[PATCH v4 1/5] mm/compaction: change tracepoint format from decimal to hexadecimal

[PATCH v4 1/5] mm/compaction: change tracepoint format from decimal to hexadecimal

[Joonsoo Kim]

To check the range that compaction is working, tracepoint print
start/end pfn of zone and start pfn of both scanner with decimal format.
Since we manage all pages in order of 2 and it is well represented by
hexadecimal, this patch change the tracepoint format from decimal to
hexadecimal. This would improve readability. For example, it makes us
easily notice whether current scanner try to compact previously
attempted pageblock or not.

Acked-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
---
 include/trace/events/compaction.h |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h
index c6814b9..1337d9e 100644
--- a/include/trace/events/compaction.h
+++ b/include/trace/events/compaction.h
@@ -104,7 +104,7 @@ TRACE_EVENT(mm_compaction_begin,
 		__entry->zone_end = zone_end;
 	),
 
-	TP_printk("zone_start=%lu migrate_start=%lu free_start=%lu zone_end=%lu",
+	TP_printk("zone_start=0x%lx migrate_start=0x%lx free_start=0x%lx zone_end=0x%lx",
 		__entry->zone_start,
 		__entry->migrate_start,
 		__entry->free_start,
-- 
1.7.9.5

[PATCH v4 2/5] mm/compaction: enhance tracepoint output for compaction begin/end

[Joonsoo Kim]

We now have tracepoint for begin event of compaction and it prints
start position of both scanners, but, tracepoint for end event of
compaction doesn't print finish position of both scanners. It'd be
also useful to know finish position of both scanners so this patch
add it. It will help to find odd behavior or problem on compaction
internal logic.

And, mode is added to both begin/end tracepoint output, since
according to mode, compaction behavior is quite different.

And, lastly, status format is changed to string rather than
status number for readability.

Changes from v3: Build fix for !CONFIG_COMPACTION, !CONFIG_TRACEPOINTS

Acked-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
---
 include/linux/compaction.h        |    1 +
 include/trace/events/compaction.h |   49 ++++++++++++++++++++++++++-----------
 mm/compaction.c                   |   15 ++++++++++--
 3 files changed, 49 insertions(+), 16 deletions(-)

diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 3238ffa..9363c08 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -12,6 +12,7 @@
 #define COMPACT_PARTIAL		3
 /* The full zone was compacted */
 #define COMPACT_COMPLETE	4
+/* When adding new state, please change compaction_status_string, too */
 
 /* Used to signal whether compaction detected need_sched() or lock contention */
 /* No contention detected */
diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h
index 1337d9e..839f6fa 100644
--- a/include/trace/events/compaction.h
+++ b/include/trace/events/compaction.h
@@ -85,46 +85,67 @@ TRACE_EVENT(mm_compaction_migratepages,
 );
 
 TRACE_EVENT(mm_compaction_begin,
-	TP_PROTO(unsigned long zone_start, unsigned long migrate_start,
-		unsigned long free_start, unsigned long zone_end),
+	TP_PROTO(unsigned long zone_start, unsigned long migrate_pfn,
+		unsigned long free_pfn, unsigned long zone_end, bool sync),
 
-	TP_ARGS(zone_start, migrate_start, free_start, zone_end),
+	TP_ARGS(zone_start, migrate_pfn, free_pfn, zone_end, sync),
 
 	TP_STRUCT__entry(
 		__field(unsigned long, zone_start)
-		__field(unsigned long, migrate_start)
-		__field(unsigned long, free_start)
+		__field(unsigned long, migrate_pfn)
+		__field(unsigned long, free_pfn)
 		__field(unsigned long, zone_end)
+		__field(bool, sync)
 	),
 
 	TP_fast_assign(
 		__entry->zone_start = zone_start;
-		__entry->migrate_start = migrate_start;
-		__entry->free_start = free_start;
+		__entry->migrate_pfn = migrate_pfn;
+		__entry->free_pfn = free_pfn;
 		__entry->zone_end = zone_end;
+		__entry->sync = sync;
 	),
 
