FAILED: patch "[PATCH] mm/hugetlb: initialize gigantic bootmem hugepage struct pages" failed to apply to 6.18-stable tree

FAILED: patch "[PATCH] mm/hugetlb: initialize gigantic bootmem hugepage struct pages" failed to apply to 6.18-stable tree

[gregkh]

The patch below does not apply to the 6.18-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable@vger.kernel.org>.

To reproduce the conflict and resubmit, you may use the following commands:

git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.18.y
git checkout FETCH_HEAD
git cherry-pick -x b1b7c045e808c761b1cc8c19b3040fadedda3fef
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable@vger.kernel.org>' --in-reply-to '2026090313-purgatory-bondless-206f@gregkh' --subject-prefix 'PATCH 6.18.y' 'HEAD^..'

Possible dependencies:



thanks,

greg k-h

------------------ original commit in Linus's tree ------------------

From b1b7c045e808c761b1cc8c19b3040fadedda3fef Mon Sep 17 00:00:00 2001
From: Muchun Song <muchun.song@linux.dev>
Date: Fri, 12 Jun 2026 11:58:48 +0800
Subject: [PATCH] mm/hugetlb: initialize gigantic bootmem hugepage struct pages
 earlier

Gigantic bootmem HugeTLB pages are currently initialized from
hugetlb_init(), but page_alloc_init_late() runs earlier and walks
pageblocks to determine zone contiguity.

If a bootmem HugeTLB region is marked noinit, set_zone_contiguous() can
observe still-uninitialized struct pages through
__pageblock_pfn_to_page().  This may not trigger an immediate failure, but
it can make set_zone_contiguous() compute the wrong zone contiguity state.
If extra poisoned-page checks are added in this path, such as
PF_POISONED_CHECK() in page_zone_id(), it can also trigger an early boot
panic.

Initialize gigantic bootmem HugeTLB struct pages from
page_alloc_init_late(), before zone contiguity is evaluated, so later page
allocator setup only sees valid struct page state.  This also makes the
initialization order more natural, as struct pages should be initialized
before later code inspects them.

Link: https://lore.kernel.org/20260612035903.2468601-5-songmuchun@bytedance.com
Fixes: fde1c4ecf916 ("mm: hugetlb: skip initialization of gigantic tail struct pages if freed by HVO")
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Acked-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Acked-by: Oscar Salvador <osalvador@suse.de>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: David Hildenbrand <david@kernel.org>
Cc: Frank van der Linden <fvdl@google.com>
Cc: Liam R. Howlett <liam@infradead.org>
Cc: Lorenzo Stoakes <ljs@kernel.org>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oscar Salvador (SUSE) <osalvador@kernel.org>
Cc: "Ritesh Harjani (IBM)" <ritesh.list@gmail.com>
Cc: Usama Arif <usama.arif@linux.dev>
Cc: Vlastimil Babka <vbabka@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index d6967fc94a49..431848873370 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -172,6 +172,7 @@ extern int movable_gigantic_pages __read_mostly;
 extern int sysctl_hugetlb_shm_group __read_mostly;
 extern struct list_head huge_boot_pages[MAX_NUMNODES];
 
+void hugetlb_bootmem_struct_page_init(void);
 void hugetlb_bootmem_alloc(void);
 extern nodemask_t hugetlb_bootmem_nodes;
 void hugetlb_bootmem_set_nodes(void);
@@ -1294,6 +1295,10 @@ static inline bool hugetlbfs_pagecache_present(
 static inline void hugetlb_bootmem_alloc(void)
 {
 }
+
+static inline void hugetlb_bootmem_struct_page_init(void)
+{
+}
 #endif	/* CONFIG_HUGETLB_PAGE */
 
 static inline spinlock_t *huge_pte_lock(struct hstate *h,
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 4c234611e7a0..78fe77a690ad 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3353,7 +3353,7 @@ static void __init gather_bootmem_prealloc_parallel(unsigned long start,
 		gather_bootmem_prealloc_node(nid);
 }
 
-static void __init gather_bootmem_prealloc(void)
+void __init hugetlb_bootmem_struct_page_init(void)
 {
 	struct padata_mt_job job = {
 		.thread_fn	= gather_bootmem_prealloc_parallel,
@@ -3582,7 +3582,7 @@ static unsigned long __init hugetlb_pages_alloc_boot(struct hstate *h)
  * - For gigantic pages, this is called early in the boot process and
  *   pages are allocated from memblock allocated or something similar.
  *   Gigantic pages are actually added to pools later with the routine
- *   gather_bootmem_prealloc.
+ *   hugetlb_bootmem_struct_page_init.
  * - For non-gigantic pages, this is called later in the boot process after
  *   all of mm is up and functional.  Pages are allocated from buddy and
  *   then added to hugetlb pools.
@@ -4152,7 +4152,6 @@ static int __init hugetlb_init(void)
 	}
 
 	hugetlb_init_hstates();
-	gather_bootmem_prealloc();
 	report_hugepages();
 
 	hugetlb_sysfs_init();
diff --git a/mm/mm_init.c b/mm/mm_init.c
index 498d62c4ece3..eb7222f133e6 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -2330,6 +2330,7 @@ void __init page_alloc_init_late(void)
 	/* Reinit limits that are based on free pages after the kernel is up */
 	files_maxfiles_init();
 #endif
+	hugetlb_bootmem_struct_page_init();
 
