#ifdef CONFIG_ARCH_HAS_HUGEPD static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end, unsigned long sz) { unsigned long __boundary = (addr + sz) & ~(sz-1); return (__boundary - 1 < end - 1) ? __boundary : end; } static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long pte_end; struct page *page; struct folio *folio; pte_t pte; int refs; pte_end = (addr + sz) & ~(sz-1); if (pte_end < end) end = pte_end; pte = huge_ptep_get(ptep); if (!pte_access_permitted(pte, flags & FOLL_WRITE)) return 0; /* hugepages are never "special" */ VM_BUG_ON(!pfn_valid(pte_pfn(pte))); page = nth_page(pte_page(pte), (addr & (sz - 1)) >> PAGE_SHIFT); refs = record_subpages(page, addr, end, pages + *nr); folio = try_grab_folio(page, refs, flags); if (!folio) return 0; if (unlikely(pte_val(pte) != pte_val(ptep_get(ptep)))) { gup_put_folio(folio, refs, flags); return 0; } if (!folio_fast_pin_allowed(folio, flags)) { gup_put_folio(folio, refs, flags); return 0; } if (!pte_write(pte) && gup_must_unshare(NULL, flags, &folio->page)) { gup_put_folio(folio, refs, flags); return 0; } *nr += refs; folio_set_referenced(folio); return 1; } static int gup_huge_pd(hugepd_t hugepd, unsigned long addr, unsigned int pdshift, unsigned long end, unsigned int flags, struct page **pages, int *nr) { pte_t *ptep; unsigned long sz = 1UL << hugepd_shift(hugepd); unsigned long next; ptep = hugepte_offset(hugepd, addr, pdshift); do { next = hugepte_addr_end(addr, end, sz); if (!gup_hugepte(ptep, sz, addr, end, flags, pages, nr)) return 0; } while (ptep++, addr = next, addr != end); return 1; } #else static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr, unsigned int pdshift, unsigned long end, unsigned int flags, struct page **pages, int *nr) { return 0; } #endif /* CONFIG_ARCH_HAS_HUGEPD */ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { struct page *page; struct folio *folio; int refs; if (!pmd_access_permitted(orig, flags & FOLL_WRITE)) return 0; if (pmd_devmap(orig)) { if (unlikely(flags & FOLL_LONGTERM)) return 0; return __gup_device_huge_pmd(orig, pmdp, addr, end, flags, pages, nr); } page = nth_page(pmd_page(orig), (addr & ~PMD_MASK) >> PAGE_SHIFT); refs = record_subpages(page, addr, end, pages + *nr); folio = try_grab_folio(page, refs, flags); if (!folio) return 0; if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) { gup_put_folio(folio, refs, flags); return 0; } if (!folio_fast_pin_allowed(folio, flags)) { gup_put_folio(folio, refs, flags); return 0; } if (!pmd_write(orig) && gup_must_unshare(NULL, flags, &folio->page)) { gup_put_folio(folio, refs, flags); return 0; } *nr += refs; folio_set_referenced(folio); return 1; } static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { struct page *page; struct folio *folio; int refs; if (!pud_access_permitted(orig, flags & FOLL_WRITE)) return 0; if (pud_devmap(orig)) { if (unlikely(flags & FOLL_LONGTERM)) return 0; return __gup_device_huge_pud(orig, pudp, addr, end, flags, pages, nr); } page = nth_page(pud_page(orig), (addr & ~PUD_MASK) >> PAGE_SHIFT); refs = record_subpages(page, addr, end, pages + *nr); folio = try_grab_folio(page, refs, flags); if (!folio) return 0; if (unlikely(pud_val(orig) != pud_val(*pudp))) { gup_put_folio(folio, refs, flags); return 0; } if (!folio_fast_pin_allowed(folio, flags)) { gup_put_folio(folio, refs, flags); return 0; } if (!pud_write(orig) && gup_must_unshare(NULL, flags, &folio->page)) { gup_put_folio(folio, refs, flags); return 0; } *nr += refs; folio_set_referenced(folio); return 1; } static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { int refs; struct page *page; struct folio *folio; if (!pgd_access_permitted(orig, flags & FOLL_WRITE)) return 0; BUILD_BUG_ON(pgd_devmap(orig)); page = nth_page(pgd_page(orig), (addr & ~PGDIR_MASK) >> PAGE_SHIFT); refs = record_subpages(page, addr, end, pages + *nr); folio = try_grab_folio(page, refs, flags); if (!folio) return 0; if (unlikely(pgd_val(orig) != pgd_val(*pgdp))) { gup_put_folio(folio, refs, flags); return 0; } if (!pgd_write(orig) && gup_must_unshare(NULL, flags, &folio->page)) { gup_put_folio(folio, refs, flags); return 0; } if (!folio_fast_pin_allowed(folio, flags)) { gup_put_folio(folio, refs, flags); return 0; } *nr += refs; folio_set_referenced(folio); return 1; } static int gup_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; pmd_t *pmdp; pmdp = pmd_offset_lockless(pudp, pud, addr); do { pmd_t pmd = pmdp_get_lockless(pmdp); next = pmd_addr_end(addr, end); if (!pmd_present(pmd)) return 0; if (unlikely(pmd_trans_huge(pmd) || pmd_huge(pmd) || pmd_devmap(pmd))) { /* See gup_pte_range() */ if (pmd_protnone(pmd)) return 0; if (!gup_huge_pmd(pmd, pmdp, addr, next, flags, pages, nr)) return 0; } else if (unlikely(is_hugepd(__hugepd(pmd_val(pmd))))) { /* * architecture have different format for hugetlbfs * pmd format and THP pmd format */ if (!gup_huge_pd(__hugepd(pmd_val(pmd)), addr, PMD_SHIFT, next, flags, pages, nr)) return 0; } else if (!gup_pte_range(pmd, pmdp, addr, next, flags, pages, nr)) return 0; } while (pmdp++, addr = next, addr != end); return 1; } static int gup_pud_range(p4d_t *p4dp, p4d_t p4d, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; pud_t *pudp; pudp = pud_offset_lockless(p4dp, p4d, addr); do { pud_t pud = READ_ONCE(*pudp); next = pud_addr_end(addr, end); if (unlikely(!pud_present(pud))) return 0; if (unlikely(pud_huge(pud) || pud_devmap(pud))) { if (!gup_huge_pud(pud, pudp, addr, next, flags, pages, nr)) return 0; } else if (unlikely(is_hugepd(__hugepd(pud_val(pud))))) { if (!gup_huge_pd(__hugepd(pud_val(pud)), addr, PUD_SHIFT, next, flags, pages, nr)) return 0; } else if (!gup_pmd_range(pudp, pud, addr, next, flags, pages, nr)) return 0; } while (pudp++, addr = next, addr != end); return 1; } static int gup_p4d_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; p4d_t *p4dp; p4dp = p4d_offset_lockless(pgdp, pgd, addr); do { p4d_t p4d = READ_ONCE(*p4dp); next = p4d_addr_end(addr, end); if (p4d_none(p4d)) return 0; BUILD_BUG_ON(p4d_huge(p4d)); if (unlikely(is_hugepd(__hugepd(p4d_val(p4d))))) { if (!gup_huge_pd(__hugepd(p4d_val(p4d)), addr, P4D_SHIFT, next, flags, pages, nr)) return 0; } else if (!gup_pud_range(p4dp, p4d, addr, next, flags, pages, nr)) return 0; } while (p4dp++, addr = next, addr != end); return 1; } static void gup_pgd_range(unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; pgd_t *pgdp; pgdp = pgd_offset(current->mm, addr); do { pgd_t pgd = READ_ONCE(*pgdp); next = pgd_addr_end(addr, end); if (pgd_none(pgd)) return; if (unlikely(pgd_huge(pgd))) { if (!gup_huge_pgd(pgd, pgdp, addr, next, flags, pages, nr)) return; } else if (unlikely(is_hugepd(__hugepd(pgd_val(pgd))))) { if (!gup_huge_pd(__hugepd(pgd_val(pgd)), addr, PGDIR_SHIFT, next, flags, pages, nr)) return; } else if (!gup_p4d_range(pgdp, pgd, addr, next, flags, pages, nr)) return; } while (pgdp++, addr = next, addr != end); } #else static inline void gup_pgd_range(unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { }

static int internal_get_user_pages_fast(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages) { unsigned long len, end; unsigned long nr_pinned; int locked = 0; int ret; if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM | FOLL_FORCE | FOLL_PIN | FOLL_GET | FOLL_FAST_ONLY | FOLL_NOFAULT | FOLL_PCI_P2PDMA | FOLL_HONOR_NUMA_FAULT))) return -EINVAL; if (gup_flags & FOLL_PIN) mm_set_has_pinned_flag(&current->mm->flags); if (!(gup_flags & FOLL_FAST_ONLY)) might_lock_read(&current->mm->mmap_lock); start = untagged_addr(start) & PAGE_MASK; len = nr_pages << PAGE_SHIFT; if (check_add_overflow(start, len, &end)) return -EOVERFLOW; if (end > TASK_SIZE_MAX) return -EFAULT; if (unlikely(!access_ok((void __user *)start, len))) return -EFAULT; nr_pinned = lockless_pages_from_mm(start, end, gup_flags, pages); if (nr_pinned == nr_pages || gup_flags & FOLL_FAST_ONLY) return nr_pinned; /* Slow path: try to get the remaining pages with get_user_pages */ start += nr_pinned << PAGE_SHIFT; pages += nr_pinned; ret = __gup_longterm_locked(current->mm, start, nr_pages - nr_pinned, pages, &locked, gup_flags | FOLL_TOUCH | FOLL_UNLOCKABLE); if (ret < 0) { /* * The caller has to unpin the pages we already pinned so * returning -errno is not an option */ if (nr_pinned) return nr_pinned; return ret; } return ret + nr_pinned; } /** * get_user_pages_fast_only() - pin user pages in memory * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying pin behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. * * Like get_user_pages_fast() except it's IRQ-safe in that it won't fall back to * the regular GUP. * * If the architecture does not support this function, simply return with no * pages pinned. * * Careful, careful! COW breaking can go either way, so a non-write * access can get ambiguous page results. If you call this function without * 'write' set, you'd better be sure that you're ok with that ambiguity. */ int get_user_pages_fast_only(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages) { /* * Internally (within mm/gup.c), gup fast variants must set FOLL_GET, * because gup fast is always a "pin with a +1 page refcount" request. * * FOLL_FAST_ONLY is required in order to match the API description of * this routine: no fall back to regular ("slow") GUP. */ if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_GET | FOLL_FAST_ONLY)) return -EINVAL; return internal_get_user_pages_fast(start, nr_pages, gup_flags, pages); } EXPORT_SYMBOL_GPL(get_user_pages_fast_only); /** * get_user_pages_fast() - pin user pages in memory * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying pin behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. * * Attempt to pin user pages in memory without taking mm->mmap_lock. * If not successful, it will fall back to taking the lock and * calling get_user_pages(). * * Returns number of pages pinned. This may be fewer than the number requested. * If nr_pages is 0 or negative, returns 0. If no pages were pinned, returns * -errno. */ int get_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages) { /* * The caller may or may not have explicitly set FOLL_GET; either way is * OK. However, internally (within mm/gup.c), gup fast variants must set * FOLL_GET, because gup fast is always a "pin with a +1 page refcount" * request. */ if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_GET)) return -EINVAL; return internal_get_user_pages_fast(start, nr_pages, gup_flags, pages); } EXPORT_SYMBOL_GPL(get_user_pages_fast); /** * pin_user_pages_fast() - pin user pages in memory without taking locks * * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying pin behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. * * Nearly the same as get_user_pages_fast(), except that FOLL_PIN is set. See * get_user_pages_fast() for documentation on the function arguments, because * the arguments here are identical. * * FOLL_PIN means that the pages must be released via unpin_user_page(). Please * see Documentation/core-api/pin_user_pages.rst for further details. * * Note that if a zero_page is amongst the returned pages, it will not have * pins in it and unpin_user_page() will not remove pins from it. */ int pin_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages) { if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_PIN)) return -EINVAL; return internal_get_user_pages_fast(start, nr_pages, gup_flags, pages); } EXPORT_SYMBOL_GPL(pin_user_pages_fast); /** * pin_user_pages_remote() - pin pages of a remote process * * @mm: mm_struct of target mm * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying lookup behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. * @locked: pointer to lock flag indicating whether lock is held and * subsequently whether VM_FAULT_RETRY functionality can be * utilised. Lock must initially be held. * * Nearly the same as get_user_pages_remote(), except that FOLL_PIN is set. See * get_user_pages_remote() for documentation on the function arguments, because * the arguments here are identical. * * FOLL_PIN means that the pages must be released via unpin_user_page(). Please * see Documentation/core-api/pin_user_pages.rst for details. * * Note that if a zero_page is amongst the returned pages, it will not have * pins in it and unpin_user_page*() will not remove pins from it. */ long pin_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked) { int local_locked = 1; if (!is_valid_gup_args(pages, locked, &gup_flags, FOLL_PIN | FOLL_TOUCH | FOLL_REMOTE)) return 0; return __gup_longterm_locked(mm, start, nr_pages, pages, locked ? locked : &local_locked, gup_flags); } EXPORT_SYMBOL(pin_user_pages_remote); /** * pin_user_pages() - pin user pages in memory for use by other devices * * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying lookup behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. * * Nearly the same as get_user_pages(), except that FOLL_TOUCH is not set, and * FOLL_PIN is set. * * FOLL_PIN means that the pages must be released via unpin_user_page(). Please * see Documentation/core-api/pin_user_pages.rst for details. * * Note that if a zero_page is amongst the returned pages, it will not have * pins in it and unpin_user_page*() will not remove pins from it. */ long pin_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages) { int locked = 1; if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_PIN)) return 0; return __gup_longterm_locked(current->mm, start, nr_pages, pages, &locked, gup_flags); } EXPORT_SYMBOL(pin_user_pages); /* * pin_user_pages_unlocked() is the FOLL_PIN variant of * get_user_pages_unlocked(). Behavior is the same, except that this one sets * FOLL_PIN and rejects FOLL_GET. * * Note that if a zero_page is amongst the returned pages, it will not have * pins in it and unpin_user_page*() will not remove pins from it. */ long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags) { int locked = 0; if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_PIN | FOLL_TOUCH | FOLL_UNLOCKABLE)) return 0; return __gup_longterm_locked(current->mm, start, nr_pages, pages, &locked, gup_flags); }

