From 3d443691ed00eff21ca049ac49c584cdcc7134ac Mon Sep 17 00:00:00 2001 From: Seongsu Park Date: Thu, 19 Feb 2026 15:35:06 +0900 Subject: mm/pkeys: remove unused tsk parameter from arch_set_user_pkey_access() The tsk parameter in arch_set_user_pkey_access() is never used in the function implementations across all architectures (arm64, powerpc, x86). Link: https://lkml.kernel.org/r/20260219063506.545148-1-sgsu.park@samsung.com Signed-off-by: Seongsu Park Cc: "Borislav Petkov (AMD)" Cc: Catalin Marinas Cc: Ingo Molnar Cc: Liam Howlett Cc: Lorenzo Stoakes Cc: Madhavan Srinivasan Cc: Michael Ellerman Cc: Thomas Gleixner Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/arm64/include/asm/pkeys.h | 3 +-- arch/arm64/mm/mmu.c | 2 +- arch/powerpc/include/asm/pkeys.h | 8 +++----- arch/powerpc/mm/book3s64/pkeys.c | 3 +-- arch/x86/include/asm/pkeys.h | 3 +-- arch/x86/kernel/fpu/xstate.c | 3 +-- arch/x86/mm/pkeys.c | 3 +-- 7 files changed, 9 insertions(+), 16 deletions(-) (limited to 'arch') diff --git a/arch/arm64/include/asm/pkeys.h b/arch/arm64/include/asm/pkeys.h index 0ca5f83ce148..cd286d3a9c94 100644 --- a/arch/arm64/include/asm/pkeys.h +++ b/arch/arm64/include/asm/pkeys.h @@ -12,8 +12,7 @@ #define arch_max_pkey() 8 -int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, - unsigned long init_val); +int arch_set_user_pkey_access(int pkey, unsigned long init_val); static inline bool arch_pkeys_enabled(void) { diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index a6a00accf4f9..a12ea8776c32 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -2206,7 +2206,7 @@ void __cpu_replace_ttbr1(pgd_t *pgdp, bool cnp) } #ifdef CONFIG_ARCH_HAS_PKEYS -int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val) +int arch_set_user_pkey_access(int pkey, unsigned long init_val) { u64 new_por; u64 old_por; diff --git a/arch/powerpc/include/asm/pkeys.h b/arch/powerpc/include/asm/pkeys.h index 28e752138996..bd20d4106471 100644 --- a/arch/powerpc/include/asm/pkeys.h +++ b/arch/powerpc/include/asm/pkeys.h @@ -143,10 +143,8 @@ static inline int arch_override_mprotect_pkey(struct vm_area_struct *vma, return __arch_override_mprotect_pkey(vma, prot, pkey); } -extern int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey, - unsigned long init_val); -static inline int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, - unsigned long init_val) +extern int __arch_set_user_pkey_access(int pkey, unsigned long init_val); +static inline int arch_set_user_pkey_access(int pkey, unsigned long init_val) { if (!mmu_has_feature(MMU_FTR_PKEY)) return -EINVAL; @@ -160,7 +158,7 @@ static inline int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, if (pkey == 0) return init_val ? -EINVAL : 0; - return __arch_set_user_pkey_access(tsk, pkey, init_val); + return __arch_set_user_pkey_access(pkey, init_val); } static inline bool arch_pkeys_enabled(void) diff --git a/arch/powerpc/mm/book3s64/pkeys.c b/arch/powerpc/mm/book3s64/pkeys.c index a974baf8f327..2002331b05ba 100644 --- a/arch/powerpc/mm/book3s64/pkeys.c +++ b/arch/powerpc/mm/book3s64/pkeys.c @@ -335,8 +335,7 @@ static inline void init_iamr(int pkey, u8 init_bits) * Set the access rights in AMR IAMR and UAMOR registers for @pkey to that * specified in @init_val. */ -int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey, - unsigned long init_val) +int __arch_set_user_pkey_access(int pkey, unsigned long init_val) { u64 new_amr_bits = 0x0ul; u64 new_iamr_bits = 0x0ul; diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h index 2e6c04d8a45b..06ed2cd2592e 100644 --- a/arch/x86/include/asm/pkeys.h +++ b/arch/x86/include/asm/pkeys.h @@ -9,8 +9,7 @@ */ #define arch_max_pkey() (cpu_feature_enabled(X86_FEATURE_OSPKE) ? 16 : 1) -extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, - unsigned long init_val); +extern int arch_set_user_pkey_access(int pkey, unsigned long init_val); static inline bool arch_pkeys_enabled(void) { diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 76153dfb58c9..a7b6524a9dea 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1080,8 +1080,7 @@ void __user *get_xsave_addr_user(struct xregs_state __user *xsave, int xfeature_ * This will go out and modify PKRU register to set the access * rights for @pkey to @init_val. */ -int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, - unsigned long init_val) +int arch_set_user_pkey_access(int pkey, unsigned long init_val) { u32 old_pkru, new_pkru_bits = 0; int pkey_shift; diff --git a/arch/x86/mm/pkeys.c b/arch/x86/mm/pkeys.c index 7418c367e328..1dfcfaf77e23 100644 --- a/arch/x86/mm/pkeys.c +++ b/arch/x86/mm/pkeys.c @@ -42,8 +42,7 @@ int __execute_only_pkey(struct mm_struct *mm) * Set up PKRU so that it denies access for everything * other than execution. */ - ret = arch_set_user_pkey_access(current, execute_only_pkey, - PKEY_DISABLE_ACCESS); + ret = arch_set_user_pkey_access(execute_only_pkey, PKEY_DISABLE_ACCESS); /* * If the PKRU-set operation failed somehow, just return * 0 and effectively disable execute-only support. -- cgit v1.2.3 From 9a1d0c738b45ea8da4e6897099c708e89f43daad Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" Date: Wed, 11 Feb 2026 12:31:39 +0200 Subject: mm: rename my_zero_pfn() to zero_pfn() my_zero_pfn() is a silly name. Rename zero_pfn variable to zero_page_pfn and my_zero_pfn() function to zero_pfn(). While on it, move extern declarations of zero_page_pfn outside the functions that use it and add a comment about what ZERO_PAGE is. Link: https://lkml.kernel.org/r/20260211103141.3215197-3-rppt@kernel.org Signed-off-by: Mike Rapoport (Microsoft) Acked-by: David Hildenbrand (Arm) Acked-by: Vlastimil Babka Reviewed-by: Liam R. Howlett Cc: Andreas Larsson Cc: "Borislav Petkov (AMD)" Cc: Catalin Marinas Cc: Christophe Leroy (CS GROUP) Cc: Dave Hansen Cc: David S. Miller Cc: Dinh Nguyen Cc: Geert Uytterhoeven Cc: Guo Ren Cc: Helge Deller Cc: Huacai Chen Cc: Ingo Molnar Cc: Johannes Berg Cc: John Paul Adrian Glaubitz Cc: Lorenzo Stoakes Cc: Madhavan Srinivasan Cc: Magnus Lindholm Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Hocko Cc: Michal Simek Cc: Palmer Dabbelt Cc: Richard Weinberger Cc: Russell King Cc: Stafford Horne Cc: Suren Baghdasaryan Cc: Vineet Gupta Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/x86/kvm/mmu/spte.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index 91ce29fd6f1b..8c0ffa2cded6 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -248,7 +248,7 @@ extern u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask; static inline hpa_t kvm_mmu_get_dummy_root(void) { - return my_zero_pfn(0) << PAGE_SHIFT; + return zero_pfn(0) << PAGE_SHIFT; } static inline bool kvm_mmu_is_dummy_root(hpa_t shadow_page) -- cgit v1.2.3 From 6215d9f4470fbb48245ffdfade821685e2728c65 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" Date: Wed, 11 Feb 2026 12:31:40 +0200 Subject: arch, mm: consolidate empty_zero_page Reduce 22 declarations of empty_zero_page to 3 and 23 declarations of ZERO_PAGE() to 4. Every architecture defines empty_zero_page that way or another, but for the most of them it is always a page aligned page in BSS and most definitions of ZERO_PAGE do virt_to_page(empty_zero_page). Move Linus vetted x86 definition of empty_zero_page and ZERO_PAGE() to the core MM and drop these definitions in architectures that do not implement colored zero page (MIPS and s390). ZERO_PAGE() remains a macro because turning it to a wrapper for a static inline causes severe pain in header dependencies. For the most part the change is mechanical, with these being noteworthy: * alpha: aliased empty_zero_page with ZERO_PGE that was also used for boot parameters. Switching to a generic empty_zero_page removes the aliasing and keeps ZERO_PGE for boot parameters only * arm64: uses __pa_symbol() in ZERO_PAGE() so that definition of ZERO_PAGE() is kept intact. * m68k/parisc/um: allocated empty_zero_page from memblock, although they do not support zero page coloring and having it in BSS will work fine. * sparc64 can have empty_zero_page in BSS rather allocate it, but it can't use virt_to_page() for BSS. Keep it's definition of ZERO_PAGE() but instead of allocating it, make mem_map_zero point to empty_zero_page. * sh: used empty_zero_page for boot parameters at the very early boot. Rename the parameters page to boot_params_page and let sh use the generic empty_zero_page. * hexagon: had an amusing comment about empty_zero_page /* A handy thing to have if one has the RAM. Declared in head.S */ that unfortunately had to go :) Link: https://lkml.kernel.org/r/20260211103141.3215197-4-rppt@kernel.org Signed-off-by: Mike Rapoport (Microsoft) Acked-by: Helge Deller [parisc] Tested-by: Helge Deller [parisc] Reviewed-by: Christophe Leroy (CS GROUP) Acked-by: Dave Hansen Acked-by: Catalin Marinas Acked-by: Magnus Lindholm [alpha] Acked-by: Dinh Nguyen [nios2] Acked-by: Andreas Larsson [sparc] Acked-by: David Hildenbrand (Arm) Acked-by: Liam R. Howlett Cc: "Borislav Petkov (AMD)" Cc: David S. Miller Cc: Geert Uytterhoeven Cc: Guo Ren Cc: Huacai Chen Cc: Ingo Molnar Cc: Johannes Berg Cc: John Paul Adrian Glaubitz Cc: Lorenzo Stoakes Cc: Madhavan Srinivasan Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Hocko Cc: Michal Simek Cc: Palmer Dabbelt Cc: Richard Weinberger Cc: Russell King Cc: Stafford Horne Cc: Suren Baghdasaryan Cc: Vineet Gupta Cc: Vlastimil Babka Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/alpha/include/asm/pgtable.h | 6 ------ arch/arc/include/asm/pgtable.h | 3 --- arch/arc/mm/init.c | 2 -- arch/arm/include/asm/pgtable.h | 9 --------- arch/arm/mm/mmu.c | 7 ------- arch/arm/mm/nommu.c | 7 ------- arch/arm64/include/asm/pgtable.h | 1 - arch/arm64/mm/mmu.c | 7 ------- arch/csky/include/asm/pgtable.h | 3 --- arch/csky/mm/init.c | 3 --- arch/hexagon/include/asm/pgtable.h | 6 ------ arch/hexagon/kernel/head.S | 5 ----- arch/hexagon/kernel/hexagon_ksyms.c | 1 - arch/loongarch/include/asm/pgtable.h | 9 --------- arch/loongarch/mm/init.c | 3 --- arch/m68k/include/asm/pgtable_mm.h | 9 --------- arch/m68k/include/asm/pgtable_no.h | 7 ------- arch/m68k/mm/init.c | 9 --------- arch/m68k/mm/mcfmmu.c | 2 -- arch/m68k/mm/motorola.c | 6 ------ arch/m68k/mm/sun3mmu.c | 2 -- arch/microblaze/include/asm/pgtable.h | 10 ---------- arch/microblaze/kernel/head.S | 4 ---- arch/microblaze/kernel/microblaze_ksyms.c | 2 -- arch/nios2/include/asm/pgtable.h | 7 ------- arch/nios2/kernel/head.S | 10 ---------- arch/nios2/kernel/nios2_ksyms.c | 1 - arch/openrisc/include/asm/pgtable.h | 4 ---- arch/openrisc/kernel/head.S | 3 --- arch/openrisc/kernel/or32_ksyms.c | 1 - arch/openrisc/mm/init.c | 3 --- arch/parisc/include/asm/pgtable.h | 11 ----------- arch/parisc/mm/init.c | 6 ------ arch/powerpc/include/asm/pgtable.h | 6 ------ arch/powerpc/mm/mem.c | 3 --- arch/riscv/include/asm/pgtable.h | 7 ------- arch/riscv/mm/init.c | 4 ---- arch/sh/include/asm/pgtable.h | 8 -------- arch/sh/include/asm/setup.h | 3 ++- arch/sh/kernel/head_32.S | 4 ++-- arch/sh/kernel/sh_ksyms_32.c | 1 - arch/sh/mm/init.c | 1 - arch/sparc/include/asm/pgtable_32.h | 8 -------- arch/sparc/include/asm/setup.h | 2 -- arch/sparc/kernel/head_32.S | 7 ------- arch/sparc/mm/init_32.c | 4 ---- arch/sparc/mm/init_64.c | 11 ++++------- arch/um/include/asm/pgtable.h | 9 --------- arch/um/include/shared/kern_util.h | 1 - arch/um/kernel/mem.c | 16 ---------------- arch/um/kernel/um_arch.c | 1 - arch/x86/include/asm/pgtable.h | 8 -------- arch/x86/kernel/head_32.S | 4 ---- arch/x86/kernel/head_64.S | 7 ------- arch/xtensa/include/asm/pgtable.h | 4 ---- arch/xtensa/kernel/head.S | 3 --- arch/xtensa/kernel/xtensa_ksyms.c | 2 -- 57 files changed, 8 insertions(+), 285 deletions(-) (limited to 'arch') diff --git a/arch/alpha/include/asm/pgtable.h b/arch/alpha/include/asm/pgtable.h index e9368c54be45..268ddde33617 100644 --- a/arch/alpha/include/asm/pgtable.h +++ b/arch/alpha/include/asm/pgtable.h @@ -126,12 +126,6 @@ struct vm_area_struct; */ #define pgprot_noncached(prot) (prot) -/* - * ZERO_PAGE is a global shared page that is always zero: used - * for zero-mapped memory areas etc.. - */ -#define ZERO_PAGE(vaddr) (virt_to_page(ZERO_PGE)) - /* * On certain platforms whose physical address space can overlap KSEG, * namely EV6 and above, we must re-twiddle the physaddr to restore the diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h index bd580e2b62d7..0fdaea81b5fa 100644 --- a/arch/arc/include/asm/pgtable.h +++ b/arch/arc/include/asm/pgtable.h @@ -21,9 +21,6 @@ #ifndef __ASSEMBLER__ -extern char empty_zero_page[PAGE_SIZE]; -#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page)) - extern pgd_t swapper_pg_dir[] __aligned(PAGE_SIZE); /* to cope with aliasing VIPT cache */ diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c index a5e92f46e5d1..d6b5c27a0098 100644 --- a/arch/arc/mm/init.c +++ b/arch/arc/mm/init.c @@ -19,8 +19,6 @@ #include pgd_t swapper_pg_dir[PTRS_PER_PGD] __aligned(PAGE_SIZE); -char empty_zero_page[PAGE_SIZE] __aligned(PAGE_SIZE); -EXPORT_SYMBOL(empty_zero_page); static const unsigned long low_mem_start = CONFIG_LINUX_RAM_BASE; static unsigned long low_mem_sz; diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h index 6fa9acd6a7f5..982795cf4563 100644 --- a/arch/arm/include/asm/pgtable.h +++ b/arch/arm/include/asm/pgtable.h @@ -10,15 +10,6 @@ #include #include -#ifndef __ASSEMBLY__ -/* - * ZERO_PAGE is a global shared page that is always zero: used - * for zero-mapped memory areas etc.. - */ -extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; -#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page)) -#endif - #include #ifndef CONFIG_MMU diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 518def8314e7..23b87b5ef7f1 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -41,13 +41,6 @@ extern unsigned long __atags_pointer; -/* - * empty_zero_page is a special page that is used for - * zero-initialized data and COW. - */ -unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss; -EXPORT_SYMBOL(empty_zero_page); - /* * The pmd table for the upper-most set of pages. */ diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c index 7e42d8accec6..040ea43cce32 100644 --- a/arch/arm/mm/nommu.c +++ b/arch/arm/mm/nommu.c @@ -27,13 +27,6 @@ unsigned long vectors_base; -/* - * empty_zero_page is a special page that is used for - * zero-initialized data and COW. - */ -unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss; -EXPORT_SYMBOL(empty_zero_page); - #ifdef CONFIG_ARM_MPU struct mpu_rgn_info mpu_rgn_info; #endif diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index b3e58735c49b..769570e43c18 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -110,7 +110,6 @@ static inline void arch_leave_lazy_mmu_mode(void) * ZERO_PAGE is a global shared page that is always zero: used * for zero-mapped memory areas etc.. */ -extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; #define ZERO_PAGE(vaddr) phys_to_page(__pa_symbol(empty_zero_page)) #define pte_ERROR(e) \ diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index a12ea8776c32..ec932f6ccddc 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -64,13 +64,6 @@ static bool rodata_is_rw __ro_after_init = true; */ long __section(".mmuoff.data.write") __early_cpu_boot_status; -/* - * Empty_zero_page is