted later will be faulted onto the
node the CPU is running on.  In itself this does nothing useful but any
placement policy will fundamentally depend on receiving hints on placement
from fault context and doing something intelligent about it.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Rik van Riel <riel@redhat.com>

5 files changed, 173 insertions, 2 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2d8927f..cad0d09 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1533,6 +1533,19 @@ static void __sched_fork(struct task_struct *p)
 #ifdef CONFIG_PREEMPT_NOTIFIERS
 	INIT_HLIST_HEAD(&p->preempt_notifiers);
 #endif
+
+#ifdef CONFIG_NUMA_BALANCING
+	if (p->mm && atomic_read(&p->mm->mm_users) == 1) {
+		p->mm->numa_next_scan = jiffies;
+		p->mm->numa_scan_seq = 0;
+	}
+
+	p->node_stamp = 0ULL;
+	p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0;
+	p->numa_migrate_seq = p->mm ? p->mm->numa_scan_seq - 1 : 0;
+	p->numa_scan_period = sysctl_numa_balancing_scan_period_min;
+	p->numa_work.next = &p->numa_work;
+#endif /* CONFIG_NUMA_BALANCING */
 }
 
 /*
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 6b800a1..6831abb 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -26,6 +26,8 @@
 #include <linux/slab.h>
 #include <linux/profile.h>
 #include <linux/interrupt.h>
+#include <linux/mempolicy.h>
+#include <linux/task_work.h>
 
 #include <trace/events/sched.h>
 
@@ -776,6 +778,126 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
  * Scheduling class queueing methods:
  */
 
+#ifdef CONFIG_NUMA_BALANCING
+/*
+ * numa task sample period in ms: 5s
+ */
+unsigned int sysctl_numa_balancing_scan_period_min = 5000;
+unsigned int sysctl_numa_balancing_scan_period_max = 5000*16;
+
+static void task_numa_placement(struct task_struct *p)
+{
+	int seq = ACCESS_ONCE(p->mm->numa_scan_seq);
+
+	if (p->numa_scan_seq == seq)
+		return;
+	p->numa_scan_seq = seq;
+
+	/* FIXME: Scheduling placement policy hints go here */
+}
+
+/*
+ * Got a PROT_NONE fault for a page on @node.
+ */
+void task_numa_fault(int node, int pages)
+{
+	struct task_struct *p = current;
+
+	/* FIXME: Allocate task-specific structure for placement policy here */
+
+	task_numa_placement(p);
+}
+
+/*
+ * The expensive part of numa migration is done from task_work context.
+ * Triggered from task_tick_numa().
+ */
+void task_numa_work(struct callback_head *work)
+{
+	unsigned long migrate, next_scan, now = jiffies;
+	struct task_struct *p = current;
+	struct mm_struct *mm = p->mm;
+
+	WARN_ON_ONCE(p != container_of(work, struct task_struct, numa_work));
+
+	work->next = work; /* protect against double add */
+	/*
+	 * Who cares about NUMA placement when they're dying.
+	 *
+	 * NOTE: make sure not to dereference p->mm before this check,
+	 * exit_task_work() happens _after_ exit_mm() so we could be called
+	 * without p->mm even though we still had it when we enqueued this
+	 * work.
+	 */
+	if (p->flags & PF_EXITING)
+		return;
+
+	/*
+	 * Enforce maximal scan/migration frequency..
+	 */
+	migrate = mm->numa_next_scan;
+	if (time_before(now, migrate))
+		return;
+
+	if (p->numa_scan_period == 0)
+		p->numa_scan_period = sysctl_numa_balancing_scan_period_min;
+
+	next_scan = now + 2*msecs_to_jiffies(p->numa_scan_period);
+	if (cmpxchg(&mm->numa_next_scan, migrate, next_scan) != migrate)
+		return;
+
+	ACCESS_ONCE(mm->numa_scan_seq)++;
+	{
+		struct vm_area_struct *vma;
+
+		down_read(&mm->mmap_sem);
+		for (vma = mm->mmap; vma; vma = vma->vm_next) {
+			if (!vma_migratable(vma))
+				continue;
+			change_prot_numa(vma, vma->vm_start, vma->vm_end);
+		}
+		up_read(&mm->mmap_sem);
+	}
+}
+
+/*
+ * Drive the periodic memory faults..
+ */
+void task_tick_numa(struct rq *rq, struct task_struct *curr)
+{
+	struct callback_head *work = &curr->numa_work;
+	u64 period, now;
+
+	/*
+	 * We don't care about NUMA placement if we don't have memory.
+	 */
+	if (!curr->mm || (curr->flags & PF_EXITING) || work->next != work)
+		return;
+
+	/*
+	 * Using runtime rather than walltime has the dual advantage that
+	 * we (mostly) drive the selection from busy threads and that the
+	 * task needs to have done some actual work before we bother with
+	 * NUMA placement.
+	 */
+	now = curr->se.sum_exec_runtime;
+	period = (u64)curr->numa_scan_period * NSEC_PER_MSEC;
+
+	if (now - curr->node_stamp > period) {
+		curr->node_stamp = now;
+
+		if (!time_before(jiffies, curr->mm->numa_next_scan)) {
+			init_task_work(work, task_numa_work); /* TODO: move this into sched_fork() */
+			task_work_add(curr, work, true);
+		}
+	}
+}
+#else
+static void task_tick_numa(struct rq *rq, struct task_struct *curr)
+{
+}
+#endif /* CONFIG_NUMA_BALANCING */
+
 static void
 account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
@@ -4954,6 +5076,9 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
 		cfs_rq = cfs_rq_of(se);
 		entity_tick(cfs_rq, se, queued);
 	}
+
+	if (sched_feat_numa(NUMA))
+		task_tick_numa(rq, curr);
 }
 