/** * unpin_user_pages() - release an array of gup-pinned pages. * @pages: array of pages to be marked dirty and released. * @npages: number of pages in the @pages array. * * For each page in the @pages array, release the page using unpin_user_page(). * * Please see the unpin_user_page() documentation for details. */ void unpin_user_pages(struct page **pages, unsigned long npages) { unsigned long i; struct folio *folio; unsigned int nr; /* * If this WARN_ON() fires, then the system *might* be leaking pages (by * leaving them pinned), but probably not. More likely, gup/pup returned * a hard -ERRNO error to the caller, who erroneously passed it here. */ if (WARN_ON(IS_ERR_VALUE(npages))) return; sanity_check_pinned_pages(pages, npages); for (i = 0; i < npages; i += nr) { folio = gup_folio_next(pages, npages, i, &nr); gup_put_folio(folio, nr, FOLL_PIN); } }

if ((flags & FOLL_DUMP) && (vma_is_anonymous(vma) || !vma->vm_ops->fault)) return ERR_PTR(-EFAULT); return NULL;

#ifdef CONFIG_ARCH_HAS_PTE_SPECIAL /* * Fast-gup relies on pte change detection to avoid concurrent pgtable * operations. * * To pin the page, fast-gup needs to do below in order: * (1) pin the page (by prefetching pte), then (2) check pte not changed. * * For the rest of pgtable operations where pgtable updates can be racy * with fast-gup, we need to do (1) clear pte, then (2) check whether page * is pinned. * * Above will work for all pte-level operations, including THP split. * * For THP collapse, it's a bit more complicated because fast-gup may be * walking a pgtable page that is being freed (pte is still valid but pmd * can be cleared already). To avoid race in such condition, we need to * also check pmd here to make sure pmd doesn't change (corresponds to * pmdp_collapse_flush() in the THP collapse code path). */ static int gup_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { struct dev_pagemap *pgmap = NULL; int nr_start = *nr, ret = 0; pte_t *ptep, *ptem; ptem = ptep = pte_offset_map(&pmd, addr); if (!ptep) return 0; do { pte_t pte = ptep_get_lockless(ptep); struct page *page; struct folio *folio; /* * Always fallback to ordinary GUP on PROT_NONE-mapped pages: * pte_access_permitted() better should reject these pages * either way: otherwise, GUP-fast might succeed in * cases where ordinary GUP would fail due to VMA access * permissions. */ if (pte_protnone(pte)) goto pte_unmap; if (!pte_access_permitted(pte, flags & FOLL_WRITE)) goto pte_unmap; if (pte_devmap(pte)) { if (unlikely(flags & FOLL_LONGTERM)) goto pte_unmap; pgmap = get_dev_pagemap(pte_pfn(pte), pgmap); if (unlikely(!pgmap)) { undo_dev_pagemap(nr, nr_start, flags, pages); goto pte_unmap; } } else if (pte_special(pte)) goto pte_unmap; VM_BUG_ON(!pfn_valid(pte_pfn(pte))); page = pte_page(pte); folio = try_grab_folio(page, 1, flags); if (!folio) goto pte_unmap; if (unlikely(folio_is_secretmem(folio))) { gup_put_folio(folio, 1, flags); goto pte_unmap; } if (unlikely(pmd_val(pmd) != pmd_val(*pmdp)) || unlikely(pte_val(pte) != pte_val(ptep_get(ptep)))) { gup_put_folio(folio, 1, flags); goto pte_unmap; } if (!folio_fast_pin_allowed(folio, flags)) { gup_put_folio(folio, 1, flags); goto pte_unmap; } if (!pte_write(pte) && gup_must_unshare(NULL, flags, page)) { gup_put_folio(folio, 1, flags); goto pte_unmap; } /* * We need to make the page accessible if and only if we are * going to access its content (the FOLL_PIN case). Please * see Documentation/core-api/pin_user_pages.rst for * details. */ if (flags & FOLL_PIN) { ret = arch_make_page_accessible(page); if (ret) { gup_put_folio(folio, 1, flags); goto pte_unmap; } } folio_set_referenced(folio); pages[*nr] = page; (*nr)++; } while (ptep++, addr += PAGE_SIZE, addr != end); ret = 1; pte_unmap: if (pgmap) put_dev_pagemap(pgmap); pte_unmap(ptem); return ret; } #else /* * If we can't determine whether or not a pte is special, then fail immediately * for ptes. Note, we can still pin HugeTLB and THP as these are guaranteed not * to be special. * * For a futex to be placed on a THP tail page, get_futex_key requires a * get_user_pages_fast_only implementation that can pin pages. Thus it's still * useful to have gup_huge_pmd even if we can't operate on ptes. */ static int gup_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { return 0; } #endif /* CONFIG_ARCH_HAS_PTE_SPECIAL */

#ifdef CONFIG_HAVE_FAST_GUP /* * Used in the GUP-fast path to determine whether a pin is permitted for a * specific folio. * * This call assumes the caller has pinned the folio, that the lowest page table * level still points to this folio, and that interrupts have been disabled. * * Writing to pinned file-backed dirty tracked folios is inherently problematic * (see comment describing the writable_file_mapping_allowed() function). We * therefore try to avoid the most egregious case of a long-term mapping doing * so. * * This function cannot be as thorough as that one as the VMA is not available * in the fast path, so instead we whitelist known good cases and if in doubt, * fall back to the slow path. */ static bool folio_fast_pin_allowed(struct folio *folio, unsigned int flags) { struct address_space *mapping; unsigned long mapping_flags; /* * If we aren't pinning then no problematic write can occur. A long term * pin is the most egregious case so this is the one we disallow. */ if ((flags & (FOLL_PIN | FOLL_LONGTERM | FOLL_WRITE)) != (FOLL_PIN | FOLL_LONGTERM | FOLL_WRITE)) return true; /* The folio is pinned, so we can safely access folio fields. */ if (WARN_ON_ONCE(folio_test_slab(folio))) return false; /* hugetlb mappings do not require dirty-tracking. */ if (folio_test_hugetlb(folio)) return true; /* * GUP-fast disables IRQs. When IRQS are disabled, RCU grace periods * cannot proceed, which means no actions performed under RCU can * proceed either. * * inodes and thus their mappings are freed under RCU, which means the * mapping cannot be freed beneath us and thus we can safely dereference * it. */ lockdep_assert_irqs_disabled(); /* * However, there may be operations which _alter_ the mapping, so ensure * we read it once and only once. */ mapping = READ_ONCE(folio->mapping); /* * The mapping may have been truncated, in any case we cannot determine * if this mapping is safe - fall back to slow path to determine how to * proceed. */ if (!mapping) return false; /* Anonymous folios pose no problem. */ mapping_flags = (unsigned long)mapping & PAGE_MAPPING_FLAGS; if (mapping_flags) return mapping_flags & PAGE_MAPPING_ANON; /* * At this point, we know the mapping is non-null and points to an * address_space object. The only remaining whitelisted file system is * shmem. */ return shmem_mapping(mapping); }

