diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 89ec31f1f0237c0387dbb3b84cd04694c8b36d71..c3f54d2eaf36d79f05f2b80d92fff4f83a956524 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -1551,6 +1551,7 @@ void xas_create_range(struct xa_state *); #ifdef CONFIG_XARRAY_MULTI int xa_get_order(struct xarray *, unsigned long index); +int xas_get_order(struct xa_state *xas); void xas_split(struct xa_state *, void *entry, unsigned int order); void xas_split_alloc(struct xa_state *, void *entry, unsigned int order, gfp_t); #else @@ -1559,6 +1560,11 @@ static inline int xa_get_order(struct xarray *xa, unsigned long index) return 0; } +static inline int xas_get_order(struct xa_state *xas) +{ + return 0; +} + static inline void xas_split(struct xa_state *xas, void *entry, unsigned int order) { diff --git a/lib/test_xarray.c b/lib/test_xarray.c index e77d4856442c3f750434e37819e13688d210048e..542926da61a3ed68a4635031d6543f33c9187ffc 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -1756,6 +1756,97 @@ static noinline void check_get_order(struct xarray *xa) } } +static noinline void check_xas_get_order(struct xarray *xa) +{ + XA_STATE(xas, xa, 0); + + unsigned int max_order = IS_ENABLED(CONFIG_XARRAY_MULTI) ? 20 : 1; + unsigned int order; + unsigned long i, j; + + for (order = 0; order < max_order; order++) { + for (i = 0; i < 10; i++) { + xas_set_order(&xas, i << order, order); + do { + xas_lock(&xas); + xas_store(&xas, xa_mk_value(i)); + xas_unlock(&xas); + } while (xas_nomem(&xas, GFP_KERNEL)); + + for (j = i << order; j < (i + 1) << order; j++) { + xas_set_order(&xas, j, 0); + rcu_read_lock(); + xas_load(&xas); + XA_BUG_ON(xa, xas_get_order(&xas) != order); + rcu_read_unlock(); + } + + xas_lock(&xas); + xas_set_order(&xas, i << order, order); + xas_store(&xas, NULL); + xas_unlock(&xas); + } + } +} + +static noinline void check_xas_conflict_get_order(struct xarray *xa) +{ + XA_STATE(xas, xa, 0); + + void *entry; + int only_once; + unsigned int max_order = IS_ENABLED(CONFIG_XARRAY_MULTI) ? 20 : 1; + unsigned int order; + unsigned long i, j, k; + + for (order = 0; order < max_order; order++) { + for (i = 0; i < 10; i++) { + xas_set_order(&xas, i << order, order); + do { + xas_lock(&xas); + xas_store(&xas, xa_mk_value(i)); + xas_unlock(&xas); + } while (xas_nomem(&xas, GFP_KERNEL)); + + /* + * Ensure xas_get_order works with xas_for_each_conflict. + */ + j = i << order; + for (k = 0; k < order; k++) { + only_once = 0; + xas_set_order(&xas, j + (1 << k), k); + xas_lock(&xas); + xas_for_each_conflict(&xas, entry) { + XA_BUG_ON(xa, entry != xa_mk_value(i)); + XA_BUG_ON(xa, xas_get_order(&xas) != order); + only_once++; + } + XA_BUG_ON(xa, only_once != 1); + xas_unlock(&xas); + } + + if (order < max_order - 1) { + only_once = 0; + xas_set_order(&xas, (i & ~1UL) << order, order + 1); + xas_lock(&xas); + xas_for_each_conflict(&xas, entry) { + XA_BUG_ON(xa, entry != xa_mk_value(i)); + XA_BUG_ON(xa, xas_get_order(&xas) != order); + only_once++; + } + XA_BUG_ON(xa, only_once != 1); + xas_unlock(&xas); + } + + xas_set_order(&xas, i << order, order); + xas_lock(&xas); + xas_store(&xas, NULL); + xas_unlock(&xas); + } + } +} + + static noinline void check_destroy(struct xarray *xa) { unsigned long index; @@ -1805,6 +1896,8 @@ static int xarray_checks(void) check_reserve(&xa0); check_multi_store(&array); check_get_order(&array); + check_xas_get_order(&array); + check_xas_conflict_get_order(&array); check_xa_alloc(); check_find(&array); check_find_entry(&array); diff --git a/lib/xarray.c b/lib/xarray.c index f49053882354565f77398a3b9a150b44bc5242c0..1c87d871cacfa0c99eb0f512324bd365c30c0666 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -1751,39 +1751,52 @@ void *xa_store_range(struct xarray *xa, unsigned long first, EXPORT_SYMBOL(xa_store_range); /** - * xa_get_order() - Get the order of an entry. - * @xa: XArray. - * @index: Index of the entry. + * xas_get_order() - Get the order of an entry. + * @xas: XArray operation state. + * + * Called after xas_load, the xas should not be in an error state. * * Return: A number between 0 and 63 indicating the order of the entry. */ -int xa_get_order(struct xarray *xa, unsigned long index) +int xas_get_order(struct xa_state *xas) { - XA_STATE(xas, xa, index); - void *entry; int order = 0; - rcu_read_lock(); - entry = xas_load(&xas); - - if (!entry) - goto unlock; - - if (!xas.xa_node) - goto unlock; + if (!xas->xa_node) + return 0; for (;;) { - unsigned int slot = xas.xa_offset + (1 << order); + unsigned int slot = xas->xa_offset + (1 << order); if (slot >= XA_CHUNK_SIZE) break; - if (!xa_is_sibling(xas.xa_node->slots[slot])) + if (!xa_is_sibling(xa_entry(xas->xa, xas->xa_node, slot))) break; order++; } - order += xas.xa_node->shift; -unlock: + order += xas->xa_node->shift; + return order; +} +EXPORT_SYMBOL_GPL(xas_get_order); + +/** + * xa_get_order() - Get the order of an entry. + * @xa: XArray. + * @index: Index of the entry. + * + * Return: A number between 0 and 63 indicating the order of the entry. + */ +int xa_get_order(struct xarray *xa, unsigned long index) +{ + XA_STATE(xas, xa, index); + int order = 0; + void *entry; + + rcu_read_lock(); + entry = xas_load(&xas); + if (entry) + order = xas_get_order(&xas); rcu_read_unlock(); return order; diff --git a/mm/filemap.c b/mm/filemap.c index e8a7bd88bf9051a9bb58839c3561a1849a1ec956..bb873391a9390ea422f068bf55eef43c7a37e5f4 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -848,23 +848,18 @@ noinline int __filemap_add_folio(struct address_space *mapping, struct folio *folio, pgoff_t index, gfp_t gfp, void **shadowp) { XA_STATE(xas, &mapping->i_pages, index); - int huge = folio_test_hugetlb(folio); - bool charged = false; - long nr = 1; + void *alloced_shadow = NULL; + int alloced_order = 0; + bool huge; + long nr; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(folio_test_swapbacked(folio), folio); mapping_set_update(&xas, mapping); - if (!huge) { - int error = mem_cgroup_charge(folio, NULL, gfp); - if (error) - return error; - charged = true; - } - VM_BUG_ON_FOLIO(index & (folio_nr_pages(folio) - 1), folio); xas_set_order(&xas, index, folio_order(folio)); + huge = folio_test_hugetlb(folio); nr = folio_nr_pages(folio); gfp &= GFP_RECLAIM_MASK; @@ -872,13 +867,10 @@ noinline int __filemap_add_folio(struct address_space *mapping, folio->mapping = mapping; folio->index = xas.xa_index; - do { - unsigned int order = xa_get_order(xas.xa, xas.xa_index); + for (;;) { + int order = -1, split_order = 0; void *entry, *old = NULL; - if (order > folio_order(folio)) - xas_split_alloc(&xas, xa_load(xas.xa, xas.xa_index), - order, gfp); xas_lock_irq(&xas); xas_for_each_conflict(&xas, entry) { old = entry; @@ -886,19 +878,33 @@ noinline int __filemap_add_folio(struct address_space *mapping, xas_set_err(&xas, -EEXIST); goto unlock; } + /* + * If a larger entry exists, + * it will be the first and only entry iterated. + */ + if (order == -1) + order = xas_get_order(&xas); + } + + /* entry may have changed before we re-acquire the lock */ + if (alloced_order && (old != alloced_shadow || order != alloced_order)) { + xas_destroy(&xas); + alloced_order = 0; } if (old) { - if (shadowp) - *shadowp = old; - /* entry may have been split before we acquired lock */ - order = xa_get_order(xas.xa, xas.xa_index); - if (order > folio_order(folio)) { + if (order > 0 && order > folio_order(folio)) { /* How to handle large swap entries? */ BUG_ON(shmem_mapping(mapping)); + if (!alloced_order) { + split_order = order; + goto unlock; + } xas_split(&xas, old, order); xas_reset(&xas); } + if (shadowp) + *shadowp = old; } xas_store(&xas, folio); @@ -914,9 +920,24 @@ noinline int __filemap_add_folio(struct address_space *mapping, __lruvec_stat_mod_folio(folio, NR_FILE_THPS, nr); } + unlock: xas_unlock_irq(&xas); - } while (xas_nomem(&xas, gfp)); + + /* split needed, alloc here and retry. */ + if (split_order) { + xas_split_alloc(&xas, old, split_order, gfp); + if (xas_error(&xas)) + goto error; + alloced_shadow = old; + alloced_order = split_order; + xas_reset(&xas); + continue; + } + + if (!xas_nomem(&xas, gfp)) + break; + } if (xas_error(&xas)) goto error; @@ -924,8 +945,6 @@ noinline int __filemap_add_folio(struct address_space *mapping, trace_mm_filemap_add_to_page_cache(folio); return 0; error: - if (charged) - mem_cgroup_uncharge(folio); folio->mapping = NULL; /* Leave page->index set: truncation relies upon it */ folio_put_refs(folio, nr); @@ -939,11 +958,16 @@ int filemap_add_folio(struct address_space *mapping, struct folio *folio, void *shadow = NULL; int ret; + ret = mem_cgroup_charge(folio, NULL, gfp); + if (ret) + return ret; + __folio_set_locked(folio); ret = __filemap_add_folio(mapping, folio, index, gfp, &shadow); - if (unlikely(ret)) + if (unlikely(ret)) { + mem_cgroup_uncharge(folio); __folio_clear_locked(folio); - else { + } else { /* * The folio might have been evicted from cache only * recently, in which case it should be activated like diff --git a/mm/memory.c b/mm/memory.c index 2c317f517d1dfec0eb1328e16cf70d30ffc20cb7..833e4d076f016c7a560b07e46f6f2c42b624384e 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -113,8 +113,10 @@ static bool vmf_pte_changed(struct vm_fault *vmf); * Return true if the original pte was a uffd-wp pte marker (so the pte was * wr-protected). */ -static bool vmf_orig_pte_uffd_wp(struct vm_fault *vmf) +static __always_inline bool vmf_orig_pte_uffd_wp(struct vm_fault *vmf) { + if (!userfaultfd_wp(vmf->vma)) + return false; if (!(vmf->flags & FAULT_FLAG_ORIG_PTE_VALID)) return false; @@ -4366,7 +4368,6 @@ static struct folio *alloc_anon_folio(struct vm_fault *vmf) */ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) { - bool uffd_wp = vmf_orig_pte_uffd_wp(vmf); struct vm_area_struct *vma = vmf->vma; unsigned long addr = vmf->address; struct folio *folio; @@ -4464,7 +4465,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) folio_add_new_anon_rmap(folio, vma, addr); folio_add_lru_vma(folio, vma); setpte: - if (uffd_wp) + if (vmf_orig_pte_uffd_wp(vmf)) entry = pte_mkuffd_wp(entry); set_ptes(vma->vm_mm, addr, vmf->pte, entry, nr_pages); @@ -4640,7 +4641,6 @@ void set_pte_range(struct vm_fault *vmf, struct folio *folio, struct page *page, unsigned int nr, unsigned long addr) { struct vm_area_struct *vma = vmf->vma; - bool uffd_wp = vmf_orig_pte_uffd_wp(vmf); bool write = vmf->flags & FAULT_FLAG_WRITE; bool prefault = in_range(vmf->address, addr, nr * PAGE_SIZE); pte_t entry; @@ -4655,7 +4655,7 @@ void set_pte_range(struct vm_fault *vmf, struct folio *folio, if (write) entry = maybe_mkwrite(pte_mkdirty(entry), vma); - if (unlikely(uffd_wp)) + if (unlikely(vmf_orig_pte_uffd_wp(vmf))) entry = pte_mkuffd_wp(entry); /* copy-on-write page */ add_reliable_folio_counter(folio, vma->vm_mm, nr); diff --git a/mm/swapfile.c b/mm/swapfile.c index 91f48df479525d990e1dc0bc3bb90c89a6c0f6c2..3312f2422b3649b18353d452f43887b5525bd06c 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2465,13 +2465,17 @@ static void reinsert_swap_info(struct swap_info_struct *p) spin_unlock(&swap_lock); } +static bool __has_usable_swap(void) +{ + return !plist_head_empty(&swap_active_head); +} + bool has_usable_swap(void) { - bool ret = true; + bool ret; spin_lock(&swap_lock); - if (plist_head_empty(&swap_active_head)) - ret = false; + ret = __has_usable_swap(); spin_unlock(&swap_lock); return ret; } @@ -3728,6 +3732,9 @@ void __folio_throttle_swaprate(struct folio *folio, gfp_t gfp) if (!(gfp & __GFP_IO)) return; + if (!__has_usable_swap()) + return; + if (!blk_cgroup_congested()) return;