diff options
Diffstat (limited to 'arch')
103 files changed, 436 insertions, 543 deletions
diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index 5db88b627439..e5f881bc8288 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -1218,14 +1218,11 @@ static unsigned long arch_get_unmapped_area_1(unsigned long addr, unsigned long len, unsigned long limit) { - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; - info.flags = 0; info.length = len; info.low_limit = addr; info.high_limit = limit; - info.align_mask = 0; - info.align_offset = 0; return vm_unmapped_area(&info); } diff --git a/arch/alpha/kernel/pci_iommu.c b/arch/alpha/kernel/pci_iommu.c index c81183935e97..7fcf3e9b7103 100644 --- a/arch/alpha/kernel/pci_iommu.c +++ b/arch/alpha/kernel/pci_iommu.c @@ -929,7 +929,7 @@ const struct dma_map_ops alpha_pci_ops = { .dma_supported = alpha_pci_supported, .mmap = dma_common_mmap, .get_sgtable = dma_common_get_sgtable, - .alloc_pages = dma_common_alloc_pages, + .alloc_pages_op = dma_common_alloc_pages, .free_pages = dma_common_free_pages, }; EXPORT_SYMBOL(alpha_pci_ops); diff --git a/arch/alpha/lib/checksum.c b/arch/alpha/lib/checksum.c index 17fa230baeef..27b2a9edf3cc 100644 --- a/arch/alpha/lib/checksum.c +++ b/arch/alpha/lib/checksum.c @@ -15,6 +15,7 @@ #include <net/checksum.h> #include <asm/byteorder.h> +#include <asm/checksum.h> static inline unsigned short from64to16(unsigned long x) { diff --git a/arch/alpha/lib/fpreg.c b/arch/alpha/lib/fpreg.c index eee11fb4c7f1..9a238e7536ae 100644 --- a/arch/alpha/lib/fpreg.c +++ b/arch/alpha/lib/fpreg.c @@ -8,6 +8,7 @@ #include <linux/compiler.h> #include <linux/export.h> #include <linux/preempt.h> +#include <asm/fpu.h> #include <asm/thread_info.h> #include <asm/fpu.h> diff --git a/arch/arc/include/asm/mmu-arcv2.h b/arch/arc/include/asm/mmu-arcv2.h index ed9036d4ede3..d85dc0721907 100644 --- a/arch/arc/include/asm/mmu-arcv2.h +++ b/arch/arc/include/asm/mmu-arcv2.h @@ -9,6 +9,8 @@ #ifndef _ASM_ARC_MMU_ARCV2_H #define _ASM_ARC_MMU_ARCV2_H +#include <soc/arc/aux.h> + /* * TLB Management regs */ diff --git a/arch/arc/mm/mmap.c b/arch/arc/mm/mmap.c index 3c1c7ae73292..69a915297155 100644 --- a/arch/arc/mm/mmap.c +++ b/arch/arc/mm/mmap.c @@ -27,7 +27,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; /* * We enforce the MAP_FIXED case. @@ -51,11 +51,9 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, return addr; } - info.flags = 0; info.length = len; info.low_limit = mm->mmap_base; info.high_limit = TASK_SIZE; - info.align_mask = 0; info.align_offset = pgoff << PAGE_SHIFT; return vm_unmapped_area(&info); } diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 749d6e3788b4..ee5115252aac 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -100,7 +100,7 @@ config ARM select HAVE_DYNAMIC_FTRACE_WITH_REGS if HAVE_DYNAMIC_FTRACE select HAVE_EFFICIENT_UNALIGNED_ACCESS if (CPU_V6 || CPU_V6K || CPU_V7) && MMU select HAVE_EXIT_THREAD - select HAVE_FAST_GUP if ARM_LPAE + select HAVE_GUP_FAST if ARM_LPAE select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL select HAVE_FUNCTION_ERROR_INJECTION select HAVE_FUNCTION_GRAPH_TRACER diff --git a/arch/arm/include/asm/hugetlb.h b/arch/arm/include/asm/hugetlb.h index a3a82b7158d4..b766c4b373f6 100644 --- a/arch/arm/include/asm/hugetlb.h +++ b/arch/arm/include/asm/hugetlb.h @@ -15,10 +15,10 @@ #include <asm/hugetlb-3level.h> #include <asm-generic/hugetlb.h> -static inline void arch_clear_hugepage_flags(struct page *page) +static inline void arch_clear_hugetlb_flags(struct folio *folio) { - clear_bit(PG_dcache_clean, &page->flags); + clear_bit(PG_dcache_clean, &folio->flags); } -#define arch_clear_hugepage_flags arch_clear_hugepage_flags +#define arch_clear_hugetlb_flags arch_clear_hugetlb_flags #endif /* _ASM_ARM_HUGETLB_H */ diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h index b0a262566eb9..6b5392e20f41 100644 --- a/arch/arm/include/asm/pgtable-2level.h +++ b/arch/arm/include/asm/pgtable-2level.h @@ -213,8 +213,8 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr) #define pmd_pfn(pmd) (__phys_to_pfn(pmd_val(pmd) & PHYS_MASK)) -#define pmd_leaf(pmd) (pmd_val(pmd) & 2) -#define pmd_bad(pmd) (pmd_val(pmd) & 2) +#define pmd_leaf(pmd) (pmd_val(pmd) & PMD_TYPE_SECT) +#define pmd_bad(pmd) pmd_leaf(pmd) #define pmd_present(pmd) (pmd_val(pmd)) #define copy_pmd(pmdpd,pmdps) \ @@ -241,7 +241,6 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr) * define empty stubs for use by pin_page_for_write. */ #define pmd_hugewillfault(pmd) (0) -#define pmd_thp_or_huge(pmd) (0) #endif /* __ASSEMBLY__ */ diff --git a/arch/arm/include/asm/pgtable-3level-hwdef.h b/arch/arm/include/asm/pgtable-3level-hwdef.h index 323ad811732e..dfab3e982cbf 100644 --- a/arch/arm/include/asm/pgtable-3level-hwdef.h +++ b/arch/arm/include/asm/pgtable-3level-hwdef.h @@ -14,6 +14,7 @@ * + Level 1/2 descriptor * - common */ +#define PUD_TABLE_BIT (_AT(pmdval_t, 1) << 1) #define PMD_TYPE_MASK (_AT(pmdval_t, 3) << 0) #define PMD_TYPE_FAULT (_AT(pmdval_t, 0) << 0) #define PMD_TYPE_TABLE (_AT(pmdval_t, 3) << 0) diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h index 4b1d9eb3908a..fa5939eb9864 100644 --- a/arch/arm/include/asm/pgtable-3level.h +++ b/arch/arm/include/asm/pgtable-3level.h @@ -112,7 +112,7 @@ #ifndef __ASSEMBLY__ #define pud_none(pud) (!pud_val(pud)) -#define pud_bad(pud) (!(pud_val(pud) & 2)) +#define pud_bad(pud) (!(pud_val(pud) & PUD_TABLE_BIT)) #define pud_present(pud) (pud_val(pud)) #define pmd_table(pmd) ((pmd_val(pmd) & PMD_TYPE_MASK) == \ PMD_TYPE_TABLE) @@ -137,7 +137,7 @@ static inline pmd_t *pud_pgtable(pud_t pud) return __va(pud_val(pud) & PHYS_MASK & (s32)PAGE_MASK); } -#define pmd_bad(pmd) (!(pmd_val(pmd) & 2)) +#define pmd_bad(pmd) (!(pmd_val(pmd) & PMD_TABLE_BIT)) #define copy_pmd(pmdpd,pmdps) \ do { \ @@ -190,7 +190,6 @@ static inline pte_t pte_mkspecial(pte_t pte) #define pmd_dirty(pmd) (pmd_isset((pmd), L_PMD_SECT_DIRTY)) #define pmd_hugewillfault(pmd) (!pmd_young(pmd) || !pmd_write(pmd)) -#define pmd_thp_or_huge(pmd) (pmd_huge(pmd) || pmd_trans_huge(pmd)) #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define pmd_trans_huge(pmd) (pmd_val(pmd) && !pmd_table(pmd)) diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c index fe28fc1f759d..dab42d066d06 100644 --- a/arch/arm/kernel/irq.c +++ b/arch/arm/kernel/irq.c @@ -32,6 +32,7 @@ #include <linux/kallsyms.h> #include <linux/proc_fs.h> #include <linux/export.h> +#include <linux/vmalloc.h> #include <asm/hardware/cache-l2x0.h> #include <asm/hardware/cache-uniphier.h> diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index 72c82a4d63ac..480e307501bb 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -26,6 +26,7 @@ #include <linux/sched/debug.h> #include <linux/sched/task_stack.h> #include <linux/irq.h> +#include <linux/vmalloc.h> #include <linux/atomic.h> #include <asm/cacheflush.h> diff --git a/arch/arm/lib/uaccess_with_memcpy.c b/arch/arm/lib/uaccess_with_memcpy.c index 2f6163f05e93..c0ac7796d775 100644 --- a/arch/arm/lib/uaccess_with_memcpy.c +++ b/arch/arm/lib/uaccess_with_memcpy.c @@ -56,10 +56,10 @@ pin_page_for_write(const void __user *_addr, pte_t **ptep, spinlock_t **ptlp) * to see that it's still huge and whether or not we will * need to fault on write. */ - if (unlikely(pmd_thp_or_huge(*pmd))) { + if (unlikely(pmd_leaf(*pmd))) { ptl = ¤t->mm->page_table_lock; spin_lock(ptl); - if (unlikely(!pmd_thp_or_huge(*pmd) + if (unlikely(!pmd_leaf(*pmd) || pmd_hugewillfault(*pmd))) { spin_unlock(ptl); return 0; diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile index f1f231f20ff9..a195cd1d3e6d 100644 --- a/arch/arm/mm/Makefile +++ b/arch/arm/mm/Makefile @@ -21,7 +21,6 @@ KASAN_SANITIZE_physaddr.o := n obj-$(CONFIG_DEBUG_VIRTUAL) += physaddr.o obj-$(CONFIG_ALIGNMENT_TRAP) += alignment.o -obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o obj-$(CONFIG_ARM_PV_FIXUP) += pv-fixup-asm.o obj-$(CONFIG_CPU_ABRT_NOMMU) += abort-nommu.o diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index dfa9554ef331..67c425341a95 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -226,9 +226,6 @@ void do_bad_area(unsigned long addr, unsigned int fsr, struct pt_regs *regs) } #ifdef CONFIG_MMU -#define VM_FAULT_BADMAP ((__force vm_fault_t)0x010000) -#define VM_FAULT_BADACCESS ((__force vm_fault_t)0x020000) - static inline bool is_permission_fault(unsigned int fsr) { int fs = fsr_fs(fsr); @@ -323,7 +320,10 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) if (!(vma->vm_flags & vm_flags)) { vma_end_read(vma); - goto lock_mmap; + count_vm_vma_lock_event(VMA_LOCK_SUCCESS); + fault = 0; + code = SEGV_ACCERR; + goto bad_area; } fault = handle_mm_fault(vma, addr, flags | FAULT_FLAG_VMA_LOCK, regs); if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED))) @@ -348,7 +348,8 @@ lock_mmap: retry: vma = lock_mm_and_find_vma(mm, addr, regs); if (unlikely(!vma)) { - fault = VM_FAULT_BADMAP; + fault = 0; + code = SEGV_MAPERR; goto bad_area; } @@ -356,10 +357,14 @@ retry: * ok, we have a good vm_area for this memory access, check the * permissions on the VMA allow for the fault which occurred. */ - if (!(vma->vm_flags & vm_flags)) - fault = VM_FAULT_BADACCESS; - else - fault = handle_mm_fault(vma, addr & PAGE_MASK, flags, regs); + if (!(vma->vm_flags & vm_flags)) { + mmap_read_unlock(mm); + fault = 0; + code = SEGV_ACCERR; + goto bad_area; + } + + fault = handle_mm_fault(vma, addr & PAGE_MASK, flags, regs); /* If we need to retry but a fatal signal is pending, handle the * signal first. We do not need to release the mmap_lock because @@ -385,12 +390,11 @@ retry: mmap_read_unlock(mm); done: - /* - * Handle the "normal" case first - VM_FAULT_MAJOR - */ - if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP | VM_FAULT_BADACCESS)))) + /* Handle the "normal" case first */ + if (likely(!