diff options
Diffstat (limited to 'mm/hugetlb.c')
| -rw-r--r-- | mm/hugetlb.c | 428 |
1 files changed, 313 insertions, 115 deletions
diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 3fc721789743..01f0e2e5ab48 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -370,7 +370,7 @@ static void coalesce_file_region(struct resv_map *resv, struct file_region *rg) } static inline long -hugetlb_resv_map_add(struct resv_map *map, struct file_region *rg, long from, +hugetlb_resv_map_add(struct resv_map *map, struct list_head *rg, long from, long to, struct hstate *h, struct hugetlb_cgroup *cg, long *regions_needed) { @@ -379,7 +379,7 @@ hugetlb_resv_map_add(struct resv_map *map, struct file_region *rg, long from, if (!regions_needed) { nrg = get_file_region_entry_from_cache(map, from, to); record_hugetlb_cgroup_uncharge_info(cg, h, map, nrg); - list_add(&nrg->link, rg->link.prev); + list_add(&nrg->link, rg); coalesce_file_region(map, nrg); } else *regions_needed += 1; @@ -402,47 +402,52 @@ static long add_reservation_in_range(struct resv_map *resv, long f, long t, long add = 0; struct list_head *head = &resv->regions; long last_accounted_offset = f; - struct file_region *rg = NULL, *trg = NULL; + struct file_region *iter, *trg = NULL; + struct list_head *rg = NULL; if (regions_needed) *regions_needed = 0; /* In this loop, we essentially handle an entry for the range - * [last_accounted_offset, rg->from), at every iteration, with some + * [last_accounted_offset, iter->from), at every iteration, with some * bounds checking. */ - list_for_each_entry_safe(rg, trg, head, link) { + list_for_each_entry_safe(iter, trg, head, link) { /* Skip irrelevant regions that start before our range. */ - if (rg->from < f) { + if (iter->from < f) { /* If this region ends after the last accounted offset, * then we need to update last_accounted_offset. */ - if (rg->to > last_accounted_offset) - last_accounted_offset = rg->to; + if (iter->to > last_accounted_offset) + last_accounted_offset = iter->to; continue; } /* When we find a region that starts beyond our range, we've * finished. */ - if (rg->from >= t) + if (iter->from >= t) { + rg = iter->link.prev; break; + } - /* Add an entry for last_accounted_offset -> rg->from, and + /* Add an entry for last_accounted_offset -> iter->from, and * update last_accounted_offset. */ - if (rg->from > last_accounted_offset) - add += hugetlb_resv_map_add(resv, rg, + if (iter->from > last_accounted_offset) + add += hugetlb_resv_map_add(resv, iter->link.prev, last_accounted_offset, - rg->from, h, h_cg, + iter->from, h, h_cg, regions_needed); - last_accounted_offset = rg->to; + last_accounted_offset = iter->to; } /* Handle the case where our range extends beyond * last_accounted_offset. */ + if (!rg) + rg = head->prev; if (last_accounted_offset < t) add += hugetlb_resv_map_add(resv, rg, last_accounted_offset, t, h, h_cg, regions_needed); @@ -1535,7 +1540,7 @@ static void __update_and_free_page(struct hstate *h, struct page *page) if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) return; - if (alloc_huge_page_vmemmap(h, page)) { + if (hugetlb_vmemmap_alloc(h, page)) { spin_lock_irq(&hugetlb_lock); /* * If we cannot allocate vmemmap pages, just refuse to free the @@ -1612,7 +1617,7 @@ static DECLARE_WORK(free_hpage_work, free_hpage_workfn); static inline void flush_free_hpage_work(struct hstate *h) { - if (free_vmemmap_pages_per_hpage(h)) + if (hugetlb_optimize_vmemmap_pages(h)) flush_work(&free_hpage_work); } @@ -1672,6 +1677,8 @@ void free_huge_page(struct page *page) VM_BUG_ON_PAGE(page_mapcount(page), page); hugetlb_set_page_subpool(page, NULL); + if (PageAnon(page)) + __ClearPageAnonExclusive(page); page->mapping = NULL; restore_reserve = HPageRestoreReserve(page); ClearHPageRestoreReserve(page); @@ -1732,7 +1739,7 @@ static void __prep_account_new_huge_page(struct hstate *h, int nid) static void __prep_new_huge_page(struct hstate *h, struct page *page) { - free_huge_page_vmemmap(h, page); + hugetlb_vmemmap_free(h, page); INIT_LIST_HEAD(&page->lru); set_compound_page_dtor(page, HUGETLB_PAGE_DTOR); hugetlb_set_page_subpool(page, NULL); @@ -2105,7 +2112,7 @@ retry: * Attempt to