diff options
Diffstat (limited to 'fs/f2fs/checkpoint.c')
| -rw-r--r-- | fs/f2fs/checkpoint.c | 1078 |
1 files changed, 758 insertions, 320 deletions
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index f661d80474be..4ed2d2a0bf02 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/checkpoint.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/bio.h> @@ -24,23 +21,32 @@ #include <trace/events/f2fs.h> static struct kmem_cache *ino_entry_slab; -struct kmem_cache *inode_entry_slab; +struct kmem_cache *f2fs_inode_entry_slab; + +void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io) +{ + f2fs_build_fault_attr(sbi, 0, 0); + set_ckpt_flags(sbi, CP_ERROR_FLAG); + if (!end_io) + f2fs_flush_merged_writes(sbi); +} /* * We guarantee no failure on the returned page. */ -struct page *grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index) +struct page *f2fs_grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index) { struct address_space *mapping = META_MAPPING(sbi); struct page *page = NULL; repeat: - page = grab_cache_page(mapping, index); + page = f2fs_grab_cache_page(mapping, index, false); if (!page) { cond_resched(); goto repeat; } - f2fs_wait_on_page_writeback(page, META); - SetPageUptodate(page); + f2fs_wait_on_page_writeback(page, META, true); + if (!PageUptodate(page)) + SetPageUptodate(page); return page; } @@ -55,15 +61,19 @@ static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index, struct f2fs_io_info fio = { .sbi = sbi, .type = META, - .rw = READ_SYNC | REQ_META | REQ_PRIO, - .blk_addr = index, + .op = REQ_OP_READ, + .op_flags = REQ_SYNC | REQ_META | REQ_PRIO, + .old_blkaddr = index, + .new_blkaddr = index, .encrypted_page = NULL, + .is_meta = is_meta, }; + int err; if (unlikely(!is_meta)) - fio.rw &= ~REQ_META; + fio.op_flags &= ~REQ_META; repeat: - page = grab_cache_page(mapping, index); + page = f2fs_grab_cache_page(mapping, index, false); if (!page) { cond_resched(); goto repeat; @@ -73,9 +83,10 @@ repeat: fio.page = page; - if (f2fs_submit_page_bio(&fio)) { + err = f2fs_submit_page_bio(&fio); + if (err) { f2fs_put_page(page, 1); - goto repeat; + return ERR_PTR(err); } lock_page(page); @@ -84,29 +95,43 @@ repeat: goto repeat; } - /* - * if there is any IO error when accessing device, make our filesystem - * readonly and make sure do not write checkpoint with non-uptodate - * meta page. - */ - if (unlikely(!PageUptodate(page))) - f2fs_stop_checkpoint(sbi); + if (unlikely(!PageUptodate(page))) { + f2fs_put_page(page, 1); + return ERR_PTR(-EIO); + } out: return page; } -struct page *get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index) +struct page *f2fs_get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index) { return __get_meta_page(sbi, index, true); } +struct page *f2fs_get_meta_page_nofail(struct f2fs_sb_info *sbi, pgoff_t index) +{ + struct page *page; + int count = 0; + +retry: + page = __get_meta_page(sbi, index, true); + if (IS_ERR(page)) { + if (PTR_ERR(page) == -EIO && + ++count <= DEFAULT_RETRY_IO_COUNT) + goto retry; + f2fs_stop_checkpoint(sbi, false); + } + return page; +} + /* for POR only */ -struct page *get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index) +struct page *f2fs_get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index) { return __get_meta_page(sbi, index, false); } -bool is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type) +bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi, + block_t blkaddr, int type) { switch (type) { case META_NAT: @@ -126,8 +151,20 @@ bool is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type) return false; break; case META_POR: + case DATA_GENERIC: if (unlikely(blkaddr >= MAX_BLKADDR(sbi) || - blkaddr < MAIN_BLKADDR(sbi))) + blkaddr < MAIN_BLKADDR(sbi))) { + if (type == DATA_GENERIC) { + f2fs_msg(sbi->sb, KERN_WARNING, + "access invalid blkaddr:%u", blkaddr); + WARN_ON(1); + } + return false; + } + break; + case META_GENERIC: + if (unlikely(blkaddr < SEG0_BLKADDR(sbi) || + blkaddr >= MAIN_BLKADDR(sbi))) return false; break; default: @@ -140,25 +177,30 @@ bool is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type) /* * Readahead CP/NAT/SIT/SSA pages */ -int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, +int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type, bool sync) { - block_t prev_blk_addr = 0; struct page *page; block_t blkno = start; struct f2fs_io_info fio = { .sbi = sbi, .type = META, - .rw = sync ? (READ_SYNC | REQ_META | REQ_PRIO) : READA, + .op = REQ_OP_READ, + .op_flags = sync ? (REQ_SYNC | REQ_META | REQ_PRIO) : + REQ_RAHEAD, .encrypted_page = NULL, + .in_list = false, + .is_meta = (type != META_POR), }; + struct blk_plug plug; if (unlikely(type == META_POR)) - fio.rw &= ~REQ_META; + fio.op_flags &= ~REQ_META; + blk_start_plug(&plug); for (; nrpages-- > 0; blkno++) { - if (!is_valid_blkaddr(sbi, blkno, type)) + if (!f2fs_is_valid_blkaddr(sbi, blkno, type)) goto out; switch (type) { @@ -167,27 +209,25 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, NAT_BLOCK_OFFSET(NM_I(sbi)->max_nid))) blkno = 0; /* get nat block addr */ - fio.blk_addr = current_nat_addr(sbi, + fio.new_blkaddr = current_nat_addr(sbi, blkno * NAT_ENTRY_PER_BLOCK); break; case META_SIT: /* get sit block addr */ - fio.blk_addr = current_sit_addr(sbi, + fio.new_blkaddr = current_sit_addr(sbi, blkno * SIT_ENTRY_PER_BLOCK); - if (blkno != start && prev_blk_addr + 1 != fio.blk_addr) - goto out; - prev_blk_addr = fio.blk_addr; break; case META_SSA: case META_CP: case META_POR: - fio.blk_addr = blkno; + fio.new_blkaddr = blkno; break; default: BUG(); } - page = grab_cache_page(META_MAPPING(sbi), fio.blk_addr); + page = f2fs_grab_cache_page(META_MAPPING(sbi), + fio.new_blkaddr, false); if (!page) continue; if (PageUptodate(page)) { @@ -196,49 +236,54 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, } fio.page = page; - f2fs_submit_page_mbio(&fio); + f2fs_submit_page_bio(&fio); f2fs_put_page(page, 0); } out: - f2fs_submit_merged_bio(sbi, META, READ); + blk_finish_plug(&plug); return blkno - start; } -void ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index) +void f2fs_ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index) { struct page *page; bool readahead = false; page = find_get_page(META_MAPPING(sbi), index); - if (!page || (page && !PageUptodate(page))) + if (!page || !PageUptodate(page)) readahead = true; f2fs_put_page(page, 0); if (readahead) - ra_meta_pages(sbi, index, MAX_BIO_BLOCKS(sbi), META_POR, true); + f2fs_ra_meta_pages(sbi, index, BIO_MAX_PAGES, META_POR, true); } -static int f2fs_write_meta_page(struct page *page, - struct writeback_control *wbc) +static int __f2fs_write_meta_page(struct page *page, + struct writeback_control *wbc, + enum iostat_type io_type) { struct f2fs_sb_info *sbi = F2FS_P_SB(page); trace_f2fs_writepage(page, META); + if (unlikely(f2fs_cp_error(sbi))) + goto redirty_out; if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) goto redirty_out; if (wbc->for_reclaim && page->index < GET_SUM_BLOCK(sbi, 0)) goto redirty_out; - if (unlikely(f2fs_cp_error(sbi))) - goto redirty_out; - f2fs_wait_on_page_writeback(page, META); - write_meta_page(sbi, page); + f2fs_do_write_meta_page(sbi, page, io_type); dec_page_count(sbi, F2FS_DIRTY_META); - unlock_page(page); if (wbc->for_reclaim) - f2fs_submit_merged_bio(sbi, META, WRITE); + f2fs_submit_merged_write_cond(sbi, NULL, page, 0, META); + + unlock_page(page); + + if (unlikely(f2fs_cp_error(sbi))) + f2fs_submit_merged_write(sbi, META); + return 0; redirty_out: @@ -246,57 +291,68 @@ redirty_out: return AOP_WRITEPAGE_ACTIVATE; } +static int f2fs_write_meta_page(struct page *page, + struct writeback_control *wbc) +{ + return __f2fs_write_meta_page(page, wbc, FS_META_IO); +} + static int f2fs_write_meta_pages(struct address_space *mapping, struct writeback_control *wbc) { struct f2fs_sb_info *sbi = F2FS_M_SB(mapping); long diff, written; - trace_f2fs_writepages(mapping->host, wbc, META); + if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) + goto skip_write; /* collect a number of dirty meta pages and write together */ if (wbc->for_kupdate || get_pages(sbi, F2FS_DIRTY_META) < nr_pages_to_skip(sbi, META)) goto skip_write; - /* if mounting is failed, skip writing node pages */ - mutex_lock(&sbi->cp_mutex); + /* if locked failed, cp will flush dirty pages instead */ + if (!mutex_trylock(&sbi->cp_mutex)) + goto skip_write; + + trace_f2fs_writepages(mapping->host, wbc, META); diff = nr_pages_to_write(sbi, META, wbc); - written = sync_meta_pages(sbi, META, wbc->nr_to_write); + written = f2fs_sync_meta_pages(sbi, META, wbc->nr_to_write, FS_META_IO); mutex_unlock(&sbi->cp_mutex); wbc->nr_to_write = max((long)0, wbc->nr_to_write - written - diff); return 0; skip_write: wbc->pages_skipped += get_pages(sbi, F2FS_DIRTY_META); + trace_f2fs_writepages(mapping->host, wbc, META); return 0; } -long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type, - long nr_to_write) +long f2fs_sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type, + long nr_to_write, enum iostat_type io_type) { struct address_space *mapping = META_MAPPING(sbi); - pgoff_t index = 0, end = LONG_MAX, prev = LONG_MAX; + pgoff_t index = 0, prev = ULONG_MAX; struct pagevec pvec; long nwritten = 0; + int nr_pages; struct writeback_control wbc = { .for_reclaim = 0, }; + struct blk_plug plug; pagevec_init(&pvec, 0); - while (index <= end) { - int i, nr_pages; - nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, - PAGECACHE_TAG_DIRTY, - min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1); - if (unlikely(nr_pages == 0)) - break; + blk_start_plug(&plug); + + while ((nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, + PAGECACHE_TAG_DIRTY))) { + int i; for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; - if (prev == LONG_MAX) + if (prev == ULONG_MAX) prev = page->index - 1; if (nr_to_write != LONG_MAX && page->index != prev + 1) { pagevec_release(&pvec); @@ -315,10 +371,13 @@ continue_unlock: goto continue_unlock; } + f2fs_wait_on_page_writeback(page, META, true); + + BUG_ON(PageWriteback(page)); if (!clear_page_dirty_for_io(page)) goto continue_unlock; - if (mapping->a_ops->writepage(page, &wbc)) { + if (__f2fs_write_meta_page(page, &wbc, io_type)) { unlock_page(page); break; } @@ -332,7 +391,9 @@ continue_unlock: } stop: if (nwritten) - f2fs_submit_merged_bio(sbi, type, WRITE); + f2fs_submit_merged_write(sbi, type); + + blk_finish_plug(&plug); return nwritten; } @@ -341,7 +402,8 @@ static int f2fs_set_meta_page_dirty(struct page *page) { trace_f2fs_set_page_dirty(page, META); - SetPageUptodate(page); + if (!PageUptodate(page)) + SetPageUptodate(page); if (!PageDirty(page)) { __set_page_dirty_nobuffers(page); inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_META); @@ -358,26 +420,28 @@ const struct address_space_operations f2fs_meta_aops = { .set_page_dirty = f2fs_set_meta_page_dirty, .invalidatepage = f2fs_invalidate_page, .releasepage = f2fs_release_page, +#ifdef CONFIG_MIGRATION + .migratepage = f2fs_migrate_page, +#endif }; -static void __add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type) +static