-	TP_printk("zone_start=0x%lx migrate_start=0x%lx free_start=0x%lx zone_end=0x%lx",
+	TP_printk("zone_start=0x%lx migrate_pfn=0x%lx free_pfn=0x%lx zone_end=0x%lx, mode=%s",
 		__entry->zone_start,
-		__entry->migrate_start,
-		__entry->free_start,
-		__entry->zone_end)
+		__entry->migrate_pfn,
+		__entry->free_pfn,
+		__entry->zone_end,
+		__entry->sync ? "sync" : "async")
 );
 
 TRACE_EVENT(mm_compaction_end,
-	TP_PROTO(int status),
+	TP_PROTO(unsigned long zone_start, unsigned long migrate_pfn,
+		unsigned long free_pfn, unsigned long zone_end, bool sync,
+		int status),
 
-	TP_ARGS(status),
+	TP_ARGS(zone_start, migrate_pfn, free_pfn, zone_end, sync, status),
 
 	TP_STRUCT__entry(
+		__field(unsigned long, zone_start)
+		__field(unsigned long, migrate_pfn)
+		__field(unsigned long, free_pfn)
+		__field(unsigned long, zone_end)
+		__field(bool, sync)
 		__field(int, status)
 	),
 
 	TP_fast_assign(
+		__entry->zone_start = zone_start;
+		__entry->migrate_pfn = migrate_pfn;
+		__entry->free_pfn = free_pfn;
+		__entry->zone_end = zone_end;
+		__entry->sync = sync;
 		__entry->status = status;
 	),
 
-	TP_printk("status=%d", __entry->status)
+	TP_printk("zone_start=0x%lx migrate_pfn=0x%lx free_pfn=0x%lx zone_end=0x%lx, mode=%s status=%s",
+		__entry->zone_start,
+		__entry->migrate_pfn,
+		__entry->free_pfn,
+		__entry->zone_end,
+		__entry->sync ? "sync" : "async",
+		compaction_status_string[__entry->status])
 );
 
 #endif /* _TRACE_COMPACTION_H */
diff --git a/mm/compaction.c b/mm/compaction.c
index 546e571..f32d456 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -34,6 +34,15 @@ static inline void count_compact_events(enum vm_event_item item, long delta)
 #endif
 
 #if defined CONFIG_COMPACTION || defined CONFIG_CMA
+#ifdef CONFIG_TRACEPOINTS
+static const char const *compaction_status_string[] = {
+	"deferred",
+	"skipped",
+	"continue",
+	"partial",
+	"complete",
+};
+#endif
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/compaction.h>
@@ -1197,7 +1206,8 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 		zone->compact_cached_migrate_pfn[1] = cc->migrate_pfn;
 	}
 
-	trace_mm_compaction_begin(start_pfn, cc->migrate_pfn, cc->free_pfn, end_pfn);
+	trace_mm_compaction_begin(start_pfn, cc->migrate_pfn,
+				cc->free_pfn, end_pfn, sync);
 
 	migrate_prep_local();
 
@@ -1299,7 +1309,8 @@ out:
 			zone->compact_cached_free_pfn = free_pfn;
 	}
 
-	trace_mm_compaction_end(ret);
+	trace_mm_compaction_end(start_pfn, cc->migrate_pfn,
+				cc->free_pfn, end_pfn, sync, ret);
 
 	return ret;
 }
-- 
1.7.9.5

[PATCH v4 3/5] mm/compaction: print current range where compaction work

[Joonsoo Kim]

It'd be useful to know current range where compaction work for detailed
analysis. With it, we can know pageblock where we actually scan and
isolate, and, how much pages we try in that pageblock and can guess why
it doesn't become freepage with pageblock order roughly.