 	/* Accounting of total+free memory is stable at this point. */
 	mem_init_print_info();
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index dff8da23eabb..50df73b8f747 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -342,8 +342,8 @@ static __meminit struct page *vmemmap_get_tail(unsigned int order, struct zone *
 	 *
 	 * Any initialization done here will be overwritten by memmap_init().
 	 *
-	 * gather_bootmem_prealloc() will take care of initialization after
-	 * memmap_init().
+	 * hugetlb_bootmem_struct_page_init() will take care of initialization
+	 * after memmap_init().
 	 */
 
 	p = vmemmap_alloc_block_zero(PAGE_SIZE, node);

[PATCH 6.18.y 1/3] mm/hugetlb: defer vmemmap population for bootmem hugepages

[Sasha Levin]

From: "Kiryl Shutsemau (Meta)" <kas@kernel.org>

[ Upstream commit 209e6d9eb13aaf1b6e0fc6f76afc00d055e5ba12 ]

Currently, the vmemmap for bootmem-allocated gigantic pages is populated
early in hugetlb_vmemmap_init_early().  However, the zone information is
only available after zones are initialized.  If it is later discovered
that a page spans multiple zones, the HVO mapping must be undone and
replaced with a normal mapping using vmemmap_undo_hvo().

Defer the actual vmemmap population to hugetlb_vmemmap_init_late().  At
this stage, zones are already initialized, so it can be checked if the
page is valid for HVO before deciding how to populate the vmemmap.

This allows us to remove vmemmap_undo_hvo() and the complex logic required
to rollback HVO mappings.

In hugetlb_vmemmap_init_late(), if HVO population fails or if the zones
are invalid, fall back to a normal vmemmap population.

Postponing population until hugetlb_vmemmap_init_late() also makes zone
information available from within vmemmap_populate_hvo().

Link: https://lkml.kernel.org/r/20260227194302.274384-10-kas@kernel.org
Signed-off-by: Kiryl Shutsemau (Meta) <kas@kernel.org>
Acked-by: David Hildenbrand (Arm) <david@kernel.org>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Baoquan He <bhe@redhat.com>
Cc: Christoph Lameter <cl@gentwo.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Frank van der Linden <fvdl@google.com>
Cc: Harry Yoo <harry.yoo@oracle.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Usama Arif <usamaarif642@gmail.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: WANG Xuerui <kernel@xen0n.name>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Stable-dep-of: b1b7c045e808 ("mm/hugetlb: initialize gigantic bootmem hugepage struct pages earlier")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/linux/mm.h   |  2 --
 mm/hugetlb_vmemmap.c | 37 +++++++++++++++----------------
 mm/sparse-vmemmap.c  | 53 --------------------------------------------
 3 files changed, 18 insertions(+), 74 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 92ba2489f2374..50710a5d4a05f 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -4101,8 +4101,6 @@ int vmemmap_populate(unsigned long start, unsigned long end, int node,
 		struct vmem_altmap *altmap);
 int vmemmap_populate_hvo(unsigned long start, unsigned long end, int node,
 			 unsigned long headsize);
-int vmemmap_undo_hvo(unsigned long start, unsigned long end, int node,
-		     unsigned long headsize);
 void vmemmap_wrprotect_hvo(unsigned long start, unsigned long end, int node,
 			  unsigned long headsize);
 void vmemmap_populate_print_last(void);
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 96ee2bd16ee15..90ecee4c377ee 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -789,7 +789,6 @@ void __init hugetlb_vmemmap_init_early(int nid)
 {
 	unsigned long psize, paddr, section_size;
 	unsigned long ns, i, pnum, pfn, nr_pages;
-	unsigned long start, end;
 	struct huge_bootmem_page *m = NULL;
 	void *map;
 
@@ -815,14 +814,6 @@ void __init hugetlb_vmemmap_init_early(int nid)
 		paddr = virt_to_phys(m);
 		pfn = PHYS_PFN(paddr);
 		map = pfn_to_page(pfn);
-		start = (unsigned long)map;
-		end = start + nr_pages * sizeof(struct page);
-
-		if (vmemmap_populate_hvo(start, end, nid,
-					HUGETLB_VMEMMAP_RESERVE_SIZE) < 0)
-			continue;
-
-		memmap_boot_pages_add(HUGETLB_VMEMMAP_RESERVE_SIZE / PAGE_SIZE);
 
 		pnum = pfn_to_section_nr(pfn);
 		ns = psize / section_size;
@@ -860,28 +851,36 @@ void __init hugetlb_vmemmap_init_late(int nid)
 		h = m->hstate;
 		pfn = PHYS_PFN(phys);
 		nr_pages = pages_per_huge_page(h);
+		map = pfn_to_page(pfn);
+		start = (unsigned long)map;
+		end = start + nr_pages * sizeof(struct page);
 
 		if (!hugetlb_bootmem_page_zones_valid(nid, m)) {
 			/*
 			 * Oops, the hugetlb page spans multiple zones.
-			 * Remove it from the list, and undo HVO.
+			 * Remove it from the list, and populate it normally.
 			 */
 			list_del(&m->list);
 
