diff options
Diffstat (limited to 'mm/memory.c')
| -rw-r--r-- | mm/memory.c | 573 |
1 files changed, 403 insertions, 170 deletions
diff --git a/mm/memory.c b/mm/memory.c index 2a12028a3749..54bcd5327b74 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -86,6 +86,7 @@ #include "pgalloc-track.h" #include "internal.h" +#include "swap.h" #if defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS) && !defined(CONFIG_COMPILE_TEST) #warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_cpupid. @@ -99,6 +100,8 @@ struct page *mem_map; EXPORT_SYMBOL(mem_map); #endif +static vm_fault_t do_fault(struct vm_fault *vmf); + /* * A number of key systems in x86 including ioremap() rely on the assumption * that high_memory defines the upper bound on direct map memory, then end @@ -720,12 +723,14 @@ static void restore_exclusive_pte(struct vm_area_struct *vma, else if (is_writable_device_exclusive_entry(entry)) pte = maybe_mkwrite(pte_mkdirty(pte), vma); + VM_BUG_ON(pte_write(pte) && !(PageAnon(page) && PageAnonExclusive(page))); + /* * No need to take a page reference as one was already * created when the swap entry was made. */ if (PageAnon(page)) - page_add_anon_rmap(page, vma, address, false); + page_add_anon_rmap(page, vma, address, RMAP_NONE); else /* * Currently device exclusive access only supports anonymous @@ -790,17 +795,23 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, &src_mm->mmlist); spin_unlock(&mmlist_lock); } + /* Mark the swap entry as shared. */ + if (pte_swp_exclusive(*src_pte)) { + pte = pte_swp_clear_exclusive(*src_pte); + set_pte_at(src_mm, addr, src_pte, pte); + } rss[MM_SWAPENTS]++; } else if (is_migration_entry(entry)) { page = pfn_swap_entry_to_page(entry); rss[mm_counter(page)]++; - if (is_writable_migration_entry(entry) && + if (!is_readable_migration_entry(entry) && is_cow_mapping(vm_flags)) { /* - * COW mappings require pages in both - * parent and child to be set to read. + * COW mappings require pages in both parent and child + * to be set to read. A previously exclusive entry is + * now shared. */ entry = make_readable_migration_entry( swp_offset(entry)); @@ -825,7 +836,8 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, */ get_page(page); rss[mm_counter(page)]++; - page_dup_rmap(page, false); + /* Cannot fail as these pages cannot get pinned. */ + BUG_ON(page_try_dup_anon_rmap(page, false, src_vma)); /* * We do not preserve soft-dirty information, because so @@ -854,6 +866,14 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, if (try_restore_exclusive_pte(src_pte, src_vma, addr)) return -EBUSY; return -ENOENT; + } else if (is_pte_marker_entry(entry)) { + /* + * We're copying the pgtable should only because dst_vma has + * uffd-wp enabled, do sanity check. + */ + WARN_ON_ONCE(!userfaultfd_wp(dst_vma)); + set_pte_at(dst_mm, addr, dst_pte, pte); + return 0; } if (!userfaultfd_wp(dst_vma)) pte = pte_swp_clear_uffd_wp(pte); @@ -862,19 +882,11 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, } /* - * Copy a present and normal page if necessary. + * Copy a present and normal page. * - * NOTE! The usual case is that this doesn't need to do - * anything, and can just return a positive value. That - * will let the caller know that it can just increase - * the page refcount and re-use the pte the traditional - * way. - * - * But _if_ we need to copy it because it needs to be - * pinned in the parent (and the child should get its own - * copy rather than just a reference to the same page), - * we'll do that here and return zero to let the caller - * know we're done. + * NOTE! The usual case is that this isn't required; + * instead, the caller can just increase the page refcount + * and re-use the pte the traditional way. * * And if we need a pre-allocated page but don't yet have * one, return a negative error to let the preallocation @@ -884,25 +896,10 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, static inline int copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss, - struct page **prealloc, pte_t pte, struct page *page) + struct page **prealloc, struct page *page) { struct page *new_page; - - /* - * What we want to do is to check whether this page may - * have been pinned by the parent process. If so, - * instead of wrprotect the pte on both sides, we copy - * the page immediately so that we'll always guarantee - * the pinned