void __add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, + unsigned int devidx, int type) { struct inode_management *im = &sbi->im[type]; struct ino_entry *e, *tmp; tmp = f2fs_kmem_cache_alloc(ino_entry_slab, GFP_NOFS); -retry: + radix_tree_preload(GFP_NOFS | __GFP_NOFAIL); spin_lock(&im->ino_lock); e = radix_tree_lookup(&im->ino_root, ino); if (!e) { e = tmp; - if (radix_tree_insert(&im->ino_root, ino, e)) { - spin_unlock(&im->ino_lock); - radix_tree_preload_end(); - goto retry; - } + if (unlikely(radix_tree_insert(&im->ino_root, ino, e))) + f2fs_bug_on(sbi, 1); + memset(e, 0, sizeof(struct ino_entry)); e->ino = ino; @@ -385,6 +449,10 @@ retry: if (type != ORPHAN_INO) im->ino_num++; } + + if (type == FLUSH_INO) + f2fs_set_bit(devidx, (char *)&e->dirty_device); + spin_unlock(&im->ino_lock); radix_tree_preload_end(); @@ -410,20 +478,20 @@ static void __remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type) spin_unlock(&im->ino_lock); } -void add_dirty_inode(struct f2fs_sb_info *sbi, nid_t ino, int type) +void f2fs_add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type) { /* add new dirty ino entry into list */ - __add_ino_entry(sbi, ino, type); + __add_ino_entry(sbi, ino, 0, type); } -void remove_dirty_inode(struct f2fs_sb_info *sbi, nid_t ino, int type) +void f2fs_remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type) { /* remove dirty ino entry from list */ __remove_ino_entry(sbi, ino, type); } /* mode should be APPEND_INO or UPDATE_INO */ -bool exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode) +bool f2fs_exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode) { struct inode_management *im = &sbi->im[mode]; struct ino_entry *e; @@ -434,12 +502,12 @@ bool exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode) return e ? true : false; } -void release_dirty_inode(struct f2fs_sb_info *sbi) +void f2fs_release_ino_entry(struct f2fs_sb_info *sbi, bool all) { struct ino_entry *e, *tmp; int i; - for (i = APPEND_INO; i <= UPDATE_INO; i++) { + for (i = all ? ORPHAN_INO : APPEND_INO; i < MAX_INO_ENTRY; i++) { struct inode_management *im = &sbi->im[i]; spin_lock(&im->ino_lock); @@ -453,12 +521,40 @@ void release_dirty_inode(struct f2fs_sb_info *sbi) } } -int acquire_orphan_inode(struct f2fs_sb_info *sbi) +void f2fs_set_dirty_device(struct f2fs_sb_info *sbi, nid_t ino, + unsigned int devidx, int type) +{ + __add_ino_entry(sbi, ino, devidx, type); +} + +bool f2fs_is_dirty_device(struct f2fs_sb_info *sbi, nid_t ino, + unsigned int devidx, int type) +{ + struct inode_management *im = &sbi->im[type]; + struct ino_entry *e; + bool is_dirty = false; + + spin_lock(&im->ino_lock); + e = radix_tree_lookup(&im->ino_root, ino); + if (e && f2fs_test_bit(devidx, (char *)&e->dirty_device)) + is_dirty = true; + spin_unlock(&im->ino_lock); + return is_dirty; +} + +int f2fs_acquire_orphan_inode(struct f2fs_sb_info *sbi) { struct inode_management *im = &sbi->im[ORPHAN_INO]; int err = 0; spin_lock(&im->ino_lock); + + if (time_to_inject(sbi, FAULT_ORPHAN)) { + spin_unlock(&im->ino_lock); + f2fs_show_injection_info(FAULT_ORPHAN); + return -ENOSPC; + } + if (unlikely(im->ino_num >= sbi->max_orphans)) err = -ENOSPC; else @@ -468,7 +564,7 @@ int acquire_orphan_inode(struct f2fs_sb_info *sbi) return err; } -void release_orphan_inode(struct f2fs_sb_info *sbi) +void f2fs_release_orphan_inode(struct f2fs_sb_info *sbi) { struct inode_management *im = &sbi->im[ORPHAN_INO]; @@ -478,13 +574,14 @@ void release_orphan_inode(struct f2fs_sb_info *sbi) spin_unlock(&im->ino_lock); } -void add_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) +void f2fs_add_orphan_inode(struct inode *inode) { /* add new orphan ino entry into list */ - __add_ino_entry(sbi, ino, ORPHAN_INO); + __add_ino_entry(F2FS_I_SB(inode), inode->i_ino, 0, ORPHAN_INO); + f2fs_update_inode_page(inode); } -void remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) +void f2fs_remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) { /* remove orphan entry from orphan list */ __remove_ino_entry(sbi, ino, ORPHAN_INO); @@ -493,8 +590,10 @@ void remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) { struct inode *inode; + struct node_info ni; + int err; - inode = f2fs_iget(sbi->sb, ino); + inode = f2fs_iget_retry(sbi->sb, ino); if (IS_ERR(inode)) { /* * there should be a bug that we can't find the entry @@ -504,44 +603,103 @@ static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) return PTR_ERR(inode); } + err = dquot_initialize(inode); + if (err) { + iput(inode); + goto err_out; + } + clear_nlink(inode); /* truncate all the data during iput */ iput(inode); + + err = f2fs_get_node_info(sbi, ino, &ni); + if (err) + goto err_out; + + /* ENOMEM was fully retried in f2fs_evict_inode. */ + if (ni.blk_addr != NULL_ADDR) { + err = -EIO; + goto err_out; + } return 0; + +err_out: + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_msg(sbi->sb, KERN_WARNING, + "%s: orphan failed (ino=%x), run fsck to fix.", + __func__, ino); + return err; } -int recover_orphan_inodes(struct f2fs_sb_info *sbi) +int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi) { block_t start_blk, orphan_blocks, i, j; - int err; + unsigned int s_flags = sbi->sb->s_flags; + int err = 0; +#ifdef CONFIG_QUOTA + int quota_enabled; +#endif - if (!is_set_ckpt_flags(F2FS_CKPT(sbi), CP_ORPHAN_PRESENT_FLAG)) + if (!is_set_ckpt_flags(sbi, CP_ORPHAN_PRESENT_FLAG)) return 0; + if (s_flags & MS_RDONLY) { + f2fs_msg(sbi->sb, KERN_INFO, "orphan cleanup on readonly fs"); + sbi->sb->s_flags &= ~MS_RDONLY; + } + +#ifdef