Acked-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
---
 include/trace/events/compaction.h |   30 +++++++++++++++++++++++-------
 mm/compaction.c                   |    9 ++++++---
 2 files changed, 29 insertions(+), 10 deletions(-)

diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h
index 839f6fa..139020b 100644
--- a/include/trace/events/compaction.h
+++ b/include/trace/events/compaction.h
@@ -11,39 +11,55 @@
 
 DECLARE_EVENT_CLASS(mm_compaction_isolate_template,
 
-	TP_PROTO(unsigned long nr_scanned,
+	TP_PROTO(
+		unsigned long start_pfn,
+		unsigned long end_pfn,
+		unsigned long nr_scanned,
 		unsigned long nr_taken),
 
-	TP_ARGS(nr_scanned, nr_taken),
+	TP_ARGS(start_pfn, end_pfn, nr_scanned, nr_taken),
 
 	TP_STRUCT__entry(
+		__field(unsigned long, start_pfn)
+		__field(unsigned long, end_pfn)
 		__field(unsigned long, nr_scanned)
 		__field(unsigned long, nr_taken)
 	),
 
 	TP_fast_assign(
+		__entry->start_pfn = start_pfn;
+		__entry->end_pfn = end_pfn;
 		__entry->nr_scanned = nr_scanned;
 		__entry->nr_taken = nr_taken;
 	),
 
-	TP_printk("nr_scanned=%lu nr_taken=%lu",
+	TP_printk("range=(0x%lx ~ 0x%lx) nr_scanned=%lu nr_taken=%lu",
+		__entry->start_pfn,
+		__entry->end_pfn,
 		__entry->nr_scanned,
 		__entry->nr_taken)
 );
 
 DEFINE_EVENT(mm_compaction_isolate_template, mm_compaction_isolate_migratepages,
 
-	TP_PROTO(unsigned long nr_scanned,
+	TP_PROTO(
+		unsigned long start_pfn,
+		unsigned long end_pfn,
+		unsigned long nr_scanned,
 		unsigned long nr_taken),
 
-	TP_ARGS(nr_scanned, nr_taken)
+	TP_ARGS(start_pfn, end_pfn, nr_scanned, nr_taken)
 );
 
 DEFINE_EVENT(mm_compaction_isolate_template, mm_compaction_isolate_freepages,
-	TP_PROTO(unsigned long nr_scanned,
+
+	TP_PROTO(
+		unsigned long start_pfn,
+		unsigned long end_pfn,
+		unsigned long nr_scanned,
 		unsigned long nr_taken),
 
-	TP_ARGS(nr_scanned, nr_taken)
+	TP_ARGS(start_pfn, end_pfn, nr_scanned, nr_taken)
 );
 
 TRACE_EVENT(mm_compaction_migratepages,
diff --git a/mm/compaction.c b/mm/compaction.c
index f32d456..70af2b1 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -430,11 +430,12 @@ isolate_fail:
 
 	}
 
+	trace_mm_compaction_isolate_freepages(*start_pfn, blockpfn,
+					nr_scanned, total_isolated);
+
 	/* Record how far we have got within the block */
 	*start_pfn = blockpfn;
 
-	trace_mm_compaction_isolate_freepages(nr_scanned, total_isolated);
-
 	/*
 	 * If strict isolation is requested by CMA then check that all the
 	 * pages requested were isolated. If there were any failures, 0 is
@@ -590,6 +591,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 	unsigned long flags = 0;
 	bool locked = false;
 	struct page *page = NULL, *valid_page = NULL;
+	unsigned long start_pfn = low_pfn;
 
 	/*
 	 * Ensure that there are not too many pages isolated from the LRU
@@ -750,7 +752,8 @@ isolate_success:
 	if (low_pfn == end_pfn)
 		update_pageblock_skip(cc, valid_page, nr_isolated, true);
 
-	trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated);
+	trace_mm_compaction_isolate_migratepages(start_pfn, low_pfn,
+						nr_scanned, nr_isolated);
 
 	count_compact_events(COMPACTMIGRATE_SCANNED, nr_scanned);
 	if (nr_isolated)
-- 
1.7.9.5

