mm, compaction: capture a page under direct compaction

Compaction is inherently race-prone as a suitable page freed during
compaction can be allocated by any parallel task.  This patch uses a
capture_control structure to isolate a page immediately when it is freed
by a direct compactor in the slow path of the page allocator.  The
intent is to avoid redundant scanning.

                                     5.0.0-rc1              5.0.0-rc1
                               selective-v3r17          capture-v3r19
Amean     fault-both-1         0.00 (   0.00%)        0.00 *   0.00%*
Amean     fault-both-3      2582.11 (   0.00%)     2563.68 (   0.71%)
Amean     fault-both-5      4500.26 (   0.00%)     4233.52 (   5.93%)
Amean     fault-both-7      5819.53 (   0.00%)     6333.65 (  -8.83%)
Amean     fault-both-12     9321.18 (   0.00%)     9759.38 (  -4.70%)
Amean     fault-both-18     9782.76 (   0.00%)    10338.76 (  -5.68%)
Amean     fault-both-24    15272.81 (   0.00%)    13379.55 *  12.40%*
Amean     fault-both-30    15121.34 (   0.00%)    16158.25 (  -6.86%)
Amean     fault-both-32    18466.67 (   0.00%)    18971.21 (  -2.73%)

Latency is only moderately affected but the devil is in the details.  A
closer examination indicates that base page fault latency is reduced but
latency of huge pages is increased as it takes creater care to succeed.
Part of the "problem" is that allocation success rates are close to 100%
even when under pressure and compaction gets harder

                                5.0.0-rc1              5.0.0-rc1
                          selective-v3r17          capture-v3r19
Percentage huge-3        96.70 (   0.00%)       98.23 (   1.58%)
Percentage huge-5        96.99 (   0.00%)       95.30 (  -1.75%)
Percentage huge-7        94.19 (   0.00%)       97.24 (   3.24%)
Percentage huge-12       94.95 (   0.00%)       97.35 (   2.53%)
Percentage huge-18       96.74 (   0.00%)       97.30 (   0.58%)
Percentage huge-24       97.07 (   0.00%)       97.55 (   0.50%)
Percentage huge-30       95.69 (   0.00%)       98.50 (   2.95%)
Percentage huge-32       96.70 (   0.00%)       99.27 (   2.65%)

And scan rates are reduced as expected by 6% for the migration scanner
and 29% for the free scanner indicating that there is less redundant
work.

Compaction migrate scanned    20815362    19573286
Compaction free scanned       16352612    11510663

[[email protected]: remove redundant check]
  Link: http://lkml.kernel.org/r/[email protected]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Mel Gorman <[email protected]>
Acked-by: Vlastimil Babka <[email protected]>
Cc: Andrea Arcangeli <[email protected]>
Cc: Dan Carpenter <[email protected]>
Cc: David Rientjes <[email protected]>
Cc: YueHaibing <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

Author: gormanm

include/linux/compaction.h

@@ -93,7 +93,8 @@ extern int sysctl_compact_unevictable_allowed;
 extern int fragmentation_index(struct zone *zone, unsigned int order);
 extern enum compact_result try_to_compact_pages(gfp_t gfp_mask,
 		unsigned int order, unsigned int alloc_flags,
-		const struct alloc_context *ac, enum compact_priority prio);
+		const struct alloc_context *ac, enum compact_priority prio,
+		struct page **page);
 extern void reset_isolation_suitable(pg_data_t *pgdat);
 extern enum compact_result compaction_suitable(struct zone *zone, int order,
 		unsigned int alloc_flags, int classzone_idx);

include/linux/sched.h

@@ -47,6 +47,7 @@ struct pid_namespace;
 struct pipe_inode_info;
 struct rcu_node;
 struct reclaim_state;
+struct capture_control;
 struct robust_list_head;
 struct sched_attr;
 struct sched_param;
@@ -958,6 +959,9 @@ struct task_struct {
 
 	struct io_context		*io_context;
 
