Merge tag 'balancenuma-v11' of git://git.kernel.org/pub/scm/linux/kernel/git/mel/linux-balancenuma

Pull Automatic NUMA Balancing bare-bones from Mel Gorman:
 "There are three implementations for NUMA balancing, this tree
  (balancenuma), numacore which has been developed in tip/master and
  autonuma which is in aa.git.

  In almost all respects balancenuma is the dumbest of the three because
  its main impact is on the VM side with no attempt to be smart about
  scheduling.  In the interest of getting the ball rolling, it would be
  desirable to see this much merged for 3.8 with the view to building
  scheduler smarts on top and adapting the VM where required for 3.9.

  The most recent set of comparisons available from different people are

    mel:    https://lkml.org/lkml/2012/12/9/108
    mingo:  https://lkml.org/lkml/2012/12/7/331
    tglx:   https://lkml.org/lkml/2012/12/10/437
    srikar: https://lkml.org/lkml/2012/12/10/397

  The results are a mixed bag.  In my own tests, balancenuma does
  reasonably well.  It's dumb as rocks and does not regress against
  mainline.  On the other hand, Ingo's tests shows that balancenuma is
  incapable of converging for this workloads driven by perf which is bad
  but is potentially explained by the lack of scheduler smarts.  Thomas'
  results show balancenuma improves on mainline but falls far short of
  numacore or autonuma.  Srikar's results indicate we all suffer on a
  large machine with imbalanced node sizes.

  My own testing showed that recent numacore results have improved
  dramatically, particularly in the last week but not universally.
  We've butted heads heavily on system CPU usage and high levels of
  migration even when it shows that overall performance is better.
  There are also cases where it regresses.  Of interest is that for
  specjbb in some configurations it will regress for lower numbers of
  warehouses and show gains for higher numbers which is not reported by
  the tool by default and sometimes missed in treports.  Recently I
  reported for numacore that the JVM was crashing with
  NullPointerExceptions but currently it's unclear what the source of
  this problem is.  Initially I thought it was in how numacore batch
  handles PTEs but I'm no longer think this is the case.  It's possible
  numacore is just able to trigger it due to higher rates of migration.

  These reports were quite late in the cycle so I/we would like to start
  with this tree as it contains much of the code we can agree on and has
  not changed significantly over the last 2-3 weeks."

* tag 'balancenuma-v11' of git://git.kernel.org/pub/scm/linux/kernel/git/mel/linux-balancenuma: (50 commits)
  mm/rmap, migration: Make rmap_walk_anon() and try_to_unmap_anon() more scalable
  mm/rmap: Convert the struct anon_vma::mutex to an rwsem
  mm: migrate: Account a transhuge page properly when rate limiting
  mm: numa: Account for failed allocations and isolations as migration failures
  mm: numa: Add THP migration for the NUMA working set scanning fault case build fix
  mm: numa: Add THP migration for the NUMA working set scanning fault case.
  mm: sched: numa: Delay PTE scanning until a task is scheduled on a new node
  mm: sched: numa: Control enabling and disabling of NUMA balancing if !SCHED_DEBUG
  mm: sched: numa: Control enabling and disabling of NUMA balancing
  mm: sched: Adapt the scanning rate if a NUMA hinting fault does not migrate
  mm: numa: Use a two-stage filter to restrict pages being migrated for unlikely task<->node relationships
  mm: numa: migrate: Set last_nid on newly allocated page
  mm: numa: split_huge_page: Transfer last_nid on tail page
  mm: numa: Introduce last_nid to the page frame
  sched: numa: Slowly increase the scanning period as NUMA faults are handled
  mm: numa: Rate limit setting of pte_numa if node is saturated
  mm: numa: Rate limit the amount of memory that is migrated between nodes
  mm: numa: Structures for Migrate On Fault per NUMA migration rate limiting
  mm: numa: Migrate pages handled during a pmd_numa hinting fault
  mm: numa: Migrate on reference policy
  ...

6 files changed, 352 insertions, 17 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index 3c31e87..115d6c2 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -823,6 +823,9 @@ struct mm_struct *dup_mm(struct task_struct *tsk)
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	mm->pmd_huge_pte = NULL;
 #endif
+#ifdef CONFIG_NUMA_BALANCING
+	mm->first_nid = NUMA_PTE_SCAN_INIT;
+#endif
 	if (!mm_init(mm, tsk))
 		goto fail_nomem;
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 0533496..c1fb821 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -193,23 +193,10 @@ static void sched_feat_disable(int i) { };
 static void sched_feat_enable(int i) { };
 #endif /* HAVE_JUMP_LABEL */
 