page won't be randomly replaced in the - * future. - * - * The page pinning checks are just "has this mm ever - * seen pinning", along with the (inexact) check of - * the page count. That might give false positives for - * for pinning, but it will work correctly. - */ - if (likely(!page_needs_cow_for_dma(src_vma, page))) - return 1; + pte_t pte; new_page = *prealloc; if (!new_page) @@ -915,7 +912,7 @@ copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma *prealloc = NULL; copy_user_highpage(new_page, page, addr, src_vma); __SetPageUptodate(new_page); - page_add_new_anon_rmap(new_page, dst_vma, addr, false); + page_add_new_anon_rmap(new_page, dst_vma, addr); lru_cache_add_inactive_or_unevictable(new_page, dst_vma); rss[mm_counter(new_page)]++; @@ -944,16 +941,24 @@ copy_present_pte(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, struct page *page; page = vm_normal_page(src_vma, addr, pte); - if (page) { - int retval; - - retval = copy_present_page(dst_vma, src_vma, dst_pte, src_pte, - addr, rss, prealloc, pte, page); - if (retval <= 0) - return retval; - + if (page && PageAnon(page)) { + /* + * If this page may have been pinned by the parent process, + * copy the page immediately for the child so that we'll always + * guarantee the pinned page won't be randomly replaced in the + * future. + */ get_page(page); - page_dup_rmap(page, false); + if (unlikely(page_try_dup_anon_rmap(page, false, src_vma))) { + /* Page maybe pinned, we have to copy. */ + put_page(page); + return copy_present_page(dst_vma, src_vma, dst_pte, src_pte, + addr, rss, prealloc, page); + } + rss[mm_counter(page)]++; + } else if (page) { + get_page(page); + page_dup_file_rmap(page, false); rss[mm_counter(page)]++; } @@ -965,6 +970,7 @@ copy_present_pte(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, ptep_set_wrprotect(src_mm, addr, src_pte); pte = pte_wrprotect(pte); } + VM_BUG_ON(page && PageAnon(page) && PageAnonExclusive(page)); /* * If it's a shared mapping, mark it clean in @@ -1222,6 +1228,38 @@ copy_p4d_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, return 0; } +/* + * Return true if the vma needs to copy the pgtable during this fork(). Return + * false when we can speed up fork() by allowing lazy page faults later until + * when the child accesses the memory range. + */ +static bool +vma_needs_copy(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) +{ + /* + * Always copy pgtables when dst_vma has uffd-wp enabled even if it's + * file-backed (e.g. shmem). Because when uffd-wp is enabled, pgtable + * contains uffd-wp protection information, that's something we can't + * retrieve from page cache, and skip copying will lose those info. + */ + if (userfaultfd_wp(dst_vma)) + return true; + + if (src_vma->vm_flags & (VM_HUGETLB | VM_PFNMAP | VM_MIXEDMAP)) + return true; + + if (src_vma->anon_vma) + return true; + + /* + * Don't copy ptes where a page fault will fill them correctly. Fork + * becomes much lighter when there are big shared or private readonly + * mappings. The tradeoff is that copy_page_range is more efficient + * than faulting. + */ + return false; +} + int copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { @@ -1235,18 +1273,11 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) bool is_cow; int ret; - /* - * Don't copy ptes where a page fault will fill them correctly. - * Fork becomes much lighter when there are big shared or private - * readonly mappings. The tradeoff is that copy_page_range is more - * efficient than faulting. - */ - if (!(src_vma->vm_flags & (VM_HUGETLB | VM_PFNMAP | VM_MIXEDMAP)) && - !src_vma->anon_vma) + if (!vma_needs_copy(dst_vma, src_vma)) return 0; if (is_vm_hugetlb_page(src_vma)) - return copy_hugetlb_page_range(dst_mm, src_mm, src_vma); + return copy_hugetlb_page_range(dst_mm, src_mm, dst_vma, src_vma); if (unlikely(src_vma->vm_flags & VM_PFNMAP)) { /* @@ -1308,6 +1339,7 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) struct zap_details { struct folio *single_folio; /* Locked folio to be unmapped */ bool even_cows; /* Zap COWed private pages too? */ + zap_flags_t zap_flags; /* Extra flags for zapping */ }; /* Whether we should zap all COWed (private) pages too */ @@ -1336,6 +1368,29 @@ static inline bool should_zap_page(struct zap_details *details, struct page *pag return !PageAnon(page); } +static inline bool