a special page that is used for zero-initialized data - * and COW. - */ -unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss; -EXPORT_SYMBOL(empty_zero_page); - static DEFINE_SPINLOCK(swapper_pgdir_lock); static DEFINE_MUTEX(fixmap_lock); diff --git a/arch/csky/include/asm/pgtable.h b/arch/csky/include/asm/pgtable.h index d606afbabce1..bafcd5823531 100644 --- a/arch/csky/include/asm/pgtable.h +++ b/arch/csky/include/asm/pgtable.h @@ -76,9 +76,6 @@ #define MAX_SWAPFILES_CHECK() \ BUILD_BUG_ON(MAX_SWAPFILES_SHIFT != 5) -extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; -#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page)) - extern void load_pgd(unsigned long pg_dir); extern pte_t invalid_pte_table[PTRS_PER_PTE]; diff --git a/arch/csky/mm/init.c b/arch/csky/mm/init.c index 573da66b2543..fa16015ea1c0 100644 --- a/arch/csky/mm/init.c +++ b/arch/csky/mm/init.c @@ -38,9 +38,6 @@ pte_t invalid_pte_table[PTRS_PER_PTE] __page_aligned_bss; pte_t kernel_pte_tables[PTRS_KERN_TABLE] __page_aligned_bss; EXPORT_SYMBOL(invalid_pte_table); -unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] - __page_aligned_bss; -EXPORT_SYMBOL(empty_zero_page); void free_initmem(void) { diff --git a/arch/hexagon/include/asm/pgtable.h b/arch/hexagon/include/asm/pgtable.h index fbf24d1d1ca6..27b269e2870d 100644 --- a/arch/hexagon/include/asm/pgtable.h +++ b/arch/hexagon/include/asm/pgtable.h @@ -14,9 +14,6 @@ #include #include -/* A handy thing to have if one has the RAM. Declared in head.S */ -extern unsigned long empty_zero_page; - /* * The PTE model described here is that of the Hexagon Virtual Machine, * which autonomously walks 2-level page tables. At a lower level, we @@ -348,9 +345,6 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd) return (unsigned long)__va(pmd_val(pmd) & PAGE_MASK); } -/* ZERO_PAGE - returns the globally shared zero page */ -#define ZERO_PAGE(vaddr) (virt_to_page(&empty_zero_page)) - /* * Encode/decode swap entries and swap PTEs. Swap PTEs are all PTEs that * are !pte_none() && !pte_present(). diff --git a/arch/hexagon/kernel/head.S b/arch/hexagon/kernel/head.S index 0b016308cc79..908ffece9132 100644 --- a/arch/hexagon/kernel/head.S +++ b/arch/hexagon/kernel/head.S @@ -216,8 +216,3 @@ __head_s_vaddr_target: .p2align PAGE_SHIFT ENTRY(external_cmdline_buffer) .fill _PAGE_SIZE,1,0 - -.data -.p2align PAGE_SHIFT -ENTRY(empty_zero_page) - .fill _PAGE_SIZE,1,0 diff --git a/arch/hexagon/kernel/hexagon_ksyms.c b/arch/hexagon/kernel/hexagon_ksyms.c index 36a80e31d187..81bc6f81e200 100644 --- a/arch/hexagon/kernel/hexagon_ksyms.c +++ b/arch/hexagon/kernel/hexagon_ksyms.c @@ -17,7 +17,6 @@ EXPORT_SYMBOL(raw_copy_to_user); EXPORT_SYMBOL(__vmgetie); EXPORT_SYMBOL(__vmsetie); EXPORT_SYMBOL(__vmyield); -EXPORT_SYMBOL(empty_zero_page); EXPORT_SYMBOL(memcpy); EXPORT_SYMBOL(memset); diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h index c33b3bcb733e..a244de27a03e 100644 --- a/arch/loongarch/include/asm/pgtable.h +++ b/arch/loongarch/include/asm/pgtable.h @@ -74,15 +74,6 @@ struct mm_struct; struct vm_area_struct; -/* - * ZERO_PAGE is a global shared page that is always zero; used - * for zero-mapped memory areas etc.. - */ - -extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; - -#define ZERO_PAGE(vaddr) virt_to_page(empty_zero_page) - #ifdef CONFIG_32BIT #define VMALLOC_START (vm_map_base + PCI_IOSIZE + (2 * PAGE_SIZE)) diff --git a/arch/loongarch/mm/init.c b/arch/loongarch/mm/init.c index c331bf69d2ec..00f3822b6e47 100644 --- a/arch/loongarch/mm/init.c +++ b/arch/loongarch/mm/init.c @@ -36,9 +36,6 @@ #include #include -unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss; -EXPORT_SYMBOL(empty_zero_page); - void copy_user_highpage(struct page *to, struct page *from, unsigned long vaddr, struct vm_area_struct *vma) { diff --git a/arch/m68k/include/asm/pgtable_mm.h b/arch/m68k/include/asm/pgtable_mm.h index bba64a9c49ac..7501ff030c63 100644 --- a/arch/m68k/include/asm/pgtable_mm.h +++ b/arch/m68k/include/asm/pgtable_mm.h @@ -110,15 +110,6 @@ extern unsigned long m68k_vmalloc_end; #define VMALLOC_END KMAP_START #endif -/* zero page used for uninitialized stuff */ -extern void *empty_zero_page; - -/* - * ZERO_PAGE is a global shared page that is always zero: used - * for zero-mapped memory areas etc.. - */ -#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page)) - extern void kernel_set_cachemode(void *addr, unsigned long size, int cmode); /* diff --git a/arch/m68k/include/asm/pgtable_no.h b/arch/m68k/include/asm/pgtable_no.h index 1a86c15b9008..11751807a3f3 100644 --- a/arch/m68k/include/asm/pgtable_no.h +++ b/arch/m68k/include/asm/pgtable_no.h @@ -30,13 +30,6 @@ #define swapper_pg_dir ((pgd_t *) 0) -/* - * ZERO_PAGE is a global shared page that is always zero: used - * for zero-mapped memory areas etc.. - */ -extern void *empty_zero_page; -#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page)) - /* * All 32bit addresses are effectively valid for vmalloc... * Sort of meaningless for non-VM targets. diff --git a/arch/m68k/mm/init.c b/arch/m68k/mm/init.c index 53b71f786c27..3b88c0dd1616 100644 --- a/arch/m68k/mm/init.c +++ b/arch/m68k/mm/init.c @@ -33,13 +33,6 @@ #include #include -/* - * ZERO_PAGE is a special page that is used for zero-initialized - * data and COW. - */ -void *empty_zero_page; -EXPORT_SYMBOL(empty_zero_page); - void __init arch_zone_limits_init(unsigned long *max_zone_pfns) { max_zone_pfns[ZONE_DMA] = PFN_DOWN(memblock_end_of_DRAM()); @@ -71,8 +64,6 @@ void __init paging_init(void) unsigned long end_mem = memory_end & PAGE_MASK; high_memory = (void *) end_mem; - - empty_zero_page = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE); } #endif /* CONFIG_MMU */ diff --git a/arch/m68k/mm/mcfmmu.c b/arch/m68k/mm/mcfmmu.c index 3418fd864237..4924f2ff8ef8 100644 --- a/arch/m68k/mm/mcfmmu.c +++ b/arch/m68k/mm/mcfmmu.c @@ -41,8 +41,6 @@ void __init paging_init(void) unsigned long next_pgtable; int i; - empty_zero_page = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE); - pg_dir = swapper_pg_dir; memset(swapper_pg_dir, 0, sizeof(swapper_pg_dir)); diff --git a/arch/m68k/mm/motorola.c b/arch/m68k/mm/motorola.c index 127a3fa69f4c..b30aa69a73a6 100644 --- a/arch/m68k/mm/motorola.c +++ b/arch/m68k/mm/motorola.c @@ -498,12 +498,6 @@ void __init paging_init(void) early_memtest(min_addr, max_addr); - /* - * initialize the bad page table and bad page to point - * to a couple of allocated pages - */ - empty_zero_page = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE); - /* * Set up SFC/DFC registers */ diff --git a/arch/m68k/mm/sun3mmu.c b/arch/m68k/mm/sun3mmu.c index c801677f7df8..f139cc15753a 100644 --- a/arch/m68k/mm/sun3mmu.c +++ b/arch/m68k/mm/sun3mmu.c @@ -43,8 +43,6 @@ void __init paging_init(void) unsigned long bootmem_end; unsigned long size; - empty_zero_page = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE); - address = PAGE_OFFSET; pg_dir = swapper_pg_dir; memset (swapper_pg_dir, 0, sizeof (swapper_pg_dir)); diff --git a/arch/microblaze/include/asm/pgtable.h b/arch/microblaze/include/asm/pgtable.h index 4eb76de6be4a..ea72291de553 100644 --- a/arch/microblaze/include/asm/pgtable.h +++ b/arch/microblaze/include/asm/pgtable.h @@ -207,16 +207,6 @@ extern pte_t *va_to_pte(unsigned long address); * Also, write permissions imply read permissions. */ -#ifndef __ASSEMBLER__ -/* - * ZERO_PAGE is a global shared page that is always zero: used - * for zero-mapped memory areas etc.. - */ -extern unsigned long empty_zero_page[1024]; -#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page)) - -#endif /* __ASSEMBLER__ */ - #define pte_none(pte) ((pte_val(pte) & ~_PTE_NONE_MASK) == 0) #define pte_present(pte) (pte_val(pte) & _PAGE_PRESENT) #define pte_clear(mm, addr, ptep) \ diff --git a/arch/microblaze/kernel/head.S b/arch/microblaze/kernel/head.S index ec2fcb545e64..808019c3b7ac 100644 --- a/arch/microblaze/kernel/head.S +++ b/arch/microblaze/kernel/head.S @@ -39,10 +39,6 @@ #include .section .data -.global empty_zero_page -.align 12 -empty_zero_page: - .space PAGE_SIZE .global swapper_pg_dir swapper_pg_dir: .space PAGE_SIZE diff --git a/arch/microblaze/kernel/microblaze_ksyms.c b/arch/microblaze/kernel/microblaze_ksyms.c index a8553f54152b..ad7596d7ba07 100644 --- a/arch/microblaze/kernel/microblaze_ksyms.c +++ b/arch/microblaze/kernel/microblaze_ksyms.c @@ -33,8 +33,6 @@ EXPORT_SYMBOL(memcpy); EXPORT_SYMBOL(memmove); #endif -EXPORT_SYMBOL(empty_zero_page); - EXPORT_SYMBOL(mbc); extern void __divsi3(void); diff --git a/arch/nios2/include/asm/pgtable.h b/arch/nios2/include/asm/pgtable.h index 844dce55569f..d389aa9ca57c 100644 --- a/arch/nios2/include/asm/pgtable.h +++ b/arch/nios2/include/asm/pgtable.h @@ -65,13 +65,6 @@ struct mm_struct; #define PGDIR_SIZE (1UL << PGDIR_SHIFT) #define PGDIR_MASK (~(PGDIR_SIZE-1)) -/* - * ZERO_PAGE is a global shared page that is always zero: used - * for zero-mapped memory areas etc.. - */ -extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; -#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page)) - extern pgd_t swapper_pg_dir[PTRS_PER_PGD]; extern pte_t invalid_pte_table[PAGE_SIZE/sizeof(pte_t)]; diff --git a/arch/nios2/kernel/head.S b/arch/nios2/kernel/head.S index 372ce4a33018..613212e1a63a 100644 --- a/arch/nios2/kernel/head.S +++ b/arch/nios2/kernel/head.S @@ -23,16 +23,6 @@ #include #include -/* - * ZERO_PAGE is a special page that is used for zero-initialized - * data and COW. - */ -.data -.global empty_zero_page -.align 12 -empty_zero_page: - .space PAGE_SIZE - /* * This global variable is used as an extension to the nios' * STATUS register to emulate a user/supervisor mode. diff --git a/arch/nios2/kernel/nios2_ksyms.c b/arch/nios2/kernel/nios2_ksyms.c index 54f7b23df1bf..c40aa39e8658 100644 --- a/arch/nios2/kernel/nios2_ksyms.c +++ b/arch/nios2/kernel/nios2_ksyms.c @@ -20,7 +20,6 @@ EXPORT_SYMBOL(memmove); /* memory management */ -EXPORT_SYMBOL(empty_zero_page); EXPORT_SYMBOL(flush_icache_range); /* diff --git a/arch/openrisc/include/asm/pgtable.h b/arch/openrisc/include/asm/pgtable.h index b218050e2f6d..6b89996d0b62 100644 --- a/arch/openrisc/include/asm/pgtable.h +++ b/arch/openrisc/include/asm/pgtable.h @@ -179,10 +179,6 @@ extern void paging_init(void); __pgprot(_PAGE_ALL | _PAGE_SRE | _PAGE_SWE \ | _PAGE_SHARED | _PAGE_DIRTY | _PAGE_EXEC | _PAGE_CI) -/* zero page used for uninitialized stuff */ -extern unsigned long empty_zero_page[2048]; -#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page)) - #define pte_none(x) (!pte_val(x)) #define pte_present(x) (pte_val(x) & _PAGE_PRESENT) #define pte_clear(mm, addr, xp) do { pte_val(*(xp)) = 0; } while (0) diff --git a/arch/openrisc/kernel/head.S b/arch/openrisc/kernel/head.S index bd760066f1cd..45890393947d 100644 --- a/arch/openrisc/kernel/head.S +++ b/arch/openrisc/kernel/head.S @@ -1563,9 +1563,6 @@ _string_nl: */ .section .data,"aw" .align 8192 - .global empty_zero_page -empty_zero_page: - .space 8192 .global swapper_pg_dir swapper_pg_dir: diff --git a/arch/openrisc/kernel/or32_ksyms.c b/arch/openrisc/kernel/or32_ksyms.c index 212e5f85004c..84a937a64e2a 100644 --- a/arch/openrisc/kernel/or32_ksyms.c +++ b/arch/openrisc/kernel/or32_ksyms.c @@ -40,7 +40,6 @@ DECLARE_EXPORT(__ashldi3); DECLARE_EXPORT(__lshrdi3); DECLARE_EXPORT(__ucmpdi2); -EXPORT_SYMBOL(empty_zero_page); EXPORT_SYMBOL(__copy_tofrom_user); EXPORT_SYMBOL(__clear_user); EXPORT_SYMBOL(memset); diff --git a/arch/openrisc/mm/init.c b/arch/openrisc/mm/init.c index 78fb0734cdbc..89d8c6df8855 100644 --- a/arch/openrisc/mm/init.c +++ b/arch/openrisc/mm/init.c @@ -188,9 +188,6 @@ void __init mem_init(void) { BUG_ON(!mem_map); - /* clear the zero-page */ - memset((void *)empty_zero_page, 0, PAGE_SIZE); - printk("mem_init_done ...........................................\n"); mem_init_done = 1; return; diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index 17afe7a59edf..f6fb99cb94d9 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -262,17 +262,6 @@ extern pgd_t swapper_pg_dir[]; /* declared in init_task.c */ extern pte_t pg0[]; -/* zero page used for uninitialized stuff */ - -extern unsigned long *empty_zero_page; - -/* - * ZERO_PAGE is a global shared page that is always zero: used - * for zero-mapped memory areas etc.. - */ - -#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page)) - #define pte_none(x) (pte_val(x) == 0) #define pte_present(x) (pte_val(x) & _PAGE_PRESENT) #define pte_user(x) (pte_val(x) & _PAGE_USER) diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c index 6a39e031e5ff..be3380c9bcda 100644 --- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -604,9 +604,6 @@ void __init mem_init(void) #endif } -unsigned long *empty_zero_page __ro_after_init; -EXPORT_SYMBOL(empty_zero_page); - /* * pagetable_init() sets up the page tables * @@ -639,9 +636,6 @@ static void __init pagetable_init(void) initrd_end - initrd_start, PAGE_KERNEL, 0); } #endif - - empty_zero_page = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE); - } static void __init gateway_init(void) diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index dcd3a88caaf6..b27d94c06d0e 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -76,12 +76,6 @@ static inline const void *pmd_page_vaddr(pmd_t pmd) } #define pmd_page_vaddr pmd_page_vaddr #endif -/* - * ZERO_PAGE is a global shared page that is always zero: used - * for zero-mapped memory areas etc.. - */ -extern unsigned long empty_zero_page[]; -#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page)) extern pgd_t swapper_pg_dir[]; diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index b7982d0243d4..648d0c5602ec 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -38,9 +38,6 @@ unsigned long long memory_limit __initdata; -unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss; -EXPORT_SYMBOL(empty_zero_page); - pgprot_t __phys_mem_access_prot(unsigned long pfn, unsigned long size, pgprot_t vma_prot) { diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 08d1ca047104..ab4ce1cc9d9c 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -1284,13 +1284,6 @@ extern u64 satp_mode; void paging_init(void); void misc_mem_init(void); -/* - * ZERO_PAGE is a global shared page that is always zero, - * used for zero-mapped memory areas, etc. - */ -extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; -#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page)) - /* * Use set_p*_safe(), and elide TLB flushing, when confident that *no* * TLB flush will be required as a result of the "set". For example, use diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 811e03786c56..017bad735d47 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -69,10 +69,6 @@ unsigned long vmemmap_start_pfn __ro_after_init; EXPORT_SYMBOL(vmemmap_start_pfn); #endif -unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] - __page_aligned_bss; -EXPORT_SYMBOL(empty_zero_page); - extern char _start[]; void *_dtb_early_va __initdata; uintptr_t _dtb_early_pa __initdata; diff --git a/arch/sh/include/asm/pgtable.h b/arch/sh/include/asm/pgtable.h index 10fa8f2bb8d1..d5ce0950a323 100644 --- a/arch/sh/include/asm/pgtable.h +++ b/arch/sh/include/asm/pgtable.h @@ -20,14 +20,6 @@ #ifndef __ASSEMBLER__ #include #include - -/* - * ZERO_PAGE is a global shared page that is always zero: used - * for zero-mapped memory areas etc.. - */ -extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; -#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page)) - #endif /* !