diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 69af2173555f..6d02168d78be 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1599,6 +1599,15 @@ The following nested keys are defined. pglazyfreed (npn) Amount of reclaimed lazyfree pages + swpin_zero + Number of pages swapped into memory and filled with zero, where I/O + was optimized out because the page content was detected to be zero + during swapout. + + swpout_zero + Number of zero-filled pages swapped out with I/O skipped due to the + content being detected as zero. + zswpin Number of pages moved in to memory from zswap. diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c index 57b4af5ad646..501ad7be5174 100644 --- a/fs/nilfs2/btnode.c +++ b/fs/nilfs2/btnode.c @@ -68,7 +68,6 @@ nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr) goto failed; } memset(bh->b_data, 0, i_blocksize(inode)); - bh->b_bdev = inode->i_sb->s_bdev; bh->b_blocknr = blocknr; set_buffer_mapped(bh); set_buffer_uptodate(bh); @@ -133,7 +132,6 @@ int nilfs_btnode_submit_block(struct address_space *btnc, __u64 blocknr, goto found; } set_buffer_mapped(bh); - bh->b_bdev = inode->i_sb->s_bdev; bh->b_blocknr = pblocknr; /* set block address for read */ bh->b_end_io = end_buffer_read_sync; get_bh(bh); diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c index 1c9ae36a03ab..ace22253fed0 100644 --- a/fs/nilfs2/gcinode.c +++ b/fs/nilfs2/gcinode.c @@ -83,10 +83,8 @@ int nilfs_gccache_submit_read_data(struct inode *inode, sector_t blkoff, goto out; } - if (!buffer_mapped(bh)) { - bh->b_bdev = inode->i_sb->s_bdev; + if (!buffer_mapped(bh)) set_buffer_mapped(bh); - } bh->b_blocknr = pbn; bh->b_end_io = end_buffer_read_sync; get_bh(bh); diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c index ceb7dc0b5bad..2db6350b5ac2 100644 --- a/fs/nilfs2/mdt.c +++ b/fs/nilfs2/mdt.c @@ -89,7 +89,6 @@ static int nilfs_mdt_create_block(struct inode *inode, unsigned long block, if (buffer_uptodate(bh)) goto failed_bh; - bh->b_bdev = sb->s_bdev; err = nilfs_mdt_insert_new_block(inode, block, bh, init_block); if (likely(!err)) { get_bh(bh); diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index 10def4b55995..6dd8b854cd1f 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -39,7 +39,6 @@ static struct buffer_head *__nilfs_get_folio_block(struct folio *folio, first_block = (unsigned long)index << (PAGE_SHIFT - blkbits); bh = get_nth_bh(bh, block - first_block); - touch_buffer(bh); wait_on_buffer(bh); return bh; } @@ -64,6 +63,7 @@ struct buffer_head *nilfs_grab_buffer(struct inode *inode, folio_put(folio); return NULL; } + bh->b_bdev = inode->i_sb->s_bdev; return bh; } diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 3d404624bb96..c79b4291777f 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -2319,6 +2319,7 @@ static int ocfs2_verify_volume(struct ocfs2_dinode *di, struct ocfs2_blockcheck_stats *stats) { int status = -EAGAIN; + u32 blksz_bits; if (memcmp(di->i_signature, OCFS2_SUPER_BLOCK_SIGNATURE, strlen(OCFS2_SUPER_BLOCK_SIGNATURE)) == 0) { @@ -2333,11 +2334,15 @@ static int ocfs2_verify_volume(struct ocfs2_dinode *di, goto out; } status = -EINVAL; - if ((1 << le32_to_cpu(di->id2.i_super.s_blocksize_bits)) != blksz) { + /* Acceptable block sizes are 512 bytes, 1K, 2K and 4K. */ + blksz_bits = le32_to_cpu(di->id2.i_super.s_blocksize_bits); + if (blksz_bits < 9 || blksz_bits > 12) { mlog(ML_ERROR, "found superblock with incorrect block " - "size: found %u, should be %u\n", - 1 << le32_to_cpu(di->id2.i_super.s_blocksize_bits), - blksz); + "size bits: found %u, should be 9, 10, 11, or 12\n", + blksz_bits); + } else if ((1 << le32_to_cpu(blksz_bits)) != blksz) { + mlog(ML_ERROR, "found superblock with incorrect block " + "size: found %u, should be %u\n", 1 << blksz_bits, blksz); } else if (le16_to_cpu(di->id2.i_super.s_major_rev_level) != OCFS2_MAJOR_REV_LEVEL || le16_to_cpu(di->id2.i_super.s_minor_rev_level) != diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 34d2da05f2f1..e1b41554a5fb 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1760,8 +1760,9 @@ static inline int memcg_kmem_id(struct mem_cgroup *memcg) struct mem_cgroup *mem_cgroup_from_slab_obj(void *p); -static inline void count_objcg_event(struct obj_cgroup *objcg, - enum vm_event_item idx) +static inline void count_objcg_events(struct obj_cgroup *objcg, + enum vm_event_item idx, + unsigned long count) { struct mem_cgroup *memcg; @@ -1770,7 +1771,7 @@ static inline void count_objcg_event(struct obj_cgroup *objcg, rcu_read_lock(); memcg = obj_cgroup_memcg(objcg); - count_memcg_events(memcg, idx, 1); + count_memcg_events(memcg, idx, count); rcu_read_unlock(); } @@ -1825,8 +1826,9 @@ static inline struct mem_cgroup *mem_cgroup_from_slab_obj(void *p) return NULL; } -static inline void count_objcg_event(struct obj_cgroup *objcg, - enum vm_event_item idx) +static inline void count_objcg_events(struct obj_cgroup *objcg, + enum vm_event_item idx, + unsigned long count) { } diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index aed952d04132..f70d0958095c 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -134,6 +134,8 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #ifdef CONFIG_SWAP SWAP_RA, SWAP_RA_HIT, + SWPIN_ZERO, + SWPOUT_ZERO, #ifdef CONFIG_KSM KSM_SWPIN_COPY, #endif diff --git a/mm/gup.c b/mm/gup.c index 4637dab7b54f..ad0c8922dac3 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -2273,20 +2273,57 @@ struct page *get_dump_page(unsigned long addr) #endif /* CONFIG_ELF_CORE */ #ifdef CONFIG_MIGRATION + +/* + * An array of either pages or folios ("pofs"). Although it may seem tempting to + * avoid this complication, by simply interpreting a list of folios as a list of + * pages, that approach won't work in the longer term, because eventually the + * layouts of struct page and struct folio will become completely different. + * Furthermore, this pof approach avoids excessive page_folio() calls. + */ +struct pages_or_folios { + union { + struct page **pages; + struct folio **folios; + void **entries; + }; + bool has_folios; + long nr_entries; +}; + +static struct folio *pofs_get_folio(struct pages_or_folios *pofs, long i) +{ + if (pofs->has_folios) + return pofs->folios[i]; + return page_folio(pofs->pages[i]); +} + +static void pofs_clear_entry(struct pages_or_folios *pofs, long i) +{ + pofs->entries[i] = NULL; +} + +static void pofs_unpin(struct pages_or_folios *pofs) +{ + if (pofs->has_folios) + unpin_folios(pofs->folios, pofs->nr_entries); + else + unpin_user_pages(pofs->pages, pofs->nr_entries); +} + /* * Returns the number of collected folios. Return value is always >= 0. */ static unsigned long collect_longterm_unpinnable_folios( - struct list_head *movable_folio_list, - unsigned long nr_folios, - struct folio **folios) + struct list_head *movable_folio_list, + struct pages_or_folios *pofs) { unsigned long i, collected = 0; struct folio *prev_folio = NULL; bool drain_allow = true; - for (i = 0; i < nr_folios; i++) { - struct folio *folio = folios[i]; + for (i = 0; i < pofs->nr_entries; i++) { + struct folio *folio = pofs_get_folio(pofs, i); if (folio == prev_folio) continue; @@ -2327,16 +2364,15 @@ static unsigned long collect_longterm_unpinnable_folios( * Returns -EAGAIN if all folios were successfully migrated or -errno for * failure (or partial success). */ -static int migrate_longterm_unpinnable_folios( - struct list_head *movable_folio_list, - unsigned long nr_folios, - struct folio **folios) +static int +migrate_longterm_unpinnable_folios(struct list_head *movable_folio_list, + struct pages_or_folios *pofs) { int ret; unsigned long i; - for (i = 0; i < nr_folios; i++) { - struct folio *folio = folios[i]; + for (i = 0; i < pofs->nr_entries; i++) { + struct folio *folio = pofs_get_folio(pofs, i); if (folio_is_device_coherent(folio)) { /* @@ -2344,7 +2380,7 @@ static int migrate_longterm_unpinnable_folios( * convert the pin on the source folio to a normal * reference. */ - folios[i] = NULL; + pofs_clear_entry(pofs, i); folio_get(folio); gup_put_folio(folio, 1, FOLL_PIN); @@ -2363,8 +2399,8 @@ static int migrate_longterm_unpinnable_folios( * calling folio_isolate_lru() which takes a reference so the * folio won't be freed if it's migrating. */ - unpin_folio(folios[i]); - folios[i] = NULL; + unpin_folio(folio); + pofs_clear_entry(pofs, i); } if (!list_empty(movable_folio_list)) { @@ -2387,12 +2423,26 @@ static int migrate_longterm_unpinnable_folios( return -EAGAIN; err: - unpin_folios(folios, nr_folios); + pofs_unpin(pofs); putback_movable_pages(movable_folio_list); return ret; } +static long +check_and_migrate_movable_pages_or_folios(struct pages_or_folios *pofs) +{ + LIST_HEAD(movable_folio_list); + unsigned long collected; + + collected = collect_longterm_unpinnable_folios(&movable_folio_list, + pofs); + if (!collected) + return 0; + + return migrate_longterm_unpinnable_folios(&movable_folio_list, pofs); +} + /* * Check whether all folios are *allowed* to be pinned indefinitely (long term). * Rather confusingly, all folios in the range are required to be pinned via @@ -2417,16 +2467,13 @@ err: static long check_and_migrate_movable_folios(unsigned long nr_folios, struct folio **folios) { - unsigned long collected; - LIST_HEAD(movable_folio_list); + struct pages_or_folios pofs = { + .folios = folios, + .has_folios = true, + .nr_entries = nr_folios, + }; - collected = collect_longterm_unpinnable_folios(&movable_folio_list, - nr_folios, folios); - if (!collected) - return 0; - - return migrate_longterm_unpinnable_folios(&movable_folio_list, - nr_folios, folios); + return check_and_migrate_movable_pages_or_folios(&pofs); } /* @@ -2436,22 +2483,13 @@ static long check_and_migrate_movable_folios(unsigned long nr_folios, static long check_and_migrate_movable_pages(unsigned long nr_pages, struct page **pages) { - struct folio **folios; - long i, ret; + struct pages_or_folios pofs = { + .pages = pages, + .has_folios = false, + .nr_entries = nr_pages, + }; - folios = kmalloc_array(nr_pages, sizeof(*folios), GFP_KERNEL); - if (!folios) { - unpin_user_pages(pages, nr_pages); - return -ENOMEM; - } - - for (i = 0; i < nr_pages; i++) - folios[i] = page_folio(pages[i]); - - ret = check_and_migrate_movable_folios(nr_pages, folios); - - kfree(folios); - return ret; + return check_and_migrate_movable_pages_or_folios(&pofs); } #else static long