diff options
Diffstat (limited to 'mm/gup.c')
| -rw-r--r-- | mm/gup.c | 1071 |
1 files changed, 667 insertions, 404 deletions
@@ -89,7 +89,7 @@ retry: * belongs to this folio. */ if (unlikely(page_folio(page) != folio)) { - if (!put_devmap_managed_page_refs(&folio->page, refs)) + if (!put_devmap_managed_folio_refs(folio, refs)) folio_put_refs(folio, refs); goto retry; } @@ -97,95 +97,6 @@ retry: return folio; } -/** - * 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 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: 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. - * - * 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. - */ -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_folio(page, refs); - - /* FOLL_PIN is set */ - - /* - * 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; - } - - /* - * 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(); - - node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, refs); - - return folio; -} - static void gup_put_folio(struct folio *folio, int refs, unsigned int flags) { if (flags & FOLL_PIN) { @@ -198,63 +109,64 @@ static void gup_put_folio(struct folio *folio, int refs, unsigned int flags) refs *= GUP_PIN_COUNTING_BIAS; } - if (!put_devmap_managed_page_refs(&folio->page, refs)) + if (!put_devmap_managed_folio_refs(folio, 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. + * try_grab_folio() - add a folio's refcount by a flag-dependent amount + * @folio: pointer to folio to be grabbed + * @refs: the value to (effectively) add to the folio's refcount + * @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. + * FOLL_PIN or FOLL_GET behavior, when incrementing the folio's refcount. * * Either FOLL_PIN or FOLL_GET (or neither) may be set, but not both at the same - * time. Cases: please see the try_grab_folio() documentation, with - * "refs=1". + * time. * * 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: * - * -ENOMEM FOLL_GET or FOLL_PIN was set, but the page could not + * -ENOMEM FOLL_GET or FOLL_PIN was set, but the folio could not * be grabbed. + * + * It is called when we have a stable reference for the folio, typically in + * GUP slow path. */ -int __must_check try_grab_page(struct page *page, unsigned int flags) +int __must_check try_grab_folio(struct folio *folio, int refs, + unsigned int flags) { - struct folio *folio = page_folio(page); - if (WARN_ON_ONCE(folio_ref_count(folio) <= 0)) return -ENOMEM; - if (unlikely(!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(page))) + if (unlikely(!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(&folio->page))) return -EREMOTEIO; if (flags & FOLL_GET) - folio_ref_inc(folio); + folio_ref_add(folio, refs); 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)) + if (is_zero_folio(folio)) return 0; /* - * Similar to try_grab_folio(): be sure to *also* - * increment the normal page refcount field at least once, + * Increment the normal page refcount field at least once, * so that the page really is pinned. */ if (folio_test_large(folio)) { - folio_ref_add(folio, 1); - atomic_add(1, &folio->_pincount); + folio_ref_add(folio, refs); + atomic_add(refs, &folio->_pincount); } else { - folio_ref_add(folio, GUP_PIN_COUNTING_BIAS); + folio_ref_add(folio, refs * GUP_PIN_COUNTING_BIAS); } - node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, 1); + node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, refs); } return 0; @@ -440,7 +352,7 @@ void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages, } EXPORT_SYMBOL(unpin_user_page_range_dirty_lock); -static void unpin_user_pages_lockless(struct page **pages, unsigned long npages) +static void gup_fast_unpin_user_pages(struct page **pages, unsigned long npages) { unsigned long i; struct folio *folio; @@ -500,22 +412,446 @@ static inline void mm_set_has_pinned_flag(unsigned long *mm_flags) } #ifdef CONFIG_MMU + +#if defined(CONFIG_ARCH_HAS_HUGEPD) || defined(CONFIG_HAVE_GUP_FAST) +static int record_subpages(struct page *page, unsigned long sz, + unsigned long addr, unsigned long end, + struct page **pages) +{ + struct page *start_page; + int nr; + + start_page = nth_page(page, (addr & (sz - 1)) >> PAGE_SHIFT); + for (nr = 0; addr != end; nr++, addr += PAGE_SIZE) + pages[nr] = nth_page(start_page, nr); + + return nr; +} + +/** + * try_grab_folio_fast() - Attempt to get or pin a folio in fast path. + * @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 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: 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. + * + * 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. + * + * It uses add ref unless zero to elevate the folio refcount and must be called + * in fast path only. + */ +static struct folio *try_grab_folio_fast(struct page *page, int refs, + unsigned int flags) +{ + struct folio *folio; + + /* Raise warn if it is not called in fast GUP */ + VM_WARN_ON_ONCE(!irqs_disabled()); + + if (WARN_ON_ONCE((flags & (FOLL_GET | FOLL_PIN)) == 0)) + return NULL; + + if (unlikely(!