-			map = pfn_to_page(pfn);
-
-			start = (unsigned long)map;
-			end = start + nr_pages * sizeof(struct page);
-
-			vmemmap_undo_hvo(start, end, nid,
-					 HUGETLB_VMEMMAP_RESERVE_SIZE);
-			nr_mmap = end - start - HUGETLB_VMEMMAP_RESERVE_SIZE;
+			vmemmap_populate(start, end, nid, NULL);
+			nr_mmap = end - start;
 			memmap_boot_pages_add(DIV_ROUND_UP(nr_mmap, PAGE_SIZE));
 
 			memblock_phys_free(phys, huge_page_size(h));
 			continue;
-		} else
+		}
+
+		if (vmemmap_populate_hvo(start, end, nid,
+					 HUGETLB_VMEMMAP_RESERVE_SIZE) < 0) {
+			/* Fallback if HVO population fails */
+			vmemmap_populate(start, end, nid, NULL);
+			nr_mmap = end - start;
+		} else {
 			m->flags |= HUGE_BOOTMEM_ZONES_VALID;
+			nr_mmap = HUGETLB_VMEMMAP_RESERVE_SIZE;
+		}
+
+		memmap_boot_pages_add(DIV_ROUND_UP(nr_mmap, PAGE_SIZE));
 	}
 }
 #endif
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index 37522d6cb3988..032a81450838b 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -302,59 +302,6 @@ int __meminit vmemmap_populate_basepages(unsigned long start, unsigned long end,
 	return vmemmap_populate_range(start, end, node, altmap, -1, 0);
 }
 
-/*
- * Undo populate_hvo, and replace it with a normal base page mapping.
- * Used in memory init in case a HVO mapping needs to be undone.
- *
- * This can happen when it is discovered that a memblock allocated
- * hugetlb page spans multiple zones, which can only be verified
- * after zones have been initialized.
- *
- * We know that:
- * 1) The first @headsize / PAGE_SIZE vmemmap pages were individually
- *    allocated through memblock, and mapped.
- *
- * 2) The rest of the vmemmap pages are mirrors of the last head page.
- */
-int __meminit vmemmap_undo_hvo(unsigned long addr, unsigned long end,
-				      int node, unsigned long headsize)
-{
-	unsigned long maddr, pfn;
-	pte_t *pte;
-	int headpages;
-
-	/*
-	 * Should only be called early in boot, so nothing will
-	 * be accessing these page structures.
-	 */
-	WARN_ON(!early_boot_irqs_disabled);
-
-	headpages = headsize >> PAGE_SHIFT;
-
-	/*
-	 * Clear mirrored mappings for tail page structs.
-	 */
-	for (maddr = addr + headsize; maddr < end; maddr += PAGE_SIZE) {
-		pte = virt_to_kpte(maddr);
-		pte_clear(&init_mm, maddr, pte);
-	}
-
-	/*
-	 * Clear and free mappings for head page and first tail page
-	 * structs.
-	 */
-	for (maddr = addr; headpages-- > 0; maddr += PAGE_SIZE) {
-		pte = virt_to_kpte(maddr);
-		pfn = pte_pfn(ptep_get(pte));
-		pte_clear(&init_mm, maddr, pte);
-		memblock_phys_free(PFN_PHYS(pfn), PAGE_SIZE);
-	}
-
-	flush_tlb_kernel_range(addr, end);
-
-	return vmemmap_populate(addr, end, node, NULL);
-}
-
 /*
  * Write protect the mirrored tail page structs for HVO. This will be
  * called from the hugetlb code when gathering and initializing the
-- 
2.53.0

[PATCH 6.18.y 2/3] mm/hugetlb: refactor code around vmemmap_walk

[Sasha Levin]

From: Kiryl Shutsemau <kas@kernel.org>

[ Upstream commit c0b495b91a47b6c5ee54cf00e620dbadeb884253 ]

To prepare for removing fake head pages, the vmemmap_walk code is being
reworked.

The reuse_page and reuse_addr variables are being eliminated.  There will
no longer be an expectation regarding the reuse address in relation to the
operated range.  Instead, the caller will provide head and tail vmemmap
pages.

Currently, vmemmap_head and vmemmap_tail are set to the same page, but
this will change in the future.

