diff options
Diffstat (limited to 'include/linux/mm.h')
| -rw-r--r-- | include/linux/mm.h | 673 |
1 files changed, 314 insertions, 359 deletions
diff --git a/include/linux/mm.h b/include/linux/mm.h index b1c3db9cf355..0ef2ba0c667a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -12,6 +12,7 @@ #include <linux/rbtree.h> #include <linux/atomic.h> #include <linux/debug_locks.h> +#include <linux/compiler.h> #include <linux/mm_types.h> #include <linux/mmap_lock.h> #include <linux/range.h> @@ -32,6 +33,7 @@ #include <linux/memremap.h> #include <linux/slab.h> #include <linux/cacheinfo.h> +#include <linux/rcuwait.h> struct mempolicy; struct anon_vma; @@ -40,22 +42,10 @@ struct user_struct; struct pt_regs; struct folio_batch; -extern int sysctl_page_lock_unfairness; - +void arch_mm_preinit(void); void mm_core_init(void); void init_mm_internals(void); -#ifndef CONFIG_NUMA /* Don't use mapnrs, do it properly */ -extern unsigned long max_mapnr; - -static inline void set_max_mapnr(unsigned long limit) -{ - max_mapnr = limit; -} -#else -static inline void set_max_mapnr(unsigned long limit) { } -#endif - extern atomic_long_t _totalram_pages; static inline unsigned long totalram_pages(void) { @@ -78,8 +68,6 @@ static inline void totalram_pages_add(long count) } extern void * high_memory; -extern int page_cluster; -extern const int page_cluster_max; #ifdef CONFIG_SYSCTL extern int sysctl_legacy_va_layout; @@ -209,17 +197,6 @@ extern int sysctl_max_map_count; extern unsigned long sysctl_user_reserve_kbytes; extern unsigned long sysctl_admin_reserve_kbytes; -extern int sysctl_overcommit_memory; -extern int sysctl_overcommit_ratio; -extern unsigned long sysctl_overcommit_kbytes; - -int overcommit_ratio_handler(const struct ctl_table *, int, void *, size_t *, - loff_t *); -int overcommit_kbytes_handler(const struct ctl_table *, int, void *, size_t *, - loff_t *); -int overcommit_policy_handler(const struct ctl_table *, int, void *, size_t *, - loff_t *); - #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n)) #define folio_page_idx(folio, p) (page_to_pfn(p) - folio_pfn(folio)) @@ -257,8 +234,6 @@ void setup_initial_init_mm(void *start_code, void *end_code, struct vm_area_struct *vm_area_alloc(struct mm_struct *); struct vm_area_struct *vm_area_dup(struct vm_area_struct *); void vm_area_free(struct vm_area_struct *); -/* Use only if VMA has no other users */ -void __vm_area_free(struct vm_area_struct *vma); #ifndef CONFIG_MMU extern struct rb_root nommu_region_tree; @@ -382,9 +357,7 @@ extern unsigned int kobjsize(const void *objp); # define VM_SHADOW_STACK VM_NONE #endif -#if defined(CONFIG_X86) -# define VM_PAT VM_ARCH_1 /* PAT reserves whole VMA at once (x86) */ -#elif defined(CONFIG_PPC64) +#if defined(CONFIG_PPC64) # define VM_SAO VM_ARCH_1 /* Strong Access Ordering (powerpc) */ #elif defined(CONFIG_PARISC) # define VM_GROWSUP VM_ARCH_1 @@ -411,7 +384,7 @@ extern unsigned int kobjsize(const void *objp); #endif #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR -# define VM_UFFD_MINOR_BIT 38 +# define VM_UFFD_MINOR_BIT 41 # define VM_UFFD_MINOR BIT(VM_UFFD_MINOR_BIT) /* UFFD minor faults */ #else /* !CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */ # define VM_UFFD_MINOR VM_NONE @@ -696,109 +669,11 @@ static inline void vma_numab_state_init(struct vm_area_struct *vma) {} static inline void vma_numab_state_free(struct vm_area_struct *vma) {} #endif /* CONFIG_NUMA_BALANCING */ -#ifdef CONFIG_PER_VMA_LOCK -/* - * Try to read-lock a vma. The function is allowed to occasionally yield false - * locked result to avoid performance overhead, in which case we fall back to - * using mmap_lock. The function should never yield false unlocked result. - */ -static inline bool vma_start_read(struct vm_area_struct *vma) -{ - /* - * Check before locking. A race might cause false locked result. - * We can use READ_ONCE() for the mm_lock_seq here, and don't need - * ACQUIRE semantics, because this is just a lockless check whose result - * we don't rely on for anything - the mm_lock_seq read against which we - * need ordering is below. - */ - if (READ_ONCE(vma->vm_lock_seq) == READ_ONCE(vma->vm_mm->mm_lock_seq)) - return false; - - if (unlikely(down_read_trylock(&vma->vm_lock->lock) == 0)) - return false; - - /* - * Overflow might produce false locked result. - * False unlocked result is impossible because we modify and check - * vma->vm_lock_seq under vma->vm_lock protection and mm->mm_lock_seq - * modification invalidates all existing locks. - * - * We must use ACQUIRE semantics for the mm_lock_seq so that if we are - * racing with vma_end_write_all(), we only start reading from the VMA - * after it has been unlocked. - * This pairs with RELEASE semantics in