__ASSEMBLER__ */ /* diff --git a/arch/sh/include/asm/setup.h b/arch/sh/include/asm/setup.h index 84bb23a771f3..63c9efc06348 100644 --- a/arch/sh/include/asm/setup.h +++ b/arch/sh/include/asm/setup.h @@ -7,7 +7,8 @@ /* * This is set up by the setup-routine at boot-time */ -#define PARAM ((unsigned char *)empty_zero_page) +extern unsigned char *boot_params_page; +#define PARAM boot_params_page #define MOUNT_ROOT_RDONLY (*(unsigned long *) (PARAM+0x000)) #define RAMDISK_FLAGS (*(unsigned long *) (PARAM+0x004)) diff --git a/arch/sh/kernel/head_32.S b/arch/sh/kernel/head_32.S index b603b7968b38..0b91bb85d40a 100644 --- a/arch/sh/kernel/head_32.S +++ b/arch/sh/kernel/head_32.S @@ -26,7 +26,7 @@ #endif .section .empty_zero_page, "aw" -ENTRY(empty_zero_page) +ENTRY(boot_params_page) .long 1 /* MOUNT_ROOT_RDONLY */ .long 0 /* RAMDISK_FLAGS */ .long 0x0200 /* ORIG_ROOT_DEV */ @@ -39,7 +39,7 @@ ENTRY(empty_zero_page) .long 0x53453f00 + 29 /* "SE?" = 29 bit */ #endif 1: - .skip PAGE_SIZE - empty_zero_page - 1b + .skip PAGE_SIZE - boot_params_page - 1b __HEAD diff --git a/arch/sh/kernel/sh_ksyms_32.c b/arch/sh/kernel/sh_ksyms_32.c index 5858936cb431..041191002e2e 100644 --- a/arch/sh/kernel/sh_ksyms_32.c +++ b/arch/sh/kernel/sh_ksyms_32.c @@ -20,7 +20,6 @@ EXPORT_SYMBOL(csum_partial); EXPORT_SYMBOL(csum_partial_copy_generic); EXPORT_SYMBOL(copy_page); EXPORT_SYMBOL(__clear_user); -EXPORT_SYMBOL(empty_zero_page); #ifdef CONFIG_FLATMEM /* need in pfn_valid macro */ EXPORT_SYMBOL(min_low_pfn); diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index 464a3a63e2fa..4e40d5e96be9 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -332,7 +332,6 @@ void __init mem_init(void) cpu_cache_init(); /* clear the zero-page */ - memset(empty_zero_page, 0, PAGE_SIZE); __flush_wback_region(empty_zero_page, PAGE_SIZE); vsyscall_init(); diff --git a/arch/sparc/include/asm/pgtable_32.h b/arch/sparc/include/asm/pgtable_32.h index a9f802d1dd64..f89b1250661d 100644 --- a/arch/sparc/include/asm/pgtable_32.h +++ b/arch/sparc/include/asm/pgtable_32.h @@ -71,14 +71,6 @@ extern unsigned long ptr_in_current_pgd; extern unsigned long phys_base; extern unsigned long pfn_base; -/* - * ZERO_PAGE is a global shared page that is always zero: used - * for zero-mapped memory areas etc.. - */ -extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; - -#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page)) - /* * In general all page table modifications should use the V8 atomic * swap instruction. This insures the mmu and the cpu are in sync diff --git a/arch/sparc/include/asm/setup.h b/arch/sparc/include/asm/setup.h index 72205684e51e..21bed5514028 100644 --- a/arch/sparc/include/asm/setup.h +++ b/arch/sparc/include/asm/setup.h @@ -17,8 +17,6 @@ extern char reboot_command[]; */ extern unsigned char boot_cpu_id; -extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; - extern int serial_console; static inline int con_is_present(void) { diff --git a/arch/sparc/kernel/head_32.S b/arch/sparc/kernel/head_32.S index 38345460d542..8c320fa25a67 100644 --- a/arch/sparc/kernel/head_32.S +++ b/arch/sparc/kernel/head_32.S @@ -57,13 +57,6 @@ sun4e_notsup: .align PAGE_SIZE -/* This was the only reasonable way I could think of to properly align - * these page-table data structures. - */ - .globl empty_zero_page -empty_zero_page: .skip PAGE_SIZE -EXPORT_SYMBOL(empty_zero_page) - .global root_flags .global ram_flags .global root_dev diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c index fdc93dd12c3e..e0e66f91ceeb 100644 --- a/arch/sparc/mm/init_32.c +++ b/arch/sparc/mm/init_32.c @@ -246,10 +246,6 @@ void __init arch_mm_preinit(void) prom_halt(); } - - /* Saves us work later. */ - memset((void *)empty_zero_page, 0, PAGE_SIZE); - i = last_valid_pfn >> ((20 - PAGE_SHIFT) + 5); i += 1; sparc_valid_addr_bitmap = (unsigned long *) diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index f46394c46a76..748790998ff5 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -2492,6 +2492,9 @@ static void __init register_page_bootmem_info(void) } void __init mem_init(void) { + phys_addr_t zero_page_pa = kern_base + + ((unsigned long)&empty_zero_page[0] - KERNBASE); + /* * Must be done after boot memory is put on freelist, because here we * might set fields in deferred struct pages that have not yet been @@ -2504,13 +2507,7 @@ void __init mem_init(void) * Set up the zero page, mark it reserved, so that page count * is not manipulated when freeing the page from user ptes. */ - mem_map_zero = alloc_pages(GFP_KERNEL|__GFP_ZERO, 0); - if (mem_map_zero == NULL) { - prom_printf("paging_init: Cannot alloc zero page.\n"); - prom_halt(); - } - mark_page_reserved(mem_map_zero); - + mem_map_zero = pfn_to_page(PHYS_PFN(zero_page_pa)); if (tlb_type == cheetah || tlb_type == cheetah_plus) cheetah_ecache_flush_init(); diff --git a/arch/um/include/asm/pgtable.h b/arch/um/include/asm/pgtable.h index 3b42b0f45bf6..19e0608fb649 100644 --- a/arch/um/include/asm/pgtable.h +++ b/arch/um/include/asm/pgtable.h @@ -34,9 +34,6 @@ extern pgd_t swapper_pg_dir[PTRS_PER_PGD]; -/* zero page used for uninitialized stuff */ -extern unsigned long *empty_zero_page; - /* Just any arbitrary offset to the start of the vmalloc VM area: the * current 8MB value just means that there will be a 8MB "hole" after the * physical memory until the kernel virtual memory starts. That means that @@ -74,12 +71,6 @@ extern unsigned long *empty_zero_page; * get.. */ -/* - * ZERO_PAGE is a global shared page that is always zero: used - * for zero-mapped memory areas etc.. - */ -#define ZERO_PAGE(vaddr) virt_to_page(empty_zero_page) - #define pte_clear(mm, addr, xp) pte_set_val(*(xp), (phys_t) 0, __pgprot(_PAGE_NEEDSYNC)) #define pmd_none(x) (!((unsigned long)pmd_val(x) & ~_PAGE_NEEDSYNC)) diff --git a/arch/um/include/shared/kern_util.h b/arch/um/include/shared/kern_util.h index 38321188c04c..9812efd14ec0 100644 --- a/arch/um/include/shared/kern_util.h +++ b/arch/um/include/shared/kern_util.h @@ -38,7 +38,6 @@ extern void timer_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs extern void uml_pm_wake(void); extern int start_uml(void); -extern void paging_init(void); extern void uml_cleanup(void); extern void do_uml_exitcalls(void); diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c index 89c8c8b94a79..1eef0e42ef5d 100644 --- a/arch/um/kernel/mem.c +++ b/arch/um/kernel/mem.c @@ -44,10 +44,6 @@ __section(".kasan_init") __used = kasan_init; #endif -/* allocated in paging_init, zeroed in mem_init, and unchanged thereafter */ -unsigned long *empty_zero_page = NULL; -EXPORT_SYMBOL(empty_zero_page); - /* * Initialized during boot, and readonly for initializing page tables * afterwards @@ -65,9 +61,6 @@ void __init arch_mm_preinit(void) /* Safe to call after jump_label_init(). Enables KASAN. */ kasan_init_generic(); - /* clear the zero-page */ - memset(empty_zero_page, 0, PAGE_SIZE); - /* Map in the area just after the brk now that kmalloc is about * to be turned on. */ @@ -89,15 +82,6 @@ void __init arch_zone_limits_init(unsigned long *max_zone_pfns) max_zone_pfns[ZONE_NORMAL] = high_physmem >> PAGE_SHIFT; } -void __init paging_init(void) -{ - empty_zero_page = (unsigned long *) memblock_alloc_low(PAGE_SIZE, - PAGE_SIZE); - if (!empty_zero_page) - panic("%s: Failed to allocate %lu bytes align=%lx\n", - __func__, PAGE_SIZE, PAGE_SIZE); -} - /* * This can't do anything because nothing in the kernel image can be freed * since it's not in kernel physical memory. diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index e2b24e1ecfa6..2141f5f1f5a2 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -413,7 +413,6 @@ void __init setup_arch(char **cmdline_p) uml_dtb_init(); read_initrd(); - paging_init(); strscpy(boot_command_line, command_line, COMMAND_LINE_SIZE); *cmdline_p = command_line; setup_hostinfo(host_info, sizeof host_info); diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 1662c5a8f445..54289f4587a4 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -47,14 +47,6 @@ void ptdump_walk_user_pgd_level_checkwx(void); #define debug_checkwx_user() do { } while (0) #endif -/* - * ZERO_PAGE is a global shared page that is always zero: used - * for zero-mapped memory areas etc.. - */ -extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] - __visible; -#define ZERO_PAGE(vaddr) ((void)(vaddr),virt_to_page(empty_zero_page)) - extern spinlock_t pgd_lock; extern struct list_head pgd_list; diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 80ef5d386b03..5171cb746444 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -441,10 +441,6 @@ initial_pg_fixmap: swapper_pg_dir: .fill 1024,4,0 .fill PTI_USER_PGD_FILL,4,0 -.globl empty_zero_page -empty_zero_page: - .fill 4096,1,0 -EXPORT_SYMBOL(empty_zero_page) /* * This starts the data section. diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 85d4a5094f6b..7ed5520dd52e 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -684,10 +684,3 @@ SYM_PIC_ALIAS(phys_base); EXPORT_SYMBOL(phys_base) #include "../xen/xen-head.S" - - __PAGE_ALIGNED_BSS -SYM_DATA_START_PAGE_ALIGNED(empty_zero_page) - .skip PAGE_SIZE -SYM_DATA_END(empty_zero_page) -EXPORT_SYMBOL(empty_zero_page) - diff --git a/arch/xtensa/include/asm/pgtable.h b/arch/xtensa/include/asm/pgtable.h index 50a136213b2b..61f07d981a94 100644 --- a/arch/xtensa/include/asm/pgtable.h +++ b/arch/xtensa/include/asm/pgtable.h @@ -209,10 +209,6 @@ #define pgd_ERROR(e) \ printk("%s:%d: bad pgd entry %08lx.\n", __FILE__, __LINE__, pgd_val(e)) -extern unsigned long empty_zero_page[1024]; - -#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page)) - #ifdef CONFIG_MMU extern pgd_t swapper_pg_dir[PAGE_SIZE/sizeof(pgd_t)]; extern void paging_init(void); diff --git a/arch/xtensa/kernel/head.S b/arch/xtensa/kernel/head.S index 8484294bc623..4b0c5c5e685a 100644 --- a/arch/xtensa/kernel/head.S +++ b/arch/xtensa/kernel/head.S @@ -381,6 +381,3 @@ ENTRY(swapper_pg_dir) .fill PAGE_SIZE, 1, 0 END(swapper_pg_dir) #endif -ENTRY(empty_zero_page) - .fill PAGE_SIZE, 1, 0 -END(empty_zero_page) diff --git a/arch/xtensa/kernel/xtensa_ksyms.c b/arch/xtensa/kernel/xtensa_ksyms.c index 62d81e76e18e..ced335b4df5f 100644 --- a/arch/xtensa/kernel/xtensa_ksyms.c +++ b/arch/xtensa/kernel/xtensa_ksyms.c @@ -15,8 +15,6 @@ #include #include -EXPORT_SYMBOL(empty_zero_page); - unsigned int __sync_fetch_and_and_4(volatile void *p, unsigned int v) { BUG(); -- cgit v1.2.3 From 26513781d1b3a1e8b4b576ed62751d604a69b374 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" Date: Wed, 11 Feb 2026 12:31:41 +0200 Subject: mm: cache struct page for empty_zero_page and return it from ZERO_PAGE() For most architectures every invocation of ZERO_PAGE() does virt_to_page(empty_zero_page). But empty_zero_page is in BSS and it is enough to get its struct page once at initialization time and then use it whenever a zero page should be accessed. Add yet another __zero_page variable that will be initialized as virt_to_page(empty_zero_page) for most architectures in a weak arch_setup_zero_pages() function. For architectures that use colored zero pages (MIPS and s390) rename their setup_zero_pages() to arch_setup_zero_pages() and make it global rather than static. For architectures that cannot use virt_to_page() for BSS (arm64 and sparc64) add override of arch_setup_zero_pages(). Link: https://lkml.kernel.org/r/20260211103141.3215197-5-rppt@kernel.org Signed-off-by: Mike Rapoport (Microsoft) Acked-by: Catalin Marinas Acked-by: David Hildenbrand (Arm) Acked-by: Liam R. Howlett Cc: Andreas Larsson Cc: "Borislav Petkov (AMD)" Cc: Christophe Leroy (CS GROUP) Cc: Dave Hansen Cc: David S. Miller Cc: Dinh Nguyen Cc: Geert Uytterhoeven Cc: Guo Ren Cc: Helge Deller Cc: Huacai Chen Cc: Ingo Molnar Cc: Johannes Berg Cc: John Paul Adrian Glaubitz Cc: Lorenzo Stoakes Cc: Madhavan Srinivasan Cc: Magnus Lindholm Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Hocko Cc: Michal Simek Cc: Palmer Dabbelt Cc: Richard Weinberger Cc: Russell King Cc: Stafford Horne Cc: Suren Baghdasaryan Cc: Vineet Gupta Cc: Vlastimil Babka Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/arm64/include/asm/pgtable.h | 6 ------ arch/arm64/mm/init.c | 5 +++++ arch/mips/mm/init.c | 11 +---------- arch/s390/mm/init.c | 4 +--- arch/sparc/include/asm/pgtable_64.h | 3 --- arch/sparc/mm/init_64.c | 17 +++++++---------- 6 files changed, 14 insertions(+), 32 deletions(-) (limited to 'arch') diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 769570e43c18..aa4b13da6371 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -106,12 +106,6 @@ static inline void arch_leave_lazy_mmu_mode(void) #define flush_tlb_fix_spurious_fault_pmd(vma, address, pmdp) \ local_flush_tlb_page_nonotify(vma, address) -/* - * ZERO_PAGE is a global shared page that is always zero: used - * for zero-mapped memory areas etc.. - */ -#define ZERO_PAGE(vaddr) phys_to_page(__pa_symbol(empty_zero_page)) - #define pte_ERROR(e) \ pr_err("%s:%d: bad pte %016llx.