The only functional change is that __hugetlb_vmemmap_optimize_folio() will
abandon optimization if memory allocation fails.

Link: https://lkml.kernel.org/r/20260227194302.274384-11-kas@kernel.org
Signed-off-by: Kiryl Shutsemau <kas@kernel.org>
Reviewed-by: Muchun Song <muchun.song@linux.dev>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Baoquan He <bhe@redhat.com>
Cc: Christoph Lameter <cl@gentwo.org>
Cc: David Hildenbrand (arm) <david@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Frank van der Linden <fvdl@google.com>
Cc: Harry Yoo <harry.yoo@oracle.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Usama Arif <usamaarif642@gmail.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: WANG Xuerui <kernel@xen0n.name>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Stable-dep-of: b1b7c045e808 ("mm/hugetlb: initialize gigantic bootmem hugepage struct pages earlier")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 mm/hugetlb_vmemmap.c | 224 +++++++++++++++++--------------------------
 1 file changed, 89 insertions(+), 135 deletions(-)

diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 90ecee4c377ee..2cb3293cb50e6 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -24,8 +24,8 @@
  *
  * @remap_pte:		called for each lowest-level entry (PTE).
  * @nr_walked:		the number of walked pte.
- * @reuse_page:		the page which is reused for the tail vmemmap pages.
- * @reuse_addr:		the virtual address of the @reuse_page page.
+ * @vmemmap_head:	the page to be installed as first in the vmemmap range
+ * @vmemmap_tail:	the page to be installed as non-first in the vmemmap range
  * @vmemmap_pages:	the list head of the vmemmap pages that can be freed
  *			or is mapped from.
  * @flags:		used to modify behavior in vmemmap page table walking
@@ -34,11 +34,13 @@
 struct vmemmap_remap_walk {
 	void			(*remap_pte)(pte_t *pte, unsigned long addr,
 					     struct vmemmap_remap_walk *walk);
+
 	unsigned long		nr_walked;
-	struct page		*reuse_page;
-	unsigned long		reuse_addr;
+	struct page		*vmemmap_head;
+	struct page		*vmemmap_tail;
 	struct list_head	*vmemmap_pages;
 
+
 /* Skip the TLB flush when we split the PMD */
 #define VMEMMAP_SPLIT_NO_TLB_FLUSH	BIT(0)
 /* Skip the TLB flush when we remap the PTE */
@@ -140,14 +142,7 @@ static int vmemmap_pte_entry(pte_t *pte, unsigned long addr,
 {
 	struct vmemmap_remap_walk *vmemmap_walk = walk->private;
 
-	/*
-	 * The reuse_page is found 'first' in page table walking before
-	 * starting remapping.
-	 */
-	if (!vmemmap_walk->reuse_page)
-		vmemmap_walk->reuse_page = pte_page(ptep_get(pte));
-	else
-		vmemmap_walk->remap_pte(pte, addr, vmemmap_walk);
+	vmemmap_walk->remap_pte(pte, addr, vmemmap_walk);
 	vmemmap_walk->nr_walked++;
 
 	return 0;
@@ -207,18 +202,12 @@ static void free_vmemmap_page_list(struct list_head *list)
 static void vmemmap_remap_pte(pte_t *pte, unsigned long addr,
 			      struct vmemmap_remap_walk *walk)
 {
-	/*
-	 * Remap the tail pages as read-only to catch illegal write operation
-	 * to the tail pages.
-	 */
-	pgprot_t pgprot = PAGE_KERNEL_RO;
 	struct page *page = pte_page(ptep_get(pte));
 	pte_t entry;
 
 	/* Remapping the head page requires r/w */
-	if (unlikely(addr == walk->reuse_addr)) {
-		pgprot = PAGE_KERNEL;
-		list_del(&walk->reuse_page->lru);
+	if (unlikely(walk->nr_walked == 0 && walk->vmemmap_head)) {
+		list_del(&walk->vmemmap_head->lru);
 
 		/*
 		 * Makes sure that preceding stores to the page contents from
@@ -226,53 +215,50 @@ static void vmemmap_remap_pte(pte_t *pte, unsigned long addr,
 		 * write.
 		 */
 		smp_wmb();
+
+		entry = mk_pte(walk->vmemmap_head, PAGE_KERNEL);
+	} else {
+		/*
+		 * Remap the tail pages as read-only to catch illegal write
+		 * operation to the tail pages.
+		 */
+		entry = mk_pte(walk->vmemmap_tail, PAGE_KERNEL_RO);
 	}
 
-	entry = mk_pte(walk->reuse_page, pgprot);
 	list_add(&page->lru, walk->vmemmap_pages);
 	set_pte_at(&init_mm, addr, pte, entry);
 }
 