CONFIG_QUOTA + /* Needed for iput() to work correctly and not trash data */ + sbi->sb->s_flags |= MS_ACTIVE; + + /* + * Turn on quotas which were not enabled for read-only mounts if + * filesystem has quota feature, so that they are updated correctly. + */ + quota_enabled = f2fs_enable_quota_files(sbi, s_flags & MS_RDONLY); +#endif + start_blk = __start_cp_addr(sbi) + 1 + __cp_payload(sbi); orphan_blocks = __start_sum_addr(sbi) - 1 - __cp_payload(sbi); - ra_meta_pages(sbi, start_blk, orphan_blocks, META_CP, true); + f2fs_ra_meta_pages(sbi, start_blk, orphan_blocks, META_CP, true); for (i = 0; i < orphan_blocks; i++) { - struct page *page = get_meta_page(sbi, start_blk + i); + struct page *page; struct f2fs_orphan_block *orphan_blk; + page = f2fs_get_meta_page(sbi, start_blk + i); + if (IS_ERR(page)) { + err = PTR_ERR(page); + goto out; + } + orphan_blk = (struct f2fs_orphan_block *)page_address(page); for (j = 0; j < le32_to_cpu(orphan_blk->entry_count); j++) { nid_t ino = le32_to_cpu(orphan_blk->ino[j]); err = recover_orphan_inode(sbi, ino); if (err) { f2fs_put_page(page, 1); - return err; + goto out; } } f2fs_put_page(page, 1); } /* clear Orphan Flag */ - clear_ckpt_flags(F2FS_CKPT(sbi), CP_ORPHAN_PRESENT_FLAG); - return 0; + clear_ckpt_flags(sbi, CP_ORPHAN_PRESENT_FLAG); +out: + set_sbi_flag(sbi, SBI_IS_RECOVERED); + +#ifdef CONFIG_QUOTA + /* Turn quotas off */ + if (quota_enabled) + f2fs_quota_off_umount(sbi->sb); +#endif + sbi->sb->s_flags = s_flags; /* Restore MS_RDONLY status */ + + return err; } static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk) @@ -567,7 +725,7 @@ static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk) /* loop for each orphan inode entry and write them in Jornal block */ list_for_each_entry(orphan, head, list) { if (!page) { - page = grab_meta_page(sbi, start_blk++); + page = f2fs_grab_meta_page(sbi, start_blk++); orphan_blk = (struct f2fs_orphan_block *)page_address(page); memset(orphan_blk, 0, sizeof(*orphan_blk)); @@ -601,59 +759,80 @@ static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk) } } -static struct page *validate_checkpoint(struct f2fs_sb_info *sbi, - block_t cp_addr, unsigned long long *version) +static int get_checkpoint_version(struct f2fs_sb_info *sbi, block_t cp_addr, + struct f2fs_checkpoint **cp_block, struct page **cp_page, + unsigned long long *version) { - struct page *cp_page_1, *cp_page_2 = NULL; unsigned long blk_size = sbi->blocksize; - struct f2fs_checkpoint *cp_block; - unsigned long long cur_version = 0, pre_version = 0; - size_t crc_offset; + size_t crc_offset = 0; __u32 crc = 0; - /* Read the 1st cp block in this CP pack */ - cp_page_1 = get_meta_page(sbi, cp_addr); + *cp_page = f2fs_get_meta_page(sbi, cp_addr); + if (IS_ERR(*cp_page)) + return PTR_ERR(*cp_page); - /* get the version number */ - cp_block = (struct f2fs_checkpoint *)page_address(cp_page_1); - crc_offset = le32_to_cpu(cp_block->checksum_offset); - if (crc_offset >= blk_size) - goto invalid_cp1; + *cp_block = (struct f2fs_checkpoint *)page_address(*cp_page); - crc = le32_to_cpu(*((__le32 *)((unsigned char *)cp_block + crc_offset))); - if (!f2fs_crc_valid(crc, cp_block, crc_offset)) - goto invalid_cp1; + crc_offset = le32_to_cpu((*cp_block)->checksum_offset); + if (crc_offset > (blk_size - sizeof(__le32))) { + f2fs_put_page(*cp_page, 1); + f2fs_msg(sbi->sb, KERN_WARNING, + "invalid crc_offset: %zu", crc_offset); + return -EINVAL; + } - pre_version = cur_cp_version(cp_block); + crc = cur_cp_crc(*cp_block); + if (!f2fs_crc_valid(sbi, crc, *cp_block, crc_offset)) { + f2fs_put_page(*cp_page, 1); + f2fs_msg(sbi->sb, KERN_WARNING, "invalid crc value"); + return -EINVAL; + } - /* Read the 2nd cp block in this CP pack */ - cp_addr += le32_to_cpu(cp_block->cp_pack_total_block_count) - 1; - cp_page_2 = get_meta_page(sbi, cp_addr); + *version = cur_cp_version(*cp_block); + return 0; +} - cp_block = (struct f2fs_checkpoint *)page_address(cp_page_2); - crc_offset = le32_to_cpu(cp_block->checksum_offset); - if (crc_offset >= blk_size) - goto invalid_cp2; +static struct page *validate_checkpoint(struct f2fs_sb_info *sbi, + block_t cp_addr, unsigned long long *version) +{ + struct page *cp_page_1 = NULL, *cp_page_2 = NULL; + struct f2fs_checkpoint *cp_block = NULL; + unsigned long long cur_version = 0, pre_version = 0; + int err; - crc = le32_to_cpu(*((__le32 *)((unsigned char *)cp_block + crc_offset))); - if (!f2fs_crc_valid(crc, cp_block, crc_offset)) - goto invalid_cp2; + err = get_checkpoint_version(sbi, cp_addr, &cp_block, + &cp_page_1, version); + if (err) + return NULL; + + if (le32_to_cpu(cp_block->cp_pack_total_block_count) > + sbi->blocks_per_seg) { + f2fs_msg(sbi->sb, KERN_WARNING, + "invalid cp_pack_total_block_count:%u", + le32_to_cpu(cp_block->cp_pack_total_block_count)); + goto invalid_cp; + } + pre_version = *version; - cur_version = cur_cp_version(cp_block); + cp_addr += le32_to_cpu(cp_block->cp_pack_total_block_count) - 1; + err = get_checkpoint_version(sbi, cp_addr, &cp_block, + &cp_page_2, version); + if (err) + goto invalid_cp; + cur_version = *version; if (cur_version == pre_version) { *version = cur_version; f2fs_put_page(cp_page_2, 1); return cp_page_1; } -invalid_cp2: f2fs_put_page(cp_page_2, 1); -invalid_cp1: +invalid_cp: f2fs_put_page(cp_page_1, 1); return NULL; } -int get_valid_checkpoint(struct f2fs_sb_info *sbi) +int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi) { struct f2fs_checkpoint *cp_block; struct f2fs_super_block *fsb = sbi->raw_super; @@ -665,7 +844,8 @@ int get_valid_checkpoint(struct