\n", __FILE__, __LINE__, pte_val(e)) diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 96711b8578fd..417ec7efe569 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -328,6 +328,11 @@ void __init bootmem_init(void) memblock_dump_all(); } +void __init arch_setup_zero_pages(void) +{ + __zero_page = phys_to_page(__pa_symbol(empty_zero_page)); +} + void __init arch_mm_preinit(void) { unsigned int flags = SWIOTLB_VERBOSE; diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index 4f6449ad02ca..55b25e85122a 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -56,10 +56,7 @@ unsigned long empty_zero_page, zero_page_mask; EXPORT_SYMBOL_GPL(empty_zero_page); EXPORT_SYMBOL(zero_page_mask); -/* - * Not static inline because used by IP27 special magic initialization code - */ -static void __init setup_zero_pages(void) +void __init arch_setup_zero_pages(void) { unsigned int order; @@ -450,7 +447,6 @@ void __init arch_mm_preinit(void) BUILD_BUG_ON(IS_ENABLED(CONFIG_32BIT) && (PFN_PTE_SHIFT > PAGE_SHIFT)); maar_init(); - setup_zero_pages(); /* Setup zeroed pages. */ highmem_init(); #ifdef CONFIG_64BIT @@ -461,11 +457,6 @@ void __init arch_mm_preinit(void) 0x80000000 - 4, KCORE_TEXT); #endif } -#else /* CONFIG_NUMA */ -void __init arch_mm_preinit(void) -{ - setup_zero_pages(); /* This comes from node 0 */ -} #endif /* !CONFIG_NUMA */ void free_init_pages(const char *what, unsigned long begin, unsigned long end) diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index 3c20475cbee2..1f72efc2a579 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -69,7 +69,7 @@ unsigned long empty_zero_page, zero_page_mask; EXPORT_SYMBOL(empty_zero_page); EXPORT_SYMBOL(zero_page_mask); -static void __init setup_zero_pages(void) +void __init arch_setup_zero_pages(void) { unsigned long total_pages = memblock_estimated_nr_free_pages(); unsigned int order; @@ -159,8 +159,6 @@ void __init arch_mm_preinit(void) cpumask_set_cpu(0, mm_cpumask(&init_mm)); pv_init(); - - setup_zero_pages(); /* Setup zeroed pages. */ } unsigned long memory_block_size_bytes(void) diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 615f460c50af..74ede706fb32 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -210,9 +210,6 @@ extern unsigned long _PAGE_CACHE; extern unsigned long pg_iobits; extern unsigned long _PAGE_ALL_SZ_BITS; -extern struct page *mem_map_zero; -#define ZERO_PAGE(vaddr) (mem_map_zero) - /* PFNs are real physical page numbers. However, mem_map only begins to record * per-page information starting at pfn_base. This is to handle systems where * the first physical page in the machine is at some huge physical address, diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 748790998ff5..3aa47f2b6c6e 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -177,9 +177,6 @@ extern unsigned long sparc_ramdisk_image64; extern unsigned int sparc_ramdisk_image; extern unsigned int sparc_ramdisk_size; -struct page *mem_map_zero __read_mostly; -EXPORT_SYMBOL(mem_map_zero); - unsigned int sparc64_highest_unlocked_tlb_ent __read_mostly; unsigned long sparc64_kern_pri_context __read_mostly; @@ -2490,11 +2487,17 @@ static void __init register_page_bootmem_info(void) register_page_bootmem_info_node(NODE_DATA(i)); #endif } -void __init mem_init(void) + +void __init arch_setup_zero_pages(void) { phys_addr_t zero_page_pa = kern_base + ((unsigned long)&empty_zero_page[0] - KERNBASE); + __zero_page = phys_to_page(zero_page_pa); +} + +void __init mem_init(void) +{ /* * Must be done after boot memory is put on freelist, because here we * might set fields in deferred struct pages that have not yet been @@ -2503,12 +2506,6 @@ void __init mem_init(void) */ register_page_bootmem_info(); - /* - * Set up the zero page, mark it reserved, so that page count - * is not manipulated when freeing the page from user ptes. - */ - mem_map_zero = pfn_to_page(PHYS_PFN(zero_page_pa)); - if (tlb_type == cheetah || tlb_type == cheetah_plus) cheetah_ecache_flush_init(); } -- cgit v1.2.3 From 845e0af36235d893c34218cb629618168f8f34b4 Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Wed, 25 Feb 2026 16:13:59 +0000 Subject: arm64: gcs: use the new common vm_mmap_shadow_stack() helper Replace the arm64 map_shadow_stack() content with a call to vm_mmap_shadow_stack(). There is no functional change. Link: https://lkml.kernel.org/r/20260225161404.3157851-3-catalin.marinas@arm.com Signed-off-by: Catalin Marinas Reviewed-by: David Hildenbrand (Arm) Reviewed-by: Mark Brown Cc: Will Deacon Cc: Albert Ou Cc: Alexandre Ghiti Cc: "Borislav Petkov (AMD)" Cc: Dave Hansen Cc: Deepak Gupta Cc: "Edgecombe, Rick P" Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: "Liam R. Howlett" Cc: Lorenzo Stoakes Cc: Michal Hocko Cc: Mike Rapoport Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Suren Baghdasaryan Cc: Thomas Gleixner Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- arch/arm64/mm/gcs.c | 14 +------------- 1 file changed, 1 insertion(+), 13 deletions(-) (limited to 'arch') diff --git a/arch/arm64/mm/gcs.c b/arch/arm64/mm/gcs.c index 04a23a497f20..680749611a9a 100644 --- a/arch/arm64/mm/gcs.c +++ b/arch/arm64/mm/gcs.c @@ -12,19 +12,7 @@ static unsigned long alloc_gcs(unsigned long addr, unsigned long size) { - int flags = MAP_ANONYMOUS | MAP_PRIVATE; - struct mm_struct *mm = current->mm; - unsigned long mapped_addr, unused; - - if (addr) - flags |= MAP_FIXED_NOREPLACE; - - mmap_write_lock(mm); - mapped_addr = do_mmap(NULL, addr, size, PROT_READ, flags, - VM_SHADOW_STACK | VM_WRITE, 0, &unused, NULL); - mmap_write_unlock(mm); - - return mapped_addr; + return vm_mmap_shadow_stack(addr, size, 0); } static unsigned long gcs_size(unsigned long size) -- cgit v1.2.3 From fecd446f0ca44e9b2c38efea99cfc54fd4517f75 Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Wed, 25 Feb 2026 16:14:00 +0000 Subject: riscv: shstk: use the new common vm_mmap_shadow_stack() helper Replace part of the allocate_shadow_stack() content with a call to vm_mmap_shadow_stack(). There is no functional change. Link: https://lkml.kernel.org/r/20260225161404.3157851-4-catalin.marinas@arm.com Signed-off-by: Catalin Marinas Tested-by: Deepak Gupta Reviewed-by: David Hildenbrand (Arm) Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Albert Ou Cc: Alexandre Ghiti Cc: "Borislav Petkov (AMD)" Cc: Dave Hansen Cc: "Edgecombe, Rick P" Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: "Liam R. Howlett" Cc: Lorenzo Stoakes Cc: Mark Brown Cc: Michal Hocko Cc: Mike Rapoport Cc: Suren Baghdasaryan Cc: Thomas Gleixner Cc: Vlastimil Babka Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/riscv/kernel/usercfi.c | 12 +----------- 1 file changed, 1 insertion(+), 11 deletions(-) (limited to 'arch') diff --git a/arch/riscv/kernel/usercfi.c b/arch/riscv/kernel/usercfi.c index 1adba746f164..7e57f54dc5b2 100644 --- a/arch/riscv/kernel/usercfi.c +++ b/arch/riscv/kernel/usercfi.c @@ -230,17 +230,7 @@ int restore_user_shstk(struct task_struct *tsk, unsigned long shstk_ptr) static unsigned long allocate_shadow_stack(unsigned long addr, unsigned long size, unsigned long token_offset, bool set_tok) { - int flags = MAP_ANONYMOUS | MAP_PRIVATE; - struct mm_struct *mm = current->mm; - unsigned long populate; - - if (addr) - flags |= MAP_FIXED_NOREPLACE; - - mmap_write_lock(mm); - addr = do_mmap(NULL, addr, size, PROT_READ, flags, - VM_SHADOW_STACK | VM_WRITE, 0, &populate, NULL); - mmap_write_unlock(mm); + addr = vm_mmap_shadow_stack(addr, size, 0); if (!set_tok || IS_ERR_VALUE(addr)) goto out; -- cgit v1.2.3 From a515ffc9de96f86318bc44e2ba702c4b5fdbd5bb Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Wed, 25 Feb 2026 16:14:01 +0000 Subject: x86: shstk: use the new common vm_mmap_shadow_stack() helper Replace part of the x86 alloc_shstk() content with a call to vm_mmap_shadow_stack(). There is no functional change. Link: https://lkml.kernel.org/r/20260225161404.3157851-5-catalin.marinas@arm.com Signed-off-by: Catalin Marinas Reviewed-by: Rick Edgecombe Tested-by: Rick Edgecombe Reviewed-by: David Hildenbrand (Arm) Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: H. Peter Anvin Cc: Albert Ou Cc: Alexandre Ghiti Cc: Deepak Gupta Cc: "Liam R. Howlett" Cc: Lorenzo Stoakes Cc: Mark Brown Cc: Michal Hocko Cc: Mike Rapoport Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/x86/kernel/shstk.c | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/shstk.c b/arch/x86/kernel/shstk.c index 978232b6d48d..9725e7d89b1e 100644 --- a/arch/x86/kernel/shstk.c +++ b/arch/x86/kernel/shstk.c @@ -100,17 +100,9 @@ static int create_rstor_token(unsigned long ssp, unsigned long *token_addr) static unsigned long alloc_shstk(unsigned long addr, unsigned long size, unsigned long token_offset, bool set_res_tok) { - int flags = MAP_ANONYMOUS | MAP_PRIVATE | MAP_ABOVE4G; - struct mm_struct *mm = current->mm; - unsigned long mapped_addr, unused; + unsigned long mapped_addr; - if (addr) - flags |= MAP_FIXED_NOREPLACE; - - mmap_write_lock(mm); - mapped_addr = do_mmap(NULL, addr, size, PROT_READ, flags, - VM_SHADOW_STACK | VM_WRITE, 0, &unused, NULL); - mmap_write_unlock(mm); + mapped_addr = vm_mmap_shadow_stack(addr, size, MAP_ABOVE4G); if (!set_res_tok || IS_ERR_VALUE(mapped_addr)) goto out; -- cgit v1.2.3 From 476849b0fba4450f5adf22196bcff9c24c673bc4 Mon Sep 17 00:00:00 2001 From: Kiryl Shutsemau Date: Fri, 27 Feb 2026 19:42:43 +0000 Subject: riscv/mm: align vmemmap to maximal folio size The upcoming change to the HugeTLB vmemmap optimization (HVO) requires struct pages of the head page to be naturally aligned with regard to the folio size. Align vmemmap to the newly introduced MAX_FOLIO_VMEMMAP_ALIGN. Link: https://lkml.kernel.org/r/20260227194302.274384-6-kas@kernel.org Signed-off-by: Kiryl Shutsemau Cc: Albert Ou Cc: Alexandre Ghiti Cc: Baoquan He Cc: Christoph Lameter Cc: David Hildenbrand (arm) Cc: David Rientjes Cc: Frank van der Linden Cc: Harry Yoo Cc: Huacai Chen Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Lorenzo Stoakes Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Mike Rapoport Cc: Muchun Song Cc: Oscar Salvador Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Roman Gushchin Cc: Usama Arif Cc: Vlastimil Babka Cc: WANG Xuerui Cc: Zi Yan Signed-off-by: Andrew Morton --- arch/riscv/mm/init.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 017bad735d47..b5c50956bb8a 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -63,7 +63,8 @@ phys_addr_t phys_ram_base __ro_after_init; EXPORT_SYMBOL(phys_ram_base); #ifdef CONFIG_SPARSEMEM_VMEMMAP -#define VMEMMAP_ADDR_ALIGN (1ULL << SECTION_SIZE_BITS) +#define VMEMMAP_ADDR_ALIGN max(1ULL << SECTION_SIZE_BITS, \ + MAX_FOLIO_VMEMMAP_ALIGN) unsigned long vmemmap_start_pfn __ro_after_init; EXPORT_SYMBOL(vmemmap_start_pfn); -- cgit v1.2.3 From 2969b42c8f994330fc020ec0d235aeb43bce317c Mon Sep 17 00:00:00 2001 From: Kiryl Shutsemau Date: Fri, 27 Feb 2026 19:42:44 +0000 Subject: LoongArch/mm: align vmemmap to maximal folio size The upcoming change to the HugeTLB vmemmap optimization (HVO) requires struct pages of the head page to be naturally aligned with regard to the folio size. Align vmemmap to MAX_FOLIO_VMEMMAP_ALIGN. Link: https://lkml.kernel.org/r/20260227194302.274384-7-kas@kernel.org Signed-off-by: Kiryl Shutsemau Cc: Albert Ou Cc: Alexandre Ghiti Cc: Baoquan He Cc: Christoph Lameter Cc: David Hildenbrand (arm) Cc: David Rientjes Cc: Frank van der Linden Cc: Harry Yoo Cc: Huacai Chen Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Lorenzo Stoakes Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Mike Rapoport Cc: Muchun Song Cc: Oscar Salvador Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Roman Gushchin Cc: Usama Arif Cc: Vlastimil Babka Cc: WANG Xuerui Cc: Zi Yan Signed-off-by: Andrew Morton --- arch/loongarch/include/asm/pgtable.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h index a244de27a03e..155f70e93460 100644 --- a/arch/loongarch/include/asm/pgtable.h +++ b/arch/loongarch/include/asm/pgtable.h @@ -104,7 +104,8 @@ struct vm_area_struct; min(PTRS_PER_PGD * PTRS_PER_PUD * PTRS_PER_PMD * PTRS_PER_PTE * PAGE_SIZE, (1UL << cpu_vabits) / 2) - PMD_SIZE - VMEMMAP_SIZE - KFENCE_AREA_SIZE) #endif -#define vmemmap ((struct page *)((VMALLOC_END + PMD_SIZE) & PMD_MASK)) +#define VMEMMAP_ALIGN max(PMD_SIZE, MAX_FOLIO_VMEMMAP_ALIGN) +#define vmemmap ((struct page *)(ALIGN(VMALLOC_END, VMEMMAP_ALIGN))) #define VMEMMAP_END ((unsigned long)vmemmap + VMEMMAP_SIZE - 1) #define KFENCE_AREA_START (VMEMMAP_END + 1) -- cgit v1.2.3 From 76351f2f0c27b36600caa8767bc384745f51c7de Mon Sep 17 00:00:00 2001 From: "Kiryl Shutsemau (Meta)" Date: Fri, 27 Feb 2026 19:42:49 +0000 Subject: x86/vdso: undefine CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP for vdso32 The 32-bit VDSO build on x86_64 uses fake_32bit_build.h to undefine various kernel configuration options that are not suitable for the VDSO context or may cause build issues when including kernel headers. Undefine CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP in fake_32bit_build.h to prepare for change in HugeTLB Vmemmap Optimization. Link: https://lkml.kernel.org/r/20260227194302.274384-12-kas@kernel.org Signed-off-by: Kiryl Shutsemau (Meta) Acked-by: David Hildenbrand (Arm) Cc: Albert Ou Cc: Alexandre Ghiti Cc: Baoquan He Cc: Christoph Lameter Cc: David Rientjes Cc: Frank van der Linden Cc: Harry Yoo Cc: Huacai Chen Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Lorenzo Stoakes Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Mike Rapoport Cc: Muchun Song Cc: Oscar Salvador Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Roman Gushchin Cc: Usama Arif Cc: Vlastimil Babka Cc: WANG Xuerui Cc: Zi Yan Signed-off-by: Andrew Morton --- arch/x86/entry/vdso/vdso32/fake_32bit_build.h | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/x86/entry/vdso/vdso32/fake_32bit_build.h b/arch/x86/entry/vdso/vdso32/fake_32bit_build.h index db1b15f686e3..bc3e549795c3 100644 --- a/arch/x86/entry/vdso/vdso32/fake_32bit_build.h +++ b/arch/x86/entry/vdso/vdso32/fake_32bit_build.h @@ -11,6 +11,7 @@ #undef CONFIG_PGTABLE_LEVELS #undef CONFIG_ILLEGAL_POINTER_VALUE #undef CONFIG_SPARSEMEM_VMEMMAP +#undef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP #undef CONFIG_NR_CPUS #undef CONFIG_PARAVIRT_XXL -- cgit v1.2.3 From de008c9ba5684f14e83bcf86cd45fb0e4e6c4d82 Mon Sep 17 00:00:00 2001 From: "David Hildenbrand (Arm)" Date: Fri, 27 Feb 2026 21:08:33 +0100 Subject: mm/memory: remove "zap_details" parameter from zap_page_range_single() Nobody except memory.c should really set that parameter to non-NULL. So let's just drop it and make unmap_mapping_range_vma() use zap_page_range_single_batched() instead. [david@kernel.org: format on a single line] Link: https://lkml.kernel.org/r/8a27e9ac-2025-4724-a46d-0a7c90894ba7@kernel.org Link: https://lkml.kernel.org/r/20260227200848.114019-3-david@kernel.org Signed-off-by: David Hildenbrand (Arm) Reviewed-by: Lorenzo Stoakes (Oracle) Acked-by: Puranjay Mohan Cc: Alexander Gordeev Cc: Alexei Starovoitov Cc: Alice Ryhl Cc: Andrii Nakryiko Cc: Andy Lutomirski Cc: Arnaldo Carvalho de Melo Cc: Arnd Bergmann Cc: Arve Cc: "Borislav Petkov (AMD)" Cc: Carlos Llamas Cc: Christian Borntraeger Cc: Christian Brauner Cc: Claudio Imbrenda Cc: Daniel Borkman Cc: Dave Airlie Cc: David Ahern Cc: David Rientjes Cc: David S. Miller Cc: Dimitri Sivanich Cc: Eric Dumazet Cc: Gerald Schaefer Cc: Greg Kroah-Hartman Cc: Hartley Sweeten Cc: Heiko Carstens Cc: Ian Abbott Cc: Ingo Molnar Cc: Jakub Kacinski Cc: Jani Nikula Cc: Jann Horn Cc: Janosch Frank Cc: Jarkko Sakkinen Cc: Jason Gunthorpe Cc: Jonas Lahtinen Cc: Leon Romanovsky Cc: Liam Howlett Cc: Madhavan Srinivasan Cc: Matthew Wilcox (Oracle) Cc: Michael Ellerman Cc: Michal Hocko Cc: Miguel Ojeda Cc: Mike Rapoport Cc: Namhyung kim Cc: Neal Cardwell Cc: Paolo Abeni Cc: Pedro Falcato Cc: Peter Zijlstra Cc: Rodrigo Vivi Cc: Shakeel Butt Cc: Suren Baghdasaryan Cc: Todd Kjos Cc: Tvrtko Ursulin Cc: Vasily Gorbik Cc: Vincenzo Frascino Signed-off-by: Andrew Morton --- arch/s390/mm/gmap_helpers.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/s390/mm/gmap_helpers.c b/arch/s390/mm/gmap_helpers.c index dea83e3103e5..ae2d59a19313 100644 --- a/arch/s390/mm/gmap_helpers.c +++ b/arch/s390/mm/gmap_helpers.c @@ -89,7 +89,7 @@ void gmap_helper_discard(struct mm_struct *mm, unsigned long vmaddr, unsigned lo if (!vma) return; if (!is_vm_hugetlb_page(vma)) - zap_page_range_single(vma, vmaddr, min(end, vma->vm_end) - vmaddr, NULL); + zap_page_range_single(vma, vmaddr, min(end, vma->vm_end) - vmaddr); vmaddr = vma->vm_end; } } -- cgit v1.2.3 From 32bc7fe4a6f4d359b6de96cbc106d2cac695154e Mon Sep 17 00:00:00 2001 From: "David Hildenbrand (Arm)" Date: Fri, 27 Feb 2026 21:08:43 +0100 Subject: mm: rename zap_vma_pages() to zap_vma() Let's rename it to an even simpler name. While at it, add some simplistic kernel doc. Link: https://lkml.kernel.org/r/20260227200848.114019-13-david@kernel.org Signed-off-by: David Hildenbrand (Arm) Reviewed-by: Lorenzo Stoakes (Oracle) Cc: Alexander Gordeev Cc: Alexei Starovoitov Cc: Alice Ryhl Cc: Andrii Nakryiko Cc: Andy Lutomirski Cc: Arnaldo Carvalho de Melo Cc: Arnd Bergmann Cc: Arve Cc: "Borislav Petkov (AMD)" Cc: Carlos Llamas Cc: Christian Borntraeger Cc: Christian Brauner Cc: Claudio Imbrenda Cc: Daniel Borkman Cc: Dave Airlie Cc: David Ahern Cc: David Rientjes Cc: David S. Miller Cc: Dimitri Sivanich Cc: Eric Dumazet Cc: Gerald Schaefer Cc: Greg Kroah-Hartman Cc: Hartley Sweeten Cc: Heiko Carstens Cc: Ian Abbott Cc: Ingo Molnar Cc: Jakub Kacinski Cc: Jani Nikula Cc: Jann Horn Cc: Janosch Frank Cc: Jarkko Sakkinen Cc: Jason Gunthorpe Cc: Jonas Lahtinen Cc: Leon Romanovsky Cc: Liam Howlett Cc: Madhavan Srinivasan Cc: Matthew Wilcox (Oracle) Cc: Michael Ellerman Cc: Michal Hocko Cc: Miguel Ojeda Cc: Mike Rapoport Cc: Namhyung kim Cc: Neal Cardwell Cc: Paolo Abeni Cc: Pedro Falcato Cc: Peter Zijlstra Cc: Rodrigo Vivi Cc: Shakeel Butt Cc: Suren Baghdasaryan Cc: Todd Kjos Cc: Tvrtko Ursulin Cc: Vasily Gorbik Cc: Vincenzo Frascino Signed-off-by: Andrew Morton --- arch/powerpc/platforms/book3s/vas-api.c | 2 +- arch/powerpc/platforms/pseries/vas.