/* * mm/rmap.c - physical to virtual reverse mappings * * Copyright 2001, Rik van Riel <[email protected]> * Released under the General Public License (GPL). * * Simple, low overhead reverse mapping scheme. * Please try to keep this thing as modular as possible. * * Provides methods for unmapping each kind of mapped page: * the anon methods track anonymous pages, and * the file methods track pages belonging to an inode. * * Original design by Rik van Riel <[email protected]> 2001 * File methods by Dave McCracken <[email protected]> 2003, 2004 * Anonymous methods by Andrea Arcangeli <[email protected]> 2004 * Contributions by Hugh Dickins 2003, 2004 */ /* * Lock ordering in mm: * * inode->i_rwsem (while writing or truncating, not reading or faulting) * mm->mmap_lock * mapping->invalidate_lock (in filemap_fault) * folio_lock * hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share, see hugetlbfs below) * vma_start_write * mapping->i_mmap_rwsem * anon_vma->rwsem * mm->page_table_lock or pte_lock * swap_lock (in swap_duplicate, swap_info_get) * mmlist_lock (in mmput, drain_mmlist and others) * mapping->private_lock (in block_dirty_folio) * folio_lock_memcg move_lock (in block_dirty_folio) * i_pages lock (widely used) * lruvec->lru_lock (in folio_lruvec_lock_irq) * inode->i_lock (in set_page_dirty's __mark_inode_dirty) * bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty) * sb_lock (within inode_lock in fs/fs-writeback.c) * i_pages lock (widely used, in set_page_dirty, * in arch-dependent flush_dcache_mmap_lock, * within bdi.wb->list_lock in __sync_single_inode) * * anon_vma->rwsem,mapping->i_mmap_rwsem (memory_failure, collect_procs_anon) * ->tasklist_lock * pte map lock * * hugetlbfs PageHuge() take locks in this order: * hugetlb_fault_mutex (hugetlbfs specific page fault mutex) * vma_lock (hugetlb specific lock for pmd_sharing) * mapping->i_mmap_rwsem (also used for hugetlb pmd sharing) * folio_lock */ #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> #include <linux/pagemap.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/rcupdate.h> #include <linux/export.h> #include <linux/memcontrol.h> #include <linux/mmu_notifier.h> #include <linux/migrate.h> #include <linux/hugetlb.h> #include <linux/huge_mm.h> #include <linux/backing-dev.h> #include <linux/page_idle.h> #include <linux/memremap.h> #include <linux/userfaultfd_k.h> #include <linux/mm_inline.h> #include <asm/tlbflush.h> #define CREATE_TRACE_POINTS #include <trace/events/tlb.h> #include <trace/events/migrate.h> #include "internal.h" static struct kmem_cache *anon_vma_cachep; static struct kmem_cache *anon_vma_chain_cachep; static inline struct anon_vma *anon_vma_alloc(void) { … } static inline void anon_vma_free(struct anon_vma *anon_vma) { … } static inline struct anon_vma_chain *anon_vma_chain_alloc(gfp_t gfp) { … } static void anon_vma_chain_free(struct anon_vma_chain *anon_vma_chain) { … } static void anon_vma_chain_link(struct vm_area_struct *vma, struct anon_vma_chain *avc, struct anon_vma *anon_vma) { … } /** * __anon_vma_prepare - attach an anon_vma to a memory region * @vma: the memory region in question * * This makes sure the memory mapping described by 'vma' has * an 'anon_vma' attached to it, so that we can associate the * anonymous pages mapped into it with that anon_vma. * * The common case will be that we already have one, which * is handled inline by anon_vma_prepare(). But if * not we either need to find an adjacent mapping that we * can re-use the anon_vma from (very common when the only * reason for splitting a vma has been mprotect()), or we * allocate a new one. * * Anon-vma allocations are very subtle, because we may have * optimistically looked up an anon_vma in folio_lock_anon_vma_read() * and that may actually touch the rwsem even in the newly * allocated vma (it depends on RCU to make sure that the * anon_vma isn't actually destroyed). * * As a result, we need to do proper anon_vma locking even * for the new allocation. At the same time, we do not want * to do any locking for the common case of already having * an anon_vma. */ int __anon_vma_prepare(struct vm_area_struct *vma) { … } /* * This is a useful helper function for locking the anon_vma root as * we traverse the vma->anon_vma_chain, looping over anon_vma's that * have the same vma. * * Such anon_vma's should have the same root, so you'd expect to see * just a single mutex_lock for the whole traversal. */ static inline struct anon_vma *lock_anon_vma_root(struct anon_vma *root, struct anon_vma *anon_vma) { … } static inline void unlock_anon_vma_root(struct anon_vma *root) { … } /* * Attach the anon_vmas from src to dst. * Returns 0 on