mm: introduce and use {pgd,p4d}_populate_kernel()

commit f2d2f95 upstream.

Introduce and use {pgd,p4d}_populate_kernel() in core MM code when
populating PGD and P4D entries for the kernel address space.  These
helpers ensure proper synchronization of page tables when updating the
kernel portion of top-level page tables.

Until now, the kernel has relied on each architecture to handle
synchronization of top-level page tables in an ad-hoc manner.  For
example, see commit 9b86152 ("x86-64, mem: Update all PGDs for direct
mapping and vmemmap mapping changes").

However, this approach has proven fragile for following reasons:

  1) It is easy to forget to perform the necessary page table
     synchronization when introducing new changes.
     For instance, commit 4917f55 ("mm/sparse-vmemmap: improve memory
     savings for compound devmaps") overlooked the need to synchronize
     page tables for the vmemmap area.

  2) It is also easy to overlook that the vmemmap and direct mapping areas
     must not be accessed before explicit page table synchronization.
     For example, commit 8d40091 ("x86/vmemmap: handle unpopulated
     sub-pmd ranges")) caused crashes by accessing the vmemmap area
     before calling sync_global_pgds().

To address this, as suggested by Dave Hansen, introduce _kernel() variants
of the page table population helpers, which invoke architecture-specific
hooks to properly synchronize page tables.  These are introduced in a new
header file, include/linux/pgalloc.h, so they can be called from common
code.

They reuse existing infrastructure for vmalloc and ioremap.
Synchronization requirements are determined by ARCH_PAGE_TABLE_SYNC_MASK,
and the actual synchronization is performed by
arch_sync_kernel_mappings().

This change currently targets only x86_64, so only PGD and P4D level
helpers are introduced.  Currently, these helpers are no-ops since no
architecture sets PGTBL_{PGD,P4D}_MODIFIED in ARCH_PAGE_TABLE_SYNC_MASK.

In theory, PUD and PMD level helpers can be added later if needed by other
architectures.  For now, 32-bit architectures (x86-32 and arm) only handle
PGTBL_PMD_MODIFIED, so p*d_populate_kernel() will never affect them unless
we introduce a PMD level helper.

[harry.yoo@oracle.com: fix KASAN build error due to p*d_populate_kernel()]
  Link: https://lkml.kernel.org/r/20250822020727.202749-1-harry.yoo@oracle.com
Link: https://lkml.kernel.org/r/20250818020206.4517-3-harry.yoo@oracle.com
Fixes: 8d40091 ("x86/vmemmap: handle unpopulated sub-pmd ranges")
Signed-off-by: Harry Yoo <harry.yoo@oracle.com>
Suggested-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Kiryl Shutsemau <kas@kernel.org>
Reviewed-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Andrey Konovalov <andreyknvl@gmail.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: bibo mao <maobibo@loongson.cn>
Cc: Borislav Betkov <bp@alien8.de>
Cc: Christoph Lameter (Ampere) <cl@gentwo.org>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Dev Jain <dev.jain@arm.com>
Cc: Dmitriy Vyukov <dvyukov@google.com>
Cc: Gwan-gyeong Mun <gwan-gyeong.mun@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jane Chu <jane.chu@oracle.com>
Cc: Joao Martins <joao.m.martins@oracle.com>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Kevin Brodsky <kevin.brodsky@arm.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Thomas Gleinxer <tglx@linutronix.de>
Cc: Thomas Huth <thuth@redhat.com>
Cc: "Uladzislau Rezki (Sony)" <urezki@gmail.com>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
[ Adjust context ]
Signed-off-by: Harry Yoo <harry.yoo@oracle.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

Author: hygoni

include/linux/pgalloc.h

@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_PGALLOC_H
+#define _LINUX_PGALLOC_H
+
+#include <linux/pgtable.h>
+#include <asm/pgalloc.h>
+
+/*
+ * {pgd,p4d}_populate_kernel() are defined as macros to allow
+ * compile-time optimization based on the configured page table levels.
+ * Without this, linking may fail because callers (e.g., KASAN) may rely
+ * on calls to these functions being optimized away when passing symbols
+ * that exist only for certain page table levels.
+ */
+#define pgd_populate_kernel(addr, pgd, p4d)				\
+	do {								\
+		pgd_populate(&init_mm, pgd, p4d);			\
+		if (ARCH_PAGE_TABLE_SYNC_MASK & PGTBL_PGD_MODIFIED)	\
+			arch_sync_kernel_mappings(addr, addr);		\
+	} while (0)
+
+#define p4d_populate_kernel(addr, p4d, pud)				\
+	do {								\
+		p4d_populate(&init_mm, p4d, pud);			\
+		if (ARCH_PAGE_TABLE_SYNC_MASK & PGTBL_P4D_MODIFIED)	\
+			arch_sync_kernel_mappings(addr, addr);		\
+	} while (0)
+
+#endif /* _LINUX_PGALLOC_H */

include/linux/pgtable.h

@@ -1474,8 +1474,8 @@ static inline int pmd_protnone(pmd_t pmd)
 