vma_end_write_all(). - */ - if (unlikely(vma->vm_lock_seq == smp_load_acquire(&vma->vm_mm->mm_lock_seq))) { - up_read(&vma->vm_lock->lock); - return false; - } - return true; -} - -static inline void vma_end_read(struct vm_area_struct *vma) -{ - rcu_read_lock(); /* keeps vma alive till the end of up_read */ - up_read(&vma->vm_lock->lock); - rcu_read_unlock(); -} - -/* WARNING! Can only be used if mmap_lock is expected to be write-locked */ -static bool __is_vma_write_locked(struct vm_area_struct *vma, int *mm_lock_seq) -{ - mmap_assert_write_locked(vma->vm_mm); - - /* - * current task is holding mmap_write_lock, both vma->vm_lock_seq and - * mm->mm_lock_seq can't be concurrently modified. - */ - *mm_lock_seq = vma->vm_mm->mm_lock_seq; - return (vma->vm_lock_seq == *mm_lock_seq); -} - /* - * Begin writing to a VMA. - * Exclude concurrent readers under the per-VMA lock until the currently - * write-locked mmap_lock is dropped or downgraded. + * These must be here rather than mmap_lock.h as dependent on vm_fault type, + * declared in this header. */ -static inline void vma_start_write(struct vm_area_struct *vma) -{ - int mm_lock_seq; - - if (__is_vma_write_locked(vma, &mm_lock_seq)) - return; - - down_write(&vma->vm_lock->lock); - /* - * We should use WRITE_ONCE() here because we can have concurrent reads - * from the early lockless pessimistic check in vma_start_read(). - * We don't really care about the correctness of that early check, but - * we should use WRITE_ONCE() for cleanliness and to keep KCSAN happy. - */ - WRITE_ONCE(vma->vm_lock_seq, mm_lock_seq); - up_write(&vma->vm_lock->lock); -} - -static inline void vma_assert_write_locked(struct vm_area_struct *vma) -{ - int mm_lock_seq; - - VM_BUG_ON_VMA(!__is_vma_write_locked(vma, &mm_lock_seq), vma); -} - -static inline void vma_assert_locked(struct vm_area_struct *vma) -{ - if (!rwsem_is_locked(&vma->vm_lock->lock)) - vma_assert_write_locked(vma); -} - -static inline void vma_mark_detached(struct vm_area_struct *vma, bool detached) -{ - /* When detaching vma should be write-locked */ - if (detached) - vma_assert_write_locked(vma); - vma->detached = detached; -} - +#ifdef CONFIG_PER_VMA_LOCK static inline void release_fault_lock(struct vm_fault *vmf) { if (vmf->flags & FAULT_FLAG_VMA_LOCK) @@ -814,32 +689,7 @@ static inline void assert_fault_locked(struct vm_fault *vmf) else mmap_assert_locked(vmf->vma->vm_mm); } - -struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, - unsigned long address); - -#else /* CONFIG_PER_VMA_LOCK */ - -static inline bool vma_start_read(struct vm_area_struct *vma) - { return false; } -static inline void vma_end_read(struct vm_area_struct *vma) {} -static inline void vma_start_write(struct vm_area_struct *vma) {} -static inline void vma_assert_write_locked(struct vm_area_struct *vma) - { mmap_assert_write_locked(vma->vm_mm); } -static inline void vma_mark_detached(struct vm_area_struct *vma, - bool detached) {} - -static inline struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, - unsigned long address) -{ - return NULL; -} - -static inline void vma_assert_locked(struct vm_area_struct *vma) -{ - mmap_assert_locked(vma->vm_mm); -} - +#else static inline void release_fault_lock(struct vm_fault *vmf) { mmap_read_unlock(vmf->vma->vm_mm); @@ -849,23 +699,17 @@ static inline void assert_fault_locked(struct vm_fault *vmf) { mmap_assert_locked(vmf->vma->vm_mm); } - #endif /* CONFIG_PER_VMA_LOCK */ extern const struct vm_operations_struct vma_dummy_vm_ops; -/* - * WARNING: vma_init does not initialize vma->vm_lock. - * Use vm_area_alloc()/vm_area_free() if vma needs locking. - */ static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) { memset(vma, 0, sizeof(*vma)); vma->vm_mm = mm; vma->vm_ops = &vma_dummy_vm_ops; INIT_LIST_HEAD(&vma->anon_vma_chain); - vma_mark_detached(vma, false); - vma_numab_state_init(vma); + vma_lock_init(vma, false); } /* Use when VMA is not part of the VMA tree and needs no locking */ @@ -1058,6 +902,7 @@ static inline int vma_iter_bulk_store(struct vma_iterator *vmi, if (unlikely(mas_is_err(&vmi->mas))) return -ENOMEM; + vma_mark_attached(vma); return 0; } @@ -1098,6 +943,25 @@ int vma_is_stack_for_current(struct vm_area_struct *vma); struct mmu_gather; struct inode; +extern void prep_compound_page(struct page *page, unsigned int order); + +static inline unsigned int folio_large_order(const struct folio *folio) +{ + return folio->_flags_1 & 0xff; +} + +#ifdef NR_PAGES_IN_LARGE_FOLIO +static inline long folio_large_nr_pages(const struct folio *folio) +{ + return folio->_nr_pages; +} +#else +static inline long folio_large_nr_pages(const struct folio *folio) +{ + return 1L << folio_large_order(folio); +} +#endif + /* * compound_order() can be