 /*
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index eebefca..5fb7aef 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -61,3 +61,10 @@ SCHED_FEAT(TTWU_QUEUE, true)
 SCHED_FEAT(FORCE_SD_OVERLAP, false)
 SCHED_FEAT(RT_RUNTIME_SHARE, true)
 SCHED_FEAT(LB_MIN, false)
+
+/*
+ * Apply the automatic NUMA scheduling policy
+ */
+#ifdef CONFIG_NUMA_BALANCING
+SCHED_FEAT(NUMA,	true)
+#endif
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 7a7db09..ae31c05 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -648,6 +648,12 @@ extern struct static_key sched_feat_keys[__SCHED_FEAT_NR];
 #define sched_feat(x) (sysctl_sched_features & (1UL << __SCHED_FEAT_##x))
 #endif /* SCHED_DEBUG && HAVE_JUMP_LABEL */
 
+#ifdef CONFIG_NUMA_BALANCING
+#define sched_feat_numa(x) sched_feat(x)
+#else
+#define sched_feat_numa(x) (0)
+#endif
+
 static inline u64 global_rt_period(void)
 {
 	return (u64)sysctl_sched_rt_period * NSEC_PER_USEC;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 26f65ea..025e1ae 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -256,9 +256,11 @@ static int min_sched_granularity_ns = 100000;		/* 100 usecs */
 static int max_sched_granularity_ns = NSEC_PER_SEC;	/* 1 second */
 static int min_wakeup_granularity_ns;			/* 0 usecs */
 static int max_wakeup_granularity_ns = NSEC_PER_SEC;	/* 1 second */
+#ifdef CONFIG_SMP
 static int min_sched_tunable_scaling = SCHED_TUNABLESCALING_NONE;
 static int max_sched_tunable_scaling = SCHED_TUNABLESCALING_END-1;
-#endif
+#endif /* CONFIG_SMP */
+#endif /* CONFIG_SCHED_DEBUG */
 
 #ifdef CONFIG_COMPACTION
 static int min_extfrag_threshold;
@@ -301,6 +303,7 @@ static struct ctl_table kern_table[] = {
 		.extra1		= &min_wakeup_granularity_ns,
 		.extra2		= &max_wakeup_granularity_ns,
 	},
+#ifdef CONFIG_SMP
 	{
 		.procname	= "sched_tunable_scaling",
 		.data		= &sysctl_sched_tunable_scaling,
@@ -347,7 +350,24 @@ static struct ctl_table kern_table[] = {
 		.extra1		= &zero,
 		.extra2		= &one,
 	},
-#endif
+#endif /* CONFIG_SMP */
+#ifdef CONFIG_NUMA_BALANCING
+	{
+		.procname	= "numa_balancing_scan_period_min_ms",
+		.data		= &sysctl_numa_balancing_scan_period_min,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "numa_balancing_scan_period_max_ms",
+		.data		= &sysctl_numa_balancing_scan_period_max,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+#endif /* CONFIG_NUMA_BALANCING */
+#endif /* CONFIG_SCHED_DEBUG */
 	{
 		.procname	= "sched_rt_period_us",
 		.data		= &sysctl_sched_rt_period,