+#ifdef CONFIG_COMPACTION
+	struct capture_control		*capture_control;
+#endif
 	/* Ptrace state: */
 	unsigned long			ptrace_message;
 	kernel_siginfo_t		*last_siginfo;

kernel/sched/core.c

@@ -2190,6 +2190,9 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	INIT_HLIST_HEAD(&p->preempt_notifiers);
 #endif
 
+#ifdef CONFIG_COMPACTION
+	p->capture_control = NULL;
+#endif
 	init_numa_balancing(clone_flags, p);
 }
 

mm/compaction.c

@@ -2056,7 +2056,8 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order,
 	return false;
 }
 
-static enum compact_result compact_zone(struct compact_control *cc)
+static enum compact_result
+compact_zone(struct compact_control *cc, struct capture_control *capc)
 {
 	enum compact_result ret;
 	unsigned long start_pfn = cc->zone->zone_start_pfn;
@@ -2225,6 +2226,11 @@ static enum compact_result compact_zone(struct compact_control *cc)
 			}
 		}
 
+		/* Stop if a page has been captured */
+		if (capc && capc->page) {
+			ret = COMPACT_SUCCESS;
+			break;
+		}
 	}
 
 out:
@@ -2258,7 +2264,8 @@ static enum compact_result compact_zone(struct compact_control *cc)
 
 static enum compact_result compact_zone_order(struct zone *zone, int order,
 		gfp_t gfp_mask, enum compact_priority prio,
-		unsigned int alloc_flags, int classzone_idx)
+		unsigned int alloc_flags, int classzone_idx,
+		struct page **capture)
 {
 	enum compact_result ret;
 	struct compact_control cc = {
@@ -2279,14 +2286,24 @@ static enum compact_result compact_zone_order(struct zone *zone, int order,
 		.ignore_skip_hint = (prio == MIN_COMPACT_PRIORITY),
 		.ignore_block_suitable = (prio == MIN_COMPACT_PRIORITY)
 	};
+	struct capture_control capc = {
+		.cc = &cc,
+		.page = NULL,
+	};
+
+	if (capture)
+		current->capture_control = &capc;
 	INIT_LIST_HEAD(&cc.freepages);
 	INIT_LIST_HEAD(&cc.migratepages);
 
-	ret = compact_zone(&cc);
+	ret = compact_zone(&cc, &capc);
 
 	VM_BUG_ON(!list_empty(&cc.freepages));
 	VM_BUG_ON(!list_empty(&cc.migratepages));
 
+	*capture = capc.page;
+	current->capture_control = NULL;
+
 	return ret;
 }
 
@@ -2304,7 +2321,7 @@ int sysctl_extfrag_threshold = 500;
  */
 enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order,
 		unsigned int alloc_flags, const struct alloc_context *ac,
-		enum compact_priority prio)
+		enum compact_priority prio, struct page **capture)
 {
 	int may_perform_io = gfp_mask & __GFP_IO;
 	struct zoneref *z;
@@ -2332,7 +2349,7 @@ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order,
 		}
 
 		status = compact_zone_order(zone, order, gfp_mask, prio,
-					alloc_flags, ac_classzone_idx(ac));
+				alloc_flags, ac_classzone_idx(ac), capture);
 		rc = max(status, rc);
 
 		/* The allocation should succeed, stop compacting */
@@ -2400,7 +2417,7 @@ static void compact_node(int nid)
 		INIT_LIST_HEAD(&cc.freepages);
 		INIT_LIST_HEAD(&cc.migratepages);
 
-		compact_zone(&cc);
+		compact_zone(&cc, NULL);
 
 		VM_BUG_ON(!list_empty(&cc.freepages));
 		VM_BUG_ON(!list_empty(&cc.migratepages));
@@ -2535,7 +2552,7 @@ static void kcompactd_do_work(pg_data_t *pgdat)
 
 		if (kthread_should_stop())
 			return;
-		status = compact_zone(&cc);
+		status = compact_zone(&cc, NULL);
 
 		if (status == COMPACT_SUCCESS) {
 			compaction_defer_reset(zone, cc.order, false);

mm/internal.h

@@ -209,6 +209,15 @@ struct compact_control {
 	bool rescan;			/* Rescanning the same pageblock */
 };
 
