diff options
Diffstat (limited to 'mm')
47 files changed, 998 insertions, 490 deletions
diff --git a/mm/compaction.c b/mm/compaction.c index a2b16b08cbbf..eb5474dea04d 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -630,7 +630,8 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, if (PageCompound(page)) { const unsigned int order = compound_order(page); - if (blockpfn + (1UL << order) <= end_pfn) { + if ((order <= MAX_PAGE_ORDER) && + (blockpfn + (1UL << order) <= end_pfn)) { blockpfn += (1UL << order) - 1; page += (1UL << order) - 1; nr_scanned += (1UL << order) - 1; @@ -979,13 +980,13 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, } if (PageHuge(page)) { + const unsigned int order = compound_order(page); /* * skip hugetlbfs if we are not compacting for pages * bigger than its order. THPs and other compound pages * are handled below. */ if (!cc->alloc_contig) { - const unsigned int order = compound_order(page); if (order <= MAX_PAGE_ORDER) { low_pfn += (1UL << order) - 1; @@ -1009,8 +1010,8 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, /* Do not report -EBUSY down the chain */ if (ret == -EBUSY) ret = 0; - low_pfn += compound_nr(page) - 1; - nr_scanned += compound_nr(page) - 1; + low_pfn += (1UL << order) - 1; + nr_scanned += (1UL << order) - 1; goto isolate_fail; } @@ -3163,6 +3164,7 @@ static int kcompactd(void *p) if (!cpumask_empty(cpumask)) set_cpus_allowed_ptr(tsk, cpumask); + current->flags |= PF_KCOMPACTD; set_freezable(); pgdat->kcompactd_max_order = 0; @@ -3219,6 +3221,8 @@ static int kcompactd(void *p) pgdat->proactive_compact_trigger = false; } + current->flags &= ~PF_KCOMPACTD; + return 0; } diff --git a/mm/damon/core.c b/mm/damon/core.c index 54f4dd8d549f..9689f5425238 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -837,6 +837,7 @@ static int damos_commit(struct damos *dst, struct damos *src) return err; dst->wmarks = src->wmarks; + dst->target_nid = src->target_nid; err = damos_commit_filters(dst, src); return err; diff --git a/mm/damon/ops-common.c b/mm/damon/ops-common.c index d25d99cb5f2b..d511be201c4c 100644 --- a/mm/damon/ops-common.c +++ b/mm/damon/ops-common.c @@ -24,7 +24,7 @@ struct folio *damon_get_folio(unsigned long pfn) struct page *page = pfn_to_online_page(pfn); struct folio *folio; - if (!page || PageTail(page)) + if (!page) return NULL; folio = page_folio(page); diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c index a9ff35341d65..4120a73f4933 100644 --- a/mm/damon/paddr.c +++ b/mm/damon/paddr.c @@ -264,11 +264,14 @@ static unsigned long damon_pa_pageout(struct damon_region *r, struct damos *s) damos_add_filter(s, filter); } - for (addr = r->ar.start; addr < r->ar.end; addr += PAGE_SIZE) { + addr = r->ar.start; + while (addr < r->ar.end) { struct folio *folio = damon_get_folio(PHYS_PFN(addr)); - if (!folio) + if (!folio) { + addr += PAGE_SIZE; continue; + } if (damos_pa_filter_out(s, folio)) goto put_folio; @@ -282,6 +285,7 @@ static unsigned long damon_pa_pageout(struct damon_region *r, struct damos *s) else list_add(&folio->lru, &folio_list); put_folio: + addr += folio_size(folio); folio_put(folio); } if (install_young_filter) @@ -296,11 +300,14 @@ static inline unsigned long damon_pa_mark_accessed_or_deactivate( { unsigned long addr, applied = 0; - for (addr = r->ar.start; addr < r->ar.end; addr += PAGE_SIZE) { + addr = r->ar.start; + while (addr < r->ar.end) { struct folio *folio = damon_get_folio(PHYS_PFN(addr)); - if (!folio) + if (!folio) { + addr += PAGE_SIZE; continue; + } if (damos_pa_filter_out(s, folio)) goto put_folio; @@ -311,6 +318,7 @@ static inline unsigned long damon_pa_mark_accessed_or_deactivate( folio_deactivate(folio); applied += folio_nr_pages(folio); put_folio: + addr += folio_size(folio); folio_put(folio); } return applied * PAGE_SIZE; @@ -423,6 +431,10 @@ static unsigned long damon_pa_migrate_pages(struct list_head *folio_list, if (list_empty(folio_list)) return nr_migrated; + if (target_nid < 0 || target_nid >= MAX_NUMNODES || + !node_state(target_nid, N_MEMORY)) + return nr_migrated; + noreclaim_flag = memalloc_noreclaim_save(); nid = folio_nid(lru_to_folio(folio_list)); @@ -454,11 +466,14 @@ static unsigned long damon_pa_migrate(struct damon_region *r, struct damos *s) unsigned long addr, applied; LIST_HEAD(folio_list); - for (addr = r->ar.start; addr < r->ar.end; addr += PAGE_SIZE) { + addr = r->ar.start; + while (addr < r->ar.end) { struct folio *folio = damon_get_folio(PHYS_PFN(addr)); - if (!folio) + if (!folio) { + addr += PAGE_SIZE; continue; + } if (damos_pa_filter_out(s, folio)) goto put_folio; @@ -467,6 +482,7 @@ static unsigned long damon_pa_migrate(struct damon_region *r, struct damos *s) goto put_folio; list_add(&folio->lru, &folio_list); put_folio: + addr += folio_size(folio); folio_put(folio); } applied = damon_pa_migrate_pages(&folio_list, s->target_nid); diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c index b095457380b5..d9e01648db70 100644 --- a/mm/damon/sysfs-schemes.c +++ b/mm/damon/sysfs-schemes.c @@ -423,6 +423,7 @@ static ssize_t memcg_path_store(struct kobject *kobj, return -ENOMEM; strscpy(path, buf, count + 1); + kfree(filter->memcg_path); filter->memcg_path = path; return count; } diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c index bc748f700a9e..80cc409ba78a 100644 --- a/mm/debug_vm_pgtable.c +++ b/mm/debug_vm_pgtable.c @@ -1049,29 +1049,34 @@ static void __init destroy_args(struct pgtable_debug_args *args) /* Free page table entries */ if (args->start_ptep) { + pmd_clear(args->pmdp); pte_free(args->mm, args->start_ptep); mm_dec_nr_ptes(args->mm); } if (args->start_pmdp) { + pud_clear(args->pudp); pmd_free(args->mm, args->start_pmdp); mm_dec_nr_pmds(args->mm); } if (args->start_pudp) { + p4d_clear(args->p4dp); pud_free(args->mm, args->start_pudp); mm_dec_nr_puds(args->mm); } - if (args->start_p4dp) + if (args->start_p4dp) { + pgd_clear(args->pgdp); p4d_free(args->mm, args->start_p4dp); + } /* Free vma and mm struct */ if (args->vma) vm_area_free(args->vma); if (args->mm) - mmdrop(args->mm); + mmput(args->mm); } static struct page * __init diff --git a/mm/filemap.c b/mm/filemap.c index 56fa431c52af..ec69fadf014c 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1750,8 +1750,9 @@ pgoff_t page_cache_next_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan) { XA_STATE(xas, &mapping->i_pages, index); + unsigned long nr = max_scan; - while (max_scan--) { + while (nr--) { void *entry = xas_next(&xas); if (!entry || xa_is_value(entry)) return xas.xa_index; @@ -1966,8 +1967,19 @@ no_page: if (err == -EEXIST) goto repeat; - if (err) + if (err) { + /* + * When NOWAIT I/O fails to allocate folios this could + * be due to a nonblocking memory allocation and not + * because the system actually is out of memory. + * Return -EAGAIN so that there caller retries in a + * blocking fashion instead of propagating -ENOMEM + * to the application. + */ + if ((fgp_flags & FGP_NOWAIT) && err == -ENOMEM) + err = -EAGAIN; return ERR_PTR(err); + } /* * filemap_add_folio locks the page, and for mmap * we expect an unlocked page. @@ -2211,6 +2223,7 @@ unsigned filemap_get_folios_contig(struct address_space *mapping, *start = folio->index + nr; goto out; } + xas_advance(&xas, folio_next_index(folio) - 1); continue; put_folio: folio_put(folio); @@ -3004,7 +3017,7 @@ static inline loff_t folio_seek_hole_data(struct xa_state *xas, if (ops->is_partially_uptodate(folio, offset, bsz) == seek_data) break; - start = (start + bsz) & ~(bsz - 1); + start = (start + bsz) & ~((u64)bsz - 1); offset += bsz; } while (offset < folio_size(folio)); unlock: @@ -4384,6 +4397,20 @@ resched: } /* + * See mincore: reveal pagecache information only for files + * that the calling process has write access to, or could (if + * tried) open for writing. + */ +static inline bool can_do_cachestat(struct file *f) +{ + if (f->f_mode & FMODE_WRITE) + return true; + if (inode_owner_or_capable(file_mnt_idmap(f), file_inode(f))) + return true; + return file_permission(f, MAY_WRITE) == 0; +} + +/* * The cachestat(2) system call. * * cachestat() returns the page cache statistics of a file in the @@ -4442,6 +4469,11 @@ SYSCALL_DEFINE4(cachestat, unsigned int, fd, return -EOPNOTSUPP; } + if (!can_do_cachestat(fd_file(f))) { + fdput(f); + return -EPERM; + } + if (flags != 0) { fdput(f); return -EINVAL; @@ -1283,6 +1283,9 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags) if ((gup_flags & FOLL_LONGTERM) && vma_is_fsdax(vma)) return -EOPNOTSUPP; + if ((gup_flags & FOLL_SPLIT_PMD) && is_vm_hugetlb_page(vma)) + return -EOPNOTSUPP; + if (vma_is_secretmem(vma)) return -EFAULT; @@ -2210,8 +2213,8 @@ size_t fault_in_safe_writeable(const char __user *uaddr, size_t size) } while (start != end); mmap_read_unlock(mm); - if (size > (unsigned long)uaddr - start) - return size - ((unsigned long)uaddr - start); + if (size > start - (unsigned long)uaddr) + return size - (start - (unsigned long)uaddr); return 0; } EXPORT_SYMBOL(fault_in_safe_writeable); @@ -173,6 +173,7 @@ static inline unsigned long hmm_pfn_flags_order(unsigned long order) return order << HMM_PFN_ORDER_SHIFT; } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline unsigned long pmd_to_hmm_pfn_flags(struct hmm_range *range, pmd_t pmd) { @@ -183,7 +184,6 @@ static inline unsigned long pmd_to_hmm_pfn_flags(struct hmm_range *range, hmm_pfn_flags_order(PMD_SHIFT - PAGE_SHIFT); } -#ifdef CONFIG_TRANSPARENT_HUGEPAGE static int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr, unsigned long end, unsigned long hmm_pfns[], pmd_t pmd) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 7e0f72cd9fd4..f94a9d413585 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2132,6 +2132,16 @@ static pmd_t move_soft_dirty_pmd(pmd_t pmd) return pmd; } +static pmd_t clear_uffd_wp_pmd(pmd_t pmd) +{ + if (pmd_present(pmd)) + pmd = pmd_clear_uffd_wp(pmd); + else if (is_swap_pmd(pmd)) + pmd = pmd_swp_clear_uffd_wp(pmd); + + return pmd; +} + bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd) { @@ -2170,6 +2180,8 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, pgtable_trans_huge_deposit(mm, new_pmd, pgtable); } pmd = move_soft_dirty_pmd(pmd); + if (vma_has_uffd_without_event_remap(vma)) + pmd = clear_uffd_wp_pmd(pmd); set_pmd_at(mm, new_addr, new_pmd, pmd); if (force_flush) flush_pmd_tlb_range(vma, old_addr, old_addr + PMD_SIZE); @@ -2867,6 +2879,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address, pmd_t *pmd, bool freeze, struct folio *folio) { + bool pmd_migration = is_pmd_migration_entry(*pmd); + VM_WARN_ON_ONCE(folio && !folio_test_pmd_mappable(folio)); VM_WARN_ON_ONCE(!IS_ALIGNED(address, HPAGE_PMD_SIZE)); VM_WARN_ON_ONCE(folio && !folio_test_locked(folio)); @@ -2877,9 +2891,12 @@ void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address, * require a folio to check the PMD against. Otherwise, there * is a risk of replacing the wrong folio. */ - if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) || - is_pmd_migration_entry(*pmd)) { - if (folio && folio != pmd_folio(*pmd)) + if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) || pmd_migration) { + /* + * Do not apply pmd_folio() to a migration entry; and folio lock + * guarantees that it must be of the wrong folio anyway. + */ + if (folio && (pmd_migration || folio != pmd_folio(*pmd))) return; __split_huge_pmd_locked(vma, pmd, address, freeze); } @@ -3212,7 +3229,7 @@ static void __split_huge_page(struct page *page, struct list_head *list, folio_account_cleaned(tail, inode_to_wb(folio->mapping->host)); __filemap_remove_folio(tail, NULL); - folio_put(tail); + folio_put_refs(tail, folio_nr_pages(tail)); } else if (!PageAnon(page)) { __xa_store(&folio->mapping->i_pages, head[i].index, head + i, 0); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 2fa87b9ecec6..9c6a4e855481 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -87,7 +87,7 @@ static void hugetlb_vma_lock_free(struct vm_area_struct *vma); static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma); static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma); static void hugetlb_unshare_pmds(struct vm_area_struct *vma, - unsigned long start, unsigned long end); + unsigned long start, unsigned long end, bool take_locks); static struct resv_map *vma_resv_map(struct vm_area_struct *vma); static void hugetlb_free_folio(struct folio *folio) @@ -1394,8 +1394,7 @@ static unsigned long available_huge_pages(struct hstate *h) static struct folio *dequeue_hugetlb_folio_vma(struct hstate *h, struct vm_area_struct *vma, - unsigned long address, int avoid_reserve, - long chg) + unsigned long address, long chg) { struct folio *folio = NULL; struct mempolicy *mpol; @@ -1411,10 +1410,6 @@ static struct folio *dequeue_hugetlb_folio_vma(struct hstate *h, if (!vma_has_reserves(vma, chg) && !available_huge_pages(h)) goto err; - /* If reserves cannot be used, ensure enough pages are in the pool */ - if (avoid_reserve && !available_huge_pages(h)) - goto err; - gfp_mask = htlb_alloc_mask(h); nid = huge_node(vma, address, gfp_mask, &mpol, &nodemask); @@ -1430,7 +1425,7 @@ static struct folio *dequeue_hugetlb_folio_vma(struct hstate *h, folio = dequeue_hugetlb_folio_nodemask(h, gfp_mask, nid, nodemask); - if (folio && !avoid_reserve && vma_has_reserves(vma, chg)) { + if (folio && vma_has_reserves(vma, chg)) { folio_set_hugetlb_restore_reserve(folio); h->resv_huge_pages--; } @@ -2960,6 +2955,14 @@ int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list) return ret; } +void wait_for_freed_hugetlb_folios(void) +{ + if (llist_empty(&hpage_freelist)) + return; + + flush_work(&free_hpage_work); +} + struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve) { @@ -3006,17 +3009,6 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, gbl_chg = hugepage_subpool_get_pages(spool, 1); if (gbl_chg < 0) goto out_end_reservation; - - /* - * Even though there was no reservation in the region/reserve - * map, there could be reservations associated with the - * subpool that can be used. This would be indicated if the - * return value of hugepage_subpool_get_pages() is zero. - * However, if avoid_reserve is specified we still avoid even - * the subpool reservations. - */ - if (avoid_reserve) - gbl_chg = 1; } /* If this allocation is not consuming a reservation, charge it now. @@ -3039,7 +3031,7 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, * from the global free pool (global change). gbl_chg == 0 indicates * a reservation exists for the allocation. */ - folio = dequeue_hugetlb_folio_vma(h, vma, addr, avoid_reserve, gbl_chg); + folio = dequeue_hugetlb_folio_vma(h, vma, addr, gbl_chg); if (!folio) { spin_unlock_irq(&hugetlb_lock); folio = alloc_buddy_hugetlb_folio_with_mpol(h, vma, addr); @@ -3287,7 +3279,7 @@ static void __init gather_bootmem_prealloc(void) .thread_fn = gather_bootmem_prealloc_parallel, .fn_arg = NULL, .start = 0, - .size = num_node_state(N_MEMORY), + .size = nr_node_ids, .align = 1, .min_chunk = 1, .max_threads = num_node_state(N_MEMORY), @@ -4871,7 +4863,7 @@ static struct ctl_table hugetlb_table[] = { }, }; -static void hugetlb_sysctl_init(void) +static void __init hugetlb_sysctl_init(void) { register_sysctl_init("vm", hugetlb_table); } @@ -5079,26 +5071,40 @@ static int hugetlb_vm_op_split(struct vm_area_struct *vma, unsigned long addr) { if (addr & ~(huge_page_mask(hstate_vma(vma)))) return -EINVAL; + return 0; +} +void hugetlb_split(struct vm_area_struct *vma, unsigned long addr) +{ /* * PMD sharing is only possible for PUD_SIZE-aligned address ranges * in HugeTLB VMAs. If we will lose PUD_SIZE alignment due to this * split, unshare PMDs in the PUD_SIZE interval surrounding addr now. + * This function is called in the middle of a VMA split operation, with + * MM, VMA and rmap all write-locked to prevent concurrent page table + * walks (except hardware and gup_fast()). */ + vma_assert_write_locked(vma); + i_mmap_assert_write_locked(vma->vm_file->f_mapping); + if (addr & ~PUD_MASK) { - /* - * hugetlb_vm_op_split is called right before we attempt to - * split the VMA. We will need to unshare PMDs in the old and - * new VMAs, so let's unshare before we split. - */ unsigned long floor = addr & PUD_MASK; unsigned long ceil = floor + PUD_SIZE; - if (floor >= vma->vm_start && ceil <= vma->vm_end) - hugetlb_unshare_pmds(vma, floor, ceil); + if (floor >= vma->vm_start && ceil <= vma->vm_end) { + /* + * Locking: + * Use take_locks=false here. + * The file rmap lock is already held. + * The hugetlb VMA lock can't be taken when we already + * hold the file rmap lock, and we don't need it because + * its purpose is to synchronize against concurrent page + * table walks, which are not possible thanks to the + * locks held by our caller. + */ + hugetlb_unshare_pmds(vma, floor, ceil, /* take_locks = */ false); + } } - - return 0; } static unsigned long hugetlb_vm_op_pagesize(struct vm_area_struct *vma) @@ -5395,6 +5401,7 @@ static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr, unsigned long new_addr, pte_t *src_pte, pte_t *dst_pte, unsigned long sz) { + bool need_clear_uffd_wp = vma_has_uffd_without_event_remap(vma); struct hstate *h = hstate_vma(vma); struct mm_struct *mm = vma->vm_mm; spinlock_t *src_ptl, *dst_ptl; @@ -5410,8 +5417,19 @@ static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr, if (src_ptl != dst_ptl) spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); - pte = huge_ptep_get_and_clear(mm, old_addr, src_pte); - set_huge_pte_at(mm, new_addr, dst_pte, pte, sz); + pte = huge_ptep_get_and_clear(mm, old_addr, src_pte, sz); + + if (need_clear_uffd_wp && pte_marker_uffd_wp(pte)) + huge_pte_clear(mm, new_addr, dst_pte, sz); + else { + if (need_clear_uffd_wp) { + if (pte_present(pte)) + pte = huge_pte_clear_uffd_wp(pte); + else if (is_swap_pte(pte)) + pte = pte_swp_clear_uffd_wp(pte); + } + set_huge_pte_at(mm, new_addr, dst_pte, pte, sz); + } if (src_ptl != dst_ptl) spin_unlock(src_ptl); @@ -5574,7 +5592,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, set_vma_resv_flags(vma, HPAGE_RESV_UNMAPPED); } - pte = huge_ptep_get_and_clear(mm, address, ptep); + pte = huge_ptep_get_and_clear(mm, address, ptep, sz); tlb_remove_huge_tlb_entry(h, tlb, ptep, address); if (huge_pte_dirty(pte)) set_page_dirty(page); @@ -7248,6 +7266,13 @@ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, return 0; pud_clear(pud); + /* + * Once our caller drops the rmap lock, some other process might be + * using this page table as a normal, non-hugetlb page table. + * Wait for pending gup_fast() in other threads to finish before letting + * that happen. + */ + tlb_remove_table_sync_one(); ptdesc_pmd_pts_dec(virt_to_ptdesc(ptep)); mm_dec_nr_pmds(mm); return 1; @@ -7480,9 +7505,16 @@ void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int re } } +/* + * If @take_locks is false, the caller must ensure that no concurrent page table + * access can happen (except for gup_fast() and hardware page walks). + * If @take_locks is true, we take the hugetlb VMA lock (to lock out things like + * concurrent page fault handling) and the file rmap lock. + */ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, unsigned long start, - unsigned long end) + unsigned long end, + bool take_locks) { struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); @@ -7506,8 +7538,12 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, start, end); mmu_notifier_invalidate_range_start(&range); - hugetlb_vma_lock_write(vma); - i_mmap_lock_write(vma->vm_file->f_mapping); + if (take_locks) { + hugetlb_vma_lock_write(vma); + i_mmap_lock_write(vma->vm_file->f_mapping); + } else { + i_mmap_assert_write_locked(vma->vm_file->f_mapping); + } for (address = start; address < end; address += PUD_SIZE) { ptep = hugetlb_walk(vma, address, sz); if (!ptep) @@ -7517,8 +7553,10 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, spin_unlock(ptl); } flush_hugetlb_tlb_range(vma, start, end); - i_mmap_unlock_write(vma->vm_file->f_mapping); - hugetlb_vma_unlock_write(vma); + if (take_locks) { + i_mmap_unlock_write(vma->vm_file->f_mapping); + hugetlb_vma_unlock_write(vma); + } /* * No need to call mmu_notifier_arch_invalidate_secondary_tlbs(), see * Documentation/mm/mmu_notifier.rst. @@ -7533,7 +7571,8 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) { hugetlb_unshare_pmds(vma, ALIGN(vma->vm_start, PUD_SIZE), - ALIGN_DOWN(vma->vm_end, PUD_SIZE)); + ALIGN_DOWN(vma->vm_end, PUD_SIZE), + /* take_locks = */ true); } #ifdef CONFIG_CMA diff --git a/mm/internal.h b/mm/internal.h index 9bb098e78f15..9e0577413087 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -204,11 +204,9 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr, pte_t *start_ptep, pte_t pte, int max_nr, fpb_t flags, bool *any_writable, bool *any_young, bool *any_dirty) { - unsigned long folio_end_pfn = folio_pfn(folio) + folio_nr_pages(folio); - const pte_t *end_ptep = start_ptep + max_nr; pte_t expected_pte, *ptep; bool writable, young, dirty; - int nr; + int nr, cur_nr; if (any_writable) *any_writable = false; @@ -221,11 +219,15 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr, VM_WARN_ON_FOLIO(!folio_test_large(folio) || max_nr < 1, folio); VM_WARN_ON_FOLIO(page_folio(pfn_to_page(pte_pfn(pte))) != folio, folio); + /* Limit max_nr to the actual remaining PFNs in the folio we could batch. */ + max_nr = min_t(unsigned long, max_nr, + folio_pfn(folio) + folio_nr_pages(folio) - pte_pfn(pte)); + nr = pte_batch_hint(start_ptep, pte); expected_pte = __pte_batch_clear_ignored(pte_advance_pfn(pte, nr), flags); ptep = start_ptep + nr; - while (ptep < end_ptep) { + while (nr < max_nr) { pte = ptep_get(ptep); if (any_writable) writable = !!pte_write(pte); @@ -238,14 +240,6 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr, if (!pte_same(pte, expected_pte)) break; - /* - * Stop immediately once we reached the end of the folio. In - * corner cases the next PFN might fall into a different - * folio. - */ - if (pte_pfn(pte) >= folio_end_pfn) - break; - if (any_writable) *any_writable |= writable; if (any_young) @@ -253,12 +247,13 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr, if (any_dirty) *any_dirty |= dirty; - nr = pte_batch_hint(ptep, pte); - expected_pte = pte_advance_pfn(expected_pte, nr); - ptep += nr; + cur_nr = pte_batch_hint(ptep, pte); + expected_pte = pte_advance_pfn(expected_pte, cur_nr); + ptep += cur_nr; + nr += cur_nr; } - return min(ptep - start_ptep, max_nr); + return min(nr, max_nr); } /** @@ -1101,7 +1096,7 @@ static inline int find_next_best_node(int node, nodemask_t *used_node_mask) * mm/memory-failure.c */ #ifdef CONFIG_MEMORY_FAILURE -void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu); +int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill); void shake_folio(struct folio *folio); extern int hwpoison_filter(struct page *p); @@ -1123,8 +1118,9 @@ void add_to_kill_ksm(struct task_struct *tsk, struct page *p, unsigned long page_mapped_in_vma(struct page *page, struct vm_area_struct *vma); #else -static inline void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu) +static inline int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill) { + return -EBUSY; } #endif diff --git a/mm/kasan/kasan_test_rust.rs b/mm/kasan/kasan_test_rust.rs index caa7175964ef..5b34edf30e72 100644 --- a/mm/kasan/kasan_test_rust.rs +++ b/mm/kasan/kasan_test_rust.rs @@ -11,11 +11,12 @@ use kernel::prelude::*; /// drop the vector, and touch it. #[no_mangle] pub extern "C" fn kasan_test_rust_uaf() -> u8 { - let mut v: Vec<u8> = Vec::new(); + let mut v: KVec<u8> = KVec::new(); for _ in 0..4096 { v.push(0x42, GFP_KERNEL).unwrap(); } let ptr: *mut u8 = addr_of_mut!