called without holding a reference, which means * that niceties like page_folio() don't work. These callers should be @@ -1111,7 +975,7 @@ static inline unsigned int compound_order(struct page *page) if (!test_bit(PG_head, &folio->flags)) return 0; - return folio->_flags_1 & 0xff; + return folio_large_order(folio); } /** @@ -1127,7 +991,24 @@ static inline unsigned int folio_order(const struct folio *folio) { if (!folio_test_large(folio)) return 0; - return folio->_flags_1 & 0xff; + return folio_large_order(folio); +} + +/** + * folio_reset_order - Reset the folio order and derived _nr_pages + * @folio: The folio. + * + * Reset the order and derived _nr_pages to 0. Must only be used in the + * process of splitting large folios. + */ +static inline void folio_reset_order(struct folio *folio) +{ + if (WARN_ON_ONCE(!folio_test_large(folio))) + return; + folio->_flags_1 &= ~0xffUL; +#ifdef NR_PAGES_IN_LARGE_FOLIO + folio->_nr_pages = 0; +#endif } #include <linux/huge_mm.h> @@ -1220,6 +1101,8 @@ static inline int is_vmalloc_or_module_addr(const void *x) static inline int folio_entire_mapcount(const struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); + if (!IS_ENABLED(CONFIG_64BIT) && unlikely(folio_large_order(folio) == 1)) + return 0; return atomic_read(&folio->_entire_mapcount) + 1; } @@ -1352,7 +1235,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) return pte; } -vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page); +vm_fault_t do_set_pmd(struct vm_fault *vmf, struct folio *folio, struct page *page); void set_pte_range(struct vm_fault *vmf, struct folio *folio, struct page *page, unsigned int nr, unsigned long addr); @@ -1393,9 +1276,9 @@ vm_fault_t finish_fault(struct vm_fault *vmf); * the page's disk buffers. PG_private must be set to tell the VM to call * into the filesystem to release these pages. * - * A page may belong to an inode's memory mapping. In this case, page->mapping - * is the pointer to the inode, and page->index is the file offset of the page, - * in units of PAGE_SIZE. + * A folio may belong to an inode's memory mapping. In this case, + * folio->mapping points to the inode, and folio->index is the file + * offset of the folio, in units of PAGE_SIZE. * * If pagecache pages are not associated with an inode, they are said to be * anonymous pages. These may become associated with the swapcache, and in that @@ -1419,25 +1302,6 @@ vm_fault_t finish_fault(struct vm_fault *vmf); * back into memory. */ -#if defined(CONFIG_ZONE_DEVICE) && defined(CONFIG_FS_DAX) -DECLARE_STATIC_KEY_FALSE(devmap_managed_key); - -bool __put_devmap_managed_folio_refs(struct folio *folio, int refs); -static inline bool put_devmap_managed_folio_refs(struct folio *folio, int refs) -{ - if (!static_branch_unlikely(&devmap_managed_key)) - return false; - if (!folio_is_zone_device(folio)) - return false; - return __put_devmap_managed_folio_refs(folio, refs); -} -#else /* CONFIG_ZONE_DEVICE && CONFIG_FS_DAX */ -static inline bool put_devmap_managed_folio_refs(struct folio *folio, int refs) -{ - return false; -} -#endif /* CONFIG_ZONE_DEVICE && CONFIG_FS_DAX */ - /* 127: arbitrary random number, small enough to assemble well */ #define folio_ref_zero_or_close_to_overflow(folio) \ ((unsigned int) folio_ref_count(folio) + 127u <= 127u) @@ -1458,7 +1322,10 @@ static inline void folio_get(struct folio *folio) static inline void get_page(struct page *page) { - folio_get(page_folio(page)); + struct folio *folio = page_folio(page); + if (WARN_ON_ONCE(folio_test_slab(folio))) + return; + folio_get(folio); } static inline __must_check bool try_get_page(struct page *page) @@ -1552,12 +1419,9 @@ static inline void put_page(struct page *page) { struct folio *folio = page_folio(page); - /* - * For some devmap managed pages we need to catch refcount transition - * from 2 to 1: - */ - if (put_devmap_managed_folio_refs(folio, 1)) + if (folio_test_slab(folio)) return; + folio_put(folio); } @@ -1916,6 +1780,52 @@ static inline struct folio *pfn_folio(unsigned long pfn) return page_folio(pfn_to_page(pfn)); } +#ifdef CONFIG_MMU +static inline pte_t mk_pte(struct page *page, pgprot_t pgprot) +{ + return pfn_pte(page_to_pfn(page), pgprot); +} + +/** + * folio_mk_pte - Create a PTE for this folio + * @folio: The folio to create a PTE for + * @pgprot: The page protection bits to use + * + * Create a page table entry for the first page of this folio. + * This is suitable for passing to set_ptes(). + * + * Return: A page table entry suitable for mapping this folio. + */ +static inline pte_t folio_mk_pte(struct folio *folio, pgprot_t pgprot) +{ + return pfn_pte(folio_pfn(folio), pgprot); +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +/** + * folio_mk_pmd - Create a PMD