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 9b861528a801 ("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 4917f55b4ef9 ("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 8d400913c231 ("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.

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. In theory, PUD and PMD level helpers can be added later if needed by other architectures.

Currently this is a no-op, since no architecture sets PGTBL_{PGD,P4D}_MODIFIED in ARCH_PAGE_TABLE_SYNC_MASK.

Cc: stable@vger.kernel.org Suggested-by: Dave Hansen dave.hansen@linux.intel.com Signed-off-by: Harry Yoo harry.yoo@oracle.com --- include/asm-generic/pgalloc.h | 16 ++++++++++++++++ include/linux/pgtable.h | 4 ++-- mm/kasan/init.c | 10 +++++----- mm/percpu.c | 4 ++-- mm/sparse-vmemmap.c | 4 ++-- 5 files changed, 27 insertions(+), 11 deletions(-)

diff --git a/include/asm-generic/pgalloc.h b/include/asm-generic/pgalloc.h index 3c8ec3bfea44..fc0ab8eed5a6 100644 --- a/include/asm-generic/pgalloc.h +++ b/include/asm-generic/pgalloc.h @@ -4,6 +4,8 @@

#ifdef CONFIG_MMU

+#include <linux/pgtable.h> + #define GFP_PGTABLE_KERNEL (GFP_KERNEL | __GFP_ZERO) #define GFP_PGTABLE_USER (GFP_PGTABLE_KERNEL | __GFP_ACCOUNT)

@@ -296,6 +298,20 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) } #endif

+#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 /* CONFIG_MMU */

#endif /* __ASM_GENERIC_PGALLOC_H */ diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index e564f338c758..2e24514ab6d0 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1332,8 +1332,8 @@ static inline void ptep_modify_prot_commit(struct vm_area_struct *vma,

/* * 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 diff --git a/mm/kasan/init.c b/mm/kasan/init.c index ced6b29fcf76..43de820ee282 100644 --- a/mm/kasan/init.c +++ b/mm/kasan/init.c @@ -191,7 +191,7 @@ 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, @@ -212,7 +212,7 @@ static int __ref zero_p4d_populate(pgd_t *pgd, unsigned long addr, } else { p = early_alloc(PAGE_SIZE, NUMA_NO_NODE); pud_init(p); - p4d_populate(&init_mm, p4d, p); + p4d_populate_kernel(addr, p4d, p); } } zero_pud_populate(p4d, addr, next); @@ -251,10 +251,10 @@ 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, @@ -273,7 +273,7 @@ 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)); } } diff --git a/mm/percpu.c b/mm/percpu.c index b35494c8ede2..1615dc3b3af5 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -3134,13 +3134,13 @@ void __init __weak pcpu_populate_pte(unsigned long addr)

if (pgd_none(*pgd)) { p4d = memblock_alloc_or_panic(P4D_TABLE_SIZE, P4D_TABLE_SIZE); - pgd_populate(&init_mm, pgd, p4d); + pgd_populate_kernel(addr, pgd, p4d); }

p4d = p4d_offset(pgd, addr); if (p4d_none(*p4d)) { pud = memblock_alloc_or_panic(PUD_TABLE_SIZE, PUD_TABLE_SIZE); - p4d_populate(&init_mm, p4d, pud); + p4d_populate_kernel(addr, p4d, pud); }

pud = pud_offset(p4d, addr); diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index fd2ab5118e13..e275310ac708 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -229,7 +229,7 @@ p4d_t * __meminit vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node) if (!p) return NULL; pud_init(p); - p4d_populate(&init_mm, p4d, p); + p4d_populate_kernel(addr, p4d, p); } return p4d; } @@ -241,7 +241,7 @@ 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; }