(v[2048]); drop(v); + // SAFETY: Incorrect, on purpose. unsafe { *ptr } } diff --git a/mm/kasan/report.c b/mm/kasan/report.c index c7c0083203cb..f17265410156 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -398,17 +398,10 @@ static void print_address_description(void *addr, u8 tag, } if (is_vmalloc_addr(addr)) { - struct vm_struct *va = find_vm_area(addr); - - if (va) { - pr_err("The buggy address belongs to the virtual mapping at\n" - " [%px, %px) created by:\n" - " %pS\n", - va->addr, va->addr + va->size, va->caller); - pr_err("\n"); - - page = vmalloc_to_page(addr); - } + pr_err("The buggy address belongs to a"); + if (!vmalloc_dump_obj(addr)) + pr_cont(" vmalloc virtual mapping\n"); + page = vmalloc_to_page(addr); } if (page) { diff --git a/mm/kfence/core.c b/mm/kfence/core.c index 67fc321db79b..102048821c22 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -21,6 +21,7 @@ #include <linux/log2.h> #include <linux/memblock.h> #include <linux/moduleparam.h> +#include <linux/nodemask.h> #include <linux/notifier.h> #include <linux/panic_notifier.h> #include <linux/random.h> @@ -1084,6 +1085,7 @@ void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) * properties (e.g. reside in DMAable memory). */ if ((flags & GFP_ZONEMASK) || + ((flags & __GFP_THISNODE) && num_online_nodes() > 1) || (s->flags & (SLAB_CACHE_DMA | SLAB_CACHE_DMA32))) { atomic_long_inc(&counters[KFENCE_COUNTER_SKIP_INCOMPAT]); return NULL; diff --git a/mm/khugepaged.c b/mm/khugepaged.c index b538c3d48386..abd5764e4864 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -2404,7 +2404,7 @@ skip: VM_BUG_ON(khugepaged_scan.address < hstart || khugepaged_scan.address + HPAGE_PMD_SIZE > hend); - if (IS_ENABLED(CONFIG_SHMEM) && vma->vm_file) { + if (IS_ENABLED(CONFIG_SHMEM) && !vma_is_anonymous(vma)) { struct file *file = get_file(vma->vm_file); pgoff_t pgoff = linear_page_index(vma, khugepaged_scan.address); @@ -2750,7 +2750,7 @@ int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev, mmap_assert_locked(mm); memset(cc->node_load, 0, sizeof(cc->node_load)); nodes_clear(cc->alloc_nmask); - if (IS_ENABLED(CONFIG_SHMEM) && vma->vm_file) { + if (IS_ENABLED(CONFIG_SHMEM) && !vma_is_anonymous(vma)) { struct file *file = get_file(vma->vm_file); pgoff_t pgoff = linear_page_index(vma, addr); diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 74f5f4c51ab8..91894fc54c64 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -465,6 +465,7 @@ static struct kmemleak_object *mem_pool_alloc(gfp_t gfp) { unsigned long flags; struct kmemleak_object *object; + bool warn = false; /* try the slab allocator first */ if (object_cache) { @@ -483,8 +484,10 @@ static struct kmemleak_object *mem_pool_alloc(gfp_t gfp) else if (mem_pool_free_count) object = &mem_pool[--mem_pool_free_count]; else - pr_warn_once("Memory pool empty, consider increasing CONFIG_DEBUG_KMEMLEAK_MEM_POOL_SIZE\n"); + warn = true; raw_spin_unlock_irqrestore(&kmemleak_lock, flags); + if (warn) + pr_warn_once("Memory pool empty, consider increasing CONFIG_DEBUG_KMEMLEAK_MEM_POOL_SIZE\n"); return object; } @@ -1071,7 +1074,7 @@ void __ref kmemleak_alloc_percpu(const void __percpu *ptr, size_t size, pr_debug("%s(0x%px, %zu)\n", __func__, ptr, size); if (kmemleak_enabled && ptr && !IS_ERR_PCPU(ptr)) - create_object_percpu((__force unsigned long)ptr, size, 0, gfp); + create_object_percpu((__force unsigned long)ptr, size, 1, gfp); } EXPORT_SYMBOL_GPL(kmemleak_alloc_percpu); @@ -1650,7 +1653,7 @@ static void kmemleak_scan(void) unsigned long phys = object->pointer; if (PHYS_PFN(phys) < min_low_pfn || - PHYS_PFN(phys + object->size) >= max_low_pfn) + PHYS_PFN(phys + object->size) > max_low_pfn) __paint_it(object, KMEMLEAK_BLACK); } @@ -2107,6 +2110,7 @@ static const struct file_operations kmemleak_fops = { static void __kmemleak_do_cleanup(void) { struct kmemleak_object *object, *tmp; + unsigned int cnt = 0; /* * Kmemleak has already been disabled, no need for RCU list traversal @@ -2115,6 +2119,10 @@ static void __kmemleak_do_cleanup(void) list_for_each_entry_safe(object, tmp, &object_list, object_list) { __remove_object(object); __delete_object(object); + + /* Call cond_resched() once per 64 iterations to avoid soft lockup */ + if (!(++cnt & 0x3f)) + cond_resched(); } } diff --git a/mm/kmsan/hooks.c b/mm/kmsan/hooks.c index 3ea50f09311f..3df45c25c1f6 100644 --- a/mm/kmsan/hooks.c +++ b/mm/kmsan/hooks.c @@ -357,6 +357,7 @@ void kmsan_handle_dma(struct page *page, size_t offset, size_t size, size -= to_go; } } +EXPORT_SYMBOL_GPL(kmsan_handle_dma); void kmsan_handle_dma_sg(struct scatterlist *sg, int nents, enum dma_data_direction dir) @@ -3643,10 +3643,10 @@ static ssize_t advisor_mode_show(struct kobject *kobj, { const char *output; - if (ksm_advisor == KSM_ADVISOR_NONE) - output = "[none] scan-time"; - else if (ksm_advisor == KSM_ADVISOR_SCAN_TIME) + if (ksm_advisor == KSM_ADVISOR_SCAN_TIME) output = "none [scan-time]"; + else + output = "[none] scan-time"; return sysfs_emit(buf, "%s\n", output); } diff --git a/mm/madvise.c b/mm/madvise.c index ff139e57cca2..2e66a08fd4f4 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -495,6 +495,7 @@ restart: pte_offset_map_lock(mm, pmd, addr, &ptl); if (!start_pte) break; + flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); if (!err) nr = 0; @@ -728,6 +729,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, start_pte = pte; if (!start_pte) break; + flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); if (!err) nr = 0; @@ -920,7 +922,16 @@ static long madvise_dontneed_free(struct vm_area_struct *vma, */ end = vma->vm_end; } - VM_WARN_ON(start >= end); + /* + * If the memory region between start and end was + * originally backed by 4kB pages and then remapped to + * be backed by hugepages while mmap_lock was dropped, + * the adjustment for hugetlb vma above may have rounded + * end down to the start address. + */ + if (start == end) + return 0; + VM_WARN_ON(start > end); } if (behavior == MADV_DONTNEED || behavior == MADV_DONTNEED_LOCKED) diff --git a/mm/memblock.c b/mm/memblock.c index 095c18b5c430..3d7b0114442c 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -456,7 +456,14 @@ static int __init_memblock memblock_double_array(struct memblock_type *type, min(new_area_start, memblock.current_limit), new_alloc_size, PAGE_SIZE); - new_array = addr ? __va(addr) : NULL; + if (addr) { + /* The memory may not have been accepted, yet. */ + accept_memory(addr, new_alloc_size); + + new_array = __va(addr); + } else { + new_array = NULL; + } } if (!addr) { pr_err("memblock: Failed to double %s array from %ld to %ld entries !\n", @@ -2160,11 +2167,14 @@ static void __init memmap_init_reserved_pages(void) struct memblock_region *region; phys_addr_t start, end; int nid; + unsigned long max_reserved; /* * set nid on all reserved pages and also treat struct * pages for the NOMAP regions as PageReserved */ +repeat: + max_reserved = memblock.reserved.max; for_each_mem_region(region) { nid = memblock_get_region_node(region); start = region->base; @@ -2173,8 +2183,15 @@ static void __init memmap_init_reserved_pages(void) if (memblock_is_nomap(region)) reserve_bootmem_region(start, end, nid); - memblock_set_node(start, end, &memblock.reserved, nid); + memblock_set_node(start, region->size, &memblock.reserved, nid); } + /* + * 'max' is changed means memblock.reserved has been doubled its + * array, which may result a new reserved region before current + * 'start'. Now we should repeat the procedure to set its node id. + */ + if (max_reserved != memblock.reserved.max) + goto repeat; /* * initialize struct pages for reserved regions that don't have diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 53db98d2c4a1..dcd2d0e15e13 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1147,8 +1147,11 @@ void mem_cgroup_scan_tasks(struct mem_cgroup *memcg, struct task_struct *task; css_task_iter_start(&iter->css, CSS_TASK_ITER_PROCS, &it); - while (!ret && (task = css_task_iter_next(&it))) + while (!ret && (task = css_task_iter_next(&it))) { ret = fn(task, arg); + /* Avoid potential softlockup warning */ + cond_resched(); + } css_task_iter_end(&it); if (ret) { mem_cgroup_iter_break(memcg, iter); @@ -1877,9 +1880,18 @@ void drain_all_stock(struct mem_cgroup *root_memcg) static int memcg_hotplug_cpu_dead(unsigned int cpu) { struct memcg_stock_pcp *stock; + struct obj_cgroup *old; + unsigned long flags; stock = &per_cpu(memcg_stock, cpu); + + /* drain_obj_stock requires stock_lock */ + local_lock_irqsave(&memcg_stock.stock_lock, flags); + old = drain_obj_stock(stock); + local_unlock_irqrestore(&memcg_stock.stock_lock, flags); + drain_stock(stock); + obj_cgroup_put(old); return 0; } diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 96ce31e5a203..8c8d78d6d306 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -845,9 +845,17 @@ static int hwpoison_hugetlb_range(pte_t *ptep, unsigned long hmask, #define hwpoison_hugetlb_range NULL #endif +static int hwpoison_test_walk(unsigned long start, unsigned long end, + struct mm_walk *walk) +{ + /* We also want to consider pages mapped into VM_PFNMAP. */ + return 0; +} + static const struct mm_walk_ops hwpoison_walk_ops = { .pmd_entry = hwpoison_pte_range, .hugetlb_entry = hwpoison_hugetlb_range, + .test_walk = hwpoison_test_walk, .walk_lock = PGWALK_RDLOCK, }; @@ -879,12 +887,17 @@ static int kill_accessing_process(struct task_struct *p, unsigned long pfn, mmap_read_lock(p->mm); ret = walk_page_range(p->mm, 0, TASK_SIZE, &hwpoison_walk_ops, (void *)&priv); + /* + * ret = 1 when CMCI wins, regardless of whether try_to_unmap() + * succeeds or fails, then kill the process with SIGBUS. + * ret = 0 when poison page is a clean page and it's dropped, no + * SIGBUS is needed. + */ if (ret == 1 && priv.tk.addr) kill_proc(&priv.tk, pfn, flags); - else - ret = 0; mmap_read_unlock(p->mm); - return ret > 0 ? -EHWPOISON : -EFAULT; + + return ret > 0 ? -EHWPOISON : 0; } /* @@ -1554,11 +1567,39 @@ static int get_hwpoison_page(struct page *p, unsigned long flags) return ret; } -void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu) +/* + * The caller must guarantee the folio isn't large folio, except hugetlb. + * try_to_unmap() can't handle it. + */ +int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill) { - if (folio_test_hugetlb(folio) && !folio_test_anon(folio)) { - struct address_space *mapping; + enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_SYNC | TTU_HWPOISON; + struct address_space *mapping; + + if (folio_test_swapcache(folio)) { + pr_err("%#lx: keeping poisoned page in swap cache\n", pfn); + ttu &= ~TTU_HWPOISON; + } + + /* + * Propagate the dirty bit from PTEs to struct page first, because we + * need this to decide if we should kill or just drop the page. + * XXX: the dirty test could be racy: set_page_dirty() may not always + * be called inside page lock (it's recommended but not enforced). + */ + mapping = folio_mapping(folio); + if (!must_kill && !folio_test_dirty(folio) && mapping && + mapping_can_writeback(mapping)) { + if (folio_mkclean(folio)) { + folio_set_dirty(folio); + } else { + ttu &= ~TTU_HWPOISON; + pr_info("%#lx: corrupted page was clean: dropped without side effects\n", + pfn); + } + } + if (folio_test_hugetlb(folio) && !folio_test_anon(folio)) { /* * For hugetlb folios in shared mappings, try_to_unmap * could potentially call huge_pmd_unshare. Because of @@ -1570,7 +1611,7 @@ void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu) if (!mapping) { pr_info("%#lx: could not lock mapping for mapped hugetlb folio\n", folio_pfn(folio)); - return; + return -EBUSY; } try_to_unmap(folio, ttu|TTU_RMAP_LOCKED); @@ -1578,6 +1619,8 @@ void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu) } else { try_to_unmap(folio, ttu); } + + return folio_mapped(folio) ? -EBUSY : 0; } /* @@ -1587,8 +1630,6 @@ void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu) static bool hwpoison_user_mappings(struct folio *folio, struct page *p, unsigned long pfn, int flags) { - enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_SYNC | TTU_HWPOISON; - struct address_space *mapping; LIST_HEAD(tokill); bool unmap_success; int forcekill; @@ -1611,29 +1652,6 @@ static bool hwpoison_user_mappings(struct folio *folio, struct page *p, if (!folio_mapped(folio)) return true; - if (folio_test_swapcache(folio)) { - pr_err("%#lx: keeping poisoned page in swap cache\n", pfn); - ttu &= ~TTU_HWPOISON; - } - - /* - * Propagate the dirty bit from PTEs to struct page first, because we - * need this to decide if we should kill or just drop the page. - * XXX: the dirty test could be racy: set_page_dirty() may not always - * be called inside page lock (it's recommended but not enforced). - */ - mapping = folio_mapping(folio); - if (!