-/*
- * How many struct page structs need to be reset. When we reuse the head
- * struct page, the special metadata (e.g. page->flags or page->mapping)
- * cannot copy to the tail struct page structs. The invalid value will be
- * checked in the free_tail_page_prepare(). In order to avoid the message
- * of "corrupted mapping in tail page". We need to reset at least 4 (one
- * head struct page struct and three tail struct page structs) struct page
- * structs.
- */
-#define NR_RESET_STRUCT_PAGE		4
-
-static inline void reset_struct_pages(struct page *start)
-{
-	struct page *from = start + NR_RESET_STRUCT_PAGE;
-
-	BUILD_BUG_ON(NR_RESET_STRUCT_PAGE * 2 > PAGE_SIZE / sizeof(struct page));
-	memcpy(start, from, sizeof(*from) * NR_RESET_STRUCT_PAGE);
-}
-
 static void vmemmap_restore_pte(pte_t *pte, unsigned long addr,
 				struct vmemmap_remap_walk *walk)
 {
-	pgprot_t pgprot = PAGE_KERNEL;
 	struct page *page;
-	void *to;
-
-	BUG_ON(pte_page(ptep_get(pte)) != walk->reuse_page);
+	struct page *from, *to;
 
 	page = list_first_entry(walk->vmemmap_pages, struct page, lru);
 	list_del(&page->lru);
+
+	/*
+	 * Initialize tail pages in the newly allocated vmemmap page.
+	 *
+	 * There is folio-scope metadata that is encoded in the first few
+	 * tail pages.
+	 *
+	 * Use the value last tail page in the page with the head page
+	 * to initialize the rest of tail pages.
+	 */
+	from = compound_head((struct page *)addr) +
+		PAGE_SIZE / sizeof(struct page) - 1;
 	to = page_to_virt(page);
-	copy_page(to, (void *)walk->reuse_addr);
-	reset_struct_pages(to);
+	for (int i = 0; i < PAGE_SIZE / sizeof(struct page); i++, to++)
+		*to = *from;
 
 	/*
 	 * Makes sure that preceding stores to the page contents become visible
 	 * before the set_pte_at() write.
 	 */
 	smp_wmb();
-	set_pte_at(&init_mm, addr, pte, mk_pte(page, pgprot));
+	set_pte_at(&init_mm, addr, pte, mk_pte(page, PAGE_KERNEL));
 }
 
 /**
@@ -282,33 +268,28 @@ static void vmemmap_restore_pte(pte_t *pte, unsigned long addr,
  *             to remap.
  * @end:       end address of the vmemmap virtual address range that we want to
  *             remap.
- * @reuse:     reuse address.
- *
  * Return: %0 on success, negative error code otherwise.
  */
-static int vmemmap_remap_split(unsigned long start, unsigned long end,
-			       unsigned long reuse)
+static int vmemmap_remap_split(unsigned long start, unsigned long end)
 {
 	struct vmemmap_remap_walk walk = {
 		.remap_pte	= NULL,
 		.flags		= VMEMMAP_SPLIT_NO_TLB_FLUSH,
 	};
 
-	/* See the comment in the vmemmap_remap_free(). */
-	BUG_ON(start - reuse != PAGE_SIZE);
-
-	return vmemmap_remap_range(reuse, end, &walk);
+	return vmemmap_remap_range(start, end, &walk);
 }
 
 /**
  * vmemmap_remap_free - remap the vmemmap virtual address range [@start, @end)
- *			to the page which @reuse is mapped to, then free vmemmap
- *			which the range are mapped to.
+ *			to use @vmemmap_head/tail, then free vmemmap which
+ *			the range are mapped to.
  * @start:	start address of the vmemmap virtual address range that we want
  *		to remap.
  * @end:	end address of the vmemmap virtual address range that we want to
  *		remap.
- * @reuse:	reuse address.
+ * @vmemmap_head: the page to be installed as first in the vmemmap range
+ * @vmemmap_tail: the page to be installed as non-first in the vmemmap range
  * @vmemmap_pages: list to deposit vmemmap pages to be freed.  It is callers
  *		responsibility to free pages.
  * @flags:	modifications to vmemmap_remap_walk flags
@@ -316,69 +297,38 @@ static int vmemmap_remap_split(unsigned long start, unsigned long end,
  * Return: %0 on success, negative error code otherwise.
  */
 static int vmemmap_remap_free(unsigned long start, unsigned long end,
-			      unsigned long reuse,
+			      struct page *vmemmap_head,
+			      struct page *vmemmap_tail,
 			      struct list_head *vmemmap_pages,
 			      unsigned long flags)
 {
 	int ret;
 	struct vmemmap_remap_walk walk = {
 		.remap_pte	= vmemmap_remap_pte,
-		.reuse_addr	= reuse,
+		.vmemmap_head	= vmemmap_head,
+		.vmemmap_tail	= vmemmap_tail,
 		.vmemmap_pages	= vmemmap_pages,
 		.flags		= flags,
 	};
-	int nid = page_to_nid((struct page *)reuse);
-	gfp_t gfp_mask = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN;
 