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/platforms/book3s/vas-api.c b/arch/powerpc/platforms/book3s/vas-api.c index ea4ffa63f043..e96d79db69fe 100644 --- a/arch/powerpc/platforms/book3s/vas-api.c +++ b/arch/powerpc/platforms/book3s/vas-api.c @@ -414,7 +414,7 @@ static vm_fault_t vas_mmap_fault(struct vm_fault *vmf) /* * When the LPAR lost credits due to core removal or during * migration, invalidate the existing mapping for the current - * paste addresses and set windows in-active (zap_vma_pages in + * paste addresses and set windows in-active (zap_vma() in * reconfig_close_windows()). * New mapping will be done later after migration or new credits * available. So continue to receive faults if the user space diff --git a/arch/powerpc/platforms/pseries/vas.c b/arch/powerpc/platforms/pseries/vas.c index ceb0a8788c0a..fa05f04364fe 100644 --- a/arch/powerpc/platforms/pseries/vas.c +++ b/arch/powerpc/platforms/pseries/vas.c @@ -807,7 +807,7 @@ static int reconfig_close_windows(struct vas_caps *vcap, int excess_creds, * is done before the original mmap() and after the ioctl. */ if (vma) - zap_vma_pages(vma); + zap_vma(vma); mutex_unlock(&task_ref->mmap_mutex); mmap_write_unlock(task_ref->mm); -- cgit v1.2.3 From 0326440c3545c86b6501c7c636fcf018d6e87b8c Mon Sep 17 00:00:00 2001 From: "David Hildenbrand (Arm)" Date: Fri, 27 Feb 2026 21:08:45 +0100 Subject: mm: rename zap_page_range_single() to zap_vma_range() Let's rename it to make it better match our new naming scheme. While at it, polish the kerneldoc. [akpm@linux-foundation.org: fix rustfmtcheck] Link: https://lkml.kernel.org/r/20260227200848.114019-15-david@kernel.org Signed-off-by: David Hildenbrand (Arm) Reviewed-by: Lorenzo Stoakes (Oracle) Acked-by: Puranjay Mohan Cc: Alexander Gordeev Cc: Alexei Starovoitov Cc: Alice Ryhl Cc: Andrii Nakryiko Cc: Andy Lutomirski Cc: Arnaldo Carvalho de Melo Cc: Arnd Bergmann Cc: Arve Cc: "Borislav Petkov (AMD)" Cc: Carlos Llamas Cc: Christian Borntraeger Cc: Christian Brauner Cc: Claudio Imbrenda Cc: Daniel Borkman Cc: Dave Airlie Cc: David Ahern Cc: David Rientjes Cc: David S. Miller Cc: Dimitri Sivanich Cc: Eric Dumazet Cc: Gerald Schaefer Cc: Greg Kroah-Hartman Cc: Hartley Sweeten Cc: Heiko Carstens Cc: Ian Abbott Cc: Ingo Molnar Cc: Jakub Kacinski Cc: Jani Nikula Cc: Jann Horn Cc: Janosch Frank Cc: Jarkko Sakkinen Cc: Jason Gunthorpe Cc: Jonas Lahtinen Cc: Leon Romanovsky Cc: Liam Howlett Cc: Madhavan Srinivasan Cc: Matthew Wilcox (Oracle) Cc: Michael Ellerman Cc: Michal Hocko Cc: Miguel Ojeda Cc: Mike Rapoport Cc: Namhyung kim Cc: Neal Cardwell Cc: Paolo Abeni Cc: Pedro Falcato Cc: Peter Zijlstra Cc: Rodrigo Vivi Cc: Shakeel Butt Cc: Suren Baghdasaryan Cc: Todd Kjos Cc: Tvrtko Ursulin Cc: Vasily Gorbik Cc: Vincenzo Frascino Signed-off-by: Andrew Morton --- arch/s390/mm/gmap_helpers.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/s390/mm/gmap_helpers.c b/arch/s390/mm/gmap_helpers.c index ae2d59a19313..f8789ffcc05c 100644 --- a/arch/s390/mm/gmap_helpers.c +++ b/arch/s390/mm/gmap_helpers.c @@ -89,7 +89,7 @@ void gmap_helper_discard(struct mm_struct *mm, unsigned long vmaddr, unsigned lo if (!vma) return; if (!is_vm_hugetlb_page(vma)) - zap_page_range_single(vma, vmaddr, min(end, vma->vm_end) - vmaddr); + zap_vma_range(vma, vmaddr, min(end, vma->vm_end) - vmaddr); vmaddr = vma->vm_end; } } -- cgit v1.2.3 From 52a9e9cd181fab8b03cf4e982533224697669976 Mon Sep 17 00:00:00 2001 From: "David Hildenbrand (Arm)" Date: Fri, 27 Feb 2026 21:08:46 +0100 Subject: mm: rename zap_vma_ptes() to zap_special_vma_range() zap_vma_ptes() is the only zapping function we export to modules. It's essentially a wrapper around zap_vma_range(), however, with some safety checks: * That the passed range fits fully into the VMA * That it's only used for VM_PFNMAP We will add support for VM_MIXEDMAP next, so use the more-generic term "special vma", although "special" is a bit overloaded. Maybe we'll later just support any VM_SPECIAL flag. While at it, improve the kerneldoc. Link: https://lkml.kernel.org/r/20260227200848.114019-16-david@kernel.org Signed-off-by: David Hildenbrand (Arm) Acked-by: Leon Romanovsky [drivers/infiniband] Reviewed-by: Lorenzo Stoakes (Oracle) Cc: Alexander Gordeev Cc: Alexei Starovoitov Cc: Alice Ryhl Cc: Andrii Nakryiko Cc: Andy Lutomirski Cc: Arnaldo Carvalho de Melo Cc: Arnd Bergmann Cc: Arve Cc: "Borislav Petkov (AMD)" Cc: Carlos Llamas Cc: Christian Borntraeger Cc: Christian Brauner Cc: Claudio Imbrenda Cc: Daniel Borkman Cc: Dave Airlie Cc: David Ahern Cc: David Rientjes Cc: David S. Miller Cc: Dimitri Sivanich Cc: Eric Dumazet Cc: Gerald Schaefer Cc: Greg Kroah-Hartman Cc: Hartley Sweeten Cc: Heiko Carstens Cc: Ian Abbott Cc: Ingo Molnar Cc: Jakub Kacinski Cc: Jani Nikula Cc: Jann Horn Cc: Janosch Frank Cc: Jarkko Sakkinen Cc: Jason Gunthorpe Cc: Jonas Lahtinen Cc: Liam Howlett Cc: Madhavan Srinivasan Cc: Matthew Wilcox (Oracle) Cc: Michael Ellerman Cc: Michal Hocko Cc: Miguel Ojeda Cc: Mike Rapoport Cc: Namhyung kim Cc: Neal Cardwell Cc: Paolo Abeni Cc: Pedro Falcato Cc: Peter Zijlstra Cc: Rodrigo Vivi Cc: Shakeel Butt Cc: Suren Baghdasaryan Cc: Todd Kjos Cc: Tvrtko Ursulin Cc: Vasily Gorbik Cc: Vincenzo Frascino Signed-off-by: Andrew Morton --- arch/x86/kernel/cpu/sgx/encl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c index ac60ebde5d9b..3f0222d10f6e 100644 --- a/arch/x86/kernel/cpu/sgx/encl.c +++ b/arch/x86/kernel/cpu/sgx/encl.c @@ -1220,7 +1220,7 @@ void sgx_zap_enclave_ptes(struct sgx_encl *encl, unsigned long addr) ret = sgx_encl_find(encl_mm->mm, addr, &vma); if (!ret && encl == vma->vm_private_data) - zap_vma_ptes(vma, addr, PAGE_SIZE); + zap_special_vma_range(vma, addr, PAGE_SIZE); mmap_read_unlock(encl_mm->mm); -- cgit v1.2.3 From 9970a9a27ffca8b45c4a242f90adeb979fcaafb0 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Fri, 6 Mar 2026 14:43:42 +0800 Subject: arm64: mm: implement the architecture-specific test_and_clear_young_ptes() Implement the Arm64 architecture-specific test_and_clear_young_ptes() to enable batched checking of young flags, improving performance during large folio reclamation when MGLRU is enabled. While we're at it, simplify ptep_test_and_clear_young() by calling test_and_clear_young_ptes(). Since callers guarantee that PTEs are present before calling these functions, we can use pte_cont() to check the CONT_PTE flag instead of pte_valid_cont(). Performance testing: Enable MGLRU, then allocate 10G clean file-backed folios by mmap() in a memory cgroup, and try to reclaim 8G file-backed folios via the memory.reclaim interface. I can observe 60%+ performance improvement on my Arm64 32-core server (and about 15% improvement on my X86 machine). W/o patchset: real 0m0.470s user 0m0.000s sys 0m0.470s W/ patchset: real 0m0.180s user 0m0.001s sys 0m0.179s Link: https://lkml.kernel.org/r/7f891d42a720cc2e57862f3b79e4f774404f313c.1772778858.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang Reviewed-by: Rik van Riel Reviewed-by: David Hildenbrand (Arm) Cc: Alistair Popple Cc: Axel Rasmussen Cc: Barry Song Cc: Catalin Marinas Cc: Dev Jain Cc: Jann Horn Cc: Johannes Weiner Cc: Liam Howlett Cc: Lorenzo Stoakes (Oracle) Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Mike Rapoport Cc: Qi Zheng Cc: Ryan Roberts Cc: Shakeel Butt Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Wei Xu Cc: Will Deacon Cc: Yuanchu Xie Signed-off-by: Andrew Morton --- arch/arm64/include/asm/pgtable.h | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) (limited to 'arch') diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index aa4b13da6371..ab451d20e4c5 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -1812,16 +1812,22 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, return __ptep_get_and_clear(mm, addr, ptep); } +#define test_and_clear_young_ptes test_and_clear_young_ptes +static inline int test_and_clear_young_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + unsigned int nr) +{ + if (likely(nr == 1 && !pte_cont(__ptep_get(ptep)))) + return __ptep_test_and_clear_young(vma, addr, ptep); + + return contpte_test_and_clear_young_ptes(vma, addr, ptep, nr); +} + #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { - pte_t orig_pte = __ptep_get(ptep); - - if (likely(!pte_valid_cont(orig_pte))) - return __ptep_test_and_clear_young(vma, addr, ptep); - - return contpte_test_and_clear_young_ptes(vma, addr, ptep, 1); + return test_and_clear_young_ptes(vma, addr, ptep, 1); } #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH -- cgit v1.2.3 From 92a9cf97a46b806e7f4e4780724203753093b5b1 Mon Sep 17 00:00:00 2001 From: Chengkaitao Date: Sun, 1 Feb 2026 14:35:31 +0800 Subject: sparc: use vmemmap_populate_hugepages for vmemmap_populate Change sparc's implementation of vmemmap_populate() using vmemmap_populate_hugepages() to streamline the code. Another benefit is that it allows us to eliminate the external declarations of vmemmap_p?d_populate functions and convert them to static functions. Since vmemmap_populate_hugepages may fallback to vmemmap_populate- _basepages, which differs from sparc's original implementation. During the v1 discussion with Mike Rapoport, sparc uses base pages in the kernel page tables, so it should be able to use them in vmemmap as well. Consequently, no additional special handling is required. 1. In the SPARC architecture, reimplement vmemmap_populate using vmemmap_populate_hugepages. 2. Allow the SPARC arch to fallback to vmemmap_populate_basepages(), when vmemmap_alloc_block returns NULL. Link: https://lkml.kernel.org/r/20260201063532.44807-2-pilgrimtao@gmail.com Signed-off-by: Chengkaitao Tested-by: Andreas Larsson Acked-by: Andreas Larsson Cc: David Hildenbrand Cc: David S. Miller Cc: Kevin Brodsky Cc: Liam Howlett Cc: Lorenzo Stoakes (Oracle) Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Mike Rapoport Cc: Qi Zheng Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Zi Yan Signed-off-by: Andrew Morton --- arch/sparc/mm/init_64.c | 47 ++++++++++++++++------------------------------- 1 file changed, 16 insertions(+), 31 deletions(-) (limited to 'arch') diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 3aa47f2b6c6e..367c269305e5 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -2562,8 +2562,8 @@ unsigned long _PAGE_CACHE __read_mostly; EXPORT_SYMBOL(_PAGE_CACHE); #ifdef CONFIG_SPARSEMEM_VMEMMAP -int __meminit vmemmap_populate(unsigned long vstart, unsigned long vend, - int node, struct vmem_altmap *altmap) +void __meminit vmemmap_set_pmd(pmd_t *pmd, void *p, int node, + unsigned long addr, unsigned long next) { unsigned long pte_base; @@ -2576,39 +2576,24 @@ int __meminit vmemmap_populate(unsigned long vstart, unsigned long vend, pte_base |= _PAGE_PMD_HUGE; - vstart = vstart & PMD_MASK; - vend = ALIGN(vend, PMD_SIZE); - for (; vstart < vend; vstart += PMD_SIZE) { - pgd_t *pgd = vmemmap_pgd_populate(vstart, node); - unsigned long pte; - p4d_t *p4d; - pud_t *pud; - pmd_t *pmd; - - if (!pgd) - return -ENOMEM; - - p4d = vmemmap_p4d_populate(pgd, vstart, node); - if (!p4d) - return -ENOMEM; - - pud = vmemmap_pud_populate(p4d, vstart, node); - if (!pud) - return -ENOMEM; + pmd_val(*pmd) = pte_base | __pa(p); +} - pmd = pmd_offset(pud, vstart); - pte = pmd_val(*pmd); - if (!(pte & _PAGE_VALID)) { - void *block = vmemmap_alloc_block(PMD_SIZE, node); +int __meminit vmemmap_check_pmd(pmd_t *pmdp, int node, + unsigned long addr, unsigned long next) +{ + int large = pmd_leaf(*pmdp); - if (!block) - return -ENOMEM; + if (large) + vmemmap_verify((pte_t *)pmdp, node, addr, next); - pmd_val(*pmd) = pte_base | __pa(block); - } - } + return large; +} - return 0; +int __meminit vmemmap_populate(unsigned long vstart, unsigned long vend, + int node, struct vmem_altmap *altmap) +{ + return vmemmap_populate_hugepages(vstart, vend, node, NULL); } #endif /* CONFIG_SPARSEMEM_VMEMMAP */ -- cgit v1.2.3 From 396042fb2b834a8fbcea9c850dbbd4ae7c7b75a9 Mon Sep 17 00:00:00 2001 From: "David Hildenbrand (Arm)" Date: Mon, 9 Mar 2026 16:19:01 +0100 Subject: KVM: PPC: remove hugetlb.h inclusion hugetlb.h is no longer required now that we moved vma_kernel_pagesize() to mm.h. Link: https://lkml.kernel.org/r/20260309151901.123947-5-david@kernel.org Signed-off-by: David Hildenbrand (Arm) Reviewed-by: Lorenzo Stoakes (Oracle) Acked-by: Mike Rapoport (Microsoft) Reviewed-by: Ritesh Harjani Cc: "Christophe Leroy (CS GROUP)" Cc: Dan Williams Cc: Jann Horn Cc: Liam Howlett Cc: Madhavan Srinivasan Cc: Michael Ellerman Cc: Michal Hocko Cc: Muchun Song Cc: Nicholas Piggin Cc: Oscar Salvador Cc: Paolo Bonzini Cc: Pedro Falcato Cc: Suren Baghdasaryan Signed-off-by: Andrew Morton --- arch/powerpc/kvm/book3s_hv.c | 1 - 1 file changed, 1 deletion(-) (limited to 'arch') diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 08e5816fdd61..61dbeea317f3 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -36,7 +36,6 @@ #include #include #include -#include #include #include #include -- cgit v1.2.3 From 078f80f909ba9fa3060e89dc634ff4b1defc43d3 Mon Sep 17 00:00:00 2001 From: "David Hildenbrand (Arm)" Date: Thu, 19 Mar 2026 09:19:40 +0100 Subject: mm: remove CONFIG_ARCH_ENABLE_MEMORY_HOTREMOVE Patch series "mm: remove CONFIG_ARCH_ENABLE_MEMORY_HOTREMOVE and cleanup CONFIG_MIGRATION". While working on memory hotplug code cleanups, I realized that CONFIG_ARCH_ENABLE_MEMORY_HOTREMOVE is not really required anymore. Changing that revealed some rather nasty looking CONFIG_MIGRATION handling. Let's clean that up by introducing a dedicated CONFIG_NUMA_MIGRATION option and reducing the dependencies that CONFIG_MIGRATION has. This patch (of 2): All architectures that select CONFIG_ARCH_ENABLE_MEMORY_HOTREMOVE also select CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG. So we can just remove CONFIG_ARCH_ENABLE_MEMORY_HOTREMOVE. For CONFIG_MIGRATION, make it depend on CONFIG_MEMORY_HOTREMOVE instead, and make CONFIG_MEMORY_HOTREMOVE select CONFIG_MIGRATION (just like CONFIG_CMA and CONFIG_COMPACTION already do). We'll clean up CONFIG_MIGRATION next. Link: https://lkml.kernel.org/r/20260319-config_migration-v1-0-42270124966f@kernel.org Link: https://lkml.kernel.org/r/20260319-config_migration-v1-1-42270124966f@kernel.org Signed-off-by: David Hildenbrand (Arm) Acked-by: Zi Yan Reviewed-by: Lorenzo Stoakes (Oracle) Reviewed-by: Joshua Hahn Reviewed-by: Gregory Price Reviewed-by: Mike Rapoport (Microsoft) Reviewed-by: Jonathan Cameron Cc: Albert