The patch titled
Subject: mm/page_alloc: keep track of free highatomic
has been added to the -mm mm-unstable branch. Its filename is
mm-page_alloc-keep-track-of-free-highatomic.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-page_alloc-keep-track-of-free-highatomic.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Yu Zhao <yuzhao@xxxxxxxxxx>
Subject: mm/page_alloc: keep track of free highatomic
Date: Fri, 25 Oct 2024 21:36:25 -0600
OOM kills due to vastly overestimated free highatomic reserves were
observed:
... invoked oom-killer: gfp_mask=0x100cca(GFP_HIGHUSER_MOVABLE), order=0 ...
Node 0 Normal free:1482936kB boost:0kB min:410416kB low:739404kB high:1068392kB reserved_highatomic:1073152KB ...
Node 0 Normal: 1292*4kB (ME) 1920*8kB (E) 383*16kB (UE) 220*32kB (ME) 340*64kB (E) 2155*128kB (UE) 3243*256kB (UE) 615*512kB (U) 1*1024kB (M) 0*2048kB 0*4096kB = 1477408kB
The second line above shows that the OOM kill was due to the following
condition:
free (1482936kB) - reserved_highatomic (1073152kB) = 409784KB < min (410416kB)
And the third line shows there were no free pages in any
MIGRATE_HIGHATOMIC pageblocks, which otherwise would show up as type
'H'. Therefore __zone_watermark_unusable_free() underestimated the
usable free memory by over 1GB, which resulted in the unnecessary OOM
kill above.
The comments in __zone_watermark_unusable_free() warns about the
potential risk, i.e.,
If the caller does not have rights to reserves below the min
watermark then subtract the high-atomic reserves. This will
over-estimate the size of the atomic reserve but it avoids a search.
However, it is possible to keep track of free pages in reserved highatomic
pageblocks with a new per-zone counter nr_free_highatomic protected by the
zone lock, to avoid a search when calculating the usable free memory. And
the cost would be minimal, i.e., simple arithmetics in the highatomic
alloc/free/move paths.
Link: https://lkml.kernel.org/r/20241026033625.2237102-1-yuzhao@xxxxxxxxxx
Signed-off-by: Yu Zhao <yuzhao@xxxxxxxxxx>
Reported-by: Link Lin <linkl@xxxxxxxxxx>
Acked-by: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/mmzone.h | 1 +
mm/page_alloc.c | 23 ++++++++++++++++++++---
2 files changed, 21 insertions(+), 3 deletions(-)
--- a/include/linux/mmzone.h~mm-page_alloc-keep-track-of-free-highatomic
+++ a/include/linux/mmzone.h
@@ -825,6 +825,7 @@ struct zone {
unsigned long watermark_boost;
unsigned long nr_reserved_highatomic;
+ unsigned long nr_free_highatomic;
/*
* We don't know if the memory that we're going to allocate will be
--- a/mm/page_alloc.c~mm-page_alloc-keep-track-of-free-highatomic
+++ a/mm/page_alloc.c
@@ -644,6 +644,18 @@ static inline void account_freepages(str
__mod_zone_page_state(zone, NR_FREE_CMA_PAGES, nr_pages);
}
+static void account_highatomic_freepages(struct zone *zone, unsigned int order,
+ int old_mt, int new_mt)
+{
+ int delta = 1 << order;
+
+ if (is_migrate_highatomic(old_mt))
+ WRITE_ONCE(zone->nr_free_highatomic, zone->nr_free_highatomic - delta);
+
+ if (is_migrate_highatomic(new_mt))
+ WRITE_ONCE(zone->nr_free_highatomic, zone->nr_free_highatomic + delta);
+}
+
/* Used for pages not on another list */
static inline void __add_to_free_list(struct page *page, struct zone *zone,
unsigned int order, int migratetype,
@@ -660,6 +672,8 @@ static inline void __add_to_free_list(st
else
list_add(&page->buddy_list, &area->free_list[migratetype]);
area->nr_free++;
+
+ account_highatomic_freepages(zone, order, -1, migratetype);
}
/*
@@ -681,6 +695,8 @@ static inline void move_to_free_list(str
account_freepages(zone, -(1 << order), old_mt);
account_freepages(zone, 1 << order, new_mt);
+
+ account_highatomic_freepages(zone, order, old_mt, new_mt);
}
static inline void __del_page_from_free_list(struct page *page, struct zone *zone,
@@ -698,6 +714,8 @@ static inline void __del_page_from_free_
__ClearPageBuddy(page);
set_page_private(page, 0);
zone->free_area[order].nr_free--;
+
+ account_highatomic_freepages(zone, order, migratetype, -1);
}
static inline void del_page_from_free_list(struct page *page, struct zone *zone,
@@ -3081,11 +3099,10 @@ static inline long __zone_watermark_unus
/*
* If the caller does not have rights to reserves below the min
- * watermark then subtract the high-atomic reserves. This will
- * over-estimate the size of the atomic reserve but it avoids a search.
+ * watermark then subtract the free pages reserved for highatomic.
*/
if (likely(!(alloc_flags & ALLOC_RESERVES)))
- unusable_free += z->nr_reserved_highatomic;
+ unusable_free += READ_ONCE(z->nr_free_highatomic);
#ifdef CONFIG_CMA
/* If allocation can't use CMA areas don't use free CMA pages */
_
Patches currently in -mm which might be from yuzhao@xxxxxxxxxx are
mm-allow-set-clear-page_type-again.patch
mm-multi-gen-lru-remove-mm_leaf_old-and-mm_nonleaf_total-stats.patch
mm-multi-gen-lru-use-pteppmdp_clear_young_notify.patch
mm-page_alloc-keep-track-of-free-highatomic.patch