(flags & MF_MUST_KILL) && !folio_test_dirty(folio) && mapping && - mapping_can_writeback(mapping)) { - if (folio_mkclean(folio)) { - folio_set_dirty(folio); - } else { - ttu &= ~TTU_HWPOISON; - pr_info("%#lx: corrupted page was clean: dropped without side effects\n", - pfn); - } - } - /* * First collect all the processes that have the page * mapped in dirty form. This has to be done before try_to_unmap, @@ -1641,9 +1659,7 @@ static bool hwpoison_user_mappings(struct folio *folio, struct page *p, */ collect_procs(folio, p, &tokill, flags & MF_ACTION_REQUIRED); - unmap_poisoned_folio(folio, ttu); - - unmap_success = !folio_mapped(folio); + unmap_success = !unmap_poisoned_folio(folio, pfn, flags & MF_MUST_KILL); if (!unmap_success) pr_err("%#lx: failed to unmap page (folio mapcount=%d)\n", pfn, folio_mapcount(folio)); diff --git a/mm/memory.c b/mm/memory.c index d322ddfe6791..b6daa0e673a5 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1356,12 +1356,12 @@ int copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { pgd_t *src_pgd, *dst_pgd; - unsigned long next; unsigned long addr = src_vma->vm_start; unsigned long end = src_vma->vm_end; struct mm_struct *dst_mm = dst_vma->vm_mm; struct mm_struct *src_mm = src_vma->vm_mm; struct mmu_notifier_range range; + unsigned long next, pfn; bool is_cow; int ret; @@ -1372,11 +1372,7 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) return copy_hugetlb_page_range(dst_mm, src_mm, dst_vma, src_vma); if (unlikely(src_vma->vm_flags & VM_PFNMAP)) { - /* - * We do not free on error cases below as remove_vma - * gets called on error from higher level routine - */ - ret = track_pfn_copy(src_vma); + ret = track_pfn_copy(dst_vma, src_vma, &pfn); if (ret) return ret; } @@ -1413,7 +1409,6 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) continue; if (unlikely(copy_p4d_range(dst_vma, src_vma, dst_pgd, src_pgd, addr, next))) { - untrack_pfn_clear(dst_vma); ret = -ENOMEM; break; } @@ -1423,6 +1418,8 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) raw_write_seqcount_end(&src_mm->write_protect_seq); mmu_notifier_invalidate_range_end(&range); } + if (ret && unlikely(src_vma->vm_flags & VM_PFNMAP)) + untrack_pfn_copy(dst_vma, pfn); return ret; } @@ -2814,11 +2811,11 @@ static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd, if (fn) { do { if (create || !pte_none(ptep_get(pte))) { - err = fn(pte++, addr, data); + err = fn(pte, addr, data); if (err) break; } - } while (addr += PAGE_SIZE, addr != end); + } while (pte++, addr += PAGE_SIZE, addr != end); } *mask |= PGTBL_PTE_MODIFIED; @@ -2957,8 +2954,10 @@ static int __apply_to_page_range(struct mm_struct *mm, unsigned long addr, next = pgd_addr_end(addr, end); if (pgd_none(*pgd) && !create) continue; - if (WARN_ON_ONCE(pgd_leaf(*pgd))) - return -EINVAL; + if (WARN_ON_ONCE(pgd_leaf(*pgd))) { + err = -EINVAL; + break; + } if (!pgd_none(*pgd) && WARN_ON_ONCE(pgd_bad(*pgd))) { if (!create) continue; @@ -5077,7 +5076,11 @@ vm_fault_t finish_fault(struct vm_fault *vmf) bool is_cow = (vmf->flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED); int type, nr_pages; - unsigned long addr = vmf->address; + unsigned long addr; + bool needs_fallback = false; + +fallback: + addr = vmf->address; /* Did we COW the page? */ if (is_cow) @@ -5116,7 +5119,8 @@ vm_fault_t finish_fault(struct vm_fault *vmf) * approach also applies to non-anonymous-shmem faults to avoid * inflating the RSS of the process. */ - if (!vma_is_anon_shmem(vma) || unlikely(userfaultfd_armed(vma))) { + if (!vma_is_anon_shmem(vma) || unlikely(userfaultfd_armed(vma)) || + unlikely(needs_fallback)) { nr_pages = 1; } else if (nr_pages > 1) { pgoff_t idx = folio_page_idx(folio, page); @@ -5152,9 +5156,9 @@ vm_fault_t finish_fault(struct vm_fault *vmf) ret = VM_FAULT_NOPAGE; goto unlock; } else if (nr_pages > 1 && !pte_range_none(vmf->pte, nr_pages)) { - update_mmu_tlb_range(vma, addr, vmf->pte, nr_pages); - ret = VM_FAULT_NOPAGE; - goto unlock; + needs_fallback = true; + pte_unmap_unlock(vmf->pte, vmf->ptl); + goto fallback; } folio_ref_add(folio, nr_pages - 1); @@ -6711,10 +6715,8 @@ void __might_fault(const char *file, int line) if (pagefault_disabled()) return; __might_sleep(file, line); -#if defined(CONFIG_DEBUG_ATOMIC_SLEEP) if (current->mm) might_lock_read(¤t->mm->mmap_lock); -#endif } EXPORT_SYMBOL(__might_fault); #endif diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 621ae1015106..0a42e9a8caba 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1795,27 +1795,24 @@ static void do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) if (folio_test_large(folio)) pfn = folio_pfn(folio) + folio_nr_pages(folio) - 1; - /* - * HWPoison pages have elevated reference counts so the migration would - * fail on them. It also doesn't make any sense to migrate them in the - * first place. Still try to unmap such a page in case it is still mapped - * (keep the unmap as the catch all safety net). - */ - if (folio_test_hwpoison(folio) || - (folio_test_large(folio) && folio_test_has_hwpoisoned(folio))) { - if (WARN_ON(folio_test_lru(folio))) - folio_isolate_lru(folio); - if (folio_mapped(folio)) - unmap_poisoned_folio(folio, TTU_IGNORE_MLOCK); - continue; - } - if (!folio_try_get(folio)) continue; if (unlikely(page_folio(page) != folio)) goto put_folio; + if (folio_contain_hwpoisoned_page(folio)) { + if (WARN_ON(folio_test_lru(folio))) + folio_isolate_lru(folio); + if (folio_mapped(folio)) { + folio_lock(folio); + unmap_poisoned_folio(folio, pfn, false); + folio_unlock(folio); + } + + goto put_folio; + } + if (!isolate_folio_to_list(folio, &source)) { if (__ratelimit(&migrate_rs)) { pr_warn("failed to isolate pfn %lx\n", diff --git a/mm/migrate.c b/mm/migrate.c index dfa24e41e8f9..25e7438af968 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -526,15 +526,13 @@ static int __folio_migrate_mapping(struct address_space *mapping, if (folio_test_anon(folio) && folio_test_large(folio)) mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON, 1); folio_ref_add(newfolio, nr); /* add cache reference */ - if (folio_test_swapbacked(folio)) { + if (folio_test_swapbacked(folio)) __folio_set_swapbacked(newfolio); - if (folio_test_swapcache(folio)) { - folio_set_swapcache(newfolio); - newfolio->private = folio_get_private(folio); - } + if (folio_test_swapcache(folio)) { + folio_set_swapcache(newfolio); + newfolio->private = folio_get_private(folio); entries = nr; } else { - VM_BUG_ON_FOLIO(folio_test_swapcache(folio), folio); entries = 1; } diff --git a/mm/migrate_device.c b/mm/migrate_device.c index 9cf26592ac93..5bd888223cc8 100644 --- a/mm/migrate_device.c +++ b/mm/migrate_device.c @@ -840,20 +840,15 @@ void migrate_device_finalize(unsigned long *src_pfns, dst = src; } + if (!folio_is_zone_device(dst)) + folio_add_lru(dst); remove_migration_ptes(src, dst, 0); folio_unlock(src); - - if (folio_is_zone_device(src)) - folio_put(src); - else - folio_putback_lru(src); + folio_put(src); if (dst != src) { folio_unlock(dst); - if (folio_is_zone_device(dst)) - folio_put(dst); - else - folio_putback_lru(dst); + folio_put(dst); } } } diff --git a/mm/mremap.c b/mm/mremap.c index dee98ff2bbd6..12af89b4342a 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -138,6 +138,7 @@ static int move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, struct vm_area_struct *new_vma, pmd_t *new_pmd, unsigned long new_addr, bool need_rmap_locks) { + bool need_clear_uffd_wp = vma_has_uffd_without_event_remap(vma); struct mm_struct *mm = vma->vm_mm; pte_t *old_pte, *new_pte, pte; spinlock_t *old_ptl, *new_ptl; @@ -207,7 +208,18 @@ static int move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, force_flush = true; pte = move_pte(pte, old_addr, new_addr); pte = move_soft_dirty_pte(pte); - set_pte_at(mm, new_addr, new_pte, pte); + + if (need_clear_uffd_wp && pte_marker_uffd_wp(pte)) + pte_clear(mm, new_addr, new_pte); + else { + if (need_clear_uffd_wp) { + if (pte_present(pte)) + pte = pte_clear_uffd_wp(pte); + else if (is_swap_pte(pte)) + pte = pte_swp_clear_uffd_wp(pte); + } + set_pte_at(mm, new_addr, new_pte, pte); + } } arch_leave_lazy_mmu_mode(); @@ -269,6 +281,15 @@ static bool move_normal_pmd(struct vm_area_struct *vma, unsigned long old_addr, if (WARN_ON_ONCE(!pmd_none(*new_pmd))) return false; + /* If this pmd belongs to a uffd vma with remap events disabled, we need + * to ensure that the uffd-wp state is cleared from all pgtables. This + * means recursing into lower page tables in move_page_tables(), and we + * can reuse the existing code if we simply treat the entry as "not + * moved". + */ + if (vma_has_uffd_without_event_remap(vma)) + return false; + /* * We don't have to worry about the ordering of src and dst * ptlocks because exclusive mmap_lock prevents deadlock. @@ -324,6 +345,15 @@ static bool move_normal_pud(struct vm_area_struct *vma, unsigned long old_addr, if (WARN_ON_ONCE(!pud_none(*new_pud))) return false; + /* If this pud belongs to a uffd vma with remap events disabled, we need + * to ensure that the uffd-wp state is cleared from all pgtables. This + * means recursing into lower page tables in move_page_tables(), and we + * can reuse the existing code if we simply treat the entry as "not + * moved". + */ + if (vma_has_uffd_without_event_remap(vma)) + return false; + /* * We don't have to worry about the ordering of src and dst * ptlocks because exclusive mmap_lock prevents deadlock. @@ -666,8 +696,8 @@ static unsigned long move_vma(struct vm_area_struct *vma, unsigned long vm_flags = vma->vm_flags; unsigned long new_pgoff; unsigned long moved_len; - unsigned long account_start = 0; - unsigned long account_end = 0; + bool account_start = false; + bool account_end = false; unsigned long hiwater_vm; int err = 0; bool need_rmap_locks; @@ -751,9 +781,9 @@ static unsigned long move_vma(struct vm_area_struct *vma, if (vm_flags & VM_ACCOUNT && !(flags & MREMAP_DONTUNMAP)) { vm_flags_clear(vma, VM_ACCOUNT); if (vma->vm_start < old_addr) - account_start = vma->vm_start; + account_start = true; if (vma->vm_end > old_addr + old_len) - account_end = vma->vm_end; + account_end = true; } /* @@ -793,7 +823,7 @@ static unsigned long move_vma(struct vm_area_struct *vma, /* OOM: unable to split vma, just get accounts right */ if (vm_flags & VM_ACCOUNT && !(flags & MREMAP_DONTUNMAP)) vm_acct_memory(old_len >> PAGE_SHIFT); - account_start = account_end = 0; + account_start = account_end = false; } if (vm_flags & VM_LOCKED) { diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 4d7a0004df2c..8aa712afd8ae 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -45,6 +45,7 @@ #include <linux/init.h> #include <linux/mmu_notifier.h> #include <linux/cred.h> +#include <linux/nmi.h> #include <asm/tlb.h> #include "internal.h" @@ -431,10 +432,15 @@ static void dump_tasks(struct oom_control *oc) mem_cgroup_scan_tasks(oc->memcg, dump_task, oc); else { struct task_struct *p; + int i = 0; rcu_read_lock(); - for_each_process(p) + for_each_process(p) { + /* Avoid potential softlockup warning */ + if ((++i & 1023) == 0) + touch_softlockup_watchdog(); dump_task(p, oc); + } rcu_read_unlock(); } } diff --git a/mm/page-writeback.c b/mm/page-writeback.c index fcd4c1439cb9..bfb3f903bb6d 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -543,8 +543,8 @@ static int dirty_ratio_handler(const struct ctl_table *table, int write, void *b ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write && vm_dirty_ratio != old_ratio) { - writeback_set_ratelimit(); vm_dirty_bytes = 0; + writeback_set_ratelimit(); } return ret; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index de65e8b4f75f..752576749db9 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -872,9 +872,7 @@ static inline bool page_expected_state(struct page *page, #ifdef CONFIG_MEMCG page->memcg_data | #endif -#ifdef CONFIG_PAGE_POOL - ((page->pp_magic & ~0x3UL) == PP_SIGNATURE) | -#endif + page_pool_page_is_pp(page) | (page->flags & check_flags))) return false; @@ -901,10 +899,8 @@ static const char *page_bad_reason(struct page *page, unsigned long flags) if (unlikely(page->memcg_data)) bad_reason = "page still charged to cgroup"; #endif -#ifdef CONFIG_PAGE_POOL - if (unlikely((page->pp_magic & ~0x3UL) == PP_SIGNATURE)) + if (unlikely(page_pool_page_is_pp(page))) bad_reason = "page_pool leak"; -#endif return bad_reason; } @@ -1907,13 +1903,12 @@ static inline bool boost_watermark(struct zone *zone) * can claim the whole pageblock for the requested migratetype. If not, we check * the pageblock for constituent pages; if at least half of the pages are free * or compatible, we can still claim the whole block, so pages freed in the - * future will be put on the correct free list. Otherwise, we isolate exactly - * the order we need from the fallback block and leave its migratetype alone. + * future will be put on the correct free list. */ static struct page * -steal_suitable_fallback(struct zone *zone, struct page *page, - int current_order, int order, int start_type, - unsigned int alloc_flags, bool whole_block) +try_to_steal_block(struct zone *zone, struct page *page, + int current_order, int order, int start_type, + unsigned int alloc_flags) { int free_pages, movable_pages, alike_pages; unsigned long start_pfn; @@ -1926,7 +1921,7 @@ steal_suitable_fallback(struct zone *zone, struct page *page, * highatomic accounting. */ if (is_migrate_highatomic(block_type)) - goto single_page; + return NULL; /* Take ownership for orders >= pageblock_order */ if (current_order >= pageblock_order) { @@ -1947,14 +1942,10 @@ steal_suitable_fallback(struct zone *zone, struct page *page, if (boost_watermark(zone) && (alloc_flags & ALLOC_KSWAPD)) set_bit(ZONE_BOOSTED_WATERMARK, &zone->flags); - /* We are not allowed to try stealing from the whole block */ - if (!whole_block) - goto single_page; - /* moving whole block can fail due to zone boundary conditions */ if (!prep_move_freepages_block(zone, page, &start_pfn, &free_pages, &movable_pages)) - goto single_page; + return NULL; /* * Determine how many pages are compatible with our allocation. @@ -1987,9 +1978,7 @@ steal_suitable_fallback(struct zone *zone, struct page *page, return __rmqueue_smallest(zone, order, start_type); } -single_page: - page_del_and_expand(zone, page, order, current_order, block_type); - return page; + return NULL; } /* @@ -2171,17 +2160,15 @@ static bool unreserve_highatomic_pageblock(const struct alloc_context *ac, } /* - * Try finding a free buddy page on the fallback list and put it on the free - * list of requested migratetype, possibly along with other pages from the same - * block, depending on fragmentation avoidance heuristics. Returns true if - * fallback was found so that __rmqueue_smallest() can grab it. + * Try to allocate from some fallback migratetype by claiming the entire block, + * i.e. converting it to the allocation's start migratetype. * * The use of signed ints for order and current_order is a deliberate * deviation from the rest of this file, to make the for loop * condition simpler. */ static __always_inline struct page * -__rmqueue_fallback(struct zone *zone, int order, int start_migratetype, +__rmqueue_claim(struct zone *zone, int order, int start_migratetype, unsigned int alloc_flags) { struct free_area *area; @@ -2212,58 +2199,66 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype, if (fallback_mt == -1) continue; - /* - * We cannot steal all free pages from the pageblock and the - * requested migratetype is movable. In that case it's better to - * steal and split the smallest available page instead of the - * largest available page, because even if the next movable - * allocation falls back into a different pageblock than this - * one, it won't cause permanent fragmentation. - */ - if (!can_steal && start_migratetype == MIGRATE_MOVABLE - && current_order > order) - goto find_smallest; + if (!can_steal) + break; - goto do_steal; + page = get_page_from_free_area(area, fallback_mt); + page = try_to_steal_block(zone, page, current_order, order, + start_migratetype, alloc_flags); + if (page) { + trace_mm_page_alloc_extfrag(page, order, current_order, + start_migratetype, fallback_mt); + return page; + } } return NULL; +} + +/* + * Try to steal a single page from some fallback migratetype. Leave the rest of + * the block as its current migratetype, potentially causing fragmentation. + */ +static __always_inline struct page * +__rmqueue_steal(struct zone *zone, int order, int start_migratetype) +{ + struct free_area *area; + int current_order; + struct page *page; + int fallback_mt; + bool can_steal; -find_smallest: for (current_order = order; current_order < NR_PAGE_ORDERS; current_order++) { area = &(zone->free_area[current_order]); fallback_mt = find_suitable_fallback(area, current_order, start_migratetype, false, &can_steal); - if (fallback_mt != -1) - break; - } - - /* - * This should not happen - we already found a suitable fallback - * when looking for the largest page. - */ - VM_BUG_ON(current_order > MAX_PAGE_ORDER); - -do_steal: - page = get_page_from_free_area(area, fallback_mt); - - /* take off list, maybe claim block, expand remainder */ - page = steal_suitable_fallback(zone, page, current_order, order, - start_migratetype, alloc_flags, can_steal); + if (fallback_mt == -1) + continue; - trace_mm_page_alloc_extfrag(page, order, current_order, - start_migratetype, fallback_mt); + page = get_page_from_free_area(area, fallback_mt); + page_del_and_expand(zone, page, order, current_order, fallback_mt); + trace_mm_page_alloc_extfrag(page, order, current_order, + start_migratetype, fallback_mt); + return page; + } - return page; + return NULL; } +enum rmqueue_mode { + RMQUEUE_NORMAL, + RMQUEUE_CMA, + RMQUEUE_CLAIM, + RMQUEUE_STEAL, +}; + /* * Do the hard work of removing an element from the buddy allocator. * Call me with the zone->lock already held. */ static __always_inline struct page * __rmqueue(struct zone *zone, unsigned int order, int migratetype, - unsigned int alloc_flags) + unsigned int alloc_flags, enum rmqueue_mode *mode) { struct page *page; @@ -2282,16 +2277,49 @@ __rmqueue(struct zone *zone, unsigned int order, int migratetype, } } - page = __rmqueue_smallest(zone, order, migratetype); - if (unlikely(!page)) { - if (alloc_flags & ALLOC_CMA) + /* + * First try the freelists of the requested migratetype, then try + * fallbacks modes with increasing levels of fragmentation risk. + * + * The fallback logic is expensive and rmqueue_bulk() calls in + * a loop with the zone->lock held, meaning the freelists are + * not subject to any outside changes. Remember in *mode where + * we found pay dirt, to save us the search on the next call. + */ + switch (*mode) { + case RMQUEUE_NORMAL: + page = __rmqueue_smallest(zone, order, migratetype); + if (page) + return page; + fallthrough; + case RMQUEUE_CMA: + if (alloc_flags & ALLOC_CMA) { page = __rmqueue_cma_fallback(zone, order); - - if (!page) - page = __rmqueue_fallback(zone, order, migratetype, - alloc_flags); + if (page) { + *mode = RMQUEUE_CMA; + return page; + } + } + fallthrough; + case RMQUEUE_CLAIM: + page = __rmqueue_claim(zone, order, migratetype, alloc_flags); + if (page) { + /* Replenished preferred freelist, back to normal mode. */ + *mode = RMQUEUE_NORMAL; + return page; + } + fallthrough; + case RMQUEUE_STEAL: + if (!(alloc_flags & ALLOC_NOFRAGMENT)) { + page = __rmqueue_steal(zone, order, migratetype); + if (page) { + *mode = RMQUEUE_STEAL; + return page; + } + } } - return page; + + return NULL; } /* @@ -2303,13 +2331,14 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, unsigned long count, struct list_head *list, int migratetype, unsigned int alloc_flags) { + enum rmqueue_mode rmqm = RMQUEUE_NORMAL; unsigned long flags; int i; spin_lock_irqsave(&zone->lock, flags); for (i = 0; i < count; ++i) { struct page *page = __rmqueue(zone, order, migratetype, - alloc_flags); + alloc_flags, &rmqm); if (unlikely(page == NULL)) break; @@ -2910,7 +2939,9 @@ struct page *rmqueue_buddy(struct zone *preferred_zone, struct zone *zone, if (alloc_flags & ALLOC_HIGHATOMIC) page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC); if (!page) { - page = __rmqueue(zone, order, migratetype, alloc_flags); + enum rmqueue_mode rmqm = RMQUEUE_NORMAL; + + page = __rmqueue(zone, order, migratetype, alloc_flags, &rmqm); /* * If the allocation fails, allow OOM handling and @@ -4243,6 +4274,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, restart: compaction_retries = 0; no_progress_loops = 0; + compact_result = COMPACT_SKIPPED; compact_priority = DEF_COMPACT_PRIORITY; cpuset_mems_cookie = read_mems_allowed_begin(); zonelist_iter_cookie = zonelist_iter_begin(); @@ -4345,6 +4377,14 @@ restart: } retry: + /* + * Deal with possible cpuset update races or zonelist updates to avoid + * infinite retries. + */ + if (check_retry_cpuset(cpuset_mems_cookie, ac) || + check_retry_zonelist(zonelist_iter_cookie)) + goto restart; + /* Ensure kswapd doesn't accidentally go to sleep as long as we loop */ if (alloc_flags & ALLOC_KSWAPD) wake_all_kswapds(order, gfp_mask, ac); @@ -5991,11 +6031,10 @@ static void setup_per_zone_lowmem_reserve(void) for (j = i + 1; j < MAX_NR_ZONES; j++) { struct zone *upper_zone = &pgdat->node_zones[j]; - bool empty = !zone_managed_pages(upper_zone); managed_pages += zone_managed_pages(upper_zone); - if (clear || empty) + if (clear) zone->lowmem_reserve[j] = 0; else zone->lowmem_reserve[j] = managed_pages / ratio; @@ -7006,9 +7045,6 @@ bool has_managed_dma(void) #ifdef CONFIG_UNACCEPTED_MEMORY -/* Counts number of zones with unaccepted pages. */ -static DEFINE_STATIC_KEY_FALSE(zones_with_unaccepted_pages); - static bool lazy_accept = true; static int __init accept_memory_parse(char *p) @@ -7035,11 +7071,7 @@ static bool page_contains_unaccepted(struct page *page, unsigned int order) static void __accept_page(struct zone *zone, unsigned long *flags, struct page *page) { - bool last; - list_del(&page->lru); - last = list_empty(&zone->unaccepted_pages); - account_freepages(zone, -MAX_ORDER_NR_PAGES, MIGRATE_MOVABLE); __mod_zone_page_state(zone, NR_UNACCEPTED, -MAX_ORDER_NR_PAGES); __ClearPageUnaccepted(page); @@ -7048,9 +7080,6 @@ static void __accept_page(struct zone *zone, unsigned long *flags, accept_memory(page_to_phys(page), PAGE_SIZE << MAX_PAGE_ORDER); __free_pages_ok(page, MAX_PAGE_ORDER, FPI_TO_TAIL); - - if (last) - static_branch_dec(&zones_with_unaccepted_pages); } void accept_page(struct page *page) @@ -7087,24 +7116,26 @@ static bool try_to_accept_memory_one(struct zone *zone) return true; } -static inline bool has_unaccepted_memory(void) -{ - return static_branch_unlikely(&zones_with_unaccepted_pages); -} - static bool cond_accept_memory(struct zone *zone, unsigned int order) { - long to_accept; + long to_accept, wmark; bool ret = false; - if (!has_unaccepted_memory()) - return false; - if (list_empty(&zone->unaccepted_pages)) return false; + wmark = promo_wmark_pages(zone); + + /* + * Watermarks have not been initialized yet. + * + * Accepting one MAX_ORDER page to ensure progress. + */ + if (!wmark) + return try_to_accept_memory_one(zone); + /* How much to accept to get to promo watermark? */ - to_accept = promo_wmark_pages(zone) - + to_accept = wmark - (zone_page_state(zone, NR_FREE_PAGES) - __zone_watermark_unusable_free(zone, order, 0) - zone_page_state(zone, NR_UNACCEPTED)); @@ -7123,22 +7154,17 @@ static bool __free_unaccepted(struct page *page) { struct zone *zone = page_zone(page); unsigned long flags; - bool first = false; if (!lazy_accept) return false; spin_lock_irqsave(&zone->lock, flags); - first = list_empty(&zone->unaccepted_pages); list_add_tail(&page->lru, &zone->unaccepted_pages); account_freepages(zone, MAX_ORDER_NR_PAGES, MIGRATE_MOVABLE); __mod_zone_page_state(zone, NR_UNACCEPTED, MAX_ORDER_NR_PAGES); __SetPageUnaccepted(page); spin_unlock_irqrestore(&zone->lock, flags); - if (first) - static_branch_inc(&zones_with_unaccepted_pages); - return true; } diff --git a/mm/page_isolation.c b/mm/page_isolation.c index 7e04047977cf..6989c5ffd474 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -612,6 +612,16 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn, int ret; /* + * Due to the deferred freeing of hugetlb folios, the hugepage folios may + * not immediately release to the buddy system. This can cause PageBuddy() + * to fail in __test_page_isolated_in_pageblock(). To ensure that the + * hugetlb folios are properly released back to the buddy system, we + * invoke the wait_for_freed_hugetlb_folios() function to wait for the + * release to complete. + */ + wait_for_freed_hugetlb_folios(); + + /* * Note: pageblock_nr_pages != MAX_PAGE_ORDER. Then, chunks of free * pages are not aligned to pageblock_nr_pages. * Then we just check migratetype first. diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index ae5cc42aa208..585a53f7b06f 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -77,6 +77,7 @@ static bool map_pte(struct page_vma_mapped_walk *pvmw, spinlock_t **ptlp) * mapped at the @pvmw->pte * @pvmw: page_vma_mapped_walk struct, includes a pair pte and pfn range * for checking + * @pte_nr: the number of small pages described by @pvmw->pte. * * page_vma_mapped_walk() found a place where pfn range is *potentially* * mapped. check_pte() has to validate this. @@ -93,7 +94,7 @@ static bool map_pte(struct page_vma_mapped_walk *pvmw, spinlock_t **ptlp) * Otherwise, return false. * */ -static bool check_pte(struct page_vma_mapped_walk *pvmw) +static bool check_pte(struct page_vma_mapped_walk *pvmw, unsigned long pte_nr) { unsigned long pfn; pte_t ptent = ptep_get(pvmw->pte); @@ -126,7 +127,11 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw) pfn = pte_pfn(ptent); } - return (pfn - pvmw->pfn) < pvmw->nr_pages; + if ((pfn + pte_nr - 1) < pvmw->pfn) + return false; + if (pfn > (pvmw->pfn + pvmw->nr_pages - 1)) + return false; + return true; } /* Returns true if the two ranges overlap. Careful to not overflow. */ @@ -201,7 +206,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) return false; pvmw->ptl = huge_pte_lock(hstate, mm, pvmw->pte); - if (!check_pte(pvmw)) + if (!check_pte(pvmw, pages_per_huge_page(hstate))) return not_found(pvmw); return true; } @@ -284,7 +289,7 @@ restart: goto next_pte; } this_pte: - if (check_pte(pvmw)) + if (check_pte(pvmw, 1)) return true; next_pte: do { diff --git a/mm/ptdump.c b/mm/ptdump.c index 106e1d66e9f9..3e78bf33da42 100644 --- a/mm/ptdump.c +++ b/mm/ptdump.c @@ -153,6 +153,7 @@ void ptdump_walk_pgd(struct ptdump_state *st, struct mm_struct *mm, pgd_t *pgd) { const struct ptdump_range *range = st->range; + get_online_mems(); mmap_write_lock(mm); while (range->start != range->end) { walk_page_range_novma(mm, range->start, range->end, @@ -160,6 +161,7 @@ void ptdump_walk_pgd(struct ptdump_state *st, struct