zap_drop_file_uffd_wp(struct zap_details *details) +{ + if (!details) + return false; + + return details->zap_flags & ZAP_FLAG_DROP_MARKER; +} + +/* + * This function makes sure that we'll replace the none pte with an uffd-wp + * swap special pte marker when necessary. Must be with the pgtable lock held. + */ +static inline void +zap_install_uffd_wp_if_needed(struct vm_area_struct *vma, + unsigned long addr, pte_t *pte, + struct zap_details *details, pte_t pteval) +{ + if (zap_drop_file_uffd_wp(details)) + return; + + pte_install_uffd_wp_if_needed(vma, addr, pte, pteval); +} + static unsigned long zap_pte_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, @@ -1373,6 +1428,8 @@ again: ptent = ptep_get_and_clear_full(mm, addr, pte, tlb->fullmm); tlb_remove_tlb_entry(tlb, pte, addr); + zap_install_uffd_wp_if_needed(vma, addr, pte, details, + ptent); if (unlikely(!page)) continue; @@ -1403,6 +1460,13 @@ again: page = pfn_swap_entry_to_page(entry); if (unlikely(!should_zap_page(details, page))) continue; + /* + * Both device private/exclusive mappings should only + * work with anonymous page so far, so we don't need to + * consider uffd-wp bit when zap. For more information, + * see zap_install_uffd_wp_if_needed(). + */ + WARN_ON_ONCE(!vma_is_anonymous(vma)); rss[mm_counter(page)]--; if (is_device_private_entry(entry)) page_remove_rmap(page, vma, false); @@ -1419,6 +1483,10 @@ again: if (!should_zap_page(details, page)) continue; rss[mm_counter(page)]--; + } else if (pte_marker_entry_uffd_wp(entry)) { + /* Only drop the uffd-wp marker if explicitly requested */ + if (!zap_drop_file_uffd_wp(details)) + continue; } else if (is_hwpoison_entry(entry)) { if (!should_zap_cows(details)) continue; @@ -1427,6 +1495,7 @@ again: WARN_ON_ONCE(1); } pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); + zap_install_uffd_wp_if_needed(vma, addr, pte, details, ptent); } while (pte++, addr += PAGE_SIZE, addr != end); add_mm_rss_vec(mm, rss); @@ -1605,8 +1674,11 @@ static void unmap_single_vma(struct mmu_gather *tlb, * safe to do nothing in this case. */ if (vma->vm_file) { + zap_flags_t zap_flags = details ? + details->zap_flags : 0; i_mmap_lock_write(vma->vm_file->f_mapping); - __unmap_hugepage_range_final(tlb, vma, start, end, NULL); + __unmap_hugepage_range_final(tlb, vma, start, end, + NULL, zap_flags); i_mmap_unlock_write(vma->vm_file->f_mapping); } } else @@ -1637,12 +1709,17 @@ void unmap_vmas(struct mmu_gather *tlb, unsigned long end_addr) { struct mmu_notifier_range range; + struct zap_details details = { + .zap_flags = ZAP_FLAG_DROP_MARKER, + /* Careful - we need to zap private pages too! */ + .even_cows = true, + }; mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, vma->vm_mm, start_addr, end_addr); mmu_notifier_invalidate_range_start(&range); for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next) - unmap_single_vma(tlb, vma, start_addr, end_addr, NULL); + unmap_single_vma(tlb, vma, start_addr, end_addr, &details); mmu_notifier_invalidate_range_end(&range); } @@ -2755,8 +2832,8 @@ static inline int pte_unmap_same(struct vm_fault *vmf) return same; } -static inline bool cow_user_page(struct page *dst, struct page *src, - struct vm_fault *vmf) +static inline bool __wp_page_copy_user(struct page *dst, struct page *src, + struct vm_fault *vmf) { bool ret; void *kaddr; @@ -2963,6 +3040,10 @@ static inline void wp_page_reuse(struct vm_fault *vmf) struct vm_area_struct *vma = vmf->vma; struct page *page = vmf->page; pte_t entry; + + VM_BUG_ON(!(vmf->flags & FAULT_FLAG_WRITE)); + VM_BUG_ON(PageAnon(page) && !PageAnonExclusive(page)); + /* * Clear the pages cpupid information as the existing * information potentially belongs to a now completely @@ -2981,7 +3062,8 @@ static inline void wp_page_reuse(struct vm_fault *vmf) } /* - * Handle the case of a page which we actually need to copy to a new page. + * Handle the case of a page which we actually need to copy to a new page, + * either due to COW or unsharing. * * Called with mmap_lock locked and the old page referenced, but * without the ptl held. @@ -2998,6 +3080,7 @@ static inline void wp_page_reuse(struct vm_fault *vmf) */ static vm_fault_t wp_page_copy(struct vm_fault *vmf) { + const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE; struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = vma->vm_mm; struct page *old_page = vmf->page; @@ -3020,7 +3103,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) if (!new_page) goto oom; - if (!cow_user_page(new_page, old_page, vmf)) { + if (!