-	/*
-	 * Allocate a new head vmemmap page to avoid breaking a contiguous
-	 * block of struct page memory when freeing it back to page allocator
-	 * in free_vmemmap_page_list(). This will allow the likely contiguous
-	 * struct page backing memory to be kept contiguous and allowing for
-	 * more allocations of hugepages. Fallback to the currently
-	 * mapped head page in case should it fail to allocate.
-	 */
-	walk.reuse_page = alloc_pages_node(nid, gfp_mask, 0);
-	if (walk.reuse_page) {
-		copy_page(page_to_virt(walk.reuse_page),
-			  (void *)walk.reuse_addr);
-		list_add(&walk.reuse_page->lru, vmemmap_pages);
-		memmap_pages_add(1);
-	}
+	ret = vmemmap_remap_range(start, end, &walk);
+	if (!ret || !walk.nr_walked)
+		return ret;
+
+	end = start + walk.nr_walked * PAGE_SIZE;
 
 	/*
-	 * In order to make remapping routine most efficient for the huge pages,
-	 * the routine of vmemmap page table walking has the following rules
-	 * (see more details from the vmemmap_pte_range()):
-	 *
-	 * - The range [@start, @end) and the range [@reuse, @reuse + PAGE_SIZE)
-	 *   should be continuous.
-	 * - The @reuse address is part of the range [@reuse, @end) that we are
-	 *   walking which is passed to vmemmap_remap_range().
-	 * - The @reuse address is the first in the complete range.
-	 *
-	 * So we need to make sure that @start and @reuse meet the above rules.
+	 * vmemmap_pages contains pages from the previous vmemmap_remap_range()
+	 * call which failed.  These are pages which were removed from
+	 * the vmemmap. They will be restored in the following call.
 	 */
-	BUG_ON(start - reuse != PAGE_SIZE);
+	walk = (struct vmemmap_remap_walk) {
+		.remap_pte	= vmemmap_restore_pte,
+		.vmemmap_pages	= vmemmap_pages,
+		.flags		= 0,
+	};
 
-	ret = vmemmap_remap_range(reuse, end, &walk);
-	if (ret && walk.nr_walked) {
-		end = reuse + walk.nr_walked * PAGE_SIZE;
-		/*
-		 * vmemmap_pages contains pages from the previous
-		 * vmemmap_remap_range call which failed.  These
-		 * are pages which were removed from the vmemmap.
-		 * They will be restored in the following call.
-		 */
-		walk = (struct vmemmap_remap_walk) {
-			.remap_pte	= vmemmap_restore_pte,
-			.reuse_addr	= reuse,
-			.vmemmap_pages	= vmemmap_pages,
-			.flags		= 0,
-		};
-
-		vmemmap_remap_range(reuse, end, &walk);
-	}
+	vmemmap_remap_range(start, end, &walk);
 
 	return ret;
 }
@@ -415,29 +365,24 @@ static int alloc_vmemmap_page_list(unsigned long start, unsigned long end,
  *		to remap.
  * @end:	end address of the vmemmap virtual address range that we want to
  *		remap.
- * @reuse:	reuse address.
  * @flags:	modifications to vmemmap_remap_walk flags
  *
  * Return: %0 on success, negative error code otherwise.
  */
 static int vmemmap_remap_alloc(unsigned long start, unsigned long end,
-			       unsigned long reuse, unsigned long flags)
+			       unsigned long flags)
 {
 	LIST_HEAD(vmemmap_pages);
 	struct vmemmap_remap_walk walk = {
 		.remap_pte	= vmemmap_restore_pte,
-		.reuse_addr	= reuse,
 		.vmemmap_pages	= &vmemmap_pages,
 		.flags		= flags,
 	};
 
-	/* See the comment in the vmemmap_remap_free(). */
-	BUG_ON(start - reuse != PAGE_SIZE);
-
 	if (alloc_vmemmap_page_list(start, end, &vmemmap_pages))
 		return -ENOMEM;
 
-	return vmemmap_remap_range(reuse, end, &walk);
+	return vmemmap_remap_range(start, end, &walk);
 }
 
 DEFINE_STATIC_KEY_FALSE(hugetlb_optimize_vmemmap_key);
@@ -454,8 +399,7 @@ static int __hugetlb_vmemmap_restore_folio(const struct hstate *h,
 					   struct folio *folio, unsigned long flags)
 {
 	int ret;
-	unsigned long vmemmap_start = (unsigned long)&folio->page, vmemmap_end;
-	unsigned long vmemmap_reuse;
+	unsigned long vmemmap_start, vmemmap_end;
 
 	VM_WARN_ON_ONCE_FOLIO(!folio_test_hugetlb(folio), folio);
 	VM_WARN_ON_ONCE_FOLIO(folio_ref_count(folio), folio);
@@ -466,18 +410,18 @@ static int __hugetlb_vmemmap_restore_folio(const struct hstate *h,
 	if (flags & VMEMMAP_SYNCHRONIZE_RCU)
 		synchronize_rcu();
 
