diff options
Diffstat (limited to 'mm/gup.c')
-rw-r--r-- | mm/gup.c | 2617 |
1 files changed, 1516 insertions, 1101 deletions
@@ -10,6 +10,7 @@ #include <linux/rmap.h> #include <linux/swap.h> #include <linux/swapops.h> +#include <linux/secretmem.h> #include <linux/sched/signal.h> #include <linux/rwsem.h> @@ -17,6 +18,7 @@ #include <linux/migrate.h> #include <linux/mm_inline.h> #include <linux/sched/mm.h> +#include <linux/shmem_fs.h> #include <asm/mmu_context.h> #include <asm/tlbflush.h> @@ -28,189 +30,235 @@ struct follow_page_context { unsigned int page_mask; }; -static void hpage_pincount_add(struct page *page, int refs) +static inline void sanity_check_pinned_pages(struct page **pages, + unsigned long npages) { - VM_BUG_ON_PAGE(!hpage_pincount_available(page), page); - VM_BUG_ON_PAGE(page != compound_head(page), page); - - atomic_add(refs, compound_pincount_ptr(page)); -} + if (!IS_ENABLED(CONFIG_DEBUG_VM)) + return; -static void hpage_pincount_sub(struct page *page, int refs) -{ - VM_BUG_ON_PAGE(!hpage_pincount_available(page), page); - VM_BUG_ON_PAGE(page != compound_head(page), page); + /* + * We only pin anonymous pages if they are exclusive. Once pinned, we + * can no longer turn them possibly shared and PageAnonExclusive() will + * stick around until the page is freed. + * + * We'd like to verify that our pinned anonymous pages are still mapped + * exclusively. The issue with anon THP is that we don't know how + * they are/were mapped when pinning them. However, for anon + * THP we can assume that either the given page (PTE-mapped THP) or + * the head page (PMD-mapped THP) should be PageAnonExclusive(). If + * neither is the case, there is certainly something wrong. + */ + for (; npages; npages--, pages++) { + struct page *page = *pages; + struct folio *folio = page_folio(page); - atomic_sub(refs, compound_pincount_ptr(page)); + if (is_zero_page(page) || + !folio_test_anon(folio)) + continue; + if (!folio_test_large(folio) || folio_test_hugetlb(folio)) + VM_BUG_ON_PAGE(!PageAnonExclusive(&folio->page), page); + else + /* Either a PTE-mapped or a PMD-mapped THP. */ + VM_BUG_ON_PAGE(!PageAnonExclusive(&folio->page) && + !PageAnonExclusive(page), page); + } } /* - * Return the compound head page with ref appropriately incremented, + * Return the folio with ref appropriately incremented, * or NULL if that failed. */ -static inline struct page *try_get_compound_head(struct page *page, int refs) +static inline struct folio *try_get_folio(struct page *page, int refs) { - struct page *head = compound_head(page); + struct folio *folio; - if (WARN_ON_ONCE(page_ref_count(head) < 0)) +retry: + folio = page_folio(page); + if (WARN_ON_ONCE(folio_ref_count(folio) < 0)) return NULL; - if (unlikely(!page_cache_add_speculative(head, refs))) + if (unlikely(!folio_ref_try_add_rcu(folio, refs))) return NULL; - return head; + + /* + * At this point we have a stable reference to the folio; but it + * could be that between calling page_folio() and the refcount + * increment, the folio was split, in which case we'd end up + * holding a reference on a folio that has nothing to do with the page + * we were given anymore. + * So now that the folio is stable, recheck that the page still + * belongs to this folio. + */ + if (unlikely(page_folio(page) != folio)) { + if (!put_devmap_managed_page_refs(&folio->page, refs)) + folio_put_refs(folio, refs); + goto retry; + } + + return folio; } -/* - * try_grab_compound_head() - attempt to elevate a page's refcount, by a - * flags-dependent amount. +/** + * try_grab_folio() - Attempt to get or pin a folio. + * @page: pointer to page to be grabbed + * @refs: the value to (effectively) add to the folio's refcount + * @flags: gup flags: these are the FOLL_* flag values. * * "grab" names in this file mean, "look at flags to decide whether to use - * FOLL_PIN or FOLL_GET behavior, when incrementing the page's refcount. + * FOLL_PIN or FOLL_GET behavior, when incrementing the folio's refcount. * * Either FOLL_PIN or FOLL_GET (or neither) must be set, but not both at the * same time. (That's true throughout the get_user_pages*() and * pin_user_pages*() APIs.) Cases: * - * FOLL_GET: page's refcount will be incremented by 1. - * FOLL_PIN: page's refcount will be incremented by GUP_PIN_COUNTING_BIAS. + * FOLL_GET: folio's refcount will be incremented by @refs. + * + * FOLL_PIN on large folios: folio's refcount will be incremented by + * @refs, and its pincount will be incremented by @refs. * - * Return: head page (with refcount appropriately incremented) for success, or - * NULL upon failure. If neither FOLL_GET nor FOLL_PIN was set, that's - * considered failure, and furthermore, a likely bug in the caller, so a warning - * is also emitted. + * FOLL_PIN on single-page folios: folio's refcount will be incremented by + * @refs * GUP_PIN_COUNTING_BIAS. + * + * Return: The folio containing @page (with refcount appropriately + * incremented) for success, or NULL upon failure. If neither FOLL_GET + * nor FOLL_PIN was set, that's considered failure, and furthermore, + * a likely bug in the caller, so a warning is also emitted. */ -static __maybe_unused struct page *try_grab_compound_head(struct page *page, - int refs, - unsigned int flags) +struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags) { + struct folio *folio; + + 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_compound_head(page, refs); - else if (flags & FOLL_PIN) { - int orig_refs = refs; + return try_get_folio(page, refs); - /* - * Can't do FOLL_LONGTERM + FOLL_PIN with CMA in the gup fast - * path, so fail and let the caller fall back to the slow path. - */ - if (unlikely(flags & FOLL_LONGTERM) && - is_migrate_cma_page(page)) - return NULL; + /* FOLL_PIN is set */ - /* - * When pinning a compound page of order > 1 (which is what - * hpage_pincount_available() checks for), use an exact count to - * track it, via hpage_pincount_add/_sub(). - * - * However, be sure to *also* increment the normal page refcount - * field at least once, so that the page really is pinned. - */ - if (!hpage_pincount_available(page)) - refs *= GUP_PIN_COUNTING_BIAS; + /* + * 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 page_folio(page); + + folio = try_get_folio(page, refs); + if (!folio) + return NULL; + + /* + * Can't do FOLL_LONGTERM + FOLL_PIN gup fast path if not in a + * right zone, so fail and let the caller fall back to the slow + * path. + */ + 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; + } - page = try_get_compound_head(page, refs); - if (!page) - return NULL; + /* + * When pinning a large folio, use an exact count to track it. + * + * However, be sure to *also* increment the normal folio + * refcount field at least once, so that the folio really + * is pinned. That's why the refcount from the earlier + * try_get_folio() is left intact. + */ + if (folio_test_large(folio)) + atomic_add(refs, &folio->_pincount); + else + folio_ref_add(folio, + refs * (GUP_PIN_COUNTING_BIAS - 1)); + /* + * Adjust the pincount before re-checking the PTE for changes. + * This is essentially a smp_mb() and is paired with a memory + * barrier in folio_try_share_anon_rmap_*(). + */ + smp_mb__after_atomic(); - if (hpage_pincount_available(page)) - hpage_pincount_add(page, refs); + node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, refs); - mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_ACQUIRED, - orig_refs); + return folio; +} - return page; +static void gup_put_folio(struct folio *folio, int refs, unsigned int flags) +{ + 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; } - WARN_ON_ONCE(1); - return NULL; + if (!put_devmap_managed_page_refs(&folio->page, refs)) + folio_put_refs(folio, refs); } /** * try_grab_page() - elevate a page's refcount by a flag-dependent amount + * @page: pointer to page to be grabbed + * @flags: gup flags: these are the FOLL_* flag values. * * This might not do anything at all, depending on the flags argument. * * "grab" names in this file mean, "look at flags to decide whether to use * FOLL_PIN or FOLL_GET behavior, when incrementing the page's refcount. * - * @page: pointer to page to be grabbed - * @flags: gup flags: these are the FOLL_* flag values. - * * Either FOLL_PIN or FOLL_GET (or neither) may be set, but not both at the same - * time. Cases: + * time. Cases: please see the try_grab_folio() documentation, with + * "refs=1". * - * FOLL_GET: page's refcount will be incremented by 1. - * FOLL_PIN: page's refcount will be incremented by GUP_PIN_COUNTING_BIAS. + * Return: 0 for success, or if no action was required (if neither FOLL_PIN + * nor FOLL_GET was set, nothing is done). A negative error code for failure: * - * Return: true for success, or if no action was required (if neither FOLL_PIN - * nor FOLL_GET was set, nothing is done). False for failure: FOLL_GET or - * FOLL_PIN was set, but the page could not be grabbed. + * -ENOMEM FOLL_GET or FOLL_PIN was set, but the page could not + * be grabbed. */ -bool __must_check try_grab_page(struct page *page, unsigned int flags) +int __must_check try_grab_page(struct page *page, unsigned int flags) { - WARN_ON_ONCE((flags & (FOLL_GET | FOLL_PIN)) == (FOLL_GET | FOLL_PIN)); - - if (flags & FOLL_GET) - return try_get_page(page); - else if (flags & FOLL_PIN) { - int refs = 1; + struct folio *folio = page_folio(page); - page = compound_head(page); + if (WARN_ON_ONCE(folio_ref_count(folio) <= 0)) + return -ENOMEM; - if (WARN_ON_ONCE(page_ref_count(page) <= 0)) - return false; + if (unlikely(!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(page))) + return -EREMOTEIO; - if (hpage_pincount_available(page)) - hpage_pincount_add(page, 1); - else - refs = GUP_PIN_COUNTING_BIAS; + 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_compound_head(): even if using the - * hpage_pincount_add/_sub() routines, be sure to - * *also* increment the normal page refcount field at least - * once, so that the page really is pinned. + * 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. */ - page_ref_add(page, refs); + if (folio_test_large(folio)) { + folio_ref_add(folio, 1); + atomic_add(1, &folio->_pincount); + } else { + folio_ref_add(folio, GUP_PIN_COUNTING_BIAS); + } - mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_ACQUIRED, 1); + node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, 1); } - return true; -} - -#ifdef CONFIG_DEV_PAGEMAP_OPS -static bool __unpin_devmap_managed_user_page(struct page *page) -{ - int count, refs = 1; - - if (!page_is_devmap_managed(page)) - return false; - - if (hpage_pincount_available(page)) - hpage_pincount_sub(page, 1); - else - refs = GUP_PIN_COUNTING_BIAS; - - count = page_ref_sub_return(page, refs); - - mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_RELEASED, 1); - /* - * devmap page refcounts are 1-based, rather than 0-based: if - * refcount is 1, then the page is free and the refcount is - * stable because nobody holds a reference on the page. - */ - if (count == 1) - free_devmap_managed_page(page); - else if (!count) - __put_page(page); - - return true; -} -#else -static bool __unpin_devmap_managed_user_page(struct page *page) -{ - return false; + return 0; } -#endif /* CONFIG_DEV_PAGEMAP_OPS */ /** * unpin_user_page() - release a dma-pinned page @@ -223,30 +271,67 @@ static bool __unpin_devmap_managed_user_page(struct page *page) */ void unpin_user_page(struct page *page) { - int refs = 1; + sanity_check_pinned_pages(&page, 1); + gup_put_folio(page_folio(page), 1, FOLL_PIN); +} +EXPORT_SYMBOL(unpin_user_page); - page = compound_head(page); +/** + * folio_add_pin - Try to get an additional pin on a pinned folio + * @folio: The folio to be pinned + * + * Get an additional pin on a folio we already