mm_struct *mm, pgd_t *pgd) range++; } mmap_write_unlock(mm); + put_online_mems(); /* Flush out the last page */ st->note_page(st, 0, -1, 0); diff --git a/mm/rmap.c b/mm/rmap.c index 73d5998677d4..674362de029d 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -2488,7 +2488,7 @@ static bool folio_make_device_exclusive(struct folio *folio, * Restrict to anonymous folios for now to avoid potential writeback * issues. */ - if (!folio_test_anon(folio)) + if (!folio_test_anon(folio) || folio_test_hugetlb(folio)) return false; rmap_walk(folio, &rwc); diff --git a/mm/secretmem.c b/mm/secretmem.c index 399552814fd0..4662f2510ae5 100644 --- a/mm/secretmem.c +++ b/mm/secretmem.c @@ -195,19 +195,11 @@ static struct file *secretmem_file_create(unsigned long flags) struct file *file; struct inode *inode; const char *anon_name = "[secretmem]"; - const struct qstr qname = QSTR_INIT(anon_name, strlen(anon_name)); - int err; - inode = alloc_anon_inode(secretmem_mnt->mnt_sb); + inode = anon_inode_make_secure_inode(secretmem_mnt->mnt_sb, anon_name, NULL); if (IS_ERR(inode)) return ERR_CAST(inode); - err = security_inode_init_security_anon(inode, &qname, NULL); - if (err) { - file = ERR_PTR(err); - goto err_free_inode; - } - file = alloc_file_pseudo(inode, secretmem_mnt, "secretmem", O_RDWR, &secretmem_fops); if (IS_ERR(file)) diff --git a/mm/shmem.c b/mm/shmem.c index dd4eb11c84b5..88fd6e2a2dcf 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -3042,8 +3042,7 @@ shmem_write_begin(struct file *file, struct address_space *mapping, if (ret) return ret; - if (folio_test_hwpoison(folio) || - (folio_test_large(folio) && folio_test_has_hwpoisoned(folio))) { + if (folio_contain_hwpoisoned_page(folio)) { folio_unlock(folio); folio_put(folio); return -EIO; @@ -3700,7 +3699,7 @@ static int shmem_unlink(struct inode *dir, struct dentry *dentry) static int shmem_rmdir(struct inode *dir, struct dentry *dentry) { - if (!simple_offset_empty(dentry)) + if (!simple_empty(dentry)) return -ENOTEMPTY; drop_nlink(d_inode(dentry)); @@ -3757,7 +3756,7 @@ static int shmem_rename2(struct mnt_idmap *idmap, return simple_offset_rename_exchange(old_dir, old_dentry, new_dir, new_dentry); - if (!simple_offset_empty(new_dentry)) + if (!simple_empty(new_dentry)) return -ENOTEMPTY; if (flags & RENAME_WHITEOUT) { diff --git a/mm/slub.c b/mm/slub.c index b9447a955f61..dc527b59f5a9 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1960,6 +1960,11 @@ static inline void handle_failed_objexts_alloc(unsigned long obj_exts, #define OBJCGS_CLEAR_MASK (__GFP_DMA | __GFP_RECLAIMABLE | \ __GFP_ACCOUNT | __GFP_NOFAIL) +static inline void init_slab_obj_exts(struct slab *slab) +{ + slab->obj_exts = 0; +} + int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s, gfp_t gfp, bool new_slab) { @@ -2030,20 +2035,12 @@ static inline void free_slab_obj_exts(struct slab *slab) slab->obj_exts = 0; } -static inline bool need_slab_obj_ext(void) -{ - if (mem_alloc_profiling_enabled()) - return true; +#else /* CONFIG_SLAB_OBJ_EXT */ - /* - * CONFIG_MEMCG creates vector of obj_cgroup objects conditionally - * inside memcg_slab_post_alloc_hook. No other users for now. - */ - return false; +static inline void init_slab_obj_exts(struct slab *slab) +{ } -#else /* CONFIG_SLAB_OBJ_EXT */ - static int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s, gfp_t gfp, bool new_slab) { @@ -2054,11 +2051,6 @@ static inline void free_slab_obj_exts(struct slab *slab) { } -static inline bool need_slab_obj_ext(void) -{ - return false; -} - #endif /* CONFIG_SLAB_OBJ_EXT */ #ifdef CONFIG_MEM_ALLOC_PROFILING @@ -2090,7 +2082,7 @@ prepare_slab_obj_exts_hook(struct kmem_cache *s, gfp_t flags, void *p) static inline void alloc_tagging_slab_alloc_hook(struct kmem_cache *s, void *object, gfp_t flags) { - if (need_slab_obj_ext()) { + if (mem_alloc_profiling_enabled()) { struct slabobj_ext *obj_exts; obj_exts = prepare_slab_obj_exts_hook(s, flags, object); @@ -2568,8 +2560,12 @@ static __always_inline void account_slab(struct slab *slab, int order, static __always_inline void unaccount_slab(struct slab *slab, int order, struct kmem_cache *s) { - if (memcg_kmem_online() || need_slab_obj_ext()) - free_slab_obj_exts(slab); + /* + * The slab object extensions should now be freed regardless of + * whether mem_alloc_profiling_enabled() or not because profiling + * might have been disabled after slab->obj_exts got allocated. + */ + free_slab_obj_exts(slab); mod_node_page_state(slab_pgdat(slab), cache_vmstat_idx(s), -(PAGE_SIZE << order)); @@ -2613,6 +2609,7 @@ static struct slab *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) slab->objects = oo_objects(oo); slab->inuse = 0; slab->frozen = 0; + init_slab_obj_exts(slab); account_slab(slab, oo_order(oo), s, flags); @@ -4228,7 +4225,12 @@ static void *___kmalloc_large_node(size_t size, gfp_t flags, int node) flags = kmalloc_fix_flags(flags); flags |= __GFP_COMP; - folio = (struct folio *)alloc_pages_node_noprof(node, flags, order); + + if (node == NUMA_NO_NODE) + folio = (struct folio *)alloc_pages_noprof(flags, order); + else + folio = (struct folio *)__alloc_pages_noprof(flags, order, node, NULL); + if (folio) { ptr = folio_address(folio); lruvec_stat_mod_folio(folio, NR_SLAB_UNRECLAIMABLE_B, diff --git a/mm/swapfile.c b/mm/swapfile.c index b0a9071cfe1d..c02493d9c7be 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -3237,43 +3237,30 @@ static unsigned long read_swap_header(struct swap_info_struct *si, #define SWAP_CLUSTER_COLS \ max_t(unsigned int, SWAP_CLUSTER_INFO_COLS, SWAP_CLUSTER_SPACE_COLS) -static int setup_swap_map_and_extents(struct swap_info_struct *si, - union swap_header *swap_header, - unsigned char *swap_map, - unsigned long maxpages, - sector_t *span) +static int setup_swap_map(struct swap_info_struct *si, + union swap_header *swap_header, + unsigned char *swap_map, + unsigned long maxpages) { - unsigned int nr_good_pages; unsigned long i; - int nr_extents; - - nr_good_pages = maxpages - 1; /* omit header page */ + swap_map[0] = SWAP_MAP_BAD; /* omit header page */ for (i = 0; i < swap_header->info.nr_badpages; i++) { unsigned int page_nr = swap_header->info.badpages[i]; if (page_nr == 0 || page_nr > swap_header->info.last_page) return -EINVAL; if (page_nr < maxpages) { swap_map[page_nr] = SWAP_MAP_BAD; - nr_good_pages--; + si->pages--; } } - if (nr_good_pages) { - swap_map[0] = SWAP_MAP_BAD; - si->max = maxpages; - si->pages = nr_good_pages; - nr_extents = setup_swap_extents(si, span); - if (nr_extents < 0) - return nr_extents; - nr_good_pages = si->pages; - } - if (!nr_good_pages) { + if (!si->pages) { pr_warn("Empty swap-file\n"); return -EINVAL; } - return nr_extents; + return 0; } static struct swap_cluster_info *setup_clusters(struct swap_info_struct *si, @@ -3318,13 +3305,17 @@ static struct swap_cluster_info *setup_clusters(struct swap_info_struct *si, * Mark unusable pages as unavailable. The clusters aren't * marked free yet, so no list operations are involved yet. * - * See setup_swap_map_and_extents(): header page, bad pages, + * See setup_swap_map(): header page, bad pages, * and the EOF part of the last cluster. */ inc_cluster_info_page(si, cluster_info, 0); - for (i = 0; i < swap_header->info.nr_badpages; i++) - inc_cluster_info_page(si, cluster_info, - swap_header->info.badpages[i]); + for (i = 0; i < swap_header->info.nr_badpages; i++) { + unsigned int page_nr = swap_header->info.badpages[i]; + + if (page_nr >= maxpages) + continue; + inc_cluster_info_page(si, cluster_info, page_nr); + } for (i = maxpages; i < round_up(maxpages, SWAPFILE_CLUSTER); i++) inc_cluster_info_page(si, cluster_info, i); @@ -3456,6 +3447,21 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) goto bad_swap_unlock_inode; } + si->max = maxpages; + si->pages = maxpages - 1; + nr_extents = setup_swap_extents(si, &span); + if (nr_extents < 0) { + error = nr_extents; + goto bad_swap_unlock_inode; + } + if (si->pages != si->max - 1) { + pr_err("swap:%u != (max:%u - 1)\n", si->pages, si->max); + error = -EINVAL; + goto bad_swap_unlock_inode; + } + + maxpages = si->max; + /* OK, set up the swap map and apply the bad block list */ swap_map = vzalloc(maxpages); if (!swap_map) { @@ -3467,12 +3473,9 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) if (error) goto bad_swap_unlock_inode; - nr_extents = setup_swap_map_and_extents(si, swap_header, swap_map, - maxpages, &span); - if (unlikely(nr_extents < 0)) { - error = nr_extents; + error = setup_swap_map(si, swap_header, swap_map, maxpages); + if (error) goto bad_swap_unlock_inode; - } /* * Use kvmalloc_array instead of bitmap_zalloc as the allocation order might diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index ce13c4062647..8b0f2fbd6a75 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -18,6 +18,7 @@ #include <asm/tlbflush.h> #include <asm/tlb.h> #include "internal.h" +#include "swap.h" static __always_inline bool validate_dst_vma(struct vm_area_struct *dst_vma, unsigned long dst_end) @@ -1058,8 +1059,13 @@ static int move_present_pte(struct mm_struct *mm, src_folio->index = linear_page_index(dst_vma, dst_addr); orig_dst_pte = mk_pte(&src_folio->page, dst_vma->vm_page_prot); - /* Follow mremap() behavior and treat the entry dirty after the move */ - orig_dst_pte = pte_mkwrite(pte_mkdirty(orig_dst_pte), dst_vma); + /* Set soft dirty bit so userspace can notice the pte was moved */ +#ifdef CONFIG_MEM_SOFT_DIRTY + orig_dst_pte = pte_mksoft_dirty(orig_dst_pte); +#endif + if (pte_dirty(orig_src_pte)) + orig_dst_pte = pte_mkdirty(orig_dst_pte); + orig_dst_pte = pte_mkwrite(orig_dst_pte, dst_vma); set_pte_at(mm, dst_addr, dst_pte, orig_dst_pte); out: @@ -1067,14 +1073,22 @@ out: return err; } -static int move_swap_pte(struct mm_struct *mm, +static int move_swap_pte(struct mm_struct *mm, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, pte_t *dst_pte, pte_t *src_pte, pte_t orig_dst_pte, pte_t orig_src_pte, - spinlock_t *dst_ptl, spinlock_t *src_ptl) + spinlock_t *dst_ptl, spinlock_t *src_ptl, + struct folio *src_folio, + struct swap_info_struct *si, swp_entry_t entry) { - if (!pte_swp_exclusive(orig_src_pte)) - return -EBUSY; + /* + * Check if the folio still belongs to the target swap entry after + * acquiring the lock. Folio can be freed in the swap cache while + * not locked. + */ + if (src_folio && unlikely(!folio_test_swapcache(src_folio) || + entry.val != src_folio->swap.val)) + return -EAGAIN; double_pt_lock(dst_ptl, src_ptl); @@ -1084,7 +1098,39 @@ static int move_swap_pte(struct mm_struct *mm, return -EAGAIN; } + /* + * The src_folio resides in the swapcache, requiring an update to its + * index and mapping to align with the dst_vma, where a swap-in may + * occur and hit the swapcache after moving the PTE. + */ + if (src_folio) { + folio_move_anon_rmap(src_folio, dst_vma); + src_folio->index = linear_page_index(dst_vma, dst_addr); + } else { + /* + * Check if the swap entry is cached after acquiring the src_pte + * lock. Otherwise, we might miss a newly loaded swap cache folio. + * + * Check swap_map directly to minimize overhead, READ_ONCE is sufficient. + * We are trying to catch newly added swap cache, the only possible case is + * when a folio is swapped in and out again staying in swap cache, using the + * same entry before the PTE check above. The PTL is acquired and released + * twice, each time after updating the swap_map's flag. So holding + * the PTL here ensures we see the updated value. False positive is possible, + * e.g. SWP_SYNCHRONOUS_IO swapin may set the flag without touching the + * cache, or during the tiny synchronization window between swap cache and + * swap_map, but it will be gone very quickly, worst result is retry jitters. + */ + if (READ_ONCE(si->swap_map[swp_offset(entry)]) & SWAP_HAS_CACHE) { + double_pt_unlock(dst_ptl, src_ptl); + return -EAGAIN; + } + } + orig_src_pte = ptep_get_and_clear(mm, src_addr, src_pte); +#ifdef CONFIG_MEM_SOFT_DIRTY + orig_src_pte = pte_swp_mksoft_dirty(orig_src_pte); +#endif set_pte_at(mm, dst_addr, dst_pte, orig_src_pte); double_pt_unlock(dst_ptl, src_ptl); @@ -1130,6 +1176,7 @@ static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, __u64 mode) { swp_entry_t entry; + struct swap_info_struct *si = NULL; pte_t orig_src_pte, orig_dst_pte; pte_t src_folio_pte; spinlock_t *src_ptl, *dst_ptl; @@ -1215,6 +1262,7 @@ retry: */ if (!src_folio) { struct folio *folio; + bool locked; /* * Pin the page while holding the lock to be sure the @@ -1234,14 +1282,28 @@ retry: goto out; } + locked = folio_trylock(folio); + /* + * We avoid waiting for folio lock with a raised + * refcount for large folios because extra