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
  ...

1 files changed, 259 insertions, 24 deletions

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index aaf54566cb6..d1b315e9862 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -90,6 +90,7 @@
 #include <linux/syscalls.h>
 #include <linux/ctype.h>
 #include <linux/mm_inline.h>
+#include <linux/mmu_notifier.h>
 
 #include <asm/tlbflush.h>
 #include <asm/uaccess.h>
@@ -117,6 +118,26 @@ static struct mempolicy default_policy = {
 	.flags = MPOL_F_LOCAL,
 };
 
+static struct mempolicy preferred_node_policy[MAX_NUMNODES];
+
+static struct mempolicy *get_task_policy(struct task_struct *p)
+{
+	struct mempolicy *pol = p->mempolicy;
+	int node;
+
+	if (!pol) {
+		node = numa_node_id();
+		if (node != -1)
+			pol = &preferred_node_policy[node];
+
+		/* preferred_node_policy is not initialised early in boot */
+		if (!pol->mode)
+			pol = NULL;
+	}
+
+	return pol;
+}
+
 static const struct mempolicy_operations {
 	int (*create)(struct mempolicy *pol, const nodemask_t *nodes);
 	/*
@@ -254,7 +275,7 @@ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags,
 	if (mode == MPOL_DEFAULT) {
 		if (nodes && !nodes_empty(*nodes))
 			return ERR_PTR(-EINVAL);
-		return NULL;	/* simply delete any existing policy */
+		return NULL;
 	}
 	VM_BUG_ON(!nodes);
 
@@ -269,6 +290,10 @@ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags,
 			     (flags & MPOL_F_RELATIVE_NODES)))
 				return ERR_PTR(-EINVAL);
 		}
+	} else if (mode == MPOL_LOCAL) {
+		if (!nodes_empty(*nodes))
+			return ERR_PTR(-EINVAL);
+		mode = MPOL_PREFERRED;
 	} else if (nodes_empty(*nodes))
 		return ERR_PTR(-EINVAL);
 	policy = kmem_cache_alloc(policy_cache, GFP_KERNEL);
@@ -561,6 +586,36 @@ static inline int check_pgd_range(struct vm_area_struct *vma,
 	return 0;
 }
 
+#ifdef CONFIG_ARCH_USES_NUMA_PROT_NONE
+/*
+ * This is used to mark a range of virtual addresses to be inaccessible.
+ * These are later cleared by a NUMA hinting fault. Depending on these
+ * faults, pages may be migrated for better NUMA placement.
+ *
+ * This is assuming that NUMA faults are handled using PROT_NONE. If
+ * an architecture makes a different choice, it will need further
+ * changes to the core.
+ */
+unsigned long change_prot_numa(struct vm_area_struct *vma,
+			unsigned long addr, unsigned long end)
+{
+	int nr_updated;
+	BUILD_BUG_ON(_PAGE_NUMA != _PAGE_PROTNONE);
+
+	nr_updated = change_protection(vma, addr, end, vma->vm_page_prot, 0, 1);
+	if (nr_updated)
+		count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated);
+
+	return nr_updated;
+}
+#else
+static unsigned long change_prot_numa(struct vm_area_struct *vma,
+			unsigned long addr, unsigned long end)
+{
+	return 0;
+}
+#endif /* CONFIG_ARCH_USES_NUMA_PROT_NONE */
+
 /*
  * Check if all pages in a range are on a set of nodes.
  * If pagelist != NULL then isolate pages from the LRU and
@@ -579,22 +634,32 @@ check_range(struct mm_struct *mm, unsigned long start, unsigned long end,
 		return ERR_PTR(-EFAULT);
 	prev = NULL;
 	for (vma = first; vma && vma->vm_start < end; vma = vma->vm_next) {
+		unsigned long endvma = vma->vm_end;
+
+		if (endvma > end)
+			endvma = end;
+		if (vma->vm_start > start)
+			start = vma->vm_start;
+
 		if (!(flags & MPOL_MF_DISCONTIG_OK)) {
 			if (!vma->vm_next && vma->vm_end < end)
 				return ERR_PTR(-EFAULT);
 			if (prev && prev->vm_end < vma->vm_start)
 				return ERR_PTR(-EFAULT);
 		}
-		if (!is_vm_hugetlb_page(vma) &&
-		    ((flags & MPOL_MF_STRICT) ||
+
+		if (is_vm_hugetlb_page(vma))
+			goto next;
+
+		if (flags & MPOL_MF_LAZY) {
+			change_prot_numa(vma, start, endvma);
+			goto next;
+		}
+
+		if ((flags & MPOL_MF_STRICT) ||
 		     ((flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) &&
-				vma_migratable(vma)))) {
-			unsigned long endvma = vma->vm_end;
+		      vma_migratable(vma))) {
 
