This is a note to let you know that I've just added the patch titled
mm/page_alloc: explicitly define what alloc flags deplete min reserves
to the 6.1-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
mm-page_alloc-explicitly-define-what-alloc-flags-dep.patch
and it can be found in the queue-6.1 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit 7f56b2ec2c70a47a901ef2da605c6c7552cd71c2
Author: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
Date: Fri Jan 13 11:12:15 2023 +0000
mm/page_alloc: explicitly define what alloc flags deplete min reserves
[ Upstream commit ab3508854353793cd35e348fde89a5c09b2fd8b5 ]
As there are more ALLOC_ flags that affect reserves, define what flags
affect reserves and clarify the effect of each flag.
Link: https://lkml.kernel.org/r/20230113111217.14134-5-mgorman@xxxxxxxxxxxxxxxxxxx
Signed-off-by: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
Acked-by: Vlastimil Babka <vbabka@xxxxxxx>
Acked-by: Michal Hocko <mhocko@xxxxxxxx>
Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
Cc: NeilBrown <neilb@xxxxxxx>
Cc: Thierry Reding <thierry.reding@xxxxxxxxx>
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>
diff --git a/mm/internal.h b/mm/internal.h
index f0f6198462cc1..cd095ce2f199e 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -768,6 +768,9 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone,
#define ALLOC_HIGHATOMIC 0x200 /* Allows access to MIGRATE_HIGHATOMIC */
#define ALLOC_KSWAPD 0x800 /* allow waking of kswapd, __GFP_KSWAPD_RECLAIM set */
+/* Flags that allow allocations below the min watermark. */
+#define ALLOC_RESERVES (ALLOC_HARDER|ALLOC_MIN_RESERVE|ALLOC_HIGHATOMIC|ALLOC_OOM)
+
enum ttu_flags;
struct tlbflush_unmap_batch;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 8e1f4d779b26c..6ab53e47ccea1 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3956,15 +3956,14 @@ ALLOW_ERROR_INJECTION(should_fail_alloc_page, TRUE);
static inline long __zone_watermark_unusable_free(struct zone *z,
unsigned int order, unsigned int alloc_flags)
{
- const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM));
long unusable_free = (1 << order) - 1;
/*
- * If the caller does not have rights to ALLOC_HARDER then subtract
- * the high-atomic reserves. This will over-estimate the size of the
- * atomic reserve but it avoids a search.
+ * 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.
*/
- if (likely(!alloc_harder))
+ if (likely(!(alloc_flags & ALLOC_RESERVES)))
unusable_free += z->nr_reserved_highatomic;
#ifdef CONFIG_CMA
@@ -3988,25 +3987,36 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
{
long min = mark;
int o;
- const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM));
/* free_pages may go negative - that's OK */
free_pages -= __zone_watermark_unusable_free(z, order, alloc_flags);
- if (alloc_flags & ALLOC_MIN_RESERVE)
- min -= min / 2;
+ if (unlikely(alloc_flags & ALLOC_RESERVES)) {
+ /*
+ * __GFP_HIGH allows access to 50% of the min reserve as well
+ * as OOM.
+ */
+ if (alloc_flags & ALLOC_MIN_RESERVE)
+ min -= min / 2;
- if (unlikely(alloc_harder)) {
/*
- * OOM victims can try even harder than normal ALLOC_HARDER
+ * Non-blocking allocations can access some of the reserve
+ * with more access if also __GFP_HIGH. The reasoning is that
+ * a non-blocking caller may incur a more severe penalty
+ * if it cannot get memory quickly, particularly if it's
+ * also __GFP_HIGH.
+ */
+ if (alloc_flags & ALLOC_HARDER)
+ min -= min / 4;
+
+ /*
+ * OOM victims can try even harder than the normal reserve
* users on the grounds that it's definitely going to be in
* the exit path shortly and free memory. Any allocation it
* makes during the free path will be small and short-lived.
*/
if (alloc_flags & ALLOC_OOM)
min -= min / 2;
- else
- min -= min / 4;
}
/*