[PATCH v4 4/5] mm/compaction: more trace to understand when/why compaction start/finish

[Joonsoo Kim]

It is not well analyzed that when/why compaction start/finish or not. With
these new tracepoints, we can know much more about start/finish reason of
compaction. I can find following bug with these tracepoint.

http://www.spinics.net/lists/linux-mm/msg81582.html

Change from v2: omit alloc_flag, classzone_idx from tracepoint output

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
---
 include/linux/compaction.h        |    3 ++
 include/trace/events/compaction.h |   74 +++++++++++++++++++++++++++++++++++++
 mm/compaction.c                   |   38 +++++++++++++++++--
 3 files changed, 111 insertions(+), 4 deletions(-)

diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 9363c08..648d183 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -12,6 +12,9 @@
 #define COMPACT_PARTIAL		3
 /* The full zone was compacted */
 #define COMPACT_COMPLETE	4
+/* For more detailed tracepoint output */
+#define COMPACT_NO_SUITABLE_PAGE	5
+#define COMPACT_NOT_SUITABLE_ZONE	6
 /* When adding new state, please change compaction_status_string, too */
 
 /* Used to signal whether compaction detected need_sched() or lock contention */
diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h
index 139020b..d465358 100644
--- a/include/trace/events/compaction.h
+++ b/include/trace/events/compaction.h
@@ -164,6 +164,80 @@ TRACE_EVENT(mm_compaction_end,
 		compaction_status_string[__entry->status])
 );
 
+TRACE_EVENT(mm_compaction_try_to_compact_pages,
+
+	TP_PROTO(
+		int order,
+		gfp_t gfp_mask,
+		enum migrate_mode mode),
+
+	TP_ARGS(order, gfp_mask, mode),
+
+	TP_STRUCT__entry(
+		__field(int, order)
+		__field(gfp_t, gfp_mask)
+		__field(enum migrate_mode, mode)
+	),
+
+	TP_fast_assign(
+		__entry->order = order;
+		__entry->gfp_mask = gfp_mask;
+		__entry->mode = mode;
+	),
+
+	TP_printk("order=%d gfp_mask=0x%x mode=%d",
+		__entry->order,
+		__entry->gfp_mask,
+		(int)__entry->mode)
+);
+
+DECLARE_EVENT_CLASS(mm_compaction_suitable_template,
+
+	TP_PROTO(struct zone *zone,
+		int order,
+		int ret),
+
+	TP_ARGS(zone, order, ret),
+
+	TP_STRUCT__entry(
+		__field(int, nid)
+		__field(char *, name)
+		__field(int, order)
+		__field(int, ret)
+	),
+
+	TP_fast_assign(
+		__entry->nid = zone_to_nid(zone);
+		__entry->name = (char *)zone->name;
+		__entry->order = order;
+		__entry->ret = ret;
+	),
+
+	TP_printk("node=%d zone=%-8s order=%d ret=%s",
+		__entry->nid,
+		__entry->name,
+		__entry->order,
+		compaction_status_string[__entry->ret])
+);
+
+DEFINE_EVENT(mm_compaction_suitable_template, mm_compaction_finished,
+
+	TP_PROTO(struct zone *zone,
+		int order,
+		int ret),
+
+	TP_ARGS(zone, order, ret)
+);
+
+DEFINE_EVENT(mm_compaction_suitable_template, mm_compaction_suitable,
+
+	TP_PROTO(struct zone *zone,
+		int order,
+		int ret),
+
+	TP_ARGS(zone, order, ret)
+);
+
 #endif /* _TRACE_COMPACTION_H */
 
 /* This part must be outside protection */
diff --git a/mm/compaction.c b/mm/compaction.c
index 70af2b1..8248a53 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -41,6 +41,8 @@ static const char const *compaction_status_string[] = {
 	"continue",
 	"partial",
 	"complete",
+	"no_suitable_page",
+	"not_suitable_zone",
 };
 #endif
 