for this folio + * @folio: The folio to create a PMD for + * @pgprot: The page protection bits to use + * + * Create a page table entry for the first page of this folio. + * This is suitable for passing to set_pmd_at(). + * + * Return: A page table entry suitable for mapping this folio. + */ +static inline pmd_t folio_mk_pmd(struct folio *folio, pgprot_t pgprot) +{ + return pmd_mkhuge(pfn_pmd(folio_pfn(folio), pgprot)); +} +#endif +#endif /* CONFIG_MMU */ + +static inline bool folio_has_pincount(const struct folio *folio) +{ + if (IS_ENABLED(CONFIG_64BIT)) + return folio_test_large(folio); + return folio_order(folio) > 1; +} + /** * folio_maybe_dma_pinned - Report if a folio may be pinned for DMA. * @folio: The folio. @@ -1932,7 +1842,7 @@ static inline struct folio *pfn_folio(unsigned long pfn) * get that many refcounts, and b) all the callers of this routine are * expected to be able to deal gracefully with a false positive. * - * For large folios, the result will be exactly correct. That's because + * For most large folios, the result will be exactly correct. That's because * we have more tracking data available: the _pincount field is used * instead of the GUP_PIN_COUNTING_BIAS scheme. * @@ -1943,7 +1853,7 @@ static inline struct folio *pfn_folio(unsigned long pfn) */ static inline bool folio_maybe_dma_pinned(struct folio *folio) { - if (folio_test_large(folio)) + if (folio_has_pincount(folio)) return atomic_read(&folio->_pincount) > 0; /* @@ -2015,6 +1925,13 @@ static inline bool folio_is_longterm_pinnable(struct folio *folio) if (folio_is_device_coherent(folio)) return false; + /* + * Filesystems can only tolerate transient delays to truncate and + * hole-punch operations + */ + if (folio_is_fsdax(folio)) + return false; + /* Otherwise, non-movable zone folios can be pinned. */ return !folio_is_zone_movable(folio); @@ -2058,11 +1975,7 @@ static inline long folio_nr_pages(const struct folio *folio) { if (!folio_test_large(folio)) return 1; -#ifdef CONFIG_64BIT - return folio->_folio_nr_pages; -#else - return 1L << (folio->_flags_1 & 0xff); -#endif + return folio_large_nr_pages(folio); } /* Only hugetlbfs can allocate folios larger than MAX_ORDER */ @@ -2077,26 +1990,13 @@ static inline long folio_nr_pages(const struct folio *folio) * page. compound_nr() can be called on a tail page, and is defined to * return 1 in that case. */ -static inline unsigned long compound_nr(struct page *page) +static inline long compound_nr(struct page *page) { struct folio *folio = (struct folio *)page; if (!test_bit(PG_head, &folio->flags)) return 1; -#ifdef CONFIG_64BIT - return folio->_folio_nr_pages; -#else - return 1L << (folio->_flags_1 & 0xff); -#endif -} - -/** - * thp_nr_pages - The number of regular pages in this huge page. - * @page: The head page of a huge page. - */ -static inline int thp_nr_pages(struct page *page) -{ - return folio_nr_pages((struct folio *)page); + return folio_large_nr_pages(folio); } /** @@ -2149,23 +2049,18 @@ static inline size_t folio_size(const struct folio *folio) } /** - * folio_likely_mapped_shared - Estimate if the folio is mapped into the page - * tables of more than one MM + * folio_maybe_mapped_shared - Whether the folio is mapped into the page + * tables of more than one MM * @folio: The folio. * - * This function checks if the folio is currently mapped into more than one - * MM ("mapped shared"), or if the folio is only mapped into a single MM - * ("mapped exclusively"). + * This function checks if the folio maybe currently mapped into more than one + * MM ("maybe mapped shared"), or if the folio is certainly mapped into a single + * MM ("mapped exclusively"). * * For KSM folios, this function also returns "mapped shared" when a folio is * mapped multiple times into the same MM, because the individual page mappings * are independent. * - * As precise information is not easily available for all folios, this function - * estimates the number of MMs ("sharers") that are currently mapping a folio - * using the number of times the first page of the folio is currently mapped - * into page tables. - * * For small anonymous folios and anonymous hugetlb folios, the return * value will be exactly correct: non-KSM folios can only be mapped at most once * into an MM, and they cannot be partially mapped. KSM folios are @@ -2173,8 +2068,8 @@ static inline size_t folio_size(const struct folio *folio) * * For other folios, the result can be fuzzy: * #. For partially-mappable large folios (THP), the return value can wrongly - * indicate "mapped exclusively" (false negative) when the folio is - * only partially mapped into at least one MM. + * indicate "mapped shared" (false positive) if a folio was mapped by + * more than two MMs at one