-static ssize_t
-sched_feat_write(struct file *filp, const char __user *ubuf,
-		size_t cnt, loff_t *ppos)
+static int sched_feat_set(char *cmp)
 {
-	char buf[64];
-	char *cmp;
-	int neg = 0;
 	int i;
-
-	if (cnt > 63)
-		cnt = 63;
-
-	if (copy_from_user(&buf, ubuf, cnt))
-		return -EFAULT;
-
-	buf[cnt] = 0;
-	cmp = strstrip(buf);
+	int neg = 0;
 
 	if (strncmp(cmp, "NO_", 3) == 0) {
 		neg = 1;
@@ -229,6 +216,27 @@ sched_feat_write(struct file *filp, const char __user *ubuf,
 		}
 	}
 
+	return i;
+}
+
+static ssize_t
+sched_feat_write(struct file *filp, const char __user *ubuf,
+		size_t cnt, loff_t *ppos)
+{
+	char buf[64];
+	char *cmp;
+	int i;
+
+	if (cnt > 63)
+		cnt = 63;
+
+	if (copy_from_user(&buf, ubuf, cnt))
+		return -EFAULT;
+
+	buf[cnt] = 0;
+	cmp = strstrip(buf);
+
+	i = sched_feat_set(cmp);
 	if (i == __SCHED_FEAT_NR)
 		return -EINVAL;
 
@@ -1560,7 +1568,40 @@ 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_next_reset = 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_delay;
+	p->numa_work.next = &p->numa_work;
+#endif /* CONFIG_NUMA_BALANCING */
+}
+
+#ifdef CONFIG_NUMA_BALANCING
+#ifdef CONFIG_SCHED_DEBUG
+void set_numabalancing_state(bool enabled)
+{
+	if (enabled)
+		sched_feat_set("NUMA");
+	else
+		sched_feat_set("NO_NUMA");
+}
+#else
+__read_mostly bool numabalancing_enabled;
+
+void set_numabalancing_state(bool enabled)
+{
+	numabalancing_enabled = enabled;
 }
+#endif /* CONFIG_SCHED_DEBUG */
+#endif /* CONFIG_NUMA_BALANCING */
 
 /*
  * fork()/clone()-time setup:
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 756f9f9..9af5af9 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -26,6 +26,9 @@
 #include <linux/slab.h>
 #include <linux/profile.h>
 #include <linux/interrupt.h>
+#include <linux/mempolicy.h>
+#include <linux/migrate.h>
+#include <linux/task_work.h>
 