(fault & VM_FAULT_ERROR))) return 0; + code = SEGV_MAPERR; bad_area: /* * If we are in kernel mode at this point, we @@ -422,8 +426,6 @@ bad_area: * isn't in our memory map.. */ sig = SIGSEGV; - code = fault == VM_FAULT_BADACCESS ? - SEGV_ACCERR : SEGV_MAPERR; } __do_user_fault(addr, fsr, sig, code, regs); diff --git a/arch/arm/mm/hugetlbpage.c b/arch/arm/mm/hugetlbpage.c deleted file mode 100644 index dd7a0277c5c0..000000000000 --- a/arch/arm/mm/hugetlbpage.c +++ /dev/null @@ -1,34 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * arch/arm/mm/hugetlbpage.c - * - * Copyright (C) 2012 ARM Ltd. - * - * Based on arch/x86/include/asm/hugetlb.h and Bill Carson's patches - */ - -#include <linux/init.h> -#include <linux/fs.h> -#include <linux/mm.h> -#include <linux/hugetlb.h> -#include <linux/pagemap.h> -#include <linux/err.h> -#include <linux/sysctl.h> -#include <asm/mman.h> -#include <asm/tlb.h> -#include <asm/tlbflush.h> - -/* - * On ARM, huge pages are backed by pmd's rather than pte's, so we do a lot - * of type casting from pmd_t * to pte_t *. - */ - -int pud_huge(pud_t pud) -{ - return 0; -} - -int pmd_huge(pmd_t pmd) -{ - return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT); -} diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c index a0f8a0ca0788..d65d0e6ed10a 100644 --- a/arch/arm/mm/mmap.c +++ b/arch/arm/mm/mmap.c @@ -34,7 +34,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, struct vm_area_struct *vma; int do_align = 0; int aliasing = cache_is_vipt_aliasing(); - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; /* * We only need to do colour alignment if either the I or D @@ -68,7 +68,6 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, return addr; } - info.flags = 0; info.length = len; info.low_limit = mm->mmap_base; info.high_limit = TASK_SIZE; @@ -87,7 +86,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, unsigned long addr = addr0; int do_align = 0; int aliasing = cache_is_vipt_aliasing(); - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; /* * We only need to do colour alignment if either the I or D diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 178765d64b3a..00cbb794aeda 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -205,7 +205,7 @@ config ARM64 select HAVE_SAMPLE_FTRACE_DIRECT select HAVE_SAMPLE_FTRACE_DIRECT_MULTI select HAVE_EFFICIENT_UNALIGNED_ACCESS - select HAVE_FAST_GUP + select HAVE_GUP_FAST select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_ERROR_INJECTION diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h index 2ddc33d93b13..3954cbd2ff56 100644 --- a/arch/arm64/include/asm/hugetlb.h +++ b/arch/arm64/include/asm/hugetlb.h @@ -18,11 +18,11 @@ extern bool arch_hugetlb_migration_supported(struct hstate *h); #endif -static inline void arch_clear_hugepage_flags(struct page *page) +static inline void arch_clear_hugetlb_flags(struct folio *folio) { - clear_bit(PG_dcache_clean, &page->flags); + clear_bit(PG_dcache_clean, &folio->flags); } -#define arch_clear_hugepage_flags arch_clear_hugepage_flags +#define arch_clear_hugetlb_flags arch_clear_hugetlb_flags pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags); #define arch_make_huge_pte arch_make_huge_pte diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index bde9fd179388..f8efbc128446 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -49,12 +49,6 @@ __flush_tlb_range(vma, addr, end, PUD_SIZE, false, 1) #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ -static inline bool arch_thp_swp_supported(void) -{ - return !system_supports_mte(); -} -#define arch_thp_swp_supported arch_thp_swp_supported - /* * Outside of a few very special situations (e.g. hibernation), we always * use broadcast TLB invalidation instructions, therefore a spurious page @@ -571,8 +565,6 @@ static inline int pmd_trans_huge(pmd_t pmd) pte_pmd(pte_swp_clear_uffd_wp(pmd_pte(pmd))) #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ -#define pmd_thp_or_huge(pmd) (pmd_huge(pmd) || pmd_trans_huge(pmd)) - #define pmd_write(pmd) pte_write(pmd_pte(pmd)) #define pmd_mkhuge(pmd) (__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT)) @@ -763,7 +755,11 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd) #define pud_none(pud) (!pud_val(pud)) #define pud_bad(pud) (!pud_table(pud)) #define pud_present(pud) pte_present(pud_pte(pud)) +#ifndef __PAGETABLE_PMD_FOLDED #define pud_leaf(pud) (pud_present(pud) && !pud_table(pud)) +#else +#define pud_leaf(pud) false +#endif #define pud_valid(pud) pte_valid(pud_pte(pud)) #define pud_user(pud) pte_user(pud_pte(pud)) #define pud_user_exec(pud) pte_user_exec(pud_pte(pud)) @@ -1284,6 +1280,46 @@ static inline void __wrprotect_ptes(struct mm_struct *mm, unsigned long address, __ptep_set_wrprotect(mm, address, ptep); } +static inline void __clear_young_dirty_pte(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t pte, cydp_t flags) +{ + pte_t old_pte; + + do { + old_pte = pte; + + if (flags & CYDP_CLEAR_YOUNG) + pte = pte_mkold(pte); + if (flags & CYDP_CLEAR_DIRTY) + pte = pte_mkclean(pte); + + pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep), + pte_val(old_pte), pte_val(pte)); + } while (pte_val(pte) != pte_val(old_pte)); +} + +static inline void __clear_young_dirty_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + unsigned int nr, cydp_t flags) +{ + pte_t pte; + + for (;;) { + pte = __ptep_get(ptep); + + if (flags == (CYDP_CLEAR_YOUNG | CYDP_CLEAR_DIRTY)) + __set_pte(ptep, pte_mkclean(pte_mkold(pte))); + else + __clear_young_dirty_pte(vma, addr, ptep, pte, flags); + + if (--nr == 0) + break; + ptep++; + addr += PAGE_SIZE; + } +} + #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_PMDP_SET_WRPROTECT static inline void pmdp_set_wrprotect(struct mm_struct *mm, @@ -1338,12 +1374,7 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma, #ifdef CONFIG_ARM64_MTE #define __HAVE_ARCH_PREPARE_TO_SWAP -static inline int arch_prepare_to_swap(struct page *page) -{ - if (system_supports_mte()) - return mte_save_tags(page); - return 0; -} +extern int arch_prepare_to_swap(struct folio *folio); #define __HAVE_ARCH_SWAP_INVALIDATE static inline void arch_swap_invalidate_page(int type, pgoff_t offset) @@ -1359,11 +1390,7 @@ static inline void arch_swap_invalidate_area(int type) } #define __HAVE_ARCH_SWAP_RESTORE -static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio) -{ - if (system_supports_mte()) - mte_restore_tags(entry, &folio->page); -} +extern void arch_swap_restore(swp_entry_t entry, struct folio *folio); #endif /* CONFIG_ARM64_MTE */ @@ -1450,6 +1477,9 @@ extern void contpte_wrprotect_ptes(struct mm_struct *mm, unsigned long addr, extern int contpte_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t entry, int dirty); +extern void contpte_clear_young_dirty_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + unsigned int nr, cydp_t flags); static __always_inline void contpte_try_fold(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) @@ -1674,6 +1704,17 @@ static inline int ptep_set_access_flags(struct vm_area_struct *vma, return contpte_ptep_set_access_flags(vma, addr, ptep, entry, dirty); } +#define clear_young_dirty_ptes clear_young_dirty_ptes +static inline void clear_young_dirty_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + unsigned int nr, cydp_t flags) +{ + if (likely(nr == 1 && !pte_cont(__ptep_get(ptep)))) + __clear_young_dirty_ptes(vma, addr, ptep, nr, flags); + else + contpte_clear_young_dirty_ptes(vma, addr, ptep, nr, flags); +} + #else /* CONFIG_ARM64_CONTPTE */ #define ptep_get __ptep_get @@ -1693,6 +1734,7 @@ static inline int ptep_set_access_flags(struct vm_area_struct *vma, #define wrprotect_ptes __wrprotect_ptes #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS #define ptep_set_access_flags __ptep_set_access_flags +#define clear_young_dirty_ptes __clear_young_dirty_ptes #endif /* CONFIG_ARM64_CONTPTE */ diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index 9afcc690fe73..4a92096db34e 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -10,6 +10,7 @@ #include <linux/efi.h> #include <linux/init.h> #include <linux/screen_info.h> +#include <linux/vmalloc.h> #include <asm/efi.h> #include <asm/stacktrace.h> diff --git a/arch/arm64/mm/contpte.c b/arch/arm64/mm/contpte.c index 1b64b4c3f8bf..9f9486de0004 100644 --- a/arch/arm64/mm/contpte.c +++ b/arch/arm64/mm/contpte.c @@ -361,6 +361,35 @@ void contpte_wrprotect_ptes(struct mm_struct *mm, unsigned long addr, } EXPORT_SYMBOL_GPL(contpte_wrprotect_ptes); +void contpte_clear_young_dirty_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + unsigned int nr, cydp_t flags) +{ + /* + * We can safely clear access/dirty without needing to unfold from + * the architectures perspective, even when contpte is set. If the + * range starts or ends midway through a contpte block, we can just + * expand to include the full contpte block. While this is not + * exactly what the core-mm asked for, it tracks access/dirty per + * folio, not per page. And since we only create a contpte block + * when it is covered by a single folio, we can get away with + * clearing access/dirty for the whole block. + */ + unsigned long start = addr; + unsigned long end = start + nr; + + if (pte_cont(__ptep_get(ptep + nr - 1))) + end = ALIGN(end, CONT_PTE_SIZE); + + if (pte_cont(__ptep_get(ptep))) { + start = ALIGN_DOWN(start, CONT_PTE_SIZE); + ptep = contpte_align_down(ptep); + } + + __clear_young_dirty_ptes(vma, start, ptep, end - start, flags); +} +EXPORT_SYMBOL_GPL(contpte_clear_young_dirty_ptes); + int contpte_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t entry, int dirty) diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 8251e2fea9c7..451ba7cbd5ad 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -486,25 +486,6 @@ static void do_bad_area(unsigned long far, unsigned long esr, } } -#define VM_FAULT_BADMAP ((__force vm_fault_t)0x010000) -#define VM_FAULT_BADACCESS ((__force vm_fault_t)0x020000) - -static vm_fault_t __do_page_fault(struct mm_struct *mm, - struct vm_area_struct *vma, unsigned long addr, - unsigned int mm_flags, unsigned long vm_flags, - struct pt_regs *regs) -{ - /* - * Ok, we have a good vm_area for this memory access, so we can handle - * it. - * Check that the permissions on the VMA allow for the fault which - * occurred. - */ - if (!(vma->vm_flags & vm_flags)) - return VM_FAULT_BADACCESS; - return handle_mm_fault(vma, addr, mm_flags, regs); -} - static bool is_el0_instruction_abort(unsigned long esr) { return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_LOW; @@ -529,6 +510,7 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr, unsigned int mm_flags = FAULT_FLAG_DEFAULT; unsigned long addr = untagged_addr(far); struct vm_area_struct *vma; + int si_code; if (kprobe_page_fault(regs, esr)) return 0; @@ -588,7 +570,10 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr, if (!(vma->vm_flags & vm_flags)) { vma_end_read(vma); - goto lock_mmap; + fault = 0; + si_code = SEGV_ACCERR; + count_vm_vma_lock_event(VMA_LOCK_SUCCESS); + goto bad_area; } fault = handle_mm_fault(vma, addr, mm_flags | FAULT_FLAG_VMA_LOCK, regs); if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED))) @@ -613,12 +598,19 @@ lock_mmap: retry: vma = lock_mm_and_find_vma(mm, addr, regs); if (unlikely(!vma)) { - fault = VM_FAULT_BADMAP; - goto done; + fault = 0; + si_code = SEGV_MAPERR; + goto bad_area; } - fault = __do_page_fault(mm, vma, addr, mm_flags, vm_flags, regs); + if (!