long get_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages) { int locked = 1; if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_TOUCH)) return -EINVAL; return __get_user_pages_locked(current->mm, start, nr_pages, pages, &locked, gup_flags); }

#ifdef CONFIG_MIGRATION /* * Returns the number of collected pages. Return value is always >= 0. */ static unsigned long collect_longterm_unpinnable_pages( struct list_head *movable_page_list, unsigned long nr_pages, struct page **pages) { unsigned long i, collected = 0; struct folio *prev_folio = NULL; bool drain_allow = true; for (i = 0; i < nr_pages; i++) { struct folio *folio = page_folio(pages[i]); if (folio == prev_folio) continue; prev_folio = folio; if (folio_is_longterm_pinnable(folio)) continue; collected++; if (folio_is_device_coherent(folio)) continue; if (folio_test_hugetlb(folio)) { isolate_hugetlb(folio, movable_page_list); continue; } if (!folio_test_lru(folio) && drain_allow) { lru_add_drain_all(); drain_allow = false; } if (!folio_isolate_lru(folio)) continue; list_add_tail(&folio->lru, movable_page_list); node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), folio_nr_pages(folio)); } return collected; }

#ifdef CONFIG_ELF_CORE struct page *get_dump_page(unsigned long addr) { struct page *page; int locked = 0; int ret; ret = __get_user_pages_locked(current->mm, addr, 1, &page, &locked, FOLL_FORCE | FOLL_DUMP | FOLL_GET); return (ret == 1) ? page : NULL; } #endif /* CONFIG_ELF_CORE */

int __mm_populate(unsigned long start, unsigned long len, int ignore_errors) { struct mm_struct *mm = current->mm; unsigned long end, nstart, nend; struct vm_area_struct *vma = NULL; int locked = 0; long ret = 0; end = start + len; for (nstart = start; nstart < end; nstart = nend) { /* * We want to fault in pages for [nstart; end) address range. * Find first corresponding VMA. */ if (!locked) { locked = 1; mmap_read_lock(mm); vma = find_vma_intersection(mm, nstart, end); } else if (nstart >= vma->vm_end) vma = find_vma_intersection(mm, vma->vm_end, end); if (!vma) break; /* * Set [nstart; nend) to intersection of desired address * range with the first VMA. Also, skip undesirable VMA types. */ nend = min(end, vma->vm_end); if (vma->vm_flags & (VM_IO | VM_PFNMAP)) continue; if (nstart < vma->vm_start) nstart = vma->vm_start; /* * Now fault in a range of pages. populate_vma_page_range() * double checks the vma flags, so that it won't mlock pages * if the vma was already munlocked. */ ret = populate_vma_page_range(vma, nstart, nend, &locked); if (ret < 0) { if (ignore_errors) { ret = 0; continue; /* continue at next VMA */ } break; } nend = nstart + ret * PAGE_SIZE; ret = 0; } if (locked) mmap_read_unlock(mm); return ret; /* 0 or negative error code */ }

long populate_vma_page_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, int *locked) { struct mm_struct *mm = vma->vm_mm; unsigned long nr_pages = (end - start) / PAGE_SIZE; int local_locked = 1; int gup_flags; long ret; VM_BUG_ON(!PAGE_ALIGNED(start)); VM_BUG_ON(!PAGE_ALIGNED(end)); VM_BUG_ON_VMA(start < vma->vm_start, vma); VM_BUG_ON_VMA(end > vma->vm_end, vma); mmap_assert_locked(mm); /* * Rightly or wrongly, the VM_LOCKONFAULT case has never used * faultin_page() to break COW, so it has no work to do here. */ if (vma->vm_flags & VM_LOCKONFAULT) return nr_pages; gup_flags = FOLL_TOUCH; /* * We want to touch writable mappings with a write fault in order * to break COW, except for shared mappings because these don't COW * and we would not want to dirty them for nothing. */ if ((vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE) gup_flags |= FOLL_WRITE; /* * We want mlock to succeed for regions that have any permissions * other than PROT_NONE. */ if (vma_is_accessible(vma)) gup_flags |= FOLL_FORCE; if (locked) gup_flags |= FOLL_UNLOCKABLE; /* * We made sure addr is within a VMA, so the following will * not result in a stack expansion that recurses back here. */ ret = __get_user_pages(mm, start, nr_pages, gup_flags, NULL, locked ? locked : &local_locked); lru_add_drain(); return ret; }

long get_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked) { int local_locked = 1; if (!is_valid_gup_args(pages, locked, &gup_flags, FOLL_TOUCH | FOLL_REMOTE)) return -EINVAL; return __get_user_pages_locked(mm, start, nr_pages, pages, locked ? locked : &local_locked, gup_flags); }