 #include <trace/events/sched.h>
 
@@ -774,6 +777,227 @@ 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
+ */
+unsigned int sysctl_numa_balancing_scan_period_min = 100;
+unsigned int sysctl_numa_balancing_scan_period_max = 100*50;
+unsigned int sysctl_numa_balancing_scan_period_reset = 100*600;
+
+/* Portion of address space to scan in MB */
+unsigned int sysctl_numa_balancing_scan_size = 256;
+
+/* Scan @scan_size MB every @scan_period after an initial @scan_delay in ms */
+unsigned int sysctl_numa_balancing_scan_delay = 1000;
+
+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, bool migrated)
+{
+	struct task_struct *p = current;
+
+	if (!sched_feat_numa(NUMA))
+		return;
+
+	/* FIXME: Allocate task-specific structure for placement policy here */
+
+	/*
+	 * If pages are properly placed (did not migrate) then scan slower.
+	 * This is reset periodically in case of phase changes
+	 */
+        if (!migrated)
+		p->numa_scan_period = min(sysctl_numa_balancing_scan_period_max,
+			p->numa_scan_period + jiffies_to_msecs(10));
+
+	task_numa_placement(p);
+}
+
+static void reset_ptenuma_scan(struct task_struct *p)
+{
+	ACCESS_ONCE(p->mm->numa_scan_seq)++;
+	p->mm->numa_scan_offset = 0;
+}
+
+/*
+ * 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;
+	struct vm_area_struct *vma;
+	unsigned long start, end;
+	long pages;
+
+	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;
+
+	/*
+	 * We do not care about task placement until a task runs on a node
+	 * other than the first one used by the address space. This is
+	 * largely because migrations are driven by what CPU the task
+	 * is running on. If it's never scheduled on another node, it'll
+	 * not migrate so why bother trapping the fault.
+	 */
+	if (mm->first_nid == NUMA_PTE_SCAN_INIT)
+		mm->first_nid = numa_node_id();
+	if (mm->first_nid != NUMA_PTE_SCAN_ACTIVE) {
+		/* Are we running on a new node yet? */
+		if (numa_node_id() == mm->first_nid &&
+		    !sched_feat_numa(NUMA_FORCE))
+			return;
+
+		mm->first_nid = NUMA_PTE_SCAN_ACTIVE;
+	}
+
+	/*
+	 * Reset the scan period if enough time has gone by. Objective is that
+	 * scanning will be reduced if pages are properly placed. As tasks
+	 * can enter different phases this needs to be re-examined. Lacking
+	 * proper tracking of reference behaviour, this blunt hammer is used.
+	 */
+	migrate = mm->numa_next_reset;
+	if (time_after(now, migrate)) {
+		p->numa_scan_period = sysctl_numa_balancing_scan_period_min;
+		next_scan = now + msecs_to_jiffies(sysctl_numa_balancing_scan_period_reset);
+		xchg(&mm->numa_next_reset, next_scan);
+	}
+
+	/*
+	 * 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 + msecs_to_jiffies(p->numa_scan_period);
+	if (cmpxchg(&mm->numa_next_scan, migrate, next_scan) != migrate)
+		return;
+
+	/*
+	 * Do not set pte_numa if the current running node is rate-limited.
+	 * This loses statistics on the fault but if we are unwilling to
+	 * migrate to this node, it is less likely we can do useful work
+	 */
+	if (migrate_ratelimited(numa_node_id()))
+		return;
+
+	start = mm->numa_scan_offset;
+	pages = sysctl_numa_balancing_scan_size;
+	pages <<= 20 - PAGE_SHIFT; /* MB in pages */
+	if (!pages)
+		return;
+
+	down_read(&mm->mmap_sem);
+	vma = find_vma(mm, start);
+	if (!vma) {
+		reset_ptenuma_scan(p);
+		start = 0;
+		vma = mm->mmap;
+	}
+	for (; vma; vma = vma->vm_next) {
+		if (!vma_migratable(vma))
+			continue;
+
+		/* Skip small VMAs. They are not likely to be of relevance */
+		if (((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) < HPAGE_PMD_NR)
+			continue;
+
+		do {
+			start = max(start, vma->vm_start);
+			end = ALIGN(start + (pages << PAGE_SHIFT), HPAGE_SIZE);
+			end = min(end, vma->vm_end);
+			pages -= change_prot_numa(vma, start, end);
+
+			start = end;
+			if (pages <= 0)
+				goto out;
+		} while (end != vma->vm_end);
+	}
+
+out:
+	/*
+	 * It is possible to reach the end of the VMA list but the last few VMAs are
+	 * not guaranteed to the vma_migratable. If they are not, we would find the
+	 * !migratable VMA on the next scan but not reset the scanner to the start
+	 * so check it now.
+	 */
+	if (vma)
+		mm->numa_scan_offset = start;
+	else
+		reset_ptenuma_scan(p);
+	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) {
+		if (!curr->node_stamp)
+			curr->numa_scan_period = sysctl_numa_balancing_scan_period_min;
+		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)
 {
@@ -5501,6 +5725,9 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
 		entity_tick(cfs_rq, se, queued);
 	}
 
+	if (sched_feat_numa(NUMA))
+		task_tick_numa(rq, curr);
+
 	update_rq_runnable_avg(rq, 1);
 }
 
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index e68e69a..1ad1d2b 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -66,3 +66,14 @@ 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. Enabled automatically
+ * at runtime if running on a NUMA machine. Can be controlled via
+ * numa_balancing=. Allow PTE scanning to be forced on UMA machines
+ * for debugging the core machinery.
+ */
+#ifdef CONFIG_NUMA_BALANCING
+SCHED_FEAT(NUMA,	false)
+SCHED_FEAT(NUMA_FORCE,	false)
+#endif
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 5eca173..fc88644 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -663,6 +663,18 @@ 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)
+#ifdef CONFIG_SCHED_DEBUG
+#define numabalancing_enabled sched_feat_numa(NUMA)
+#else
+extern bool numabalancing_enabled;
+#endif /* CONFIG_SCHED_DEBUG */
+#else
+#define sched_feat_numa(x) (0)
+#define numabalancing_enabled (0)
+#endif /* CONFIG_NUMA_BALANCING */
+
 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 33f71f3..c88878d 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 +350,45 @@ static struct ctl_table kern_table[] = {
 		.extra1		= &zero,
 		.extra2		= &one,
 	},
-#endif
+#endif /* CONFIG_SMP */
+#ifdef CONFIG_NUMA_BALANCING
+	{
+		.procname	= "numa_balancing_scan_delay_ms",
+		.data		= &sysctl_numa_balancing_scan_delay,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.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_reset",
+		.data		= &sysctl_numa_balancing_scan_period_reset,
+		.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,
+	},
+	{
+		.procname	= "numa_balancing_scan_size_mb",
+		.data		= &sysctl_numa_balancing_scan_size,
+		.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,