Ou Cc: Alexander Gordeev Cc: Alexandre Ghiti Cc: Alistair Popple Cc: "Borislav Petkov (AMD)" Cc: Byungchul Park Cc: Catalin Marinas Cc: Christian Borntraeger Cc: Heiko Carstens Cc: "H. Peter Anvin" Cc: Huacai Chen Cc: "Huang, Ying" Cc: Ingo Molnar Cc: Liam Howlett Cc: Madhavan Srinivasan Cc: Matthew Brost Cc: Michael Ellerman Cc: Michal Hocko Cc: Nicholas Piggin Cc: Palmer Dabbelt Cc: Rakie Kim Cc: Sebastian Andrzej Siewior Cc: Steven Rostedt Cc: Suren Baghdasaryan Cc: Sven Schnelle Cc: Vasily Gorbik Cc: WANG Xuerui Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/arm64/Kconfig | 1 - arch/loongarch/Kconfig | 1 - arch/powerpc/Kconfig | 1 - arch/riscv/Kconfig | 1 - arch/s390/Kconfig | 1 - arch/x86/Kconfig | 1 - 6 files changed, 6 deletions(-) (limited to 'arch') diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 38dba5f7e4d2..bcd9f5bc66e2 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -16,7 +16,6 @@ config ARM64 select ARCH_BINFMT_ELF_STATE select ARCH_ENABLE_HUGEPAGE_MIGRATION if HUGETLB_PAGE && MIGRATION select ARCH_ENABLE_MEMORY_HOTPLUG - select ARCH_ENABLE_MEMORY_HOTREMOVE select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2 select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE select ARCH_HAS_CACHE_LINE_SIZE diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index 92068ff38685..ac714d14133a 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -12,7 +12,6 @@ config LOONGARCH select ARCH_NEEDS_DEFER_KASAN select ARCH_DISABLE_KASAN_INLINE select ARCH_ENABLE_MEMORY_HOTPLUG - select ARCH_ENABLE_MEMORY_HOTREMOVE select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI select ARCH_HAS_CPU_FINALIZE_INIT diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 10240cb80904..617758d7155b 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -126,7 +126,6 @@ config PPC select ARCH_DISABLE_KASAN_INLINE if PPC_RADIX_MMU select ARCH_DMA_DEFAULT_COHERENT if !NOT_COHERENT_CACHE select ARCH_ENABLE_MEMORY_HOTPLUG - select ARCH_ENABLE_MEMORY_HOTREMOVE select ARCH_HAS_COPY_MC if PPC64 select ARCH_HAS_CURRENT_STACK_POINTER select ARCH_HAS_DEBUG_VIRTUAL diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 90c531e6abf5..61a9d8d3ea64 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -21,7 +21,6 @@ config RISCV select ARCH_DMA_DEFAULT_COHERENT select ARCH_ENABLE_HUGEPAGE_MIGRATION if HUGETLB_PAGE && MIGRATION select ARCH_ENABLE_MEMORY_HOTPLUG if SPARSEMEM_VMEMMAP - select ARCH_ENABLE_MEMORY_HOTREMOVE if MEMORY_HOTPLUG select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2 select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE select ARCH_HAS_BINFMT_FLAT diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index edc927d9e85a..d01800962d84 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -85,7 +85,6 @@ config S390 select ARCH_32BIT_USTAT_F_TINODE select ARCH_CORRECT_STACKTRACE_ON_KRETPROBE select ARCH_ENABLE_MEMORY_HOTPLUG if SPARSEMEM - select ARCH_ENABLE_MEMORY_HOTREMOVE select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2 select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE select ARCH_HAS_CC_CAN_LINK diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index e2df1b147184..c290fe363f27 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -69,7 +69,6 @@ config X86 select ARCH_CORRECT_STACKTRACE_ON_KRETPROBE select ARCH_ENABLE_HUGEPAGE_MIGRATION if X86_64 && HUGETLB_PAGE && MIGRATION select ARCH_ENABLE_MEMORY_HOTPLUG if X86_64 - select ARCH_ENABLE_MEMORY_HOTREMOVE if MEMORY_HOTPLUG select ARCH_ENABLE_SPLIT_PMD_PTLOCK if (PGTABLE_LEVELS > 2) && (X86_64 || X86_PAE) select ARCH_ENABLE_THP_MIGRATION if X86_64 && TRANSPARENT_HUGEPAGE select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI -- cgit v1.2.3 From a62ca3f40feaaaf0dfc4db1f2edeca5a70f4123d Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Sat, 21 Mar 2026 14:42:49 +0800 Subject: mm: change to return bool for ptep_test_and_clear_young() Patch series "change young flag check functions to return bool", v2. This is a cleanup patchset to change all young flag check functions to return bool, as discussed with David in the previous thread[1]. Since callers only care about whether the young flag was set, returning bool makes the intention clearer. No functional changes intended. This patch (of 6): Callers use ptep_test_and_clear_young() to clear the young flag and check whether it was set. Change the return type to bool to make the intention clearer. Link: https://lkml.kernel.org/r/cover.1774075004.git.baolin.wang@linux.alibaba.com Link: https://lkml.kernel.org/r/57e70efa9703d43959aa645246ea3cbdba14fa17.1774075004.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang Reviewed-by: Ritesh Harjani (IBM) Reviewed-by: Lorenzo Stoakes (Oracle) Acked-by: David Hildenbrand (Arm) Cc: Liam Howlett Cc: Michal Hocko Cc: Mike Rapoport Cc: Suren Baghdasaryan Signed-off-by: Andrew Morton --- arch/arm64/include/asm/pgtable.h | 16 +++++++--------- arch/arm64/mm/contpte.c | 7 +++---- arch/microblaze/include/asm/pgtable.h | 2 +- arch/parisc/include/asm/pgtable.h | 7 ++++--- arch/powerpc/include/asm/book3s/32/pgtable.h | 4 ++-- arch/powerpc/include/asm/book3s/64/pgtable.h | 6 +++--- arch/powerpc/include/asm/nohash/pgtable.h | 4 ++-- arch/riscv/include/asm/pgtable.h | 4 ++-- arch/riscv/mm/pgtable.c | 7 +++---- arch/s390/include/asm/pgtable.h | 4 ++-- arch/x86/include/asm/pgtable.h | 4 ++-- arch/x86/mm/pgtable.c | 6 +++--- arch/xtensa/include/asm/pgtable.h | 9 ++++----- 13 files changed, 38 insertions(+), 42 deletions(-) (limited to 'arch') diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index ab451d20e4c5..79596cc05dcb 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -1282,9 +1282,8 @@ static inline void __pte_clear(struct mm_struct *mm, __set_pte(ptep, __pte(0)); } -static inline int __ptep_test_and_clear_young(struct vm_area_struct *vma, - unsigned long address, - pte_t *ptep) +static inline bool __ptep_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep) { pte_t old_pte, pte; @@ -1646,7 +1645,7 @@ extern void contpte_clear_full_ptes(struct mm_struct *mm, unsigned long addr, extern pte_t contpte_get_and_clear_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full); -int contpte_test_and_clear_young_ptes(struct vm_area_struct *vma, +bool contpte_test_and_clear_young_ptes(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, unsigned int nr); int contpte_clear_flush_young_ptes(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, unsigned int nr); @@ -1813,9 +1812,8 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, } #define test_and_clear_young_ptes test_and_clear_young_ptes -static inline int test_and_clear_young_ptes(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep, - unsigned int nr) +static inline bool test_and_clear_young_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, unsigned int nr) { if (likely(nr == 1 && !pte_cont(__ptep_get(ptep)))) return __ptep_test_and_clear_young(vma, addr, ptep); @@ -1824,8 +1822,8 @@ static inline int test_and_clear_young_ptes(struct vm_area_struct *vma, } #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG -static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) +static inline bool ptep_test_and_clear_young(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) { return test_and_clear_young_ptes(vma, addr, ptep, 1); } diff --git a/arch/arm64/mm/contpte.c b/arch/arm64/mm/contpte.c index 1519d090d5ea..a31cae78f712 100644 --- a/arch/arm64/mm/contpte.c +++ b/arch/arm64/mm/contpte.c @@ -508,9 +508,8 @@ pte_t contpte_get_and_clear_full_ptes(struct mm_struct *mm, } EXPORT_SYMBOL_GPL(contpte_get_and_clear_full_ptes); -int contpte_test_and_clear_young_ptes(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep, - unsigned int nr) +bool contpte_test_and_clear_young_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, unsigned int nr) { /* * ptep_clear_flush_young() technically requires us to clear the access @@ -525,7 +524,7 @@ int contpte_test_and_clear_young_ptes(struct vm_area_struct *vma, */ unsigned long end = addr + nr * PAGE_SIZE; - int young = 0; + bool young = false; ptep = contpte_align_addr_ptep(&addr, &end, ptep, nr); for (; addr != end; ptep++, addr += PAGE_SIZE) diff --git a/arch/microblaze/include/asm/pgtable.h b/arch/microblaze/include/asm/pgtable.h index ea72291de553..7678c040a2fd 100644 --- a/arch/microblaze/include/asm/pgtable.h +++ b/arch/microblaze/include/asm/pgtable.h @@ -318,7 +318,7 @@ static inline void set_pte(pte_t *ptep, pte_t pte) #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG struct vm_area_struct; -static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, +static inline bool ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { return (pte_update(ptep, _PAGE_ACCESSED, 0) & _PAGE_ACCESSED) != 0; diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index f6fb99cb94d9..7097c785f690 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -438,16 +438,17 @@ static inline pte_t ptep_get(pte_t *ptep) } #define ptep_get ptep_get -static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) +static inline bool ptep_test_and_clear_young(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) { pte_t pte; pte = ptep_get(ptep); if (!pte_young(pte)) { - return 0; + return false; } set_pte_at(vma->vm_mm, addr, ptep, pte_mkold(pte)); - return 1; + return true; } int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h index 001e28f9eabc..4a271318dee8 100644 --- a/arch/powerpc/include/asm/book3s/32/pgtable.h +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h @@ -295,8 +295,8 @@ static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, p * for our hash-based implementation, we fix that up here. */ #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG -static inline int __ptep_test_and_clear_young(struct mm_struct *mm, - unsigned long addr, pte_t *ptep) +static inline bool __ptep_test_and_clear_young(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) { unsigned long old; old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0, 0); diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 1a91762b455d..c049a2e26e25 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -349,13 +349,13 @@ static inline unsigned long pte_update(struct mm_struct *mm, unsigned long addr, * For radix: H_PAGE_HASHPTE should be zero. Hence we can use the same * function for both hash and radix. */ -static inline int __ptep_test_and_clear_young(struct mm_struct *mm, - unsigned long addr, pte_t *ptep) +static inline bool __ptep_test_and_clear_young(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) { unsigned long old; if ((pte_raw(*ptep) & cpu_to_be64(_PAGE_ACCESSED | H_PAGE_HASHPTE)) == 0) - return 0; + return false; old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0, 0); return (old & _PAGE_ACCESSED) != 0; } diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h index e6da5eaccff6..3a6f20a1c800 100644 --- a/arch/powerpc/include/asm/nohash/pgtable.h +++ b/arch/powerpc/include/asm/nohash/pgtable.h @@ -101,8 +101,8 @@ static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, p } #endif -static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) +static inline bool ptep_test_and_clear_young(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) { unsigned long old; diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index ab4ce1cc9d9c..643d12481b02 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -659,8 +659,8 @@ static inline void pte_clear(struct mm_struct *mm, extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t entry, int dirty); #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG /* defined in mm/pgtable.c */ -extern int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, - pte_t *ptep); +bool ptep_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep); #define __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, diff --git a/arch/riscv/mm/pgtable.c b/arch/riscv/mm/pgtable.c index b1ed2f14dc3a..9c4427d0b187 100644 --- a/arch/riscv/mm/pgtable.c +++ b/arch/riscv/mm/pgtable.c @@ -29,12 +29,11 @@ int ptep_set_access_flags(struct vm_area_struct *vma, return true; } -int ptep_test_and_clear_young(struct vm_area_struct *vma, - unsigned long address, - pte_t *ptep) +bool ptep_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep) { if (!pte_young(ptep_get(ptep))) - return 0; + return false; return test_and_clear_bit(_PAGE_ACCESSED_OFFSET, &pte_val(*ptep)); } EXPORT_SYMBOL_GPL(ptep_test_and_clear_young); diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 1c3c3be93be9..ef4748ee3a2b 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1164,8 +1164,8 @@ pte_t ptep_xchg_direct(struct mm_struct *, unsigned long, pte_t *, pte_t); pte_t ptep_xchg_lazy(struct mm_struct *, unsigned long, pte_t *, pte_t); #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG -static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) +static inline bool ptep_test_and_clear_young(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) { pte_t pte = *ptep; diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 54289f4587a4..1d86fb33239f 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -1232,8 +1232,8 @@ extern int ptep_set_access_flags(struct vm_area_struct *vma, pte_t entry, int dirty); #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG -extern int ptep_test_and_clear_young(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep); +bool ptep_test_and_clear_young(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep); #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH extern int ptep_clear_flush_young(struct vm_area_struct *vma, diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 2e5ecfdce73c..5ee38dda9124 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -443,10 +443,10 @@ int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address, } #endif -int ptep_test_and_clear_young(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) +bool ptep_test_and_clear_young(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) { - int ret = 0; + bool ret = false; if (pte_young(*ptep)) ret = test_and_clear_bit(_PAGE_BIT_ACCESSED, diff --git a/arch/xtensa/include/asm/pgtable.h b/arch/xtensa/include/asm/pgtable.h index 61f07d981a94..f00a879dc298 100644 --- a/arch/xtensa/include/asm/pgtable.h +++ b/arch/xtensa/include/asm/pgtable.h @@ -304,15 +304,14 @@ set_pmd(pmd_t *pmdp, pmd_t pmdval) struct vm_area_struct; -static inline int -ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, - pte_t *ptep) +static inline bool ptep_test_and_clear_young(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) { pte_t pte = *ptep; if (!pte_young(pte)) - return 0; + return false; update_pte(ptep, pte_mkold(pte)); - return 1; + return true; } static inline pte_t -- cgit v1.2.3 From 06c4dfa3ced61635895d0e258da8dc63da539f42 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Sat, 21 Mar 2026 14:42:50 +0800 Subject: mm: change to return bool for ptep_clear_flush_young()/clear_flush_young_ptes() The ptep_clear_flush_young() and clear_flush_young_ptes() are used to clear the young flag and flush the TLB, returning whether the young flag was set. Change the return type to bool to make the intention clearer. Link: https://lkml.kernel.org/r/24af5144b96103631594501f77d4525f2475c1be.1774075004.