Move ARCH_PAGE_TABLE_SYNC_MASK and arch_sync_kernel_mappings() to linux/pgtable.h so that they can be used outside of vmalloc and ioremap. Cc: Fixes: 8d400913c231 ("x86/vmemmap: handle unpopulated sub-pmd ranges") Signed-off-by: Harry Yoo --- include/linux/pgtable.h | 16 ++++++++++++++++ include/linux/vmalloc.h | 16 ---------------- 2 files changed, 16 insertions(+), 16 deletions(-) diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 4c035637eeb7..ba699df6ef69 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1467,6 +1467,22 @@ static inline void modify_prot_commit_ptes(struct vm_area_struct *vma, unsigned } #endif +/* + * 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. + */ +#ifndef ARCH_PAGE_TABLE_SYNC_MASK +#define ARCH_PAGE_TABLE_SYNC_MASK 0 +#endif + +/* + * There is no default implementation for arch_sync_kernel_mappings(). It is + * relied upon the compiler to optimize calls out if ARCH_PAGE_TABLE_SYNC_MASK + * is 0. + */ +void arch_sync_kernel_mappings(unsigned long start, unsigned long end); + #endif /* CONFIG_MMU */ /* diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index fdc9aeb74a44..2759dac6be44 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -219,22 +219,6 @@ extern int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, int vmap_pages_range(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift); -/* - * 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. - */ -#ifndef ARCH_PAGE_TABLE_SYNC_MASK -#define ARCH_PAGE_TABLE_SYNC_MASK 0 -#endif - -/* - * There is no default implementation for arch_sync_kernel_mappings(). It is - * relied upon the compiler to optimize calls out if ARCH_PAGE_TABLE_SYNC_MASK - * is 0. - */ -void arch_sync_kernel_mappings(unsigned long start, unsigned long end); - /* * Lowlevel-APIs (not for driver use!) */ -- 2.43.0 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. 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. 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: Fixes: 8d400913c231 ("x86/vmemmap: handle unpopulated sub-pmd ranges") Suggested-by: Dave Hansen Signed-off-by: Harry Yoo --- include/linux/pgalloc.h | 24 ++++++++++++++++++++++++ include/linux/pgtable.h | 4 ++-- mm/kasan/init.c | 12 ++++++------ mm/percpu.c | 6 +++--- mm/sparse-vmemmap.c | 6 +++--- 5 files changed, 38 insertions(+), 14 deletions(-) create mode 100644 include/linux/pgalloc.h diff --git a/include/linux/pgalloc.h b/include/linux/pgalloc.h new file mode 100644 index 000000000000..290ab864320f --- /dev/null +++ b/include/linux/pgalloc.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_PGALLOC_H +#define _LINUX_PGALLOC_H + +#include +#include + +static inline void pgd_populate_kernel(unsigned long addr, pgd_t *pgd, + p4d_t *p4d) +{ + pgd_populate(&init_mm, pgd, p4d); + if (ARCH_PAGE_TABLE_SYNC_MASK & PGTBL_PGD_MODIFIED) + arch_sync_kernel_mappings(addr, addr); +} + +static inline void p4d_populate_kernel(unsigned long addr, p4d_t *p4d, + pud_t *pud) +{ + p4d_populate(&init_mm, p4d, pud); + if (ARCH_PAGE_TABLE_SYNC_MASK & PGTBL_P4D_MODIFIED) + arch_sync_kernel_mappings(addr, addr); +} + +#endif /* _LINUX_PGALLOC_H */ diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index ba699df6ef69..0cf5c6c3e483 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1469,8 +1469,8 @@ static inline void modify_prot_commit_ptes(struct vm_area_struct *vma, unsigned /* * 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..8fce3370c84e 100644 --- a/mm/kasan/init.c +++ b/mm/kasan/init.c @@ -13,9 +13,9 @@ #include #include #include +#include #include -#include #include "kasan.h" @@ -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 d9cbaee92b60..a56f35dcc417 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -3108,7 +3108,7 @@ 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 +#include #ifndef P4D_TABLE_SIZE #define P4D_TABLE_SIZE PAGE_SIZE @@ -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 41aa0493eb03..dbd8daccade2 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -27,9 +27,9 @@ #include #include #include +#include #include -#include #include #include "hugetlb_vmemmap.h" @@ -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; } -- 2.43.0 Define ARCH_PAGE_TABLE_SYNC_MASK and arch_sync_kernel_mappings() to ensure page tables are properly synchronized when calling p*d_populate_kernel(). It is inteneded to synchronize page tables via pgd_pouplate_kernel() when 5-level paging is in use and via p4d_pouplate_kernel() when 4-level paging is used. This fixes intermittent boot failures on systems using 4-level paging and a large amount of persistent memory: BUG: unable to handle page fault for address: ffffe70000000034 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 0 P4D 0 Oops: 0002 [#1] SMP NOPTI RIP: 0010:__init_single_page+0x9/0x6d Call Trace: __init_zone_device_page+0x17/0x5d memmap_init_zone_device+0x154/0x1bb pagemap_range+0x2e0/0x40f memremap_pages+0x10b/0x2f0 devm_memremap_pages+0x1e/0x60 dev_dax_probe+0xce/0x2ec [device_dax] dax_bus_probe+0x6d/0xc9 [... snip ...] It also fixes a crash in vmemmap_set_pmd() caused by accessing vmemmap before sync_global_pgds() [1]: BUG: unable to handle page fault for address: ffffeb3ff1200000 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 0 P4D 0 Oops: Oops: 0002 [#1] PREEMPT SMP NOPTI Tainted: [W]=WARN RIP: 0010:vmemmap_set_pmd+0xff/0x230 vmemmap_populate_hugepages+0x176/0x180 vmemmap_populate+0x34/0x80 __populate_section_memmap+0x41/0x90 sparse_add_section+0x121/0x3e0 __add_pages+0xba/0x150 add_pages+0x1d/0x70 memremap_pages+0x3dc/0x810 devm_memremap_pages+0x1c/0x60 xe_devm_add+0x8b/0x100 [xe] xe_tile_init_noalloc+0x6a/0x70 [xe] xe_device_probe+0x48c/0x740 [xe] [... snip ...] Cc: Fixes: 8d400913c231 ("x86/vmemmap: handle unpopulated sub-pmd ranges") Closes: https://lore.kernel.org/linux-mm/20250311114420.240341-1-gwan-gyeong.mun@intel.com [1] Suggested-by: Dave Hansen Signed-off-by: Harry Yoo --- arch/x86/include/asm/pgtable_64_types.h | 3 +++ arch/x86/mm/init_64.c | 5 +++++ 2 files changed, 8 insertions(+) diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index 4604f924d8b8..7eb61ef6a185 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -36,6 +36,9 @@ static inline bool pgtable_l5_enabled(void) #define pgtable_l5_enabled() cpu_feature_enabled(X86_FEATURE_LA57) #endif /* USE_EARLY_PGTABLE_L5 */ +#define ARCH_PAGE_TABLE_SYNC_MASK \ + (pgtable_l5_enabled() ? PGTBL_PGD_MODIFIED : PGTBL_P4D_MODIFIED) + extern unsigned int pgdir_shift; extern unsigned int ptrs_per_p4d; diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 76e33bd7c556..a78b498c0dc3 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -223,6 +223,11 @@ static void sync_global_pgds(unsigned long start, unsigned long end) sync_global_pgds_l4(start, end); } +void arch_sync_kernel_mappings(unsigned long start, unsigned long end) +{ + sync_global_pgds(start, end); +} + /* * NOTE: This function is marked __ref because it calls __init function * (alloc_bootmem_pages). It's safe to do it ONLY when after_bootmem == 0. -- 2.43.0