__wp_page_copy_user(new_page, old_page, vmf)) { /* * COW failed, if the fault was solved by other, * it's fine. If not, userspace would re-fault on @@ -3062,7 +3145,14 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte)); entry = mk_pte(new_page, vma->vm_page_prot); entry = pte_sw_mkyoung(entry); - entry = maybe_mkwrite(pte_mkdirty(entry), vma); + if (unlikely(unshare)) { + if (pte_soft_dirty(vmf->orig_pte)) + entry = pte_mksoft_dirty(entry); + if (pte_uffd_wp(vmf->orig_pte)) + entry = pte_mkuffd_wp(entry); + } else { + entry = maybe_mkwrite(pte_mkdirty(entry), vma); + } /* * Clear the pte entry and flush it first, before updating the @@ -3072,13 +3162,14 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) * some TLBs while the old PTE remains in others. */ ptep_clear_flush_notify(vma, vmf->address, vmf->pte); - page_add_new_anon_rmap(new_page, vma, vmf->address, false); + page_add_new_anon_rmap(new_page, vma, vmf->address); lru_cache_add_inactive_or_unevictable(new_page, vma); /* * We call the notify macro here because, when using secondary * mmu page tables (such as kvm shadow page tables), we want the * new page to be mapped directly into the secondary page table. */ + BUG_ON(unshare && pte_write(entry)); set_pte_at_notify(mm, vmf->address, vmf->pte, entry); update_mmu_cache(vma, vmf->address, vmf->pte); if (old_page) { @@ -3128,7 +3219,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) free_swap_cache(old_page); put_page(old_page); } - return page_copied ? VM_FAULT_WRITE : 0; + return (page_copied && !unshare) ? VM_FAULT_WRITE : 0; oom_free_new: put_page(new_page); oom: @@ -3228,18 +3319,22 @@ static vm_fault_t wp_page_shared(struct vm_fault *vmf) } /* - * This routine handles present pages, when users try to write - * to a shared page. It is done by copying the page to a new address - * and decrementing the shared-page counter for the old page. + * This routine handles present pages, when + * * users try to write to a shared page (FAULT_FLAG_WRITE) + * * GUP wants to take a R/O pin on a possibly shared anonymous page + * (FAULT_FLAG_UNSHARE) + * + * It is done by copying the page to a new address and decrementing the + * shared-page counter for the old page. * * Note that this routine assumes that the protection checks have been * done by the caller (the low-level page fault routine in most cases). - * Thus we can safely just mark it writable once we've done any necessary - * COW. + * Thus, with FAULT_FLAG_WRITE, we can safely just mark it writable once we've + * done any necessary COW. * - * We also mark the page dirty at this point even though the page will - * change only once the write actually happens. This avoids a few races, - * and potentially makes it more efficient. + * In case of FAULT_FLAG_WRITE, we also mark the page dirty at this point even + * though the page will change only once the write actually happens. This + * avoids a few races, and potentially makes it more efficient. * * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults), with pte both mapped and locked. @@ -3248,23 +3343,35 @@ static vm_fault_t wp_page_shared(struct vm_fault *vmf) static vm_fault_t do_wp_page(struct vm_fault *vmf) __releases(vmf->ptl) { + const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE; struct vm_area_struct *vma = vmf->vma; - if (userfaultfd_pte_wp(vma, *vmf->pte)) { - pte_unmap_unlock(vmf->pte, vmf->ptl); - return handle_userfault(vmf, VM_UFFD_WP); - } + VM_BUG_ON(unshare && (vmf->flags & FAULT_FLAG_WRITE)); + VM_BUG_ON(!unshare && !(vmf->flags & FAULT_FLAG_WRITE)); - /* - * Userfaultfd write-protect can defer flushes. Ensure the TLB - * is flushed in this case before copying. - */ - if (unlikely(userfaultfd_wp(vmf->vma) && - mm_tlb_flush_pending(vmf->vma->vm_mm))) - flush_tlb_page(vmf->vma, vmf->address); + if (likely(!unshare)) { + if (userfaultfd_pte_wp(vma, *vmf->pte)) { + pte_unmap_unlock(vmf->pte, vmf->ptl); + return handle_userfault(vmf, VM_UFFD_WP); + } + + /* + * Userfaultfd write-protect can defer flushes. Ensure the TLB + * is flushed in this case before copying. + */ + if (unlikely(userfaultfd_wp(vmf->vma) && + mm_tlb_flush_pending(vmf->vma->vm_mm))) + flush_tlb_page(vmf->vma, vmf->address); + } vmf->page = vm_normal_page(vma, vmf->address, vmf->orig_pte); if (!vmf->page) { + if (unlikely(unshare)) { + /* No anonymous page -> nothing to do. */ + pte_unmap_unlock(vmf->pte, vmf->ptl); + return 0; + } + /* * VM_MIXEDMAP !pfn_valid() case, or VM_SOFTDIRTY clear on a * VM_PFNMAP VMA. @@ -3288,6 +3395,13 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf) struct page *page = vmf->page; /* + * If the page is exclusive to this process we must reuse the + * page without further checks. + */ + if (PageAnonExclusive(page)) + goto reuse; + + /* * We have to verify under page lock: these early checks are * just an optimization to avoid locking the page and freeing * the swapcache if there is little hope that we can reuse. @@ -3317,9 +3431,19 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf) * and the page is locked, it's dark out, and we're wearing * sunglasses. Hit it. */ + page_move_anon_rmap(page, vma); unlock_page(page); +reuse: + if (unlikely(unshare)) { + pte_unmap_unlock(vmf->pte, vmf->ptl); + return 0; + } wp_page_reuse(vmf); return VM_FAULT_WRITE; + } else if (unshare) { + /* No anonymous page -> nothing to do. */ + pte_unmap_unlock(vmf->pte, vmf->ptl); + return 0; } else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED))) { return wp_page_shared(vmf); @@ -3331,6 +3455,10 @@ copy: get_page(vmf->page); pte_unmap_unlock(vmf->pte, vmf->ptl); +#ifdef CONFIG_KSM + if (PageKsm(vmf->page)) + count_vm_event(COW_KSM); +#endif return wp_page_copy(vmf); } @@ -3387,6 +3515,7 @@ void unmap_mapping_folio(struct folio *folio) details.even_cows = false; details.single_folio = folio; + details.zap_flags = ZAP_FLAG_DROP_MARKER; i_mmap_lock_read(mapping); if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) @@ -3508,6 +3637,59 @@ static inline bool should_try_to_free_swap(struct page *page, page_count(page) == 2; } +static vm_fault_t pte_marker_clear(struct vm_fault *vmf) +{ + vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, + vmf->address, &vmf->ptl); + /* + * Be careful so that we will only recover a special uffd-wp pte into a + * none pte. Otherwise it means the pte could have changed, so retry. + */ + if (is_pte_marker(*vmf->pte)) + pte_clear(vmf->vma->vm_mm, vmf->address, vmf->pte); + pte_unmap_unlock(vmf->pte, vmf->ptl); + return 0; +} + +/* + * This is actually a page-missing access, but with uffd-wp special pte + * installed. It means this pte was wr-protected before being unmapped. + */ +static vm_fault_t pte_marker_handle_uffd_wp(struct vm_fault *vmf) +{ + /* + * Just in case there're leftover special ptes even after the region + * got unregistered - we can simply clear them. We can also do that + * proactively when e.g. when we do UFFDIO_UNREGISTER upon some uffd-wp + * ranges, but it should be more efficient to be done lazily here. + */ + if (unlikely(!userfaultfd_wp(vmf->vma) || vma_is_anonymous(vmf->vma))) + return pte_marker_clear(vmf); + + /* do_fault() can handle pte markers too like none pte */ + return do_fault(vmf); +} + +static vm_fault_t handle_pte_marker(struct vm_fault *vmf) +{ + swp_entry_t entry = pte_to_swp_entry(vmf->orig_pte); + unsigned long marker = pte_marker_get(entry); + + /* + * PTE markers should always be with file-backed memories, and the + * marker should never be empty. If anything weird happened, the best + * thing to do is to kill the process along with its mm. + */ + if (WARN_ON_ONCE(vma_is_anonymous(vmf->vma) || !marker)) + return VM_FAULT_SIGBUS; + + if (pte_marker_entry_uffd_wp(entry)) + return pte_marker_handle_uffd_wp(vmf); + + /* This is an unknown pte marker */ + return VM_FAULT_SIGBUS; +} + /* * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults), and pte mapped but not yet locked. @@ -3521,10 +3703,11 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) struct vm_area_struct *vma = vmf->vma; struct page *page = NULL, *swapcache; struct swap_info_struct *si = NULL; + rmap_t rmap_flags = RMAP_NONE; + bool exclusive = false; swp_entry_t entry; pte_t pte; int locked; - int exclusive = 0; vm_fault_t ret = 0; void *shadow = NULL; @@ -3544,6 +3727,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) ret = vmf->page->pgmap->ops->migrate_to_ram(vmf); } else if (is_hwpoison_entry(entry)) { ret = VM_FAULT_HWPOISON; + } else if (is_pte_marker_entry(entry)) { + ret = handle_pte_marker(vmf); } else { print_bad_pte(vma, vmf->address, vmf->orig_pte, NULL); ret = VM_FAULT_SIGBUS; @@ -3585,7 +3770,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) /* To provide entry to swap_readpage() */ set_page_private(page, entry.val); - swap_readpage(page, true); + swap_readpage(page, true, NULL); set_page_private(page, 0); } } else { @@ -3677,6 +3862,57 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) } /* + * PG_anon_exclusive reuses PG_mappedtodisk for anon pages. A swap pte + * must never point at an anonymous page in the swapcache that is + * PG_anon_exclusive. Sanity check that this holds and especially, that + * no filesystem set PG_mappedtodisk on a page in the swapcache. Sanity + * check after taking the PT lock and making sure that nobody + * concurrently faulted in this page and set PG_anon_exclusive. + */ + BUG_ON(!PageAnon(page) && PageMappedToDisk(page)); + BUG_ON(PageAnon(page) && PageAnonExclusive(page)); + + /* + * Check under PT lock (to protect against concurrent fork() sharing + * the swap entry concurrently) for certainly exclusive pages. + */ + if (!PageKsm(page)) { + /* + * Note that pte_swp_exclusive() == false for architectures + * without __HAVE_ARCH_PTE_SWP_EXCLUSIVE. + */ + exclusive = pte_swp_exclusive(vmf->orig_pte); + if (page != swapcache) { + /* + * We have a fresh page that is not exposed to the + * swapcache -> certainly exclusive. + */ + exclusive = true; + } else if (exclusive && PageWriteback(page) && + data_race(si->flags & SWP_STABLE_WRITES)) { + /* + * This is tricky: not all swap backends support + * concurrent page modifications while under writeback. + * + * So if we stumble over such a page in the swapcache + * we must not set the page exclusive, otherwise we can + * map it writable without further checks and modify it + * while still under writeback. + * + * For these problematic swap backends, simply drop the + * exclusive marker: this is perfectly fine as we start + * writeback only if we fully unmapped the page and + * there are no unexpected references on the page after + * unmapping succeeded. After fully unmapped, no + * further GUP references (FOLL_GET and FOLL_PIN) can + * appear, so dropping the exclusive marker and mapping + * it only R/O is fine. + */ + exclusive = false; + } + } + + /* * Remove the swap entry and conditionally try to free up the swapcache. * We're already holding a reference on the page but haven't mapped it * yet. @@ -3690,16 +3926,18 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) pte = mk_pte(page, vma->vm_page_prot); /* - * Same logic as in do_wp_page(); however, optimize for fresh pages - * that are certainly not shared because we just allocated them without - * exposing them to the swapcache. + * Same logic as in do_wp_page(); however, optimize for pages that are + * certainly not shared either because we just allocated them without + * exposing them to the swapcache or because the swap entry indicates + * exclusivity. */ - if ((vmf->flags & FAULT_FLAG_WRITE) && !PageKsm(page) && - (page != swapcache || page_count(page) == 1)) { - pte = maybe_mkwrite(pte_mkdirty(pte), vma); - vmf->flags &= ~FAULT_FLAG_WRITE; - ret |= VM_FAULT_WRITE; - exclusive = RMAP_EXCLUSIVE; + if (!PageKsm(page) && (exclusive || page_count(page) == 1)) { + if (vmf->flags & FAULT_FLAG_WRITE) { + pte = maybe_mkwrite(pte_mkdirty(pte), vma); + vmf->flags &= ~FAULT_FLAG_WRITE; + ret |= VM_FAULT_WRITE; + } + rmap_flags |= RMAP_EXCLUSIVE; } flush_icache_page(vma, page); if (pte_swp_soft_dirty(vmf->orig_pte)) @@ -3712,12 +3950,13 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) /* ksm created a completely new copy */ if (unlikely(page != swapcache && swapcache)) { - page_add_new_anon_rmap(page, vma, vmf->address, false); + page_add_new_anon_rmap(page, vma, vmf->address); lru_cache_add_inactive_or_unevictable(page, vma); } else { - do_page_add_anon_rmap(page, vma, vmf->address, exclusive); + page_add_anon_rmap(page, vma, vmf->address, rmap_flags); } + VM_BUG_ON(!PageAnon(page) || (pte_write(pte) && !PageAnonExclusive(page))); set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte); arch_do_swap_page(vma->vm_mm, vma, vmf->address, pte, vmf->orig_pte); @@ -3862,7 +4101,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) } inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); - page_add_new_anon_rmap(page, vma, vmf->address, false); + page_add_new_anon_rmap(page, vma, vmf->address); lru_cache_add_inactive_or_unevictable(page, vma); setpte: set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry); @@ -4032,6 +4271,7 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr) { struct vm_area_struct *vma = vmf->vma; + bool uffd_wp = pte_marker_uffd_wp(vmf->orig_pte); bool write = vmf->flags & FAULT_FLAG_WRITE; bool prefault = vmf->address != addr; pte_t entry; @@ -4046,10 +4286,12 @@ void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr) if (write) entry = maybe_mkwrite(pte_mkdirty(entry), vma); + if (unlikely(uffd_wp)) + entry = pte_mkuffd_wp(pte_wrprotect(entry)); /* copy-on-write page */ if (write && !(vma->vm_flags & VM_SHARED)) { inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); - page_add_new_anon_rmap(page, vma, addr, false); + page_add_new_anon_rmap(page, vma, addr); lru_cache_add_inactive_or_unevictable(page, vma); } else { inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page)); @@ -4058,6 +4300,14 @@ void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr) set_pte_at(vma->vm_mm, addr, vmf->pte, entry); } +static bool vmf_pte_changed(struct vm_fault *vmf) +{ + if (vmf->flags & FAULT_FLAG_ORIG_PTE_VALID) + return !pte_same(*vmf->pte, vmf->orig_pte); + + return !pte_none(*vmf->pte); +} + /** * finish_fault - finish page fault once we have prepared the page to fault * @@ -4116,7 +4366,7 @@ vm_fault_t finish_fault(struct vm_fault *vmf) vmf->address, &vmf->ptl); ret = 0; /* Re-check under ptl */ - if (likely(pte_none(*vmf->pte))) + if (likely(!vmf_pte_changed(vmf))) do_set_pte(vmf, page, vmf->address); else ret = VM_FAULT_NOPAGE; @@ -4219,9 +4469,21 @@ static vm_fault_t do_fault_around(struct vm_fault *vmf) return vmf->vma->vm_ops->map_pages(vmf, start_pgoff, end_pgoff); } +/* Return true if we should do read fault-around, false otherwise */ +static inline bool should_fault_around(struct vm_fault *vmf) +{ + /* No ->map_pages? No way to fault around... */ + if (!vmf->vma->vm_ops->map_pages) + return false; + + if (uffd_disable_fault_around(vmf->vma)) + return false; + + return fault_around_bytes >> PAGE_SHIFT > 1; +} + static vm_fault_t do_read_fault(struct vm_fault *vmf) { - struct vm_area_struct *vma = vmf->vma; vm_fault_t ret = 0; /* @@ -4229,12 +4491,10 @@ static vm_fault_t do_read_fault(struct vm_fault *vmf) * if page by the offset is not ready to be mapped (cold cache or * something). */ - if (vma->vm_ops->map_pages && fault_around_bytes >> PAGE_SHIFT > 1) { - if (likely(!userfaultfd_minor(vmf->vma))) { - ret = do_fault_around(vmf); - if (ret) - return ret; - } + if (should_fault_around(vmf)) { + ret = do_fault_around(vmf); + if (ret) + return ret; } ret = __do_fault(vmf); @@ -4504,8 +4764,11 @@ static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf) /* `inline' is required to avoid gcc 4.1.2 build error */ static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf) { + const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE; + if (vma_is_anonymous(vmf->vma)) { - if (userfaultfd_huge_pmd_wp(vmf->vma, vmf->orig_pmd)) + if (likely(!unshare) && + userfaultfd_huge_pmd_wp(vmf->vma, vmf->orig_pmd)) return handle_userfault(vmf, VM_UFFD_WP); return do_huge_pmd_wp_page(vmf); } @@ -4581,6 +4844,7 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf) * concurrent faults and from rmap lookups. */ vmf->pte = NULL; + vmf->flags &= ~FAULT_FLAG_ORIG_PTE_VALID; } else { /* * If a huge pmd materialized under us just retry later. Use @@ -4604,6 +4868,7 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf) */ vmf->pte = pte_offset_map(vmf->pmd, vmf->address); vmf->orig_pte = *vmf->pte; + vmf->flags |= FAULT_FLAG_ORIG_PTE_VALID; /* * some architectures can have larger ptes than wordsize, @@ -4640,10 +4905,11 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf) update_mmu_tlb(vmf->vma, vmf->address, vmf->pte); goto unlock; } - if (vmf->flags & FAULT_FLAG_WRITE) { + if (vmf->flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) { if (!pte_write(entry)) return do_wp_page(vmf); - entry = pte_mkdirty(entry); + else if (likely(vmf->flags & FAULT_FLAG_WRITE)) + entry = pte_mkdirty(entry); } entry = pte_mkyoung(entry); if (ptep_set_access_flags(vmf->vma, vmf->address, vmf->pte, entry, @@ -4684,7 +4950,6 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma, .pgoff = linear_page_index(vma, address), .gfp_mask = __get_fault_gfp_mask(vma), }; - unsigned int dirty = flags & FAULT_FLAG_WRITE; struct mm_struct *mm = vma->vm_mm; pgd_t *pgd; p4d_t *p4d; @@ -4709,9 +4974,11 @@ retry_pud: barrier(); if (pud_trans_huge(orig_pud) || pud_devmap(orig_pud)) { - /* NUMA case for anonymous PUDs would go here */ - - if (dirty && !pud_write(orig_pud)) { + /* + * TODO once we support anonymous PUDs: NUMA case and + * FAULT_FLAG_UNSHARE handling. + */ + if ((flags & FAULT_FLAG_WRITE) && !pud_write(orig_pud)) { ret = wp_huge_pud(&vmf, orig_pud); if (!