allocate vmemmmap here so that we can take * appropriate action on failure. */ - rc = alloc_huge_page_vmemmap(h, head); + rc = hugetlb_vmemmap_alloc(h, head); if (!rc) { /* * Move PageHWPoison flag from head page to the raw @@ -2979,8 +2986,6 @@ int __alloc_bootmem_huge_page(struct hstate *h, int nid) struct huge_bootmem_page *m = NULL; /* initialize for clang */ int nr_nodes, node; - if (nid != NUMA_NO_NODE && nid >= nr_online_nodes) - return 0; /* do node specific alloc */ if (nid != NUMA_NO_NODE) { m = memblock_alloc_try_nid_raw(huge_page_size(h), huge_page_size(h), @@ -3088,7 +3093,7 @@ static void __init hugetlb_hstate_alloc_pages(struct hstate *h) } /* do node specific alloc */ - for (i = 0; i < nr_online_nodes; i++) { + for_each_online_node(i) { if (h->max_huge_pages_node[i] > 0) { hugetlb_hstate_alloc_pages_onenode(h, i); node_specific_alloc = true; @@ -3420,7 +3425,7 @@ static int demote_free_huge_page(struct hstate *h, struct page *page) remove_hugetlb_page_for_demote(h, page, false); spin_unlock_irq(&hugetlb_lock); - rc = alloc_huge_page_vmemmap(h, page); + rc = hugetlb_vmemmap_alloc(h, page); if (rc) { /* Allocation of vmemmmap failed, we can not demote page */ spin_lock_irq(&hugetlb_lock); @@ -4052,7 +4057,7 @@ static int __init hugetlb_init(void) default_hstate.max_huge_pages = default_hstate_max_huge_pages; - for (i = 0; i < nr_online_nodes; i++) + for_each_online_node(i) default_hstate.max_huge_pages_node[i] = default_hugepages_in_node[i]; } @@ -4119,6 +4124,20 @@ bool __init __weak hugetlb_node_alloc_supported(void) { return true; } + +static void __init hugepages_clear_pages_in_node(void) +{ + if (!hugetlb_max_hstate) { + default_hstate_max_huge_pages = 0; + memset(default_hugepages_in_node, 0, + MAX_NUMNODES * sizeof(unsigned int)); + } else { + parsed_hstate->max_huge_pages = 0; + memset(parsed_hstate->max_huge_pages_node, 0, + MAX_NUMNODES * sizeof(unsigned int)); + } +} + /* * hugepages command line processing * hugepages normally follows a valid hugepagsz or default_hugepagsz @@ -4138,7 +4157,7 @@ static int __init hugepages_setup(char *s) if (!parsed_valid_hugepagesz) { pr_warn("HugeTLB: hugepages=%s does not follow a valid hugepagesz, ignoring\n", s); parsed_valid_hugepagesz = true; - return 0; + return 1; } /* @@ -4154,7 +4173,7 @@ static int __init hugepages_setup(char *s) if (mhp == last_mhp) { pr_warn("HugeTLB: hugepages= specified twice without interleaving hugepagesz=, ignoring hugepages=%s\n", s); - return 0; + return 1; } while (*p) { @@ -4165,11 +4184,11 @@ static int __init hugepages_setup(char *s) if (p[count] == ':') { if (!hugetlb_node_alloc_supported()) { pr_warn("HugeTLB: architecture can't support node specific alloc, ignoring!\n"); - return 0; + return 1; } - if (tmp >= nr_online_nodes) + if (tmp >= MAX_NUMNODES || !node_online(tmp)) goto invalid; - node = array_index_nospec(tmp, nr_online_nodes); + node = array_index_nospec(tmp, MAX_NUMNODES); p += count + 1; /* Parse hugepages */ if (sscanf(p, "%lu%n", &tmp, &count) != 1) @@ -4206,7 +4225,8 @@ static int __init hugepages_setup(char *s) invalid: pr_warn("HugeTLB: Invalid hugepages parameter %s\n", p); - return 0; + hugepages_clear_pages_in_node(); + return 1; } __setup("hugepages=", hugepages_setup); @@ -4227,7 +4247,7 @@ static int __init hugepagesz_setup(char *s) if (!arch_hugetlb_valid_size(size)) { pr_err("HugeTLB: unsupported hugepagesz=%s\n", s); - return 0; + return 1; } h = size_to_hstate(size); @@ -4242,7 +4262,7 @@ static int __init hugepagesz_setup(char *s) if (!parsed_default_hugepagesz || h != &default_hstate || default_hstate.max_huge_pages) { pr_warn("HugeTLB: hugepagesz=%s specified twice, ignoring\n", s); - return 0; + return 1; } /* @@ -4273,14 +4293,14 @@ static int __init default_hugepagesz_setup(char *s) parsed_valid_hugepagesz = false; if (parsed_default_hugepagesz) { pr_err("HugeTLB: default_hugepagesz previously specified, ignoring %s\n", s); - return 0; + return 1; } size = (unsigned long)memparse(s, NULL); if (!arch_hugetlb_valid_size(size)) { pr_err("HugeTLB: unsupported default_hugepagesz=%s\n", s); - return 0; + return 1; } hugetlb_add_hstate(ilog2(size) - PAGE_SHIFT); @@ -4297,7 +4317,7 @@ static int __init default_hugepagesz_setup(char *s) */ if (default_hstate_max_huge_pages) { default_hstate.max_huge_pages = default_hstate_max_huge_pages; - for (i = 0; i < nr_online_nodes; i++) + for_each_online_node(i) default_hstate.max_huge_pages_node[i] = default_hugepages_in_node[i]; if (hstate_is_gigantic(&default_hstate)) @@ -4699,24 +4719,27 @@ hugetlb_install_page(struct vm_area_struct *vma, pte_t *ptep, unsigned long addr } int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, - struct vm_area_struct *vma) + struct vm_area_struct *dst_vma, + struct vm_area_struct *src_vma) { pte_t *src_pte, *dst_pte, entry, dst_entry; struct page *ptepage; unsigned long addr; - bool cow = is_cow_mapping(vma->vm_flags); - struct hstate *h = hstate_vma(vma); + bool cow = is_cow_mapping(src_vma->vm_flags); + struct hstate *h = hstate_vma(src_vma); unsigned long sz = huge_page_size(h); unsigned long npages = pages_per_huge_page(h); - struct address_space *mapping = vma->vm_file->f_mapping; + struct address_space *mapping = src_vma->vm_file->f_mapping; struct mmu_notifier_range range; int ret = 0; if (cow) { - mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, src, - vma->vm_start, - vma->vm_end); + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, src_vma, src, + src_vma->vm_start, + src_vma->vm_end); mmu_notifier_invalidate_range_start(&range); + mmap_assert_write_locked(src); + raw_write_seqcount_begin(&src->write_protect_seq); } else { /* * For shared mappings i_mmap_rwsem must be held to call @@ -4727,12 +4750,12 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, i_mmap_lock_read(mapping); } - for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) { + for (addr = src_vma->vm_start; addr < src_vma->vm_end; addr += sz) { spinlock_t *src_ptl, *dst_ptl; src_pte = huge_pte_offset(src, addr, sz); if (!src_pte) continue; - dst_pte = huge_pte_alloc(dst, vma, addr, sz); + dst_pte = huge_pte_alloc(dst, dst_vma, addr, sz); if (!dst_pte) { ret = -ENOMEM; break; @@ -4767,8 +4790,9 @@ again: } else if (unlikely(is_hugetlb_entry_migration(entry) || is_hugetlb_entry_hwpoisoned(entry))) { swp_entry_t swp_entry = pte_to_swp_entry(entry); + bool uffd_wp = huge_pte_uffd_wp(entry); - if (is_writable_migration_entry(swp_entry) && cow) { + if (!is_readable_migration_entry(swp_entry) && cow) { /* * COW mappings require pages in both * parent and child to be set to read. @@ -4776,38 +4800,53 @@ again: swp_entry = make_readable_migration_entry( swp_offset(swp_entry)); entry = swp_entry_to_pte(swp_entry); + if (userfaultfd_wp(src_vma) && uffd_wp) + entry = huge_pte_mkuffd_wp(entry); set_huge_swap_pte_at(src, addr, src_pte, entry, sz); } + if (!userfaultfd_wp(dst_vma) && uffd_wp) + entry = huge_pte_clear_uffd_wp(entry); set_huge_swap_pte_at(dst, addr, dst_pte, entry, sz); + } else if (unlikely(is_pte_marker(entry))) { + /* + * We copy the pte marker only if the dst vma has + * uffd-wp enabled. + */ + if (userfaultfd_wp(dst_vma)) + set_huge_pte_at(dst, addr, dst_pte, entry); } else { entry = huge_ptep_get(src_pte); ptepage = pte_page(entry); get_page(ptepage); /* - * This is a rare case where we see pinned hugetlb - * pages while they're prone to COW. We need to do the - * COW earlier during fork. + * Failing to duplicate the anon rmap is a rare case + * where we see pinned hugetlb pages while they're + * prone to COW. We need to do the COW earlier during + * fork. * * When pre-allocating the page or copying data, we * need to be without the pgtable locks since we could * sleep during the process. */ - if (unlikely(page_needs_cow_for_dma(vma, ptepage))) { + if (!PageAnon(ptepage)) { + page_dup_file_rmap(ptepage, true); + } else if (page_try_dup_anon_rmap(ptepage, true, + src_vma)) { pte_t src_pte_old = entry; struct page *new; spin_unlock(src_ptl); spin_unlock(dst_ptl); /* Do not use reserve as it's private owned */ - new = alloc_huge_page(vma, addr, 1); + new = alloc_huge_page(dst_vma, addr, 1); if (IS_ERR(new)) { put_page(ptepage); ret = PTR_ERR(new); break; } - copy_user_huge_page(new, ptepage, addr, vma, + copy_user_huge_page(new, ptepage, addr, dst_vma, npages); put_page(ptepage); @@ -4817,13 +4856,13 @@ again: spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); entry = huge_ptep_get(src_pte); if (!pte_same(src_pte_old, entry)) { - restore_reserve_on_error(h, vma, addr, + restore_reserve_on_error(h, dst_vma, addr, new); put_page(new); /* dst_entry won't change as in child */ goto again; } - hugetlb_install_page(vma, dst_pte, addr, new); + hugetlb_install_page(dst_vma, dst_pte, addr, new); spin_unlock(src_ptl); spin_unlock(dst_ptl); continue; @@ -4841,7 +4880,6 @@ again: entry = huge_pte_wrprotect(entry); } - page_dup_rmap(ptepage, true); set_huge_pte_at(dst, addr, dst_pte, entry); hugetlb_count_add(npages, dst); } @@ -4849,10 +4887,12 @@ again: spin_unlock(dst_ptl); } - if (cow) + if (cow) { + raw_write_seqcount_end(&src->write_protect_seq); mmu_notifier_invalidate_range_end(&range); - else + } else { i_mmap_unlock_read(mapping); + } return ret; } @@ -4896,10 +4936,17 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, unsigned long old_addr_copy; pte_t *src_pte, *dst_pte; struct mmu_notifier_range range; + bool shared_pmd = false; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, old_addr, old_end); adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); + /* + * In case of shared PMDs, we should cover the maximum possible + * range. + */ + flush_cache_range(vma, range.start, range.end); + mmu_notifier_invalidate_range_start(&range); /* Prevent race with file truncation */ i_mmap_lock_write(mapping); @@ -4916,8 +4963,10 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, */ old_addr_copy = old_addr; - if (huge_pmd_unshare(mm, vma, &old_addr_copy, src_pte)) + if (huge_pmd_unshare(mm, vma, &old_addr_copy, src_pte)) { + shared_pmd = true; continue; + } dst_pte = huge_pte_alloc(mm, new_vma, new_addr, sz); if (!dst_pte) @@ -4925,7 +4974,11 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, move_huge_pte(vma, old_addr, new_addr, src_pte, dst_pte); } - flush_tlb_range(vma, old_end - len, old_end); + + if (shared_pmd) + flush_tlb_range(vma, range.start, range.end); + else + flush_tlb_range(vma, old_end - len, old_end); mmu_notifier_invalidate_range_end(&range); i_mmap_unlock_write(mapping); @@ -4934,7 +4987,7 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, - struct page *ref_page) + struct page *ref_page, zap_flags_t zap_flags) { struct mm_struct *mm = vma->vm_mm; unsigned long address; @@ -4990,7 +5043,18 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct * unmapped and its refcount is dropped, so just clear pte here. */ if (unlikely(!pte_present(pte))) { - huge_pte_clear(mm, address, ptep, sz); + /* + * If the pte was wr-protected by uffd-wp in any of the + * swap forms, meanwhile the caller does not want to + * drop the uffd-wp bit in this zap, then replace the + * pte with a marker. + */ + if (pte_swp_uffd_wp_any(pte) && + !(zap_flags & ZAP_FLAG_DROP_MARKER)) + set_huge_pte_at(mm, address, ptep, + make_pte_marker(PTE_MARKER_UFFD_WP)); + else + huge_pte_clear(mm, address, ptep, sz); spin_unlock(ptl); continue; } @@ -5018,7 +5082,11 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct tlb_remove_huge_tlb_entry(h, tlb, ptep, address); if (huge_pte_dirty(pte)) set_page_dirty(page); - + /* Leave a uffd-wp pte marker if needed */ + if (huge_pte_uffd_wp(pte) && + !(zap_flags & ZAP_FLAG_DROP_MARKER)) + set_huge_pte_at(mm, address, ptep, + make_pte_marker(PTE_MARKER_UFFD_WP)); hugetlb_count_sub(pages_per_huge_page(h), mm); page_remove_rmap(page, vma, true); @@ -5052,9 +5120,10 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct void __unmap_hugepage_range_final(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, - unsigned long end, struct page *ref_page) + unsigned long end, struct page *ref_page, + zap_flags_t zap_flags) { - __unmap_hugepage_range(tlb, vma, start, end, ref_page); + __unmap_hugepage_range(tlb, vma, start, end, ref_page, zap_flags); /* * Clear this flag so that x86's huge_pmd_share page_table_shareable @@ -5070,12 +5139,13 @@ void __unmap_hugepage_range_final(struct mmu_gather *tlb, } void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, - unsigned long end, struct page *ref_page) + unsigned long end, struct page *ref_page, + zap_flags_t zap_flags) { struct mmu_gather tlb; tlb_gather_mmu(&tlb, vma->vm_mm); - __unmap_hugepage_range(&tlb, vma, start, end, ref_page); + __unmap_hugepage_range(&tlb, vma, start, end, ref_page, zap_flags); tlb_finish_mmu(&tlb); } @@ -5130,21 +5200,22 @@ static void unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma, */ if (!is_vma_resv_set(iter_vma, HPAGE_RESV_OWNER)) unmap_hugepage_range(iter_vma, address, - address + huge_page_size(h), page); + address + huge_page_size(h), page, 0); } i_mmap_unlock_write(mapping); } /* - * Hugetlb_cow() should be called with page lock of the original hugepage held. + * hugetlb_wp() should be called with page lock of the original hugepage held. * Called with hugetlb_fault_mutex_table held and pte_page locked so we * cannot race with other handlers or page migration. * Keep the pte_same checks anyway to make transition from the mutex easier. */ -static vm_fault_t hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pte_t *ptep, +static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, pte_t *ptep, unsigned int flags, struct page *pagecache_page, spinlock_t *ptl) { + const bool unshare = flags & FAULT_FLAG_UNSHARE; pte_t pte; struct hstate *h = hstate_vma(vma); struct page *old_page, *new_page; @@ -5153,17 +5224,26 @@ static vm_fault_t hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long haddr = address & huge_page_mask(h); struct mmu_notifier_range range; + VM_BUG_ON(unshare && (flags & FOLL_WRITE)); + VM_BUG_ON(!unshare && !(flags & FOLL_WRITE)); + pte = huge_ptep_get(ptep); old_page = pte_page(pte); retry_avoidcopy: - /* If no-one else is actually using this page, avoid the copy - * and just make the page writable */ + /* + * If no-one else is actually using this page, we're the exclusive + * owner and can reuse this page. + */ if (page_mapcount(old_page) == 1 && PageAnon(old_page)) { - page_move_anon_rmap(old_page, vma); - set_huge_ptep_writable(vma, haddr, ptep); + if (!PageAnonExclusive(old_page)) + page_move_anon_rmap(old_page, vma); + if (likely(!unshare)) + set_huge_ptep_writable(vma, haddr, ptep); return 0; } + VM_BUG_ON_PAGE(PageAnon(old_page) && PageAnonExclusive(old_page), + old_page); /* * If the process that created a MAP_PRIVATE mapping is about to @@ -5262,13 +5342,13 @@ retry_avoidcopy: if (likely(ptep && pte_same(huge_ptep_get(ptep), pte))) { ClearHPageRestoreReserve(new_page); - /* Break COW */ + /* Break COW or unshare */ huge_ptep_clear_flush(vma, haddr, ptep); mmu_notifier_invalidate_range(mm, range.start, range.end); page_remove_rmap(old_page, vma, true); hugepage_add_new_anon_rmap(new_page, vma, haddr); set_huge_pte_at(mm, haddr, ptep, - make_huge_pte(vma, new_page, 1)); + make_huge_pte(vma, new_page, !unshare)); SetHPageMigratable(new_page); /* Make the old page be freed below */ new_page = old_page; @@ -5276,7 +5356,10 @@ retry_avoidcopy: spin_unlock(ptl); mmu_notifier_invalidate_range_end(&range); out_release_all: - /* No restore in case of successful pagetable update (Break COW) */ + /* + * No restore in case of successful pagetable update (Break COW or + * unshare) + */ if (new_page != old_page) restore_reserve_on_error(h, vma, haddr, new_page); put_page(new_page); @@ -5386,7 +5469,8 @@ static inline vm_fault_t hugetlb_handle_userfault(struct vm_area_struct *vma, static vm_fault_t hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, struct address_space *mapping, pgoff_t idx, - unsigned long address, pte_t *ptep, unsigned int flags) + unsigned long address, pte_t *ptep, + pte_t old_pte, unsigned int flags) { struct hstate *h = hstate_vma(vma); vm_fault_t ret = VM_FAULT_SIGBUS; @@ -5401,7 +5485,8 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, /* * Currently, we are forced to kill the process in the event the * original mapper has unmapped pages from the child due to a failed - * COW. Warn that such a situation has occurred as it may not be obvious + * COW/unsharing. Warn that such a situation has occurred as it may not + * be obvious. */ if (is_vma_resv_set(vma, HPAGE_RESV_UNMAPPED)) { pr_warn_ratelimited("PID %d killed due to inadequate hugepage pool\n", @@ -5512,22 +5597,29 @@ retry: ptl = huge_pte_lock(h, mm, ptep); ret = 0; - if (!huge_pte_none(huge_ptep_get(ptep))) + /* If pte changed from under us, retry */ + if (!pte_same(huge_ptep_get(ptep), old_pte)) goto backout; if (anon_rmap) { ClearHPageRestoreReserve(page); hugepage_add_new_anon_rmap(page, vma, haddr); } else - page_dup_rmap(page, true); + page_dup_file_rmap(page, true); new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE) && (vma->vm_flags & VM_SHARED))); + /* + * If this pte was previously wr-protected, keep it wr-protected even + * if populated. + */ + if (unlikely(pte_marker_uffd_wp(old_pte))) + new_pte = huge_pte_wrprotect(huge_pte_mkuffd_wp(new_pte)); set_huge_pte_at(mm, haddr, ptep, new_pte); hugetlb_count_add(pages_per_huge_page(h), mm); if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { /* Optimization, do the COW without a second fault */ - ret = hugetlb_cow(mm, vma, address, ptep, page, ptl); + ret = hugetlb_wp(mm, vma, address, ptep, flags, page, ptl); } spin_unlock(ptl); @@ -5639,8 +5731,10 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, mutex_lock(&hugetlb_fault_mutex_table[hash]); entry = huge_ptep_get(ptep); - if (huge_pte_none(entry)) { - ret = hugetlb_no_page(mm, vma, mapping, idx, address, ptep, flags); + /* PTE markers should be handled the same way as none pte */ + if (huge_pte_none_mostly(entry)) { + ret = hugetlb_no_page(mm, vma, mapping, idx, address, ptep, + entry, flags); goto out_mutex; } @@ -5657,14 +5751,15 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, goto out_mutex; /* - * If we are going to COW the mapping later, we examine the pending - * reservations for this page now. This will ensure that any + * If we are going to COW/unshare the mapping later, we examine the + * pending reservations for this page now. This will ensure that any * allocations necessary to record that reservation occur outside the * spinlock. For private mappings, we also lookup the pagecache * page now as it is used to determine if a reservation has been * consumed. */ - if ((flags & FAULT_FLAG_WRITE) && !huge_pte_write(entry)) { + if ((flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) && + !huge_pte_write(entry)) { if (vma_needs_reservation(h, vma, haddr) < 0) { ret = VM_FAULT_OOM; goto out_mutex; @@ -5679,12 +5774,32 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, ptl = huge_pte_lock(h, mm, ptep); - /* Check for a racing update before calling hugetlb_cow */ + /* Check for a racing update before calling hugetlb_wp() */ if (unlikely(!pte_same(entry, huge_ptep_get(ptep)))) goto out_ptl; + /* Handle userfault-wp first, before trying to lock more pages */ + if (userfaultfd_wp(vma) && huge_pte_uffd_wp(huge_ptep_get(ptep)) && + (flags & FAULT_FLAG_WRITE) && !huge_pte_write(entry)) { + struct vm_fault vmf = { + .vma = vma, + .address = haddr, + .real_address = address, + .flags = flags, + }; + + spin_unlock(ptl); + if (pagecache_page) { + unlock_page(pagecache_page); + put_page(pagecache_page); + } + mutex_unlock(&hugetlb_fault_mutex_table[hash]); + i_mmap_unlock_read(mapping); + return handle_userfault(&vmf, VM_UFFD_WP); + } + /* - * hugetlb_cow() requires page locks of pte_page(entry) and + * hugetlb_wp() requires page locks of pte_page(entry) and * pagecache_page, so here we need take the former one * when page != pagecache_page or !pagecache_page. */ @@ -5697,13 +5812,14 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, get_page(page); - if (flags & FAULT_FLAG_WRITE) { + if (flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) { if (!huge_pte_write(entry)) { - ret = hugetlb_cow(mm, vma, address, ptep, - pagecache_page, ptl); + ret = hugetlb_wp(mm, vma, address, ptep, flags, + pagecache_page, ptl); goto out_put_page; + } else if (likely(flags & FAULT_FLAG_WRITE)) { + entry = huge_pte_mkdirty(entry); } - entry = huge_pte_mkdirty(entry); } entry = pte_mkyoung(entry); if (huge_ptep_set_access_flags(vma, haddr, ptep, entry, @@ -5746,7 +5862,8 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, unsigned long dst_addr, unsigned long src_addr, enum mcopy_atomic_mode mode, - struct page **pagep) + struct page **pagep, + bool wp_copy) { bool is_continue = (mode == MCOPY_ATOMIC_CONTINUE); struct hstate *h = hstate_vma(dst_vma); @@ -5876,27 +5993,43 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, goto out_release_unlock; ret = -EEXIST; - if (!huge_pte_none(huge_ptep_get(dst_pte))) + /* + * We allow to overwrite a pte marker: consider when both MISSING|WP + * registered, we firstly wr-protect a none pte which has no page cache + * page backing it, then access the page. + */ + if (!huge_pte_none_mostly(huge_ptep_get(dst_pte))) goto out_release_unlock; if (vm_shared) { - page_dup_rmap(page, true); + page_dup_file_rmap(page, true); } else { ClearHPageRestoreReserve(page); hugepage_add_new_anon_rmap(page, dst_vma, dst_addr); } - /* For CONTINUE on a non-shared VMA, don't set VM_WRITE for CoW. */ - if (is_continue && !vm_shared) + /* + * For either: (1) CONTINUE on a non-shared VMA, or (2) UFFDIO_COPY + * with wp flag set, don't set pte write bit. + */ + if (wp_copy || (is_continue && !vm_shared)) writable = 0; else writable = dst_vma->vm_flags & VM_WRITE; _dst_pte = make_huge_pte(dst_vma, page, writable); - if (writable) - _dst_pte = huge_pte_mkdirty(_dst_pte); + /* + * Always mark UFFDIO_COPY page dirty; note that this may not be + * extremely important for hugetlbfs for now since swapping is not + * supported, but we should still be clear in that this page cannot be + * thrown away at will, even if write bit not set. + */ + _dst_pte = huge_pte_mkdirty(_dst_pte); _dst_pte = pte_mkyoung(_dst_pte); + if (wp_copy) + _dst_pte = huge_pte_mkuffd_wp(_dst_pte); + set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); (void)huge_ptep_set_access_flags(dst_vma, dst_addr, dst_pte, _dst_pte, @@ -5940,6 +6073,25 @@ static void record_subpages_vmas(struct page *page, struct vm_area_struct *vma, } } +static inline bool __follow_hugetlb_must_fault(unsigned int flags, pte_t *pte, + bool *unshare) +{ + pte_t pteval = huge_ptep_get(pte); + + *unshare = false; + if (is_swap_pte(pteval)) + return true; + if (huge_pte_write(pteval)) + return false; + if (flags & FOLL_WRITE) + return true; + if (gup_must_unshare(flags, pte_page(pteval))) { + *unshare = true; + return true; + } + return false; +} + long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, struct page **pages, struct vm_area_struct **vmas, unsigned long *position, unsigned long *nr_pages, @@ -5954,6 +6106,7 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, while (vaddr < vma->vm_end && remainder) { pte_t *pte; spinlock_t *ptl = NULL; + bool unshare = false; int absent; struct page *page; @@ -6004,9 +6157,8 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, * both cases, and because we can't follow correct pages * directly from any kind of swap entries. */ - if (absent || is_swap_pte(huge_ptep_get(pte)) || - ((flags & FOLL_WRITE) && - !huge_pte_write(huge_ptep_get(pte)))) { + if (absent || + __follow_hugetlb_must_fault(flags, pte, &unshare)) { vm_fault_t ret; unsigned int fault_flags = 0; @@ -6014,6 +6166,8 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, spin_unlock(ptl); if (flags & FOLL_WRITE) fault_flags |= FAULT_FLAG_WRITE; + else if (unshare) + fault_flags |= FAULT_FLAG_UNSHARE; if (locked) fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; @@ -6055,6 +6209,9 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, pfn_offset = (vaddr & ~huge_page_mask(h)) >> PAGE_SHIFT; page = pte_page(huge_ptep_get(pte)); + VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) && + !PageAnonExclusive(page), page); + /* * If subpage information not requested, update counters * and skip the same_page loop below. @@ -6117,16 +6274,19 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, } unsigned long hugetlb_change_protection(struct vm_area_struct *vma, - unsigned long address, unsigned long end, pgprot_t newprot) + unsigned long address, unsigned long end, + pgprot_t newprot, unsigned long cp_flags) { struct mm_struct *mm = vma->vm_mm; unsigned long start = address; pte_t *ptep; pte_t pte; struct hstate *h = hstate_vma(vma); - unsigned long pages = 0; + unsigned long pages = 0, psize = huge_page_size(h); bool shared_pmd = false; struct mmu_notifier_range range; + bool uffd_wp = cp_flags & MM_CP_UFFD_WP; + bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE; /* * In the case of shared PMDs, the area to flush could be beyond @@ -6142,13 +6302,19 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, mmu_notifier_invalidate_range_start(&range); i_mmap_lock_write(vma->vm_file->f_mapping); - for (; address < end; address += huge_page_size(h)) { + for (; address < end; address += psize) { spinlock_t *ptl; - ptep = huge_pte_offset(mm, address, huge_page_size(h)); + ptep = huge_pte_offset(mm, address, psize); if (!ptep) continue; ptl = huge_pte_lock(h, mm, ptep); if (huge_pmd_unshare(mm, vma, &address, ptep)) { + /* + * When uffd-wp is enabled on the vma, unshare + * shouldn't happen at all. Warn about it if it + * happened due to some reason. + */ + WARN_ON_ONCE(uffd_wp || uffd_wp_resolve); pages++; spin_unlock(ptl); shared_pmd = true; @@ -6161,20 +6327,37 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, } if (unlikely(is_hugetlb_entry_migration(pte))) { swp_entry_t entry = pte_to_swp_entry(pte); + struct page *page = pfn_swap_entry_to_page(entry); - if (is_writable_migration_entry(entry)) { + if (!is_readable_migration_entry(entry)) { pte_t newpte; - entry = make_readable_migration_entry( - swp_offset(entry)); + if (PageAnon(page)) + entry = make_readable_exclusive_migration_entry( + swp_offset(entry)); + else + entry = make_readable_migration_entry( + swp_offset(entry)); newpte = swp_entry_to_pte(entry); + if (uffd_wp) + newpte = pte_swp_mkuffd_wp(newpte); + else if (uffd_wp_resolve) + newpte = pte_swp_clear_uffd_wp(newpte); set_huge_swap_pte_at(mm, address, ptep, - newpte, huge_page_size(h)); + newpte, psize); pages++; } spin_unlock(ptl); continue; } + if (unlikely(pte_marker_uffd_wp(pte))) { + /* + * This is changing a non-present pte into a none pte, + * no need for huge_ptep_modify_prot_start/commit(). + */ + if (uffd_wp_resolve) + huge_pte_clear(mm, address, ptep, psize); + } if (!huge_pte_none(pte)) { pte_t old_pte; unsigned int shift = huge_page_shift(hstate_vma(vma)); @@ -6182,8 +6365,18 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, old_pte = huge_ptep_modify_prot_start(vma, address, ptep); pte = huge_pte_modify(old_pte, newprot); pte = arch_make_huge_pte(pte, shift, vma->vm_flags); + if (uffd_wp) + pte = huge_pte_mkuffd_wp(huge_pte_wrprotect(pte)); + else if (uffd_wp_resolve) + pte = huge_pte_clear_uffd_wp(pte); huge_ptep_modify_prot_commit(vma, address, ptep, old_pte, pte); pages++; + } else { + /* None pte */ + if (unlikely(uffd_wp)) + /* Safe to modify directly (none->non-present). */ + set_huge_pte_at(mm, address, ptep, + make_pte_marker(PTE_MARKER_UFFD_WP)); } spin_unlock(ptl); } @@ -6686,9 +6879,11 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address, spinlock_t *ptl; pte_t pte; - /* FOLL_GET and FOLL_PIN are mutually exclusive. */ - if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) == - (FOLL_PIN | FOLL_GET))) + /* + * FOLL_PIN is not supported for follow_page(). Ordinary GUP goes via + * follow_hugetlb_page(). + */ + if (WARN_ON_ONCE(flags & FOLL_PIN)) return NULL; retry: @@ -6776,7 +6971,9 @@ int get_hwpoison_huge_page(struct page *page, bool *hugetlb) spin_lock_irq(&hugetlb_lock); if (PageHeadHuge(page)) { *hugetlb = true; - if (HPageFreed(page) || HPageMigratable(page)) + if (HPageFreed(page)) + ret = 0; + else if (HPageMigratable(page)) ret = get_page_unless_zero(page); else ret = -EBUSY; @@ -6866,6 +7063,7 @@ void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) if (start >= end) return; + flush_cache_range(vma, start, end); /* * No need to call adjust_range_if_pmd_sharing_possible(), because * we have already done the PUD_SIZE alignment. @@ -6951,7 +7149,7 @@ void __init hugetlb_cma_reserve(int order) if (hugetlb_cma_size_in_node[nid] == 0) continue; - if (!node_state(nid, N_ONLINE)) { + if (!node_online(nid)) { pr_warn("hugetlb_cma: invalid node %d specified\n", nid); hugetlb_cma_size -= hugetlb_cma_size_in_node[nid]; hugetlb_cma_size_in_node[nid] = 0; @@ -6990,7 +7188,7 @@ void __init hugetlb_cma_reserve(int order) } reserved = 0; - for_each_node_state(nid, N_ONLINE) { + for_each_online_node(nid) { int res; char name[CMA_MAX_NAME]; |