-			if (endvma > end)
-				endvma = end;
-			if (vma->vm_start > start)
-				start = vma->vm_start;
 			err = check_pgd_range(vma, start, endvma, nodes,
 						flags, private);
 			if (err) {
@@ -602,6 +667,7 @@ check_range(struct mm_struct *mm, unsigned long start, unsigned long end,
 				break;
 			}
 		}
+next:
 		prev = vma;
 	}
 	return first;
@@ -961,7 +1027,8 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest,
 
 	if (!list_empty(&pagelist)) {
 		err = migrate_pages(&pagelist, new_node_page, dest,
-							false, MIGRATE_SYNC);
+							false, MIGRATE_SYNC,
+							MR_SYSCALL);
 		if (err)
 			putback_lru_pages(&pagelist);
 	}
@@ -1133,8 +1200,7 @@ static long do_mbind(unsigned long start, unsigned long len,
 	int err;
 	LIST_HEAD(pagelist);
 
-	if (flags & ~(unsigned long)(MPOL_MF_STRICT |
-				     MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
+	if (flags & ~(unsigned long)MPOL_MF_VALID)
 		return -EINVAL;
 	if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE))
 		return -EPERM;
@@ -1157,6 +1223,9 @@ static long do_mbind(unsigned long start, unsigned long len,
 	if (IS_ERR(new))
 		return PTR_ERR(new);
 
+	if (flags & MPOL_MF_LAZY)
+		new->flags |= MPOL_F_MOF;
+
 	/*
 	 * If we are using the default policy then operation
 	 * on discontinuous address spaces is okay after all
@@ -1193,21 +1262,24 @@ static long do_mbind(unsigned long start, unsigned long len,
 	vma = check_range(mm, start, end, nmask,
 			  flags | MPOL_MF_INVERT, &pagelist);
 
-	err = PTR_ERR(vma);
-	if (!IS_ERR(vma)) {
-		int nr_failed = 0;
-
+	err = PTR_ERR(vma);	/* maybe ... */
+	if (!IS_ERR(vma))
 		err = mbind_range(mm, start, end, new);
 
+	if (!err) {
+		int nr_failed = 0;
+
 		if (!list_empty(&pagelist)) {
+			WARN_ON_ONCE(flags & MPOL_MF_LAZY);
 			nr_failed = migrate_pages(&pagelist, new_vma_page,
 						(unsigned long)vma,
-						false, MIGRATE_SYNC);
+						false, MIGRATE_SYNC,
+						MR_MEMPOLICY_MBIND);
 			if (nr_failed)
 				putback_lru_pages(&pagelist);
 		}
 
-		if (!err && nr_failed && (flags & MPOL_MF_STRICT))
+		if (nr_failed && (flags & MPOL_MF_STRICT))
 			err = -EIO;
 	} else
 		putback_lru_pages(&pagelist);
@@ -1546,7 +1618,7 @@ asmlinkage long compat_sys_mbind(compat_ulong_t start, compat_ulong_t len,
 struct mempolicy *get_vma_policy(struct task_struct *task,
 		struct vm_area_struct *vma, unsigned long addr)
 {
-	struct mempolicy *pol = task->mempolicy;
+	struct mempolicy *pol = get_task_policy(task);
 
 	if (vma) {
 		if (vma->vm_ops && vma->vm_ops->get_policy) {
@@ -1956,7 +2028,7 @@ retry_cpuset:
  */
 struct page *alloc_pages_current(gfp_t gfp, unsigned order)
 {
-	struct mempolicy *pol = current->mempolicy;
+	struct mempolicy *pol = get_task_policy(current);
 	struct page *page;
 	unsigned int cpuset_mems_cookie;
 