static __always_inline long __get_user_pages_locked(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, struct page **pages, int *locked, unsigned int flags) { long ret, pages_done; bool must_unlock = false; /* * The internal caller expects GUP to manage the lock internally and the * lock must be released when this returns. */ if (!*locked) { if (mmap_read_lock_killable(mm)) return -EAGAIN; must_unlock = true; *locked = 1; } else mmap_assert_locked(mm); if (flags & FOLL_PIN) mm_set_has_pinned_flag(&mm->flags); /* * FOLL_PIN and FOLL_GET are mutually exclusive. Traditional behavior * is to set FOLL_GET if the caller wants pages[] filled in (but has * carelessly failed to specify FOLL_GET), so keep doing that, but only * for FOLL_GET, not for the newer FOLL_PIN. * * FOLL_PIN always expects pages to be non-null, but no need to assert * that here, as any failures will be obvious enough. */ if (pages && !(flags & FOLL_PIN)) flags |= FOLL_GET; pages_done = 0; for (;;) { ret = __get_user_pages(mm, start, nr_pages, flags, pages, locked); if (!(flags & FOLL_UNLOCKABLE)) { /* VM_FAULT_RETRY couldn't trigger, bypass */ pages_done = ret; break; } /* VM_FAULT_RETRY or VM_FAULT_COMPLETED cannot return errors */ if (!*locked) { BUG_ON(ret < 0); BUG_ON(ret >= nr_pages); } if (ret > 0) { nr_pages -= ret; pages_done += ret; if (!nr_pages) break; } if (*locked) { /* * VM_FAULT_RETRY didn't trigger or it was a * FOLL_NOWAIT. */ if (!pages_done) pages_done = ret; break; } /* * VM_FAULT_RETRY triggered, so seek to the faulting offset. * For the prefault case (!pages) we only update counts. */ if (likely(pages)) pages += ret; start += ret << PAGE_SHIFT; /* The lock was temporarily dropped, so we must unlock later */ must_unlock = true; retry: /* * Repeat on the address that fired VM_FAULT_RETRY * with both FAULT_FLAG_ALLOW_RETRY and * FAULT_FLAG_TRIED. Note that GUP can be interrupted * by fatal signals of even common signals, depending on * the caller's request. So we need to check it before we * start trying again otherwise it can loop forever. */ if (gup_signal_pending(flags)) { if (!pages_done) pages_done = -EINTR; break; } ret = mmap_read_lock_killable(mm); if (ret) { BUG_ON(ret > 0); if (!pages_done) pages_done = ret; break; } *locked = 1; ret = __get_user_pages(mm, start, 1, flags | FOLL_TRIED, pages, locked); if (!*locked) { /* Continue to retry until we succeeded */ BUG_ON(ret != 0); goto retry; } if (ret != 1) { BUG_ON(ret > 1); if (!pages_done) pages_done = ret; break; } nr_pages--; pages_done++; if (!nr_pages) break; if (likely(pages)) pages++; start += PAGE_SIZE; } if (must_unlock && *locked) { /* * We either temporarily dropped the lock, or the caller * requested that we both acquire and drop the lock. Either way, * we must now unlock, and notify the caller of that state. */ mmap_read_unlock(mm); *locked = 0; } return pages_done; }

if (!(flags & FOLL_INTERRUPTIBLE)) return false;

int fixup_user_fault(struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked) { struct vm_area_struct *vma; vm_fault_t ret; address = untagged_addr_remote(mm, address); if (unlocked) fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; retry: vma = gup_vma_lookup(mm, address); if (!vma) return -EFAULT; if (!vma_permits_fault(vma, fault_flags)) return -EFAULT; if ((fault_flags & FAULT_FLAG_KILLABLE) && fatal_signal_pending(current)) return -EINTR; ret = handle_mm_fault(vma, address, fault_flags, NULL); if (ret & VM_FAULT_COMPLETED) { /* * NOTE: it's a pity that we need to retake the lock here * to pair with the unlock() in the callers. Ideally we * could tell the callers so they do not need to unlock. */ mmap_read_lock(mm); *unlocked = true; return 0; } if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, 0); if (err) return err; BUG(); } if (ret & VM_FAULT_RETRY) { mmap_read_lock(mm); *unlocked = true; fault_flags |= FAULT_FLAG_TRIED; goto retry; } return 0; }

static bool writable_file_mapping_allowed(struct vm_area_struct *vma, unsigned long gup_flags) { /* * If we aren't pinning then no problematic write can occur. A long term * pin is the most egregious case so this is the case we disallow. */ if ((gup_flags & (FOLL_PIN | FOLL_LONGTERM)) != (FOLL_PIN | FOLL_LONGTERM)) return true; /* * If the VMA does not require dirty tracking then no problematic write * can occur either. */ return !vma_needs_dirty_tracking(vma); }

if (*flags & FOLL_NOFAULT) return -EFAULT; if (*flags & FOLL_WRITE) fault_flags |= FAULT_FLAG_WRITE; if (*flags & FOLL_REMOTE) fault_flags |= FAULT_FLAG_REMOTE; if (*flags & FOLL_UNLOCKABLE) { fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; /* * FAULT_FLAG_INTERRUPTIBLE is opt-in. GUP callers must set * FOLL_INTERRUPTIBLE to enable FAULT_FLAG_INTERRUPTIBLE. * That's because some callers may not be prepared to * handle early exits caused by non-fatal signals. */ if (*flags & FOLL_INTERRUPTIBLE) fault_flags |= FAULT_FLAG_INTERRUPTIBLE; } if (*flags & FOLL_NOWAIT) fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT; if (*flags & FOLL_TRIED) { /* * Note: FAULT_FLAG_ALLOW_RETRY and FAULT_FLAG_TRIED * can co-exist */ fault_flags |= FAULT_FLAG_TRIED; } if (unshare) { fault_flags |= FAULT_FLAG_UNSHARE; /* FAULT_FLAG_WRITE and FAULT_FLAG_UNSHARE are incompatible */ VM_BUG_ON(fault_flags & FAULT_FLAG_WRITE); } ret = handle_mm_fault(vma, address, fault_flags, NULL); if (ret & VM_FAULT_COMPLETED) { /* * With FAULT_FLAG_RETRY_NOWAIT we'll never release the * mmap lock in the page fault handler. Sanity check this. */ WARN_ON_ONCE(fault_flags & FAULT_FLAG_RETRY_NOWAIT); *locked = 0; /* * We should do the same as VM_FAULT_RETRY, but let's not * return -EBUSY since that's not reflecting the reality of * what has happened - we've just fully completed a page * fault, with the mmap lock released. Use -EAGAIN to show * that we want to take the mmap lock _again_. */ return -EAGAIN; } if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, *flags); if (err) return err; BUG(); } if (ret & VM_FAULT_RETRY) { if (!(fault_flags & FAULT_FLAG_RETRY_NOWAIT)) *locked = 0; return -EBUSY; }

static struct page *follow_page_mask(struct vm_area_struct *vma, unsigned long address, unsigned int flags, struct follow_page_context *ctx) { pgd_t *pgd; struct mm_struct *mm = vma->vm_mm; ctx->page_mask = 0; /* * Call hugetlb_follow_page_mask for hugetlb vmas as it will use * special hugetlb page table walking code. This eliminates the * need to check for hugetlb entries in the general walking code. */ if (is_vm_hugetlb_page(vma)) return hugetlb_follow_page_mask(vma, address, flags, &ctx->page_mask); pgd = pgd_offset(mm, address); if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) return no_page_table(vma, flags); return follow_p4d_mask(vma, address, pgd, flags, ctx); }

struct page *follow_page(struct vm_area_struct *vma, unsigned long address, unsigned int foll_flags) { struct follow_page_context ctx = { NULL }; struct page *page; if (vma_is_secretmem(vma)) return NULL; if (WARN_ON_ONCE(foll_flags & FOLL_PIN)) return NULL; /* * We never set FOLL_HONOR_NUMA_FAULT because callers don't expect * to fail on PROT_NONE-mapped pages. */ page = follow_page_mask(vma, address, foll_flags, &ctx); if (ctx.pgmap) put_dev_pagemap(ctx.pgmap); return page; }

if (flags & FOLL_SPLIT_PMD) { spin_unlock(ptl); split_huge_pmd(vma, pmd, address); /* If pmd was left empty, stuff a page table in there quickly */ return pte_alloc(mm, pmd) ? ERR_PTR(-ENOMEM) : follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); } page = follow_trans_huge_pmd(vma, address, pmd, flags); spin_unlock(ptl); ctx->page_mask = HPAGE_PMD_NR - 1; return page;