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(page))) + return NULL; + + if (flags & FOLL_GET) + return try_get_folio(page, refs); + + /* FOLL_PIN is set */ + + /* + * 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_folio_refs(folio, refs)) + folio_put_refs(folio, refs); + 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(); + + node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, refs); + + return folio; +} +#endif /* CONFIG_ARCH_HAS_HUGEPD || CONFIG_HAVE_GUP_FAST */ + +#ifdef CONFIG_ARCH_HAS_HUGEPD +static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end, + unsigned long sz) +{ + unsigned long __boundary = (addr + sz) & ~(sz-1); + return (__boundary - 1 < end - 1) ? __boundary : end; +} + +/* + * Returns 1 if succeeded, 0 if failed, -EMLINK if unshare needed. + * + * NOTE: for the same entry, gup-fast and gup-slow can return different + * results (0 v.s. -EMLINK) depending on whether vma is available. This is + * the expected behavior, where we simply want gup-fast to fallback to + * gup-slow to take the vma reference first. + */ +static int gup_hugepte(struct vm_area_struct *vma, pte_t *ptep, unsigned long sz, + unsigned long addr, unsigned long end, unsigned int flags, + struct page **pages, int *nr, bool fast) +{ + unsigned long pte_end; + struct page *page; + struct folio *folio; + pte_t pte; + int refs; + + pte_end = (addr + sz) & ~(sz-1); + if (pte_end < end) + end = pte_end; + + pte = huge_ptep_get(ptep); + + if (!pte_access_permitted(pte, flags & FOLL_WRITE)) + return 0; + + /* hugepages are never "special" */ + VM_BUG_ON(!pfn_valid(pte_pfn(pte))); + + page = pte_page(pte); + refs = record_subpages(page, sz, addr, end, pages + *nr); + + if (fast) { + folio = try_grab_folio_fast(page, refs, flags); + if (!folio) + return 0; + } else { + folio = page_folio(page); + if (try_grab_folio(folio, refs, flags)) + return 0; + } + + if (unlikely(pte_val(pte) != pte_val(ptep_get(ptep)))) { + gup_put_folio(folio, refs, flags); + return 0; + } + + if (!pte_write(pte) && gup_must_unshare(vma, flags, &folio->page)) { + gup_put_folio(folio, refs, flags); + return -EMLINK; + } + + *nr += refs; + folio_set_referenced(folio); + return 1; +} + +/* + * NOTE: currently GUP for a hugepd is only possible on hugetlbfs file + * systems on Power, which does not have issue with folio writeback against + * GUP updates. When hugepd will be extended to support non-hugetlbfs or + * even anonymous memory, we need to do extra check as what we do with most + * of the other folios. See writable_file_mapping_allowed() and + * gup_fast_folio_allowed() for more information. + */ +static int gup_hugepd(struct vm_area_struct *vma, hugepd_t hugepd, + unsigned long addr, unsigned int pdshift, + unsigned long end, unsigned int flags, + struct page **pages, int *nr, bool fast) +{ + pte_t *ptep; + unsigned long sz = 1UL << hugepd_shift(hugepd); + unsigned long next; + int ret; + + ptep = hugepte_offset(hugepd, addr, pdshift); + do { + next = hugepte_addr_end(addr, end, sz); + ret = gup_hugepte(vma, ptep, sz, addr, end, flags, pages, nr, + fast); + if (ret != 1) + return ret; + } while (ptep++, addr = next, addr != end); + + return 1; +} + +static struct page *follow_hugepd(struct vm_area_struct *vma, hugepd_t hugepd, + unsigned long addr, unsigned int pdshift, + unsigned int flags, + struct follow_page_context *ctx) +{ + struct page *page; + struct hstate *h; + spinlock_t *ptl; + int nr = 0, ret; + pte_t *ptep; + + /* Only hugetlb supports hugepd */ + if (WARN_ON_ONCE(!is_vm_hugetlb_page(vma))) + return ERR_PTR(-EFAULT); + + h = hstate_vma(vma); + ptep = hugepte_offset(hugepd, addr, pdshift); + ptl = huge_pte_lock(h, vma->vm_mm, ptep); + ret = gup_hugepd(vma, hugepd, addr, pdshift, addr + PAGE_SIZE, + flags, &page, &nr, false); + spin_unlock(ptl); + + if (ret == 1) { + /* GUP succeeded */ + WARN_ON_ONCE(nr != 1); + ctx->page_mask = (1U << huge_page_order(h)) - 1; + return page; + } + + /* ret can be either 0 (translates to NULL) or negative */ + return ERR_PTR(ret); +} +#else /* CONFIG_ARCH_HAS_HUGEPD */ +static inline int gup_hugepd(struct vm_area_struct *vma, hugepd_t hugepd, + unsigned long addr, unsigned int pdshift, + unsigned long end, unsigned int flags, + struct page **pages, int *nr, bool fast) +{ + return 0; +} + +static struct page *follow_hugepd(struct vm_area_struct *vma, hugepd_t hugepd, + unsigned long addr, unsigned int pdshift, + unsigned int flags, + struct follow_page_context *ctx) +{ + return NULL; +} +#endif /* CONFIG_ARCH_HAS_HUGEPD */ + + static struct page *no_page_table(struct vm_area_struct *vma, - unsigned int flags) + unsigned int flags, unsigned long address) { + if (!(flags & FOLL_DUMP)) + return NULL; + /* - * When core dumping an enormous anonymous area that nobody - * has touched so far, we don't want to allocate unnecessary pages or + * When core dumping, we don't want to allocate unnecessary pages or * page tables. Return error instead of NULL to skip handle_mm_fault, * then get_dump_page() will return NULL to leave a hole in the dump. * But we can only make this optimization where a hole would surely * be zero-filled if handle_mm_fault() actually did handle it. */ - if ((flags & FOLL_DUMP) && - (vma_is_anonymous(vma) || !vma->vm_ops->fault)) + if (is_vm_hugetlb_page(vma)) { + struct hstate *h = hstate_vma(vma); + + if (!hugetlbfs_pagecache_present(h, vma, address)) + return ERR_PTR(-EFAULT); + } else if ((vma_is_anonymous(vma) || !vma->vm_ops->fault)) { return ERR_PTR(-EFAULT); + } + + return NULL; +} + +#ifdef CONFIG_PGTABLE_HAS_HUGE_LEAVES +static struct page *follow_huge_pud(struct vm_area_struct *vma, + unsigned long addr, pud_t *pudp, + int flags, struct follow_page_context *ctx) +{ + struct mm_struct *mm = vma->vm_mm; + struct page *page; + pud_t pud = *pudp; + unsigned long pfn = pud_pfn(pud); + int ret; + + assert_spin_locked(pud_lockptr(mm, pudp)); + + if ((flags & FOLL_WRITE) && !pud_write(pud)) + return NULL; + + if (!pud_present(pud)) + return NULL; + + pfn += (addr & ~PUD_MASK) >> PAGE_SHIFT; + + if (IS_ENABLED(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) && + pud_devmap(pud)) { + /* + * device mapped pages can only be returned if the caller + * will manage the page reference count. + * + * At least one of FOLL_GET | FOLL_PIN must be set, so + * assert that here: + */ + if (!