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang Reviewed-by: Ritesh Harjani (IBM) Reviewed-by: Lorenzo Stoakes (Oracle) Acked-by: David Hildenbrand (Arm) Cc: Liam Howlett Cc: Michal Hocko Cc: Mike Rapoport Cc: Suren Baghdasaryan Signed-off-by: Andrew Morton --- arch/arm64/include/asm/pgtable.h | 17 ++++++++--------- arch/arm64/mm/contpte.c | 7 +++---- arch/parisc/include/asm/pgtable.h | 2 +- arch/parisc/kernel/cache.c | 8 ++++---- arch/powerpc/include/asm/nohash/64/pgtable.h | 2 +- arch/riscv/include/asm/pgtable.h | 4 ++-- arch/s390/include/asm/pgtable.h | 4 ++-- arch/x86/include/asm/pgtable.h | 4 ++-- arch/x86/mm/pgtable.c | 4 ++-- 9 files changed, 25 insertions(+), 27 deletions(-) (limited to 'arch') diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 79596cc05dcb..1009f719b157 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -1298,10 +1298,10 @@ static inline bool __ptep_test_and_clear_young(struct vm_area_struct *vma, return pte_young(pte); } -static inline int __ptep_clear_flush_young(struct vm_area_struct *vma, - unsigned long address, pte_t *ptep) +static inline bool __ptep_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep) { - int young = __ptep_test_and_clear_young(vma, address, ptep); + bool young = __ptep_test_and_clear_young(vma, address, ptep); if (young) { /* @@ -1647,7 +1647,7 @@ extern pte_t contpte_get_and_clear_full_ptes(struct mm_struct *mm, unsigned int nr, int full); bool contpte_test_and_clear_young_ptes(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, unsigned int nr); -int contpte_clear_flush_young_ptes(struct vm_area_struct *vma, +bool contpte_clear_flush_young_ptes(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, unsigned int nr); extern void contpte_wrprotect_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr); @@ -1829,8 +1829,8 @@ static inline bool ptep_test_and_clear_young(struct vm_area_struct *vma, } #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH -static inline int ptep_clear_flush_young(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) +static inline bool ptep_clear_flush_young(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) { pte_t orig_pte = __ptep_get(ptep); @@ -1841,9 +1841,8 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma, } #define clear_flush_young_ptes clear_flush_young_ptes -static inline int clear_flush_young_ptes(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep, - unsigned int nr) +static inline bool clear_flush_young_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, unsigned int nr) { if (likely(nr == 1 && !pte_cont(__ptep_get(ptep)))) return __ptep_clear_flush_young(vma, addr, ptep); diff --git a/arch/arm64/mm/contpte.c b/arch/arm64/mm/contpte.c index a31cae78f712..2dc1b8ad71e8 100644 --- a/arch/arm64/mm/contpte.c +++ b/arch/arm64/mm/contpte.c @@ -534,11 +534,10 @@ bool contpte_test_and_clear_young_ptes(struct vm_area_struct *vma, } EXPORT_SYMBOL_GPL(contpte_test_and_clear_young_ptes); -int contpte_clear_flush_young_ptes(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep, - unsigned int nr) +bool contpte_clear_flush_young_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, unsigned int nr) { - int young; + bool young; young = contpte_test_and_clear_young_ptes(vma, addr, ptep, nr); diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index 7097c785f690..467b8547ac8b 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -451,7 +451,7 @@ static inline bool ptep_test_and_clear_young(struct vm_area_struct *vma, return true; } -int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); +bool ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); struct mm_struct; diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index b189265785dc..0170b69a21d3 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -781,18 +781,18 @@ void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned lon __flush_cache_page(vma, vmaddr, PFN_PHYS(page_to_pfn(page))); } -int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long addr, - pte_t *ptep) +bool ptep_clear_flush_young(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) { pte_t pte = ptep_get(ptep); if (!pte_young(pte)) - return 0; + return false; set_pte(ptep, pte_mkold(pte)); #if CONFIG_FLUSH_PAGE_ACCESSED __flush_cache_page(vma, addr, PFN_PHYS(pte_pfn(pte))); #endif - return 1; + return true; } /* diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h index 2deb955b7bc8..661eb3820d12 100644 --- a/arch/powerpc/include/asm/nohash/64/pgtable.h +++ b/arch/powerpc/include/asm/nohash/64/pgtable.h @@ -155,7 +155,7 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH #define ptep_clear_flush_young(__vma, __address, __ptep) \ ({ \ - int __young = ptep_test_and_clear_young(__vma, __address, __ptep);\ + bool __young = ptep_test_and_clear_young(__vma, __address, __ptep);\ __young; \ }) diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 643d12481b02..b9dacfc280b1 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -695,8 +695,8 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, } #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH -static inline int ptep_clear_flush_young(struct vm_area_struct *vma, - unsigned long address, pte_t *ptep) +static inline bool ptep_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep) { /* * This comment is borrowed from x86, but applies equally to RISC-V: diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index ef4748ee3a2b..ac74b5076d8f 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1174,8 +1174,8 @@ static inline bool ptep_test_and_clear_young(struct vm_area_struct *vma, } #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH -static inline int ptep_clear_flush_young(struct vm_area_struct *vma, - unsigned long address, pte_t *ptep) +static inline bool ptep_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep) { return ptep_test_and_clear_young(vma, address, ptep); } diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 1d86fb33239f..3993657e0a35 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -1236,8 +1236,8 @@ bool ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH -extern int ptep_clear_flush_young(struct vm_area_struct *vma, - unsigned long address, pte_t *ptep); +bool ptep_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep); #define __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 5ee38dda9124..1348384a3bb9 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -483,8 +483,8 @@ int pudp_test_and_clear_young(struct vm_area_struct *vma, } #endif -int ptep_clear_flush_young(struct vm_area_struct *vma, - unsigned long address, pte_t *ptep) +bool ptep_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep) { /* * On x86 CPUs, clearing the accessed bit without a TLB flush -- cgit v1.2.3 From 42e26354c4ef28772398b1d71b7477834037305c Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Sat, 21 Mar 2026 14:42:51 +0800 Subject: mm: change to return bool for pmdp_test_and_clear_young() Callers use pmdp_test_and_clear_young() to clear the young flag and check whether it was set for this PMD entry. Change the return type to bool to make the intention clearer. Link: https://lkml.kernel.org/r/f1d31307a13365d3d0fed5809727dcc2dd59631b.1774075004.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang Reviewed-by: Ritesh Harjani (IBM) Reviewed-by: Lorenzo Stoakes (Oracle) Acked-by: David Hildenbrand (Arm) Cc: Liam Howlett Cc: Michal Hocko Cc: Mike Rapoport Cc: Suren Baghdasaryan Signed-off-by: Andrew Morton --- arch/arm64/include/asm/pgtable.h | 5 ++--- arch/powerpc/include/asm/book3s/64/pgtable.h | 10 +++++----- arch/powerpc/mm/book3s64/pgtable.c | 4 ++-- arch/riscv/include/asm/pgtable.h | 4 ++-- arch/s390/include/asm/pgtable.h | 4 ++-- arch/x86/include/asm/pgtable.h | 4 ++-- arch/x86/mm/pgtable.c | 6 +++--- 7 files changed, 18 insertions(+), 19 deletions(-) (limited to 'arch') diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 1009f719b157..52bafe79c10a 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -1320,9 +1320,8 @@ static inline bool __ptep_clear_flush_young(struct vm_area_struct *vma, #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) #define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG -static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, - unsigned long address, - pmd_t *pmdp) +static inline bool pmdp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp) { /* Operation applies to PMD table entry only if FEAT_HAFT is enabled */ VM_WARN_ON(pmd_table(READ_ONCE(*pmdp)) && !system_supports_haft()); diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index c049a2e26e25..8b354e81ab22 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -1161,13 +1161,13 @@ pud_hugepage_update(struct mm_struct *mm, unsigned long addr, pud_t *pudp, * For radix we should always find H_PAGE_HASHPTE zero. Hence * the below will work for radix too */ -static inline int __pmdp_test_and_clear_young(struct mm_struct *mm, - unsigned long addr, pmd_t *pmdp) +static inline bool __pmdp_test_and_clear_young(struct mm_struct *mm, + unsigned long addr, pmd_t *pmdp) { unsigned long old; if ((pmd_raw(*pmdp) & cpu_to_be64(_PAGE_ACCESSED | H_PAGE_HASHPTE)) == 0) - return 0; + return false; old = pmd_hugepage_update(mm, addr, pmdp, _PAGE_ACCESSED, 0); return ((old & _PAGE_ACCESSED) != 0); } @@ -1300,8 +1300,8 @@ extern int pudp_set_access_flags(struct vm_area_struct *vma, pud_t entry, int dirty); #define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG -extern int pmdp_test_and_clear_young(struct vm_area_struct *vma, - unsigned long address, pmd_t *pmdp); +bool pmdp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp); #define __HAVE_ARCH_PUDP_TEST_AND_CLEAR_YOUNG extern int pudp_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pud_t *pudp); diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c index 4b09c04654a8..c584321e3d41 100644 --- a/arch/powerpc/mm/book3s64/pgtable.c +++ b/arch/powerpc/mm/book3s64/pgtable.c @@ -98,8 +98,8 @@ int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address, } -int pmdp_test_and_clear_young(struct vm_area_struct *vma, - unsigned long address, pmd_t *pmdp) +bool pmdp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp) { return __pmdp_test_and_clear_young(vma->vm_mm, address, pmdp); } diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index b9dacfc280b1..67e7746e3fbe 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -1015,8 +1015,8 @@ static inline int pmdp_set_access_flags(struct vm_area_struct *vma, } #define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG -static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, - unsigned long address, pmd_t *pmdp) +static inline bool pmdp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp) { return ptep_test_and_clear_young(vma, address, (pte_t *)pmdp); } diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index ac74b5076d8f..87a5082da28e 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1683,8 +1683,8 @@ static inline int pmdp_set_access_flags(struct vm_area_struct *vma, } #define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG -static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, - unsigned long addr, pmd_t *pmdp) +static inline bool pmdp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long addr, pmd_t *pmdp) { pmd_t pmd = *pmdp; diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 3993657e0a35..ba867bac6096 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -1295,8 +1295,8 @@ extern int pudp_set_access_flags(struct vm_area_struct *vma, pud_t entry, int dirty); #define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG -extern int pmdp_test_and_clear_young(struct vm_area_struct *vma, - unsigned long addr, pmd_t *pmdp); +bool pmdp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long addr, pmd_t *pmdp); extern int pudp_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pud_t *pudp); diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 1348384a3bb9..b09e8c5dadf9 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -456,10 +456,10 @@ bool ptep_test_and_clear_young(struct vm_area_struct *vma, } #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) -int pmdp_test_and_clear_young(struct vm_area_struct *vma, - unsigned long addr, pmd_t *pmdp) +bool pmdp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long addr, pmd_t *pmdp) { - int ret = 0; + bool ret = false; if (pmd_young(*pmdp)) ret = test_and_clear_bit(_PAGE_BIT_ACCESSED, -- cgit v1.2.3 From 2d46a397472191a10b0df294d64da542bfd1de57 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Sat, 21 Mar 2026 14:42:52 +0800 Subject: mm: change to return bool for pmdp_clear_flush_young() The pmdp_clear_flush_young() is used to clear the young flag and flush the TLB, returning whether the young flag was set for this PMD entry. Change the return type to bool to make the intention clearer. Link: https://lkml.kernel.org/r/a668b9a974c0d675e7a41f6973bcbe3336e8b373.1774075004.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang Reviewed-by: Lorenzo Stoakes (Oracle) Acked-by: David Hildenbrand (Arm) Cc: Liam Howlett Cc: Michal Hocko Cc: Mike Rapoport Cc: Ritesh Harjani (IBM) Cc: Suren Baghdasaryan Signed-off-by: Andrew Morton --- arch/s390/include/asm/pgtable.h | 4 ++-- arch/x86/include/asm/pgtable.h | 4 ++-- arch/x86/mm/pgtable.c | 6 +++--- 3 files changed, 7 insertions(+), 7 deletions(-) (limited to 'arch') diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 87a5082da28e..40a6fb19dd1d 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1693,8 +1693,8 @@ static inline bool pmdp_test_and_clear_young(struct vm_area_struct *vma, } #define __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH -static inline int pmdp_clear_flush_young(struct vm_area_struct *vma, - unsigned long addr, pmd_t *pmdp) +static inline bool pmdp_clear_flush_young(struct vm_area_struct *vma, + unsigned long addr, pmd_t *pmdp) { VM_BUG_ON(addr & ~HPAGE_MASK); return pmdp_test_and_clear_young(vma, addr, pmdp); diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index ba867bac6096..6c8f2b17d3f9 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -1301,8 +1301,8 @@ extern int pudp_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pud_t *pudp); #define __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH -extern int pmdp_clear_flush_young(struct vm_area_struct *vma, - unsigned long address, pmd_t *pmdp); +bool pmdp_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp); #define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index b09e8c5dadf9..fc1c996c5b2d 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -503,10 +503,10 @@ bool ptep_clear_flush_young(struct vm_area_struct *vma, } #ifdef CONFIG_TRANSPARENT_HUGEPAGE -int pmdp_clear_flush_young(struct vm_area_struct *vma, - unsigned long address, pmd_t *pmdp) +bool pmdp_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp) { - int young; + bool young; VM_BUG_ON(address & ~HPAGE_PMD_MASK); -- cgit v1.2.3 From fb87c88272973fa310d36dc60530fd6781bd1a55 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Sat, 21 Mar 2026 14:42:53 +0800 Subject: mm: change to return bool for pudp_test_and_clear_young() The pudp_test_and_clear_young() is used to clear the young flag, returning whether the young flag was set for this PUD entry. Change the return type to bool to make the intention clearer. Link: https://lkml.kernel.org/r/2c56fe52c1bf9404145274d7e91d4a65060f6c7c.1774075004.