(vma->vm_flags & vm_flags)) { + mmap_read_unlock(mm); + fault = 0; + si_code = SEGV_ACCERR; + goto bad_area; + } + fault = handle_mm_fault(vma, addr, mm_flags, regs); /* Quick path to respond to signals */ if (fault_signal_pending(fault, regs)) { if (!user_mode(regs)) @@ -637,13 +629,12 @@ retry: mmap_read_unlock(mm); done: - /* - * Handle the "normal" (no error) case first. - */ - if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP | - VM_FAULT_BADACCESS)))) + /* Handle the "normal" (no error) case first. */ + if (likely(!(fault & VM_FAULT_ERROR))) return 0; + si_code = SEGV_MAPERR; +bad_area: /* * If we are in kernel mode at this point, we have no context to * handle this fault with. @@ -678,13 +669,8 @@ done: arm64_force_sig_mceerr(BUS_MCEERR_AR, far, lsb, inf->name); } else { - /* - * Something tried to access memory that isn't in our memory - * map. - */ - arm64_force_sig_fault(SIGSEGV, - fault == VM_FAULT_BADACCESS ? SEGV_ACCERR : SEGV_MAPERR, - far, inf->name); + /* Something tried to access memory that out of memory map */ + arm64_force_sig_fault(SIGSEGV, si_code, far, inf->name); } return 0; diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index b872b003a55f..3f09ac73cce3 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -79,20 +79,6 @@ bool arch_hugetlb_migration_supported(struct hstate *h) } #endif -int pmd_huge(pmd_t pmd) -{ - return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT); -} - -int pud_huge(pud_t pud) -{ -#ifndef __PAGETABLE_PMD_FOLDED - return pud_val(pud) && !(pud_val(pud) & PUD_TABLE_BIT); -#else - return 0; -#endif -} - static int find_num_contig(struct mm_struct *mm, unsigned long addr, pte_t *ptep, size_t *pgsize) { @@ -328,7 +314,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm, if (sz != PUD_SIZE && pud_none(pud)) return NULL; /* hugepage or swap? */ - if (pud_huge(pud) || !pud_present(pud)) + if (pud_leaf(pud) || !pud_present(pud)) return (pte_t *)pudp; /* table; check the next level */ @@ -340,7 +326,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm, if (!(sz == PMD_SIZE || sz == CONT_PMD_SIZE) && pmd_none(pmd)) return NULL; - if (pmd_huge(pmd) || !pmd_present(pmd)) + if (pmd_leaf(pmd) || !pmd_present(pmd)) return (pte_t *)pmdp; if (sz == CONT_PTE_SIZE) diff --git a/arch/arm64/mm/mteswap.c b/arch/arm64/mm/mteswap.c index a31833e3ddc5..63e8d72f202a 100644 --- a/arch/arm64/mm/mteswap.c +++ b/arch/arm64/mm/mteswap.c @@ -68,6 +68,13 @@ void mte_invalidate_tags(int type, pgoff_t offset) mte_free_tag_storage(tags); } +static inline void __mte_invalidate_tags(struct page *page) +{ + swp_entry_t entry = page_swap_entry(page); + + mte_invalidate_tags(swp_type(entry), swp_offset(entry)); +} + void mte_invalidate_tags_area(int type) { swp_entry_t entry = swp_entry(type, 0); @@ -83,3 +90,41 @@ void mte_invalidate_tags_area(int type) } xa_unlock(&mte_pages); } + +int arch_prepare_to_swap(struct folio *folio) +{ + long i, nr; + int err; + + if (!system_supports_mte()) + return 0; + + nr = folio_nr_pages(folio); + + for (i = 0; i < nr; i++) { + err = mte_save_tags(folio_page(folio, i)); + if (err) + goto out; + } + return 0; + +out: + while (i--) + __mte_invalidate_tags(folio_page(folio, i)); + return err; +} + +void arch_swap_restore(swp_entry_t entry, struct folio *folio) +{ + long i, nr; + + if (!system_supports_mte()) + return; + + nr = folio_nr_pages(folio); + + for (i = 0; i < nr; i++) { + mte_restore_tags(entry, folio_page(folio, i)); + entry.val++; + } +} diff --git a/arch/csky/abiv1/mmap.c b/arch/csky/abiv1/mmap.c index 6792aca49999..7f826331d409 100644 --- a/arch/csky/abiv1/mmap.c +++ b/arch/csky/abiv1/mmap.c @@ -28,7 +28,12 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, struct mm_struct *mm = current->mm; struct vm_area_struct *vma; int do_align = 0; - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = { + .length = len, + .low_limit = mm->mmap_base, + .high_limit = TASK_SIZE, + .align_offset = pgoff << PAGE_SHIFT + }; /* * We only need to do colour alignment if either the I or D @@ -61,11 +66,6 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, return addr; } - info.flags = 0; - info.length = len; - info.low_limit = mm->mmap_base; - info.high_limit = TASK_SIZE; info.align_mask = do_align ? (PAGE_MASK & (SHMLBA - 1)) : 0; - info.align_offset = pgoff << PAGE_SHIFT; return vm_unmapped_area(&info); } diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index 42331d9a8dd7..4bda59525a13 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -119,7 +119,7 @@ config LOONGARCH select HAVE_EBPF_JIT select HAVE_EFFICIENT_UNALIGNED_ACCESS if !ARCH_STRICT_ALIGN select HAVE_EXIT_THREAD - select HAVE_FAST_GUP + select HAVE_GUP_FAST select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_ARG_ACCESS_API select HAVE_FUNCTION_ERROR_INJECTION diff --git a/arch/loongarch/include/asm/kfence.h b/arch/loongarch/include/asm/kfence.h index a6a5760da3a3..92636e82957c 100644 --- a/arch/loongarch/include/asm/kfence.h +++ b/arch/loongarch/include/asm/kfence.h @@ -10,6 +10,7 @@ #define _ASM_LOONGARCH_KFENCE_H #include <linux/kfence.h> +#include <linux/vmalloc.h> #include <asm/pgtable.h> #include <asm/tlb.h> diff --git a/arch/loongarch/mm/hugetlbpage.c b/arch/loongarch/mm/hugetlbpage.c index 1e76fcb83093..12222c56cb59 100644 --- a/arch/loongarch/mm/hugetlbpage.c +++ b/arch/loongarch/mm/hugetlbpage.c @@ -50,21 +50,11 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, return (pte_t *) pmd; } -int pmd_huge(pmd_t pmd) -{ - return (pmd_val(pmd) & _PAGE_HUGE) != 0; -} - -int pud_huge(pud_t pud) -{ - return (pud_val(pud) & _PAGE_HUGE) != 0; -} - uint64_t pmd_to_entrylo(unsigned long pmd_val) { uint64_t val; /* PMD as PTE. Must be huge page */ - if (!pmd_huge(__pmd(pmd_val))) + if (!pmd_leaf(__pmd(pmd_val))) panic("%s", __func__); val = pmd_val ^ _PAGE_HUGE; diff --git a/arch/loongarch/mm/mmap.c b/arch/loongarch/mm/mmap.c index 89af7c12e8c0..889030985135 100644 --- a/arch/loongarch/mm/mmap.c +++ b/arch/loongarch/mm/mmap.c @@ -25,7 +25,7 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp, struct vm_area_struct *vma; unsigned long addr = addr0; int do_color_align; - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; if (unlikely(len > TASK_SIZE)) return -ENOMEM; @@ -83,7 +83,6 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp, */ } - info.flags = 0; info.low_limit = mm->mmap_base; info.high_limit = TASK_SIZE; return vm_unmapped_area(&info); diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 516dc7022bd7..f1aa1bf11166 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -68,7 +68,7 @@ config MIPS select HAVE_DYNAMIC_FTRACE select HAVE_EBPF_JIT if !CPU_MICROMIPS select HAVE_EXIT_THREAD - select HAVE_FAST_GUP + select HAVE_GUP_FAST select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER diff --git a/arch/mips/include/asm/pgtable-32.h b/arch/mips/include/asm/pgtable-32.h index 0e196650f4f4..92b7591aac2a 100644 --- a/arch/mips/include/asm/pgtable-32.h +++ b/arch/mips/include/asm/pgtable-32.h @@ -129,7 +129,7 @@ static inline int pmd_none(pmd_t pmd) static inline int pmd_bad(pmd_t pmd) { #ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT - /* pmd_huge(pmd) but inline */ + /* pmd_leaf(pmd) but inline */ if (unlikely(pmd_val(pmd) & _PAGE_HUGE)) return 0; #endif diff --git a/arch/mips/include/asm/pgtable-64.h b/arch/mips/include/asm/pgtable-64.h index c0109aff223b..401c1d9e4409 100644 --- a/arch/mips/include/asm/pgtable-64.h +++ b/arch/mips/include/asm/pgtable-64.h @@ -245,7 +245,7 @@ static inline int pmd_none(pmd_t pmd) static inline int pmd_bad(pmd_t pmd) { #ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT - /* pmd_huge(pmd) but inline */ + /* pmd_leaf(pmd) but inline */ if (unlikely(pmd_val(pmd) & _PAGE_HUGE)) return 0; #endif diff --git a/arch/mips/jazz/jazzdma.c b/arch/mips/jazz/jazzdma.c index eabddb89d221..c97b089b9902 100644 --- a/arch/mips/jazz/jazzdma.c +++ b/arch/mips/jazz/jazzdma.c @@ -617,7 +617,7 @@ const struct dma_map_ops jazz_dma_ops = { .sync_sg_for_device = jazz_dma_sync_sg_for_device, .mmap = dma_common_mmap, .get_sgtable = dma_common_get_sgtable, - .alloc_pages = dma_common_alloc_pages, + .alloc_pages_op = dma_common_alloc_pages, .free_pages = dma_common_free_pages, }; EXPORT_SYMBOL(jazz_dma_ops); diff --git a/arch/mips/mm/hugetlbpage.c b/arch/mips/mm/hugetlbpage.c index 7eaff5b07873..0b9e15555b59 100644 --- a/arch/mips/mm/hugetlbpage.c +++ b/arch/mips/mm/hugetlbpage.c @@ -57,13 +57,3 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, } return (pte_t *) pmd; } - -int pmd_huge(pmd_t pmd) -{ - return (pmd_val(pmd) & _PAGE_HUGE) != 0; -} - -int pud_huge(pud_t pud) -{ - return (pud_val(pud) & _PAGE_HUGE) != 0; -} diff --git a/arch/mips/mm/mmap.c b/arch/mips/mm/mmap.c index 00fe90c6db3e..7e11d7b58761 100644 --- a/arch/mips/mm/mmap.c +++ b/arch/mips/mm/mmap.c @@ -34,7 +34,7 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp, struct vm_area_struct *vma; unsigned long addr = addr0; int do_color_align; - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; if (unlikely(len > TASK_SIZE)) return -ENOMEM; @@ -92,7 +92,6 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp, */ } - info.flags = 0; info.low_limit = mm->mmap_base; info.high_limit = TASK_SIZE; return vm_unmapped_area(&info); diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c index 4106084e57d7..76f3b9c0a9f0 100644 --- a/arch/mips/mm/tlb-r4k.c +++ b/arch/mips/mm/tlb-r4k.c @@ -326,7 +326,7 @@ void __update_tlb(struct vm_area_struct * vma, unsigned long address, pte_t pte) idx = read_c0_index(); #ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT /* this could be a huge page */ - if (pmd_huge(*pmdp)) { + if (pmd_leaf(*pmdp)) { unsigned long lo; write_c0_pagemask(PM_HUGE_MASK); ptep = (pte_t *)pmdp; diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c index 98af719d5f85..f7722451276e 100644 --- a/arch/parisc/kernel/sys_parisc.c +++ b/arch/parisc/kernel/sys_parisc.c @@ -104,7 +104,9 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp, struct vm_area_struct *vma, *prev; unsigned long filp_pgoff; int do_color_align; - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = { + .length = len + }; if (unlikely(len > TASK_SIZE)) return -ENOMEM; @@ -139,7 +141,6 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp, return addr; } - info.length = len; info.align_mask = do_color_align ? (PAGE_MASK & (SHM_COLOUR - 1)) : 0; info.align_offset = shared_align_offset(filp_pgoff, pgoff); @@ -160,7 +161,6 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp, */ } - info.flags = 0; info.low_limit = mm->mmap_base; info.high_limit = mmap_upper_limit(NULL); return vm_unmapped_area(&info); diff --git a/arch/parisc/mm/hugetlbpage.c b/arch/parisc/mm/hugetlbpage.c index a9f7e21f6656..0356199bd9e7 100644 --- a/arch/parisc/mm/hugetlbpage.c +++ b/arch/parisc/mm/hugetlbpage.c @@ -180,14 +180,3 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma, } return changed; } - - -int pmd_huge(pmd_t pmd) -{ - return 0; -} - -int pud_huge(pud_t pud) -{ - return 0; -} diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 70e118f140eb..56dcafbb83b3 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -237,7 +237,7 @@ config PPC select HAVE_DYNAMIC_FTRACE_WITH_REGS if ARCH_USING_PATCHABLE_FUNCTION_ENTRY || MPROFILE_KERNEL || PPC32 select HAVE_EBPF_JIT select HAVE_EFFICIENT_UNALIGNED_ACCESS - select HAVE_FAST_GUP + select HAVE_GUP_FAST select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_ARG_ACCESS_API select HAVE_FUNCTION_DESCRIPTORS if PPC64_ELF_ABI_V1 diff --git a/arch/powerpc/include/asm/book3s/64/pgtable-4k.h b/arch/powerpc/include/asm/book3s/64/pgtable-4k.h index 48f21820afe2..baf934578c3a 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable-4k.