@@ -1049,7 +1051,7 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 	return cc->nr_migratepages ? ISOLATE_SUCCESS : ISOLATE_NONE;
 }
 
-static int compact_finished(struct zone *zone, struct compact_control *cc,
+static int __compact_finished(struct zone *zone, struct compact_control *cc,
 			    const int migratetype)
 {
 	unsigned int order;
@@ -1104,7 +1106,20 @@ static int compact_finished(struct zone *zone, struct compact_control *cc,
 			return COMPACT_PARTIAL;
 	}
 
-	return COMPACT_CONTINUE;
+	return COMPACT_NO_SUITABLE_PAGE;
+}
+
+static int compact_finished(struct zone *zone, struct compact_control *cc,
+			    const int migratetype)
+{
+	int ret;
+
+	ret = __compact_finished(zone, cc, migratetype);
+	trace_mm_compaction_finished(zone, cc->order, ret);
+	if (ret == COMPACT_NO_SUITABLE_PAGE)
+		ret = COMPACT_CONTINUE;
+
+	return ret;
 }
 
 /*
@@ -1114,7 +1129,7 @@ static int compact_finished(struct zone *zone, struct compact_control *cc,
  *   COMPACT_PARTIAL  - If the allocation would succeed without compaction
  *   COMPACT_CONTINUE - If compaction should run now
  */
-unsigned long compaction_suitable(struct zone *zone, int order,
+static unsigned long __compaction_suitable(struct zone *zone, int order,
 					int alloc_flags, int classzone_idx)
 {
 	int fragindex;
@@ -1158,11 +1173,24 @@ unsigned long compaction_suitable(struct zone *zone, int order,
 	 */
 	fragindex = fragmentation_index(zone, order);
 	if (fragindex >= 0 && fragindex <= sysctl_extfrag_threshold)
-		return COMPACT_SKIPPED;
+		return COMPACT_NOT_SUITABLE_ZONE;
 
 	return COMPACT_CONTINUE;
 }
 
+unsigned long compaction_suitable(struct zone *zone, int order,
+					int alloc_flags, int classzone_idx)
+{
+	unsigned long ret;
+
+	ret = __compaction_suitable(zone, order, alloc_flags, classzone_idx);
+	trace_mm_compaction_suitable(zone, order, ret);
+	if (ret == COMPACT_NOT_SUITABLE_ZONE)
+		ret = COMPACT_SKIPPED;
+
+	return ret;
+}
+
 static int compact_zone(struct zone *zone, struct compact_control *cc)
 {
 	int ret;
@@ -1378,6 +1406,8 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 	if (!order || !may_enter_fs || !may_perform_io)
 		return COMPACT_SKIPPED;
 
+	trace_mm_compaction_try_to_compact_pages(order, gfp_mask, mode);
+
 	/* Compact each zone in the list */
 	for_each_zone_zonelist_nodemask(zone, z, zonelist, high_zoneidx,
 								nodemask) {
-- 
1.7.9.5

[PATCH v4 5/5] mm/compaction: add tracepoint to observe behaviour of compaction defer

[Joonsoo Kim]

compaction deferring logic is heavy hammer that block the way to
the compaction. It doesn't consider overall system state, so it
could prevent user from doing compaction falsely. In other words,
even if system has enough range of memory to compact, compaction would be
skipped due to compaction deferring logic. This patch add new tracepoint
to understand work of deferring logic. This will also help to check
compaction success and fail.