check_and_migrate_movable_pages(unsigned long nr_pages, diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 03fd4bc39ea1..5734d5d5060f 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -3790,7 +3790,9 @@ next: * in the case it was underused, then consider it used and * don't add it back to split_queue. */ - if (!did_split && !folio_test_partially_mapped(folio)) { + if (did_split) { + ; /* folio already removed from list */ + } else if (!folio_test_partially_mapped(folio)) { list_del_init(&folio->_deferred_list); removed++; } else { diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 06df2af97415..53db98d2c4a1 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -431,6 +431,10 @@ static const unsigned int memcg_vm_event_stat[] = { PGDEACTIVATE, PGLAZYFREE, PGLAZYFREED, +#ifdef CONFIG_SWAP + SWPIN_ZERO, + SWPOUT_ZERO, +#endif #ifdef CONFIG_ZSWAP ZSWPIN, ZSWPOUT, diff --git a/mm/nommu.c b/mm/nommu.c index e9b5f527ab5b..9cb6e99215e2 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -573,7 +573,7 @@ static int delete_vma_from_mm(struct vm_area_struct *vma) VMA_ITERATOR(vmi, vma->vm_mm, vma->vm_start); vma_iter_config(&vmi, vma->vm_start, vma->vm_end); - if (vma_iter_prealloc(&vmi, vma)) { + if (vma_iter_prealloc(&vmi, NULL)) { pr_warn("Allocation of vma tree for process %d failed\n", current->pid); return -ENOMEM; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index c6c7bb3ea71b..216fbbfbedcf 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1048,6 +1048,7 @@ __always_inline bool free_pages_prepare(struct page *page, bool skip_kasan_poison = should_skip_kasan_poison(page); bool init = want_init_on_free(); bool compound = PageCompound(page); + struct folio *folio = page_folio(page); VM_BUG_ON_PAGE(PageTail(page), page); @@ -1057,6 +1058,20 @@ __always_inline bool free_pages_prepare(struct page *page, if (memcg_kmem_online() && PageMemcgKmem(page)) __memcg_kmem_uncharge_page(page, order); + /* + * In rare cases, when truncation or holepunching raced with + * munlock after VM_LOCKED was cleared, Mlocked may still be + * found set here. This does not indicate a problem, unless + * "unevictable_pgs_cleared" appears worryingly large. + */ + if (unlikely(folio_test_mlocked(folio))) { + long nr_pages = folio_nr_pages(folio); + + __folio_clear_mlocked(folio); + zone_stat_mod_folio(folio, NR_MLOCK, -nr_pages); + count_vm_events(UNEVICTABLE_PGCLEARED, nr_pages); + } + if (unlikely(PageHWPoison(page)) && !order) { /* Do not let hwpoison pages hit pcplists/buddy */ reset_page_owner(page, order); diff --git a/mm/page_io.c b/mm/page_io.c index 69536a2b3c13..01749b99fb54 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -204,7 +204,9 @@ static bool is_folio_zero_filled(struct folio *folio) static void swap_zeromap_folio_set(struct folio *folio) { + struct obj_cgroup *objcg = get_obj_cgroup_from_folio(folio); struct swap_info_struct *sis = swp_swap_info(folio->swap); + int nr_pages = folio_nr_pages(folio); swp_entry_t entry; unsigned int i; @@ -212,6 +214,12 @@ static void swap_zeromap_folio_set(struct folio *folio) entry = page_swap_entry(folio_page(folio, i)); set_bit(swp_offset(entry), sis->zeromap); } + + count_vm_events(SWPOUT_ZERO, nr_pages); + if (objcg) { + count_objcg_events(objcg, SWPOUT_ZERO, nr_pages); + obj_cgroup_put(objcg); + } } static void swap_zeromap_folio_clear(struct folio *folio) @@ -503,6 +511,7 @@ static void sio_read_complete(struct kiocb *iocb, long ret) static bool