+ x86-mm-fix-freeing-of-pmd-sized-vmemmap-pages.patch added to mm-hotfixes-unstable branch

[Andrew Morton <akpm@linux-foundation.org>]

The patch titled
     Subject: x86/mm: fix freeing of PMD-sized vmemmap pages
has been added to the -mm mm-hotfixes-unstable branch.  Its filename is
     x86-mm-fix-freeing-of-pmd-sized-vmemmap-pages.patch

This patch will shortly appear at
     https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/x86-mm-fix-freeing-of-pmd-sized-vmemmap-pages.patch

This patch will later appear in the mm-hotfixes-unstable branch at
    git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Before you just go and hit "reply", please:
   a) Consider who else should be cc'ed
   b) Prefer to cc a suitable mailing list as well
   c) Ideally: find the original patch on the mailing list and do a
      reply-to-all to that, adding suitable additional cc's

*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***

The -mm tree is included into linux-next via various
branches at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there most days

------------------------------------------------------
From: "David Hildenbrand (Arm)" <david@kernel.org>
Subject: x86/mm: fix freeing of PMD-sized vmemmap pages
Date: Wed, 29 Apr 2026 12:49:14 +0200

In commit bf9e4e30f353 ("x86/mm: use pagetable_free()"), we switched from
freeing non-boot page tables through __free_pages() to pagetable_free().

However, the function is also called to free vmemmap pages.

Given that vmemmap pages are not page tables, already the
page_ptdesc(page) is wrong.  But worse, pagetable_free() calls

	__free_pages(page, compound_order(page));

As vmemmap pages are not compound pages (see vmemmap_alloc_block()) --
except for HVO, which doesn't apply here -- we will only free the first
page when freeing a PMD-sized vmemmap page, leaking the other ones.

Fix it by properly decoupling pagetable and vmemmap freeing. 
free_pagetable() no longer has to mess with SECTION_INFO, as only the
vmemmap is marked like that in register_page_bootmem_memmap().

The indentation in remove_pmd_table() is messed up, let's fix that while
touching it.

Note that we'll try to get rid of that bootmem info handling soon.  For
now, we'll handle it similar to free_pagetable(), just avoiding the ifdef.

Link: https://lore.kernel.org/20260429-vmemmap-v2-1-8dfcacffd877@kernel.org
Fixes: bf9e4e30f353 ("x86/mm: use pagetable_free()")
Signed-off-by: David Hildenbrand (Arm) <david@kernel.org>
Tested-by: Lance Yang <lance.yang@linux.dev>
Acked-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Baolu Lu <baolu.lu@linux.intel.com>
Cc: "Borislav Petkov (AMD)" <bp@alien8.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 arch/x86/mm/init_64.c |   40 ++++++++++++++++++++++++++--------------
 1 file changed, 26 insertions(+), 14 deletions(-)

--- a/arch/x86/mm/init_64.c~x86-mm-fix-freeing-of-pmd-sized-vmemmap-pages
+++ a/arch/x86/mm/init_64.c
@@ -1014,7 +1014,7 @@ static void __meminit free_pagetable(str
 #ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE
 		enum bootmem_type type = bootmem_type(page);
 
-		if (type == SECTION_INFO || type == MIX_SECTION_INFO) {
+		if (type == MIX_SECTION_INFO) {
 			while (nr_pages--)
 				put_page_bootmem(page++);
 		} else {
@@ -1028,13 +1028,24 @@ static void __meminit free_pagetable(str
 	}
 }
 
-static void __meminit free_hugepage_table(struct page *page,
+static void __meminit free_vmemmap_pages(struct page *page, unsigned int order,
 		struct vmem_altmap *altmap)
 {
-	if (altmap)
-		vmem_altmap_free(altmap, PMD_SIZE / PAGE_SIZE);
-	else
-		free_pagetable(page, get_order(PMD_SIZE));
+	unsigned long nr_pages = 1u << order;
+
+	if (altmap) {
+		vmem_altmap_free(altmap, nr_pages);
+	} else if (PageReserved(page)) {
+		if (IS_ENABLED(CONFIG_HAVE_BOOTMEM_INFO_NODE) &&
+		    bootmem_type(page) == SECTION_INFO) {
+			while (nr_pages--)
+				put_page_bootmem(page++);
+		} else {
+			free_reserved_pages(page, nr_pages);
+		}
+	} else {
+		__free_pages(page, order);
+	}
 }
 
 static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd)
@@ -1118,7 +1129,8 @@ remove_pte_table(pte_t *pte_start, unsig
 			return;
 
 		if (!direct)
-			free_pagetable(pte_page(*pte), 0);
+			/* We never populate base pages from the altmap. */
+			free_vmemmap_pages(pte_page(*pte), 0, NULL);
 
 		spin_lock(&init_mm.page_table_lock);
 		pte_clear(&init_mm, addr, pte);
@@ -1153,19 +1165,19 @@ remove_pmd_table(pmd_t *pmd_start, unsig
 			if (IS_ALIGNED(addr, PMD_SIZE) &&
 			    IS_ALIGNED(next, PMD_SIZE)) {
 				if (!direct)
-					free_hugepage_table(pmd_page(*pmd),
-							    altmap);
+					free_vmemmap_pages(pmd_page(*pmd),
+							   PMD_ORDER, altmap);
 
 				spin_lock(&init_mm.page_table_lock);
 				pmd_clear(pmd);
 				spin_unlock(&init_mm.page_table_lock);
 				pages++;
 			} else if (vmemmap_pmd_is_unused(addr, next)) {
-					free_hugepage_table(pmd_page(*pmd),
-							    altmap);
-					spin_lock(&init_mm.page_table_lock);
-					pmd_clear(pmd);
-					spin_unlock(&init_mm.page_table_lock);
+				free_vmemmap_pages(pmd_page(*pmd), PMD_ORDER,
+						   altmap);
+				spin_lock(&init_mm.page_table_lock);
+				pmd_clear(pmd);
+				spin_unlock(&init_mm.page_table_lock);
 			}
 			continue;
 		}
_

Patches currently in -mm which might be from david@kernel.org are

mm-page_alloc-fix-initialization-of-tags-of-the-huge-zero-folio-with-init_on_free.patch
x86-mm-fix-freeing-of-pmd-sized-vmemmap-pages.patch
sh-use-folio_mapped-instead-of-page_mapped-in-sh4_flush_cache_page.patch
bpf-arena-use-page_ref_count-instead-of-page_mapped-in-arena_free_pages.patch
mm-remove-page_mapped.patch