5.15-stable review patch. If anyone has any objections, please let me know.
------------------
From: Wonhyuk Yang <vvghjk1234@xxxxxxxxx>
[ Upstream commit 10e0f7530205799e7e971aba699a7cb3a47456de ]
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, 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@xxxxxxxxx
Signed-off-by: Wonhyuk Yang <vvghjk1234@xxxxxxxxx>
Acked-by: Mel Gorman <mgorman@xxxxxxx>
Cc: Baik Song An <bsahn@xxxxxxxxxx>
Cc: Hong Yeon Kim <kimhy@xxxxxxxxxx>
Cc: Taeung Song <taeung@xxxxxxxxxxxxxxx>
Cc: <linuxgeek@xxxxxxxxxxxx>
Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Stable-dep-of: 281dd25c1a01 ("mm/page_alloc: let GFP_ATOMIC order-0 allocs access highatomic reserves")
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
include/trace/events/kmem.h | 14 +++++++++-----
mm/page_alloc.c | 13 +++++--------
2 files changed, 14 insertions(+), 13 deletions(-)
diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index ddc8c944f417a..f89fb3afcd46a 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 474150584ba48..264cb1914ab5b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2461,6 +2461,9 @@ 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;
}
@@ -2988,7 +2991,7 @@ __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:
@@ -3001,9 +3004,6 @@ __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;
}
@@ -3708,11 +3708,8 @@ 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)
--
2.43.0