swap_read_folio_zeromap(struct folio *folio) { int nr_pages = folio_nr_pages(folio); + struct obj_cgroup *objcg; bool is_zeromap; /* @@ -517,6 +526,13 @@ static bool swap_read_folio_zeromap(struct folio *folio) if (!is_zeromap) return false; + objcg = get_obj_cgroup_from_folio(folio); + count_vm_events(SWPIN_ZERO, nr_pages); + if (objcg) { + count_objcg_events(objcg, SWPIN_ZERO, nr_pages); + obj_cgroup_put(objcg); + } + folio_zero_range(folio, 0, folio_size(folio)); folio_mark_uptodate(folio); return true; diff --git a/mm/swap.c b/mm/swap.c index b8e3259ea2c4..59f30a981c6f 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -78,20 +78,6 @@ static void __page_cache_release(struct folio *folio, struct lruvec **lruvecp, lruvec_del_folio(*lruvecp, folio); __folio_clear_lru_flags(folio); } - - /* - * In rare cases, when truncation or holepunching raced with - * munlock after VM_LOCKED was cleared, Mlocked may still be - * found set here. This does not indicate a problem, unless - * "unevictable_pgs_cleared" appears worryingly large. - */ - if (unlikely(folio_test_mlocked(folio))) { - long nr_pages = folio_nr_pages(folio); - - __folio_clear_mlocked(folio); - zone_stat_mod_folio(folio, NR_MLOCK, -nr_pages); - count_vm_events(UNEVICTABLE_PGCLEARED, nr_pages); - } } /* diff --git a/mm/swapfile.c b/mm/swapfile.c index 46bd4b1a3c07..9c85bd46ab7f 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -929,7 +929,7 @@ static void swap_range_alloc(struct swap_info_struct *si, unsigned long offset, si->highest_bit = 0; del_from_avail_list(si); - if (vm_swap_full()) + if (si->cluster_info && vm_swap_full()) schedule_work(&si->reclaim_work); } } diff --git a/mm/vmstat.c b/mm/vmstat.c index b5a4cea423e1..ac6a5aa34eab 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1415,6 +1415,8 @@ const char * const vmstat_text[] = { #ifdef CONFIG_SWAP "swap_ra", "swap_ra_hit", + "swpin_zero", + "swpout_zero", #ifdef CONFIG_KSM "ksm_swpin_copy", #endif diff --git a/mm/zswap.c b/mm/zswap.c index 162013952074..0030ce8fecfc 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1053,7 +1053,7 @@ static int zswap_writeback_entry(struct zswap_entry *entry, count_vm_event(ZSWPWB); if (entry->objcg) - count_objcg_event(entry->objcg, ZSWPWB); + count_objcg_events(entry->objcg, ZSWPWB, 1); zswap_entry_free(entry); @@ -1483,7 +1483,7 @@ bool zswap_store(struct folio *folio) if (objcg) { obj_cgroup_charge_zswap(objcg, entry->length); - count_objcg_event(objcg, ZSWPOUT); + count_objcg_events(objcg, ZSWPOUT, 1); } /* @@ -1577,7 +1577,7 @@ bool zswap_load(struct folio *folio) count_vm_event(ZSWPIN); if (entry->objcg) - count_objcg_event(entry->objcg, ZSWPIN); + count_objcg_events(entry->objcg, ZSWPIN, 1); if (swapcache) { zswap_entry_free(entry); diff --git a/tools/testing/selftests/mm/hugetlb_dio.c b/tools/testing/selftests/mm/hugetlb_dio.c index 60001c142ce9..432d5af15e66 100644 --- a/tools/testing/selftests/mm/hugetlb_dio.c +++ b/tools/testing/selftests/mm/hugetlb_dio.c @@ -44,6 +44,13 @@ void run_dio_using_hugetlb(unsigned int start_off, unsigned int end_off) if (fd < 0) ksft_exit_fail_perror("Error opening file\n"); + /* Get the free huge pages before allocation */ + free_hpage_b = get_free_hugepages(); + if (free_hpage_b == 0) { + close(fd); + ksft_exit_skip("No free hugepage, exiting!\n"); + } + /* Allocate a hugetlb page */ orig_buffer = mmap(NULL, h_pagesize, mmap_prot, mmap_flags, -1, 0); if (orig_buffer == MAP_FAILED) {