linux-kernel - [PATCH v3] mm: fix accounting of memmap pages

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>] [day] [month] [year] [list]

Message-ID: <20250807182531.1321991-1-sumanthk@linux.ibm.com>
Date: Thu,  7 Aug 2025 20:25:31 +0200
From: Sumanth Korikkar <sumanthk@...ux.ibm.com>
To: Andrew Morton <akpm@...ux-foundation.org>, linux-mm <linux-mm@...ck.org>,
        LKML <linux-kernel@...r.kernel.org>,
        David Hildenbrand <david@...hat.com>, richard.weiyang@...il.com
Cc: Gerald Schaefer <gerald.schaefer@...ux.ibm.com>,
        Heiko Carstens <hca@...ux.ibm.com>, Vasily Gorbik <gor@...ux.ibm.com>,
        Alexander Gordeev <agordeev@...ux.ibm.com>,
        linux-s390 <linux-s390@...r.kernel.org>, sumanthk@...ux.ibm.com
Subject: [PATCH v3] mm: fix accounting of memmap pages

For !CONFIG_SPARSEMEM_VMEMMAP, memmap page accounting is currently done
upfront in sparse_buffer_init(). However, sparse_buffer_alloc() may
return NULL in failure scenario.

Also, memmap pages may be allocated either from the memblock allocator
during early boot or from the buddy allocator. When removed via
arch_remove_memory(), accounting of memmap pages must reflect the
original allocation source.

To ensure correctness:
* Account memmap pages after successful allocation in sparse_init_nid()
  and section_activate().
* Account memmap pages in section_deactivate() based on allocation
  source.

Signed-off-by: Sumanth Korikkar <sumanthk@...ux.ibm.com>
---
v3: 
* Account memmap pages for !CONFIG_SPARSEMEM_VMEMMAP and only when memmap
  allocation succeeds. Thanks Wei Yang.

v2: 
* Account memmap pages for  !CONFIG_SPARSEMEM_VMEMMAP in
  section_deactivate().  Thanks David.
* https://lore.kernel.org/all/20250804151328.2326642-1-sumanthk@linux.ibm.com/

v1: 
* Account memmap pages for early sections.
* https://lore.kernel.org/all/20250804084015.270570-1-sumanthk@linux.ibm.com/

 mm/sparse-vmemmap.c |  5 -----
 mm/sparse.c         | 15 +++++++++------
 2 files changed, 9 insertions(+), 11 deletions(-)

diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index fd2ab5118e13..41aa0493eb03 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -578,11 +578,6 @@ struct page * __meminit __populate_section_memmap(unsigned long pfn,
 	if (r < 0)
 		return NULL;
 
-	if (system_state == SYSTEM_BOOTING)
-		memmap_boot_pages_add(DIV_ROUND_UP(end - start, PAGE_SIZE));
-	else
-		memmap_pages_add(DIV_ROUND_UP(end - start, PAGE_SIZE));
-
 	return pfn_to_page(pfn);
 }
 
diff --git a/mm/sparse.c b/mm/sparse.c
index 066cbf82acb8..24323122f6cb 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -454,9 +454,6 @@ static void __init sparse_buffer_init(unsigned long size, int nid)
 	 */
 	sparsemap_buf = memmap_alloc(size, section_map_size(), addr, nid, true);
 	sparsemap_buf_end = sparsemap_buf + size;
-#ifndef CONFIG_SPARSEMEM_VMEMMAP
-	memmap_boot_pages_add(DIV_ROUND_UP(size, PAGE_SIZE));
-#endif
 }
 
 static void __init sparse_buffer_fini(void)
@@ -567,6 +564,8 @@ static void __init sparse_init_nid(int nid, unsigned long pnum_begin,
 				sparse_buffer_fini();
 				goto failed;
 			}
+			memmap_boot_pages_add(DIV_ROUND_UP(PAGES_PER_SECTION * sizeof(struct page),
+							   PAGE_SIZE));
 			sparse_init_early_section(nid, map, pnum, 0);
 		}
 	}
@@ -680,7 +679,6 @@ static void depopulate_section_memmap(unsigned long pfn, unsigned long nr_pages,
 	unsigned long start = (unsigned long) pfn_to_page(pfn);
 	unsigned long end = start + nr_pages * sizeof(struct page);
 
-	memmap_pages_add(-1L * (DIV_ROUND_UP(end - start, PAGE_SIZE)));
 	vmemmap_free(start, end, altmap);
 }
 static void free_map_bootmem(struct page *memmap)
@@ -856,10 +854,14 @@ static void section_deactivate(unsigned long pfn, unsigned long nr_pages,
 	 * The memmap of early sections is always fully populated. See
 	 * section_activate() and pfn_valid() .
 	 */
-	if (!section_is_early)
+	if (!section_is_early) {
+		memmap_pages_add(-1L * (DIV_ROUND_UP(nr_pages * sizeof(struct page), PAGE_SIZE)));
 		depopulate_section_memmap(pfn, nr_pages, altmap);
-	else if (memmap)
+	} else if (memmap) {
+		memmap_boot_pages_add(-1L * (DIV_ROUND_UP(nr_pages * sizeof(struct page),
+							  PAGE_SIZE)));
 		free_map_bootmem(memmap);
+	}
 
 	if (empty)
 		ms->section_mem_map = (unsigned long)NULL;
@@ -904,6 +906,7 @@ static struct page * __meminit section_activate(int nid, unsigned long pfn,
 		section_deactivate(pfn, nr_pages, altmap);
 		return ERR_PTR(-ENOMEM);
 	}
+	memmap_pages_add(DIV_ROUND_UP(nr_pages * sizeof(struct page), PAGE_SIZE));
 
 	return memmap;
 }
-- 
2.48.1