The quilt patch titled
Subject: mm: optimization on page allocation when CMA enabled
has been removed from the -mm tree. Its filename was
mm-optimization-on-page-allocation-when-cma-enabled.patch
This patch was dropped because it is obsolete
------------------------------------------------------
From: Zhaoyang Huang <zhaoyang.huang@xxxxxxxxxx>
Subject: mm: optimization on page allocation when CMA enabled
Date: Thu, 11 May 2023 13:22:30 +0800
According to current CMA utilization policy, an alloc_pages(GFP_USER)
could 'steal' UNMOVABLE & RECLAIMABLE page blocks via the help of CMA(pass
zone_watermark_ok by counting CMA in but use U&R in rmqueue), which could
lead to following alloc_pages(GFP_KERNEL) fail. Solving this by
introducing second watermark checking for GFP_MOVABLE, which could have
the allocation use CMA when proper.
-- Free_pages(30MB)
|
|
-- WMARK_LOW(25MB)
|
-- Free_CMA(12MB)
|
|
--
Link: https://lkml.kernel.org/r/20231016071245.2865233-1-zhaoyang.huang@xxxxxxxxxx
Link: https://lkml.kernel.org/r/1683782550-25799-1-git-send-email-zhaoyang.huang@xxxxxxxxxx
Signed-off-by: Zhaoyang Huang <zhaoyang.huang@xxxxxxxxxx>
Cc: Joonsoo Kim <iamjoonsoo.kim@xxxxxxx>
Cc: ke.wang <ke.wang@xxxxxxxxxx>
Cc: Minchan Kim <minchan@xxxxxxxxxx>
Cc: Roman Gushchin <roman.gushchin@xxxxxxxxx>
Cc: Zhaoyang Huang <huangzhaoyang@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/page_alloc.c | 44 ++++++++++++++++++++++++++++++++++++++++----
1 file changed, 40 insertions(+), 4 deletions(-)
--- a/mm/page_alloc.c~mm-optimization-on-page-allocation-when-cma-enabled
+++ a/mm/page_alloc.c
@@ -2262,6 +2262,43 @@ do_steal:
return page;
}
+#ifdef CONFIG_CMA
+/*
+ * GFP_MOVABLE allocation could drain UNMOVABLE & RECLAIMABLE page blocks via
+ * the help of CMA which makes GFP_KERNEL failed. Checking if zone_watermark_ok
+ * again without ALLOC_CMA to see if to use CMA first.
+ */
+static bool use_cma_first(struct zone *zone, unsigned int order, unsigned int alloc_flags)
+{
+ unsigned long watermark;
+ bool cma_first = false;
+
+ watermark = wmark_pages(zone, alloc_flags & ALLOC_WMARK_MASK);
+ /* check if GFP_MOVABLE pass previous zone_watermark_ok via the help of CMA */
+ if (zone_watermark_ok(zone, order, watermark, 0, alloc_flags & (~ALLOC_CMA))) {
+ /*
+ * Balance movable allocations between regular and CMA areas by
+ * allocating from CMA when over half of the zone's free memory
+ * is in the CMA area.
+ */
+ cma_first = (zone_page_state(zone, NR_FREE_CMA_PAGES) >
+ zone_page_state(zone, NR_FREE_PAGES) / 2);
+ } else {
+ /*
+ * watermark failed means UNMOVABLE & RECLAIMBLE is not enough
+ * now, we should use cma first to keep them stay around the
+ * corresponding watermark
+ */
+ cma_first = true;
+ }
+ return cma_first;
+}
+#else
+static bool use_cma_first(struct zone *zone, unsigned int order, unsigned int alloc_flags)
+{
+ return false;
+}
+#endif
/*
* Do the hard work of removing an element from the buddy allocator.
* Call me with the zone->lock already held.
@@ -2275,12 +2312,11 @@ __rmqueue(struct zone *zone, unsigned in
if (IS_ENABLED(CONFIG_CMA)) {
/*
* Balance movable allocations between regular and CMA areas by
- * allocating from CMA when over half of the zone's free memory
- * is in the CMA area.
+ * allocating from CMA base on judging zone_watermark_ok again
+ * to see if the latest check got pass via the help of CMA
*/
if (alloc_flags & ALLOC_CMA &&
- zone_page_state(zone, NR_FREE_CMA_PAGES) >
- zone_page_state(zone, NR_FREE_PAGES) / 2) {
+ use_cma_first(zone, order, alloc_flags)) {
page = __rmqueue_cma_fallback(zone, order);
if (page)
return page;
_
Patches currently in -mm which might be from zhaoyang.huang@xxxxxxxxxx are