refcounts + * will result in split_folio() failing later and + * retrying. If multiple tasks are trying to move a + * large folio we can end up livelocking. + */ + if (!locked && folio_test_large(folio)) { + spin_unlock(src_ptl); + err = -EAGAIN; + goto out; + } + folio_get(folio); src_folio = folio; src_folio_pte = orig_src_pte; spin_unlock(src_ptl); - if (!folio_trylock(src_folio)) { - pte_unmap(&orig_src_pte); - pte_unmap(&orig_dst_pte); + if (!locked) { + pte_unmap(src_pte); + pte_unmap(dst_pte); src_pte = dst_pte = NULL; /* now we can block and wait */ folio_lock(src_folio); @@ -1257,8 +1319,8 @@ retry: /* at this point we have src_folio locked */ if (folio_test_large(src_folio)) { /* split_folio() can block */ - pte_unmap(&orig_src_pte); - pte_unmap(&orig_dst_pte); + pte_unmap(src_pte); + pte_unmap(dst_pte); src_pte = dst_pte = NULL; err = split_folio(src_folio); if (err) @@ -1283,8 +1345,8 @@ retry: goto out; } if (!anon_vma_trylock_write(src_anon_vma)) { - pte_unmap(&orig_src_pte); - pte_unmap(&orig_dst_pte); + pte_unmap(src_pte); + pte_unmap(dst_pte); src_pte = dst_pte = NULL; /* now we can block and wait */ anon_vma_lock_write(src_anon_vma); @@ -1297,11 +1359,13 @@ retry: orig_dst_pte, orig_src_pte, dst_ptl, src_ptl, src_folio); } else { + struct folio *folio = NULL; + entry = pte_to_swp_entry(orig_src_pte); if (non_swap_entry(entry)) { if (is_migration_entry(entry)) { - pte_unmap(&orig_src_pte); - pte_unmap(&orig_dst_pte); + pte_unmap(src_pte); + pte_unmap(dst_pte); src_pte = dst_pte = NULL; migration_entry_wait(mm, src_pmd, src_addr); err = -EAGAIN; @@ -1310,10 +1374,53 @@ retry: goto out; } - err = move_swap_pte(mm, dst_addr, src_addr, - dst_pte, src_pte, - orig_dst_pte, orig_src_pte, - dst_ptl, src_ptl); + if (!pte_swp_exclusive(orig_src_pte)) { + err = -EBUSY; + goto out; + } + + si = get_swap_device(entry); + if (unlikely(!si)) { + err = -EAGAIN; + goto out; + } + /* + * Verify the existence of the swapcache. If present, the folio's + * index and mapping must be updated even when the PTE is a swap + * entry. The anon_vma lock is not taken during this process since + * the folio has already been unmapped, and the swap entry is + * exclusive, preventing rmap walks. + * + * For large folios, return -EBUSY immediately, as split_folio() + * also returns -EBUSY when attempting to split unmapped large + * folios in the swapcache. This issue needs to be resolved + * separately to allow proper handling. + */ + if (!src_folio) + folio = filemap_get_folio(swap_address_space(entry), + swap_cache_index(entry)); + if (!IS_ERR_OR_NULL(folio)) { + if (folio_test_large(folio)) { + err = -EBUSY; + folio_put(folio); + goto out; + } + src_folio = folio; + src_folio_pte = orig_src_pte; + if (!folio_trylock(src_folio)) { + pte_unmap(src_pte); + pte_unmap(dst_pte); + src_pte = dst_pte = NULL; + put_swap_device(si); + si = NULL; + /* now we can block and wait */ + folio_lock(src_folio); + goto retry; + } + } + err = move_swap_pte(mm, dst_vma, dst_addr, src_addr, dst_pte, src_pte, + orig_dst_pte, orig_src_pte, + dst_ptl, src_ptl, src_folio, si, entry); } out: @@ -1330,6 +1437,8 @@ out: if (src_pte) pte_unmap(src_pte); mmu_notifier_invalidate_range_end(&range); + if (si) + put_swap_device(si); return err; } @@ -1691,13 +1800,16 @@ ssize_t move_pages(struct userfaultfd_ctx *ctx, unsigned long dst_start, /* Check if we can move the pmd without splitting it. */ if (move_splits_huge_pmd(dst_addr, src_addr, src_start + len) || !pmd_none(dst_pmdval)) { - struct folio *folio = pmd_folio(*src_pmd); - - if (!folio || (!is_huge_zero_folio(folio) && - !PageAnonExclusive(&folio->page))) { - spin_unlock(ptl); - err = -EBUSY; - break; + /* Can be a migration entry */ + if (pmd_present(*src_pmd)) { + struct folio *folio = pmd_folio(*src_pmd); + + if (!is_huge_zero_folio(folio) && + !PageAnonExclusive(&folio->page)) { + spin_unlock(ptl); + err = -EBUSY; + break; + } } spin_unlock(ptl); @@ -1801,6 +1913,14 @@ struct vm_area_struct *userfaultfd_clear_vma(struct vma_iterator *vmi, unsigned long end) { struct vm_area_struct *ret; + bool give_up_on_oom = false; + + /* + * If we are modifying only and not splitting, just give up on the merge + * if OOM prevents us from merging successfully. + */ + if (start == vma->vm_start && end == vma->vm_end) + give_up_on_oom = true; /* Reset ptes for the whole vma range if wr-protected */ if (userfaultfd_wp(vma)) @@ -1808,7 +1928,7 @@ struct vm_area_struct *userfaultfd_clear_vma(struct vma_iterator *vmi, ret = vma_modify_flags_uffd(vmi, prev, vma, start, end, vma->vm_flags & ~__VM_UFFD_FLAGS, - NULL_VM_UFFD_CTX); + NULL_VM_UFFD_CTX, give_up_on_oom); /* * In the vma_merge() successful mprotect-like case 8: @@ -1859,7 +1979,8 @@ int userfaultfd_register_range(struct userfaultfd_ctx *ctx, new_flags = (vma->vm_flags & ~__VM_UFFD_FLAGS) | vm_flags; vma = vma_modify_flags_uffd(&vmi, prev, vma, start, vma_end, new_flags, - (struct vm_userfaultfd_ctx){ctx}); + (struct vm_userfaultfd_ctx){ctx}, + /* give_up_on_oom = */false); if (IS_ERR(vma)) return PTR_ERR(vma); @@ -416,7 +416,14 @@ static int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, init_vma_prep(&vp, vma); vp.insert = new; vma_prepare(&vp); + + /* + * Get rid of huge pages and shared page tables straddling the split + * boundary. + */ vma_adjust_trans_huge(vma, vma->vm_start, addr, 0); + if (is_vm_hugetlb_page(vma)) + hugetlb_split(vma, addr); if (new_below) { vma->vm_start = addr; @@ -829,9 +836,6 @@ static struct vm_area_struct *vma_merge_existing_range(struct vma_merge_struct * err = dup_anon_vma(next, vma, &anon_dup); } - if (err) - goto abort; - /* * In nearly all cases, we expand vmg->vma. There is one exception - * merge_right where we partially span the VMA. In this case we shrink @@ -839,16 +843,11 @@ static struct vm_area_struct *vma_merge_existing_range(struct vma_merge_struct * */ expanded = !merge_right || merge_will_delete_vma; - if (commit_merge(vmg, adjust, - merge_will_delete_vma ? vma : NULL, - merge_will_delete_next ? next : NULL, - adj_start, expanded)) { - if (anon_dup) - unlink_anon_vmas(anon_dup); - - vmg->state = VMA_MERGE_ERROR_NOMEM; - return NULL; - } + if (err || commit_merge(vmg, adjust, + merge_will_delete_vma ? vma : NULL, + merge_will_delete_next ? next : NULL, + adj_start, expanded)) + goto abort; res = merge_left ? prev : next; khugepaged_enter_vma(res, vmg->flags); @@ -859,7 +858,18 @@ static struct vm_area_struct *vma_merge_existing_range(struct vma_merge_struct * abort: vma_iter_set(vmg->vmi, start); vma_iter_load(vmg->vmi); - vmg->state = VMA_MERGE_ERROR_NOMEM; + + if (anon_dup) + unlink_anon_vmas(anon_dup); + + /* + * This means we have failed to clone anon_vma's correctly, but no + * actual changes to VMAs have occurred, so no harm no foul - if the + * user doesn't want this reported and instead just wants to give up on + * the merge, allow it. + */ + if (!vmg->give_up_on_oom) + vmg->state = VMA_MERGE_ERROR_NOMEM; return NULL; } @@ -1033,9 +1043,15 @@ int vma_expand(struct vma_merge_struct *vmg) return 0; nomem: - vmg->state = VMA_MERGE_ERROR_NOMEM; if (anon_dup) unlink_anon_vmas(anon_dup); + /* + * If the user requests that we just give upon OOM, we are safe to do so + * here, as commit merge provides this contract to us. Nothing has been + * changed - no harm no foul, just don't report it. + */ + if (!vmg->give_up_on_oom) + vmg->state = VMA_MERGE_ERROR_NOMEM; return -ENOMEM; } @@ -1417,24 +1433,35 @@ int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm, static struct vm_area_struct *vma_modify(struct vma_merge_struct *vmg) { struct vm_area_struct *vma = vmg->vma; + unsigned long start = vmg->start; + unsigned long end = vmg->end; struct vm_area_struct *merged; /* First, try to merge. */ merged = vma_merge_existing_range(vmg); if (merged) return merged; + if (vmg_nomem(vmg)) + return ERR_PTR(-ENOMEM); + + /* + * Split can fail for reasons other than OOM, so if the user requests + * this it's probably a mistake. + */ + VM_WARN_ON(vmg->give_up_on_oom && + (vma->vm_start != start || vma->vm_end != end)); /* Split any preceding portion of the VMA. */ - if (vma->vm_start < vmg->start) { - int err = split_vma(vmg->vmi, vma, vmg->start, 1); + if (vma->vm_start < start) { + int err = split_vma(vmg->vmi, vma, start, 1); if (err) return ERR_PTR(err); } /* Split any trailing portion of the VMA. */ - if (vma->vm_end > vmg->end) { - int err = split_vma(vmg->vmi, vma, vmg->end, 0); + if (vma->vm_end > end) { + int err = split_vma(vmg->vmi, vma, end, 0); if (err) return ERR_PTR(err); @@ -1492,12 +1519,15 @@ struct vm_area_struct struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long new_flags, - struct vm_userfaultfd_ctx new_ctx) + struct vm_userfaultfd_ctx new_ctx, + bool give_up_on_oom) { VMG_VMA_STATE(vmg, vmi, prev, vma, start, end); vmg.flags = new_flags; vmg.uffd_ctx = new_ctx; + if (give_up_on_oom) + vmg.give_up_on_oom = true; return vma_modify(&vmg); } @@ -87,6 +87,12 @@ struct vma_merge_struct { struct anon_vma_name *anon_name; enum vma_merge_flags merge_flags; enum vma_merge_state state; + + /* + * If a merge is possible, but an OOM error occurs, give up and don't + * execute the merge, returning NULL. + */ + bool give_up_on_oom :1; }; static inline bool vmg_nomem(struct vma_merge_struct *vmg) @@ -303,7 +309,8 @@ struct vm_area_struct struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long new_flags, - struct vm_userfaultfd_ctx new_ctx); + struct vm_userfaultfd_ctx new_ctx, + bool give_up_on_oom); struct vm_area_struct *vma_merge_new_range(struct vma_merge_struct *vmg); diff --git a/mm/vma_internal.h b/mm/vma_internal.h index b930ab12a587..1dd119f266e6 100644 --- a/mm/vma_internal.h +++ b/mm/vma_internal.h @@ -17,6 +17,7 @@ #include <linux/file.h> #include <linux/fs.h> #include <linux/huge_mm.h> +#include <linux/hugetlb.h> #include <linux/hugetlb_inline.h> #include <linux/kernel.h> #include <linux/khugepaged.h> diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 3f9255dfacb0..3519c4e4f841 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -487,6 +487,7 @@ static int vmap_pages_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, int *nr, pgtbl_mod_mask *mask) { + int err = 0; pte_t *pte; /* @@ -500,18 +501,25 @@ static int vmap_pages_pte_range(pmd_t *pmd, unsigned long addr, do { struct page *page = pages[*nr]; - if (WARN_ON(!pte_none(ptep_get(pte)))) - return -EBUSY; - if (WARN_ON(!page)) - return -ENOMEM; - if (WARN_ON(!pfn_valid(page_to_pfn(page)))) - return -EINVAL; + if (WARN_ON(!pte_none(ptep_get(pte)))) { + err = -EBUSY; + break; + } + if (WARN_ON(!page)) { + err = -ENOMEM; + break; + } + if (WARN_ON(!pfn_valid(page_to_pfn(page)))) { + err = -EINVAL; + break; + } set_pte_at(&init_mm, addr, pte, mk_pte(page, prot)); (*nr)++; } while (pte++, addr += PAGE_SIZE, addr != end); *mask |= PGTBL_PTE_MODIFIED; - return 0; + + return err; } static int vmap_pages_pmd_range(pud_t *pud, unsigned long addr, @@ -586,13 +594,13 @@ static int vmap_small_pages_range_noflush(unsigned long addr, unsigned long end, mask |= PGTBL_PGD_MODIFIED; err = vmap_pages_p4d_range(pgd, addr, next, prot, pages, &nr, &mask); if (err) - return err; + break; } while (pgd++, addr = next, addr != end); if (mask & ARCH_PAGE_TABLE_SYNC_MASK) arch_sync_kernel_mappings(start, end); - return 0; + return err; } /* @@ -1940,7 +1948,7 @@ static inline void setup_vmalloc_vm(struct vm_struct *vm, { vm->flags = flags; vm->addr = (void *)va->va_start; - vm->size = va_size(va); + vm->size = vm->requested_size = va_size(va); vm->caller = caller; va->vm = vm; } @@ -3095,7 +3103,7 @@ static void clear_vm_uninitialized_flag(struct vm_struct *vm) /* * Before removing VM_UNINITIALIZED, * we should make sure that vm has proper values. - * Pair with smp_rmb() in show_numa_info(). + * Pair with smp_rmb() in vread_iter() and vmalloc_info_show(). */ smp_wmb(); vm->flags &= ~VM_UNINITIALIZED; @@ -3128,6 +3136,7 @@ static struct vm_struct *__get_vm_area_node(unsigned long size, area->flags = flags; area->caller = caller; + area->requested_size = requested_size; va = alloc_vmap_area(size, align, start, end, node, gfp_mask, 0, area); if (IS_ERR(va)) { @@ -4067,6 +4076,8 @@ EXPORT_SYMBOL(vzalloc_node_noprof); */ void *vrealloc_noprof(const void *p, size_t size, gfp_t flags) { + struct vm_struct *vm = NULL; + size_t alloced_size = 0; size_t old_size = 0; void *n; @@ -4076,15 +4087,17 @@ void *vrealloc_noprof(const void *p, size_t size, gfp_t flags) } if (p) { - struct vm_struct *vm; - vm = find_vm_area(p); if (unlikely(!vm)) { WARN(1, "Trying to vrealloc() nonexistent vm area (%p)\n", p); return NULL; } - old_size = get_vm_area_size(vm); + alloced_size = get_vm_area_size(vm); + old_size = vm->requested_size; + if (WARN(alloced_size < old_size, + "vrealloc() has mismatched area vs requested sizes (%p)\n", p)) + return NULL; } /* @@ -4092,11 +4105,26 @@ void *vrealloc_noprof(const void *p, size_t size, gfp_t flags) * would be a good heuristic for when to shrink the vm_area? */ if (size <= old_size) { - /* Zero out spare memory. */ - if (want_init_on_alloc(flags)) + /* Zero out "freed" memory, potentially for future realloc. */ + if (want_init_on_free() || want_init_on_alloc(flags)) memset((void *)p + size, 0, old_size - size); + vm->requested_size = size; kasan_poison_vmalloc(p + size, old_size - size); - kasan_unpoison_vmalloc(p, size, KASAN_VMALLOC_PROT_NORMAL); + return (void *)p; + } + + /* + * We already have the bytes available in the allocation; use them. + */ + if (size <= alloced_size) { + kasan_unpoison_vmalloc(p + old_size, size - old_size, + KASAN_VMALLOC_PROT_NORMAL); + /* + * No need to zero memory here, as unused memory will have + * already been zeroed at initial allocation time or during + * realloc shrink time. + */ + vm->requested_size = size; return (void *)p; } @@ -4918,28 +4946,29 @@ bool vmalloc_dump_obj(void *object) #endif #ifdef CONFIG_PROC_FS -static void show_numa_info(struct seq_file *m, struct vm_struct *v) -{ - if (IS_ENABLED(CONFIG_NUMA)) { - unsigned int nr, *counters = m->private; - unsigned int step = 1U << vm_area_page_order(v); - if (!counters) - return; +/* + * Print number of pages allocated on each memory node. + * + * This function can only be called if CONFIG_NUMA is enabled + * and VM_UNINITIALIZED bit in v->flags is disabled. + */ +static void show_numa_info(struct seq_file *m, struct vm_struct *v, + unsigned int *counters) +{ + unsigned int nr; + unsigned int step = 1U << vm_area_page_order(v); - if (v->flags & VM_UNINITIALIZED) - return; - /* Pair with smp_wmb() in clear_vm_uninitialized_flag() */ - smp_rmb(); + if (!counters) + return; - memset(counters, 0, nr_node_ids * sizeof(unsigned int)); + memset(counters, 0, nr_node_ids * sizeof(unsigned int)); - for (nr = 0; nr < v->nr_pages; nr += step) - counters[page_to_nid(v->pages[nr])] += step; - for_each_node_state(nr, N_HIGH_MEMORY) - if (counters[nr]) - seq_printf(m, " N%u=%u", nr, counters[nr]); - } + for (nr = 0; nr < v->nr_pages; nr += step) + counters[page_to_nid(v->pages[nr])] += step; + for_each_node_state(nr, N_HIGH_MEMORY) + if (counters[nr]) + seq_printf(m, " N%u=%u", nr, counters[nr]); } static void show_purge_info(struct seq_file *m) @@ -4967,6 +4996,10 @@ static int vmalloc_info_show(struct seq_file *m, void *p) struct vmap_area *va; struct vm_struct *v; int i; + unsigned int *counters; + + if (IS_ENABLED(CONFIG_NUMA)) + counters = kmalloc(nr_node_ids * sizeof(unsigned int), GFP_KERNEL); for (i = 0; i < nr_vmap_nodes; i++) { vn = &vmap_nodes[i]; @@ -4983,6 +5016,11 @@ static int vmalloc_info_show(struct seq_file *m, void *p) } v = va->vm; + if (v->flags & VM_UNINITIALIZED) + continue; + + /* Pair with smp_wmb() in clear_vm_uninitialized_flag() */ + smp_rmb(); seq_printf(m, "0x%pK-0x%pK %7ld", v->addr, v->addr + v->size, v->size); @@ -5017,7 +5055,9 @@ static int vmalloc_info_show(struct seq_file *m, void *p) if (is_vmalloc_addr(v->pages)) seq_puts(m, " vpages"); - show_numa_info(m, v); + if (IS_ENABLED(CONFIG_NUMA)) + show_numa_info(m, v, counters); + seq_putc(m, '\n'); } spin_unlock(&vn->busy.lock); @@ -5027,19 +5067,14 @@ static int vmalloc_info_show(struct seq_file *m, void *p) * As a final step, dump "unpurged" areas. */ show_purge_info(m); + if (IS_ENABLED(CONFIG_NUMA)) + kfree(counters); return 0; } static int __init proc_vmalloc_init(void) { - void *priv_data = NULL; - - if (IS_ENABLED(CONFIG_NUMA)) - priv_data = kmalloc(nr_node_ids * sizeof(unsigned int), GFP_KERNEL); - - proc_create_single_data("vmallocinfo", - 0400, NULL, vmalloc_info_show, priv_data); - + proc_create_single("vmallocinfo", 0400, NULL, vmalloc_info_show); return 0; } module_init(proc_vmalloc_init); diff --git a/mm/vmscan.c b/mm/vmscan.c index 67a680e4b484..e3c1e2e1560d 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1053,7 +1053,7 @@ static unsigned int shrink_folio_list(struct list_head *folio_list, struct folio_batch free_folios; LIST_HEAD(ret_folios); LIST_HEAD(demote_folios); - unsigned int nr_reclaimed = 0; + unsigned int nr_reclaimed = 0, nr_demoted = 0; unsigned int pgactivate = 0; bool do_demote_pass; struct swap_iocb *plug = NULL; @@ -1079,6 +1079,21 @@ retry: if (!folio_trylock(folio)) goto keep; + if (folio_contain_hwpoisoned_page(folio)) { + /* + * unmap_poisoned_folio() can't handle large + * folio, just skip it. memory_failure() will + * handle it if the UCE is triggered again. + */ + if (folio_test_large(folio)) + goto keep_locked; + + unmap_poisoned_folio(folio, folio_pfn(folio), false); + folio_unlock(folio); + folio_put(folio); + continue; + } + VM_BUG_ON_FOLIO(folio_test_active(folio), folio); nr_pages = folio_nr_pages(folio); @@ -1522,8 +1537,9 @@ keep: /* 'folio_list' is always empty here */ /* Migrate folios selected for demotion */ - stat->nr_demoted = demote_folio_list(&demote_folios, pgdat); - nr_reclaimed += stat->nr_demoted; + nr_demoted = demote_folio_list(&demote_folios, pgdat); + nr_reclaimed += nr_demoted; + stat->nr_demoted += nr_demoted; /* Folios that could not be demoted are still in @demote_folios */ if (!list_empty(&demote_folios)) { /* Folios which weren't demoted go back on @folio_list */ @@ -4637,6 +4653,9 @@ retry: reset_batch_size(walk); } + __mod_lruvec_state(lruvec, PGDEMOTE_KSWAPD + reclaimer_offset(), + stat.nr_demoted); + item = PGSTEAL_KSWAPD + reclaimer_offset(); if (!cgroup_reclaim(sc)) __count_vm_events(item, reclaimed); @@ -7553,7 +7572,7 @@ int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order) return NODE_RECLAIM_NOSCAN; ret = __node_reclaim(pgdat, gfp_mask, order); - clear_bit(PGDAT_RECLAIM_LOCKED, &pgdat->flags); + clear_bit_unlock(PGDAT_RECLAIM_LOCKED, &pgdat->flags); if (ret) count_vm_event(PGSCAN_ZONE_RECLAIM_SUCCESS); diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 16a07def09c9..e4326af00e5e 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -976,6 +976,9 @@ static struct zspage *alloc_zspage(struct zs_pool *pool, if (!zspage) return NULL; + if (!IS_ENABLED(CONFIG_COMPACTION)) + gfp &= ~__GFP_MOVABLE; + zspage->magic = ZSPAGE_MAGIC; migrate_lock_init(zspage); diff --git a/mm/zswap.c b/mm/zswap.c index 0030ce8fecfc..00d51d013757 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -251,7 +251,7 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor) struct zswap_pool *pool; char name[38]; /* 'zswap' + 32 char (max) num + \0 */ gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM; - int ret; + int ret, cpu; if (!zswap_has_pool) { /* if either are unset, pool initialization failed, and we @@ -285,6 +285,9 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor) goto error; } + for_each_possible_cpu(cpu) + mutex_init(&per_cpu_ptr(pool->acomp_ctx, cpu)->mutex); + ret = cpuhp_state_add_instance(CPUHP_MM_ZSWP_POOL_PREPARE, &pool->node); if (ret) @@ -812,36 +815,41 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node) { struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node); struct crypto_acomp_ctx *acomp_ctx = per_cpu_ptr(pool->acomp_ctx, cpu); - struct crypto_acomp *acomp; - struct acomp_req *req; + struct crypto_acomp *acomp = NULL; + struct acomp_req *req = NULL; + u8 *buffer = NULL; int ret; - mutex_init(&acomp_ctx->mutex); - - acomp_ctx->buffer = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu)); - if (!acomp_ctx->buffer) - return -ENOMEM; + buffer = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu)); + if (!buffer) { + ret = -ENOMEM; + goto fail; + } acomp = crypto_alloc_acomp_node(pool->tfm_name, 0, 0, cpu_to_node(cpu)); if (IS_ERR(acomp)) { pr_err("could not alloc crypto acomp %s : %ld\n", pool->tfm_name, PTR_ERR(acomp)); ret = PTR_ERR(acomp); - goto acomp_fail; + goto fail; } - acomp_ctx->acomp = acomp; - acomp_ctx->is_sleepable = acomp_is_async(acomp); - req = acomp_request_alloc(acomp_ctx->acomp); + req = acomp_request_alloc(acomp); if (!req) { pr_err("could not alloc crypto acomp_request %s\n", pool->tfm_name); ret = -ENOMEM; - goto req_fail; + goto fail; } - acomp_ctx->req = req; + /* + * Only hold the mutex after completing allocations, otherwise we may + * recurse into zswap through reclaim and attempt to hold the mutex + * again resulting in a deadlock. + */ + mutex_lock(&acomp_ctx->mutex); crypto_init_wait(&acomp_ctx->wait); + /* * if the backend of acomp is async zip, crypto_req_done() will wakeup * crypto_wait_req(); if the backend of acomp is scomp, the callback @@ -850,12 +858,17 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node) acomp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, crypto_req_done, &acomp_ctx->wait); + acomp_ctx->buffer = buffer; + acomp_ctx->acomp = acomp; + acomp_ctx->is_sleepable = acomp_is_async(acomp); + acomp_ctx->req = req; + mutex_unlock(&acomp_ctx->mutex); return 0; -req_fail: - crypto_free_acomp(acomp_ctx->acomp); -acomp_fail: - kfree(acomp_ctx->buffer); +fail: + if (acomp) + crypto_free_acomp(acomp); + kfree(buffer); return ret; } @@ -863,18 +876,60 @@ static int zswap_cpu_comp_dead(unsigned int cpu, struct hlist_node *node) { struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node); struct crypto_acomp_ctx *acomp_ctx = per_cpu_ptr(pool->acomp_ctx, cpu); + struct acomp_req *req; + struct crypto_acomp *acomp; + u8 *buffer; - if (!IS_ERR_OR_NULL(acomp_ctx)) { - if (!IS_ERR_OR_NULL(acomp_ctx->req)) - acomp_request_free(acomp_ctx->req); - if (!IS_ERR_OR_NULL(acomp_ctx->acomp)) - crypto_free_acomp(acomp_ctx->acomp); - kfree(acomp_ctx->buffer); - } + if (IS_ERR_OR_NULL(acomp_ctx)) + return 0; + + mutex_lock(&acomp_ctx->mutex); + req = acomp_ctx->req; + acomp = acomp_ctx->acomp; + buffer = acomp_ctx->buffer; + acomp_ctx->req = NULL; + acomp_ctx->acomp = NULL; + acomp_ctx->buffer = NULL; + mutex_unlock(&acomp_ctx->mutex); + + /* + * Do the actual freeing after releasing the mutex to avoid subtle + * locking dependencies causing deadlocks. + */ + if (!IS_ERR_OR_NULL(req)) + acomp_request_free(req); + if (!IS_ERR_OR_NULL(acomp)) + crypto_free_acomp(acomp); + kfree(buffer); return 0; } +static struct crypto_acomp_ctx *acomp_ctx_get_cpu_lock(struct zswap_pool *pool) +{ + struct crypto_acomp_ctx *acomp_ctx; + + for (;;) { + acomp_ctx = raw_cpu_ptr(pool->acomp_ctx); + mutex_lock(&acomp_ctx->mutex); + if (likely(acomp_ctx->req)) + return acomp_ctx; + /* + * It is possible that we were migrated to a different CPU after + * getting the per-CPU ctx but before the mutex was acquired. If + * the old CPU got offlined, zswap_cpu_comp_dead() could have + * already freed ctx->req (among other things) and set it to + * NULL. Just try again on the new CPU that we ended up on. + */ + mutex_unlock(&acomp_ctx->mutex); + } +} + +static void acomp_ctx_put_unlock(struct crypto_acomp_ctx *acomp_ctx) +{ + mutex_unlock(&acomp_ctx->mutex); +} + static bool zswap_compress(struct folio *folio, struct zswap_entry *entry) { struct crypto_acomp_ctx *acomp_ctx; @@ -887,10 +942,7 @@ static bool zswap_compress(struct folio *folio, struct zswap_entry *entry) gfp_t gfp; u8 *dst; - acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx); - - mutex_lock(&acomp_ctx->mutex); - + acomp_ctx = acomp_ctx_get_cpu_lock(entry->pool); dst = acomp_ctx->buffer; sg_init_table(&input, 1); sg_set_folio(&input, folio, PAGE_SIZE, 0); @@ -943,7 +995,7 @@ unlock: else if (alloc_ret) zswap_reject_alloc_fail++; - mutex_unlock(&acomp_ctx->mutex); + acomp_ctx_put_unlock(acomp_ctx); return comp_ret == 0 && alloc_ret == 0; } @@ -954,9 +1006,7 @@ static void zswap_decompress(struct zswap_entry *entry, struct folio *folio) struct crypto_acomp_ctx *acomp_ctx; u8 *src; - acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx); - mutex_lock(&acomp_ctx->mutex); - + acomp_ctx = acomp_ctx_get_cpu_lock(entry->pool); src = zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO); /* * If zpool_map_handle is atomic, we cannot reliably utilize its mapped buffer @@ -980,10 +1030,10 @@ static void zswap_decompress(struct zswap_entry *entry, struct folio *folio) acomp_request_set_params(acomp_ctx->req, &input, &output, entry->length, PAGE_SIZE); BUG_ON(crypto_wait_req(crypto_acomp_decompress(acomp_ctx->req), &acomp_ctx->wait)); BUG_ON(acomp_ctx->req->dlen != PAGE_SIZE); - mutex_unlock(&acomp_ctx->mutex); if (src != acomp_ctx->buffer) zpool_unmap_handle(zpool, entry->handle); + acomp_ctx_put_unlock(acomp_ctx); } /********************************* |