point in time. * #. For pagecache folios (including hugetlb), the return value can wrongly * indicate "mapped shared" (false positive) when two VMAs in the same MM * cover the same file range. @@ -2191,7 +2086,7 @@ static inline size_t folio_size(const struct folio *folio) * * Return: Whether the folio is estimated to be mapped into more than one MM. */ -static inline bool folio_likely_mapped_shared(struct folio *folio) +static inline bool folio_maybe_mapped_shared(struct folio *folio) { int mapcount = folio_mapcount(folio); @@ -2199,16 +2094,77 @@ static inline bool folio_likely_mapped_shared(struct folio *folio) if (!folio_test_large(folio) || unlikely(folio_test_hugetlb(folio))) return mapcount > 1; - /* A single mapping implies "mapped exclusively". */ + /* + * vm_insert_page() without CONFIG_TRANSPARENT_HUGEPAGE ... + * simply assume "mapped shared", nobody should really care + * about this for arbitrary kernel allocations. + */ + if (!IS_ENABLED(CONFIG_MM_ID)) + return true; + + /* + * A single mapping implies "mapped exclusively", even if the + * folio flag says something different: it's easier to handle this + * case here instead of on the RMAP hot path. + */ if (mapcount <= 1) return false; + return test_bit(FOLIO_MM_IDS_SHARED_BITNUM, &folio->_mm_ids); +} - /* If any page is mapped more than once we treat it "mapped shared". */ - if (folio_entire_mapcount(folio) || mapcount > folio_nr_pages(folio)) - return true; +/** + * folio_expected_ref_count - calculate the expected folio refcount + * @folio: the folio + * + * Calculate the expected folio refcount, taking references from the pagecache, + * swapcache, PG_private and page table mappings into account. Useful in + * combination with folio_ref_count() to detect unexpected references (e.g., + * GUP or other temporary references). + * + * Does currently not consider references from the LRU cache. If the folio + * was isolated from the LRU (which is the case during migration or split), + * the LRU cache does not apply. + * + * Calling this function on an unmapped folio -- !folio_mapped() -- that is + * locked will return a stable result. + * + * Calling this function on a mapped folio will not result in a stable result, + * because nothing stops additional page table mappings from coming (e.g., + * fork()) or going (e.g., munmap()). + * + * Calling this function without the folio lock will also not result in a + * stable result: for example, the folio might get dropped from the swapcache + * concurrently. + * + * However, even when called without the folio lock or on a mapped folio, + * this function can be used to detect unexpected references early (for example, + * if it makes sense to even lock the folio and unmap it). + * + * The caller must add any reference (e.g., from folio_try_get()) it might be + * holding itself to the result. + * + * Returns the expected folio refcount. + */ +static inline int folio_expected_ref_count(const struct folio *folio) +{ + const int order = folio_order(folio); + int ref_count = 0; + + if (WARN_ON_ONCE(folio_test_slab(folio))) + return 0; - /* Let's guess based on the first subpage. */ - return atomic_read(&folio->_mapcount) > 0; + if (folio_test_anon(folio)) { + /* One reference per page from the swapcache. */ + ref_count += folio_test_swapcache(folio) << order; + } else if (!((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS)) { + /* One reference per page from the pagecache. */ + ref_count += !!folio->mapping << order; + /* One reference from PG_private. */ + ref_count += folio_test_private(folio); + } + + /* One reference per page table mapping. */ + return ref_count + folio_mapcount(folio); } #ifndef HAVE_ARCH_MAKE_FOLIO_ACCESSIBLE @@ -2311,7 +2267,6 @@ static inline void clear_page_pfmemalloc(struct page *page) extern void pagefault_out_of_memory(void); #define offset_in_page(p) ((unsigned long)(p) & ~PAGE_MASK) -#define offset_in_thp(page, p) ((unsigned long)(p) & (thp_size(page) - 1)) #define offset_in_folio(folio, p) ((unsigned long)(p) & (folio_size(folio) - 1)) /* @@ -2320,6 +2275,7 @@ extern void pagefault_out_of_memory(void); struct zap_details { struct folio *single_folio; /* Locked folio to be unmapped */ bool even_cows; /* Zap COWed private pages too? */ + bool reclaim_pt; /* Need reclaim page tables? */ zap_flags_t zap_flags; /* Extra flags for zapping */ }; @@ -2416,11 +2372,13 @@ struct follow_pfnmap_args { * Outputs: * * @pfn: the PFN of the address + * @addr_mask: address mask covering pfn * @pgprot: the pgprot_t of the mapping * @writable: whether the mapping is writable * @special: whether the mapping is a special mapping (real PFN maps) */ unsigned long pfn; + unsigned long addr_mask; pgprot_t pgprot; bool writable; bool