+	vmemmap_start	= (unsigned long)&folio->page;
 	vmemmap_end	= vmemmap_start + hugetlb_vmemmap_size(h);
-	vmemmap_reuse	= vmemmap_start;
+
 	vmemmap_start	+= HUGETLB_VMEMMAP_RESERVE_SIZE;
 
 	/*
 	 * The pages which the vmemmap virtual address range [@vmemmap_start,
-	 * @vmemmap_end) are mapped to are freed to the buddy allocator, and
-	 * the range is mapped to the page which @vmemmap_reuse is mapped to.
+	 * @vmemmap_end) are mapped to are freed to the buddy allocator.
 	 * When a HugeTLB page is freed to the buddy allocator, previously
 	 * discarded vmemmap pages must be allocated and remapping.
 	 */
-	ret = vmemmap_remap_alloc(vmemmap_start, vmemmap_end, vmemmap_reuse, flags);
+	ret = vmemmap_remap_alloc(vmemmap_start, vmemmap_end, flags);
 	if (!ret) {
 		folio_clear_hugetlb_vmemmap_optimized(folio);
 		static_branch_dec(&hugetlb_optimize_vmemmap_key);
@@ -565,9 +509,9 @@ static int __hugetlb_vmemmap_optimize_folio(const struct hstate *h,
 					    struct list_head *vmemmap_pages,
 					    unsigned long flags)
 {
-	int ret = 0;
-	unsigned long vmemmap_start = (unsigned long)&folio->page, vmemmap_end;
-	unsigned long vmemmap_reuse;
+	unsigned long vmemmap_start, vmemmap_end;
+	struct page *vmemmap_head, *vmemmap_tail;
+	int nid, ret = 0;
 
 	VM_WARN_ON_ONCE_FOLIO(!folio_test_hugetlb(folio), folio);
 	VM_WARN_ON_ONCE_FOLIO(folio_ref_count(folio), folio);
@@ -592,18 +536,30 @@ static int __hugetlb_vmemmap_optimize_folio(const struct hstate *h,
 	 */
 	folio_set_hugetlb_vmemmap_optimized(folio);
 
+	nid = folio_nid(folio);
+	vmemmap_head = alloc_pages_node(nid, GFP_KERNEL, 0);
+	if (!vmemmap_head) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	copy_page(page_to_virt(vmemmap_head), folio);
+	list_add(&vmemmap_head->lru, vmemmap_pages);
+	memmap_pages_add(1);
+
+	vmemmap_tail	= vmemmap_head;
+	vmemmap_start	= (unsigned long)&folio->page;
 	vmemmap_end	= vmemmap_start + hugetlb_vmemmap_size(h);
-	vmemmap_reuse	= vmemmap_start;
-	vmemmap_start	+= HUGETLB_VMEMMAP_RESERVE_SIZE;
 
 	/*
-	 * Remap the vmemmap virtual address range [@vmemmap_start, @vmemmap_end)
-	 * to the page which @vmemmap_reuse is mapped to.  Add pages previously
-	 * mapping the range to vmemmap_pages list so that they can be freed by
-	 * the caller.
+	 * Remap the vmemmap virtual address range [@vmemmap_start, @vmemmap_end).
+	 * Add pages previously mapping the range to vmemmap_pages list so that
+	 * they can be freed by the caller.
 	 */
-	ret = vmemmap_remap_free(vmemmap_start, vmemmap_end, vmemmap_reuse,
+	ret = vmemmap_remap_free(vmemmap_start, vmemmap_end,
+				 vmemmap_head, vmemmap_tail,
 				 vmemmap_pages, flags);
+out:
 	if (ret) {
 		static_branch_dec(&hugetlb_optimize_vmemmap_key);
 		folio_clear_hugetlb_vmemmap_optimized(folio);
@@ -632,21 +588,19 @@ void hugetlb_vmemmap_optimize_folio(const struct hstate *h, struct folio *folio)
 
 static int hugetlb_vmemmap_split_folio(const struct hstate *h, struct folio *folio)
 {
-	unsigned long vmemmap_start = (unsigned long)&folio->page, vmemmap_end;
-	unsigned long vmemmap_reuse;
+	unsigned long vmemmap_start, vmemmap_end;
 
 	if (!vmemmap_should_optimize_folio(h, folio))
 		return 0;
 
+	vmemmap_start	= (unsigned long)&folio->page;
 	vmemmap_end	= vmemmap_start + hugetlb_vmemmap_size(h);
-	vmemmap_reuse	= vmemmap_start;
-	vmemmap_start	+= HUGETLB_VMEMMAP_RESERVE_SIZE;
 
 	/*
 	 * Split PMDs on the vmemmap virtual address range [@vmemmap_start,
 	 * @vmemmap_end]
 	 */
-	return vmemmap_remap_split(vmemmap_start, vmemmap_end, vmemmap_reuse);
+	return vmemmap_remap_split(vmemmap_start, vmemmap_end);
 }
 
 static void __hugetlb_vmemmap_optimize_folios(struct hstate *h,
-- 
2.53.0

[PATCH 6.18.y 3/3] mm/hugetlb: initialize gigantic bootmem hugepage struct pages earlier

[Sasha Levin]

From: Muchun Song <songmuchun@bytedance.com>

[ Upstream commit b1b7c045e808c761b1cc8c19b3040fadedda3fef ]

Gigantic bootmem HugeTLB pages are currently initialized from
hugetlb_init(), but page_alloc_init_late() runs earlier and walks
pageblocks to determine zone contiguity.