have a pin on. Makes no change + * if the folio is a zero_page. + */ +void folio_add_pin(struct folio *folio) +{ + if (is_zero_folio(folio)) + return; /* - * For devmap managed pages we need to catch refcount transition from - * GUP_PIN_COUNTING_BIAS to 1, when refcount reach one it means the - * page is free and we need to inform the device driver through - * callback. See include/linux/memremap.h and HMM for details. + * 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 (__unpin_devmap_managed_user_page(page)) - return; + if (folio_test_large(folio)) { + WARN_ON_ONCE(atomic_read(&folio->_pincount) < 1); + folio_ref_inc(folio); + atomic_inc(&folio->_pincount); + } else { + WARN_ON_ONCE(folio_ref_count(folio) < GUP_PIN_COUNTING_BIAS); + folio_ref_add(folio, GUP_PIN_COUNTING_BIAS); + } +} - if (hpage_pincount_available(page)) - hpage_pincount_sub(page, 1); - else - refs = GUP_PIN_COUNTING_BIAS; +static inline struct folio *gup_folio_range_next(struct page *start, + unsigned long npages, unsigned long i, unsigned int *ntails) +{ + struct page *next = nth_page(start, i); + struct folio *folio = page_folio(next); + unsigned int nr = 1; - if (page_ref_sub_and_test(page, refs)) - __put_page(page); + if (folio_test_large(folio)) + nr = min_t(unsigned int, npages - i, + folio_nr_pages(folio) - folio_page_idx(folio, next)); - mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_RELEASED, 1); + *ntails = nr; + return folio; +} + +static inline struct folio *gup_folio_next(struct page **list, + unsigned long npages, unsigned long i, unsigned int *ntails) +{ + struct folio *folio = page_folio(list[i]); + unsigned int nr; + + for (nr = i + 1; nr < npages; nr++) { + if (page_folio(list[nr]) != folio) + break; + } + + *ntails = nr - i; + return folio; } -EXPORT_SYMBOL(unpin_user_page); /** * unpin_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages @@ -273,21 +358,18 @@ EXPORT_SYMBOL(unpin_user_page); void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages, bool make_dirty) { - unsigned long index; - - /* - * TODO: this can be optimized for huge pages: if a series of pages is - * physically contiguous and part of the same compound page, then a - * single operation to the head page should suffice. - */ + unsigned long i; + struct folio *folio; + unsigned int nr; if (!make_dirty) { unpin_user_pages(pages, npages); return; } - for (index = 0; index < npages; index++) { - struct page *page = compound_head(pages[index]); + sanity_check_pinned_pages(pages, npages); + for (i = 0; i < npages; i += nr) { + folio = gup_folio_next(pages, npages, i, &nr); /* * Checking PageDirty at this point may race with * clear_page_dirty_for_io(), but that's OK. Two key @@ -308,14 +390,74 @@ void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages, * written back, so it gets written back again in the * next writeback cycle. This is harmless. */ - if (!PageDirty(page)) - set_page_dirty_lock(page); - unpin_user_page(page); + if (!folio_test_dirty(folio)) { + folio_lock(folio); + folio_mark_dirty(folio); + folio_unlock(folio); + } + gup_put_folio(folio, nr, FOLL_PIN); } } EXPORT_SYMBOL(unpin_user_pages_dirty_lock); /** + * unpin_user_page_range_dirty_lock() - release and optionally dirty + * gup-pinned page range + * + * @page: the starting page of a range maybe marked dirty, and definitely released. + * @npages: number of consecutive pages to release. + * @make_dirty: whether to mark the pages dirty + * + * "gup-pinned page range" refers to a range of pages that has had one of the + * pin_user_pages() variants called on that page. + * + * For the page ranges defined by [page .. page+npages], make that range (or + * its head pages, if a compound page) dirty, if @make_dirty is true, and if the + * page range was previously listed as clean. + * + * set_page_dirty_lock() is used internally. If instead, set_page_dirty() is + * required, then the caller should a) verify that this is really correct, + * because _lock() is usually required, and b) hand code it: + * set_page_dirty_lock(), unpin_user_page(). + * + */ +void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages, + bool make_dirty) +{ + unsigned long i; + struct folio *folio; + unsigned int nr; + + for (i = 0; i < npages; i += nr) { + folio = gup_folio_range_next(page, npages, i, &nr); + if (make_dirty && !folio_test_dirty(folio)) { + folio_lock(folio); + folio_mark_dirty(folio); + folio_unlock(folio); + } + gup_put_folio(folio, nr, FOLL_PIN); + } +} +EXPORT_SYMBOL(unpin_user_page_range_dirty_lock); + +static void unpin_user_pages_lockless(struct page **pages, unsigned long npages) +{ + unsigned long i; + struct folio *folio; + unsigned int nr; + + /* + * Don't perform any sanity checks because we might have raced with + * fork() and some anonymous pages might now actually be shared -- + * which is why we're unpinning after all. + */ + for (i = 0; i < npages; i += nr) { + folio = gup_folio_next(pages, npages, i, &nr); + gup_put_folio(folio, nr, FOLL_PIN); + } +} + +/** * 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. @@ -326,7 +468,9 @@ EXPORT_SYMBOL(unpin_user_pages_dirty_lock); */ void unpin_user_pages(struct page **pages, unsigned long npages) { - unsigned long index; + unsigned long i; + struct folio *folio; + unsigned int nr; /* * If this WARN_ON() fires, then the system *might* be leaking pages (by @@ -335,16 +479,26 @@ void unpin_user_pages(struct page **pages, unsigned long npages) */ if (WARN_ON(IS_ERR_VALUE(npages))) return; - /* - * TODO: this can be optimized for huge pages: if a series of pages is - * physically contiguous and part of the same compound page, then a - * single operation to the head page should suffice. - */ - for (index = 0; index < npages; index++) - unpin_user_page(pages[index]); + + 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); + } } EXPORT_SYMBOL(unpin_user_pages); +/* + * Set the MMF_HAS_PINNED if not set yet; after set it'll be there for the mm's + * lifecycle. Avoid setting the bit unless necessary, or it might cause write + * cache bouncing on large SMP machines for concurrent pinned gups. + */ +static inline void mm_set_has_pinned_flag(unsigned long *mm_flags) +{ + if (!test_bit(MMF_HAS_PINNED, mm_flags)) + set_bit(MMF_HAS_PINNED, mm_flags); +} + #ifdef CONFIG_MMU static struct page *no_page_table(struct vm_area_struct *vma, unsigned int flags) @@ -366,18 +520,15 @@ static struct page *no_page_table(struct vm_area_struct *vma, static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address, pte_t *pte, unsigned int flags) { - /* No page to get reference */ - if (flags & FOLL_GET) - return -EFAULT; - if (flags & FOLL_TOUCH) { - pte_t entry = *pte; + 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(*pte, entry)) { + if (!pte_same(orig_entry, entry)) { set_pte_at(vma->vm_mm, address, pte, entry); update_mmu_cache(vma, address, pte); } @@ -387,14 +538,42 @@ static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address, return -EEXIST; } -/* - * FOLL_FORCE can write to even unwritable pte's, but only - * after we've gone through a COW cycle and they are dirty. - */ -static inline bool can_follow_write_pte(pte_t pte, unsigned int flags) +/* FOLL_FORCE can write to even unwritable PTEs in COW mappings. */ +static inline bool can_follow_write_pte(pte_t pte, struct page *page, + struct vm_area_struct *vma, + unsigned int flags) { - return pte_write(pte) || - ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pte_dirty(pte)); + /* If the pte is writable, we can write to the 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); } static struct page *follow_page_pte(struct vm_area_struct *vma, @@ -411,38 +590,28 @@ static struct page *follow_page_pte(struct vm_area_struct *vma, if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) == (FOLL_PIN | FOLL_GET))) return ERR_PTR(-EINVAL); -retry: - if (unlikely(pmd_bad(*pmd))) - return no_page_table(vma, flags); ptep = pte_offset_map_lock(mm, pmd, address, &ptl); - pte = *ptep; - if (!pte_present(pte)) { - swp_entry_t entry; - /* - * KSM's break_ksm() relies upon recognizing a ksm page - * even while it is being migrated, so for that case we - * need migration_entry_wait(). - */ - if (likely(!(flags & FOLL_MIGRATION))) - goto no_page; - if (pte_none(pte)) - goto no_page; - entry = pte_to_swp_entry(pte); - if (!is_migration_entry(entry)) - goto no_page; - pte_unmap_unlock(ptep, ptl); - migration_entry_wait(mm, pmd, address); - goto retry; - } - if ((flags & FOLL_NUMA) && pte_protnone(pte)) + 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; - if ((flags & FOLL_WRITE) && !can_follow_write_pte(pte, flags)) { - pte_unmap_unlock(ptep, ptl); - return NULL; - } 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 @@ -470,23 +639,21 @@ retry: } } - if (flags & FOLL_SPLIT && PageTransCompound(page)) { - get_page(page); - pte_unmap_unlock(ptep, ptl); - lock_page(page); - ret = split_huge_page(page); - unlock_page(page); - put_page(page); - if (ret) - return ERR_PTR(ret); - goto retry; + 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. */ - if (unlikely(!try_grab_page(page, flags))) { - page = ERR_PTR(-ENOMEM); + 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 @@ -511,32 +678,6 @@ retry: */ mark_page_accessed(page); } - if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) { - /* Do not mlock pte-mapped THP */ - if (PageTransCompound(page)) - goto out; - - /* - * The preliminary mapping check is mainly to avoid the - * pointless overhead of lock_page on the ZERO_PAGE - * which might bounce very badly if there is contention. - * - * If the page is already locked, we don't need to - * handle it now - vmscan will handle it later if and - * when it attempts to reclaim the page. - */ - if (page->mapping && trylock_page(page)) { - lru_add_drain(); /* push cached pages to LRU */ - /* - * Because we lock page here, and migration is - * blocked by the pte's page reference, and we - * know the page is still mapped, we don't even - * need to check for file-cache page truncation. - */ - mlock_vma_page(page); - unlock_page(page); - } - } out: pte_unmap_unlock(ptep, ptl); return page; @@ -558,102 +699,39 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma, struct mm_struct *mm = vma->vm_mm; pmd = pmd_offset(pudp, address); - /* - * The READ_ONCE() will stabilize the pmdval in a register or - * on the stack so that it will stop changing under the code. - */ - pmdval = READ_ONCE(*pmd); + pmdval = pmdp_get_lockless(pmd); if (pmd_none(pmdval)) return no_page_table(vma, flags); - if (pmd_huge(pmdval) && is_vm_hugetlb_page(vma)) { - page = follow_huge_pmd(mm, address, pmd, flags); - if (page) - return page; + if (!pmd_present(pmdval)) return no_page_table(vma, flags); - } - if (is_hugepd(__hugepd(pmd_val(pmdval)))) { - page = follow_huge_pd(vma, address, - __hugepd(pmd_val(pmdval)), flags, - PMD_SHIFT); - if (page) - return page; - return no_page_table(vma, flags); - } -retry: - if (!pmd_present(pmdval)) { - if (likely(!(flags & FOLL_MIGRATION))) - return no_page_table(vma, flags); - VM_BUG_ON(thp_migration_supported() && - !is_pmd_migration_entry(pmdval)); - if (is_pmd_migration_entry(pmdval)) - pmd_migration_entry_wait(mm, pmd); - pmdval = READ_ONCE(*pmd); - /* - * MADV_DONTNEED may convert the pmd to null because - * mmap_lock is held in read mode - */ - if (pmd_none(pmdval)) - return no_page_table(vma, flags); - goto retry; - } if (pmd_devmap(pmdval)) { ptl = pmd_lock(mm, pmd); page = follow_devmap_pmd(vma, address, pmd, flags, &ctx->pgmap); spin_unlock(ptl); if (page) return page; + return no_page_table(vma, flags); } if (likely(!pmd_trans_huge(pmdval))) return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); - if ((flags & FOLL_NUMA) && pmd_protnone(pmdval)) + if (pmd_protnone(pmdval) && !gup_can_follow_protnone(vma, flags)) return no_page_table(vma, flags); -retry_locked: ptl = pmd_lock(mm, pmd); - if (unlikely(pmd_none(*pmd))) { - spin_unlock(ptl); - return no_page_table(vma, flags); - } if (unlikely(!pmd_present(*pmd))) { spin_unlock(ptl); - if (likely(!