mm: fix accounting of memmap pages

[ Upstream commit c3576889d87b603cb66b417e08844a53c1077a37 ]

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.

Link: https://lkml.kernel.org/r/20250807183545.1424509-1-sumanthk@linux.ibm.com
Fixes: 15995a352474 ("mm: report per-page metadata information")
Signed-off-by: Sumanth Korikkar <sumanthk@linux.ibm.com>
Suggested-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Wei Yang <richard.weiyang@gmail.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

2 files changed, 9 insertions, 11 deletions

diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index c0388b2e959d..2628fc02be08 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -474,10 +474,5 @@ 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 dc38539f8560..eb6c5cb27ed1 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -462,9 +462,6 @@ 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)
@@ -532,6 +529,8 @@ 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));
 		check_usemap_section_nr(nid, usage);
 		sparse_init_one_section(__nr_to_section(pnum), pnum, map, usage,
 				SECTION_IS_EARLY);
@@ -643,7 +642,6 @@ 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)
@@ -819,10 +817,14 @@ 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;
@@ -867,6 +869,7 @@ 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;
 }