success, -ENOMEM on failure. * * anon_vma_clone() is called by vma_expand(), vma_merge(), __split_vma(), * copy_vma() and anon_vma_fork(). The first four want an exact copy of src, * while the last one, anon_vma_fork(), may try to reuse an existing anon_vma to * prevent endless growth of anon_vma. Since dst->anon_vma is set to NULL before * call, we can identify this case by checking (!dst->anon_vma && * src->anon_vma). * * If (!dst->anon_vma && src->anon_vma) is true, this function tries to find * and reuse existing anon_vma which has no vmas and only one child anon_vma. * This prevents degradation of anon_vma hierarchy to endless linear chain in * case of constantly forking task. On the other hand, an anon_vma with more * than one child isn't reused even if there was no alive vma, thus rmap * walker has a good chance of avoiding scanning the whole hierarchy when it * searches where page is mapped. */ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src) { … } /* * Attach vma to its own anon_vma, as well as to the anon_vmas that * the corresponding VMA in the parent process is attached to. * Returns 0 on success, non-zero on failure. */ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) { … } void unlink_anon_vmas(struct vm_area_struct *vma) { … } static void anon_vma_ctor(void *data) { … } void __init anon_vma_init(void) { … } /* * Getting a lock on a stable anon_vma from a page off the LRU is tricky! * * Since there is no serialization what so ever against folio_remove_rmap_*() * the best this function can do is return a refcount increased anon_vma * that might have been relevant to this page. * * The page might have been remapped to a different anon_vma or the anon_vma * returned may already be freed (and even reused). * * In case it was remapped to a different anon_vma, the new anon_vma will be a * child of the old anon_vma, and the anon_vma lifetime rules will therefore * ensure that any anon_vma obtained from the page will still be valid for as * long as we observe page_mapped() [ hence all those page_mapped() tests ]. * * All users of this function must be very careful when walking the anon_vma * chain and verify that the page in question is indeed mapped in it * [ something equivalent to page_mapped_in_vma() ]. * * Since anon_vma's slab is SLAB_TYPESAFE_BY_RCU and we know from * folio_remove_rmap_*() that the anon_vma pointer from page->mapping is valid * if there is a mapcount, we can dereference the anon_vma after observing * those. * * NOTE: the caller should normally hold folio lock when calling this. If * not, the caller needs to double check the anon_vma didn't change after * taking the anon_vma lock for either read or write (UFFDIO_MOVE can modify it * concurrently without folio lock protection). See folio_lock_anon_vma_read() * which has already covered that, and comment above remap_pages(). */ struct anon_vma *folio_get_anon_vma(struct folio *folio) { … } /* * Similar to folio_get_anon_vma() except it locks the anon_vma. * * Its a little more complex as it tries to keep the fast path to a single * atomic op -- the trylock. If we fail the trylock, we fall back to getting a * reference like with folio_get_anon_vma() and then block on the mutex * on !rwc->try_lock case. */ struct anon_vma *folio_lock_anon_vma_read(struct folio *folio, struct rmap_walk_control *rwc) { … } #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH /* * Flush TLB entries for recently unmapped pages from remote CPUs. It is * important if a PTE was dirty when it was unmapped that it's flushed * before any IO is initiated on the page to prevent lost writes. Similarly, * it must be flushed before freeing to prevent data leakage. */ void try_to_unmap_flush(void) { … } /* Flush iff there are potentially writable TLB entries that can race with IO */ void try_to_unmap_flush_dirty(void) { … } /* * Bits 0-14 of mm->tlb_flush_batched record pending generations. * Bits 16-30 of mm->tlb_flush_batched bit record flushed generations. */ #define TLB_FLUSH_BATCH_FLUSHED_SHIFT … #define TLB_FLUSH_BATCH_PENDING_MASK … #define TLB_FLUSH_BATCH_PENDING_LARGE … static void set_tlb_ubc_flush_pending(struct mm_struct *mm, pte_t pteval, unsigned long uaddr) { … } /* * Returns true if the TLB flush should be deferred to the end of a batch of * unmap operations to reduce IPIs. */ static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) { … } /* * Reclaim unmaps pages under the PTL but do not flush the TLB prior to * releasing the PTL if TLB flushes are batched. It's possible for a parallel * operation such as mprotect or munmap to race between reclaim unmapping * the page and flushing the page. If this race occurs, it potentially