@@ -2140,6 +2212,115 @@ static void sp_free(struct sp_node *n)
 	kmem_cache_free(sn_cache, n);
 }
 
+/**
+ * mpol_misplaced - check whether current page node is valid in policy
+ *
+ * @page   - page to be checked
+ * @vma    - vm area where page mapped
+ * @addr   - virtual address where page mapped
+ *
+ * Lookup current policy node id for vma,addr and "compare to" page's
+ * node id.
+ *
+ * Returns:
+ *	-1	- not misplaced, page is in the right node
+ *	node	- node id where the page should be
+ *
+ * Policy determination "mimics" alloc_page_vma().
+ * Called from fault path where we know the vma and faulting address.
+ */
+int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long addr)
+{
+	struct mempolicy *pol;
+	struct zone *zone;
+	int curnid = page_to_nid(page);
+	unsigned long pgoff;
+	int polnid = -1;
+	int ret = -1;
+
+	BUG_ON(!vma);
+
+	pol = get_vma_policy(current, vma, addr);
+	if (!(pol->flags & MPOL_F_MOF))
+		goto out;
+
+	switch (pol->mode) {
+	case MPOL_INTERLEAVE:
+		BUG_ON(addr >= vma->vm_end);
+		BUG_ON(addr < vma->vm_start);
+
+		pgoff = vma->vm_pgoff;
+		pgoff += (addr - vma->vm_start) >> PAGE_SHIFT;
+		polnid = offset_il_node(pol, vma, pgoff);
+		break;
+
+	case MPOL_PREFERRED:
+		if (pol->flags & MPOL_F_LOCAL)
+			polnid = numa_node_id();
+		else
+			polnid = pol->v.preferred_node;
+		break;
+
+	case MPOL_BIND:
+		/*
+		 * allows binding to multiple nodes.
+		 * use current page if in policy nodemask,
+		 * else select nearest allowed node, if any.
+		 * If no allowed nodes, use current [!misplaced].
+		 */
+		if (node_isset(curnid, pol->v.nodes))
+			goto out;
+		(void)first_zones_zonelist(
+				node_zonelist(numa_node_id(), GFP_HIGHUSER),
+				gfp_zone(GFP_HIGHUSER),
+				&pol->v.nodes, &zone);
+		polnid = zone->node;
+		break;
+
+	default:
+		BUG();
+	}
+
+	/* Migrate the page towards the node whose CPU is referencing it */
+	if (pol->flags & MPOL_F_MORON) {
+		int last_nid;
+
+		polnid = numa_node_id();
+
+		/*
+		 * Multi-stage node selection is used in conjunction
+		 * with a periodic migration fault to build a temporal
+		 * task<->page relation. By using a two-stage filter we
+		 * remove short/unlikely relations.
+		 *
+		 * Using P(p) ~ n_p / n_t as per frequentist
+		 * probability, we can equate a task's usage of a
+		 * particular page (n_p) per total usage of this
+		 * page (n_t) (in a given time-span) to a probability.
+		 *
+		 * Our periodic faults will sample this probability and
+		 * getting the same result twice in a row, given these
+		 * samples are fully independent, is then given by
+		 * P(n)^2, provided our sample period is sufficiently
+		 * short compared to the usage pattern.
+		 *
+		 * This quadric squishes small probabilities, making
+		 * it less likely we act on an unlikely task<->page
+		 * relation.
+		 */
+		last_nid = page_xchg_last_nid(page, polnid);
+		if (last_nid != polnid)
+			goto out;
+	}
+
+	if (curnid != polnid)
+		ret = polnid;
+out:
+	mpol_cond_put(pol);
+
+	return ret;
+}
+
 static void sp_delete(struct shared_policy *sp, struct sp_node *n)
 {
 	pr_debug("deleting %lx-l%lx\n", n->start, n->end);
@@ -2305,6 +2486,50 @@ void mpol_free_shared_policy(struct shared_policy *p)
 	mutex_unlock(&p->mutex);
 }
 
