---

yaml
---
r: 344796
b: refs/heads/master
c: cbee9f8
h: refs/heads/master
v: v3

[refs]

@@ -1,2 +1,2 @@
 ---
-refs/heads/master: a720094ded8cbb303111035be91858011d2eac71
+refs/heads/master: cbee9f88ec1b8dd6b58f25f54e4f52c82ed77690

trunk/arch/sh/mm/Kconfig

@@ -111,6 +111,7 @@ config VSYSCALL
 config NUMA
 	bool "Non Uniform Memory Access (NUMA) Support"
 	depends on MMU && SYS_SUPPORTS_NUMA && EXPERIMENTAL
+	select ARCH_WANT_NUMA_VARIABLE_LOCALITY
 	default n
 	help
 	  Some SH systems have many various memories scattered around

trunk/arch/x86/Kconfig

@@ -22,6 +22,8 @@ config X86
 	def_bool y
 	select HAVE_AOUT if X86_32
 	select HAVE_UNSTABLE_SCHED_CLOCK
+	select ARCH_SUPPORTS_NUMA_BALANCING
+	select ARCH_WANTS_PROT_NUMA_PROT_NONE
 	select HAVE_IDE
 	select HAVE_OPROFILE
 	select HAVE_PCSPKR_PLATFORM

trunk/include/linux/mm_types.h

@@ -397,6 +397,17 @@ struct mm_struct {
 #endif
 #ifdef CONFIG_CPUMASK_OFFSTACK
 	struct cpumask cpumask_allocation;
+#endif
+#ifdef CONFIG_NUMA_BALANCING
+	/*
+	 * numa_next_scan is the next time when the PTEs will me marked
+	 * pte_numa to gather statistics and migrate pages to new nodes
+	 * if necessary
+	 */
+	unsigned long numa_next_scan;
+
+	/* numa_scan_seq prevents two threads setting pte_numa */
+	int numa_scan_seq;
 #endif
 	struct uprobes_state uprobes_state;
 };

trunk/include/linux/sched.h

@@ -1479,6 +1479,14 @@ struct task_struct {
 	short il_next;
 	short pref_node_fork;
 #endif
+#ifdef CONFIG_NUMA_BALANCING
+	int numa_scan_seq;
+	int numa_migrate_seq;
+	unsigned int numa_scan_period;
+	u64 node_stamp;			/* migration stamp  */
+	struct callback_head numa_work;
+#endif /* CONFIG_NUMA_BALANCING */
+
 	struct rcu_head rcu;
 
 	/*
@@ -1553,6 +1561,14 @@ struct task_struct {
 /* Future-safe accessor for struct task_struct's cpus_allowed. */
 #define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed)
 
+#ifdef CONFIG_NUMA_BALANCING
+extern void task_numa_fault(int node, int pages);
+#else
+static inline void task_numa_fault(int node, int pages)
+{
+}
+#endif
+
 /*
  * Priority of a process goes from 0..MAX_PRIO-1, valid RT
  * priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL/SCHED_BATCH
@@ -1990,6 +2006,10 @@ enum sched_tunable_scaling {
 };
 extern enum sched_tunable_scaling sysctl_sched_tunable_scaling;
 
+extern unsigned int sysctl_numa_balancing_scan_period_min;
+extern unsigned int sysctl_numa_balancing_scan_period_max;
+extern unsigned int sysctl_numa_balancing_settle_count;
+
 #ifdef CONFIG_SCHED_DEBUG
 extern unsigned int sysctl_sched_migration_cost;
 extern unsigned int sysctl_sched_nr_migrate;

trunk/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 */
 }
 
 /*

trunk/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);
 }
 
 /*

trunk/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

trunk/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;

trunk/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,

trunk/mm/huge_memory.c

@@ -1046,6 +1046,7 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	 */
 	split_huge_page(page);
 	put_page(page);
+
 	return 0;
 
 clear_pmdnuma:
@@ -1060,8 +1061,10 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 out_unlock:
 	spin_unlock(&mm->page_table_lock);
-	if (page)
+	if (page) {
 		put_page(page);
+		task_numa_fault(numa_node_id(), HPAGE_PMD_NR);
+	}
 	return 0;
 }
 

trunk/mm/memory.c

@@ -3454,7 +3454,8 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 {
 	struct page *page = NULL;
 	spinlock_t *ptl;
-	int current_nid, target_nid;
+	int current_nid = -1;
+	int target_nid;
 
 	/*
 	* The "pte" at this point cannot be used safely without
@@ -3501,6 +3502,7 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		current_nid = target_nid;
 
 out:
+	task_numa_fault(current_nid, 1);
 	return 0;
 }
 
@@ -3537,6 +3539,7 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	for (addr = _addr + offset; addr < _addr + PMD_SIZE; pte++, addr += PAGE_SIZE) {
 		pte_t pteval = *pte;
 		struct page *page;
+		int curr_nid;
 		if (!pte_present(pteval))
 			continue;
 		if (!pte_numa(pteval))
@@ -3554,6 +3557,15 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		page = vm_normal_page(vma, addr, pteval);
 		if (unlikely(!page))
 			continue;
+		/* only check non-shared pages */
+		if (unlikely(page_mapcount(page) != 1))
+			continue;
+		pte_unmap_unlock(pte, ptl);
+
+		curr_nid = page_to_nid(page);
+		task_numa_fault(curr_nid, 1);
+
+		pte = pte_offset_map_lock(mm, pmdp, addr, &ptl);
 	}
 	pte_unmap_unlock(orig_pte, ptl);