allows * access to data via a stale TLB entry. Tracking all mm's that have TLB * batching in flight would be expensive during reclaim so instead track * whether TLB batching occurred in the past and if so then do a flush here * if required. This will cost one additional flush per reclaim cycle paid * by the first operation at risk such as mprotect and mumap. * * This must be called under the PTL so that an access to tlb_flush_batched * that is potentially a "reclaim vs mprotect/munmap/etc" race will synchronise * via the PTL. */ void flush_tlb_batched_pending(struct mm_struct *mm) { … } #else static void set_tlb_ubc_flush_pending(struct mm_struct *mm, pte_t pteval, unsigned long uaddr) { } static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) { return false; } #endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */ /* * At what user virtual address is page expected in vma? * Caller should check the page is actually part of the vma. */ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) { … } /* * Returns the actual pmd_t* where we expect 'address' to be mapped from, or * NULL if it doesn't exist. No guarantees / checks on what the pmd_t* * represents. */ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address) { … } struct folio_referenced_arg { … }; /* * arg: folio_referenced_arg will be passed */ static bool folio_referenced_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { … } static bool invalid_folio_referenced_vma(struct vm_area_struct *vma, void *arg) { … } /** * folio_referenced() - Test if the folio was referenced. * @folio: The folio to test. * @is_locked: Caller holds lock on the folio. * @memcg: target memory cgroup * @vm_flags: A combination of all the vma->vm_flags which referenced the folio. * * Quick test_and_clear_referenced for all mappings of a folio, * * Return: The number of mappings which referenced the folio. Return -1 if * the function bailed out due to rmap lock contention. */ int folio_referenced(struct folio *folio, int is_locked, struct mem_cgroup *memcg, unsigned long *vm_flags) { … } static int page_vma_mkclean_one(struct page_vma_mapped_walk *pvmw) { … } static bool page_mkclean_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { … } static bool invalid_mkclean_vma(struct vm_area_struct *vma, void *arg) { … } int folio_mkclean(struct folio *folio) { … } EXPORT_SYMBOL_GPL(…); /** * pfn_mkclean_range - Cleans the PTEs (including PMDs) mapped with range of * [@pfn, @pfn + @nr_pages) at the specific offset (@pgoff) * within the @vma of shared mappings. And since clean PTEs * should also be readonly, write protects them too. * @pfn: start pfn. * @nr_pages: number of physically contiguous pages srarting with @pfn. * @pgoff: page offset that the @pfn mapped with. * @vma: vma that @pfn mapped within. * * Returns the number of cleaned PTEs (including PMDs). */ int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff, struct vm_area_struct *vma) { … } static __always_inline unsigned int __folio_add_rmap(struct folio *folio, struct page *page, int nr_pages, enum rmap_level level, int *nr_pmdmapped) { … } /** * folio_move_anon_rmap - move a folio to our anon_vma * @folio: The folio to move to our anon_vma * @vma: The vma the folio belongs to * * When a folio belongs exclusively to one process after a COW event, * that folio can be moved into the anon_vma that belongs to just that * process, so the rmap code will not search the parent or sibling processes. */ void folio_move_anon_rmap(struct folio *folio, struct vm_area_struct *vma) { … } /** * __folio_set_anon - set up a new anonymous rmap for a folio * @folio: The folio to set up the new anonymous rmap for. * @vma: VM area to add the folio to. * @address: User virtual address of the mapping * @exclusive: Whether the folio is exclusive to the process. */ static void __folio_set_anon(struct folio *folio, struct vm_area_struct *vma, unsigned long address, bool exclusive) { … } /** * __page_check_anon_rmap - sanity check anonymous rmap addition * @folio: The folio containing @page. * @page: the page to check the mapping of * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped */ static void __page_check_anon_rmap(struct folio *folio, struct page *page, struct vm_area_struct *vma, unsigned long address) { … } static void __folio_mod_stat(struct folio *folio, int nr, int nr_pmdmapped) { … } static __always_inline void __folio_add_anon_rmap(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, unsigned long address, rmap_t flags, enum rmap_level level) { … } /** * folio_add_anon_rmap_ptes - add PTE mappings to a page range of an anon folio * @folio: The folio to add the mappings to * @page: The first