/* FOLL_GET and FOLL_PIN are mutually exclusive. */ if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) == (FOLL_PIN | FOLL_GET))) return ERR_PTR(-EINVAL); ptep = pte_offset_map_lock(mm, pmd, address, &ptl); if (!ptep) return no_page_table(vma, flags); pte = ptep_get(ptep); if (!pte_present(pte)) goto no_page; if (pte_protnone(pte) && !gup_can_follow_protnone(vma, flags)) goto no_page; page = vm_normal_page(vma, address, pte); /* * We only care about anon pages in can_follow_write_pte() and don't * have to worry about pte_devmap() because they are never anon. */ if ((flags & FOLL_WRITE) && !can_follow_write_pte(pte, page, vma, flags)) { page = NULL; goto out; } if (!page && pte_devmap(pte) && (flags & (FOLL_GET | FOLL_PIN))) { /* * Only return device mapping pages in the FOLL_GET or FOLL_PIN * case since they are only valid while holding the pgmap * reference. */ *pgmap = get_dev_pagemap(pte_pfn(pte), *pgmap); if (*pgmap) page = pte_page(pte); else goto no_page; } else if (unlikely(!page)) { if (flags & FOLL_DUMP) { /* Avoid special (like zero) pages in core dumps */ page = ERR_PTR(-EFAULT); goto out; } if (is_zero_pfn(pte_pfn(pte))) { page = pte_page(pte); } else { ret = follow_pfn_pte(vma, address, ptep, flags); page = ERR_PTR(ret); goto out; } } if (!pte_write(pte) && gup_must_unshare(vma, flags, page)) { page = ERR_PTR(-EMLINK); goto out; } VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) && !PageAnonExclusive(page), page); /* try_grab_page() does nothing unless FOLL_GET or FOLL_PIN is set. */ ret = try_grab_page(page, flags); if (unlikely(ret)) { page = ERR_PTR(ret); goto out; } /* * We need to make the page accessible if and only if we are going * to access its content (the FOLL_PIN case). Please see * Documentation/core-api/pin_user_pages.rst for details. */ if (flags & FOLL_PIN) { ret = arch_make_page_accessible(page); if (ret) { unpin_user_page(page); page = ERR_PTR(ret); goto out; } } if (flags & FOLL_TOUCH) { if ((flags & FOLL_WRITE) && !pte_dirty(pte) && !PageDirty(page)) set_page_dirty(page); /* * pte_mkyoung() would be more correct here, but atomic care * is needed to avoid losing the dirty bit: it is easier to use * mark_page_accessed(). */ mark_page_accessed(page); }

if (pte_write(pte)) return true; /* Maybe FOLL_FORCE is set to override it? */ if (!(flags & FOLL_FORCE)) return false; /* But FOLL_FORCE has no effect on shared mappings */ if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED)) return false; /* ... or read-only private ones */ if (!(vma->vm_flags & VM_MAYWRITE)) return false; /* ... or already writable ones that just need to take a write fault */ if (vma->vm_flags & VM_WRITE) return false; /* * See can_change_pte_writable(): we broke COW and could map the page * writable if we have an exclusive anonymous page ... */ if (!page || !PageAnon(page) || !PageAnonExclusive(page)) return false; /* ... and a write-fault isn't required for other reasons. */ if (vma_soft_dirty_enabled(vma) && !pte_soft_dirty(pte)) return false; return !userfaultfd_pte_wp(vma, pte);

if (flags & FOLL_TOUCH) { pte_t orig_entry = ptep_get(pte); pte_t entry = orig_entry; if (flags & FOLL_WRITE) entry = pte_mkdirty(entry); entry = pte_mkyoung(entry); if (!pte_same(orig_entry, entry)) { set_pte_at(vma->vm_mm, address, pte, entry); update_mmu_cache(vma, address, pte); }

struct folio *folio = page_folio(page); if (WARN_ON_ONCE(folio_ref_count(folio) <= 0)) return -ENOMEM; if (unlikely(!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(page))) return -EREMOTEIO; if (flags & FOLL_GET) folio_ref_inc(folio);

else if (flags & FOLL_PIN) { /* * Don't take a pin on the zero page - it's not going anywhere * and it is used in a *lot* of places. */ if (is_zero_page(page)) return 0; /* * Similar to try_grab_folio(): be sure to *also* * increment the normal page refcount field at least once, * so that the page really is pinned. */ if (folio_test_large(folio)) { folio_ref_add(folio, 1); atomic_add(1, &folio->_pincount); } else { folio_ref_add(folio, GUP_PIN_COUNTING_BIAS); } node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, 1); }

if (flags & FOLL_PIN) { if (is_zero_folio(folio)) return; node_stat_mod_folio(folio, NR_FOLL_PIN_RELEASED, refs); if (folio_test_large(folio)) atomic_sub(refs, &folio->_pincount); else refs *= GUP_PIN_COUNTING_BIAS; }

if (unlikely((flags & FOLL_LONGTERM) && !folio_is_longterm_pinnable(folio))) { if (!put_devmap_managed_page_refs(&folio->page, refs)) folio_put_refs(folio, refs); return NULL;

if (WARN_ON_ONCE((flags & (FOLL_GET | FOLL_PIN)) == 0)) return NULL; if (unlikely(!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(page))) return NULL;

if (flags & FOLL_GET) return try_get_folio(page, refs);

if (gup_flags & FOLL_PIN) mm_set_has_pinned_flag(&current->mm->flags); if (!(gup_flags & FOLL_FAST_ONLY)) might_lock_read(&current->mm->mmap_lock); start = untagged_addr(start) & PAGE_MASK; len = nr_pages << PAGE_SHIFT; if (check_add_overflow(start, len, &end)) return -EOVERFLOW; if (end > TASK_SIZE_MAX) return -EFAULT; if (unlikely(!access_ok((void __user *)start, len))) return -EFAULT;

if (flags & FOLL_PIN) { ret = arch_make_page_accessible(page); if (ret) { gup_put_folio(folio, 1, flags); goto pte_unmap; } }

if (!(gup_flags & FOLL_LONGTERM)) return __get_user_pages_locked(mm, start, nr_pages, pages, locked, gup_flags);

vm_flags = (foll_flags & FOLL_WRITE) ? (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD); vm_flags &= (foll_flags & FOLL_FORCE) ? (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);

if (!(flags & FOLL_UNLOCKABLE)) { /* VM_FAULT_RETRY couldn't trigger, bypass */ pages_done = ret; break; }

if (ret & VM_FAULT_COMPLETED) { /* * NOTE: it's a pity that we need to retake the lock here * to pair with the unlock() in the callers. Ideally we * could tell the callers so they do not need to unlock. */ mmap_read_lock(mm); *unlocked = true; return 0; } if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, 0); if (err) return err; BUG(); } if (ret & VM_FAULT_RETRY) { mmap_read_lock(mm); *unlocked = true; fault_flags |= FAULT_FLAG_TRIED; goto retry; }

if (flags & FOLL_PIN) mm_set_has_pinned_flag(&mm->flags);

if (unlocked) fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;

if (page_increm > nr_pages) page_increm = nr_pages;

