linux-kernel - [PATCH v4 2/2] mm: Init page count in reserve_bootmem_region when MEMINIT

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-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20230928083302.386202-3-yajun.deng@linux.dev>
Date:   Thu, 28 Sep 2023 16:33:02 +0800
From:   Yajun Deng <yajun.deng@...ux.dev>
To:     akpm@...ux-foundation.org, rppt@...nel.org
Cc:     mike.kravetz@...cle.com, muchun.song@...ux.dev,
        willy@...radead.org, david@...hat.com, linux-mm@...ck.org,
        linux-kernel@...r.kernel.org, Yajun Deng <yajun.deng@...ux.dev>
Subject: [PATCH v4 2/2] mm: Init page count in reserve_bootmem_region when MEMINIT_EARLY

memmap_init_range() would init page count of all pages, but the free
pages count would be reset in __free_pages_core(). There are opposite
operations. It's unnecessary and time-consuming when it's MEMINIT_EARLY
context.

Init page count in reserve_bootmem_region when in MEMINIT_EARLY context,
and check the page count before reset it.

At the same time, the INIT_LIST_HEAD in reserve_bootmem_region isn't
need, as it already done in __init_single_page.

The following data was tested on an x86 machine with 190GB of RAM.

before:
free_low_memory_core_early()    341ms

after:
free_low_memory_core_early()    285ms

Signed-off-by: Yajun Deng <yajun.deng@...ux.dev>
---
v4: same with v2.
v3: same with v2.
v2: check page count instead of check context before reset it.
v1: https://lore.kernel.org/all/20230922070923.355656-1-yajun.deng@linux.dev/
---
 mm/mm_init.c    | 18 +++++++++++++-----
 mm/page_alloc.c | 20 ++++++++++++--------
 2 files changed, 25 insertions(+), 13 deletions(-)

diff --git a/mm/mm_init.c b/mm/mm_init.c
index 9716c8a7ade9..3ab8861e1ef3 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -718,7 +718,7 @@ static void __meminit init_reserved_page(unsigned long pfn, int nid)
 		if (zone_spans_pfn(zone, pfn))
 			break;
 	}
-	__init_single_page(pfn_to_page(pfn), pfn, zid, nid, INIT_PAGE_COUNT);
+	__init_single_page(pfn_to_page(pfn), pfn, zid, nid, 0);
 }
 #else
 static inline void pgdat_set_deferred_range(pg_data_t *pgdat) {}
@@ -756,8 +756,8 @@ void __meminit reserve_bootmem_region(phys_addr_t start,
 
 			init_reserved_page(start_pfn, nid);
 
-			/* Avoid false-positive PageTail() */
-			INIT_LIST_HEAD(&page->lru);
+			/* Init page count for reserved region */
+			init_page_count(page);
 
 			/*
 			 * no need for atomic set_bit because the struct
@@ -888,9 +888,17 @@ void __meminit memmap_init_range(unsigned long size, int nid, unsigned long zone
 		}
 
 		page = pfn_to_page(pfn);
-		__init_single_page(page, pfn, zone, nid, INIT_PAGE_COUNT);
-		if (context == MEMINIT_HOTPLUG)
+
+		/* If the context is MEMINIT_EARLY, we will init page count and
+		 * mark page reserved in reserve_bootmem_region, the free region
+		 * wouldn't have page count and we will check the pages count
+		 * in __free_pages_core.
+		 */
+		__init_single_page(page, pfn, zone, nid, 0);
+		if (context == MEMINIT_HOTPLUG) {
+			init_page_count(page);
 			__SetPageReserved(page);
+		}
 
 		/*
 		 * Usually, we want to mark the pageblock MIGRATE_MOVABLE,
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 06be8821d833..b868caabe8dc 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1285,18 +1285,22 @@ void __free_pages_core(struct page *page, unsigned int order)
 	unsigned int loop;
 
 	/*
-	 * When initializing the memmap, __init_single_page() sets the refcount
-	 * of all pages to 1 ("allocated"/"not free"). We have to set the
-	 * refcount of all involved pages to 0.
+	 * When initializing the memmap, memmap_init_range sets the refcount
+	 * of all pages to 1 ("reserved" and "free") in hotplug context. We
+	 * have to set the refcount of all involved pages to 0. Otherwise,
+	 * we don't do it, as reserve_bootmem_region only set the refcount on
+	 * reserve region ("reserved") in early context.
 	 */
-	prefetchw(p);
-	for (loop = 0; loop < (nr_pages - 1); loop++, p++) {
-		prefetchw(p + 1);
+	if (page_count(page)) {
+		prefetchw(p);
+		for (loop = 0; loop < (nr_pages - 1); loop++, p++) {
+			prefetchw(p + 1);
+			__ClearPageReserved(p);
+			set_page_count(p, 0);
+		}
 		__ClearPageReserved(p);
 		set_page_count(p, 0);
 	}
-	__ClearPageReserved(p);
-	set_page_count(p, 0);
 
 	atomic_long_add(nr_pages, &page_zone(page)->managed_pages);
 
-- 
2.25.1