special; @@ -2485,6 +2443,11 @@ extern int access_process_vm(struct task_struct *tsk, unsigned long addr, extern int access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags); +#ifdef CONFIG_BPF_SYSCALL +extern int copy_remote_vm_str(struct task_struct *tsk, unsigned long addr, + void *buf, int len, unsigned int gup_flags); +#endif + long get_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, @@ -2548,7 +2511,7 @@ int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc, struct task_struct *task, bool bypass_rlim); struct kvec; -struct page *get_dump_page(unsigned long addr); +struct page *get_dump_page(unsigned long addr, int *locked); bool folio_mark_dirty(struct folio *folio); bool folio_mark_dirty_lock(struct folio *folio); @@ -2664,7 +2627,7 @@ static inline void update_hiwater_rss(struct mm_struct *mm) { unsigned long _rss = get_mm_rss(mm); - if ((mm)->hiwater_rss < _rss) + if (data_race(mm->hiwater_rss) < _rss) (mm)->hiwater_rss = _rss; } @@ -2991,18 +2954,15 @@ static inline bool ptlock_init(struct ptdesc *ptdesc) { return true; } static inline void ptlock_free(struct ptdesc *ptdesc) {} #endif /* defined(CONFIG_SPLIT_PTE_PTLOCKS) */ -static inline bool pagetable_pte_ctor(struct ptdesc *ptdesc) +static inline void __pagetable_ctor(struct ptdesc *ptdesc) { struct folio *folio = ptdesc_folio(ptdesc); - if (!ptlock_init(ptdesc)) - return false; __folio_set_pgtable(folio); lruvec_stat_add_folio(folio, NR_PAGETABLE); - return true; } -static inline void pagetable_pte_dtor(struct ptdesc *ptdesc) +static inline void pagetable_dtor(struct ptdesc *ptdesc) { struct folio *folio = ptdesc_folio(ptdesc); @@ -3011,6 +2971,21 @@ static inline void pagetable_pte_dtor(struct ptdesc *ptdesc) lruvec_stat_sub_folio(folio, NR_PAGETABLE); } +static inline void pagetable_dtor_free(struct ptdesc *ptdesc) +{ + pagetable_dtor(ptdesc); + pagetable_free(ptdesc); +} + +static inline bool pagetable_pte_ctor(struct mm_struct *mm, + struct ptdesc *ptdesc) +{ + if (mm != &init_mm && !ptlock_init(ptdesc)) + return false; + __pagetable_ctor(ptdesc); + return true; +} + pte_t *___pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp); static inline pte_t *__pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp) @@ -3087,14 +3062,6 @@ static inline bool pmd_ptlock_init(struct ptdesc *ptdesc) return ptlock_init(ptdesc); } -static inline void pmd_ptlock_free(struct ptdesc *ptdesc) -{ -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - VM_BUG_ON_PAGE(ptdesc->pmd_huge_pte, ptdesc_page(ptdesc)); -#endif - ptlock_free(ptdesc); -} - #define pmd_huge_pte(mm, pmd) (pmd_ptdesc(pmd)->pmd_huge_pte) #else @@ -3105,7 +3072,6 @@ static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd) } static inline bool pmd_ptlock_init(struct ptdesc *ptdesc) { return true; } -static inline void pmd_ptlock_free(struct ptdesc *ptdesc) {} #define pmd_huge_pte(mm, pmd) ((mm)->pmd_huge_pte) @@ -3118,27 +3084,16 @@ static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd) return ptl; } -static inline bool pagetable_pmd_ctor(struct ptdesc *ptdesc) +static inline bool pagetable_pmd_ctor(struct mm_struct *mm, + struct ptdesc *ptdesc) { - struct folio *folio = ptdesc_folio(ptdesc); - - if (!pmd_ptlock_init(ptdesc)) + if (mm != &init_mm && !pmd_ptlock_init(ptdesc)) return false; - __folio_set_pgtable(folio); ptdesc_pmd_pts_init(ptdesc); - lruvec_stat_add_folio(folio, NR_PAGETABLE); + __pagetable_ctor(ptdesc); return true; } -static inline void pagetable_pmd_dtor(struct ptdesc *ptdesc) -{ - struct folio *folio = ptdesc_folio(ptdesc); - - pmd_ptlock_free(ptdesc); - __folio_clear_pgtable(folio); - lruvec_stat_sub_folio(folio, NR_PAGETABLE); -} - /* * No scalability reason to split PUD locks yet, but follow the same pattern * as the PMD locks to make it easier if we decide to. The VM should not be @@ -3160,18 +3115,17 @@ static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud) static inline void pagetable_pud_ctor(struct ptdesc *ptdesc) { - struct folio *folio = ptdesc_folio(ptdesc); - - __folio_set_pgtable(folio); - lruvec_stat_add_folio(folio, NR_PAGETABLE); + __pagetable_ctor(ptdesc); } -static inline void pagetable_pud_dtor(struct ptdesc *ptdesc) +static inline void pagetable_p4d_ctor(struct ptdesc *ptdesc) { - struct folio *folio = ptdesc_folio(ptdesc); + __pagetable_ctor(ptdesc); +} - __folio_clear_pgtable(folio); - lruvec_stat_sub_folio(folio, NR_PAGETABLE); +static inline void pagetable_pgd_ctor(struct ptdesc *ptdesc) +{ + __pagetable_ctor(ptdesc); } extern void __init pagecache_init(void); @@ -3193,7 +3147,6 @@ extern void reserve_bootmem_region(phys_addr_t start, /* Free the reserved page into the buddy system, so it gets managed. */ void free_reserved_page(struct page *page); -#define