*/ if (gup_flags & FOLL_MADV_POPULATE) { vma = vma_lookup(mm, start); if (!vma) { ret = -ENOMEM; goto out; } if (check_vma_flags(vma, gup_flags)) { ret = -EINVAL; goto out; } goto retry; }

if (!(vm_flags & VM_WRITE) || (vm_flags & VM_SHADOW_STACK)) { if (!(gup_flags & FOLL_FORCE)) return -EFAULT; /* hugetlb does not support FOLL_FORCE|FOLL_WRITE. */ if (is_vm_hugetlb_page(vma)) return -EFAULT; /* * We used to let the write,force case do COW in a * VM_MAYWRITE VM_SHARED !VM_WRITE vma, so ptrace could * set a breakpoint in a read-only mapping of an * executable, without corrupting the file (yet only * when that file had been opened for writing!). * Anon pages in shared mappings are surprising: now * just reject it. */ if (!is_cow_mapping(vm_flags)) return -EFAULT; } } else if (!(vm_flags & VM_READ)) { if (!(gup_flags & FOLL_FORCE)) return -EFAULT; /* * Is there actually any vma we can reach here which does not * have VM_MAYREAD set? */ if (!(vm_flags & VM_MAYREAD)) return -EFAULT; }

if ((gup_flags & (FOLL_PIN | FOLL_LONGTERM)) != (FOLL_PIN | FOLL_LONGTERM)) return true;

if (s->flags & __CMPXCHG_DOUBLE) { ret = __update_freelist_fast(slab, freelist_old, counters_old, freelist_new, counters_new); } else { ret = __update_freelist_slow(slab, freelist_old, counters_old, freelist_new, counters_new); }

#ifdef CONFIG_SLAB_FREELIST_HARDENED encoded = (unsigned long)ptr ^ s->random ^ swab(ptr_addr); #else encoded = (unsigned long)ptr; #endif

#ifdef CONFIG_SLAB_FREELIST_HARDENED decoded = (void *)(ptr.v ^ s->random ^ swab(ptr_addr)); #else decoded = (void *)ptr.v; #endif

#ifdef CONFIG_SLAB_FREELIST_RANDOM /* Pre-initialize the random sequence cache */ static int init_cache_random_seq(struct kmem_cache *s) { unsigned int count = oo_objects(s->oo); int err; /* Bailout if already initialised */ if (s->random_seq) return 0; err = cache_random_seq_create(s, count, GFP_KERNEL); if (err) { pr_err("SLUB: Unable to initialize free list for %s\n", s->name); return err; } /* Transform to an offset on the set of pages */ if (s->random_seq) { unsigned int i; for (i = 0; i < count; i++) s->random_seq[i] *= s->size; } return 0; } /* Initialize each random sequence freelist per cache */ static void __init init_freelist_randomization(void) { struct kmem_cache *s; mutex_lock(&slab_mutex); list_for_each_entry(s, &slab_caches, list) init_cache_random_seq(s); mutex_unlock(&slab_mutex); } /* Get the next entry on the pre-computed freelist randomized */ static void *next_freelist_entry(struct kmem_cache *s, struct slab *slab, unsigned long *pos, void *start, unsigned long page_limit, unsigned long freelist_count) { unsigned int idx; /* * If the target page allocation failed, the number of objects on the * page might be smaller than the usual size defined by the cache. */ do { idx = s->random_seq[*pos]; *pos += 1; if (*pos >= freelist_count) *pos = 0; } while (unlikely(idx >= page_limit)); return (char *)start + idx; } /* Shuffle the single linked freelist based on a random pre-computed sequence */ static bool shuffle_freelist(struct kmem_cache *s, struct slab *slab) { void *start; void *cur; void *next; unsigned long idx, pos, page_limit, freelist_count; if (slab->objects < 2 || !s->random_seq) return false; freelist_count = oo_objects(s->oo); pos = get_random_u32_below(freelist_count); page_limit = slab->objects * s->size; start = fixup_red_left(s, slab_address(slab)); /* First entry is used as the base of the freelist */ cur = next_freelist_entry(s, slab, &pos, start, page_limit, freelist_count); cur = setup_object(s, cur); slab->freelist = cur; for (idx = 1; idx < slab->objects; idx++) { next = next_freelist_entry(s, slab, &pos, start, page_limit, freelist_count); next = setup_object(s, next); set_freepointer(s, cur, next); cur = next; } set_freepointer(s, cur, NULL); return true; } #else static inline int init_cache_random_seq(struct kmem_cache *s) { return 0; } static inline void init_freelist_randomization(void) { } static inline bool shuffle_freelist(struct kmem_cache *s, struct slab *slab) { return false; } #endif /* CONFIG_SLAB_FREELIST_RANDOM */

if (s->flags & __CMPXCHG_DOUBLE) { ret = __update_freelist_fast(slab, freelist_old, counters_old, freelist_new, counters_new); } else { unsigned long flags; local_irq_save(flags); ret = __update_freelist_slow(slab, freelist_old, counters_old, freelist_new, counters_new); local_irq_restore(flags); }

if (dtc->wb_thresh < 2 * wb_stat_error()) { wb_reclaimable = wb_stat_sum(wb, WB_RECLAIMABLE); dtc->wb_dirty = wb_reclaimable + wb_stat_sum(wb, WB_WRITEBACK); } else { wb_reclaimable = wb_stat(wb, WB_RECLAIMABLE); dtc->wb_dirty = wb_reclaimable + wb_stat(wb, WB_WRITEBACK); }

static long wb_min_pause(struct bdi_writeback *wb, long max_pause, unsigned long task_ratelimit, unsigned long dirty_ratelimit, int *nr_dirtied_pause

if (!laptop_mode && nr_reclaimable > gdtc->bg_thresh && !writeback_in_progress(wb)) wb_start_background_writeback(wb);

if (thresh > dirty) return 1UL << (ilog2(thresh - dirty) >> 1);

limit -= (limit - thresh) >> 5;