Changes from v2: Remove reason part from tracepoint output
Changes from v3: Build fix for !CONFIG_COMPACTION

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
---
 include/linux/compaction.h        |   65 +++------------------------------
 include/trace/events/compaction.h |   56 +++++++++++++++++++++++++++++
 mm/compaction.c                   |   71 +++++++++++++++++++++++++++++++++++++
 3 files changed, 132 insertions(+), 60 deletions(-)

diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 648d183..5024019 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -43,66 +43,11 @@ extern void reset_isolation_suitable(pg_data_t *pgdat);
 extern unsigned long compaction_suitable(struct zone *zone, int order,
 					int alloc_flags, int classzone_idx);
 
-/* Do not skip compaction more than 64 times */
-#define COMPACT_MAX_DEFER_SHIFT 6
-
-/*
- * Compaction is deferred when compaction fails to result in a page
- * allocation success. 1 << compact_defer_limit compactions are skipped up
- * to a limit of 1 << COMPACT_MAX_DEFER_SHIFT
- */
-static inline void defer_compaction(struct zone *zone, int order)
-{
-	zone->compact_considered = 0;
-	zone->compact_defer_shift++;
-
-	if (order < zone->compact_order_failed)
-		zone->compact_order_failed = order;
-
-	if (zone->compact_defer_shift > COMPACT_MAX_DEFER_SHIFT)
-		zone->compact_defer_shift = COMPACT_MAX_DEFER_SHIFT;
-}
-
-/* Returns true if compaction should be skipped this time */
-static inline bool compaction_deferred(struct zone *zone, int order)
-{
-	unsigned long defer_limit = 1UL << zone->compact_defer_shift;
-
-	if (order < zone->compact_order_failed)
-		return false;
-
-	/* Avoid possible overflow */
-	if (++zone->compact_considered > defer_limit)
-		zone->compact_considered = defer_limit;
-
-	return zone->compact_considered < defer_limit;
-}
-
-/*
- * Update defer tracking counters after successful compaction of given order,
- * which means an allocation either succeeded (alloc_success == true) or is
- * expected to succeed.
- */
-static inline void compaction_defer_reset(struct zone *zone, int order,
-		bool alloc_success)
-{
-	if (alloc_success) {
-		zone->compact_considered = 0;
-		zone->compact_defer_shift = 0;
-	}
-	if (order >= zone->compact_order_failed)
-		zone->compact_order_failed = order + 1;
-}
-
-/* Returns true if restarting compaction after many failures */
-static inline bool compaction_restarting(struct zone *zone, int order)
-{
-	if (order < zone->compact_order_failed)
-		return false;
-
-	return zone->compact_defer_shift == COMPACT_MAX_DEFER_SHIFT &&
-		zone->compact_considered >= 1UL << zone->compact_defer_shift;
-}
+extern void defer_compaction(struct zone *zone, int order);
+extern bool compaction_deferred(struct zone *zone, int order);
+extern void compaction_defer_reset(struct zone *zone, int order,
+				bool alloc_success);
+extern bool compaction_restarting(struct zone *zone, int order);
 
 #else
 static inline unsigned long try_to_compact_pages(struct zonelist *zonelist,
diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h
index d465358..9a6a3fe 100644
--- a/include/trace/events/compaction.h
+++ b/include/trace/events/compaction.h
@@ -238,6 +238,62 @@ DEFINE_EVENT(mm_compaction_suitable_template, mm_compaction_suitable,
 	TP_ARGS(zone, order, ret)
 );
 