free_highmem_page(page) free_reserved_page(page) static inline void mark_page_reserved(struct page *page) { @@ -3323,7 +3276,8 @@ void anon_vma_interval_tree_verify(struct anon_vma_chain *node); extern int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin); extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *); extern void exit_mmap(struct mm_struct *); -int relocate_vma_down(struct vm_area_struct *vma, unsigned long shift); +bool mmap_read_lock_maybe_expand(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long addr, bool write); static inline int check_data_rlimit(unsigned long rlim, unsigned long new, @@ -3371,9 +3325,6 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, return __get_unmapped_area(file, addr, len, pgoff, flags, 0); } -extern unsigned long mmap_region(struct file *file, unsigned long addr, - unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, - struct list_head *uf); extern unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate, @@ -3437,9 +3388,6 @@ extern unsigned long stack_guard_gap; int expand_stack_locked(struct vm_area_struct *vma, unsigned long address); struct vm_area_struct *expand_stack(struct mm_struct * mm, unsigned long addr); -/* CONFIG_STACK_GROWSUP still needs to grow downwards at some places */ -int expand_downwards(struct vm_area_struct *vma, unsigned long address); - /* Look up the first VMA which satisfies addr < vm_end, NULL if none. */ extern struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long addr); extern struct vm_area_struct * find_vma_prev(struct mm_struct * mm, unsigned long addr, @@ -3557,6 +3505,8 @@ int vm_map_pages(struct vm_area_struct *vma, struct page **pages, unsigned long num); int vm_map_pages_zero(struct vm_area_struct *vma, struct page **pages, unsigned long num); +vm_fault_t vmf_insert_page_mkwrite(struct vm_fault *vmf, struct page *page, + bool write); vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, @@ -3817,12 +3767,6 @@ static inline int in_gate_area(struct mm_struct *mm, unsigned long addr) extern bool process_shares_mm(struct task_struct *p, struct mm_struct *mm); -#ifdef CONFIG_SYSCTL -extern int sysctl_drop_caches; -int drop_caches_sysctl_handler(const struct ctl_table *, int, void *, size_t *, - loff_t *); -#endif - void drop_slab(void); #ifndef CONFIG_MMU @@ -3841,6 +3785,7 @@ static inline void print_vma_addr(char *prefix, unsigned long rip) #endif void *sparse_buffer_alloc(unsigned long size); +unsigned long section_map_size(void); struct page * __populate_section_memmap(unsigned long pfn, unsigned long nr_pages, int nid, struct vmem_altmap *altmap, struct dev_pagemap *pgmap); @@ -3849,7 +3794,8 @@ p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node); pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node); pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node); pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node, - struct vmem_altmap *altmap, struct page *reuse); + struct vmem_altmap *altmap, unsigned long ptpfn, + unsigned long flags); void *vmemmap_alloc_block(unsigned long size, int node); struct vmem_altmap; void *vmemmap_alloc_block_buf(unsigned long size, int node, @@ -3865,6 +3811,12 @@ int vmemmap_populate_hugepages(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap); int vmemmap_populate(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap); +int vmemmap_populate_hvo(unsigned long start, unsigned long end, int node, + unsigned long headsize); +int vmemmap_undo_hvo(unsigned long start, unsigned long end, int node, + unsigned long headsize); +void vmemmap_wrprotect_hvo(unsigned long start, unsigned long end, int node, + unsigned long headsize); void vmemmap_populate_print_last(void); #ifdef CONFIG_MEMORY_HOTPLUG void vmemmap_free(unsigned long start, unsigned long end, @@ -3931,9 +3883,6 @@ static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap, } #endif -void register_page_bootmem_memmap(unsigned long section_nr, struct page *map, - unsigned long nr_pages); - enum mf_flags { MF_COUNT_INCREASED = 1 << 0, MF_ACTION_REQUIRED = 1 << 1, @@ -4094,69 +4043,6 @@ unsigned long wp_shared_mapping_range(struct address_space *mapping, pgoff_t first_index, pgoff_t nr); #endif -extern int sysctl_nr_trim_pages; - -#ifdef CONFIG_PRINTK -void mem_dump_obj(void *object); -#else -static inline void mem_dump_obj(void *object) {} -#endif - -static inline bool is_write_sealed(int seals) -{ - return seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE); -} - -/** - * is_readonly_sealed - Checks whether write-sealed but mapped read-only, - * in which case writes should be disallowing moving - * forwards. - * @seals: the seals to check - * @vm_flags: the VMA flags to check - * - * Returns whether readonly