 /*
  * Architectures can set this mask to a combination of PGTBL_P?D_MODIFIED values
- * and let generic vmalloc and ioremap code know when arch_sync_kernel_mappings()
- * needs to be called.
+ * and let generic vmalloc, ioremap and page table update code know when
+ * arch_sync_kernel_mappings() needs to be called.
  */
 #ifndef ARCH_PAGE_TABLE_SYNC_MASK
 #define ARCH_PAGE_TABLE_SYNC_MASK 0
@@ -1608,10 +1608,11 @@ static inline bool arch_has_pfn_modify_check(void)
 /*
  * Page Table Modification bits for pgtbl_mod_mask.
  *
- * These are used by the p?d_alloc_track*() set of functions an in the generic
- * vmalloc/ioremap code to track at which page-table levels entries have been
- * modified. Based on that the code can better decide when vmalloc and ioremap
- * mapping changes need to be synchronized to other page-tables in the system.
+ * These are used by the p?d_alloc_track*() and p*d_populate_kernel()
+ * functions in the generic vmalloc, ioremap and page table update code
+ * to track at which page-table levels entries have been modified.
+ * Based on that the code can better decide when page table changes need
+ * to be synchronized to other page-tables in the system.
  */
 #define		__PGTBL_PGD_MODIFIED	0
 #define		__PGTBL_P4D_MODIFIED	1

mm/kasan/init.c

@@ -13,9 +13,9 @@
 #include <linux/mm.h>
 #include <linux/pfn.h>
 #include <linux/slab.h>
+#include <linux/pgalloc.h>
 
 #include <asm/page.h>
-#include <asm/pgalloc.h>
 
 #include "kasan.h"
 
@@ -188,7 +188,7 @@ static int __ref zero_p4d_populate(pgd_t *pgd, unsigned long addr,
 			pud_t *pud;
 			pmd_t *pmd;
 
-			p4d_populate(&init_mm, p4d,
+			p4d_populate_kernel(addr, p4d,
 					lm_alias(kasan_early_shadow_pud));
 			pud = pud_offset(p4d, addr);
 			pud_populate(&init_mm, pud,
@@ -207,7 +207,7 @@ static int __ref zero_p4d_populate(pgd_t *pgd, unsigned long addr,
 				if (!p)
 					return -ENOMEM;
 			} else {
-				p4d_populate(&init_mm, p4d,
+				p4d_populate_kernel(addr, p4d,
 					early_alloc(PAGE_SIZE, NUMA_NO_NODE));
 			}
 		}
@@ -247,10 +247,10 @@ int __ref kasan_populate_early_shadow(const void *shadow_start,
 			 * puds,pmds, so pgd_populate(), pud_populate()
 			 * is noops.
 			 */
-			pgd_populate(&init_mm, pgd,
+			pgd_populate_kernel(addr, pgd,
 					lm_alias(kasan_early_shadow_p4d));
 			p4d = p4d_offset(pgd, addr);
-			p4d_populate(&init_mm, p4d,
+			p4d_populate_kernel(addr, p4d,
 					lm_alias(kasan_early_shadow_pud));
 			pud = pud_offset(p4d, addr);
 			pud_populate(&init_mm, pud,
@@ -269,7 +269,7 @@ int __ref kasan_populate_early_shadow(const void *shadow_start,
 				if (!p)
 					return -ENOMEM;
 			} else {
-				pgd_populate(&init_mm, pgd,
+				pgd_populate_kernel(addr, pgd,
 					early_alloc(PAGE_SIZE, NUMA_NO_NODE));
 			}
 		}

mm/percpu.c

@@ -3172,7 +3172,7 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
 #endif /* BUILD_EMBED_FIRST_CHUNK */
 
 #ifdef BUILD_PAGE_FIRST_CHUNK
-#include <asm/pgalloc.h>
+#include <linux/pgalloc.h>
 
 #ifndef P4D_TABLE_SIZE
 #define P4D_TABLE_SIZE PAGE_SIZE
@@ -3202,7 +3202,7 @@ void __init __weak pcpu_populate_pte(unsigned long addr)
 		new = memblock_alloc(P4D_TABLE_SIZE, P4D_TABLE_SIZE);
 		if (!new)
 			goto err_alloc;
-		pgd_populate(&init_mm, pgd, new);
+		pgd_populate_kernel(addr, pgd, new);
 	}
 
 	p4d = p4d_offset(pgd, addr);
@@ -3212,7 +3212,7 @@ void __init __weak pcpu_populate_pte(unsigned long addr)
 		new = memblock_alloc(PUD_TABLE_SIZE, PUD_TABLE_SIZE);
 		if (!new)
 			goto err_alloc;
-		p4d_populate(&init_mm, p4d, new);
+		p4d_populate_kernel(addr, p4d, new);
 	}
 
 	pud = pud_offset(p4d, addr);

mm/sparse-vmemmap.c

@@ -27,9 +27,9 @@
 #include <linux/spinlock.h>
 #include <linux/vmalloc.h>
 #include <linux/sched.h>
+#include <linux/pgalloc.h>
 
 #include <asm/dma.h>
-#include <asm/pgalloc.h>
 
 /*
  * Allocate a block of memory to be used to back the virtual memory map
@@ -215,7 +215,7 @@ p4d_t * __meminit vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node)
 		void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node);
 		if (!p)
 			return NULL;
-		p4d_populate(&init_mm, p4d, p);
+		p4d_populate_kernel(addr, p4d, p);
 	}
 	return p4d;
 }
@@ -227,7 +227,7 @@ pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node)
 		void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node);
 		if (!p)
 			return NULL;
-		pgd_populate(&init_mm, pgd, p);
+		pgd_populate_kernel(addr, pgd, p);
 	}
 	return pgd;
 }