If a bootmem HugeTLB region is marked noinit, set_zone_contiguous() can
observe still-uninitialized struct pages through
__pageblock_pfn_to_page().  This may not trigger an immediate failure, but
it can make set_zone_contiguous() compute the wrong zone contiguity state.
If extra poisoned-page checks are added in this path, such as
PF_POISONED_CHECK() in page_zone_id(), it can also trigger an early boot
panic.

Initialize gigantic bootmem HugeTLB struct pages from
page_alloc_init_late(), before zone contiguity is evaluated, so later page
allocator setup only sees valid struct page state.  This also makes the
initialization order more natural, as struct pages should be initialized
before later code inspects them.

Link: https://lore.kernel.org/20260612035903.2468601-5-songmuchun@bytedance.com
Fixes: fde1c4ecf916 ("mm: hugetlb: skip initialization of gigantic tail struct pages if freed by HVO")
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Acked-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Acked-by: Oscar Salvador <osalvador@suse.de>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: David Hildenbrand <david@kernel.org>
Cc: Frank van der Linden <fvdl@google.com>
Cc: Liam R. Howlett <liam@infradead.org>
Cc: Lorenzo Stoakes <ljs@kernel.org>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oscar Salvador (SUSE) <osalvador@kernel.org>
Cc: "Ritesh Harjani (IBM)" <ritesh.list@gmail.com>
Cc: Usama Arif <usama.arif@linux.dev>
Cc: Vlastimil Babka <vbabka@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
[ adapted the header context and omitted a comment update for an absent HVO helper. ]
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/linux/hugetlb.h | 5 +++++
 mm/hugetlb.c            | 5 ++---
 mm/mm_init.c            | 1 +
 3 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index a3f6cdf8a2b6d..bf666f9ece1eb 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -173,6 +173,7 @@ struct address_space *hugetlb_folio_mapping_lock_write(struct folio *folio);
 extern int sysctl_hugetlb_shm_group;
 extern struct list_head huge_boot_pages[MAX_NUMNODES];
 
+void hugetlb_bootmem_struct_page_init(void);
 void hugetlb_bootmem_alloc(void);
 bool hugetlb_bootmem_allocated(void);
 extern nodemask_t hugetlb_bootmem_nodes;
@@ -1314,6 +1315,10 @@ static inline bool hugetlb_bootmem_allocated(void)
 {
 	return false;
 }
+
+static inline void hugetlb_bootmem_struct_page_init(void)
+{
+}
 #endif	/* CONFIG_HUGETLB_PAGE */
 
 static inline spinlock_t *huge_pte_lock(struct hstate *h,
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 5515870b5b155..1d40bb65421c5 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3451,7 +3451,7 @@ static void __init gather_bootmem_prealloc_parallel(unsigned long start,
 		gather_bootmem_prealloc_node(nid);
 }
 
-static void __init gather_bootmem_prealloc(void)
+void __init hugetlb_bootmem_struct_page_init(void)
 {
 	struct padata_mt_job job = {
 		.thread_fn	= gather_bootmem_prealloc_parallel,
@@ -3648,7 +3648,7 @@ static unsigned long __init hugetlb_pages_alloc_boot(struct hstate *h)
  * - For gigantic pages, this is called early in the boot process and
  *   pages are allocated from memblock allocated or something similar.
  *   Gigantic pages are actually added to pools later with the routine
- *   gather_bootmem_prealloc.
+ *   hugetlb_bootmem_struct_page_init.
  * - For non-gigantic pages, this is called later in the boot process after
  *   all of mm is up and functional.  Pages are allocated from buddy and
  *   then added to hugetlb pools.
@@ -4715,7 +4715,6 @@ static int __init hugetlb_init(void)
 
 	hugetlb_cma_check();
 	hugetlb_init_hstates();
-	gather_bootmem_prealloc();
 	report_hugepages();
 
 	hugetlb_sysfs_init();
diff --git a/mm/mm_init.c b/mm/mm_init.c
index d2d915984611a..d11eb841b45ca 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -2354,6 +2354,7 @@ void __init page_alloc_init_late(void)
 	/* Reinit limits that are based on free pages after the kernel is up */
 	files_maxfiles_init();
 #endif
+	hugetlb_bootmem_struct_page_init();
 
 	/* Accounting of total+free memory is stable at this point. */
 	mem_init_print_info();
-- 
2.53.0