(flags & (FOLL_GET | FOLL_PIN))) + return ERR_PTR(-EEXIST); + + if (flags & FOLL_TOUCH) + touch_pud(vma, addr, pudp, flags & FOLL_WRITE); + + ctx->pgmap = get_dev_pagemap(pfn, ctx->pgmap); + if (!ctx->pgmap) + return ERR_PTR(-EFAULT); + } + + page = pfn_to_page(pfn); + + if (!pud_devmap(pud) && !pud_write(pud) && + gup_must_unshare(vma, flags, page)) + return ERR_PTR(-EMLINK); + + ret = try_grab_folio(page_folio(page), 1, flags); + if (ret) + page = ERR_PTR(ret); + else + ctx->page_mask = HPAGE_PUD_NR - 1; + + return page; +} + +/* FOLL_FORCE can write to even unwritable PMDs in COW mappings. */ +static inline bool can_follow_write_pmd(pmd_t pmd, struct page *page, + struct vm_area_struct *vma, + unsigned int flags) +{ + /* If the pmd is writable, we can write to the page. */ + if (pmd_write(pmd)) + 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) && !pmd_soft_dirty(pmd)) + return false; + return !userfaultfd_huge_pmd_wp(vma, pmd); +} + +static struct page *follow_huge_pmd(struct vm_area_struct *vma, + unsigned long addr, pmd_t *pmd, + unsigned int flags, + struct follow_page_context *ctx) +{ + struct mm_struct *mm = vma->vm_mm; + pmd_t pmdval = *pmd; + struct page *page; + int ret; + + assert_spin_locked(pmd_lockptr(mm, pmd)); + + page = pmd_page(pmdval); + if ((flags & FOLL_WRITE) && + !can_follow_write_pmd(pmdval, page, vma, flags)) + return NULL; + + /* Avoid dumping huge zero page */ + if ((flags & FOLL_DUMP) && is_huge_zero_pmd(pmdval)) + return ERR_PTR(-EFAULT); + + if (pmd_protnone(*pmd) && !gup_can_follow_protnone(vma, flags)) + return NULL; + + if (!pmd_write(pmdval) && gup_must_unshare(vma, flags, page)) + return ERR_PTR(-EMLINK); + + VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) && + !PageAnonExclusive(page), page); + + ret = try_grab_folio(page_folio(page), 1, flags); + if (ret) + return ERR_PTR(ret); + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + if (pmd_trans_huge(pmdval) && (flags & FOLL_TOUCH)) + touch_pmd(vma, addr, pmd, flags & FOLL_WRITE); +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + + page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT; + ctx->page_mask = HPAGE_PMD_NR - 1; + + return page; +} + +#else /* CONFIG_PGTABLE_HAS_HUGE_LEAVES */ +static struct page *follow_huge_pud(struct vm_area_struct *vma, + unsigned long addr, pud_t *pudp, + int flags, struct follow_page_context *ctx) +{ + return NULL; +} + +static struct page *follow_huge_pmd(struct vm_area_struct *vma, + unsigned long addr, pmd_t *pmd, + unsigned int flags, + struct follow_page_context *ctx) +{ return NULL; } +#endif /* CONFIG_PGTABLE_HAS_HUGE_LEAVES */ static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address, pte_t *pte, unsigned int flags) @@ -593,7 +929,7 @@ static struct page *follow_page_pte(struct vm_area_struct *vma, ptep = pte_offset_map_lock(mm, pmd, address, &ptl); if (!ptep) - return no_page_table(vma, flags); + return no_page_table(vma, flags, address); pte = ptep_get(ptep); if (!pte_present(pte)) goto no_page; @@ -647,8 +983,8 @@ static struct page *follow_page_pte(struct vm_area_struct *vma, VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) && !PageAnonExclusive(page), page); - /* try_grab_page() does nothing unless FOLL_GET or FOLL_PIN is set. */ - ret = try_grab_page(page, flags); + /* try_grab_folio() does nothing unless FOLL_GET or FOLL_PIN is set. */ + ret = try_grab_folio(page_folio(page), 1, flags); if (unlikely(ret)) { page = ERR_PTR(ret); goto out; @@ -685,7 +1021,7 @@ no_page: pte_unmap_unlock(ptep, ptl); if (!pte_none(pte)) return NULL; - return no_page_table(vma, flags); + return no_page_table(vma, flags, address); } static struct page *follow_pmd_mask(struct vm_area_struct *vma, @@ -701,42 +1037,45 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma, pmd = pmd_offset(pudp, address); pmdval = pmdp_get_lockless(pmd); if (pmd_none(pmdval)) - return no_page_table(vma, flags); + return no_page_table(vma, flags, address); if (!pmd_present(pmdval)) - return no_page_table(vma, flags); + return no_page_table(vma, flags, address); + if (unlikely(is_hugepd(__hugepd(pmd_val(pmdval))))) + return follow_hugepd(vma, __hugepd(pmd_val(pmdval)), + address, PMD_SHIFT, flags, ctx); 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); + return no_page_table(vma, flags, address); } - if (likely(!pmd_trans_huge(pmdval))) + if (likely(!pmd_leaf(pmdval))) return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); if (pmd_protnone(pmdval) && !gup_can_follow_protnone(vma, flags)) - return no_page_table(vma, flags); + return no_page_table(vma, flags, address); ptl = pmd_lock(mm, pmd); - if (unlikely(!pmd_present(*pmd))) { + pmdval = *pmd; + if (unlikely(!pmd_present(pmdval))) { spin_unlock(ptl); - return no_page_table(vma, flags); + return no_page_table(vma, flags, address); } - if (unlikely(!pmd_trans_huge(*pmd))) { + if (unlikely(!pmd_leaf(pmdval))) { spin_unlock(ptl); return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); } - if (flags & FOLL_SPLIT_PMD) { + if (pmd_trans_huge(pmdval) && (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); + page = follow_huge_pmd(vma, address, pmd, flags, ctx); spin_unlock(ptl); - ctx->page_mask = HPAGE_PMD_NR - 1; return page; } @@ -745,26 +1084,30 @@ static struct page *follow_pud_mask(struct vm_area_struct *vma, unsigned int flags, struct follow_page_context *ctx) { - pud_t *pud; + pud_t *pudp, pud; spinlock_t *ptl; struct page *page; struct mm_struct *mm = vma->vm_mm; - pud = pud_offset(p4dp, address); - if (pud_none(*pud)) - 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); + pudp = pud_offset(p4dp, address); + pud = READ_ONCE(*pudp); + if (!pud_present(pud)) + return no_page_table(vma, flags, address); + if (unlikely(is_hugepd(__hugepd(pud_val(pud))))) + return follow_hugepd(vma, __hugepd(pud_val(pud)), + address, PUD_SHIFT, flags, ctx); + if (pud_leaf(pud)) { + ptl = pud_lock(mm, pudp); + page = follow_huge_pud(vma, address, pudp, flags, ctx); spin_unlock(ptl); if (page) return page; - return no_page_table(vma, flags); + return no_page_table(vma, flags, address); } - if (unlikely(pud_bad(*pud))) - return no_page_table(vma, flags); + if (unlikely(pud_bad(pud))) + return no_page_table(vma, flags, address); - return follow_pmd_mask(vma, address, pud, flags, ctx); + return follow_pmd_mask(vma, address, pudp, flags, ctx); } static struct page *follow_p4d_mask(struct vm_area_struct *vma, @@ -772,16 +1115,20 @@ static struct page *follow_p4d_mask(struct vm_area_struct *vma, unsigned int flags, struct follow_page_context *ctx) { - p4d_t *p4d; + p4d_t *p4dp, p4d; - p4d = p4d_offset(pgdp, address); - if (p4d_none(*p4d)) - return no_page_table(vma, flags); - BUILD_BUG_ON(p4d_huge(*p4d)); - if (unlikely(p4d_bad(*p4d))) - return no_page_table(vma, flags); + p4dp = p4d_offset(pgdp, address); + p4d = READ_ONCE(*p4dp); + BUILD_BUG_ON(p4d_leaf(p4d)); + + if (unlikely(is_hugepd(__hugepd(p4d_val(p4d))))) + return follow_hugepd(vma, __hugepd(p4d_val(p4d)), + address, P4D_SHIFT, flags, ctx); - return follow_pud_mask(vma, address, p4d, flags, ctx); + if (!p4d_present(p4d) || p4d_bad(p4d)) + return no_page_table(vma, flags, address); + + return follow_pud_mask(vma, address, p4dp, flags, ctx); } /** @@ -814,24 +1161,24 @@ static struct page *follow_page_mask(struct vm_area_struct *vma, { pgd_t *pgd; struct mm_struct *mm = vma->vm_mm; + struct page *page; - ctx->page_mask = 0; - - /* - * Call hugetlb_follow_page_mask for hugetlb vmas as it will use - * special hugetlb page table walking code. This eliminates the - * need to check for hugetlb entries in the general walking code. - */ - if (is_vm_hugetlb_page(vma)) - return hugetlb_follow_page_mask(vma, address, flags, - &ctx->page_mask); + vma_pgtable_walk_begin(vma); + ctx->page_mask = 0; pgd = pgd_offset(mm, address); - if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) - return no_page_table(vma, flags); + if (unlikely(is_hugepd(__hugepd(pgd_val(*pgd))))) + page = follow_hugepd(vma, __hugepd(pgd_val(*pgd)), + address, PGDIR_SHIFT, flags, ctx); + else if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) + page = no_page_table(vma, flags, address); + else + page = follow_p4d_mask(vma, address, pgd, flags, ctx); + + vma_pgtable_walk_end(vma); - return follow_p4d_mask(vma, address, pgd, flags, ctx); + return page; } struct page *follow_page(struct vm_area_struct *vma, unsigned long address, @@ -901,7 +1248,7 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address, goto unmap; *page = pte_page(entry); } - ret = try_grab_page(*page, gup_flags); + ret = try_grab_folio(page_folio(*page), 1, gup_flags); if (unlikely(ret)) goto unmap; out: @@ -1304,20 +1651,19 @@ next_page: * pages. */ if (page_increm > 1) { - struct folio *folio; + struct folio *folio = page_folio(page); /* * 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)) { + if (try_grab_folio(folio, page_increm - 1, + foll_flags)) { /* * Release the 1st page ref if the * folio is problematic, fail hard. */ - gup_put_folio(page_folio(page), 1, + gup_put_folio(folio, 1, foll_flags); ret = -EFAULT; goto out; @@ -2144,6 +2490,7 @@ static int migrate_longterm_unpinnable_pages( struct migration_target_control mtc = { .nid = NUMA_NO_NODE, .gfp_mask = GFP_USER | __GFP_NOWARN, + .reason = MR_LONGTERM_PIN, }; if (migrate_pages(movable_page_list, alloc_migration_target, @@ -2431,7 +2778,7 @@ long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, EXPORT_SYMBOL(get_user_pages_unlocked); /* - * Fast GUP + * GUP-fast * * get_user_pages_fast attempts to pin user pages by walking the page * tables directly and avoids taking locks. Thus the walker needs to be @@ -2445,7 +2792,7 @@ EXPORT_SYMBOL(get_user_pages_unlocked); * * Another way to achieve this is to batch up page table containing pages * belonging to more than one mm_user, then rcu_sched a callback to free those - * pages. Disabling interrupts will allow the fast_gup walker to both block + * pages. Disabling interrupts will allow the gup_fast() walker to both block * the rcu_sched callback, and an IPI that we broadcast for splitting THPs * (which is a relatively rare event). The code below adopts this strategy. * @@ -2463,15 +2810,16 @@ EXPORT_SYMBOL(get_user_pages_unlocked); * * This code is based heavily on the PowerPC implementation by Nick Piggin. */ -#ifdef CONFIG_HAVE_FAST_GUP - +#ifdef CONFIG_HAVE_GUP_FAST /* - * Used in the GUP-fast path to determine whether a pin is permitted for a - * specific