sealed, in which case writess should be disallowed - * going forward. - */ -static inline bool is_readonly_sealed(int seals, vm_flags_t vm_flags) -{ - /* - * Since an F_SEAL_[FUTURE_]WRITE sealed memfd can be mapped as - * MAP_SHARED and read-only, take care to not allow mprotect to - * revert protections on such mappings. Do this only for shared - * mappings. For private mappings, don't need to mask - * VM_MAYWRITE as we still want them to be COW-writable. - */ - if (is_write_sealed(seals) && - ((vm_flags & (VM_SHARED | VM_WRITE)) == VM_SHARED)) - return true; - - return false; -} - -/** - * seal_check_write - Check for F_SEAL_WRITE or F_SEAL_FUTURE_WRITE flags and - * handle them. - * @seals: the seals to check - * @vma: the vma to operate on - * - * Check whether F_SEAL_WRITE or F_SEAL_FUTURE_WRITE are set; if so, do proper - * check/handling on the vma flags. Return 0 if check pass, or <0 for errors. - */ -static inline int seal_check_write(int seals, struct vm_area_struct *vma) -{ - if (!is_write_sealed(seals)) - return 0; - - /* - * New PROT_WRITE and MAP_SHARED mmaps are not allowed when - * write seals are active. - */ - if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE)) - return -EPERM; - - return 0; -} - #ifdef CONFIG_ANON_VMA_NAME int madvise_set_anon_name(struct mm_struct *mm, unsigned long start, unsigned long len_in, @@ -4197,6 +4083,7 @@ void vma_pgtable_walk_begin(struct vm_area_struct *vma); void vma_pgtable_walk_end(struct vm_area_struct *vma); int reserve_mem_find_by_name(const char *name, phys_addr_t *start, phys_addr_t *size); +int reserve_mem_release_by_name(const char *name); #ifdef CONFIG_64BIT int do_mseal(unsigned long start, size_t len_in, unsigned long flags); @@ -4229,4 +4116,72 @@ int arch_get_shadow_stack_status(struct task_struct *t, unsigned long __user *st int arch_set_shadow_stack_status(struct task_struct *t, unsigned long status); int arch_lock_shadow_stack_status(struct task_struct *t, unsigned long status); + +/* + * mseal of userspace process's system mappings. + */ +#ifdef CONFIG_MSEAL_SYSTEM_MAPPINGS +#define VM_SEALED_SYSMAP VM_SEALED +#else +#define VM_SEALED_SYSMAP VM_NONE +#endif + +/* + * DMA mapping IDs for page_pool + * + * When DMA-mapping a page, page_pool allocates an ID (from an xarray) and + * stashes it in the upper bits of page->pp_magic. We always want to be able to + * unambiguously identify page pool pages (using page_pool_page_is_pp()). Non-PP + * pages can have arbitrary kernel pointers stored in the same field as pp_magic + * (since it overlaps with page->lru.next), so we must ensure that we cannot + * mistake a valid kernel pointer with any of the values we write into this + * field. + * + * On architectures that set POISON_POINTER_DELTA, this is already ensured, + * since this value becomes part of PP_SIGNATURE; meaning we can just use the + * space between the PP_SIGNATURE value (without POISON_POINTER_DELTA), and the + * lowest bits of POISON_POINTER_DELTA. On arches where POISON_POINTER_DELTA is + * 0, we make sure that we leave the two topmost bits empty, as that guarantees + * we won't mistake a valid kernel pointer for a value we set, regardless of the + * VMSPLIT setting. + * + * Altogether, this means that the number of bits available is constrained by + * the size of an unsigned long (at the upper end, subtracting two bits per the + * above), and the definition of PP_SIGNATURE (with or without + * POISON_POINTER_DELTA). + */ +#define PP_DMA_INDEX_SHIFT (1 + __fls(PP_SIGNATURE - POISON_POINTER_DELTA)) +#if POISON_POINTER_DELTA > 0 +/* PP_SIGNATURE includes POISON_POINTER_DELTA, so limit the size of the DMA + * index to not overlap with that if set + */ +#define PP_DMA_INDEX_BITS MIN(32, __ffs(POISON_POINTER_DELTA) - PP_DMA_INDEX_SHIFT) +#else +/* Always leave out the topmost two; see above. */ +#define PP_DMA_INDEX_BITS MIN(32, BITS_PER_LONG - PP_DMA_INDEX_SHIFT - 2) +#endif + +#define PP_DMA_INDEX_MASK GENMASK(PP_DMA_INDEX_BITS + PP_DMA_INDEX_SHIFT - 1, \ + PP_DMA_INDEX_SHIFT) + +/* Mask used for checking in page_pool_page_is_pp() below. page->pp_magic is + * OR'ed with PP_SIGNATURE after the allocation in order to preserve bit 0 for + * the head page of compound page and bit 1 for pfmemalloc page, as well as the + * bits used for the DMA index. page_is_pfmemalloc() is checked in + * __page_pool_put_page() to avoid recycling the pfmemalloc page. + */ +#define PP_MAGIC_MASK ~(PP_DMA_INDEX_MASK | 0x3UL) + +#ifdef CONFIG_PAGE_POOL +static inline bool page_pool_page_is_pp(struct page *page) +{ + return (page->pp_magic & PP_MAGIC_MASK) == PP_SIGNATURE; +} +#else +static inline bool page_pool_page_is_pp(struct page *page) +{ + return false; +} +#endif + #endif /* _LINUX_MM_H */ |