+#ifdef CONFIG_NUMA_BALANCING
+static bool __initdata numabalancing_override;
+
+static void __init check_numabalancing_enable(void)
+{
+	bool numabalancing_default = false;
+
+	if (IS_ENABLED(CONFIG_NUMA_BALANCING_DEFAULT_ENABLED))
+		numabalancing_default = true;
+
+	if (nr_node_ids > 1 && !numabalancing_override) {
+		printk(KERN_INFO "Enabling automatic NUMA balancing. "
+			"Configure with numa_balancing= or sysctl");
+		set_numabalancing_state(numabalancing_default);
+	}
+}
+
+static int __init setup_numabalancing(char *str)
+{
+	int ret = 0;
+	if (!str)
+		goto out;
+	numabalancing_override = true;
+
+	if (!strcmp(str, "enable")) {
+		set_numabalancing_state(true);
+		ret = 1;
+	} else if (!strcmp(str, "disable")) {
+		set_numabalancing_state(false);
+		ret = 1;
+	}
+out:
+	if (!ret)
+		printk(KERN_WARNING "Unable to parse numa_balancing=\n");
+
+	return ret;
+}
+__setup("numa_balancing=", setup_numabalancing);
+#else
+static inline void __init check_numabalancing_enable(void)
+{
+}
+#endif /* CONFIG_NUMA_BALANCING */
+
 /* assumes fs == KERNEL_DS */
 void __init numa_policy_init(void)
 {
@@ -2320,6 +2545,15 @@ void __init numa_policy_init(void)
 				     sizeof(struct sp_node),
 				     0, SLAB_PANIC, NULL);
 
+	for_each_node(nid) {
+		preferred_node_policy[nid] = (struct mempolicy) {
+			.refcnt = ATOMIC_INIT(1),
+			.mode = MPOL_PREFERRED,
+			.flags = MPOL_F_MOF | MPOL_F_MORON,
+			.v = { .preferred_node = nid, },
+		};
+	}
+
 	/*
 	 * Set interleaving policy for system init. Interleaving is only
 	 * enabled across suitably sized nodes (default is >= 16MB), or
@@ -2346,6 +2580,8 @@ void __init numa_policy_init(void)
 
 	if (do_set_mempolicy(MPOL_INTERLEAVE, 0, &interleave_nodes))
 		printk("numa_policy_init: interleaving failed\n");
+
+	check_numabalancing_enable();
 }
 
 /* Reset policy of current process to default */
@@ -2362,14 +2598,13 @@ void numa_default_policy(void)
  * "local" is pseudo-policy:  MPOL_PREFERRED with MPOL_F_LOCAL flag
  * Used only for mpol_parse_str() and mpol_to_str()
  */
-#define MPOL_LOCAL MPOL_MAX
 static const char * const policy_modes[] =
 {
 	[MPOL_DEFAULT]    = "default",
 	[MPOL_PREFERRED]  = "prefer",
 	[MPOL_BIND]       = "bind",
 	[MPOL_INTERLEAVE] = "interleave",
-	[MPOL_LOCAL]      = "local"
+	[MPOL_LOCAL]      = "local",
 };
 
 
@@ -2415,12 +2650,12 @@ int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context)
 	if (flags)
 		*flags++ = '\0';	/* terminate mode string */
 
-	for (mode = 0; mode <= MPOL_LOCAL; mode++) {
+	for (mode = 0; mode < MPOL_MAX; mode++) {
 		if (!strcmp(str, policy_modes[mode])) {
 			break;
 		}
 	}
-	if (mode > MPOL_LOCAL)
+	if (mode >= MPOL_MAX)
 		goto out;
 
 	switch (mode) {