folio. + * Used in the GUP-fast path to determine whether GUP is permitted to work on + * 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. * + * GUP-fast must reject all secretmem folios. + * * 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 @@ -2481,25 +2829,34 @@ EXPORT_SYMBOL(get_user_pages_unlocked); * 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) +static bool gup_fast_folio_allowed(struct folio *folio, unsigned int flags) { + bool reject_file_backed = false; struct address_space *mapping; + bool check_secretmem = false; unsigned long mapping_flags; /* * If we aren't pinning then no problematic write can occur. A long term * pin is the most egregious case so this is the one we disallow. */ - if ((flags & (FOLL_PIN | FOLL_LONGTERM | FOLL_WRITE)) != + if ((flags & (FOLL_PIN | FOLL_LONGTERM | FOLL_WRITE)) == (FOLL_PIN | FOLL_LONGTERM | FOLL_WRITE)) - return true; + reject_file_backed = true; + + /* We hold a folio reference, so we can safely access folio fields. */ - /* The folio is pinned, so we can safely access folio fields. */ + /* secretmem folios are always order-0 folios. */ + if (IS_ENABLED(CONFIG_SECRETMEM) && !folio_test_large(folio)) + check_secretmem = true; + + if (!reject_file_backed && !check_secretmem) + return true; if (WARN_ON_ONCE(folio_test_slab(folio))) return false; - /* hugetlb mappings do not require dirty-tracking. */ + /* hugetlb neither requires dirty-tracking nor can be secretmem. */ if (folio_test_hugetlb(folio)) return true; @@ -2535,50 +2892,48 @@ static bool folio_fast_pin_allowed(struct folio *folio, unsigned int flags) /* * 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. + * address_space object. */ - return shmem_mapping(mapping); + if (check_secretmem && secretmem_mapping(mapping)) + return false; + /* The only remaining allowed file system is shmem. */ + return !reject_file_backed || shmem_mapping(mapping); } -static void __maybe_unused undo_dev_pagemap(int *nr, int nr_start, - unsigned int flags, - struct page **pages) +static void __maybe_unused gup_fast_undo_dev_pagemap(int *nr, int nr_start, + unsigned int flags, struct page **pages) { while ((*nr) - nr_start) { - struct page *page = pages[--(*nr)]; + struct folio *folio = page_folio(pages[--(*nr)]); - ClearPageReferenced(page); - if (flags & FOLL_PIN) - unpin_user_page(page); - else - put_page(page); + folio_clear_referenced(folio); + gup_put_folio(folio, 1, flags); } } #ifdef CONFIG_ARCH_HAS_PTE_SPECIAL /* - * Fast-gup relies on pte change detection to avoid concurrent pgtable + * GUP-fast relies on pte change detection to avoid concurrent pgtable * operations. * - * To pin the page, fast-gup needs to do below in order: + * To pin the page, GUP-fast 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 + * with GUP-fast, 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 + * For THP collapse, it's a bit more complicated because GUP-fast 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) +static int gup_fast_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; @@ -2611,7 +2966,7 @@ static int gup_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr, pgmap = get_dev_pagemap(pte_pfn(pte), pgmap); if (unlikely(!pgmap)) { - undo_dev_pagemap(nr, nr_start, flags, pages); + gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); goto pte_unmap; } } else if (pte_special(pte)) @@ -2620,22 +2975,17 @@ static int gup_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr, VM_BUG_ON(!pfn_valid(pte_pfn(pte))); page = pte_page(pte); - folio = try_grab_folio(page, 1, flags); + folio = try_grab_folio_fast(page, 1, flags); if (!folio) goto pte_unmap; - if (unlikely(folio_is_secretmem(folio))) { - gup_put_folio(folio, 1, flags); - goto pte_unmap; - } - if (unlikely(pmd_val(pmd) != pmd_val(*pmdp)) || unlikely(pte_val(pte) != pte_val(ptep_get(ptep)))) { gup_put_folio(folio, 1, flags); goto pte_unmap; } - if (!folio_fast_pin_allowed(folio, flags)) { + if (!gup_fast_folio_allowed(folio, flags)) { gup_put_folio(folio, 1, flags); goto pte_unmap; } @@ -2680,44 +3030,45 @@ pte_unmap: * * For a futex to be placed on a THP tail page, get_futex_key requires a * get_user_pages_fast_only implementation that can pin pages. Thus it's still - * useful to have gup_huge_pmd even if we can't operate on ptes. + * useful to have gup_fast_pmd_leaf even if we can't operate on ptes. */ -static int gup_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr, - unsigned long end, unsigned int flags, - struct page **pages, int *nr) +static int gup_fast_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr, + unsigned long end, unsigned int flags, struct page **pages, + int *nr) { return 0; } #endif /* CONFIG_ARCH_HAS_PTE_SPECIAL */ #if defined(CONFIG_ARCH_HAS_PTE_DEVMAP) && defined(CONFIG_TRANSPARENT_HUGEPAGE) -static int __gup_device_huge(unsigned long pfn, unsigned long addr, - unsigned long end, unsigned int flags, - struct page **pages, int *nr) +static int gup_fast_devmap_leaf(unsigned long pfn, unsigned long addr, + unsigned long end, unsigned int flags, struct page **pages, int *nr) { int nr_start = *nr; struct dev_pagemap *pgmap = NULL; do { + struct folio *folio; struct page *page = pfn_to_page(pfn); pgmap = get_dev_pagemap(pfn, pgmap); if (unlikely(!pgmap)) { - undo_dev_pagemap(nr, nr_start, flags, pages); + gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); break; } if (!