(flags & FOLL_MIGRATION))) - return no_page_table(vma, flags); - pmd_migration_entry_wait(mm, pmd); - goto retry_locked; + return no_page_table(vma, flags); } if (unlikely(!pmd_trans_huge(*pmd))) { spin_unlock(ptl); return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); } - if (flags & (FOLL_SPLIT | FOLL_SPLIT_PMD)) { - int ret; - page = pmd_page(*pmd); - if (is_huge_zero_page(page)) { - spin_unlock(ptl); - ret = 0; - split_huge_pmd(vma, pmd, address); - if (pmd_trans_unstable(pmd)) - ret = -EBUSY; - } else if (flags & FOLL_SPLIT) { - if (unlikely(!try_get_page(page))) { - spin_unlock(ptl); - return ERR_PTR(-ENOMEM); - } - spin_unlock(ptl); - lock_page(page); - ret = split_huge_page(page); - unlock_page(page); - put_page(page); - if (pmd_none(*pmd)) - return no_page_table(vma, flags); - } else { /* flags & FOLL_SPLIT_PMD */ - spin_unlock(ptl); - split_huge_pmd(vma, pmd, address); - ret = pte_alloc(mm, pmd) ? -ENOMEM : 0; - } - - return ret ? ERR_PTR(ret) : + 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); @@ -675,26 +753,13 @@ static struct page *follow_pud_mask(struct vm_area_struct *vma, pud = pud_offset(p4dp, address); if (pud_none(*pud)) return no_page_table(vma, flags); - if (pud_huge(*pud) && is_vm_hugetlb_page(vma)) { - page = follow_huge_pud(mm, address, pud, flags); - if (page) - return page; - return no_page_table(vma, flags); - } - if (is_hugepd(__hugepd(pud_val(*pud)))) { - page = follow_huge_pd(vma, address, - __hugepd(pud_val(*pud)), flags, - PUD_SHIFT); - if (page) - return page; - return no_page_table(vma, flags); - } if (pud_devmap(*pud)) { ptl = pud_lock(mm, pud); page = follow_devmap_pud(vma, address, pud, flags, &ctx->pgmap); spin_unlock(ptl); if (page) return page; + return no_page_table(vma, flags); } if (unlikely(pud_bad(*pud))) return no_page_table(vma, flags); @@ -708,7 +773,6 @@ static struct page *follow_p4d_mask(struct vm_area_struct *vma, struct follow_page_context *ctx) { p4d_t *p4d; - struct page *page; p4d = p4d_offset(pgdp, address); if (p4d_none(*p4d)) @@ -717,14 +781,6 @@ static struct page *follow_p4d_mask(struct vm_area_struct *vma, if (unlikely(p4d_bad(*p4d))) return no_page_table(vma, flags); - if (is_hugepd(__hugepd(p4d_val(*p4d)))) { - page = follow_huge_pd(vma, address, - __hugepd(p4d_val(*p4d)), flags, - P4D_SHIFT); - if (page) - return page; - return no_page_table(vma, flags); - } return follow_pud_mask(vma, address, p4d, flags, ctx); } @@ -741,6 +797,11 @@ static struct page *follow_p4d_mask(struct vm_area_struct *vma, * When getting pages from ZONE_DEVICE memory, the @ctx->pgmap caches * the device's dev_pagemap metadata to avoid repeating expensive lookups. * + * When getting an anonymous page and the caller has to trigger unsharing + * of a shared anonymous page first, -EMLINK is returned. The caller should + * trigger a fault with FAULT_FLAG_UNSHARE set. Note that unsharing is only + * relevant with FOLL_PIN and !FOLL_WRITE. + * * On output, the @ctx->page_mask is set according to the size of the page. * * Return: the mapped (struct page *), %NULL if no mapping exists, or @@ -752,38 +813,24 @@ static struct page *follow_page_mask(struct vm_area_struct *vma, struct follow_page_context *ctx) { pgd_t *pgd; - struct page *page; struct mm_struct *mm = vma->vm_mm; ctx->page_mask = 0; - /* make this handle hugepd */ - page = follow_huge_addr(mm, address, flags & FOLL_WRITE); - if (!IS_ERR(page)) { - WARN_ON_ONCE(flags & (FOLL_GET | FOLL_PIN)); - return page; - } + /* + * 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); - if (pgd_huge(*pgd)) { - page = follow_huge_pgd(mm, address, pgd, flags); - if (page) - return page; - return no_page_table(vma, flags); - } - if (is_hugepd(__hugepd(pgd_val(*pgd)))) { - page = follow_huge_pd(vma, address, - __hugepd(pgd_val(*pgd)), flags, - PGDIR_SHIFT); - if (page) - return page; - return no_page_table(vma, flags); - } - return follow_p4d_mask(vma, address, pgd, flags, ctx); } @@ -793,6 +840,16 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, 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); @@ -808,6 +865,7 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address, pud_t *pud; pmd_t *pmd; pte_t *pte; + pte_t entry; int ret = -EFAULT; /* user gate pages are read-only */ @@ -828,23 +886,24 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address, pmd = pmd_offset(pud, address); if (!pmd_present(*pmd)) return -EFAULT; - VM_BUG_ON(pmd_trans_huge(*pmd)); pte = pte_offset_map(pmd, address); - if (pte_none(*pte)) + if (!pte) + return -EFAULT; + entry = ptep_get(pte); + if (pte_none(entry)) goto unmap; *vma = get_gate_vma(mm); if (!page) goto out; - *page = vm_normal_page(*vma, address, *pte); + *page = vm_normal_page(*vma, address, entry); if (!*page) { - if ((gup_flags & FOLL_DUMP) || !is_zero_pfn(pte_pfn(*pte))) + if ((gup_flags & FOLL_DUMP) || !is_zero_pfn(pte_pfn(entry))) goto unmap; - *page = pte_page(*pte); + *page = pte_page(entry); } - if (unlikely(!try_grab_page(*page, gup_flags))) { - ret = -ENOMEM; + ret = try_grab_page(*page, gup_flags); + if (unlikely(ret)) goto unmap; - } out: ret = 0; unmap: @@ -853,25 +912,34 @@ unmap: } /* - * mmap_lock must be held on entry. If @locked != NULL and *@flags - * does not include FOLL_NOWAIT, the mmap_lock may be released. If it - * is, *@locked will be set to 0 and -EBUSY returned. + * mmap_lock must be held on entry. If @flags has FOLL_UNLOCKABLE but not + * FOLL_NOWAIT, the mmap_lock may be released. If it is, *@locked will be set + * to 0 and -EBUSY returned. */ static int faultin_page(struct vm_area_struct *vma, - unsigned long address, unsigned int *flags, int *locked) + unsigned long address, unsigned int *flags, bool unshare, + int *locked) { unsigned int fault_flags = 0; vm_fault_t ret; - /* mlock all present pages, but do not fault in new pages */ - if ((*flags & (FOLL_POPULATE | FOLL_MLOCK)) == FOLL_MLOCK) - return -ENOENT; + 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 (locked) + 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) { @@ -881,8 +949,32 @@ static int faultin_page(struct vm_area_struct *vma, */ 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); @@ -892,23 +984,49 @@ static int faultin_page(struct vm_area_struct *vma, } if (ret & VM_FAULT_RETRY) { - if (locked && !(fault_flags & FAULT_FLAG_RETRY_NOWAIT)) + if (!(fault_flags & FAULT_FLAG_RETRY_NOWAIT)) *locked = 0; return -EBUSY; } + return 0; +} + +/* + * Writing to file-backed mappings which require folio dirty tracking using GUP + * is a fundamentally broken operation, as kernel write access to GUP mappings + * do not adhere to the semantics expected by a file system. + * + * Consider the following scenario:- + * + * 1. A folio is written to via GUP which write-faults the memory, notifying + * the file system and dirtying the folio. + * 2. Later, writeback is triggered, resulting in the folio being cleaned and + * the PTE being marked read-only. + * 3. The GUP caller writes to the folio, as it is mapped read/write via the + * direct mapping. + * 4. The GUP caller, now done with the page, unpins it and sets it dirty + * (though it does not have to). + * + * This results in both data being written to a folio without writenotify, and + * the folio being dirtied unexpectedly (if the caller decides to do so). + */ +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; + /* - * The VM_FAULT_WRITE bit tells us that do_wp_page has broken COW when - * necessary, even if maybe_mkwrite decided not to set pte_write. We - * can thus safely do subsequent page lookups as if they were reads. - * But only do so when looping for pte_write is futile: in some cases - * userspace may also be wanting to write to the gotten user page, - * which a read fault here might prevent (a readonly page might get - * reCOWed by userspace write). + * If the VMA does not require dirty tracking then no problematic write + * can occur either. */ - if ((ret & VM_FAULT_WRITE) && !(vma->vm_flags & VM_WRITE)) - *flags |= FOLL_COW; - return 0; + return !vma_needs_dirty_tracking(vma); } static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags) @@ -916,17 +1034,31 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags) vm_flags_t vm_flags = vma->vm_flags; int write = (gup_flags & FOLL_WRITE); int foreign = (gup_flags & FOLL_REMOTE); + bool vma_anon = vma_is_anonymous(vma); if (vm_flags & (VM_IO | VM_PFNMAP)) return -EFAULT; - if (gup_flags & FOLL_ANON && !vma_is_anonymous(vma)) + if ((gup_flags & FOLL_ANON) && !vma_anon) + return -EFAULT; + + if ((gup_flags & FOLL_LONGTERM) && vma_is_fsdax(vma)) + return -EOPNOTSUPP; + + if (vma_is_secretmem(vma)) return -EFAULT; if (write) { - if (!(vm_flags & VM_WRITE)) { + if (!vma_anon && + !writable_file_mapping_allowed(vma, gup_flags)) + return -EFAULT; + + 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 @@ -958,6 +1090,45 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags) return 0; } +/* + * This is "vma_lookup()", but with a warning if we would have + * historically expanded the stack in the GUP code. + */ +static struct vm_area_struct *gup_vma_lookup(struct mm_struct *mm, + unsigned long addr) +{ +#ifdef CONFIG_STACK_GROWSUP + return vma_lookup(mm, addr); +#else + static volatile unsigned long next_warn; + struct vm_area_struct *vma; + unsigned long now, next; + + vma = find_vma(mm, addr); + if (!vma || (addr >= vma->vm_start)) + return vma; + + /* Only warn for half-way relevant accesses */ + if (!(vma->vm_flags & VM_GROWSDOWN)) + return NULL; + if (vma->vm_start - addr > 65536) + return NULL; + + /* Let's not warn more than once an hour.. */ + now = jiffies; next = next_warn; + if (next && time_before(now, next)) + return NULL; + next_warn = now + 60*60*HZ; + + /* Let people know things may have changed. */ + pr_warn("GUP no longer grows the stack in %s (%d): %lx-%lx (%lx)\n", + current->comm, task_pid_nr(current), + vma->vm_start, vma->vm_end, addr); + dump_stack(); + return NULL; +#endif +} + /** * __get_user_pages() - pin user pages in memory * @mm: mm_struct of target mm @@ -967,8 +1138,6 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags) * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. Or NULL, if caller * only intends to ensure the pages are faulted in. - * @vmas: array of pointers to vmas corresponding to each page. - * Or NULL if the caller does not require them. * @locked: whether we're still with the mmap_lock held * * Returns either number of pages pinned (which may be less than the @@ -982,8 +1151,6 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags) * * The caller is responsible for releasing returned @pages, via put_page(). * - * @vmas are valid only as long as mmap_lock is held. - * * Must be called with mmap_lock held. It may be released. See below. * * __get_user_pages walks a process's page tables and takes a reference to @@ -994,7 +1161,7 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags) * This does not guarantee that the page exists in the user mappings when * __get_user_pages returns, and there may even be a completely different * page there in some cases (eg. if mmapped pagecache has been invalidated - * and subsequently re faulted). However it does guarantee that the page + * and subsequently re-faulted). However it does guarantee that the page * won't be freed completely. And mostly callers simply care that the page * contains data that was valid *at some point in time*. Typically, an IO * or similar operation cannot guarantee anything stronger anyway because @@ -1005,14 +1172,12 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags) * appropriate) must be called after the page is finished with, and * before put_page is called. * - * If @locked != NULL, *@locked will be set to 0 when mmap_lock is - * released by an up_read(). That can happen if @gup_flags does not - * have FOLL_NOWAIT. + * If FOLL_UNLOCKABLE is set without FOLL_NOWAIT then the mmap_lock may + * be released. If this happens *@locked will be set to 0 on return. * - * A caller using such a combination of @locked and @gup_flags - * must therefore hold the mmap_lock for reading only, and recognize - * when it's been released. Otherwise, it must be held for either - * reading or writing and will not be released. + * A caller using such a combination of @gup_flags must therefore hold the + * mmap_lock for reading only, and recognize when it's been released. Otherwise, + * it must be held for either reading or writing and will not be released. * * In most cases, get_user_pages or get_user_pages_fast should be used * instead of __get_user_pages. __get_user_pages should be used only if @@ -1021,7 +1186,7 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags) static long __get_user_pages(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, - struct vm_area_struct **vmas, int *locked) + int *locked) { long ret = 0, i = 0; struct vm_area_struct *vma = NULL; @@ -1030,18 +1195,10 @@ static long __get_user_pages(struct mm_struct *mm, if (!nr_pages) return 0; - start = untagged_addr(start); + start = untagged_addr_remote(mm, start); VM_BUG_ON(!!pages != !!