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable-4k.h @@ -6,26 +6,6 @@ */ #ifndef __ASSEMBLY__ #ifdef CONFIG_HUGETLB_PAGE -static inline int pmd_huge(pmd_t pmd) -{ - /* - * leaf pte for huge page - */ - if (radix_enabled()) - return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE)); - return 0; -} - -static inline int pud_huge(pud_t pud) -{ - /* - * leaf pte for huge page - */ - if (radix_enabled()) - return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE)); - return 0; -} - /* * With radix , we have hugepage ptes in the pud and pmd entries. We don't * need to setup hugepage directory for them. Our pte and page directory format diff --git a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h b/arch/powerpc/include/asm/book3s/64/pgtable-64k.h index ced7ee8b42fc..6ac73da7b80e 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable-64k.h @@ -4,31 +4,6 @@ #ifndef __ASSEMBLY__ #ifdef CONFIG_HUGETLB_PAGE -/* - * We have PGD_INDEX_SIZ = 12 and PTE_INDEX_SIZE = 8, so that we can have - * 16GB hugepage pte in PGD and 16MB hugepage pte at PMD; - * - * Defined in such a way that we can optimize away code block at build time - * if CONFIG_HUGETLB_PAGE=n. - * - * returns true for pmd migration entries, THP, devmap, hugetlb - * But compile time dependent on CONFIG_HUGETLB_PAGE - */ -static inline int pmd_huge(pmd_t pmd) -{ - /* - * leaf pte for huge page - */ - return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE)); -} - -static inline int pud_huge(pud_t pud) -{ - /* - * leaf pte for huge page - */ - return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE)); -} /* * With 64k page size, we have hugepage ptes in the pgd and pmd entries. We don't diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index fac5615e6bc5..8f9432e3855a 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -262,6 +262,18 @@ extern unsigned long __kernel_io_end; extern struct page *vmemmap; extern unsigned long pci_io_base; + +#define pmd_leaf pmd_leaf +static inline bool pmd_leaf(pmd_t pmd) +{ + return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE)); +} + +#define pud_leaf pud_leaf +static inline bool pud_leaf(pud_t pud) +{ + return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE)); +} #endif /* __ASSEMBLY__ */ #include <asm/book3s/64/hash.h> @@ -1426,20 +1438,5 @@ static inline bool is_pte_rw_upgrade(unsigned long old_val, unsigned long new_va return false; } -/* - * Like pmd_huge(), but works regardless of config options - */ -#define pmd_leaf pmd_leaf -static inline bool pmd_leaf(pmd_t pmd) -{ - return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE)); -} - -#define pud_leaf pud_leaf -static inline bool pud_leaf(pud_t pud) -{ - return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE)); -} - #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ */ diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index 24f830cf9bb4..8a27b046c6a2 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -406,9 +406,5 @@ extern void *abatron_pteptrs[2]; #include <asm/nohash/mmu.h> #endif -#if defined(CONFIG_FA_DUMP) || defined(CONFIG_PRESERVE_FA_DUMP) -#define __HAVE_ARCH_RESERVED_KERNEL_PAGES -#endif - #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_MMU_H_ */ diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h index 427db14292c9..f5f39d4f03c8 100644 --- a/arch/powerpc/include/asm/nohash/pgtable.h +++ b/arch/powerpc/include/asm/nohash/pgtable.h @@ -351,16 +351,6 @@ static inline int hugepd_ok(hugepd_t hpd) #endif } -static inline int pmd_huge(pmd_t pmd) -{ - return 0; -} - -static inline int pud_huge(pud_t pud) -{ - return 0; -} - #define is_hugepd(hpd) (hugepd_ok(hpd)) #endif diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c index 8920862ffd79..f0ae39e77e37 100644 --- a/arch/powerpc/kernel/dma-iommu.c +++ b/arch/powerpc/kernel/dma-iommu.c @@ -216,6 +216,6 @@ const struct dma_map_ops dma_iommu_ops = { .get_required_mask = dma_iommu_get_required_mask, .mmap = dma_common_mmap, .get_sgtable = dma_common_get_sgtable, - .alloc_pages = dma_common_alloc_pages, + .alloc_pages_op = dma_common_alloc_pages, .free_pages = dma_common_free_pages, }; diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index 60f974775fc8..a612e7513a4f 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -1883,8 +1883,3 @@ static void __init fadump_reserve_crash_area(u64 base) memblock_reserve(mstart, msize); } } - -unsigned long __init arch_reserved_kernel_pages(void) -{ - return memblock_reserved_size() / PAGE_SIZE; -} diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 29a8c8e18585..b70b4f93561f 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -26,6 +26,7 @@ #include <linux/iommu.h> #include <linux/sched.h> #include <linux/debugfs.h> +#include <linux/vmalloc.h> #include <asm/io.h> #include <asm/iommu.h> #include <asm/pci-bridge.h> diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c index 83823db3488b..2975ea0841ba 100644 --- a/arch/powerpc/mm/book3s64/pgtable.c +++ b/arch/powerpc/mm/book3s64/pgtable.c @@ -170,6 +170,7 @@ pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, { unsigned long old_pmd; + VM_WARN_ON_ONCE(!pmd_present(*pmdp)); old_pmd = pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, _PAGE_INVALID); flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); return __pmd(old_pmd); diff --git a/arch/powerpc/mm/book3s64/slice.c b/arch/powerpc/mm/book3s64/slice.c index c0b58afb9a47..ef3ce37f1bb3 100644 --- a/arch/powerpc/mm/book3s64/slice.c +++ b/arch/powerpc/mm/book3s64/slice.c @@ -282,12 +282,10 @@ static unsigned long slice_find_area_bottomup(struct mm_struct *mm, { int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT); unsigned long found, next_end; - struct vm_unmapped_area_info info; - - info.flags = 0; - info.length = len; - info.align_mask = PAGE_MASK & ((1ul << pshift) - 1); - info.align_offset = 0; + struct vm_unmapped_area_info info = { + .length = len, + .align_mask = PAGE_MASK & ((1ul << pshift) - 1), + }; /* * Check till the allow max value for this mmap request */ @@ -326,13 +324,13 @@ static unsigned long slice_find_area_topdown(struct mm_struct *mm, { int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT); unsigned long found, prev; - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = { + .flags = VM_UNMAPPED_AREA_TOPDOWN, + .length = len, + .align_mask = PAGE_MASK & ((1ul << pshift) - 1), + }; unsigned long min_addr = max(PAGE_SIZE, mmap_min_addr); - info.flags = VM_UNMAPPED_AREA_TOPDOWN; - info.length = len; - info.align_mask = PAGE_MASK & ((1ul << pshift) - 1); - info.align_offset = 0; /* * If we are trying to allocate above DEFAULT_MAP_WINDOW * Add the different to the mmap_base. diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 53335ae21a40..215690452495 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -71,23 +71,26 @@ static noinline int bad_area_nosemaphore(struct pt_regs *regs, unsigned long add return __bad_area_nosemaphore(regs, address, SEGV_MAPERR); } -static int __bad_area(struct pt_regs *regs, unsigned long address, int si_code) +static int __bad_area(struct pt_regs *regs, unsigned long address, int si_code, + struct mm_struct *mm, struct vm_area_struct *vma) { - struct mm_struct *mm = current->mm; /* * Something tried to access memory that isn't in our memory map.. * Fix it, but check if it's kernel or user first.. */ - mmap_read_unlock(mm); + if (mm) + mmap_read_unlock(mm); + else + vma_end_read(vma); return __bad_area_nosemaphore(regs, address, si_code); } static noinline int bad_access_pkey(struct pt_regs *regs, unsigned long address, + struct mm_struct *mm, struct vm_area_struct *vma) { - struct mm_struct *mm = current->mm; int pkey; /* @@ -109,7 +112,10 @@ static noinline int bad_access_pkey(struct pt_regs *regs, unsigned long address, */ pkey = vma_pkey(vma); - mmap_read_unlock(mm); + if (mm) + mmap_read_unlock(mm); + else + vma_end_read(vma); /* * If we are in kernel mode, bail out with a SEGV, this will @@ -124,9 +130,10 @@ static noinline int bad_access_pkey(struct pt_regs *regs, unsigned long address, return 0; } -static noinline int bad_access(struct pt_regs *regs, unsigned long address) +static noinline int bad_access(struct pt_regs *regs, unsigned long address, + struct mm_struct *mm, struct vm_area_struct *vma) { - return __bad_area(regs, address, SEGV_ACCERR); + return __bad_area(regs, address, SEGV_ACCERR, mm, vma); } static int do_sigbus(struct pt_regs *regs, unsigned long address, @@ -479,13 +486,13 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address, if (unlikely(access_pkey_error(is_write, is_exec, (error_code & DSISR_KEYFAULT), vma))) { - vma_end_read(vma); - goto lock_mmap; + count_vm_vma_lock_event(VMA_LOCK_SUCCESS); + return bad_access_pkey(regs, address, NULL, vma); } if (unlikely(access_error(is_write, is_exec, vma))) { - vma_end_read(vma); - goto lock_mmap; + count_vm_vma_lock_event(VMA_LOCK_SUCCESS); + return bad_access(regs, address, NULL, vma); } fault = handle_mm_fault(vma, address, flags | FAULT_FLAG_VMA_LOCK, regs); @@ -521,10 +528,10 @@ retry: if (unlikely(access_pkey_error(is_write, is_exec, (error_code & DSISR_KEYFAULT), vma))) - return bad_access_pkey(regs, address, vma); + return bad_access_pkey(regs, address, mm, vma); if (unlikely(access_error(is_write, is_exec, vma))) - return bad_access(regs, address); + return bad_access(regs, address, mm, vma); /* * If for any reason at all we couldn't handle the fault, diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 22cc978cdb47..d325217ab201 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -17,6 +17,7 @@ #include <linux/suspend.h> #include <linux/dma-direct.h> #include <linux/execmem.h> +#include <linux/vmalloc.h> #include <asm/swiotlb.h> #include <asm/machdep.h> diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index 9b99113cb51a..6621cfc3baf8 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -102,7 +102,7 @@ struct page *p4d_page(p4d_t p4d) { if (p4d_leaf(p4d)) { if (!