if (dirty <= dirty_freerun_ceiling(thresh, bg_thresh) && (!mdtc || m_dirty <= dirty_freerun_ceiling(m_thresh, m_bg_thresh))) { unsigned long intv; unsigned long m_intv; free_running: intv = dirty_poll_interval(dirty, thresh); m_intv = ULONG_MAX; current->dirty_paused_when = now; current->nr_dirtied = 0; if (mdtc) m_intv = dirty_poll_interval(m_dirty, m_thresh); current->nr_dirtied_pause = min(intv, m_intv); break; } /* Start writeback even when in laptop mode */ if (unlikely(!writeback_in_progress(wb))) wb_start_background_writeback(wb); mem_cgroup_flush_foreign(wb); /* * Calculate global domain's pos_ratio and select the * global dtc by default. */ if (!strictlimit) { wb_dirty_limits(gdtc); if ((current->flags & PF_LOCAL_THROTTLE) && gdtc->wb_dirty < dirty_freerun_ceiling(gdtc->wb_thresh, gdtc->wb_bg_thresh)) /* * LOCAL_THROTTLE tasks must not be throttled * when below the per-wb freerun ceiling. */ goto free_running; } dirty_exceeded = (gdtc->wb_dirty > gdtc->wb_thresh) && ((gdtc->dirty > gdtc->thresh) || strictlimit); wb_position_ratio(gdtc); sdtc = gdtc; if (mdtc) { /* * If memcg domain is in effect, calculate its * pos_ratio. @wb should satisfy constraints from * both global and memcg domains. Choose the one * w/ lower pos_ratio. */ if (!strictlimit) { wb_dirty_limits(mdtc); if ((current->flags & PF_LOCAL_THROTTLE) && mdtc->wb_dirty < dirty_freerun_ceiling(mdtc->wb_thresh, mdtc->wb_bg_thresh)) /* * LOCAL_THROTTLE tasks must not be * throttled when below the per-wb * freerun ceiling. */ goto free_running; } dirty_exceeded |= (mdtc->wb_dirty > mdtc->wb_thresh) && ((mdtc->dirty > mdtc->thresh) || strictlimit); wb_position_ratio(mdtc); if (mdtc->pos_ratio < gdtc->pos_ratio) sdtc = mdtc; }

shift = dirty_ratelimit / (2 * step + 1); if (shift < BITS_PER_LONG) step = DIV_ROUND_UP(step >> shift, 8); else step = 0; if (dirty_ratelimit < balanced_dirty_ratelimit) dirty_ratelimit += step; else dirty_ratelimit -= step;

ratelimit_pages = dirty_thresh / (num_online_cpus() * 32); if (ratelimit_pages < 16) ratelimit_pages = 16;

t = wb_dirty / (1 + bw / roundup_pow_of_two(1 + HZ / 8));

if (IS_ENABLED(CONFIG_CGROUP_WRITEBACK) && mdtc) {

enum get_ksm_page_flags { GET_KSM_PAGE_NOLOCK, GET_KSM_PAGE_LOCK, GET_KSM_PAGE_TRYLOCK };

static int ksmd_should_run(void) { return (ksm_run & KSM_RUN_MERGE) && !list_empty(&ksm_mm_head.slot.mm_node); }

randomize_stack_top

if (movable_node_is_enabled()) {

if (page_poisoning_enabled() || (!IS_ENABLED(CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC) && debug_pagealloc_enabled())) {

if (descending)

if (overcommit_policy == OVERCOMMIT_NEVER)

if (prev_class) { if (can_merge(prev_class, pages_per_zspage, objs_per_zspage)) { pool->size_class[i] = prev_class; continue; } }

zspage = find_get_zspage(class); if (likely(zspage)) { obj = obj_malloc(pool, zspage, handle); /* Now move the zspage to another fullness group, if required */ fix_fullness_group(class, zspage); record_obj(handle, obj); class_stat_inc(class, ZS_OBJS_INUSE, 1); goto out; }

1

if (!(flags & VM_ALLOC)) area->addr = kasan_unpoison_vmalloc(area->addr, requested_size, KASAN_VMALLOC_PROT_NORMAL);

100U

if (!order) {

if (likely(count <= VMAP_MAX_ALLOC)) { mem = vb_alloc(size, GFP_KERNEL); if (IS_ERR(mem)) return NULL; addr = (unsigned long)mem; } else { struct vmap_area *va; va = alloc_vmap_area(size, PAGE_SIZE, VMALLOC_START, VMALLOC_END, node, GFP_KERNEL, VMAP_RAM); if (IS_ERR(va)) return NULL; addr = va->va_start; mem = (void *)addr; }

VMAP_PURGE_THRESHOLD

if (!(force_purge

resched_threshold = lazy_max_pages() << 1;

log = fls(num_online_cpus());

32UL * 1024 * 1024

static bool should_skip_region(struct memblock_type *type, struct memblock_region *m, int nid, int flags) { int m_nid = memblock_get_region_node(m); /* we never skip regions when iterating memblock.reserved or physmem */ if (type != memblock_memory) return false; /* only memory regions are associated with nodes, check it */ if (nid != NUMA_NO_NODE && nid != m_nid) return true; /* skip hotpluggable memory regions if needed */ if (movable_node_is_enabled() && memblock_is_hotpluggable(m) && !(flags & MEMBLOCK_HOTPLUG)) return true; /* if we want mirror memory skip non-mirror memory regions */ if ((flags & MEMBLOCK_MIRROR) && !memblock_is_mirror(m)) return true; /* skip nomap memory unless we were asked for it explicitly */ if (!(flags & MEMBLOCK_NOMAP) && memblock_is_nomap(m)) return true; /* skip driver-managed memory unless we were asked for it explicitly */ if (!(flags & MEMBLOCK_DRIVER_MANAGED) && memblock_is_driver_managed(m)) return true; return false; }

if (memblock_bottom_up())

if (lruvec->file_cost + lruvec->anon_cost > lrusize / 4) { lruvec->file_cost /= 2; lruvec->anon_cost /= 2; }

if (megs < 16) page_cluster = 2; else page_cluster = 3;

mod_memcg_page_state(area->pages[i], MEMCG_VMALLOC, 1);

schedule_timeout_uninterruptible(1);

if (array_size > PAGE_SIZE) { area->pages = __vmalloc_node(array_size, 1, nested_gfp, node, area->caller); } else { area->pages = kmalloc_node(array_size, nested_gfp, node); }

if (!counters) return; if (v->flags & VM_UNINITIALIZED) return;

if (page) copied = copy_page_to_iter_nofault(page, offset, length, iter); else copied = zero_iter(iter, length);

if (base + last_end < vmalloc_start + last_end) goto overflow; /* * Fitting base has not been found. */ if (va == NULL) goto overflow;

if (base + start < va->va_start) { va = node_to_va(rb_prev(&va->rb_node)); base = pvm_determine_end_from_reverse(&va, align) - end; term_area = area; continue; }

if (base + end > va->va_end) { base = pvm_determine_end_from_reverse(&va, align) - end; term_area = area; continue; }

va = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT); if (WARN_ON_ONCE(!va)) continue;

if (!spin_trylock(&vmap_area_lock)) return false;

if (hugetlb_cgroup_disabled())