mm/page_alloc: fix tracepoint mm_page_alloc_zone_locked()

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 44042b4 ("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, make mm_page_alloc_zone_locked() only be called
by __rmqueue_smallest with correct migration type.  With a new argument
called percpu_refill, it can show roughly whether it is a refill of
percpu-list.

Link: https://lkml.kernel.org/r/20220512025307.57924-1-vvghjk1234@gmail.com
Signed-off-by: Wonhyuk Yang <vvghjk1234@gmail.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Baik Song An <bsahn@etri.re.kr>
Cc: Hong Yeon Kim <kimhy@etri.re.kr>
Cc: Taeung Song <taeung@reallinux.co.kr>
Cc: <linuxgeek@linuxgeek.io>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Author: YWHyuk

include/trace/events/kmem.h

@@ -229,35 +229,39 @@ 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",
 		__entry->pfn != -1UL ? pfn_to_page(__entry->pfn) : NULL,
 		__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,

mm/page_alloc.c

@@ -2466,6 +2466,9 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
 		del_page_from_free_list(page, zone, current_order);
 		expand(zone, page, order, current_order, migratetype);
 		set_pcppage_migratetype(page, migratetype);
+		trace_mm_page_alloc_zone_locked(page, order, migratetype,
+				pcp_allowed_order(order) &&
+				migratetype < MIGRATE_PCPTYPES);
 		return page;
 	}
 
@@ -2989,7 +2992,7 @@ __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:
@@ -3002,9 +3005,6 @@ __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;
 }
 
@@ -3723,11 +3723,8 @@ struct page *rmqueue(struct zone *preferred_zone,
 		 * reserved for high-order atomic allocation, so order-0
 		 * request should skip it.
 		 */
-		if (order > 0 && alloc_flags & ALLOC_HARDER) {
+		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)