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMAP)) - VM_WARN_ON(!p4d_huge(p4d)); + VM_WARN_ON(!p4d_leaf(p4d)); return pte_page(p4d_pte(p4d)); } return virt_to_page(p4d_pgtable(p4d)); @@ -113,7 +113,7 @@ struct page *pud_page(pud_t pud) { if (pud_leaf(pud)) { if (!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMAP)) - VM_WARN_ON(!pud_huge(pud)); + VM_WARN_ON(!pud_leaf(pud)); return pte_page(pud_pte(pud)); } return virt_to_page(pud_pgtable(pud)); @@ -132,7 +132,7 @@ struct page *pmd_page(pmd_t pmd) * enabled so these checks can't be used. */ if (!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMAP)) - VM_WARN_ON(!(pmd_leaf(pmd) || pmd_huge(pmd))); + VM_WARN_ON(!pmd_leaf(pmd)); return pte_page(pmd_pte(pmd)); } return virt_to_page(pmd_page_vaddr(pmd)); diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c index d6b5f5ecd515..56dc6b29a3e7 100644 --- a/arch/powerpc/platforms/ps3/system-bus.c +++ b/arch/powerpc/platforms/ps3/system-bus.c @@ -695,7 +695,7 @@ static const struct dma_map_ops ps3_sb_dma_ops = { .unmap_page = ps3_unmap_page, .mmap = dma_common_mmap, .get_sgtable = dma_common_get_sgtable, - .alloc_pages = dma_common_alloc_pages, + .alloc_pages_op = dma_common_alloc_pages, .free_pages = dma_common_free_pages, }; @@ -709,7 +709,7 @@ static const struct dma_map_ops ps3_ioc0_dma_ops = { .unmap_page = ps3_unmap_page, .mmap = dma_common_mmap, .get_sgtable = dma_common_get_sgtable, - .alloc_pages = dma_common_alloc_pages, + .alloc_pages_op = dma_common_alloc_pages, .free_pages = dma_common_free_pages, }; diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c index b2babfdbc40b..36d1c7d4156b 100644 --- a/arch/powerpc/platforms/pseries/vio.c +++ b/arch/powerpc/platforms/pseries/vio.c @@ -611,7 +611,7 @@ static const struct dma_map_ops vio_dma_mapping_ops = { .get_required_mask = dma_iommu_get_required_mask, .mmap = dma_common_mmap, .get_sgtable = dma_common_get_sgtable, - .alloc_pages = dma_common_alloc_pages, + .alloc_pages_op = dma_common_alloc_pages, .free_pages = dma_common_free_pages, }; diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 9e87287942dc..410d1d6e1b6c 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -132,7 +132,7 @@ config RISCV select HAVE_FUNCTION_GRAPH_RETVAL if HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER if !XIP_KERNEL && !PREEMPTION select HAVE_EBPF_JIT if MMU - select HAVE_FAST_GUP if MMU + select HAVE_GUP_FAST if MMU select HAVE_FUNCTION_ARG_ACCESS_API select HAVE_FUNCTION_ERROR_INJECTION select HAVE_GCC_PLUGINS diff --git a/arch/riscv/include/asm/hugetlb.h b/arch/riscv/include/asm/hugetlb.h index 22deb7a2a6ec..b1ce97a9dbfc 100644 --- a/arch/riscv/include/asm/hugetlb.h +++ b/arch/riscv/include/asm/hugetlb.h @@ -5,11 +5,11 @@ #include <asm/cacheflush.h> #include <asm/page.h> -static inline void arch_clear_hugepage_flags(struct page *page) +static inline void arch_clear_hugetlb_flags(struct folio *folio) { - clear_bit(PG_dcache_clean, &page->flags); + clear_bit(PG_dcache_clean, &folio->flags); } -#define arch_clear_hugepage_flags arch_clear_hugepage_flags +#define arch_clear_hugetlb_flags arch_clear_hugetlb_flags #ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION bool arch_hugetlb_migration_supported(struct hstate *h); diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 381137ce70d4..55a7c3ec246b 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -651,6 +651,7 @@ static inline unsigned long pmd_pfn(pmd_t pmd) #define __pud_to_phys(pud) (__page_val_to_pfn(pud_val(pud)) << PAGE_SHIFT) +#define pud_pfn pud_pfn static inline unsigned long pud_pfn(pud_t pud) { return ((__pud_to_phys(pud) & PUD_MASK) >> PAGE_SHIFT); diff --git a/arch/riscv/kernel/elf_kexec.c b/arch/riscv/kernel/elf_kexec.c index 54260c16f991..11c0d2e0becf 100644 --- a/arch/riscv/kernel/elf_kexec.c +++ b/arch/riscv/kernel/elf_kexec.c @@ -19,6 +19,7 @@ #include <linux/libfdt.h> #include <linux/types.h> #include <linux/memblock.h> +#include <linux/vmalloc.h> #include <asm/setup.h> int arch_kimage_file_post_load_cleanup(struct kimage *image) diff --git a/arch/riscv/kernel/probes/kprobes.c b/arch/riscv/kernel/probes/kprobes.c index e64f2f3064eb..dfb28e57d900 100644 --- a/arch/riscv/kernel/probes/kprobes.c +++ b/arch/riscv/kernel/probes/kprobes.c @@ -6,6 +6,7 @@ #include <linux/extable.h> #include <linux/slab.h> #include <linux/stop_machine.h> +#include <linux/vmalloc.h> #include <asm/ptrace.h> #include <linux/uaccess.h> #include <asm/sections.h> diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 3ba1d4dde5dd..5224f3733802 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -292,7 +292,10 @@ void handle_page_fault(struct pt_regs *regs) if (unlikely(access_error(cause, vma))) { vma_end_read(vma); - goto lock_mmap; + count_vm_vma_lock_event(VMA_LOCK_SUCCESS); + tsk->thread.bad_cause = cause; + bad_area_nosemaphore(regs, SEGV_ACCERR, addr); + return; } fault = handle_mm_fault(vma, addr, flags | FAULT_FLAG_VMA_LOCK, regs); diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c index 5ef2a6891158..0ebd968b33c9 100644 --- a/arch/riscv/mm/hugetlbpage.c +++ b/arch/riscv/mm/hugetlbpage.c @@ -399,16 +399,6 @@ static bool is_napot_size(unsigned long size) #endif /*CONFIG_RISCV_ISA_SVNAPOT*/ -int pud_huge(pud_t pud) -{ - return pud_leaf(pud); -} - -int pmd_huge(pmd_t pmd) -{ - return pmd_leaf(pmd); -} - static bool __hugetlb_valid_size(unsigned long size) { if (size == HPAGE_SIZE) diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 7e7fe89c9b25..c59d2b54df49 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -177,7 +177,7 @@ config S390 select HAVE_DYNAMIC_FTRACE_WITH_REGS select HAVE_EBPF_JIT if HAVE_MARCH_Z196_FEATURES select HAVE_EFFICIENT_UNALIGNED_ACCESS - select HAVE_FAST_GUP + select HAVE_GUP_FAST select HAVE_FENTRY select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_ARG_ACCESS_API diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h index deb198a61039..ce5f4fe8be4d 100644 --- a/arch/s390/include/asm/hugetlb.h +++ b/arch/s390/include/asm/hugetlb.h @@ -39,11 +39,11 @@ static inline int prepare_hugepage_range(struct file *file, return 0; } -static inline void arch_clear_hugepage_flags(struct page *page) +static inline void arch_clear_hugetlb_flags(struct folio *folio) { - clear_bit(PG_arch_1, &page->flags); + clear_bit(PG_arch_1, &folio->flags); } -#define arch_clear_hugepage_flags arch_clear_hugepage_flags +#define arch_clear_hugetlb_flags arch_clear_hugetlb_flags static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long sz) diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 6f11d063d545..ad55b5b99a75 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1421,6 +1421,7 @@ static inline unsigned long pud_deref(pud_t pud) return (unsigned long)__va(pud_val(pud) & origin_mask); } +#define pud_pfn pud_pfn static inline unsigned long pud_pfn(pud_t pud) { return __pa(pud_deref(pud)) >> PAGE_SHIFT; @@ -1784,8 +1785,10 @@ static inline pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, static inline pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp) { - pmd_t pmd = __pmd(pmd_val(*pmdp) | _SEGMENT_ENTRY_INVALID); + pmd_t pmd; + VM_WARN_ON_ONCE(!pmd_present(*pmdp)); + pmd = __pmd(pmd_val(*pmdp) | _SEGMENT_ENTRY_INVALID); return pmdp_xchg_direct(vma->vm_mm, addr, pmdp, pmd); } diff --git a/arch/s390/kernel/cert_store.c b/arch/s390/kernel/cert_store.c index 554447768bdd..bf983513dd33 100644 --- a/arch/s390/kernel/cert_store.c +++ b/arch/s390/kernel/cert_store.c @@ -21,6 +21,7 @@ #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/sysfs.h> +#include <linux/vmalloc.h> #include <crypto/sha2.h> #include <keys/user-type.h> #include <asm/debug.h> diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index 7dc54571f18e..f3609a0d453d 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -20,6 +20,7 @@ #include <linux/gfp.h> #include <linux/crash_dump.h> #include <linux/debug_locks.h> +#include <linux/vmalloc.h> #include <asm/asm-extable.h> #include <asm/diag.h> #include <asm/ipl.h> diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 0c66b32e0f9f..65747f15dbec 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -325,7 +325,8 @@ static void do_exception(struct pt_regs *regs, int access) goto lock_mmap; if (!(vma->vm_flags & access)) { vma_end_read(vma); - goto lock_mmap; + count_vm_vma_lock_event(VMA_LOCK_SUCCESS); + return handle_fault_error_nolock(regs, SEGV_ACCERR); } fault = handle_mm_fault(vma, address, flags | FAULT_FLAG_VMA_LOCK, regs); if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED))) diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index dc3db86e13ff..2675aab4acc7 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -233,16 +233,6 @@ pte_t *huge_pte_offset(struct mm_struct *mm, return (pte_t *) pmdp; } -int pmd_huge(pmd_t pmd) -{ - return pmd_leaf(pmd); -} - -int pud_huge(pud_t pud) -{ - return pud_leaf(pud); -} - bool __init arch_hugetlb_valid_size(unsigned long size) { if (MACHINE_HAS_EDAT1 && size == PMD_SIZE) @@ -258,14 +248,12 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file, unsigned long pgoff, unsigned long flags) { struct hstate *h = hstate_file(file); - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; - info.flags = 0; info.length = len; info.low_limit = current->mm->mmap_base; info.high_limit = TASK_SIZE; info.align_mask = PAGE_MASK & ~huge_page_mask(h); - info.align_offset = 0; return vm_unmapped_area(&info); } @@ -274,7 +262,7 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file, unsigned long pgoff, unsigned long flags) { struct hstate *h = hstate_file(file); - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; unsigned long addr; info.flags = VM_UNMAPPED_AREA_TOPDOWN; @@ -282,7 +270,6 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file, info.low_limit = PAGE_SIZE; info.high_limit = current->mm->mmap_base; info.align_mask = PAGE_MASK & ~huge_page_mask(h); - info.align_offset = 0; addr = vm_unmapped_area(&info); /* @@ -328,7 +315,7 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, goto check_asce_limit; } - if (mm->get_unmapped_area == arch_get_unmapped_area) + if (!test_bit(MMF_TOPDOWN, &mm->flags)) addr = hugetlb_get_unmapped_area_bottomup(file, addr, len, pgoff, flags); else diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index b14fc0887654..206756946589 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -86,7 +86,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; if (len > TASK_SIZE - mmap_min_addr) return -ENOMEM; @@ -102,7 +102,6 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, goto check_asce_limit; } - info.flags = 0; info.length = len; info.low_limit = mm->mmap_base; info.high_limit = TASK_SIZE; @@ -122,7 +121,7 @@ unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long ad { struct vm_area_struct *vma; struct mm_struct *mm = current->mm; - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; /* requested length too big for entire address space */ if (len > TASK_SIZE - mmap_min_addr) @@ -185,10 +184,10 @@ void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) */ if (mmap_is_legacy(rlim_stack)) { mm->mmap_base = mmap_base_legacy(random_factor); - mm->get_unmapped_area = arch_get_unmapped_area; + clear_bit(MMF_TOPDOWN, &mm->flags); } else { mm->mmap_base = mmap_base(random_factor, rlim_stack); - mm->get_unmapped_area = arch_get_unmapped_area_topdown; + set_bit(MMF_TOPDOWN, &mm->flags); } } diff --git a/arch/s390/pci/pci_mmio.c b/arch/s390/pci/pci_mmio.c index a90499c087f0..5398729bfe1b 100644 --- a/arch/s390/pci/pci_mmio.c +++ b/arch/s390/pci/pci_mmio.c @@ -169,7 +169,7 @@ SYSCALL_DEFINE3(s390_pci_mmio_write, unsigned long, mmio_addr, if (!