(gup_flags & (FOLL_GET | FOLL_PIN))); - /* - * If FOLL_FORCE is set then do not force a full fault as the hinting - * fault information is unrelated to the reference behaviour of a task - * using the address space - */ - if (!(gup_flags & FOLL_FORCE)) - gup_flags |= FOLL_NUMA; - do { struct page *page; unsigned int foll_flags = gup_flags; @@ -1049,37 +1206,24 @@ static long __get_user_pages(struct mm_struct *mm, /* first iteration or cross vma bound */ if (!vma || start >= vma->vm_end) { - vma = find_extend_vma(mm, start); + vma = gup_vma_lookup(mm, start); if (!vma && in_gate_area(mm, start)) { ret = get_gate_page(mm, start & PAGE_MASK, gup_flags, &vma, - pages ? &pages[i] : NULL); + pages ? &page : NULL); if (ret) goto out; ctx.page_mask = 0; goto next_page; } - if (!vma || check_vma_flags(vma, gup_flags)) { + if (!vma) { ret = -EFAULT; goto out; } - if (is_vm_hugetlb_page(vma)) { - i = follow_hugetlb_page(mm, vma, pages, vmas, - &start, &nr_pages, i, - gup_flags, locked); - if (locked && *locked == 0) { - /* - * We've got a VM_FAULT_RETRY - * and we've lost mmap_lock. - * We must stop here. - */ - BUG_ON(gup_flags & FOLL_NOWAIT); - BUG_ON(ret != 0); - goto out; - } - continue; - } + ret = check_vma_flags(vma, gup_flags); + if (ret) + goto out; } retry: /* @@ -1093,46 +1237,85 @@ retry: cond_resched(); page = follow_page_mask(vma, start, foll_flags, &ctx); - if (!page) { - ret = faultin_page(vma, start, &foll_flags, locked); + if (!page || PTR_ERR(page) == -EMLINK) { + ret = faultin_page(vma, start, &foll_flags, + PTR_ERR(page) == -EMLINK, locked); switch (ret) { case 0: goto retry; case -EBUSY: + case -EAGAIN: ret = 0; fallthrough; case -EFAULT: case -ENOMEM: case -EHWPOISON: goto out; - case -ENOENT: - goto next_page; } BUG(); } else if (PTR_ERR(page) == -EEXIST) { /* * Proper page table entry exists, but no corresponding - * struct page. + * struct page. If the caller expects **pages to be + * filled in, bail out now, because that can't be done + * for this page. */ - goto next_page; + if (pages) { + ret = PTR_ERR(page); + goto out; + } } else if (IS_ERR(page)) { ret = PTR_ERR(page); goto out; } - if (pages) { - pages[i] = page; - flush_anon_page(vma, page, start); - flush_dcache_page(page); - ctx.page_mask = 0; - } next_page: - if (vmas) { - vmas[i] = vma; - ctx.page_mask = 0; - } page_increm = 1 + (~(start >> PAGE_SHIFT) & ctx.page_mask); if (page_increm > nr_pages) page_increm = nr_pages; + + if (pages) { + struct page *subpage; + unsigned int j; + + /* + * This must be a large folio (and doesn't need to + * be the whole folio; it can be part of it), do + * the refcount work for all the subpages too. + * + * NOTE: here the page may not be the head page + * e.g. when start addr is not thp-size aligned. + * try_grab_folio() should have taken care of tail + * pages. + */ + if (page_increm > 1) { + struct folio *folio; + + /* + * Since we already hold refcount on the + * large folio, this should never fail. + */ + folio = try_grab_folio(page, page_increm - 1, + foll_flags); + if (WARN_ON_ONCE(!folio)) { + /* + * Release the 1st page ref if the + * folio is problematic, fail hard. + */ + gup_put_folio(page_folio(page), 1, + foll_flags); + ret = -EFAULT; + goto out; + } + } + + for (j = 0; j < page_increm; j++) { + subpage = nth_page(page, j); + pages[i + j] = subpage; + flush_anon_page(vma, subpage, start + j * PAGE_SIZE); + flush_dcache_page(subpage); + } + } + i += page_increm; start += page_increm * PAGE_SIZE; nr_pages -= page_increm; @@ -1200,16 +1383,16 @@ int fixup_user_fault(struct mm_struct *mm, bool *unlocked) { struct vm_area_struct *vma; - vm_fault_t ret, major = 0; + vm_fault_t ret; - address = untagged_addr(address); + address = untagged_addr_remote(mm, address); if (unlocked) fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; retry: - vma = find_extend_vma(mm, address); - if (!vma || address < vma->vm_start) + vma = gup_vma_lookup(mm, address); + if (!vma) return -EFAULT; if (!vma_permits_fault(vma, fault_flags)) @@ -1220,7 +1403,18 @@ retry: return -EINTR; ret = handle_mm_fault(vma, address, fault_flags, NULL); - major |= ret & VM_FAULT_MAJOR; + + 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); @@ -1241,29 +1435,62 @@ retry: EXPORT_SYMBOL_GPL(fixup_user_fault); /* - * Please note that this function, unlike __get_user_pages will not - * return 0 for nr_pages > 0 without FOLL_NOWAIT + * GUP always responds to fatal signals. When FOLL_INTERRUPTIBLE is + * specified, it'll also respond to generic signals. The caller of GUP + * that has FOLL_INTERRUPTIBLE should take care of the GUP interruption. + */ +static bool gup_signal_pending(unsigned int flags) +{ + if (fatal_signal_pending(current)) + return true; + + if (!(flags & FOLL_INTERRUPTIBLE)) + return false; + + return signal_pending(current); +} + +/* + * Locking: (*locked == 1) means that the mmap_lock has already been acquired by + * the caller. This function may drop the mmap_lock. If it does so, then it will + * set (*locked = 0). + * + * (*locked == 0) means that the caller expects this function to acquire and + * drop the mmap_lock. Therefore, the value of *locked will still be zero when + * the function returns, even though it may have changed temporarily during + * function execution. + * + * Please note that this function, unlike __get_user_pages(), will not return 0 + * for nr_pages > 0, unless FOLL_NOWAIT is used. */ static __always_inline long __get_user_pages_locked(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, struct page **pages, - struct vm_area_struct **vmas, int *locked, unsigned int flags) { long ret, pages_done; - bool lock_dropped; + bool must_unlock = false; - if (locked) { - /* if VM_FAULT_RETRY can be returned, vmas become invalid */ - BUG_ON(vmas); - /* check caller initialized locked */ - BUG_ON(*locked != 1); + if (!nr_pages) + return 0; + + /* + * 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) - atomic_set(&mm->has_pinned, 1); + mm_set_has_pinned_flag(&mm->flags); /* * FOLL_PIN and FOLL_GET are mutually exclusive. Traditional behavior @@ -1278,15 +1505,16 @@ static __always_inline long __get_user_pages_locked(struct mm_struct *mm, flags |= FOLL_GET; pages_done = 0; - lock_dropped = false; for (;;) { ret = __get_user_pages(mm, start, nr_pages, flags, pages, - vmas, locked); - if (!locked) + locked); + if (!(flags & FOLL_UNLOCKABLE)) { /* VM_FAULT_RETRY couldn't trigger, bypass */ - return ret; + pages_done = ret; + break; + } - /* VM_FAULT_RETRY cannot return errors */ + /* VM_FAULT_RETRY or VM_FAULT_COMPLETED cannot return errors */ if (!*locked) { BUG_ON(ret < 0); BUG_ON(ret >= nr_pages); @@ -1314,18 +1542,20 @@ static __always_inline long __get_user_pages_locked(struct mm_struct *mm, if (likely(pages)) pages += ret; start += ret << PAGE_SHIFT; - lock_dropped = true; + + /* 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, so we need to check it before we + * 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 (fatal_signal_pending(current)) { + if (gup_signal_pending(flags)) { if (!pages_done) pages_done = -EINTR; break; @@ -1341,7 +1571,7 @@ retry: *locked = 1; ret = __get_user_pages(mm, start, 1, flags | FOLL_TRIED, - pages, NULL, locked); + pages, locked); if (!*locked) { /* Continue to retry until we succeeded */ BUG_ON(ret != 0); @@ -1361,14 +1591,23 @@ retry: pages++; start += PAGE_SIZE; } - if (lock_dropped && *locked) { + if (must_unlock && *locked) { /* - * We must let the caller know we temporarily dropped the lock - * and so the critical section protected by it was lost. + * 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; } + + /* + * Failing to pin anything implies something has gone wrong (except when + * FOLL_NOWAIT is specified). + */ + if (WARN_ON_ONCE(pages_done == 0 && !(flags & FOLL_NOWAIT))) + return -EFAULT; + return pages_done; } @@ -1397,17 +1636,24 @@ long populate_vma_page_range(struct vm_area_struct *vma, { 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(start & ~PAGE_MASK); - VM_BUG_ON(end & ~PAGE_MASK); + 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); - gup_flags = FOLL_TOUCH | FOLL_POPULATE | FOLL_MLOCK; + /* + * 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) - gup_flags &= ~FOLL_POPULATE; + 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 @@ -1423,12 +1669,75 @@ long populate_vma_page_range(struct vm_area_struct *vma, 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. */ - return __get_user_pages(mm, start, nr_pages, gup_flags, - NULL, NULL, locked); + ret = __get_user_pages(mm, start, nr_pages, gup_flags, + NULL, locked ? locked : &local_locked); + lru_add_drain(); + return ret; +} + +/* + * faultin_vma_page_range() - populate (prefault) page tables inside the + * given VMA range readable/writable + * + * This takes care of mlocking the pages, too, if VM_LOCKED is set. + * + * @vma: target vma + * @start: start address + * @end: end address + * @write: whether to prefault readable or writable + * @locked: whether the mmap_lock is still held + * + * Returns either number of processed pages in the vma, or a negative error + * code on error (see __get_user_pages()). + * + * vma->vm_mm->mmap_lock must be held. The range must be page-aligned and + * covered by the VMA. If it's released, *@locked will be set to 0. + */ +long faultin_vma_page_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end, bool write, int *locked) +{ + struct mm_struct *mm = vma->vm_mm; + unsigned long nr_pages = (end - start) / PAGE_SIZE; + 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); + + /* + * FOLL_TOUCH: Mark page accessed and thereby young; will also mark + * the page dirty with FOLL_WRITE -- which doesn't make a + * difference with !FOLL_FORCE, because the page is writable + * in the page table. + * FOLL_HWPOISON: Return -EHWPOISON instead of -EFAULT when we hit + * a poisoned page. + * !FOLL_FORCE: Require proper access permissions. + */ + gup_flags = FOLL_TOUCH | FOLL_HWPOISON | FOLL_UNLOCKABLE; + if (write) + gup_flags |= FOLL_WRITE; + + /* + * We want to report -EINVAL instead of -EFAULT for any