(ret & VM_FAULT_FALLBACK)) return ret; @@ -4749,7 +5016,8 @@ retry_pud: if (pmd_protnone(vmf.orig_pmd) && vma_is_accessible(vma)) return do_huge_pmd_numa_page(&vmf); - if (dirty && !pmd_write(vmf.orig_pmd)) { + if ((flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) && + !pmd_write(vmf.orig_pmd)) { ret = wp_huge_pmd(&vmf); if (!(ret & VM_FAULT_FALLBACK)) return ret; @@ -4949,9 +5217,29 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) } #endif /* __PAGETABLE_PMD_FOLDED */ -int follow_invalidate_pte(struct mm_struct *mm, unsigned long address, - struct mmu_notifier_range *range, pte_t **ptepp, - pmd_t **pmdpp, spinlock_t **ptlp) +/** + * follow_pte - look up PTE at a user virtual address + * @mm: the mm_struct of the target address space + * @address: user virtual address + * @ptepp: location to store found PTE + * @ptlp: location to store the lock for the PTE + * + * On a successful return, the pointer to the PTE is stored in @ptepp; + * the corresponding lock is taken and its location is stored in @ptlp. + * The contents of the PTE are only stable until @ptlp is released; + * any further use, if any, must be protected against invalidation + * with MMU notifiers. + * + * Only IO mappings and raw PFN mappings are allowed. The mmap semaphore + * should be taken for read. + * + * KVM uses this function. While it is arguably less bad than ``follow_pfn``, + * it is not a good general-purpose API. + * + * Return: zero on success, -ve otherwise. + */ +int follow_pte(struct mm_struct *mm, unsigned long address, + pte_t **ptepp, spinlock_t **ptlp) { pgd_t *pgd; p4d_t *p4d; @@ -4974,35 +5262,9 @@ int follow_invalidate_pte(struct mm_struct *mm, unsigned long address, pmd = pmd_offset(pud, address); VM_BUG_ON(pmd_trans_huge(*pmd)); - if (pmd_huge(*pmd)) { - if (!pmdpp) - goto out; - - if (range) { - mmu_notifier_range_init(range, MMU_NOTIFY_CLEAR, 0, - NULL, mm, address & PMD_MASK, - (address & PMD_MASK) + PMD_SIZE); - mmu_notifier_invalidate_range_start(range); - } - *ptlp = pmd_lock(mm, pmd); - if (pmd_huge(*pmd)) { - *pmdpp = pmd; - return 0; - } - spin_unlock(*ptlp); - if (range) - mmu_notifier_invalidate_range_end(range); - } - if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd))) goto out; - if (range) { - mmu_notifier_range_init(range, MMU_NOTIFY_CLEAR, 0, NULL, mm, - address & PAGE_MASK, - (address & PAGE_MASK) + PAGE_SIZE); - mmu_notifier_invalidate_range_start(range); - } ptep = pte_offset_map_lock(mm, pmd, address, ptlp); if (!pte_present(*ptep)) goto unlock; @@ -5010,38 +5272,9 @@ int follow_invalidate_pte(struct mm_struct *mm, unsigned long address, return 0; unlock: pte_unmap_unlock(ptep, *ptlp); - if (range) - mmu_notifier_invalidate_range_end(range); out: return -EINVAL; } - -/** - * follow_pte - look up PTE at a user virtual address - * @mm: the mm_struct of the target address space - * @address: user virtual address - * @ptepp: location to store found PTE - * @ptlp: location to store the lock for the PTE - * - * On a successful return, the pointer to the PTE is stored in @ptepp; - * the corresponding lock is taken and its location is stored in @ptlp. - * The contents of the PTE are only stable until @ptlp is released; - * any further use, if any, must be protected against invalidation - * with MMU notifiers. - * - * Only IO mappings and raw PFN mappings are allowed. The mmap semaphore - * should be taken for read. - * - * KVM uses this function. While it is arguably less bad than ``follow_pfn``, - * it is not a good general-purpose API. - * - * Return: zero on success, -ve otherwise. - */ -int follow_pte(struct mm_struct *mm, unsigned long address, - pte_t **ptepp, spinlock_t **ptlp) -{ - return follow_invalidate_pte(mm, address, NULL, ptepp, NULL, ptlp); -} EXPORT_SYMBOL_GPL(follow_pte); /** |