[PATCH] mm/page_alloc: Fix tracepoint mm_page_alloc_zone_locked()

[Wonhyuk Yang]

Currently, trace point mm_page_alloc_zone_locked() doesn't show
correct information.

First, when alloc_flag has ALLOC_HARDER/ALLOC_CMA, page can
be allocated from MIGRATE_HIGHATOMIC/MIGRATE_CMA. Nevertheless,
tracepoint use requested migration type not MIGRATE_HIGHATOMIC and
MIGRATE_CMA.

Second, after Commit 44042b4498728 ("mm/page_alloc: allow high-order
pages to be stored on the per-cpu lists") percpu-list can store
high order pages. But trace point determine whether it is a refiil
of percpu-list by comparing requested order and 0.

To handle these problems, use cached migration type by
get_pcppage_migratetype() instead of requested migration type.
Then, make mm_page_alloc_zone_locked() be called only two contexts
(rmqueue_bulk, rmqueue). With a new argument called percpu_refill,
it can show whether it is a refill of percpu-list correctly.

Cc: Baik Song An <bsahn@xxxxxxxxxx>
Cc: Hong Yeon Kim <kimhy@xxxxxxxxxx>
Cc: Taeung Song <taeung@xxxxxxxxxxxxxxx>
Cc: linuxgeek@xxxxxxxxxxxx
Signed-off-by: Wonhyuk Yang <vvghjk1234@xxxxxxxxx>
---
 include/trace/events/kmem.h | 14 +++++++++-----
 mm/page_alloc.c             | 18 +++++++++---------
 2 files changed, 18 insertions(+), 14 deletions(-)

diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index ddc8c944f417..f89fb3afcd46 100644
--- a/include/trace/events/kmem.h
+++ b/include/trace/events/kmem.h
@@ -229,20 +229,23 @@ TRACE_EVENT(mm_page_alloc,
 
 DECLARE_EVENT_CLASS(mm_page,
 
-	TP_PROTO(struct page *page, unsigned int order, int migratetype),
+	TP_PROTO(struct page *page, unsigned int order, int migratetype,
+		 int percpu_refill),
 
-	TP_ARGS(page, order, migratetype),
+	TP_ARGS(page, order, migratetype, percpu_refill),
 
 	TP_STRUCT__entry(
 		__field(	unsigned long,	pfn		)
 		__field(	unsigned int,	order		)
 		__field(	int,		migratetype	)
+		__field(	int,		percpu_refill	)
 	),
 
 	TP_fast_assign(
 		__entry->pfn		= page ? page_to_pfn(page) : -1UL;
 		__entry->order		= order;
 		__entry->migratetype	= migratetype;
+		__entry->percpu_refill	= percpu_refill;
 	),
 
 	TP_printk("page=%p pfn=0x%lx order=%u migratetype=%d percpu_refill=%d",
@@ -250,14 +253,15 @@ DECLARE_EVENT_CLASS(mm_page,
 		__entry->pfn != -1UL ? __entry->pfn : 0,
 		__entry->order,
 		__entry->migratetype,
-		__entry->order == 0)
+		__entry->percpu_refill)
 );
 
 DEFINE_EVENT(mm_page, mm_page_alloc_zone_locked,
 
-	TP_PROTO(struct page *page, unsigned int order, int migratetype),
+	TP_PROTO(struct page *page, unsigned int order, int migratetype,
+		 int percpu_refill),
 
-	TP_ARGS(page, order, migratetype)
+	TP_ARGS(page, order, migratetype, percpu_refill)
 );
 
 TRACE_EVENT(mm_page_pcpu_drain,
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 0e42038382c1..0351808322ba 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2999,7 +2999,7 @@ __rmqueue(struct zone *zone, unsigned int order, int migratetype,
 		    zone_page_state(zone, NR_FREE_PAGES) / 2) {
 			page = __rmqueue_cma_fallback(zone, order);
 			if (page)
-				goto out;
+				return page;
 		}
 	}
 retry:
@@ -3012,9 +3012,6 @@ __rmqueue(struct zone *zone, unsigned int order, int migratetype,
 								alloc_flags))
 			goto retry;
 	}
-out:
-	if (page)
-		trace_mm_page_alloc_zone_locked(page, order, migratetype);
 	return page;
 }
 
@@ -3028,6 +3025,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
 			int migratetype, unsigned int alloc_flags)
 {
 	int i, allocated = 0;
+	int mt;
 
 	/*
 	 * local_lock_irq held so equivalent to spin_lock_irqsave for
@@ -3055,7 +3053,9 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
 		 */
 		list_add_tail(&page->lru, list);
 		allocated++;
-		if (is_migrate_cma(get_pcppage_migratetype(page)))
+		mt = get_pcppage_migratetype(page);
+		trace_mm_page_alloc_zone_locked(page, order, mt, true);
+		if (is_migrate_cma(mt))
 			__mod_zone_page_state(zone, NR_FREE_CMA_PAGES,
 					      -(1 << order));
 	}
@@ -3704,6 +3704,7 @@ struct page *rmqueue(struct zone *preferred_zone,
 {
 	unsigned long flags;
 	struct page *page;
+	int mt;
 
 	if (likely(pcp_allowed_order(order))) {
 		/*
@@ -3735,16 +3736,15 @@ struct page *rmqueue(struct zone *preferred_zone,
 		 */
 		if (order > 0 && alloc_flags & ALLOC_HARDER) {
 			page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC);
-			if (page)
-				trace_mm_page_alloc_zone_locked(page, order, migratetype);
 		}
 		if (!page) {
 			page = __rmqueue(zone, order, migratetype, alloc_flags);
 			if (!page)
 				goto failed;
 		}
-		__mod_zone_freepage_state(zone, -(1 << order),
-					  get_pcppage_migratetype(page));
+		mt = get_pcppage_migratetype(page);
+		trace_mm_page_alloc_zone_locked(page, order, mt, false);
+		__mod_zone_freepage_state(zone, -(1 << order), mt);
 		spin_unlock_irqrestore(&zone->lock, flags);
 	} while (check_new_pages(page, order));
 
-- 
2.30.2