permission + * problems or incompatible mappings. + */ + if (check_vma_flags(vma, gup_flags)) + return -EINVAL; + + ret = __get_user_pages(mm, start, nr_pages, gup_flags, + NULL, locked); + lru_add_drain(); + return ret; } /* @@ -1456,10 +1765,11 @@ int __mm_populate(unsigned long start, unsigned long len, int ignore_errors) if (!locked) { locked = 1; mmap_read_lock(mm); - vma = find_vma(mm, nstart); + vma = find_vma_intersection(mm, nstart, end); } else if (nstart >= vma->vm_end) - vma = vma->vm_next; - if (!vma || vma->vm_start >= end) + vma = find_vma_intersection(mm, vma->vm_end, end); + + if (!vma) break; /* * Set [nstart; nend) to intersection of desired address @@ -1490,44 +1800,29 @@ int __mm_populate(unsigned long start, unsigned long len, int ignore_errors) mmap_read_unlock(mm); return ret; /* 0 or negative error code */ } - -/** - * get_dump_page() - pin user page in memory while writing it to core dump - * @addr: user address - * - * Returns struct page pointer of user page pinned for dump, - * to be freed afterwards by put_page(). - * - * Returns NULL on any kind of failure - a hole must then be inserted into - * the corefile, to preserve alignment with its headers; and also returns - * NULL wherever the ZERO_PAGE, or an anonymous pte_none, has been found - - * allowing a hole to be left in the corefile to save diskspace. - * - * Called without mmap_lock, but after all other threads have been killed. - */ -#ifdef CONFIG_ELF_CORE -struct page *get_dump_page(unsigned long addr) -{ - struct vm_area_struct *vma; - struct page *page; - - if (__get_user_pages(current->mm, addr, 1, - FOLL_FORCE | FOLL_DUMP | FOLL_GET, &page, &vma, - NULL) < 1) - return NULL; - flush_cache_page(vma, addr, page_to_pfn(page)); - return page; -} -#endif /* CONFIG_ELF_CORE */ #else /* CONFIG_MMU */ static long __get_user_pages_locked(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, struct page **pages, - struct vm_area_struct **vmas, int *locked, - unsigned int foll_flags) + int *locked, unsigned int foll_flags) { struct vm_area_struct *vma; + bool must_unlock = false; unsigned long vm_flags; - int i; + long i; + + if (!nr_pages) + return 0; + + /* + * 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; + } /* calculate required read or write permissions. * If FOLL_FORCE is set, we only require the "MAY" flags. @@ -1540,153 +1835,363 @@ static long __get_user_pages_locked(struct mm_struct *mm, unsigned long start, for (i = 0; i < nr_pages; i++) { vma = find_vma(mm, start); if (!vma) - goto finish_or_fault; + break; /* protect what we can, including chardevs */ if ((vma->vm_flags & (VM_IO | VM_PFNMAP)) || !(vm_flags & vma->vm_flags)) - goto finish_or_fault; + break; if (pages) { - pages[i] = virt_to_page(start); + pages[i] = virt_to_page((void *)start); if (pages[i]) get_page(pages[i]); } - if (vmas) - vmas[i] = vma; + start = (start + PAGE_SIZE) & PAGE_MASK; } - return i; + if (must_unlock && *locked) { + mmap_read_unlock(mm); + *locked = 0; + } -finish_or_fault: return i ? : -EFAULT; } #endif /* !CONFIG_MMU */ -#if defined(CONFIG_FS_DAX) || defined (CONFIG_CMA) -static bool check_dax_vmas(struct vm_area_struct **vmas, long nr_pages) +/** + * fault_in_writeable - fault in userspace address range for writing + * @uaddr: start of address range + * @size: size of address range + * + * Returns the number of bytes not faulted in (like copy_to_user() and + * copy_from_user()). + */ +size_t fault_in_writeable(char __user *uaddr, size_t size) { - long i; - struct vm_area_struct *vma_prev = NULL; + char __user *start = uaddr, *end; - for (i = 0; i < nr_pages; i++) { - struct vm_area_struct *vma = vmas[i]; + if (unlikely(size == 0)) + return 0; + if (!user_write_access_begin(uaddr, size)) + return size; + if (!PAGE_ALIGNED(uaddr)) { + unsafe_put_user(0, uaddr, out); + uaddr = (char __user *)PAGE_ALIGN((unsigned long)uaddr); + } + end = (char __user *)PAGE_ALIGN((unsigned long)start + size); + if (unlikely(end < start)) + end = NULL; + while (uaddr != end) { + unsafe_put_user(0, uaddr, out); + uaddr += PAGE_SIZE; + } - if (vma == vma_prev) - continue; +out: + user_write_access_end(); + if (size > uaddr - start) + return size - (uaddr - start); + return 0; +} +EXPORT_SYMBOL(fault_in_writeable); + +/** + * fault_in_subpage_writeable - fault in an address range for writing + * @uaddr: start of address range + * @size: size of address range + * + * Fault in a user address range for writing while checking for permissions at + * sub-page granularity (e.g. arm64 MTE). This function should be used when + * the caller cannot guarantee forward progress of a copy_to_user() loop. + * + * Returns the number of bytes not faulted in (like copy_to_user() and + * copy_from_user()). + */ +size_t fault_in_subpage_writeable(char __user *uaddr, size_t size) +{ + size_t faulted_in; + + /* + * Attempt faulting in at page granularity first for page table + * permission checking. The arch-specific probe_subpage_writeable() + * functions may not check for this. + */ + faulted_in = size - fault_in_writeable(uaddr, size); + if (faulted_in) + faulted_in -= probe_subpage_writeable(uaddr, faulted_in); + + return size - faulted_in; +} +EXPORT_SYMBOL(fault_in_subpage_writeable); + +/* + * fault_in_safe_writeable - fault in an address range for writing + * @uaddr: start of address range + * @size: length of address range + * + * Faults in an address range for writing. This is primarily useful when we + * already know that some or all of the pages in the address range aren't in + * memory. + * + * Unlike fault_in_writeable(), this function is non-destructive. + * + * Note that we don't pin or otherwise hold the pages referenced that we fault + * in. There's no guarantee that they'll stay in memory for any duration of + * time. + * + * Returns the number of bytes not faulted in, like copy_to_user() and + * copy_from_user(). + */ +size_t fault_in_safe_writeable(const char __user *uaddr, size_t size) +{ + unsigned long start = (unsigned long)uaddr, end; + struct mm_struct *mm = current->mm; + bool unlocked = false; + + if (unlikely(size == 0)) + return 0; + end = PAGE_ALIGN(start + size); + if (end < start) + end = 0; + + mmap_read_lock(mm); + do { + if (fixup_user_fault(mm, start, FAULT_FLAG_WRITE, &unlocked)) + break; + start = (start + PAGE_SIZE) & PAGE_MASK; + } while (start != end); + mmap_read_unlock(mm); - vma_prev = vma; + if (size > (unsigned long)uaddr - start) + return size - ((unsigned long)uaddr - start); + return 0; +} +EXPORT_SYMBOL(fault_in_safe_writeable); - if (vma_is_fsdax(vma)) - return true; +/** + * fault_in_readable - fault in userspace address range for reading + * @uaddr: start of user address range + * @size: size of user address range + * + * Returns the number of bytes not faulted in (like copy_to_user() and + * copy_from_user()). + */ +size_t fault_in_readable(const char __user *uaddr, size_t size) +{ + const char __user *start = uaddr, *end; + volatile char c; + + if (unlikely(size == 0)) + return 0; + if (!user_read_access_begin(uaddr, size)) + return size; + if (!PAGE_ALIGNED(uaddr)) { + unsafe_get_user(c, uaddr, out); + uaddr = (const char __user *)PAGE_ALIGN((unsigned long)uaddr); + } + end = (const char __user *)PAGE_ALIGN((unsigned long)start + size); + if (unlikely(end < start)) + end = NULL; + while (uaddr != end) { + unsafe_get_user(c, uaddr, out); + uaddr += PAGE_SIZE; } - return false; + +out: + user_read_access_end(); + (void)c; + if (size > uaddr - start) + return size - (uaddr - start); + return 0; } +EXPORT_SYMBOL(fault_in_readable); + +/** + * get_dump_page() - pin user page in memory while writing it to core dump + * @addr: user address + * + * Returns struct page pointer of user page pinned for dump, + * to be freed afterwards by put_page(). + * + * Returns NULL on any kind of failure - a hole must then be inserted into + * the corefile, to preserve alignment with its headers; and also returns + * NULL wherever the ZERO_PAGE, or an anonymous pte_none, has been found - + * allowing a hole to be left in the corefile to save disk space. + * + * Called without mmap_lock (takes and releases the mmap_lock by itself). + */ +#ifdef CONFIG_ELF_CORE +struct page *get_dump_page(unsigned long addr) +{ + struct page *page; + int locked = 0; + int ret; -#ifdef CONFIG_CMA -static long check_and_migrate_cma_pages(struct mm_struct *mm, - unsigned long start, + 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 */ + +#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, - struct vm_area_struct **vmas, - unsigned int gup_flags) + struct page **pages) { - unsigned long i; - unsigned long step; + unsigned long i, collected = 0; + struct folio *prev_folio = NULL; bool drain_allow = true; - bool migrate_allow = true; - LIST_HEAD(cma_page_list); - long ret = nr_pages; - struct migration_target_control mtc = { - .nid = NUMA_NO_NODE, - .gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_NOWARN, - }; -check_again: - for (i = 0; i < nr_pages;) { + for (i = 0; i < nr_pages; i++) { + struct folio *folio = page_folio(pages[i]); - struct page *head = compound_head(pages[i]); + if (folio == prev_folio) + continue; + prev_folio = folio; - /* - * gup may start from a tail page. Advance step by the left - * part. - */ - step = compound_nr(head) - (pages[i] - head); - /* - * If we get a page from the CMA zone, since we are going to - * be pinning these entries, we might as well move them out - * of the CMA zone if possible. - */ - if (is_migrate_cma_page(head)) { - if (PageHuge(head)) - isolate_huge_page(head, &cma_page_list); - else { - if (!PageLRU(head) && drain_allow) { - lru_add_drain_all(); - drain_allow = false; - } + if (folio_is_longterm_pinnable(folio)) + continue; - if (!isolate_lru_page(head)) { - list_add_tail(&head->lru, &cma_page_list); - mod_node_page_state(page_pgdat(head), - NR_ISOLATED_ANON + - page_is_file_lru(head), - thp_nr_pages(head)); - } - } + 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; } - i += step; + 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)); } - if (!list_empty(&cma_page_list)) { - /* - * drop the above get_user_pages reference. - */ - for (i = 0; i < nr_pages; i++) - put_page(pages[i]); + return collected; +} - if (migrate_pages(&cma_page_list, alloc_migration_target, NULL, - (unsigned long)&mtc, MIGRATE_SYNC, MR_CONTIG_RANGE)) { +/* + * Unpins all pages and migrates device coherent pages and movable_page_list. + * Returns -EAGAIN if all pages were successfully migrated or -errno for failure + * (or partial success). + */ +static int migrate_longterm_unpinnable_pages( + struct list_head *movable_page_list, + unsigned long nr_pages, + struct page **pages) +{ + int ret; + unsigned long i; + + for (i = 0; i < nr_pages; i++) { + struct folio *folio = page_folio(pages[i]); + + if (folio_is_device_coherent(folio)) { /* - * some of the pages failed migration. Do get_user_pages - * without migration. + * Migration will fail if the page is pinned, so convert + * the pin on the source page to a normal reference. */ - migrate_allow = false; + pages[i] = NULL; + folio_get(folio); + gup_put_folio(folio, 1, FOLL_PIN); - if (!list_empty(&cma_page_list)) - putback_movable_pages(&cma_page_list); + if (migrate_device_coherent_page(&folio->page)) { + ret = -EBUSY; + goto err; + } + + continue; } + /* - * We did migrate all the pages, Try to get the page references - * again migrating any new CMA pages which we failed to isolate - * earlier. + * We can't migrate pages with unexpected references, so drop + * the reference obtained by __get_user_pages_locked(). + * Migrating pages have been added to movable_page_list after + * calling folio_isolate_lru() which takes a reference so the + * page won't be freed if it's