page to add * @nr_pages: The number of pages which will be mapped * @vma: The vm area in which the mappings are added * @address: The user virtual address of the first page to map * @flags: The rmap flags * * The page range of folio is defined by [first_page, first_page + nr_pages) * * The caller needs to hold the page table lock, and the page must be locked in * the anon_vma case: to serialize mapping,index checking after setting, * and to ensure that an anon folio is not being upgraded racily to a KSM folio * (but KSM folios are never downgraded). */ void folio_add_anon_rmap_ptes(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { … } /** * folio_add_anon_rmap_pmd - add a PMD mapping to a page range of an anon folio * @folio: The folio to add the mapping to * @page: The first page to add * @vma: The vm area in which the mapping is added * @address: The user virtual address of the first page to map * @flags: The rmap flags * * The page range of folio is defined by [first_page, first_page + HPAGE_PMD_NR) * * The caller needs to hold the page table lock, and the page must be locked in * the anon_vma case: to serialize mapping,index checking after setting. */ void folio_add_anon_rmap_pmd(struct folio *folio, struct page *page, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { … } /** * folio_add_new_anon_rmap - Add mapping to a new anonymous folio. * @folio: The folio to add the mapping to. * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped * @flags: The rmap flags * * Like folio_add_anon_rmap_*() but must only be called on *new* folios. * This means the inc-and-test can be bypassed. * The folio doesn't necessarily need to be locked while it's exclusive * unless two threads map it concurrently. However, the folio must be * locked if it's shared. * * If the folio is pmd-mappable, it is accounted as a THP. */ void folio_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { … } static __always_inline void __folio_add_file_rmap(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, enum rmap_level level) { … } /** * folio_add_file_rmap_ptes - add PTE mappings to a page range of a folio * @folio: The folio to add the mappings to * @page: The first page to add * @nr_pages: The number of pages that will be mapped using PTEs * @vma: The vm area in which the mappings are added * * The page range of the folio is defined by [page, page + nr_pages) * * The caller needs to hold the page table lock. */ void folio_add_file_rmap_ptes(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma) { … } /** * folio_add_file_rmap_pmd - add a PMD mapping to a page range of a folio * @folio: The folio to add the mapping to * @page: The first page to add * @vma: The vm area in which the mapping is added * * The page range of the folio is defined by [page, page + HPAGE_PMD_NR) * * The caller needs to hold the page table lock. */ void folio_add_file_rmap_pmd(struct folio *folio, struct page *page, struct vm_area_struct *vma) { … } static __always_inline void __folio_remove_rmap(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, enum rmap_level level) { … } /** * folio_remove_rmap_ptes - remove PTE mappings from a page range of a folio * @folio: The folio to remove the mappings from * @page: The first page to remove * @nr_pages: The number of pages that will be removed from the mapping * @vma: The vm area from which the mappings are removed * * The page range of the folio is defined by [page, page + nr_pages) * * The caller needs to hold the page table lock. */ void folio_remove_rmap_ptes(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma) { … } /** * folio_remove_rmap_pmd - remove a PMD mapping from a page range of a folio * @folio: The folio to remove the mapping from * @page: The first page to remove * @vma: The vm area from which the mapping is removed * * The page range of the folio is defined by [page, page + HPAGE_PMD_NR) * * The caller needs to hold the page table lock. */ void folio_remove_rmap_pmd(struct folio *folio, struct page *page, struct vm_area_struct *vma) { … } /* * @arg: enum ttu_flags will be passed to this argument */ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { … } static bool invalid_migration_vma(struct vm_area_struct *vma, void *arg) { … } static int folio_not_mapped(struct folio *folio) { … } /** * try_to_unmap - Try to remove all page table mappings to a folio. * @folio: The folio to unmap. * @flags: action and flags * * Tries to remove all the page table entries which are mapping this * folio. It is the caller's responsibility to check if the folio is * still mapped if needed (use TTU_SYNC to prevent accounting races). * * Context: Caller must hold the folio lock. */ void try_to_unmap(struct folio *folio, enum ttu_flags flags) { … } /* * @arg: enum ttu_flags will be passed to this argument. * * If TTU_SPLIT_HUGE_PMD is specified any PMD mappings will be split into PTEs * containing migration entries. */ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { … } /** * try_to_migrate - try to replace all page table mappings with swap entries * @folio: the folio to replace page table entries for * @flags: action and flags * * Tries to remove all the page table entries which are mapping this folio and * replace them with special swap entries. Caller must hold the folio lock. */ void try_to_migrate(struct folio *folio, enum ttu_flags flags) { … } #ifdef CONFIG_DEVICE_PRIVATE struct make_exclusive_args { … }; static bool page_make_device_exclusive_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *priv) { … } /** * folio_make_device_exclusive - Mark the folio exclusively owned by a device. * @folio: The folio to replace page table entries for. * @mm: The mm_struct where the folio is expected to be mapped. * @address: Address where the folio is expected to be mapped. * @owner: passed to MMU_NOTIFY_EXCLUSIVE range notifier callbacks * * Tries to remove all the page table entries which are mapping this * folio and replace them with special device exclusive swap entries to * grant a device exclusive access to the folio. * * Context: Caller must hold the folio lock. * Return: false if the page is still mapped, or if it could not be unmapped * from the expected address. Otherwise returns true (success). */ static bool folio_make_device_exclusive(struct folio *folio, struct mm_struct *mm, unsigned long address, void *owner) { … } /** * make_device_exclusive_range() - Mark a range for exclusive use by a device * @mm: mm_struct of associated target process * @start: start of the region to mark for exclusive device access * @end: end address of region * @pages: returns the pages which were successfully marked for exclusive access * @owner: passed to MMU_NOTIFY_EXCLUSIVE range notifier to allow filtering * * Returns: number of pages found in the range by GUP. A page is marked for * exclusive access only if the page pointer is non-NULL. * * This function finds ptes mapping page(s) to the given address range, locks * them and replaces mappings with special swap entries preventing userspace CPU * access. On fault these entries are replaced with the original mapping after * calling MMU notifiers. * * A driver using this to program access from a device must use a mmu notifier * critical section to hold a device specific lock during programming. Once * programming is complete it should drop the page lock and reference after * which point CPU access to the page will revoke the exclusive access. */ int make_device_exclusive_range(struct mm_struct *mm, unsigned long start, unsigned long end, struct page **pages, void *owner) { … } EXPORT_SYMBOL_GPL(…); #endif void __put_anon_vma(struct anon_vma *anon_vma) { … } static struct anon_vma *rmap_walk_anon_lock(struct folio *folio, struct rmap_walk_control *rwc) { … } /* * rmap_walk_anon - do something to anonymous page using the object-based * rmap method * @folio: the folio to be handled * @rwc: control variable according to each walk type * @locked: caller holds relevant rmap lock * * Find all the mappings of a folio using the mapping pointer and the vma * chains contained in the anon_vma struct it points to. */ static void rmap_walk_anon(struct folio *folio, struct rmap_walk_control *rwc, bool locked) { … } /* * rmap_walk_file - do something to file page using the object-based rmap method * @folio: the folio to be handled * @rwc: control variable according to each walk type * @locked: caller holds relevant rmap lock * * Find all the mappings of a folio using the mapping pointer and the vma chains * contained in the address_space struct it points to. */ static void rmap_walk_file(struct folio *folio, struct rmap_walk_control *rwc, bool locked) { … } void rmap_walk(struct folio *folio, struct rmap_walk_control *rwc) { … } /* Like rmap_walk, but caller holds relevant rmap lock */ void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc) { … } #ifdef CONFIG_HUGETLB_PAGE /* * The following two functions are for anonymous (private mapped) hugepages. * Unlike common anonymous pages, anonymous hugepages have no accounting code * and no lru code, because we handle hugepages differently from common pages. */ void hugetlb_add_anon_rmap(struct folio *folio, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { … } void hugetlb_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma, unsigned long address) { … } #endif /* CONFIG_HUGETLB_PAGE */