+/*
+ * Used in direct compaction when a page should be taken from the freelists
+ * immediately when one is created during the free path.
+ */
+struct capture_control {
+	struct compact_control *cc;
+	struct page *page;
+};
+
 unsigned long
 isolate_freepages_range(struct compact_control *cc,
 			unsigned long start_pfn, unsigned long end_pfn);

mm/page_alloc.c

@@ -789,6 +789,57 @@ static inline int page_is_buddy(struct page *page, struct page *buddy,
 	return 0;
 }
 
+#ifdef CONFIG_COMPACTION
+static inline struct capture_control *task_capc(struct zone *zone)
+{
+	struct capture_control *capc = current->capture_control;
+
+	return capc &&
+		!(current->flags & PF_KTHREAD) &&
+		!capc->page &&
+		capc->cc->zone == zone &&
+		capc->cc->direct_compaction ? capc : NULL;
+}
+
+static inline bool
+compaction_capture(struct capture_control *capc, struct page *page,
+		   int order, int migratetype)
+{
+	if (!capc || order != capc->cc->order)
+		return false;
+
+	/* Do not accidentally pollute CMA or isolated regions*/
+	if (is_migrate_cma(migratetype) ||
+	    is_migrate_isolate(migratetype))
+		return false;
+
+	/*
+	 * Do not let lower order allocations polluate a movable pageblock.
+	 * This might let an unmovable request use a reclaimable pageblock
+	 * and vice-versa but no more than normal fallback logic which can
+	 * have trouble finding a high-order free page.
+	 */
+	if (order < pageblock_order && migratetype == MIGRATE_MOVABLE)
+		return false;
+
+	capc->page = page;
+	return true;
+}
+
+#else
+static inline struct capture_control *task_capc(struct zone *zone)
+{
+	return NULL;
+}
+
+static inline bool
+compaction_capture(struct capture_control *capc, struct page *page,
+		   int order, int migratetype)
+{
+	return false;
+}
+#endif /* CONFIG_COMPACTION */
+
 /*
  * Freeing function for a buddy system allocator.
  *
@@ -822,6 +873,7 @@ static inline void __free_one_page(struct page *page,
 	unsigned long uninitialized_var(buddy_pfn);
 	struct page *buddy;
 	unsigned int max_order;
+	struct capture_control *capc = task_capc(zone);
 
 	max_order = min_t(unsigned int, MAX_ORDER, pageblock_order + 1);
 
@@ -837,6 +889,11 @@ static inline void __free_one_page(struct page *page,
 
 continue_merging:
 	while (order < max_order - 1) {
+		if (compaction_capture(capc, page, order, migratetype)) {
+			__mod_zone_freepage_state(zone, -(1 << order),
+								migratetype);
+			return;
+		}
 		buddy_pfn = __find_buddy_pfn(pfn, order);
 		buddy = page + (buddy_pfn - pfn);
 
@@ -3710,7 +3767,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 		unsigned int alloc_flags, const struct alloc_context *ac,
 		enum compact_priority prio, enum compact_result *compact_result)
 {
-	struct page *page;
+	struct page *page = NULL;
 	unsigned long pflags;
 	unsigned int noreclaim_flag;
 
@@ -3721,21 +3778,29 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	noreclaim_flag = memalloc_noreclaim_save();
 
 	*compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac,
-									prio);
+								prio, &page);
 
 	memalloc_noreclaim_restore(noreclaim_flag);
 	psi_memstall_leave(&pflags);
 
-	if (*compact_result <= COMPACT_INACTIVE)
+	if (*compact_result <= COMPACT_INACTIVE) {
+		WARN_ON_ONCE(page);
 		return NULL;
+	}
 
 	/*
 	 * At least in one zone compaction wasn't deferred or skipped, so let's
 	 * count a compaction stall
 	 */
 	count_vm_event(COMPACTSTALL);
 
-	page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac);
+	/* Prep a captured page if available */
+	if (page)
+		prep_new_page(page, order, gfp_mask, alloc_flags);
+
+	/* Try get a page from the freelist if available */
+	if (!page)
+		page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac);
 
 	if (page) {
 		struct zone *zone = page_zone(page);