linux-kernel - [PATCH] mm:ALLOC_HIGHATOMIC flag allocation issuse

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-ID: <20231108065408.1861-1-justinjiang@vivo.com>
Date:   Wed,  8 Nov 2023 14:54:07 +0800
From:   Zhiguo Jiang <justinjiang@...o.com>
To:     Andrew Morton <akpm@...ux-foundation.org>, linux-mm@...ck.org,
        linux-kernel@...r.kernel.org
Cc:     Johannes Weiner <hannes@...xchg.org>, opensource.kernel@...o.com,
        Zhiguo Jiang <justinjiang@...o.com>
Subject: [PATCH] mm:ALLOC_HIGHATOMIC flag allocation issuse

In case that alloc_flags contains ALLOC_HIGHATOMIC and alloc order
is order1/2/3/10 in rmqueue(), if pages are alloced successfully
from pcplist, a free pageblock will be also moved from the alloced
migratetype freelist to MIGRATE_HIGHATOMIC freelist, rather than
alloc from MIGRATE_HIGHATOMIC freelist firstly, so this will result
in an increasing number of pages on the MIGRATE_HIGHATOMIC freelist,
pages in other migratetype freelist are reduced and more likely to
allocation failure.

Currently the sequence of ALLOC_HIGHATOMIC allocation is:
pcplist --> rmqueue_bulk() --> rmqueue_buddy() MIGRATE_HIGHATOMIC
--> rmqueue_buddy() allocation migratetype.

Due to the fact that requesting pages from the pcplist is faster than
buddy, the sequence of modifying the ALLOC_HIGHATOMIC allocation is:
pcplist --> rmqueue_buddy() MIGRATE_HIGHATOMIC --> rmqueue_buddy()
allocation migratetype.

This patch can solve the failure problem of allocating other types of
pages due to excessive MIGRATE_HIGHATOMIC freelist reservations.

In comparative testing, cat /proc/pagetypeinfo and the HighAtomic
freelist size is:
Test without this patch:
Node 0, zone Normal, type HighAtomic 2369 771 138 15 0 0 0 0 0 0 0
Test with this patch:
Node 0, zone Normal, type HighAtomic 206 82 4 2 1 0 0 0 0 0 0 

Signed-off-by: Zhiguo Jiang <justinjiang@...o.com>
---
 mm/internal.h   |  1 +
 mm/page_alloc.c | 21 ++++++++++++++-------
 2 files changed, 15 insertions(+), 7 deletions(-)
 mode change 100644 => 100755 mm/internal.h
 mode change 100644 => 100755 mm/page_alloc.c

diff --git a/mm/internal.h b/mm/internal.h
index b61034bd50f5..f523242baf0c
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -905,6 +905,7 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone,
 #endif
 #define ALLOC_HIGHATOMIC	0x200 /* Allows access to MIGRATE_HIGHATOMIC */
 #define ALLOC_KSWAPD		0x800 /* allow waking of kswapd, __GFP_KSWAPD_RECLAIM set */
+#define ALLOC_PCPLIST		0x1000 /* Allocations from pcplist */
 
 /* Flags that allow allocations below the min watermark. */
 #define ALLOC_RESERVES (ALLOC_NON_BLOCK|ALLOC_MIN_RESERVE|ALLOC_HIGHATOMIC|ALLOC_OOM)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index b8544f08cc36..67cec88164b1
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2854,11 +2854,15 @@ struct page *__rmqueue_pcplist(struct zone *zone, unsigned int order,
 			int batch = nr_pcp_alloc(pcp, zone, order);
 			int alloced;
 
+			if (alloc_flags & ALLOC_HIGHATOMIC)
+				goto out;
+
 			alloced = rmqueue_bulk(zone, order,
 					batch, list,
 					migratetype, alloc_flags);
 
 			pcp->count += alloced << order;
+out:
 			if (unlikely(list_empty(list)))
 				return NULL;
 		}
@@ -2921,7 +2925,7 @@ __no_sanitize_memory
 static inline
 struct page *rmqueue(struct zone *preferred_zone,
 			struct zone *zone, unsigned int order,
-			gfp_t gfp_flags, unsigned int alloc_flags,
+			gfp_t gfp_flags, unsigned int *alloc_flags,
 			int migratetype)
 {
 	struct page *page;
@@ -2934,17 +2938,19 @@ struct page *rmqueue(struct zone *preferred_zone,
 
 	if (likely(pcp_allowed_order(order))) {
 		page = rmqueue_pcplist(preferred_zone, zone, order,
-				       migratetype, alloc_flags);
-		if (likely(page))
+				       migratetype, *alloc_flags);
+		if (likely(page)) {
+			*alloc_flags |= ALLOC_PCPLIST;
 			goto out;
+		}
 	}
 
-	page = rmqueue_buddy(preferred_zone, zone, order, alloc_flags,
+	page = rmqueue_buddy(preferred_zone, zone, order, *alloc_flags,
 							migratetype);

 out:
 	/* Separate test+clear to avoid unnecessary atomics */
-	if ((alloc_flags & ALLOC_KSWAPD) &&
+	if ((*alloc_flags & ALLOC_KSWAPD) &&
 	    unlikely(test_bit(ZONE_BOOSTED_WATERMARK, &zone->flags))) {
 		clear_bit(ZONE_BOOSTED_WATERMARK, &zone->flags);
 		wakeup_kswapd(zone, 0, 0, zone_idx(zone));
@@ -3343,7 +3349,7 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
 
 try_this_zone:
 		page = rmqueue(ac->preferred_zoneref->zone, zone, order,
-				gfp_mask, alloc_flags, ac->migratetype);
+				gfp_mask, &alloc_flags, ac->migratetype);
 		if (page) {
 			prep_new_page(page, order, gfp_mask, alloc_flags);
 
@@ -3351,7 +3357,8 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
 			 * If this is a high-order atomic allocation then check
 			 * if the pageblock should be reserved for the future
 			 */
-			if (unlikely(alloc_flags & ALLOC_HIGHATOMIC))
+			if (unlikely(alloc_flags & ALLOC_HIGHATOMIC) &&
+				unlikely(!(alloc_flags & ALLOC_PCPLIST)))
 				reserve_highatomic_pageblock(page, zone);
 
 			return page;
-- 
2.39.0