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(page)) { - undo_dev_pagemap(nr, nr_start, flags, pages); + gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); break; } - SetPageReferenced(page); - pages[*nr] = page; - if (unlikely(try_grab_page(page, flags))) { - undo_dev_pagemap(nr, nr_start, flags, pages); + folio = try_grab_folio_fast(page, 1, flags); + if (!folio) { + gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); break; } + folio_set_referenced(folio); + pages[*nr] = page; (*nr)++; pfn++; } while (addr += PAGE_SIZE, addr != end); @@ -2726,156 +3077,62 @@ static int __gup_device_huge(unsigned long pfn, unsigned long addr, return addr == end; } -static int __gup_device_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, - unsigned long end, unsigned int flags, - struct page **pages, int *nr) +static int gup_fast_devmap_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr, + unsigned long end, unsigned int flags, struct page **pages, + int *nr) { unsigned long fault_pfn; int nr_start = *nr; fault_pfn = pmd_pfn(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); - if (!__gup_device_huge(fault_pfn, addr, end, flags, pages, nr)) + if (!gup_fast_devmap_leaf(fault_pfn, addr, end, flags, pages, nr)) return 0; if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) { - undo_dev_pagemap(nr, nr_start, flags, pages); + gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); return 0; } return 1; } -static int __gup_device_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, - unsigned long end, unsigned int flags, - struct page **pages, int *nr) +static int gup_fast_devmap_pud_leaf(pud_t orig, pud_t *pudp, unsigned long addr, + unsigned long end, unsigned int flags, struct page **pages, + int *nr) { unsigned long fault_pfn; int nr_start = *nr; fault_pfn = pud_pfn(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); - if (!__gup_device_huge(fault_pfn, addr, end, flags, pages, nr)) + if (!gup_fast_devmap_leaf(fault_pfn, addr, end, flags, pages, nr)) return 0; if (unlikely(pud_val(orig) != pud_val(*pudp))) { - undo_dev_pagemap(nr, nr_start, flags, pages); + gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); return 0; } return 1; } #else -static int __gup_device_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, - unsigned long end, unsigned int flags, - struct page **pages, int *nr) +static int gup_fast_devmap_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr, + unsigned long end, unsigned int flags, struct page **pages, + int *nr) { BUILD_BUG(); return 0; } -static int __gup_device_huge_pud(pud_t pud, pud_t *pudp, unsigned long addr, - unsigned long end, unsigned int flags, - struct page **pages, int *nr) +static int gup_fast_devmap_pud_leaf(pud_t pud, pud_t *pudp, unsigned long addr, + unsigned long end, unsigned int flags, struct page **pages, + int *nr) { BUILD_BUG(); return 0; } #endif -static int record_subpages(struct page *page, unsigned long addr, - unsigned long end, struct page **pages) -{ - int nr; - - for (nr = 0; addr != end; nr++, addr += PAGE_SIZE) - pages[nr] = nth_page(page, nr); - - return nr; -} - -#ifdef CONFIG_ARCH_HAS_HUGEPD -static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end, - unsigned long sz) -{ - unsigned long __boundary = (addr + sz) & ~(sz-1); - return (__boundary - 1 < end - 1) ? __boundary : end; -} - -static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, - unsigned long end, unsigned int flags, - struct page **pages, int *nr) -{ - unsigned long pte_end; - struct page *page; - struct folio *folio; - pte_t pte; - int refs; - - pte_end = (addr + sz) & ~(sz-1); - if (pte_end < end) - end = pte_end; - - pte = huge_ptep_get(ptep); - - if (!pte_access_permitted(pte, flags & FOLL_WRITE)) - return 0; - - /* hugepages are never "special" */ - VM_BUG_ON(!pfn_valid(pte_pfn(pte))); - - page = nth_page(pte_page(pte), (addr & (sz - 1)) >> PAGE_SHIFT); - refs = record_subpages(page, addr, end, pages + *nr); - - folio = try_grab_folio(page, refs, flags); - if (!folio) - return 0; - - if (unlikely(pte_val(pte) != pte_val(ptep_get(ptep)))) { - gup_put_folio(folio, refs, flags); - return 0; - } - - if (!folio_fast_pin_allowed(folio, flags)) { - gup_put_folio(folio, refs, flags); - return 0; - } - - if (!pte_write(pte) && gup_must_unshare(NULL, flags, &folio->page)) { - gup_put_folio(folio, refs, flags); - return 0; - } - - *nr += refs; - folio_set_referenced(folio); - return 1; -} - -static int gup_huge_pd(hugepd_t hugepd, unsigned long addr, - unsigned int pdshift, unsigned long end, unsigned int flags, - struct page **pages, int *nr) -{ - pte_t *ptep; - unsigned long sz = 1UL << hugepd_shift(hugepd); - unsigned long next; - - ptep = hugepte_offset(hugepd, addr, pdshift); - do { - next = hugepte_addr_end(addr, end, sz); - if (!gup_hugepte(ptep, sz, addr, end, flags, pages, nr)) - return 0; - } while (ptep++, addr = next, addr != end); - - return 1; -} -#else -static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr, - unsigned int pdshift, unsigned long end, unsigned int flags, - struct page **pages, int *nr) -{ - return 0; -} -#endif /* CONFIG_ARCH_HAS_HUGEPD */ - -static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, - unsigned long end, unsigned int flags, - struct page **pages, int *nr) +static int gup_fast_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr, + unsigned long end, unsigned int flags, struct page **pages, + int *nr) { struct page *page; struct folio *folio; @@ -2887,14 +3144,14 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, if (pmd_devmap(orig)) { if (unlikely(flags & FOLL_LONGTERM)) return 0; - return __gup_device_huge_pmd(orig, pmdp, addr, end, flags, - pages, nr); + return gup_fast_devmap_pmd_leaf(orig, pmdp, addr, end, flags, + pages, nr); } - page = nth_page(pmd_page(orig), (addr & ~PMD_MASK) >> PAGE_SHIFT); - refs = record_subpages(page, addr, end, pages + *nr); + page = pmd_page(orig); + refs = record_subpages(page, PMD_SIZE, addr, end, pages + *nr); - folio = try_grab_folio(page, refs, flags); + folio = try_grab_folio_fast(page, refs, flags); if (!folio) return 0; @@ -2903,7 +3160,7 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, return 0; } - if (!folio_fast_pin_allowed(folio, flags)) { + if (!gup_fast_folio_allowed(folio, flags)) { gup_put_folio(folio, refs, flags); return 0; } @@ -2917,9 +3174,9 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, return 1; } -static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, - unsigned long end, unsigned int flags, - struct page **pages, int *nr) +static int gup_fast_pud_leaf(pud_t orig, pud_t *pudp, unsigned long addr, + unsigned long end, unsigned int flags, struct page **pages, + int *nr) { struct page *page; struct folio *folio; @@ -2931,14 +3188,14 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, if (pud_devmap(orig)) { if (unlikely(flags & FOLL_LONGTERM)) return 0; - return __gup_device_huge_pud(orig, pudp, addr, end, flags, - pages, nr); + return gup_fast_devmap_pud_leaf(orig, pudp, addr, end, flags, + pages, nr); } - page = nth_page(pud_page(orig), (addr & ~PUD_MASK) >> PAGE_SHIFT); - refs = record_subpages(page, addr, end, pages + *nr); + page = pud_page(orig); + refs = record_subpages(page, PUD_SIZE, addr, end, pages + *nr); - folio = try_grab_folio(page, refs, flags); + folio = try_grab_folio_fast(page, refs, flags); if (!folio) return 0; @@ -2947,7 +3204,7 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, return 0; } - if (!folio_fast_pin_allowed(folio, flags)) { + if (!gup_fast_folio_allowed(folio, flags)) { gup_put_folio(folio, refs, flags); return 0; } @@ -2962,9 +3219,9 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, return 1; } -static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr, - unsigned long end, unsigned int flags, - struct page **pages, int *nr) +static int gup_fast_pgd_leaf(pgd_t orig, pgd_t *pgdp, unsigned long addr, + unsigned long end, unsigned int flags, struct page **pages, + int *nr) { int refs; struct page *page; @@ -2975,10 +3232,10 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr, BUILD_BUG_ON(pgd_devmap(orig)); - page = nth_page(pgd_page(orig), (addr & ~PGDIR_MASK) >> PAGE_SHIFT); - refs = record_subpages(page, addr, end, pages + *nr); + page = pgd_page(orig); + refs = record_subpages(page, PGDIR_SIZE, addr, end, pages + *nr); - folio = try_grab_folio(page, refs, flags); + folio = try_grab_folio_fast(page, refs, flags); if (!folio) return 0; @@ -2992,7 +3249,7 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr, return 0; } - if (!folio_fast_pin_allowed(folio, flags)) { + if (!gup_fast_folio_allowed(folio, flags)) { gup_put_folio(folio, refs, flags); return 0; } @@ -3002,8 +3259,9 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr, return 1; } -static int gup_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr, unsigned long end, - unsigned int flags, struct page **pages, int *nr) +static int gup_fast_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr, + unsigned long end, unsigned int flags, struct page **pages, + int *nr) { unsigned long next; pmd_t *pmdp; @@ -3016,13 +3274,12 @@ static int gup_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr, unsigned lo if (!pmd_present(pmd)) return 0; - if (unlikely(pmd_trans_huge(pmd) || pmd_huge(pmd) || - pmd_devmap(pmd))) { - /* See gup_pte_range() */ + if (unlikely(pmd_leaf(pmd))) { + /* See gup_fast_pte_range() */ if (pmd_protnone(pmd)) return 0; - if (!gup_huge_pmd(pmd, pmdp, addr, next, flags, + if (!gup_fast_pmd_leaf(pmd, pmdp, addr, next, flags, pages, nr)) return 0; @@ -3031,18 +3288,21 @@ static int gup_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr, unsigned lo * architecture have different format for hugetlbfs * pmd format and THP pmd format */ - if (!gup_huge_pd(__hugepd(pmd_val(pmd)), addr, - PMD_SHIFT, next, flags, pages, nr)) + if (gup_hugepd(NULL, __hugepd(pmd_val(pmd)), addr, + PMD_SHIFT, next, flags, pages, nr, + true) != 1) return 0; - } else if (!gup_pte_range(pmd, pmdp, addr, next, flags, pages, nr)) + } else if (!gup_fast_pte_range(pmd, pmdp, addr, next, flags, + pages, nr)) return 0; } while (pmdp++, addr = next, addr != end); return 1; } -static int gup_pud_range(p4d_t *p4dp, p4d_t p4d, unsigned long addr, unsigned long end, - unsigned int flags, struct page **pages, int *nr) +static int gup_fast_pud_range(p4d_t *p4dp, p4d_t p4d, unsigned long addr, + unsigned long end, unsigned int flags, struct page **pages, + int *nr) { unsigned long next; pud_t *pudp; @@ -3054,23 +3314,26 @@ 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) || pud_devmap(pud))) { - if (!gup_huge_pud(pud, pudp, addr, next, flags, - pages, nr)) + if (unlikely(pud_leaf(pud))) { + if (!gup_fast_pud_leaf(pud, pudp, addr, next, flags, + pages, nr)) return 0; } else if (unlikely(is_hugepd(__hugepd(pud_val(pud))))) { - if (!gup_huge_pd(__hugepd(pud_val(pud)), addr, - PUD_SHIFT, next, flags, pages, nr)) + if (gup_hugepd(NULL, __hugepd(pud_val(pud)), addr, + PUD_SHIFT, next, flags, pages, nr, + true) != 