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang Reviewed-by: Ritesh Harjani (IBM) Reviewed-by: Lorenzo Stoakes (Oracle) Acked-by: David Hildenbrand (Arm) Cc: Liam Howlett Cc: Michal Hocko Cc: Mike Rapoport Cc: Suren Baghdasaryan Signed-off-by: Andrew Morton --- arch/powerpc/include/asm/book3s/64/pgtable.h | 10 +++++----- arch/powerpc/mm/book3s64/pgtable.c | 4 ++-- arch/riscv/include/asm/pgtable.h | 4 ++-- arch/x86/include/asm/pgtable.h | 4 ++-- arch/x86/mm/pgtable.c | 6 +++--- 5 files changed, 14 insertions(+), 14 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 8b354e81ab22..60e283cf22be 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -1172,13 +1172,13 @@ static inline bool __pmdp_test_and_clear_young(struct mm_struct *mm, return ((old & _PAGE_ACCESSED) != 0); } -static inline int __pudp_test_and_clear_young(struct mm_struct *mm, - unsigned long addr, pud_t *pudp) +static inline bool __pudp_test_and_clear_young(struct mm_struct *mm, + unsigned long addr, pud_t *pudp) { unsigned long old; if ((pud_raw(*pudp) & cpu_to_be64(_PAGE_ACCESSED | H_PAGE_HASHPTE)) == 0) - return 0; + return false; old = pud_hugepage_update(mm, addr, pudp, _PAGE_ACCESSED, 0); return ((old & _PAGE_ACCESSED) != 0); } @@ -1303,8 +1303,8 @@ extern int pudp_set_access_flags(struct vm_area_struct *vma, bool pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); #define __HAVE_ARCH_PUDP_TEST_AND_CLEAR_YOUNG -extern int pudp_test_and_clear_young(struct vm_area_struct *vma, - unsigned long address, pud_t *pudp); +bool pudp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, pud_t *pudp); #define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c index c584321e3d41..ddc766e95855 100644 --- a/arch/powerpc/mm/book3s64/pgtable.c +++ b/arch/powerpc/mm/book3s64/pgtable.c @@ -104,8 +104,8 @@ bool pmdp_test_and_clear_young(struct vm_area_struct *vma, return __pmdp_test_and_clear_young(vma->vm_mm, address, pmdp); } -int pudp_test_and_clear_young(struct vm_area_struct *vma, - unsigned long address, pud_t *pudp) +bool pudp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, pud_t *pudp) { return __pudp_test_and_clear_young(vma->vm_mm, address, pudp); } diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 67e7746e3fbe..a6e0eaba2653 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -1109,8 +1109,8 @@ static inline int pudp_set_access_flags(struct vm_area_struct *vma, return ptep_set_access_flags(vma, address, (pte_t *)pudp, pud_pte(entry), dirty); } -static inline int pudp_test_and_clear_young(struct vm_area_struct *vma, - unsigned long address, pud_t *pudp) +static inline bool pudp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, pud_t *pudp) { return ptep_test_and_clear_young(vma, address, (pte_t *)pudp); } diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 6c8f2b17d3f9..13e3e9a054cb 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -1297,8 +1297,8 @@ extern int pudp_set_access_flags(struct vm_area_struct *vma, #define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG bool pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp); -extern int pudp_test_and_clear_young(struct vm_area_struct *vma, - unsigned long addr, pud_t *pudp); +bool pudp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long addr, pud_t *pudp); #define __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH bool pmdp_clear_flush_young(struct vm_area_struct *vma, diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index fc1c996c5b2d..da7f0a03cf90 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -470,10 +470,10 @@ bool pmdp_test_and_clear_young(struct vm_area_struct *vma, #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE -int pudp_test_and_clear_young(struct vm_area_struct *vma, - unsigned long addr, pud_t *pudp) +bool pudp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long addr, pud_t *pudp) { - int ret = 0; + bool ret = false; if (pud_young(*pudp)) ret = test_and_clear_bit(_PAGE_BIT_ACCESSED, -- cgit v1.2.3 From 3a6455d56bd7c4cfb1ea35ddae052943065e338e Mon Sep 17 00:00:00 2001 From: "Lorenzo Stoakes (Oracle)" Date: Fri, 20 Mar 2026 19:38:34 +0000 Subject: mm: convert do_brk_flags() to use vma_flags_t In order to be able to do this, we need to change VM_DATA_DEFAULT_FLAGS and friends and update the architecture-specific definitions also. We then have to update some KSM logic to handle VMA flags, and introduce VMA_STACK_FLAGS to define the vma_flags_t equivalent of VM_STACK_FLAGS. We also introduce two helper functions for use during the time we are converting legacy flags to vma_flags_t values - vma_flags_to_legacy() and legacy_to_vma_flags(). This enables us to iteratively make changes to break these changes up into separate parts. We use these explicitly here to keep VM_STACK_FLAGS around for certain users which need to maintain the legacy vm_flags_t values for the time being. We are no longer able to rely on the simple VM_xxx being set to zero if the feature is not enabled, so in the case of VM_DROPPABLE we introduce VMA_DROPPABLE as the vma_flags_t equivalent, which is set to EMPTY_VMA_FLAGS if the droppable flag is not available. While we're here, we make the description of do_brk_flags() into a kdoc comment, as it almost was already. We use vma_flags_to_legacy() to not need to update the vm_get_page_prot() logic as this time. Note that in create_init_stack_vma() we have to replace the BUILD_BUG_ON() with a VM_WARN_ON_ONCE() as the tested values are no longer build time available. We also update mprotect_fixup() to use VMA flags where possible, though we have to live with a little duplication between vm_flags_t and vma_flags_t values for the time being until further conversions are made. While we're here, update VM_SPECIAL to be defined in terms of VMA_SPECIAL_FLAGS now we have vma_flags_to_legacy(). Finally, we update the VMA tests to reflect these changes. Link: https://lkml.kernel.org/r/d02e3e45d9a33d7904b149f5604904089fd640ae.1774034900.git.ljs@kernel.org Signed-off-by: Lorenzo Stoakes (Oracle) Acked-by: Paul Moore [SELinux] Acked-by: Vlastimil Babka (SUSE) Cc: Albert Ou Cc: Alexander Gordeev Cc: Alexandre Ghiti Cc: Al Viro Cc: Anton Ivanov Cc: "Borislav Petkov (AMD)" Cc: Catalin Marinas Cc: Chengming Zhou Cc: Christian Borntraeger Cc: Christian Brauner Cc: David Hildenbrand Cc: Dinh Nguyen Cc: Heiko Carstens Cc: "H. Peter Anvin" Cc: Huacai Chen Cc: Ingo Molnar Cc: Jan Kara Cc: Jann Horn Cc: Johannes Berg Cc: Kees Cook Cc: Liam Howlett Cc: Madhavan Srinivasan Cc: Michael Ellerman Cc: Michal Hocko Cc: Mike Rapoport Cc: Nicholas Piggin Cc: Ondrej Mosnacek Cc: Palmer Dabbelt Cc: Pedro Falcato Cc: Richard Weinberger Cc: Russell King Cc: Stephen Smalley Cc: Suren Baghdasaryan Cc: Sven Schnelle Cc: Thomas Bogendoerfer Cc: Vasily Gorbik Cc: Vineet Gupta Cc: WANG Xuerui Cc: Will Deacon Cc: xu xin Signed-off-by: Andrew Morton --- arch/arc/include/asm/page.h | 2 +- arch/arm/include/asm/page.h | 2 +- arch/arm64/include/asm/page.h | 7 ++++++- arch/hexagon/include/asm/page.h | 2 +- arch/loongarch/include/asm/page.h | 2 +- arch/mips/include/asm/page.h | 2 +- arch/nios2/include/asm/page.h | 2 +- arch/powerpc/include/asm/page.h | 4 ++-- arch/powerpc/include/asm/page_32.h | 2 +- arch/powerpc/include/asm/page_64.h | 12 ++++++------ arch/riscv/include/asm/page.h | 2 +- arch/s390/include/asm/page.h | 2 +- arch/x86/include/asm/page_types.h | 2 +- arch/x86/um/asm/vm-flags.h | 4 ++-- 14 files changed, 26 insertions(+), 21 deletions(-) (limited to 'arch') diff --git a/arch/arc/include/asm/page.h b/arch/arc/include/asm/page.h index 38214e126c6d..facc7a03b250 100644 --- a/arch/arc/include/asm/page.h +++ b/arch/arc/include/asm/page.h @@ -131,7 +131,7 @@ static inline unsigned long virt_to_pfn(const void *kaddr) #define virt_addr_valid(kaddr) pfn_valid(virt_to_pfn(kaddr)) /* Default Permissions for stack/heaps pages (Non Executable) */ -#define VM_DATA_DEFAULT_FLAGS VM_DATA_FLAGS_NON_EXEC +#define VMA_DATA_DEFAULT_FLAGS VMA_DATA_FLAGS_NON_EXEC #define WANT_PAGE_VIRTUAL 1 diff --git a/arch/arm/include/asm/page.h b/arch/arm/include/asm/page.h index ef11b721230e..fa4c1225dde5 100644 --- a/arch/arm/include/asm/page.h +++ b/arch/arm/include/asm/page.h @@ -184,7 +184,7 @@ extern int pfn_valid(unsigned long); #include -#define VM_DATA_DEFAULT_FLAGS VM_DATA_FLAGS_TSK_EXEC +#define VMA_DATA_DEFAULT_FLAGS VMA_DATA_FLAGS_TSK_EXEC #include #include diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h index b39cc1127e1f..e25d0d18f6d7 100644 --- a/arch/arm64/include/asm/page.h +++ b/arch/arm64/include/asm/page.h @@ -46,7 +46,12 @@ int pfn_is_map_memory(unsigned long pfn); #endif /* !__ASSEMBLER__ */ -#define VM_DATA_DEFAULT_FLAGS (VM_DATA_FLAGS_TSK_EXEC | VM_MTE_ALLOWED) +#ifdef CONFIG_ARM64_MTE +#define VMA_DATA_DEFAULT_FLAGS append_vma_flags(VMA_DATA_FLAGS_TSK_EXEC, \ + VMA_MTE_ALLOWED_BIT) +#else +#define VMA_DATA_DEFAULT_FLAGS VMA_DATA_FLAGS_TSK_EXEC +#endif #include diff --git a/arch/hexagon/include/asm/page.h b/arch/hexagon/include/asm/page.h index f0aed3ed812b..6d82572a7f21 100644 --- a/arch/hexagon/include/asm/page.h +++ b/arch/hexagon/include/asm/page.h @@ -90,7 +90,7 @@ struct page; #define virt_to_page(kaddr) pfn_to_page(PFN_DOWN(__pa(kaddr))) /* Default vm area behavior is non-executable. */ -#define VM_DATA_DEFAULT_FLAGS VM_DATA_FLAGS_NON_EXEC +#define VMA_DATA_DEFAULT_FLAGS VMA_DATA_FLAGS_NON_EXEC #define virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT) diff --git a/arch/loongarch/include/asm/page.h b/arch/loongarch/include/asm/page.h index 327bf0bc92bf..79235f4fc399 100644 --- a/arch/loongarch/include/asm/page.h +++ b/arch/loongarch/include/asm/page.h @@ -104,7 +104,7 @@ struct page *tlb_virt_to_page(unsigned long kaddr); extern int __virt_addr_valid(volatile void *kaddr); #define virt_addr_valid(kaddr) __virt_addr_valid((volatile void *)(kaddr)) -#define VM_DATA_DEFAULT_FLAGS VM_DATA_FLAGS_TSK_EXEC +#define VMA_DATA_DEFAULT_FLAGS VMA_DATA_FLAGS_TSK_EXEC #include #include diff --git a/arch/mips/include/asm/page.h b/arch/mips/include/asm/page.h index 5ec428fcc887..50a382a0d8f6 100644 --- a/arch/mips/include/asm/page.h +++ b/arch/mips/include/asm/page.h @@ -213,7 +213,7 @@ extern bool __virt_addr_valid(const volatile void *kaddr); #define virt_addr_valid(kaddr) \ __virt_addr_valid((const volatile void *) (kaddr)) -#define VM_DATA_DEFAULT_FLAGS VM_DATA_FLAGS_TSK_EXEC +#define VMA_DATA_DEFAULT_FLAGS VMA_DATA_FLAGS_TSK_EXEC extern unsigned long __kaslr_offset; static inline unsigned long kaslr_offset(void) diff --git a/arch/nios2/include/asm/page.h b/arch/nios2/include/asm/page.h index 722956ac0bf8..71eb7c1b67d4 100644 --- a/arch/nios2/include/asm/page.h +++ b/arch/nios2/include/asm/page.h @@ -85,7 +85,7 @@ extern struct page *mem_map; # define virt_to_page(vaddr) pfn_to_page(PFN_DOWN(virt_to_phys(vaddr))) # define virt_addr_valid(vaddr) pfn_valid(PFN_DOWN(virt_to_phys(vaddr))) -# define VM_DATA_DEFAULT_FLAGS VM_DATA_FLAGS_NON_EXEC +# define VMA_DATA_DEFAULT_FLAGS VMA_DATA_FLAGS_NON_EXEC #include diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index f2bb1f98eebe..281f25e071a3 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -240,8 +240,8 @@ static inline const void *pfn_to_kaddr(unsigned long pfn) * and needs to be executable. This means the whole heap ends * up being executable. */ -#define VM_DATA_DEFAULT_FLAGS32 VM_DATA_FLAGS_TSK_EXEC -#define VM_DATA_DEFAULT_FLAGS64 VM_DATA_FLAGS_NON_EXEC +#define VMA_DATA_DEFAULT_FLAGS32 VMA_DATA_FLAGS_TSK_EXEC +#define VMA_DATA_DEFAULT_FLAGS64 VMA_DATA_FLAGS_NON_EXEC #ifdef __powerpc64__ #include diff --git a/arch/powerpc/include/asm/page_32.h b/arch/powerpc/include/asm/page_32.h index 25482405a811..1fd8c21f0a42 100644 --- a/arch/powerpc/include/asm/page_32.h +++ b/arch/powerpc/include/asm/page_32.h @@ -10,7 +10,7 @@ #endif #endif -#define VM_DATA_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS32 +#define VMA_DATA_DEFAULT_FLAGS VMA_DATA_DEFAULT_FLAGS32 #if defined(CONFIG_PPC_256K_PAGES) || \ (defined(CONFIG_PPC_8xx) && defined(CONFIG_PPC_16K_PAGES)) diff --git a/arch/powerpc/include/asm/page_64.h b/arch/powerpc/include/asm/page_64.h index 0f564a06bf68..d96c984d023b 100644 --- a/arch/powerpc/include/asm/page_64.h +++ b/arch/powerpc/include/asm/page_64.h @@ -84,9 +84,9 @@ extern u64 ppc64_pft_size; #endif /* __ASSEMBLER__ */ -#define VM_DATA_DEFAULT_FLAGS \ +#define VMA_DATA_DEFAULT_FLAGS \ (is_32bit_task() ? \ - VM_DATA_DEFAULT_FLAGS32 : VM_DATA_DEFAULT_FLAGS64) + VMA_DATA_DEFAULT_FLAGS32 : VMA_DATA_DEFAULT_FLAGS64) /* * This is the default if a program doesn't have a PT_GNU_STACK @@ -94,12 +94,12 @@ extern u64 ppc64_pft_size; * stack by default, so in the absence of a PT_GNU_STACK program header * we turn execute permission off. */ -#define VM_STACK_DEFAULT_FLAGS32 VM_DATA_FLAGS_EXEC -#define VM_STACK_DEFAULT_FLAGS64 VM_DATA_FLAGS_NON_EXEC +#define VMA_STACK_DEFAULT_FLAGS32 VMA_DATA_FLAGS_EXEC +#define VMA_STACK_DEFAULT_FLAGS64 VMA_DATA_FLAGS_NON_EXEC -#define VM_STACK_DEFAULT_FLAGS \ +#define VMA_STACK_DEFAULT_FLAGS \ (is_32bit_task() ? \ - VM_STACK_DEFAULT_FLAGS32 : VM_STACK_DEFAULT_FLAGS64) + VMA_STACK_DEFAULT_FLAGS32 : VMA_STACK_DEFAULT_FLAGS64) #include diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h index 187aad0a7b03..c78017061b17 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -204,7 +204,7 @@ static __always_inline void *pfn_to_kaddr(unsigned long pfn) (unsigned long)(_addr) >= PAGE_OFFSET && pfn_valid(virt_to_pfn(_addr)); \ }) -#define VM_DATA_DEFAULT_FLAGS VM_DATA_FLAGS_NON_EXEC +#define VMA_DATA_DEFAULT_FLAGS VMA_DATA_FLAGS_NON_EXEC #include #include diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h index f339258135f7..56da819a79e6 100644 --- a/arch/s390/include/asm/page.h +++ b/arch/s390/include/asm/page.h @@ -277,7 +277,7 @@ static inline unsigned long virt_to_pfn(const void *kaddr) #define virt_addr_valid(kaddr) pfn_valid(phys_to_pfn(__pa_nodebug((unsigned long)(kaddr)))) -#define VM_DATA_DEFAULT_FLAGS VM_DATA_FLAGS_NON_EXEC +#define VMA_DATA_DEFAULT_FLAGS VMA_DATA_FLAGS_NON_EXEC #endif /* !__ASSEMBLER__ */ diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h index 018a8d906ca3..3e0801a0f782 100644 --- a/arch/x86/include/asm/page_types.h +++ b/arch/x86/include/asm/page_types.h @@ -26,7 +26,7 @@ #define PAGE_OFFSET ((unsigned long)__PAGE_OFFSET) -#define VM_DATA_DEFAULT_FLAGS VM_DATA_FLAGS_TSK_EXEC +#define VMA_DATA_DEFAULT_FLAGS VMA_DATA_FLAGS_TSK_EXEC /* Physical address where kernel should be loaded. */ #define LOAD_PHYSICAL_ADDR __ALIGN_KERNEL_MASK(CONFIG_PHYSICAL_START, CONFIG_PHYSICAL_ALIGN - 1) diff --git a/arch/x86/um/asm/vm-flags.h b/arch/x86/um/asm/vm-flags.h index df7a3896f5dd..622d36d6ddff 100644 --- a/arch/x86/um/asm/vm-flags.h +++ b/arch/x86/um/asm/vm-flags.h @@ -9,11 +9,11 @@ #ifdef CONFIG_X86_32 -#define VM_DATA_DEFAULT_FLAGS VM_DATA_FLAGS_TSK_EXEC +#define VMA_DATA_DEFAULT_FLAGS VMA_DATA_FLAGS_TSK_EXEC #else -#define VM_STACK_DEFAULT_FLAGS (VM_GROWSDOWN | VM_DATA_FLAGS_EXEC) +#define VMA_STACK_DEFAULT_FLAGS append_vma_flags(VMA_DATA_FLAGS_EXEC, VMA_GROWSDOWN_BIT) #endif #endif -- cgit v1.2.3