// SPDX-License-Identifier: GPL-2.0 /* * linux/mm/madvise.c * * Copyright (C) 1999 Linus Torvalds * Copyright (C) 2002 Christoph Hellwig */ #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/syscalls.h> #include <linux/mempolicy.h> #include <linux/page-isolation.h> #include <linux/page_idle.h> #include <linux/userfaultfd_k.h> #include <linux/hugetlb.h> #include <linux/falloc.h> #include <linux/fadvise.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/mm_inline.h> #include <linux/string.h> #include <linux/uio.h> #include <linux/ksm.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/pagewalk.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/shmem_fs.h> #include <linux/mmu_notifier.h> #include <asm/tlb.h> #include "internal.h" #include "swap.h" struct madvise_walk_private { … }; /* * Any behaviour which results in changes to the vma->vm_flags needs to * take mmap_lock for writing. Others, which simply traverse vmas, need * to only take it for reading. */ static int madvise_need_mmap_write(int behavior) { … } #ifdef CONFIG_ANON_VMA_NAME struct anon_vma_name *anon_vma_name_alloc(const char *name) { … } void anon_vma_name_free(struct kref *kref) { … } struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma) { … } /* mmap_lock should be write-locked */ static int replace_anon_vma_name(struct vm_area_struct *vma, struct anon_vma_name *anon_name) { … } #else /* CONFIG_ANON_VMA_NAME */ static int replace_anon_vma_name(struct vm_area_struct *vma, struct anon_vma_name *anon_name) { if (anon_name) return -EINVAL; return 0; } #endif /* CONFIG_ANON_VMA_NAME */ /* * Update the vm_flags on region of a vma, splitting it or merging it as * necessary. Must be called with mmap_lock held for writing; * Caller should ensure anon_name stability by raising its refcount even when * anon_name belongs to a valid vma because this function might free that vma. */ static int madvise_update_vma(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, unsigned long new_flags, struct anon_vma_name *anon_name) { … } #ifdef CONFIG_SWAP static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start, unsigned long end, struct mm_walk *walk) { … } static const struct mm_walk_ops swapin_walk_ops = …; static void shmem_swapin_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct address_space *mapping) { … } #endif /* CONFIG_SWAP */ /* * Schedule all required I/O operations. Do not wait for completion. */ static long madvise_willneed(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end) { … } static inline bool can_do_file_pageout(struct vm_area_struct *vma) { … } static inline int madvise_folio_pte_batch(unsigned long addr, unsigned long end, struct folio *folio, pte_t *ptep, pte_t pte, bool *any_young, bool *any_dirty) { … } static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { … } static const struct mm_walk_ops cold_walk_ops = …; static void madvise_cold_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long end) { … } static inline bool can_madv_lru_vma(struct vm_area_struct *vma) { … } static long madvise_cold(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start_addr, unsigned long end_addr) { … } static void madvise_pageout_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long end) { … } static long madvise_pageout(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start_addr, unsigned long end_addr) { … } static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { … } static const struct mm_walk_ops madvise_free_walk_ops = …; static int madvise_free_single_vma(struct vm_area_struct *vma, unsigned long start_addr, unsigned long end_addr) { … } /* * Application no longer needs these pages. If the pages are dirty, * it's OK to just throw them away. The app will be more careful about * data it wants to keep. Be sure to free swap resources too. The * zap_page_range_single call sets things up for shrink_active_list to actually * free these pages later if no one else has touched them in the meantime, * although we could add these pages to a global reuse list for * shrink_active_list to pick up before reclaiming other pages. * * NB: This interface discards data rather than pushes it out to swap, * as some implementations do. This has performance implications for * applications like large transactional databases which want to discard * pages in anonymous maps after committing to backing store the data * that was kept in them. There is no reason to write this data out to * the swap area if the application is discarding it. * * An interface that causes the system to free clean pages and flush * dirty pages is already available as msync(MS_INVALIDATE). */ static long madvise_dontneed_single_vma(struct vm_area_struct *vma, unsigned long start, unsigned long end) { … } static bool madvise_dontneed_free_valid_vma(struct vm_area_struct *vma, unsigned long start, unsigned long *end, int behavior) { … } static long madvise_dontneed_free(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, int behavior) { … } static long madvise_populate(struct mm_struct *mm, unsigned long start, unsigned long end, int behavior) { … } /* * Application wants to free up the pages and associated backing store. * This is effectively punching a hole into the middle of a file. */ static long madvise_remove(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end) { … } /* * Apply an madvise behavior to a region of a vma. madvise_update_vma * will handle splitting a vm area into separate areas, each area with its own * behavior. */ static int madvise_vma_behavior(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, unsigned long behavior) { … } #ifdef CONFIG_MEMORY_FAILURE /* * Error injection support for memory error handling. */ static int madvise_inject_error(int behavior, unsigned long start, unsigned long end) { … } #endif static bool madvise_behavior_valid(int behavior) { … } static bool process_madvise_behavior_valid(int behavior) { … } /* * Walk the vmas in range [start,end), and call the visit function on each one. * The visit function will get start and end parameters that cover the overlap * between the current vma and the original range. Any unmapped regions in the * original range will result in this function returning -ENOMEM while still * calling the visit function on all of the existing vmas in the range. * Must be called with the mmap_lock held for reading or writing. */ static int madvise_walk_vmas(struct mm_struct *mm, unsigned long start, unsigned long end, unsigned long arg, int (*visit)(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, unsigned long arg)) { … } #ifdef CONFIG_ANON_VMA_NAME static int madvise_vma_anon_name(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, unsigned long anon_name) { … } int madvise_set_anon_name(struct mm_struct *mm, unsigned long start, unsigned long len_in, struct anon_vma_name *anon_name) { … } #endif /* CONFIG_ANON_VMA_NAME */ /* * The madvise(2) system call. * * Applications can use madvise() to advise the kernel how it should * handle paging I/O in this VM area. The idea is to help the kernel * use appropriate read-ahead and caching techniques. The information * provided is advisory only, and can be safely disregarded by the * kernel without affecting the correct operation of the application. * * behavior values: * MADV_NORMAL - the default behavior is to read clusters. This * results in some read-ahead and read-behind. * MADV_RANDOM - the system should read the minimum amount of data * on any access, since it is unlikely that the appli- * cation will need more than what it asks for. * MADV_SEQUENTIAL - pages in the given range will probably be accessed * once, so they can be aggressively read ahead, and * can be freed soon after they are accessed. * MADV_WILLNEED - the application is notifying the system to read * some pages ahead. * MADV_DONTNEED - the application is finished with the given range, * so the kernel can free resources associated with it. * MADV_FREE - the application marks pages in the given range as lazy free, * where actual purges are postponed until memory pressure happens. * MADV_REMOVE - the application wants to free up the given range of * pages and associated backing store. * MADV_DONTFORK - omit this area from child's address space when forking: * typically, to avoid COWing pages pinned by get_user_pages(). * MADV_DOFORK - cancel MADV_DONTFORK: no longer omit this area when forking. * MADV_WIPEONFORK - present the child process with zero-filled memory in this * range after a fork. * MADV_KEEPONFORK - undo the effect of MADV_WIPEONFORK * MADV_HWPOISON - trigger memory error handler as if the given memory range * were corrupted by unrecoverable hardware memory failure. * MADV_SOFT_OFFLINE - try to soft-offline the given range of memory. * MADV_MERGEABLE - the application recommends that KSM try to merge pages in * this area with pages of identical content from other such areas. * MADV_UNMERGEABLE- cancel MADV_MERGEABLE: no longer merge pages with others. * MADV_HUGEPAGE - the application wants to back the given range by transparent * huge pages in the future. Existing pages might be coalesced and * new pages might be allocated as THP. * MADV_NOHUGEPAGE - mark the given range as not worth being backed by * transparent huge pages so the existing pages will not be * coalesced into THP and new pages will not be allocated as THP. * MADV_COLLAPSE - synchronously coalesce pages into new THP. * MADV_DONTDUMP - the application wants to prevent pages in the given range * from being included in its core dump. * MADV_DODUMP - cancel MADV_DONTDUMP: no longer exclude from core dump. * MADV_COLD - the application is not expected to use this memory soon, * deactivate pages in this range so that they can be reclaimed * easily if memory pressure happens. * MADV_PAGEOUT - the application is not expected to use this memory soon, * page out the pages in this range immediately. * MADV_POPULATE_READ - populate (prefault) page tables readable by * triggering read faults if required * MADV_POPULATE_WRITE - populate (prefault) page tables writable by * triggering write faults if required * * return values: * zero - success * -EINVAL - start + len < 0, start is not page-aligned, * "behavior" is not a valid value, or application * is attempting to release locked or shared pages, * or the specified address range includes file, Huge TLB, * MAP_SHARED or VMPFNMAP range. * -ENOMEM - addresses in the specified range are not currently * mapped, or are outside the AS of the process. * -EIO - an I/O error occurred while paging in data. * -EBADF - map exists, but area maps something that isn't a file. * -EAGAIN - a kernel resource was temporarily unavailable. * -EPERM - memory is sealed. */ int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior) { … } SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior) { … } SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec, size_t, vlen, int, behavior, unsigned int, flags) { … }
Codebase Browser
linux