(vma->vm_flags & VM_WRITE)) goto out_unlock_mmap; - ret = follow_pte(vma->vm_mm, mmio_addr, &ptep, &ptl); + ret = follow_pte(vma, mmio_addr, &ptep, &ptl); if (ret) goto out_unlock_mmap; @@ -308,7 +308,7 @@ SYSCALL_DEFINE3(s390_pci_mmio_read, unsigned long, mmio_addr, if (!(vma->vm_flags & VM_WRITE)) goto out_unlock_mmap; - ret = follow_pte(vma->vm_mm, mmio_addr, &ptep, &ptl); + ret = follow_pte(vma, mmio_addr, &ptep, &ptl); if (ret) goto out_unlock_mmap; diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 01cb1eb01277..5e6a3ead51fb 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -38,7 +38,7 @@ config SUPERH select HAVE_DEBUG_BUGVERBOSE select HAVE_DEBUG_KMEMLEAK select HAVE_DYNAMIC_FTRACE - select HAVE_FAST_GUP if MMU + select HAVE_GUP_FAST if MMU select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER select HAVE_FTRACE_MCOUNT_RECORD diff --git a/arch/sh/include/asm/hugetlb.h b/arch/sh/include/asm/hugetlb.h index 4d3ba39e681c..75028bd568ba 100644 --- a/arch/sh/include/asm/hugetlb.h +++ b/arch/sh/include/asm/hugetlb.h @@ -27,11 +27,11 @@ static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, return *ptep; } -static inline void arch_clear_hugepage_flags(struct page *page) +static inline void arch_clear_hugetlb_flags(struct folio *folio) { - clear_bit(PG_dcache_clean, &page->flags); + clear_bit(PG_dcache_clean, &folio->flags); } -#define arch_clear_hugepage_flags arch_clear_hugepage_flags +#define arch_clear_hugetlb_flags arch_clear_hugetlb_flags #include <asm-generic/hugetlb.h> diff --git a/arch/sh/mm/cache-sh4.c b/arch/sh/mm/cache-sh4.c index 195e739ee2be..46393b00137e 100644 --- a/arch/sh/mm/cache-sh4.c +++ b/arch/sh/mm/cache-sh4.c @@ -241,13 +241,14 @@ static void sh4_flush_cache_page(void *args) if ((vma->vm_mm == current->active_mm)) vaddr = NULL; else { + struct folio *folio = page_folio(page); /* * Use kmap_coherent or kmap_atomic to do flushes for * another ASID than the current one. */ map_coherent = (current_cpu_data.dcache.n_aliases && - test_bit(PG_dcache_clean, &page->flags) && - page_mapcount(page)); + test_bit(PG_dcache_clean, folio_flags(folio, 0)) && + page_mapped(page)); if (map_coherent) vaddr = kmap_coherent(page, address); else diff --git a/arch/sh/mm/cache.c b/arch/sh/mm/cache.c index ceffd3ffc81e..6ebdeaff3021 100644 --- a/arch/sh/mm/cache.c +++ b/arch/sh/mm/cache.c @@ -84,7 +84,7 @@ void copy_from_user_page(struct vm_area_struct *vma, struct page *page, { struct folio *folio = page_folio(page); - if (boot_cpu_data.dcache.n_aliases && page_mapcount(page) && + if (boot_cpu_data.dcache.n_aliases && folio_mapped(folio) && test_bit(PG_dcache_clean, &folio->flags)) { void *vfrom = kmap_coherent(page, vaddr) + (vaddr & ~PAGE_MASK); memcpy(dst, vfrom, len); diff --git a/arch/sh/mm/hugetlbpage.c b/arch/sh/mm/hugetlbpage.c index 6cb0ad73dbb9..ff209b55285a 100644 --- a/arch/sh/mm/hugetlbpage.c +++ b/arch/sh/mm/hugetlbpage.c @@ -70,13 +70,3 @@ pte_t *huge_pte_offset(struct mm_struct *mm, return pte; } - -int pmd_huge(pmd_t pmd) -{ - return 0; -} - -int pud_huge(pud_t pud) -{ - return 0; -} diff --git a/arch/sh/mm/mmap.c b/arch/sh/mm/mmap.c index b82199878b45..bee329d4149a 100644 --- a/arch/sh/mm/mmap.c +++ b/arch/sh/mm/mmap.c @@ -57,7 +57,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, struct mm_struct *mm = current->mm; struct vm_area_struct *vma; int do_colour_align; - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; if (flags & MAP_FIXED) { /* We do not accept a shared mapping if it would violate @@ -88,7 +88,6 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, return addr; } - info.flags = 0; info.length = len; info.low_limit = TASK_UNMAPPED_BASE; info.high_limit = TASK_SIZE; @@ -106,7 +105,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, struct mm_struct *mm = current->mm; unsigned long addr = addr0; int do_colour_align; - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; if (flags & MAP_FIXED) { /* We do not accept a shared mapping if it would violate diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 4d1bafaba942..3fe429d73a65 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -875,6 +875,7 @@ static inline bool pud_leaf(pud_t pud) return pte_val(pte) & _PAGE_PMD_HUGE; } +#define pud_pfn pud_pfn static inline unsigned long pud_pfn(pud_t pud) { pte_t pte = __pte(pud_val(pud)); @@ -956,7 +957,7 @@ static inline void set_ptes(struct mm_struct *mm, unsigned long addr, #ifdef DCACHE_ALIASING_POSSIBLE #define __HAVE_ARCH_MOVE_PTE -#define move_pte(pte, prot, old_addr, new_addr) \ +#define move_pte(pte, old_addr, new_addr) \ ({ \ pte_t newpte = (pte); \ if (tlb_type != hypervisor && pte_present(pte)) { \ diff --git a/arch/sparc/kernel/sys_sparc_32.c b/arch/sparc/kernel/sys_sparc_32.c index 082a551897ed..08a19727795c 100644 --- a/arch/sparc/kernel/sys_sparc_32.c +++ b/arch/sparc/kernel/sys_sparc_32.c @@ -41,7 +41,7 @@ SYSCALL_DEFINE0(getpagesize) unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; if (flags & MAP_FIXED) { /* We do not accept a shared mapping if it would violate @@ -59,7 +59,6 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi if (!addr) addr = TASK_UNMAPPED_BASE; - info.flags = 0; info.length = len; info.low_limit = addr; info.high_limit = TASK_SIZE; diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c index 1e9a9e016237..d9c3b34ca744 100644 --- a/arch/sparc/kernel/sys_sparc_64.c +++ b/arch/sparc/kernel/sys_sparc_64.c @@ -93,7 +93,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi struct vm_area_struct * vma; unsigned long task_size = TASK_SIZE; int do_color_align; - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; if (flags & MAP_FIXED) { /* We do not accept a shared mapping if it would violate @@ -126,7 +126,6 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi return addr; } - info.flags = 0; info.length = len; info.low_limit = TASK_UNMAPPED_BASE; info.high_limit = min(task_size, VA_EXCLUDE_START); @@ -154,7 +153,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, unsigned long task_size = STACK_TOP32; unsigned long addr = addr0; int do_color_align; - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; /* This should only ever run for 32-bit processes. */ BUG_ON(!test_thread_flag(TIF_32BIT)); @@ -218,14 +217,10 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, unsigned long get_fb_unmapped_area(struct file *filp, unsigned long orig_addr, unsigned long len, unsigned long pgoff, unsigned long flags) { unsigned long align_goal, addr = -ENOMEM; - unsigned long (*get_area)(struct file *, unsigned long, - unsigned long, unsigned long, unsigned long); - - get_area = current->mm->get_unmapped_area; if (flags & MAP_FIXED) { /* Ok, don't mess with it. */ - return get_area(NULL, orig_addr, len, pgoff, flags); + return mm_get_unmapped_area(current->mm, NULL, orig_addr, len, pgoff, flags); } flags &= ~MAP_SHARED; @@ -238,7 +233,8 @@ unsigned long get_fb_unmapped_area(struct file *filp, unsigned long orig_addr, u align_goal = (64UL * 1024); do { - addr = get_area(NULL, orig_addr, len + (align_goal - PAGE_SIZE), pgoff, flags); + addr = mm_get_unmapped_area(current->mm, NULL, orig_addr, + len + (align_goal - PAGE_SIZE), pgoff, flags); if (!(addr & ~PAGE_MASK)) { addr = (addr + (align_goal - 1UL)) & ~(align_goal - 1UL); break; @@ -256,7 +252,7 @@ unsigned long get_fb_unmapped_area(struct file *filp, unsigned long orig_addr, u * be obtained. */ if (addr & ~PAGE_MASK) - addr = get_area(NULL, orig_addr, len, pgoff, flags); + addr = mm_get_unmapped_area(current->mm, NULL, orig_addr, len, pgoff, flags); return addr; } @@ -292,7 +288,7 @@ void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) gap == RLIM_INFINITY || sysctl_legacy_va_layout) { mm->mmap_base = TASK_UNMAPPED_BASE + random_factor; - mm->get_unmapped_area = arch_get_unmapped_area; + clear_bit(MMF_TOPDOWN, &mm->flags); } else { /* We know it's 32-bit */ unsigned long task_size = STACK_TOP32; @@ -303,7 +299,7 @@ void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) gap = (task_size / 6 * 5); mm->mmap_base = PAGE_ALIGN(task_size - gap - random_factor); - mm->get_unmapped_area = arch_get_unmapped_area_topdown; + set_bit(MMF_TOPDOWN, &mm->flags); } } diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c index b432500c13a5..cc91ca7a1e18 100644 --- a/arch/sparc/mm/hugetlbpage.c +++ b/arch/sparc/mm/hugetlbpage.c @@ -31,17 +31,15 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *filp, { struct hstate *h = hstate_file(filp); unsigned long task_size = TASK_SIZE; - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; if (test_thread_flag(TIF_32BIT)) task_size = STACK_TOP32; - info.flags = 0; info.length = len; info.low_limit = TASK_UNMAPPED_BASE; info.high_limit = min(task_size, VA_EXCLUDE_START); info.align_mask = PAGE_MASK & ~huge_page_mask(h); - info.align_offset = 0; addr = vm_unmapped_area(&info); if ((addr & ~PAGE_MASK) && task_size > VA_EXCLUDE_END) { @@ -63,7 +61,7 @@ hugetlb_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, struct hstate *h = hstate_file(filp); struct mm_struct *mm = current->mm; unsigned long addr = addr0; - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; /* This should only ever run for 32-bit processes. */ BUG_ON(!test_thread_flag(TIF_32BIT)); @@ -73,7 +71,6 @@ hugetlb_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, info.low_limit = PAGE_SIZE; info.high_limit = mm->mmap_base; info.align_mask = PAGE_MASK & ~huge_page_mask(h); - info.align_offset = 0; addr = vm_unmapped_area(&info); /* @@ -123,7 +120,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, (!vma || addr + len <= vm_start_gap(vma))) return addr; } - if (mm->get_unmapped_area == arch_get_unmapped_area) + if (!test_bit(MMF_TOPDOWN, &mm->flags)) return hugetlb_get_unmapped_area_bottomup(file, addr, len, pgoff, flags); else @@ -407,18 +404,6 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, return entry; } -int pmd_huge(pmd_t pmd) -{ - return !pmd_none(pmd) && - (pmd_val(pmd) & (_PAGE_VALID|_PAGE_PMD_HUGE)) != _PAGE_VALID; -} - -int pud_huge(pud_t pud) -{ - return !pud_none(pud) && - (pud_val(pud) & (_PAGE_VALID|_PAGE_PUD_HUGE)) != _PAGE_VALID; -} - static void hugetlb_free_pte_range(struct mmu_gather *tlb, pmd_t *pmd, unsigned long addr) { diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c index b44d79d778c7..8648a50afe88 100644 --- a/arch/sparc/mm/tlb.c +++ b/arch/sparc/mm/tlb.c @@ -183,12 +183,12 @@ static void __set_pmd_acct(struct mm_struct *mm, unsigned long addr, * hugetlb_pte_count. */ if (pmd_val(pmd) & _PAGE_PMD_HUGE) { - if (is_huge_zero_page(pmd_page(pmd))) + if (is_huge_zero_pmd(pmd)) mm->context.hugetlb_pte_count++; else mm->context.thp_pte_count++; } else { - if (is_huge_zero_page(pmd_page(orig))) + if (is_huge_zero_pmd(orig)) mm->context.hugetlb_pte_count--; else mm->context.thp_pte_count--; @@ -249,6 +249,7 @@ pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, { pmd_t old, entry; + VM_WARN_ON_ONCE(!pmd_present(*pmdp)); entry = __pmd(pmd_val(*pmdp) & ~_PAGE_VALID); old = pmdp_establish(vma, address, pmdp, entry); flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); @@ -259,7 +260,7 @@ pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, * Sanity check pmd before doing the actual decrement. */ if ((pmd_val(entry) & _PAGE_PMD_HUGE) && - !is_huge_zero_page(pmd_page(entry))) + !is_huge_zero_pmd(entry)) (vma->vm_mm)->context.thp_pte_count--; return old; diff --git a/arch/um/include/shared/um_malloc.h b/arch/um/include/shared/um_malloc.h index 13da93284c2c..bf503658f08e 100644 --- a/arch/um/include/shared/um_malloc.h +++ b/arch/um/include/shared/um_malloc.h @@ -11,7 +11,8 @@ extern void *uml_kmalloc(int size, int flags); extern void kfree(const void *ptr); -extern void *vmalloc(unsigned long size); +extern void *vmalloc_noprof(unsigned long size); +#define vmalloc(...) vmalloc_noprof(__VA_ARGS__) extern void vfree(void *ptr); #endif /* __UM_MALLOC_H__ */ diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index bc47bc9841ff..671bc6fd557c 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -224,7 +224,7 @@ config X86 select HAVE_EFFICIENT_UNALIGNED_ACCESS select HAVE_EISA select HAVE_EXIT_THREAD - select HAVE_FAST_GUP + select HAVE_GUP_FAST select HAVE_FENTRY if X86_64 || DYNAMIC_FTRACE select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_GRAPH_RETVAL if HAVE_FUNCTION_GRAPH_TRACER diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index 4b99ed326b17..1d60427379c9 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -42,6 +42,7 @@ #include <asm/early_ioremap.h> #include <asm/pgtable_types.h> #include <asm/shared/io.h> +#include <asm/special_insns.h> #define build_mmio_read(name, size, type, reg, barrier) \ static inline type name(const volatile void __iomem *addr) \ diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 315535ffb258..65b8e5bb902c 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -234,6 +234,7 @@ static inline unsigned long pmd_pfn(pmd_t pmd) return (pfn & pmd_pfn_mask(pmd)) >> PAGE_SHIFT; } +#define pud_pfn pud_pfn static inline unsigned long pud_pfn(pud_t pud) { phys_addr_t pfn = pud_val(pud); @@ -387,23 +388,7 @@ static inline pte_t pte_wrprotect(pte_t pte) #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP static inline int pte_uffd_wp(pte_t pte) { - bool wp = pte_flags(pte) & _PAGE_UFFD_WP; - -#ifdef CONFIG_DEBUG_VM - /* - * Having write bit for wr-protect-marked present ptes is fatal, - * because it means the uffd-wp bit will be ignored and write will - * just go through. - * - * Use any chance of pgtable walking to verify this (e.g., when - * page swapped out or being migrated for all purposes). It means - * something is already wrong. Tell the admin even before the - * process crashes. We also nail it with wrong pgtable setup. - */ - WARN_ON_ONCE(wp && pte_write(pte)); -#endif - - return wp; + return pte_flags(pte) & _PAGE_UFFD_WP; } static inline pte_t pte_mkuffd_wp(pte_t pte) @@ -1200,7 +1185,6 @@ static inline int pgd_none(pgd_t pgd) extern int direct_gbpages; void init_mem_mapping(void); void early_alloc_pgt_buf(void); -extern void memblock_find_dma_reserve(void); void __init poking_init(void); unsigned long init_memory_mapping(unsigned long start, unsigned long end, pgprot_t prot); diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 7e9db77231ac..3c4407271d08 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -245,6 +245,7 @@ extern void cleanup_highmap(void); #define HAVE_ARCH_UNMAPPED_AREA #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN +#define HAVE_ARCH_UNMAPPED_AREA_VMFLAGS #define PAGE_AGP PAGE_KERNEL_NOCACHE #define HAVE_PAGE_AGP 1 diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c index 2ae98f754e59..c884deca839b 100644 --- a/arch/x86/kernel/amd_gart_64.c +++ b/arch/x86/kernel/amd_gart_64.c @@ -676,7 +676,7 @@ static const struct dma_map_ops gart_dma_ops = { .get_sgtable = dma_common_get_sgtable, .dma_supported = dma_direct_supported, .get_required_mask = dma_direct_get_required_mask, - .alloc_pages = dma_direct_alloc_pages, + .alloc_pages_op = dma_direct_alloc_pages, .free_pages = dma_direct_free_pages, }; diff --git a/arch/x86/kernel/cpu/sgx/driver.c b/arch/x86/kernel/cpu/sgx/driver.c index 262f5fb18d74..22b65a5f5ec6 100644 --- a/arch/x86/kernel/cpu/sgx/driver.c +++ b/arch/x86/kernel/cpu/sgx/driver.c @@ -113,7 +113,7 @@ static unsigned long sgx_get_unmapped_area(struct file *file, if (flags & MAP_FIXED) return addr; - return current->mm->get_unmapped_area(file, addr, len, pgoff, flags); + return mm_get_unmapped_area(current->mm, file, addr, len, pgoff, flags); } #ifdef CONFIG_COMPAT diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c index 166692f2d501..27892e57c4ef 100644 --- a/arch/x86/kernel/cpu/sgx/main.c +++ b/arch/x86/kernel/cpu/sgx/main.c @@ -13,6 +13,7 @@ #include <linux/sched/signal.h> #include <linux/slab.h> #include <linux/sysfs.h> +#include <linux/vmalloc.h> #include <asm/sgx.h> #include "driver.h" #include "encl.h" diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index fe0c859873d1..ade0043ce56e 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -18,6 +18,7 @@ #include <linux/uaccess.h> #include <linux/smp.h> #include <linux/sched/task_stack.h> +#include <linux/vmalloc.h> #include <asm/cpu_entry_area.h> #include <asm/softirq_stack.h> diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 55a1fc332e20..05c5aa951da7 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1108,8 +1108,6 @@ void __init setup_arch(char **cmdline_p) */ arch_reserve_crashkernel(); - memblock_find_dma_reserve(); - if (!early_xdbc_setup_hardware()) early_xdbc_register_console(); diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index cb9fa1d5c66f..01d7cd85ef97 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -112,13 +112,21 @@ static void find_start_end(unsigned long addr, unsigned long flags, *end = task_size_64bit(addr > DEFAULT_MAP_WINDOW); } +static inline unsigned long stack_guard_placement(vm_flags_t vm_flags) +{ + if (vm_flags & VM_SHADOW_STACK) + return PAGE_SIZE; + + return 0; +} + unsigned long -arch_get_unmapped_area(struct file *filp, unsigned long addr, - unsigned long len, unsigned long pgoff, unsigned long flags) +arch_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, unsigned long len, + unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; unsigned long begin, end; if (flags & MAP_FIXED) @@ -137,12 +145,11 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, return addr; } - info.flags = 0; info.length = len; info.low_limit = begin; info.high_limit = end; - info.align_mask = 0; info.align_offset = pgoff << PAGE_SHIFT; + info.start_gap = stack_guard_placement(vm_flags); if (filp) { info.align_mask = get_align_mask(); info.align_offset += get_align_bits(); @@ -151,14 +158,14 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, } unsigned long -arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, - const unsigned long len, const unsigned long pgoff, - const unsigned long flags) +arch_get_unmapped_area_topdown_vmflags(struct file *filp, unsigned long addr0, + unsigned long len, unsigned long pgoff, + unsigned long flags, vm_flags_t vm_flags) { struct vm_area_struct *vma; struct mm_struct *mm = current->mm; unsigned long addr = addr0; - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; /* requested length too big for entire address space */ if (len > TASK_SIZE) @@ -192,6 +199,7 @@ get_unmapped_area: info.low_limit = PAGE_SIZE; info.high_limit = get_mmap_base(0); + info.start_gap = stack_guard_placement(vm_flags); /* * If hint address is above DEFAULT_MAP_WINDOW, look for unmapped area @@ -203,7 +211,6 @@ get_unmapped_area: if (addr > DEFAULT_MAP_WINDOW && !in_32bit_syscall()) info.high_limit += TASK_SIZE_MAX - DEFAULT_MAP_WINDOW; - info.align_mask = 0; info.align_offset = pgoff << PAGE_SHIFT; if (filp) { info.align_mask = get_align_mask(); @@ -223,3 +230,18 @@ bottomup: */ return arch_get_unmapped_area(filp, addr0, len, pgoff, flags); } + +unsigned long +arch_get_unmapped_area(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, unsigned long flags) +{ + return arch_get_unmapped_area_vmflags(filp, addr, len, pgoff, flags, 0); +} + +unsigned long +arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr, + const unsigned long len, const unsigned long pgoff, + const unsigned long flags) +{ + return arch_get_unmapped_area_topdown_vmflags(filp, addr, len, pgoff, flags, 0); +} diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index f26ecabc9424..e6c469b323cc 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -20,6 +20,7 @@ #include <linux/efi.h> /* efi_crash_gracefully_on_page_fault()*/ #include <linux/mm_types.h> #include <linux/mm.h> /* find_and_lock_vma() */ +#include <linux/vmalloc.h> #include <asm/cpufeature.h> /* boot_cpu_has, ... */ #include <asm/traps.h> /* dotraplinkage, ... */ @@ -835,14 +836,17 @@ bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, static void __bad_area(struct pt_regs *regs, unsigned long error_code, - unsigned long address, u32 pkey, int si_code) + unsigned long address, struct mm_struct *mm, + struct vm_area_struct *vma, u32 pkey, int si_code) { - struct mm_struct *mm = current->mm; /* * Something tried to access memory that isn't in our memory map.. * Fix it, but check if it's kernel or user first.. */ - mmap_read_unlock(mm); + if (mm) + mmap_read_unlock(mm); + else + vma_end_read(vma); __bad_area_nosemaphore(regs, error_code, address, pkey, si_code); } @@ -866,7 +870,8 @@ static inline bool bad_area_access_from_pkeys(unsigned long error_code, static noinline void bad_area_access_error(struct pt_regs *regs, unsigned long error_code, - unsigned long address, struct vm_area_struct *vma) + unsigned long address, struct mm_struct *mm, + struct vm_area_struct *vma) { /* * This OSPKE check is not strictly necessary at runtime. @@ -896,9 +901,9 @@ bad_area_access_error(struct pt_regs *regs, unsigned long error_code, */ u32 pkey = vma_pkey(vma); - __bad_area(regs, error_code, address, pkey, SEGV_PKUERR); + __bad_area(regs, error_code, address, mm, vma, pkey, SEGV_PKUERR); } else { - __bad_area(regs, error_code, address, 0, SEGV_ACCERR); + __bad_area(regs, error_code, address, mm, vma, 0, SEGV_ACCERR); } } @@ -1326,8 +1331,9 @@ void do_user_addr_fault(struct pt_regs *regs, goto lock_mmap; if (unlikely(access_error(error_code, vma))) { - vma_end_read(vma); - goto lock_mmap; + bad_area_access_error(regs, error_code, address, NULL, vma); + count_vm_vma_lock_event(VMA_LOCK_SUCCESS); + return; } fault = handle_mm_fault(vma, address, flags | FAULT_FLAG_VMA_LOCK, regs); if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED))) @@ -1363,7 +1369,7 @@ retry: * we can handle it.. */ if (unlikely(access_error(error_code, vma))) { - bad_area_access_error(regs, error_code, address, vma); + bad_area_access_error(regs, error_code, address, mm, vma); return; } diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 5804bbae4f01..807a5859a3c4 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -19,41 +19,14 @@ #include <asm/tlbflush.h> #include <asm/elf.h> -/* - * pmd_huge() returns 1 if @pmd is hugetlb related entry, that is normal - * hugetlb entry or non-present (migration or hwpoisoned) hugetlb entry. - * Otherwise, returns 0. - */ -int pmd_huge(pmd_t pmd) -{ - return !pmd_none(pmd) && - (pmd_val(pmd) & (_PAGE_PRESENT|_PAGE_PSE)) != _PAGE_PRESENT; -} - -/* - * pud_huge() returns 1 if @pud is hugetlb related entry, that is normal - * hugetlb entry or non-present (migration or hwpoisoned) hugetlb entry. - * Otherwise, returns 0. - */ -int pud_huge(pud_t pud) -{ -#if CONFIG_PGTABLE_LEVELS > 2 - return !pud_none(pud) && - (pud_val(pud) & (_PAGE_PRESENT|_PAGE_PSE)) != _PAGE_PRESENT; -#else - return 0; -#endif -} - #ifdef CONFIG_HUGETLB_PAGE static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct hstate *h = hstate_file(file); - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; - info.flags = 0; info.length = len; info.low_limit = get_mmap_base(1); @@ -65,7 +38,6 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file, task_size_32bit() : task_size_64bit(addr > DEFAULT_MAP_WINDOW); info.align_mask = PAGE_MASK & ~huge_page_mask(h); - info.align_offset = 0; return vm_unmapped_area(&info); } @@ -74,7 +46,7 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file, unsigned long pgoff, unsigned long flags) { struct hstate *h = hstate_file(file); - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; @@ -89,7 +61,6 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file, info.high_limit += TASK_SIZE_MAX - DEFAULT_MAP_WINDOW; info.align_mask = PAGE_MASK & ~huge_page_mask(h); - info.align_offset = 0; addr = vm_unmapped_area(&info); /* @@ -141,7 +112,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, } get_unmapped_area: - if (mm->get_unmapped_area == arch_get_unmapped_area) + if (!test_bit(MMF_TOPDOWN, &mm->flags)) return hugetlb_get_unmapped_area_bottomup(file, addr, len, pgoff, flags); else diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index a51f22c90a7a..eb503f53c319 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -987,53 +987,6 @@ void __init free_initrd_mem(unsigned long start, unsigned long end) } #endif -/* - * Calculate the precise size of the DMA zone (first 16 MB of RAM), - * and pass it to the MM layer - to help it set zone watermarks more - * accurately. - * - * Done on 64-bit systems only for the time being, although 32-bit systems - * might benefit from this as well. - */ -void __init memblock_find_dma_reserve(void) -{ -#ifdef CONFIG_X86_64 - u64 nr_pages = 0, nr_free_pages = 0; - unsigned long start_pfn, end_pfn; - phys_addr_t start_addr, end_addr; - int i; - u64 u; - - /* - * Iterate over all memory ranges (free and reserved ones alike), - * to calculate the total number of pages in the first 16 MB of RAM: - */ - nr_pages = 0; - for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) { - start_pfn = min(start_pfn, MAX_DMA_PFN); - end_pfn = min(end_pfn, MAX_DMA_PFN); - - nr_pages += end_pfn - start_pfn; - } - - /* - * Iterate over free memory ranges to calculate the number of free - * pages in the DMA zone, while not counting potential partial - * pages at the beginning or the end of the range: - */ - nr_free_pages = 0; - for_each_free_mem_range(u, NUMA_NO_NODE, MEMBLOCK_NONE, &start_addr, &end_addr, NULL) { - start_pfn = min_t(unsigned long, PFN_UP(start_addr), MAX_DMA_PFN); - end_pfn = min_t(unsigned long, PFN_DOWN(end_addr), MAX_DMA_PFN); - - if (start_pfn < end_pfn) - nr_free_pages += end_pfn - start_pfn; - } - - set_dma_reserve(nr_pages - nr_free_pages); -#endif -} - void __init zone_sizes_init(void) { unsigned long max_zone_pfns[MAX_NR_ZONES]; diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index c90c20904a60..a2cabb1c81e1 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -129,9 +129,9 @@ static void arch_pick_mmap_base(unsigned long *base, unsigned long *legacy_base, void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) { if (mmap_is_legacy()) - mm->get_unmapped_area = arch_get_unmapped_area; + clear_bit(MMF_TOPDOWN, &mm->flags); else - mm->get_unmapped_area = arch_get_unmapped_area_topdown; + set_bit(MMF_TOPDOWN, &mm->flags); arch_pick_mmap_base(&mm->mmap_base, &mm->mmap_legacy_base, arch_rnd(mmap64_rnd_bits), task_size_64bit(0), diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c index 025fd7ea5d69..65fda406e6f2 100644 --- a/arch/x86/mm/numa_32.c +++ b/arch/x86/mm/numa_32.c @@ -24,6 +24,7 @@ #include <linux/memblock.h> #include <linux/init.h> +#include <linux/vmalloc.h> #include <asm/pgtable_areas.h> #include "numa_internal.h" diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index 36b603d0cdde..bdc2a240c2aa 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -39,6 +39,7 @@ #include <linux/pfn_t.h> #include <linux/slab.h> #include <linux/mm.h> +#include <linux/highmem.h> #include <linux/fs.h> #include <linux/rbtree.h> @@ -947,6 +948,29 @@ static void free_pfn_range(u64 paddr, unsigned long size) memtype_free(paddr, paddr + size); } +static int follow_phys(struct vm_area_struct *vma, unsigned long *prot, + resource_size_t *phys) +{ + pte_t *ptep, pte; + spinlock_t *ptl; + + if (follow_pte(vma, vma->vm_start, &ptep, &ptl)) + return -EINVAL; + + pte = ptep_get(ptep); + + /* Never return PFNs of anon folios in COW mappings. */ + if (vm_normal_folio(vma, vma->vm_start, pte)) { + pte_unmap_unlock(ptep, ptl); + return -EINVAL; + } + + *prot = pgprot_val(pte_pgprot(pte)); + *phys = (resource_size_t)pte_pfn(pte) << PAGE_SHIFT; + pte_unmap_unlock(ptep, ptl); + return 0; +} + static int get_pat_info(struct vm_area_struct *vma, resource_size_t *paddr, pgprot_t *pgprot) { @@ -964,7 +988,7 @@ static int get_pat_info(struct vm_area_struct *vma, resource_size_t *paddr, * detect the PFN. If we need the cachemode as well, we're out of luck * for now and have to fail fork(). */ - if (!follow_phys(vma, vma->vm_start, 0, &prot, paddr)) { + if (!follow_phys(vma, &prot, paddr)) { if (pgprot) *pgprot = __pgprot(prot); return 0; diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index d007591b8059..93e54ba91fbf 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -631,6 +631,8 @@ int pmdp_clear_flush_young(struct vm_area_struct *vma, pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { + VM_WARN_ON_ONCE(!pmd_present(*pmdp)); + /* * No flush is necessary. Once an invalid PTE is established, the PTE's * access and dirty bits cannot be updated. @@ -731,7 +733,7 @@ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) return 0; /* Bail out if we are we on a populated non-leaf entry: */ - if (pud_present(*pud) && !pud_huge(*pud)) + if (pud_present(*pud) && !pud_leaf(*pud)) return 0; set_pte((pte_t *)pud, pfn_pte( @@ -760,7 +762,7 @@ int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) } /* Bail out if we are we on a populated non-leaf entry: */ - if (pmd_present(*pmd) && !pmd_huge(*pmd)) + if (pmd_present(*pmd) && !pmd_leaf(*pmd)) return 0; set_pte((pte_t *)pmd, pfn_pte( diff --git a/arch/xtensa/mm/cache.c b/arch/xtensa/mm/cache.c index 7ec66a79f472..23be0e7516ce 100644 --- a/arch/xtensa/mm/cache.c +++ b/arch/xtensa/mm/cache.c @@ -87,12 +87,13 @@ static inline void *coherent_kvaddr(struct page *page, unsigned long base, void clear_user_highpage(struct page *page, unsigned long vaddr) { + struct folio *folio = page_folio(page); unsigned long paddr; void *kvaddr = coherent_kvaddr(page, TLBTEMP_BASE_1, vaddr, &paddr); preempt_disable(); kmap_invalidate_coherent(page, vaddr); - set_bit(PG_arch_1, &page->flags); + set_bit(PG_arch_1, folio_flags(folio, 0)); clear_page_alias(kvaddr, paddr); preempt_enable(); } @@ -101,6 +102,7 @@ EXPORT_SYMBOL(clear_user_highpage); void copy_user_highpage(struct page *dst, struct page *src, unsigned long vaddr, struct vm_area_struct *vma) { + struct folio *folio = page_folio(dst); unsigned long dst_paddr, src_paddr; void *dst_vaddr = coherent_kvaddr(dst, TLBTEMP_BASE_1, vaddr, &dst_paddr); @@ -109,7 +111,7 @@ void copy_user_highpage(struct page *dst, struct page *src, preempt_disable(); kmap_invalidate_coherent(dst, vaddr); - set_bit(PG_arch_1, &dst->flags); + set_bit(PG_arch_1, folio_flags(folio, 0)); copy_page_alias(dst_vaddr, src_vaddr, dst_paddr, src_paddr); preempt_enable(); } diff --git a/arch/xtensa/mm/tlb.c b/arch/xtensa/mm/tlb.c index 4f974b74883c..d8b60d6e50a8 100644 --- a/arch/xtensa/mm/tlb.c +++ b/arch/xtensa/mm/tlb.c @@ -256,12 +256,13 @@ static int check_tlb_entry(unsigned w, unsigned e, bool dtlb) dtlb ? 'D' : 'I', w, e, r0, r1, pte); if (pte == 0 || !pte_present(__pte(pte))) { struct page *p = pfn_to_page(r1 >> PAGE_SHIFT); - pr_err("page refcount: %d, mapcount: %d\n", - page_count(p), - page_mapcount(p)); - if (!page_count(p)) + struct folio *f = page_folio(p); + + pr_err("folio refcount: %d, mapcount: %d\n", + folio_ref_count(f), folio_mapcount(f)); + if (!folio_ref_count(f)) rc |= TLB_INSANE; - else if (page_mapcount(p)) + else if (folio_mapped(f)) rc |= TLB_SUSPICIOUS; } else { rc |= TLB_INSANE; |