migrating. */ - ret = __get_user_pages_locked(mm, start, nr_pages, - pages, vmas, NULL, - gup_flags); - - if ((ret > 0) && migrate_allow) { - nr_pages = ret; - drain_allow = true; - goto check_again; + unpin_user_page(pages[i]); + pages[i] = NULL; + } + + if (!list_empty(movable_page_list)) { + struct migration_target_control mtc = { + .nid = NUMA_NO_NODE, + .gfp_mask = GFP_USER | __GFP_NOWARN, + }; + + if (migrate_pages(movable_page_list, alloc_migration_target, + NULL, (unsigned long)&mtc, MIGRATE_SYNC, + MR_LONGTERM_PIN, NULL)) { + ret = -ENOMEM; + goto err; } } + putback_movable_pages(movable_page_list); + + return -EAGAIN; + +err: + for (i = 0; i < nr_pages; i++) + if (pages[i]) + unpin_user_page(pages[i]); + putback_movable_pages(movable_page_list); + return ret; } + +/* + * Check whether all pages are *allowed* to be pinned. Rather confusingly, all + * pages in the range are required to be pinned via FOLL_PIN, before calling + * this routine. + * + * If any pages in the range are not allowed to be pinned, then this routine + * will migrate those pages away, unpin all the pages in the range and return + * -EAGAIN. The caller should re-pin the entire range with FOLL_PIN and then + * call this routine again. + * + * If an error other than -EAGAIN occurs, this indicates a migration failure. + * The caller should give up, and propagate the error back up the call stack. + * + * If everything is OK and all pages in the range are allowed to be pinned, then + * this routine leaves all pages pinned and returns zero for success. + */ +static long check_and_migrate_movable_pages(unsigned long nr_pages, + struct page **pages) +{ + unsigned long collected; + LIST_HEAD(movable_page_list); + + collected = collect_longterm_unpinnable_pages(&movable_page_list, + nr_pages, pages); + if (!collected) + return 0; + + return migrate_longterm_unpinnable_pages(&movable_page_list, nr_pages, + pages); +} #else -static long check_and_migrate_cma_pages(struct mm_struct *mm, - unsigned long start, - unsigned long nr_pages, - struct page **pages, - struct vm_area_struct **vmas, - unsigned int gup_flags) +static long check_and_migrate_movable_pages(unsigned long nr_pages, + struct page **pages) { - return nr_pages; + return 0; } -#endif /* CONFIG_CMA */ +#endif /* CONFIG_MIGRATION */ /* * __gup_longterm_locked() is a wrapper for __get_user_pages_locked which @@ -1696,113 +2201,84 @@ static long __gup_longterm_locked(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, struct page **pages, - struct vm_area_struct **vmas, + int *locked, unsigned int gup_flags) { - struct vm_area_struct **vmas_tmp = vmas; - unsigned long flags = 0; - long rc, i; + unsigned int flags; + long rc, nr_pinned_pages; - if (gup_flags & FOLL_LONGTERM) { - if (!pages) - return -EINVAL; + if (!(gup_flags & FOLL_LONGTERM)) + return __get_user_pages_locked(mm, start, nr_pages, pages, + locked, gup_flags); - if (!vmas_tmp) { - vmas_tmp = kcalloc(nr_pages, - sizeof(struct vm_area_struct *), - GFP_KERNEL); - if (!vmas_tmp) - return -ENOMEM; + flags = memalloc_pin_save(); + do { + nr_pinned_pages = __get_user_pages_locked(mm, start, nr_pages, + pages, locked, + gup_flags); + if (nr_pinned_pages <= 0) { + rc = nr_pinned_pages; + break; } - flags = memalloc_nocma_save(); - } - rc = __get_user_pages_locked(mm, start, nr_pages, pages, - vmas_tmp, NULL, gup_flags); + /* FOLL_LONGTERM implies FOLL_PIN */ + rc = check_and_migrate_movable_pages(nr_pinned_pages, pages); + } while (rc == -EAGAIN); + memalloc_pin_restore(flags); + return rc ? rc : nr_pinned_pages; +} - if (gup_flags & FOLL_LONGTERM) { - if (rc < 0) - goto out; +/* + * Check that the given flags are valid for the exported gup/pup interface, and + * update them with the required flags that the caller must have set. + */ +static bool is_valid_gup_args(struct page **pages, int *locked, + unsigned int *gup_flags_p, unsigned int to_set) +{ + unsigned int gup_flags = *gup_flags_p; - if (check_dax_vmas(vmas_tmp, rc)) { - for (i = 0; i < rc; i++) - put_page(pages[i]); - rc = -EOPNOTSUPP; - goto out; - } + /* + * These flags not allowed to be specified externally to the gup + * interfaces: + * - FOLL_TOUCH/FOLL_PIN/FOLL_TRIED/FOLL_FAST_ONLY are internal only + * - FOLL_REMOTE is internal only and used on follow_page() + * - FOLL_UNLOCKABLE is internal only and used if locked is !NULL + */ + if (WARN_ON_ONCE(gup_flags & INTERNAL_GUP_FLAGS)) + return false; - rc = check_and_migrate_cma_pages(mm, start, rc, pages, - vmas_tmp, gup_flags); -out: - memalloc_nocma_restore(flags); + gup_flags |= to_set; + if (locked) { + /* At the external interface locked must be set */ + if (WARN_ON_ONCE(*locked != 1)) + return false; + + gup_flags |= FOLL_UNLOCKABLE; } - if (vmas_tmp != vmas) - kfree(vmas_tmp); - return rc; -} -#else /* !CONFIG_FS_DAX && !CONFIG_CMA */ -static __always_inline long __gup_longterm_locked(struct mm_struct *mm, - unsigned long start, - unsigned long nr_pages, - struct page **pages, - struct vm_area_struct **vmas, - unsigned int flags) -{ - return __get_user_pages_locked(mm, start, nr_pages, pages, vmas, - NULL, flags); -} -#endif /* CONFIG_FS_DAX || CONFIG_CMA */ + /* FOLL_GET and FOLL_PIN are mutually exclusive. */ + if (WARN_ON_ONCE((gup_flags & (FOLL_PIN | FOLL_GET)) == + (FOLL_PIN | FOLL_GET))) + return false; -static bool is_valid_gup_flags(unsigned int gup_flags) -{ - /* - * FOLL_PIN must only be set internally by the pin_user_pages*() APIs, - * never directly by the caller, so enforce that with an assertion: - */ - if (WARN_ON_ONCE(gup_flags & FOLL_PIN)) + /* LONGTERM can only be specified when pinning */ + if (WARN_ON_ONCE(!(gup_flags & FOLL_PIN) && (gup_flags & FOLL_LONGTERM))) return false; - /* - * FOLL_PIN is a prerequisite to FOLL_LONGTERM. Another way of saying - * that is, FOLL_LONGTERM is a specific case, more restrictive case of - * FOLL_PIN. - */ - if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM)) + + /* Pages input must be given if using GET/PIN */ + if (WARN_ON_ONCE((gup_flags & (FOLL_GET | FOLL_PIN)) && !pages)) + return false; + + /* We want to allow the pgmap to be hot-unplugged at all times */ + if (WARN_ON_ONCE((gup_flags & FOLL_LONGTERM) && + (gup_flags & FOLL_PCI_P2PDMA))) return false; + *gup_flags_p = gup_flags; return true; } #ifdef CONFIG_MMU -static long __get_user_pages_remote(struct mm_struct *mm, - unsigned long start, unsigned long nr_pages, - unsigned int gup_flags, struct page **pages, - struct vm_area_struct **vmas, int *locked) -{ - /* - * Parts of FOLL_LONGTERM behavior are incompatible with - * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on - * vmas. However, this only comes up if locked is set, and there are - * callers that do request FOLL_LONGTERM, but do not set locked. So, - * allow what we can. - */ - if (gup_flags & FOLL_LONGTERM) { - if (WARN_ON_ONCE(locked)) - return -EINVAL; - /* - * This will check the vmas (even if our vmas arg is NULL) - * and return -ENOTSUPP if DAX isn't allowed in this case: - */ - return __gup_longterm_locked(mm, start, nr_pages, pages, - vmas, gup_flags | FOLL_TOUCH | - FOLL_REMOTE); - } - - return __get_user_pages_locked(mm, start, nr_pages, pages, vmas, - locked, - gup_flags | FOLL_TOUCH | FOLL_REMOTE); -} - /** * get_user_pages_remote() - pin user pages in memory * @mm: mm_struct of target mm @@ -1812,8 +2288,6 @@ static long __get_user_pages_remote(struct mm_struct *mm, * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. Or NULL, if caller * only intends to ensure the pages are faulted in. - * @vmas: array of pointers to vmas corresponding to each page. - * Or NULL if the caller does not require them. * @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. @@ -1828,8 +2302,6 @@ static long __get_user_pages_remote(struct mm_struct *mm, * * The caller is responsible for releasing returned @pages, via put_page(). * - * @vmas are valid only as long as mmap_lock is held. - * * Must be called with mmap_lock held for read or write. * * get_user_pages_remote walks a process's page tables and takes a reference @@ -1840,7 +2312,7 @@ static long __get_user_pages_remote(struct mm_struct *mm, * This does not guarantee that the page exists in the user mappings when * get_user_pages_remote returns, and there may even be a completely different * page there in some cases (eg. if mmapped pagecache has been invalidated - * and subsequently re faulted). However it does guarantee that the page + * and subsequently re-faulted). However it does guarantee that the page * won't be freed completely. And mostly callers simply care that the page * contains data that was valid *at some point in time*. Typically, an IO * or similar operation cannot guarantee anything stronger anyway because @@ -1866,13 +2338,17 @@ static long __get_user_pages_remote(struct mm_struct *mm, long get_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, - struct vm_area_struct **vmas, int *locked) + int *locked) { - if (!is_valid_gup_flags(gup_flags)) + int local_locked = 1; + + if (!is_valid_gup_args(pages, locked, &gup_flags, + FOLL_TOUCH | FOLL_REMOTE)) return -EINVAL; - return __get_user_pages_remote(mm, start, nr_pages, gup_flags, - pages, vmas, locked); + return __get_user_pages_locked(mm, start, nr_pages, pages, + locked ? locked : &local_locked, + gup_flags); } EXPORT_SYMBOL(get_user_pages_remote); @@ -1880,15 +2356,7 @@ EXPORT_SYMBOL(get_user_pages_remote); long get_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, - struct vm_area_struct **vmas, int *locked) -{ - return 0; -} - -static long __get_user_pages_remote(struct mm_struct *mm, - unsigned long start, unsigned long nr_pages, - unsigned int gup_flags, struct page **pages, - struct vm_area_struct **vmas, int *locked) + int *locked) { return 0; } @@ -1902,8 +2370,6 @@ static long __get_user_pages_remote(struct mm_struct *mm, * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. Or NULL, if caller * only intends to ensure the pages are faulted in. - * @vmas: array of pointers to vmas corresponding to each page. - * Or NULL if the caller does not require them. * * This is the same as get_user_pages_remote(), just with a less-flexible * calling convention where we assume that the mm being operated on belongs to @@ -1911,73 +2377,17 @@ static long __get_user_pages_remote(struct mm_struct *mm, * obviously don't pass FOLL_REMOTE in here. */ long get_user_pages(unsigned long start, unsigned long nr_pages, - unsigned int gup_flags, struct page **pages, - struct vm_area_struct **vmas) + unsigned int gup_flags, struct page **pages) { - if (!is_valid_gup_flags(gup_flags)) - return -EINVAL; - - return __gup_longterm_locked(current->mm, start, nr_pages, - pages, vmas, gup_flags | FOLL_TOUCH); -} -EXPORT_SYMBOL(get_user_pages); + int locked = 1; -/** - * get_user_pages_locked() is suitable to replace the form: - * - * mmap_read_lock(mm); - * do_something() - * get_user_pages(mm, ..., pages, NULL); - * mmap_read_unlock(mm); - * - * to: - * - * int locked = 1; - * mmap_read_lock(mm); - * do_something() - * get_user_pages_locked(mm, ..., pages, &locked); - * if (locked) - * mmap_read_unlock(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. Or NULL, if caller - * only intends to ensure the pages are faulted in. - * @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. - * - * We can leverage the VM_FAULT_RETRY functionality in the page fault - * paths better by using either get_user_pages_locked() or - * get_user_pages_unlocked(). - * - */ -long get_user_pages_locked(unsigned long start, unsigned long nr_pages, - unsigned int gup_flags, struct page **pages, - int *locked) -{ - /* - * FIXME: Current FOLL_LONGTERM behavior is incompatible with - * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on - * vmas. As there are no users of this flag in this call we simply - * disallow this option for now. - */ - if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM)) - return -EINVAL; - /* - * FOLL_PIN must only be set internally by the pin_user_pages*() APIs, - * never directly by the caller, so enforce that: - */ - if (WARN_ON_ONCE(gup_flags & FOLL_PIN)) + if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_TOUCH)) return -EINVAL; - return __get_user_pages_locked(current->mm, start, nr_pages, - pages, NULL, locked, - gup_flags | FOLL_TOUCH); + return __get_user_pages_locked(current->mm, start, nr_pages, pages, + &locked, gup_flags); } -EXPORT_SYMBOL(get_user_pages_locked); +EXPORT_SYMBOL(get_user_pages); /* * get_user_pages_unlocked() is suitable to replace the form: @@ -1997,25 +2407,14 @@ EXPORT_SYMBOL(get_user_pages_locked); long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags) { - struct mm_struct *mm = current->mm; - int locked = 1; - long ret; + int locked = 0; - /* - * FIXME: Current FOLL_LONGTERM behavior is incompatible with - * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on - * vmas. As there are no users of this flag in this call we simply - * disallow this option for now. - */ - if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM)) + if (!is_valid_gup_args(pages, NULL, &gup_flags, + FOLL_TOUCH | FOLL_UNLOCKABLE)) return -EINVAL; - mmap_read_lock(mm); - ret = __get_user_pages_locked(mm, start, nr_pages, pages, NULL, - &locked, gup_flags | FOLL_TOUCH); - if (locked) - mmap_read_unlock(mm); - return ret; + return __get_user_pages_locked(current->mm, start, nr_pages, pages, + &locked, gup_flags); } EXPORT_SYMBOL(get_user_pages_unlocked); @@ -2054,83 +2453,81 @@ EXPORT_SYMBOL(get_user_pages_unlocked); */ #ifdef CONFIG_HAVE_FAST_GUP -static void put_compound_head(struct page *page, int refs, unsigned int flags) +/* + * 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) { - if (flags & FOLL_PIN) { - mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_RELEASED, - refs); + struct address_space *mapping; + unsigned long mapping_flags; - if (hpage_pincount_available(page)) - hpage_pincount_sub(page, refs); - else - refs *= GUP_PIN_COUNTING_BIAS; - } + /* + * 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; - VM_BUG_ON_PAGE(page_ref_count(page) < refs, page); /* - * Calling put_page() for each ref is unnecessarily slow. Only the last - * ref needs a put_page(). + * 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. */ - if (refs > 1) - page_ref_sub(page, refs - 1); - put_page(page); -} + lockdep_assert_irqs_disabled(); -#ifdef CONFIG_GUP_GET_PTE_LOW_HIGH + /* + * However, there may be operations which _alter_ the mapping, so ensure + * we read it once and only once. + */ + mapping = READ_ONCE(folio->mapping); -/* - * WARNING: only to be used in the get_user_pages_fast() implementation. - * - * With get_user_pages_fast(), we walk down the pagetables without taking any - * locks. For this we would like to load the pointers atomically, but sometimes - * that is not possible (e.g. without expensive cmpxchg8b on x86_32 PAE). What - * we do have is the guarantee that a PTE will only either go from not present - * to present, or present to not present or both -- it will not switch to a - * completely different present page without a TLB flush in between; something - * that we are blocking by holding interrupts off. - * - * Setting ptes from not present to present goes: - * - * ptep->pte_high = h; - * smp_wmb(); - * ptep->pte_low = l; - * - * And present to not present goes: - * - * ptep->pte_low = 0; - * smp_wmb(); - * ptep->pte_high = 0; - * - * We must ensure here that the load of pte_low sees 'l' IFF pte_high sees 'h'. - * We load pte_high *after* loading pte_low, which ensures we don't see an older - * value of pte_high. *Then* we recheck pte_low, which ensures that we haven't - * picked up a changed pte high. We might have gotten rubbish values from - * pte_low and pte_high, but we are guaranteed that pte_low will not have the - * present bit set *unless* it is 'l'. Because get_user_pages_fast() only - * operates on present ptes we're safe. - */ -static inline pte_t gup_get_pte(pte_t *ptep) -{ - pte_t pte; + /* + * 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; - do { - pte.pte_low = ptep->pte_low; - smp_rmb(); - pte.pte_high = ptep->pte_high; - smp_rmb(); - } while (unlikely(pte.pte_low != ptep->pte_low)); + /* Anonymous folios pose no problem. */ + mapping_flags = (unsigned long)mapping & PAGE_MAPPING_FLAGS; + if (mapping_flags) + return mapping_flags & PAGE_MAPPING_ANON; - return pte; -} -#else /* CONFIG_GUP_GET_PTE_LOW_HIGH */ -/* - * We require that the PTE can be read atomically. - */ -static inline pte_t gup_get_pte(pte_t *ptep) -{ - return ptep_get(ptep); + /* + * 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); } -#endif /* CONFIG_GUP_GET_PTE_LOW_HIGH */ static void __maybe_unused undo_dev_pagemap(int *nr, int nr_start, unsigned int flags, @@ -2148,21 +2545,47 @@ static void __maybe_unused undo_dev_pagemap(int *nr, int nr_start, } #ifdef CONFIG_ARCH_HAS_PTE_SPECIAL -static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, - unsigned int flags, struct page **pages, int *nr) +/* + * 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 = gup_get_pte(ptep); - struct page *head, *page; + pte_t pte = ptep_get_lockless(ptep); + struct page *page; + struct folio *folio; /* - * Similar to the PMD case below, NUMA hinting must take slow - * path using the pte_protnone check. + * 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; @@ -2185,16 +2608,30 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, VM_BUG_ON(!pfn_valid(pte_pfn(pte))); page = pte_page(pte); - head = try_grab_compound_head(page, 1, flags); - if (!head) + 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 (unlikely(pte_val(pte) != pte_val(*ptep))) { - put_compound_head(head, 1, flags); + if (!folio_fast_pin_allowed(folio, flags)) { + gup_put_folio(folio, 1, flags); goto pte_unmap; } - VM_BUG_ON_PAGE(compound_head(page) != head, page); + 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 @@ -2205,14 +2642,13 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, if (flags & FOLL_PIN) { ret = arch_make_page_accessible(page); if (ret) { - unpin_user_page(page); + gup_put_folio(folio, 1, flags); goto pte_unmap; } } - SetPageReferenced(page); + folio_set_referenced(folio); pages[*nr] = page; (*nr)++; - } while (ptep++, addr += PAGE_SIZE, addr != end); ret = 1; @@ -2234,8 +2670,9 @@ pte_unmap: * 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, unsigned long addr, unsigned long end, - unsigned int flags, struct page **pages, int *nr) +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; } @@ -2255,21 +2692,26 @@ static int __gup_device_huge(unsigned long pfn, unsigned long addr, pgmap = get_dev_pagemap(pfn, pgmap); if (unlikely(!pgmap)) { undo_dev_pagemap(nr, nr_start, flags, pages); - return 0; + break; } + + if (!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(page)) { + undo_dev_pagemap(nr, nr_start, flags, pages); + break; + } + SetPageReferenced(page); pages[*nr] = page; - if (unlikely(!try_grab_page(page, flags))) { + if (unlikely(try_grab_page(page, flags))) { undo_dev_pagemap(nr, nr_start, flags, pages); - return 0; + break; } (*nr)++; pfn++; } while (addr += PAGE_SIZE, addr != end); - if (pgmap) - put_dev_pagemap(pgmap); - return 1; + put_dev_pagemap(pgmap); + return addr == end; } static int __gup_device_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, @@ -2330,8 +2772,8 @@ static int record_subpages(struct page *page, unsigned long addr, { int nr; - for (nr = 0; addr != end; addr += PAGE_SIZE) - pages[nr++] = page++; + for (nr = 0; addr != end; nr++, addr += PAGE_SIZE) + pages[nr] = nth_page(page, nr); return nr; } @@ -2349,7 +2791,8 @@ static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, struct page **pages, int *nr) { unsigned long pte_end; - struct page *head, *page; + struct page *page; + struct folio *folio; pte_t pte; int refs; @@ -2365,21 +2808,30 @@ static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, /* hugepages are never "special" */ VM_BUG_ON(!pfn_valid(pte_pfn(pte))); - head = pte_page(pte); - page = head + ((addr & (sz-1)) >> PAGE_SHIFT); + page = nth_page(pte_page(pte), (addr & (sz - 1)) >> PAGE_SHIFT); refs = record_subpages(page, addr, end, pages + *nr); - head = try_grab_compound_head(head, refs, flags); - if (!head) + folio = try_grab_folio(page, refs, flags); + if (!folio) return 0; - if (unlikely(pte_val(pte) != pte_val(*ptep))) { - put_compound_head(head, refs, flags); + 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; - SetPageReferenced(head); + folio_set_referenced(folio); return 1; } @@ -2413,7 +2865,8 @@ 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 *head, *page; + struct page *page; + struct folio *folio; int refs; if (!pmd_access_permitted(orig, flags & FOLL_WRITE)) @@ -2426,20 +2879,29 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, pages, nr); } - page = pmd_page(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); + page = nth_page(pmd_page(orig), (addr & ~PMD_MASK) >> PAGE_SHIFT); refs = record_subpages(page, addr, end, pages + *nr); - head = try_grab_compound_head(pmd_page(orig), refs, flags); - if (!head) + folio = try_grab_folio(page, refs, flags); + if (!folio) return 0; if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) { - put_compound_head(head, refs, flags); + 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; - SetPageReferenced(head); + folio_set_referenced(folio); return 1; } @@ -2447,7 +2909,8 @@ 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 *head, *page; + struct page *page; + struct folio *folio; int refs; if (!pud_access_permitted(orig, flags & FOLL_WRITE)) @@ -2460,20 +2923,30 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, pages, nr); } - page = pud_page(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); + page = nth_page(pud_page(orig), (addr & ~PUD_MASK) >> PAGE_SHIFT); refs = record_subpages(page, addr, end, pages + *nr); - head = try_grab_compound_head(pud_page(orig), refs, flags); - if (!head) + folio = try_grab_folio(page, refs, flags); + if (!folio) return 0; if (unlikely(pud_val(orig) != pud_val(*pudp))) { - put_compound_head(head, refs, flags); + 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; - SetPageReferenced(head); + folio_set_referenced(folio); return 1; } @@ -2482,27 +2955,38 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr, struct page **pages, int *nr) { int refs; - struct page *head, *page; + struct page *page; + struct folio *folio; if (!pgd_access_permitted(orig, flags & FOLL_WRITE)) return 0; BUILD_BUG_ON(pgd_devmap(orig)); - page = pgd_page(orig) + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT); + page = nth_page(pgd_page(orig), (addr & ~PGDIR_MASK) >> PAGE_SHIFT); refs = record_subpages(page, addr, end, pages + *nr); - head = try_grab_compound_head(pgd_page(orig), refs, flags); - if (!head) + folio = try_grab_folio(page, refs, flags); + if (!folio) return 0; if (unlikely(pgd_val(orig) != pgd_val(*pgdp))) { - put_compound_head(head, refs, flags); + 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; - SetPageReferenced(head); + folio_set_referenced(folio); return 1; } @@ -2514,7 +2998,7 @@ static int gup_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr, unsigned lo pmdp = pmd_offset_lockless(pudp, pud, addr); do { - pmd_t pmd = READ_ONCE(*pmdp); + pmd_t pmd = pmdp_get_lockless(pmdp); next = pmd_addr_end(addr, end); if (!pmd_present(pmd)) @@ -2522,11 +3006,7 @@ static int gup_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr, unsigned lo if (unlikely(pmd_trans_huge(pmd) || pmd_huge(pmd) || pmd_devmap(pmd))) { - /* - * NUMA hinting faults need to be handled in the GUP - * slowpath for accounting purposes and so that they - * can be serialised against THP migration. - */ + /* See gup_pte_range() */ if (pmd_protnone(pmd)) return 0; @@ -2542,7 +3022,7 @@ static int gup_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr, unsigned lo if (!gup_huge_pd(__hugepd(pmd_val(pmd)), addr, PMD_SHIFT, next, flags, pages, nr)) return 0; - } else if (!gup_pte_range(pmd, addr, next, flags, pages, nr)) + } else if (!gup_pte_range(pmd, pmdp, addr, next, flags, pages, nr)) return 0; } while (pmdp++, addr = next, addr != end); @@ -2562,7 +3042,7 @@ static int gup_pud_range(p4d_t *p4dp, p4d_t p4d, unsigned long addr, unsigned lo next = pud_addr_end(addr, end); if (unlikely(!pud_present(pud))) return 0; - if (unlikely(pud_huge(pud))) { + if (unlikely(pud_huge(pud) || pud_devmap(pud))) { if (!gup_huge_pud(pud, pudp, addr, next, flags, pages, nr)) return 0; @@ -2645,97 +3125,108 @@ static bool gup_fast_permitted(unsigned long start, unsigned long end) } #endif -static int __gup_longterm_unlocked(unsigned long start, int nr_pages, - unsigned int gup_flags, struct page **pages) +static unsigned long lockless_pages_from_mm(unsigned long start, + unsigned long end, + unsigned int gup_flags, + struct page **pages) { - int ret; + unsigned long flags; + int nr_pinned = 0; + unsigned seq; + + if (!IS_ENABLED(CONFIG_HAVE_FAST_GUP) || + !gup_fast_permitted(start, end)) + return 0; + + if (gup_flags & FOLL_PIN) { + seq = raw_read_seqcount(¤t->mm->write_protect_seq); + if (seq & 1) + return 0; + } /* - * FIXME: FOLL_LONGTERM does not work with - * get_user_pages_unlocked() (see comments in that function) + * Disable interrupts. The nested form is used, in order to allow full, + * general purpose use of this routine. + * + * With interrupts disabled, we block page table pages from being freed + * from under us. See struct mmu_table_batch comments in + * include/asm-generic/tlb.h for more details. + * + * We do not adopt an rcu_read_lock() here as we also want to block IPIs + * that come from THPs splitting. */ - if (gup_flags & FOLL_LONGTERM) { - mmap_read_lock(current->mm); - ret = __gup_longterm_locked(current->mm, - start, nr_pages, - pages, NULL, gup_flags); - mmap_read_unlock(current->mm); - } else { - ret = get_user_pages_unlocked(start, nr_pages, - pages, gup_flags); - } + local_irq_save(flags); + gup_pgd_range(start, end, gup_flags, pages, &nr_pinned); + local_irq_restore(flags); - return ret; + /* + * When pinning pages for DMA there could be a concurrent write protect + * from fork() via copy_page_range(), in this case always fail fast GUP. + */ + if (gup_flags & FOLL_PIN) { + if (read_seqcount_retry(¤t->mm->write_protect_seq, seq)) { + unpin_user_pages_lockless(pages, nr_pinned); + return 0; + } else { + sanity_check_pinned_pages(pages, nr_pinned); + } + } + return nr_pinned; } -static int internal_get_user_pages_fast(unsigned long start, int nr_pages, +static int internal_get_user_pages_fast(unsigned long start, + unsigned long nr_pages, unsigned int gup_flags, struct page **pages) { - unsigned long addr, len, end; - unsigned long flags; - int nr_pinned = 0, ret = 0; + 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_FAST_ONLY | FOLL_NOFAULT | + FOLL_PCI_P2PDMA | FOLL_HONOR_NUMA_FAULT))) return -EINVAL; if (gup_flags & FOLL_PIN) - atomic_set(¤t->mm->has_pinned, 1); + mm_set_has_pinned_flag(¤t->mm->flags); if (!(gup_flags & FOLL_FAST_ONLY)) might_lock_read(¤t->mm->mmap_lock); start = untagged_addr(start) & PAGE_MASK; - addr = start; - len = (unsigned long) nr_pages << PAGE_SHIFT; - end = start + len; - - if (end <= start) - return 0; + 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; - /* - * Disable interrupts. The nested form is used, in order to allow - * full, general purpose use of this routine. - * - * With interrupts disabled, we block page table pages from being - * freed from under us. See struct mmu_table_batch comments in - * include/asm-generic/tlb.h for more details. - * - * We do not adopt an rcu_read_lock(.) here as we also want to - * block IPIs that come from THPs splitting. - */ - if (IS_ENABLED(CONFIG_HAVE_FAST_GUP) && gup_fast_permitted(start, end)) { - unsigned long fast_flags = gup_flags; - - local_irq_save(flags); - gup_pgd_range(addr, end, fast_flags, pages, &nr_pinned); - local_irq_restore(flags); - ret = nr_pinned; - } - - if (nr_pinned < nr_pages && !(gup_flags & FOLL_FAST_ONLY)) { - /* Try to get the remaining pages with get_user_pages */ - start += nr_pinned << PAGE_SHIFT; - pages += nr_pinned; - - ret = __gup_longterm_unlocked(start, nr_pages - nr_pinned, - gup_flags, pages); - - /* Have to be a bit careful with return values */ - if (nr_pinned > 0) { - if (ret < 0) - ret = nr_pinned; - else - ret += nr_pinned; - } + 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; + return ret + nr_pinned; } + /** * get_user_pages_fast_only() - pin user pages in memory * @start: starting user address @@ -2746,8 +3237,6 @@ static int internal_get_user_pages_fast(unsigned long start, int nr_pages, * * Like get_user_pages_fast() except it's IRQ-safe in that it won't fall back to * the regular GUP. - * Note a difference with get_user_pages_fast: this always returns the - * number of pages pinned, 0 if no pages were pinned. * * If the architecture does not support this function, simply return with no * pages pinned. @@ -2759,7 +3248,6 @@ static int internal_get_user_pages_fast(unsigned long start, int nr_pages, int get_user_pages_fast_only(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages) { - int nr_pinned; /* * 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. @@ -2767,21 +3255,11 @@ int get_user_pages_fast_only(unsigned long start, int nr_pages, * FOLL_FAST_ONLY is required in order to match the API description of * this routine: no fall back to regular ("slow") GUP. */ - gup_flags |= FOLL_GET | FOLL_FAST_ONLY; - - nr_pinned = internal_get_user_pages_fast(start, nr_pages, gup_flags, - pages); - - /* - * As specified in the API description above, this routine is not - * allowed to return negative values. However, the common core - * routine internal_get_user_pages_fast() *can* return -errno. - * Therefore, correct for that here: - */ - if (nr_pinned < 0) - nr_pinned = 0; + if (!is_valid_gup_args(pages, NULL, &gup_flags, + FOLL_GET | FOLL_FAST_ONLY)) + return -EINVAL; - return nr_pinned; + return internal_get_user_pages_fast(start, nr_pages, gup_flags, pages); } EXPORT_SYMBOL_GPL(get_user_pages_fast_only); @@ -2804,16 +3282,14 @@ EXPORT_SYMBOL_GPL(get_user_pages_fast_only); int get_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages) { - if (!is_valid_gup_flags(gup_flags)) - return -EINVAL; - /* * 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. */ - gup_flags |= FOLL_GET; + 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); @@ -2833,55 +3309,19 @@ EXPORT_SYMBOL_GPL(get_user_pages_fast); * * 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) { - /* FOLL_GET and FOLL_PIN are mutually exclusive. */ - if (WARN_ON_ONCE(gup_flags & FOLL_GET)) + if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_PIN)) return -EINVAL; - - gup_flags |= FOLL_PIN; return internal_get_user_pages_fast(start, nr_pages, gup_flags, pages); } EXPORT_SYMBOL_GPL(pin_user_pages_fast); -/* - * This is the FOLL_PIN equivalent of get_user_pages_fast_only(). Behavior - * is the same, except that this one sets FOLL_PIN instead of FOLL_GET. - * - * The API rules are the same, too: no negative values may be returned. - */ -int pin_user_pages_fast_only(unsigned long start, int nr_pages, - unsigned int gup_flags, struct page **pages) -{ - int nr_pinned; - - /* - * FOLL_GET and FOLL_PIN are mutually exclusive. Note that the API - * rules require returning 0, rather than -errno: - */ - if (WARN_ON_ONCE(gup_flags & FOLL_GET)) - return 0; - /* - * FOLL_FAST_ONLY is required in order to match the API description of - * this routine: no fall back to regular ("slow") GUP. - */ - gup_flags |= (FOLL_PIN | FOLL_FAST_ONLY); - nr_pinned = internal_get_user_pages_fast(start, nr_pages, gup_flags, - pages); - /* - * This routine is not allowed to return negative values. However, - * internal_get_user_pages_fast() *can* return -errno. Therefore, - * correct for that here: - */ - if (nr_pinned < 0) - nr_pinned = 0; - - return nr_pinned; -} -EXPORT_SYMBOL_GPL(pin_user_pages_fast_only); - /** * pin_user_pages_remote() - pin pages of a remote process * @@ -2890,10 +3330,7 @@ EXPORT_SYMBOL_GPL(pin_user_pages_fast_only); * @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. Or NULL, if caller - * only intends to ensure the pages are faulted in. - * @vmas: array of pointers to vmas corresponding to each page. - * Or NULL if the caller does not require them. + * 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. @@ -2904,19 +3341,23 @@ EXPORT_SYMBOL_GPL(pin_user_pages_fast_only); * * 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, - struct vm_area_struct **vmas, int *locked) + int *locked) { - /* FOLL_GET and FOLL_PIN are mutually exclusive. */ - if (WARN_ON_ONCE(gup_flags & FOLL_GET)) - return -EINVAL; + int local_locked = 1; - gup_flags |= FOLL_PIN; - return __get_user_pages_remote(mm, start, nr_pages, gup_flags, - pages, vmas, locked); + 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); @@ -2927,28 +3368,26 @@ EXPORT_SYMBOL(pin_user_pages_remote); * @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. Or NULL, if caller - * only intends to ensure the pages are faulted in. - * @vmas: array of pointers to vmas corresponding to each page. - * Or NULL if the caller does not require them. + * 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, - struct vm_area_struct **vmas) + unsigned int gup_flags, struct page **pages) { - /* FOLL_GET and FOLL_PIN are mutually exclusive. */ - if (WARN_ON_ONCE(gup_flags & FOLL_GET)) - return -EINVAL; + int locked = 1; - gup_flags |= FOLL_PIN; + if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_PIN)) + return 0; return __gup_longterm_locked(current->mm, start, nr_pages, - pages, vmas, gup_flags); + pages, &locked, gup_flags); } EXPORT_SYMBOL(pin_user_pages); @@ -2956,44 +3395,20 @@ 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) { - /* FOLL_GET and FOLL_PIN are mutually exclusive. */ - if (WARN_ON_ONCE(gup_flags & FOLL_GET)) - return -EINVAL; - - gup_flags |= FOLL_PIN; - return get_user_pages_unlocked(start, nr_pages, pages, gup_flags); -} -EXPORT_SYMBOL(pin_user_pages_unlocked); - -/* - * pin_user_pages_locked() is the FOLL_PIN variant of get_user_pages_locked(). - * Behavior is the same, except that this one sets FOLL_PIN and rejects - * FOLL_GET. - */ -long pin_user_pages_locked(unsigned long start, unsigned long nr_pages, - unsigned int gup_flags, struct page **pages, - int *locked) -{ - /* - * FIXME: Current FOLL_LONGTERM behavior is incompatible with - * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on - * vmas. As there are no users of this flag in this call we simply - * disallow this option for now. - */ - if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM)) - return -EINVAL; + int locked = 0; - /* FOLL_GET and FOLL_PIN are mutually exclusive. */ - if (WARN_ON_ONCE(gup_flags & FOLL_GET)) - return -EINVAL; + if (!is_valid_gup_args(pages, NULL, &gup_flags, + FOLL_PIN | FOLL_TOUCH | FOLL_UNLOCKABLE)) + return 0; - gup_flags |= FOLL_PIN; - return __get_user_pages_locked(current->mm, start, nr_pages, - pages, NULL, locked, - gup_flags | FOLL_TOUCH); + return __gup_longterm_locked(current->mm, start, nr_pages, pages, + &locked, gup_flags); } -EXPORT_SYMBOL(pin_user_pages_locked); +EXPORT_SYMBOL(pin_user_pages_unlocked); |