+#ifdef CONFIG_COMPACTION
+DECLARE_EVENT_CLASS(mm_compaction_defer_template,
+
+	TP_PROTO(struct zone *zone, int order),
+
+	TP_ARGS(zone, order),
+
+	TP_STRUCT__entry(
+		__field(int, nid)
+		__field(char *, name)
+		__field(int, order)
+		__field(unsigned int, considered)
+		__field(unsigned int, defer_shift)
+		__field(int, order_failed)
+	),
+
+	TP_fast_assign(
+		__entry->nid = zone_to_nid(zone);
+		__entry->name = (char *)zone->name;
+		__entry->order = order;
+		__entry->considered = zone->compact_considered;
+		__entry->defer_shift = zone->compact_defer_shift;
+		__entry->order_failed = zone->compact_order_failed;
+	),
+
+	TP_printk("node=%d zone=%-8s order=%d order_failed=%d consider=%u limit=%lu",
+		__entry->nid,
+		__entry->name,
+		__entry->order,
+		__entry->order_failed,
+		__entry->considered,
+		1UL << __entry->defer_shift)
+);
+
+DEFINE_EVENT(mm_compaction_defer_template, mm_compaction_deferred,
+
+	TP_PROTO(struct zone *zone, int order),
+
+	TP_ARGS(zone, order)
+);
+
+DEFINE_EVENT(mm_compaction_defer_template, mm_compaction_defer_compaction,
+
+	TP_PROTO(struct zone *zone, int order),
+
+	TP_ARGS(zone, order)
+);
+
+DEFINE_EVENT(mm_compaction_defer_template, mm_compaction_defer_reset,
+
+	TP_PROTO(struct zone *zone, int order),
+
+	TP_ARGS(zone, order)
+);
+#endif
+
 #endif /* _TRACE_COMPACTION_H */
 
 /* This part must be outside protection */
diff --git a/mm/compaction.c b/mm/compaction.c
index 8248a53..6183114 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -124,6 +124,77 @@ static struct page *pageblock_pfn_to_page(unsigned long start_pfn,
 }
 
 #ifdef CONFIG_COMPACTION
+
+/* Do not skip compaction more than 64 times */
+#define COMPACT_MAX_DEFER_SHIFT 6
+
+/*
+ * Compaction is deferred when compaction fails to result in a page
+ * allocation success. 1 << compact_defer_limit compactions are skipped up
+ * to a limit of 1 << COMPACT_MAX_DEFER_SHIFT
+ */
+void defer_compaction(struct zone *zone, int order)
+{
+	zone->compact_considered = 0;
+	zone->compact_defer_shift++;
+
+	if (order < zone->compact_order_failed)
+		zone->compact_order_failed = order;
+
+	if (zone->compact_defer_shift > COMPACT_MAX_DEFER_SHIFT)
+		zone->compact_defer_shift = COMPACT_MAX_DEFER_SHIFT;
+
+	trace_mm_compaction_defer_compaction(zone, order);
+}
+
+/* Returns true if compaction should be skipped this time */
+bool compaction_deferred(struct zone *zone, int order)
+{
+	unsigned long defer_limit = 1UL << zone->compact_defer_shift;
+
+	if (order < zone->compact_order_failed)
+		return false;
+
+	/* Avoid possible overflow */
+	if (++zone->compact_considered > defer_limit)
+		zone->compact_considered = defer_limit;
+
+	if (zone->compact_considered >= defer_limit)
+		return false;
+
+	trace_mm_compaction_deferred(zone, order);
+
+	return true;
+}
+
+/*
+ * Update defer tracking counters after successful compaction of given order,
+ * which means an allocation either succeeded (alloc_success == true) or is
+ * expected to succeed.
+ */
+void compaction_defer_reset(struct zone *zone, int order,
+		bool alloc_success)
+{
+	if (alloc_success) {
+		zone->compact_considered = 0;
+		zone->compact_defer_shift = 0;
+	}
+	if (order >= zone->compact_order_failed)
+		zone->compact_order_failed = order + 1;
+
+	trace_mm_compaction_defer_reset(zone, order);
+}
+
+/* Returns true if restarting compaction after many failures */
+bool compaction_restarting(struct zone *zone, int order)
+{
+	if (order < zone->compact_order_failed)
+		return false;
+
+	return zone->compact_defer_shift == COMPACT_MAX_DEFER_SHIFT &&
+		zone->compact_considered >= 1UL << zone->compact_defer_shift;
+}
+
 /* Returns true if the pageblock should be scanned for pages to isolate. */
 static inline bool isolation_suitable(struct compact_control *cc,
 					struct page *page)
-- 
1.7.9.5