1) return 0; - } else if (!gup_pmd_range(pudp, pud, addr, next, flags, pages, nr)) + } else if (!gup_fast_pmd_range(pudp, pud, addr, next, flags, + pages, nr)) return 0; } while (pudp++, addr = next, addr != end); return 1; } -static int gup_p4d_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr, unsigned long end, - unsigned int flags, struct page **pages, int *nr) +static int gup_fast_p4d_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr, + unsigned long end, unsigned int flags, struct page **pages, + int *nr) { unsigned long next; p4d_t *p4dp; @@ -3080,21 +3343,23 @@ static int gup_p4d_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr, unsigned lo p4d_t p4d = READ_ONCE(*p4dp); next = p4d_addr_end(addr, end); - if (p4d_none(p4d)) + if (!p4d_present(p4d)) return 0; - BUILD_BUG_ON(p4d_huge(p4d)); + BUILD_BUG_ON(p4d_leaf(p4d)); if (unlikely(is_hugepd(__hugepd(p4d_val(p4d))))) { - if (!gup_huge_pd(__hugepd(p4d_val(p4d)), addr, - P4D_SHIFT, next, flags, pages, nr)) + if (gup_hugepd(NULL, __hugepd(p4d_val(p4d)), addr, + P4D_SHIFT, next, flags, pages, nr, + true) != 1) return 0; - } else if (!gup_pud_range(p4dp, p4d, addr, next, flags, pages, nr)) + } else if (!gup_fast_pud_range(p4dp, p4d, addr, next, flags, + pages, nr)) return 0; } while (p4dp++, addr = next, addr != end); return 1; } -static void gup_pgd_range(unsigned long addr, unsigned long end, +static void gup_fast_pgd_range(unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; @@ -3107,24 +3372,26 @@ static void gup_pgd_range(unsigned long addr, unsigned long end, next = pgd_addr_end(addr, end); if (pgd_none(pgd)) return; - if (unlikely(pgd_huge(pgd))) { - if (!gup_huge_pgd(pgd, pgdp, addr, next, flags, - pages, nr)) + if (unlikely(pgd_leaf(pgd))) { + if (!gup_fast_pgd_leaf(pgd, pgdp, addr, next, flags, + pages, nr)) return; } else if (unlikely(is_hugepd(__hugepd(pgd_val(pgd))))) { - if (!gup_huge_pd(__hugepd(pgd_val(pgd)), addr, - PGDIR_SHIFT, next, flags, pages, nr)) + if (gup_hugepd(NULL, __hugepd(pgd_val(pgd)), addr, + PGDIR_SHIFT, next, flags, pages, nr, + true) != 1) return; - } else if (!gup_p4d_range(pgdp, pgd, addr, next, flags, pages, nr)) + } else if (!gup_fast_p4d_range(pgdp, pgd, addr, next, flags, + pages, nr)) return; } while (pgdp++, addr = next, addr != end); } #else -static inline void gup_pgd_range(unsigned long addr, unsigned long end, +static inline void gup_fast_pgd_range(unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { } -#endif /* CONFIG_HAVE_FAST_GUP */ +#endif /* CONFIG_HAVE_GUP_FAST */ #ifndef gup_fast_permitted /* @@ -3137,16 +3404,14 @@ static bool gup_fast_permitted(unsigned long start, unsigned long end) } #endif -static unsigned long lockless_pages_from_mm(unsigned long start, - unsigned long end, - unsigned int gup_flags, - struct page **pages) +static unsigned long gup_fast(unsigned long start, unsigned long end, + unsigned int gup_flags, struct page **pages) { unsigned long flags; int nr_pinned = 0; unsigned seq; - if (!IS_ENABLED(CONFIG_HAVE_FAST_GUP) || + if (!IS_ENABLED(CONFIG_HAVE_GUP_FAST) || !gup_fast_permitted(start, end)) return 0; @@ -3168,16 +3433,16 @@ static unsigned long lockless_pages_from_mm(unsigned long start, * that come from THPs splitting. */ local_irq_save(flags); - gup_pgd_range(start, end, gup_flags, pages, &nr_pinned); + gup_fast_pgd_range(start, end, gup_flags, pages, &nr_pinned); local_irq_restore(flags); /* * 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. + * from fork() via copy_page_range(), in this case always fail GUP-fast. */ if (gup_flags & FOLL_PIN) { if (read_seqcount_retry(¤t->mm->write_protect_seq, seq)) { - unpin_user_pages_lockless(pages, nr_pinned); + gup_fast_unpin_user_pages(pages, nr_pinned); return 0; } else { sanity_check_pinned_pages(pages, nr_pinned); @@ -3186,10 +3451,8 @@ static unsigned long lockless_pages_from_mm(unsigned long start, return nr_pinned; } -static int internal_get_user_pages_fast(unsigned long start, - unsigned long nr_pages, - unsigned int gup_flags, - struct page **pages) +static int gup_fast_fallback(unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages) { unsigned long len, end; unsigned long nr_pinned; @@ -3217,7 +3480,7 @@ static int internal_get_user_pages_fast(unsigned long start, if (unlikely(!access_ok((void __user *)start, len))) return -EFAULT; - nr_pinned = lockless_pages_from_mm(start, end, gup_flags, pages); + nr_pinned = gup_fast(start, end, gup_flags, pages); if (nr_pinned == nr_pages || gup_flags & FOLL_FAST_ONLY) return nr_pinned; @@ -3271,7 +3534,7 @@ int get_user_pages_fast_only(unsigned long start, int nr_pages, FOLL_GET | FOLL_FAST_ONLY)) return -EINVAL; - return internal_get_user_pages_fast(start, nr_pages, gup_flags, pages); + return gup_fast_fallback(start, nr_pages, gup_flags, pages); } EXPORT_SYMBOL_GPL(get_user_pages_fast_only); @@ -3302,7 +3565,7 @@ int get_user_pages_fast(unsigned long start, int nr_pages, */ 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); + return gup_fast_fallback(start, nr_pages, gup_flags, pages); } EXPORT_SYMBOL_GPL(get_user_pages_fast); @@ -3330,7 +3593,7 @@ int pin_user_pages_fast(unsigned long start, int nr_pages, { if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_PIN)) return -EINVAL; - return internal_get_user_pages_fast(start, nr_pages, gup_flags, pages); + return gup_fast_fallback(start, nr_pages, gup_flags, pages); } EXPORT_SYMBOL_GPL(pin_user_pages_fast); |