f2fs_sb_info *sbi) block_t cp_blk_no; int i; - sbi->ckpt = kzalloc(cp_blks * blk_size, GFP_KERNEL); + sbi->ckpt = f2fs_kzalloc(sbi, array_size(blk_size, cp_blks), + GFP_KERNEL); if (!sbi->ckpt) return -ENOMEM; /* @@ -696,6 +876,15 @@ int get_valid_checkpoint(struct f2fs_sb_info *sbi) cp_block = (struct f2fs_checkpoint *)page_address(cur_page); memcpy(sbi->ckpt, cp_block, blk_size); + if (cur_page == cp1) + sbi->cur_cp_pack = 1; + else + sbi->cur_cp_pack = 2; + + /* Sanity checking of checkpoint */ + if (f2fs_sanity_check_ckpt(sbi)) + goto free_fail_no_cp; + if (cp_blks <= 1) goto done; @@ -707,7 +896,9 @@ int get_valid_checkpoint(struct f2fs_sb_info *sbi) void *sit_bitmap_ptr; unsigned char *ckpt = (unsigned char *)sbi->ckpt; - cur_page = get_meta_page(sbi, cp_blk_no + i); + cur_page = f2fs_get_meta_page(sbi, cp_blk_no + i); + if (IS_ERR(cur_page)) + goto free_fail_no_cp; sit_bitmap_ptr = page_address(cur_page); memcpy(ckpt + i * blk_size, sit_bitmap_ptr, blk_size); f2fs_put_page(cur_page, 1); @@ -717,137 +908,193 @@ done: f2fs_put_page(cp2, 1); return 0; +free_fail_no_cp: + f2fs_put_page(cp1, 1); + f2fs_put_page(cp2, 1); fail_no_cp: kfree(sbi->ckpt); return -EINVAL; } -static int __add_dirty_inode(struct inode *inode, struct inode_entry *new) +static void __add_dirty_inode(struct inode *inode, enum inode_type type) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + int flag = (type == DIR_INODE) ? FI_DIRTY_DIR : FI_DIRTY_FILE; - if (is_inode_flag_set(F2FS_I(inode), FI_DIRTY_DIR)) - return -EEXIST; + if (is_inode_flag_set(inode, flag)) + return; - set_inode_flag(F2FS_I(inode), FI_DIRTY_DIR); - F2FS_I(inode)->dirty_dir = new; - list_add_tail(&new->list, &sbi->dir_inode_list); - stat_inc_dirty_dir(sbi); - return 0; + set_inode_flag(inode, flag); + if (!f2fs_is_volatile_file(inode)) + list_add_tail(&F2FS_I(inode)->dirty_list, + &sbi->inode_list[type]); + stat_inc_dirty_inode(sbi, type); } -void update_dirty_page(struct inode *inode, struct page *page) +static void __remove_dirty_inode(struct inode *inode, enum inode_type type) { - struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct inode_entry *new; - int ret = 0; + int flag = (type == DIR_INODE) ? FI_DIRTY_DIR : FI_DIRTY_FILE; - if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode) && - !S_ISLNK(inode->i_mode)) + if (get_dirty_pages(inode) || !is_inode_flag_set(inode, flag)) return; - if (!S_ISDIR(inode->i_mode)) { - inode_inc_dirty_pages(inode); - goto out; - } - - new = f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS); - new->inode = inode; - INIT_LIST_HEAD(&new->list); - - spin_lock(&sbi->dir_inode_lock); - ret = __add_dirty_inode(inode, new); - inode_inc_dirty_pages(inode); - spin_unlock(&sbi->dir_inode_lock); - - if (ret) - kmem_cache_free(inode_entry_slab, new); -out: - SetPagePrivate(page); - f2fs_trace_pid(page); + list_del_init(&F2FS_I(inode)->dirty_list); + clear_inode_flag(inode, flag); + stat_dec_dirty_inode(F2FS_I_SB(inode), type); } -void add_dirty_dir_inode(struct inode *inode) +void f2fs_update_dirty_page(struct inode *inode, struct page *page) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct inode_entry *new = - f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS); - int ret = 0; + enum inode_type type = S_ISDIR(inode->i_mode) ? DIR_INODE : FILE_INODE; - new->inode = inode; - INIT_LIST_HEAD(&new->list); + if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode) && + !S_ISLNK(inode->i_mode)) + return; - spin_lock(&sbi->dir_inode_lock); - ret = __add_dirty_inode(inode, new); - spin_unlock(&sbi->dir_inode_lock); + spin_lock(&sbi->inode_lock[type]); + if (type != FILE_INODE || test_opt(sbi, DATA_FLUSH)) + __add_dirty_inode(inode, type); + inode_inc_dirty_pages(inode); + spin_unlock(&sbi->inode_lock[type]); - if (ret) - kmem_cache_free(inode_entry_slab, new); + SetPagePrivate(page); + f2fs_trace_pid(page); } -void remove_dirty_dir_inode(struct inode *inode) +void f2fs_remove_dirty_inode(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct inode_entry *entry; + enum inode_type type = S_ISDIR(inode->i_mode) ? DIR_INODE : FILE_INODE; - if (!S_ISDIR(inode->i_mode)) + if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode) && + !S_ISLNK(inode->i_mode)) return; - spin_lock(&sbi->dir_inode_lock); - if (get_dirty_pages(inode) || - !is_inode_flag_set(F2FS_I(inode), FI_DIRTY_DIR)) { - spin_unlock(&sbi->dir_inode_lock); + if (type == FILE_INODE && !test_opt(sbi, DATA_FLUSH)) return; - } - entry = F2FS_I(inode)->dirty_dir; - list_del(&entry->list); - F2FS_I(inode)->dirty_dir = NULL; - clear_inode_flag(F2FS_I(inode), FI_DIRTY_DIR); - stat_dec_dirty_dir(sbi); - spin_unlock(&sbi->dir_inode_lock); - kmem_cache_free(inode_entry_slab, entry); - - /* Only from the recovery routine */ - if (is_inode_flag_set(F2FS_I(inode), FI_DELAY_IPUT)) { - clear_inode_flag(F2FS_I(inode), FI_DELAY_IPUT); - iput(inode); - } + spin_lock(&sbi->inode_lock[type]); + __remove_dirty_inode(inode, type); + spin_unlock(&sbi->inode_lock[type]); } -void sync_dirty_dir_inodes(struct f2fs_sb_info *sbi) +int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type) { struct list_head *head; - struct inode_entry *entry; struct inode *inode; + struct f2fs_inode_info *fi; + bool is_dir = (type == DIR_INODE); + unsigned long ino = 0; + + trace_f2fs_sync_dirty_inodes_enter(sbi->sb, is_dir, + get_pages(sbi, is_dir ? + F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA)); retry: if (unlikely(f2fs_cp_error(sbi))) - return; + return -EIO; - spin_lock(&sbi->dir_inode_lock); + spin_lock(&sbi->inode_lock[type]); - head = &sbi->dir_inode_list; + head = &sbi->inode_list[type]; if (list_empty(head)) { - spin_unlock(&sbi->dir_inode_lock); - return; + spin_unlock(&sbi->inode_lock[type]); + trace_f2fs_sync_dirty_inodes_exit(sbi->sb, is_dir, + get_pages(sbi, is_dir ? + F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA)); + return 0; } - entry = list_entry(head->next, struct inode_entry, list); - inode = igrab(entry->inode); - spin_unlock(&sbi->dir_inode_lock); + fi = list_first_entry(head, struct f2fs_inode_info, dirty_list); + inode = igrab(&fi->vfs_inode); + spin_unlock(&sbi->inode_lock[type]); if (inode) { + unsigned long cur_ino = inode->i_ino; + + if (is_dir) + F2FS_I(inode)->cp_task = current; + filemap_fdatawrite(inode->i_mapping); + + if (is_dir) + F2FS_I(inode)->cp_task = NULL; + iput(inode); + /* We need to give cpu to another writers. */ + if (ino == cur_ino) + cond_resched(); + else + ino = cur_ino; } else { /* * We should submit bio, since it exists several * wribacking dentry pages in the freeing inode. */ - f2fs_submit_merged_bio(sbi, DATA, WRITE); + f2fs_submit_merged_write(sbi, DATA); cond_resched(); } goto retry; } +int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi) +{ + struct list_head *head = &sbi->inode_list[DIRTY_META]; + struct inode *inode; + struct f2fs_inode_info *fi; + s64 total = get_pages(sbi, F2FS_DIRTY_IMETA); + + while (total--) { + if (unlikely(f2fs_cp_error(sbi))) + return -EIO; + + spin_lock(&sbi->inode_lock[DIRTY_META]); + if (list_empty(head)) { + spin_unlock(&sbi->inode_lock[DIRTY_META]); + return 0; + } + fi = list_first_entry(head, struct f2fs_inode_info, + gdirty_list); + inode = igrab(&fi->vfs_inode); + spin_unlock(&sbi->inode_lock[DIRTY_META]); + if (inode) { + sync_inode_metadata(inode, 0); + + /* it's on eviction */ + if (is_inode_flag_set(inode, FI_DIRTY_INODE)) + f2fs_update_inode_page(inode); + iput(inode); + } + } + return 0; +} + +static void __prepare_cp_block(struct f2fs_sb_info *sbi) +{ + struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); + struct f2fs_nm_info *nm_i = NM_I(sbi); + nid_t last_nid = nm_i->next_scan_nid; + + next_free_nid(sbi, &last_nid); + ckpt->valid_block_count = cpu_to_le64(valid_user_blocks(sbi)); + ckpt->valid_node_count = cpu_to_le32(valid_node_count(sbi)); + ckpt->valid_inode_count = cpu_to_le32(valid_inode_count(sbi)); + ckpt->next_free_nid = cpu_to_le32(last_nid); +} + +static bool __need_flush_quota(struct f2fs_sb_info *sbi) +{ + if (!is_journalled_quota(sbi)) + return false; + if (is_sbi_flag_set(sbi, SBI_QUOTA_SKIP_FLUSH)) + return false; + if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_REPAIR)) + return false; + if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_FLUSH)) + return true; + if (get_pages(sbi, F2FS_DIRTY_QDATA)) + return true; + return false; +} + /* * Freeze all the FS-operations for checkpoint. */ @@ -859,40 +1106,91 @@ static int block_operations(struct f2fs_sb_info *sbi) .for_reclaim = 0, }; struct blk_plug plug; - int err = 0; + int err = 0, cnt = 0; blk_start_plug(&plug); -retry_flush_dents: +retry_flush_quotas: + if (__need_flush_quota(sbi)) { + int locked; + + if (++cnt > DEFAULT_RETRY_QUOTA_FLUSH_COUNT) { + set_sbi_flag(sbi, SBI_QUOTA_SKIP_FLUSH); + f2fs_lock_all(sbi); + goto retry_flush_dents; + } + clear_sbi_flag(sbi, SBI_QUOTA_NEED_FLUSH); + + /* only failed during mount/umount/freeze/quotactl */ + locked = down_read_trylock(&sbi->sb->s_umount); + f2fs_quota_sync(sbi->sb, -1); + if (locked) + up_read(&sbi->sb->s_umount); + } + f2fs_lock_all(sbi); + if (__need_flush_quota(sbi)) { + f2fs_unlock_all(sbi); + cond_resched(); + goto retry_flush_quotas; + } + +retry_flush_dents: /* write all the dirty dentry pages */ if (get_pages(sbi, F2FS_DIRTY_DENTS)) { f2fs_unlock_all(sbi); - sync_dirty_dir_inodes(sbi); - if (unlikely(f2fs_cp_error(sbi))) { - err = -EIO; + err = f2fs_sync_dirty_inodes(sbi, DIR_INODE); + if (err) goto out; - } - goto retry_flush_dents; + cond_resched(); + goto retry_flush_quotas; } /* * POR: we should ensure that there are no dirty node pages - * until finishing nat/sit flush. + * until finishing nat/sit flush. inode->i_blocks can be updated. */ + down_write(&sbi->node_change); + + if (__need_flush_quota(sbi)) { + up_write(&sbi->node_change); + f2fs_unlock_all(sbi); + goto retry_flush_quotas; + } + + if (get_pages(sbi, F2FS_DIRTY_IMETA)) { + up_write(&sbi->node_change); + f2fs_unlock_all(sbi); + err = f2fs_sync_inode_meta(sbi); + if (err) + goto out; + cond_resched(); + goto retry_flush_quotas; + } + retry_flush_nodes: down_write(&sbi->node_write); if (get_pages(sbi, F2FS_DIRTY_NODES)) { up_write(&sbi->node_write); - sync_node_pages(sbi, 0, &wbc); - if (unlikely(f2fs_cp_error(sbi))) { + atomic_inc(&sbi->wb_sync_req[NODE]); + err = f2fs_sync_node_pages(sbi, &wbc, false, FS_CP_NODE_IO); + atomic_dec(&sbi->wb_sync_req[NODE]); + if (err) { + up_write(&sbi->node_change); f2fs_unlock_all(sbi); - err = -EIO; goto out; } + cond_resched(); goto retry_flush_nodes; } + + /* + * sbi->node_change is used only for AIO write_begin path which produces + * dirty node blocks and some checkpoint values by block allocation. + */ + __prepare_cp_block(sbi); + up_write(&sbi->node_change); out: blk_finish_plug(&plug); return err; @@ -904,58 +1202,144 @@ static void unblock_operations(struct f2fs_sb_info *sbi) f2fs_unlock_all(sbi); } -static void wait_on_all_pages_writeback(struct f2fs_sb_info *sbi) +void f2fs_wait_on_all_pages_writeback(struct f2fs_sb_info *sbi) { DEFINE_WAIT(wait); for (;;) { prepare_to_wait(&sbi->cp_wait, &wait, TASK_UNINTERRUPTIBLE); - if (!get_pages(sbi, F2FS_WRITEBACK)) + if (!get_pages(sbi, F2FS_WB_CP_DATA)) break; - io_schedule(); + if (unlikely(f2fs_cp_error(sbi))) + break; + + io_schedule_timeout(5*HZ); } finish_wait(&sbi->cp_wait, &wait); } -static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) +static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc) +{ + unsigned long orphan_num = sbi->im[ORPHAN_INO].ino_num; + struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); + unsigned long flags; + + spin_lock_irqsave(&sbi->cp_lock, flags); + + if ((cpc->reason & CP_UMOUNT) && + le32_to_cpu(ckpt->cp_pack_total_block_count) > + sbi->blocks_per_seg - NM_I(sbi)->nat_bits_blocks) + disable_nat_bits(sbi, false); + + if (cpc->reason & CP_TRIMMED) + __set_ckpt_flags(ckpt, CP_TRIMMED_FLAG); + else + __clear_ckpt_flags(ckpt, CP_TRIMMED_FLAG); + + if (cpc->reason & CP_UMOUNT) + __set_ckpt_flags(ckpt, CP_UMOUNT_FLAG); + else + __clear_ckpt_flags(ckpt, CP_UMOUNT_FLAG); + + if (cpc->reason & CP_FASTBOOT) + __set_ckpt_flags(ckpt, CP_FASTBOOT_FLAG); + else + __clear_ckpt_flags(ckpt, CP_FASTBOOT_FLAG); + + if (orphan_num) + __set_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG); + else + __clear_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG); + + if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) + __set_ckpt_flags(ckpt, CP_FSCK_FLAG); + + if (is_sbi_flag_set(sbi, SBI_CP_DISABLED)) + __set_ckpt_flags(ckpt, CP_DISABLED_FLAG); + else + __clear_ckpt_flags(ckpt, CP_DISABLED_FLAG); + + if (is_sbi_flag_set(sbi, SBI_QUOTA_SKIP_FLUSH)) + __set_ckpt_flags(ckpt, CP_QUOTA_NEED_FSCK_FLAG); + else + __clear_ckpt_flags(ckpt, CP_QUOTA_NEED_FSCK_FLAG); + + if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_REPAIR)) + __set_ckpt_flags(ckpt, CP_QUOTA_NEED_FSCK_FLAG); + + /* set this flag to activate crc|cp_ver for recovery */ + __set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG); + __clear_ckpt_flags(ckpt, CP_NOCRC_RECOVERY_FLAG); + + spin_unlock_irqrestore(&sbi->cp_lock, flags); +} + +static void commit_checkpoint(struct f2fs_sb_info *sbi, + void *src, block_t blk_addr) +{ + struct writeback_control wbc = { + .for_reclaim = 0, + }; + + /* + * pagevec_lookup_tag and lock_page again will take + * some extra time. Therefore, f2fs_update_meta_pages and + * f2fs_sync_meta_pages are combined in this function. + */ + struct page *page = f2fs_grab_meta_page(sbi, blk_addr); + int err; + + memcpy(page_address(page), src, PAGE_SIZE); + set_page_dirty(page); + + f2fs_wait_on_page_writeback(page, META, true); + f2fs_bug_on(sbi, PageWriteback(page)); + if (unlikely(!clear_page_dirty_for_io(page))) + f2fs_bug_on(sbi, 1); + + /* writeout cp pack 2 page */ + err = __f2fs_write_meta_page(page, &wbc, FS_CP_META_IO); + if (unlikely(err && f2fs_cp_error(sbi))) { + f2fs_put_page(page, 1); + return; + } + + f2fs_bug_on(sbi, err); + f2fs_put_page(page, 0); + + /* submit checkpoint (with barrier if NOBARRIER is not set) */ + f2fs_submit_merged_write(sbi, META_FLUSH); +} + +static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) { struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); - struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_WARM_NODE); struct f2fs_nm_info *nm_i = NM_I(sbi); - unsigned long orphan_num = sbi->im[ORPHAN_INO].ino_num; - nid_t last_nid = nm_i->next_scan_nid; + unsigned long orphan_num = sbi->im[ORPHAN_INO].ino_num, flags; block_t start_blk; unsigned int data_sum_blocks, orphan_blocks; __u32 crc32 = 0; int i; int cp_payload_blks = __cp_payload(sbi); - block_t discard_blk = NEXT_FREE_BLKADDR(sbi, curseg); - bool invalidate = false; - - /* - * This avoids to conduct wrong roll-forward operations and uses - * metapages, so should be called prior to sync_meta_pages below. - */ - if (discard_next_dnode(sbi, discard_blk)) - invalidate = true; + struct super_block *sb = sbi->sb; + struct curseg_info *seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE); + u64 kbytes_written; + int err; /* Flush all the NAT/SIT pages */ while (get_pages(sbi, F2FS_DIRTY_META)) { - sync_meta_pages(sbi, META, LONG_MAX); + f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO); if (unlikely(f2fs_cp_error(sbi))) - return; + break; } - next_free_nid(sbi, &last_nid); - /* * modify checkpoint * version number is already updated */ - ckpt->elapsed_time = cpu_to_le64(get_mtime(sbi)); - ckpt->valid_block_count = cpu_to_le64(valid_user_blocks(sbi)); + ckpt->elapsed_time = cpu_to_le64(get_mtime(sbi, true)); ckpt->free_segment_count = cpu_to_le32(free_segments(sbi)); for (i = 0; i < NR_CURSEG_NODE_TYPE; i++) { ckpt->cur_node_segno[i] = @@ -974,16 +1358,14 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) curseg_alloc_type(sbi, i + CURSEG_HOT_DATA); } - ckpt->valid_node_count = cpu_to_le32(valid_node_count(sbi)); - ckpt->valid_inode_count = cpu_to_le32(valid_inode_count(sbi)); - ckpt->next_free_nid = cpu_to_le32(last_nid); - /* 2 cp + n data seg summary + orphan inode blocks */ - data_sum_blocks = npages_for_summary_flush(sbi, false); + data_sum_blocks = f2fs_npages_for_summary_flush(sbi, false); + spin_lock_irqsave(&sbi->cp_lock, flags); if (data_sum_blocks < NR_CURSEG_DATA_TYPE) - set_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG); + __set_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG); else - clear_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG); + __clear_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG); + spin_unlock_irqrestore(&sbi->cp_lock, flags); orphan_blocks = GET_ORPHAN_BLOCKS(orphan_num); ckpt->cp_pack_start_sum = cpu_to_le32(1 + cp_payload_blks + @@ -998,45 +1380,47 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) cp_payload_blks + data_sum_blocks + orphan_blocks); - if (cpc->reason == CP_UMOUNT) - set_ckpt_flags(ckpt, CP_UMOUNT_FLAG); - else - clear_ckpt_flags(ckpt, CP_UMOUNT_FLAG); - - if (cpc->reason == CP_FASTBOOT) - set_ckpt_flags(ckpt, CP_FASTBOOT_FLAG); - else - clear_ckpt_flags(ckpt, CP_FASTBOOT_FLAG); - - if (orphan_num) - set_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG); - else - clear_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG); - - if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) - set_ckpt_flags(ckpt, CP_FSCK_FLAG); + /* update ckpt flag for checkpoint */ + update_ckpt_flags(sbi, cpc); /* update SIT/NAT bitmap */ get_sit_bitmap(sbi, __bitmap_ptr(sbi, SIT_BITMAP)); get_nat_bitmap(sbi, __bitmap_ptr(sbi, NAT_BITMAP)); - crc32 = f2fs_crc32(ckpt, le32_to_cpu(ckpt->checksum_offset)); + crc32 = f2fs_crc32(sbi, ckpt, le32_to_cpu(ckpt->checksum_offset)); *((__le32 *)((unsigned char *)ckpt + le32_to_cpu(ckpt->checksum_offset))) = cpu_to_le32(crc32); - start_blk = __start_cp_addr(sbi); + start_blk = __start_cp_next_addr(sbi); - /* need to wait for end_io results */ - wait_on_all_pages_writeback(sbi); - if (unlikely(f2fs_cp_error(sbi))) - return; + /* write nat bits */ + if (enabled_nat_bits(sbi, cpc)) { + __u64 cp_ver = cur_cp_version(ckpt); + block_t blk; + + cp_ver |= ((__u64)crc32 << 32); + *(__le64 *)nm_i->nat_bits = cpu_to_le64(cp_ver); + + blk = start_blk + sbi->blocks_per_seg - nm_i->nat_bits_blocks; + for (i = 0; i < nm_i->nat_bits_blocks; i++) + f2fs_update_meta_page(sbi, nm_i->nat_bits + + (i << F2FS_BLKSIZE_BITS), blk + i); + + /* Flush all the NAT BITS pages */ + while (get_pages(sbi, F2FS_DIRTY_META)) { + f2fs_sync_meta_pages(sbi, META, LONG_MAX, + FS_CP_META_IO); + if (unlikely(f2fs_cp_error(sbi))) + break; + } + } /* write out checkpoint buffer at block 0 */ - update_meta_page(sbi, ckpt, start_blk++); + f2fs_update_meta_page(sbi, ckpt, start_blk++); for (i = 1; i < 1 + cp_payload_blks; i++) - update_meta_page(sbi, (char *)ckpt + i * F2FS_BLKSIZE, + f2fs_update_meta_page(sbi, (char *)ckpt + i * F2FS_BLKSIZE, start_blk++); if (orphan_num) { @@ -1044,81 +1428,127 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) start_blk += orphan_blocks; } - write_data_summaries(sbi, start_blk); + f2fs_write_data_summaries(sbi, start_blk); start_blk += data_sum_blocks; - if (__remain_node_summaries(cpc->reason)) { - write_node_summaries(sbi, start_blk); - start_blk += NR_CURSEG_NODE_TYPE; - } - /* writeout checkpoint block */ - update_meta_page(sbi, ckpt, start_blk); + /* Record write statistics in the hot node summary */ + kbytes_written = sbi->kbytes_written; + if (sb->s_bdev->bd_part) + kbytes_written += BD_PART_WRITTEN(sbi); - /* wait for previous submitted node/meta pages writeback */ - wait_on_all_pages_writeback(sbi); + seg_i->journal->info.kbytes_written = cpu_to_le64(kbytes_written); - if (unlikely(f2fs_cp_error(sbi))) - return; - - filemap_fdatawait_range(NODE_MAPPING(sbi), 0, LONG_MAX); - filemap_fdatawait_range(META_MAPPING(sbi), 0, LONG_MAX); + if (__remain_node_summaries(cpc->reason)) { + f2fs_write_node_summaries(sbi, start_blk); + start_blk += NR_CURSEG_NODE_TYPE; + } /* update user_block_counts */ sbi->last_valid_block_count = sbi->total_valid_block_count; - sbi->alloc_valid_block_count = 0; + percpu_counter_set(&sbi->alloc_valid_block_count, 0); - /* Here, we only have one bio having CP pack */ - sync_meta_pages(sbi, META_FLUSH, LONG_MAX); + /* Here, we have one bio having CP pack except cp pack 2 page */ + f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO); /* wait for previous submitted meta pages writeback */ - wait_on_all_pages_writeback(sbi); + f2fs_wait_on_all_pages_writeback(sbi); + + /* flush all device cache */ + err = f2fs_flush_device_cache(sbi); + if (err) + return err; + + /* barrier and flush checkpoint cp pack 2 page if it can */ + commit_checkpoint(sbi, ckpt, start_blk); + f2fs_wait_on_all_pages_writeback(sbi); /* - * invalidate meta page which is used temporarily for zeroing out - * block at the end of warm node chain. + * invalidate intermediate page cache borrowed from meta inode + * which are used for migration of encrypted inode's blocks. */ - if (invalidate) - invalidate_mapping_pages(META_MAPPING(sbi), discard_blk, - discard_blk); + if (f2fs_sb_has_encrypt(sbi->sb)) + invalidate_mapping_pages(META_MAPPING(sbi), + MAIN_BLKADDR(sbi), MAX_BLKADDR(sbi) - 1); - release_dirty_inode(sbi); + f2fs_release_ino_entry(sbi, false); - if (unlikely(f2fs_cp_error(sbi))) - return; + f2fs_reset_fsync_node_info(sbi); - clear_prefree_segments(sbi, cpc); clear_sbi_flag(sbi, SBI_IS_DIRTY); + clear_sbi_flag(sbi, SBI_NEED_CP); + clear_sbi_flag(sbi, SBI_QUOTA_SKIP_FLUSH); + sbi->unusable_block_count = 0; + __set_cp_next_pack(sbi); + + /* + * redirty superblock if metadata like node page or inode cache is + * updated during writing checkpoint. + */ + if (get_pages(sbi, F2FS_DIRTY_NODES) || + get_pages(sbi, F2FS_DIRTY_IMETA)) + set_sbi_flag(sbi, SBI_IS_DIRTY); + + f2fs_bug_on(sbi, get_pages(sbi, F2FS_DIRTY_DENTS)); + + return unlikely(f2fs_cp_error(sbi)) ? -EIO : 0; } /* * We guarantee that this checkpoint procedure will not fail. */ -void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) +int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) { struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); unsigned long long ckpt_ver; + int err = 0; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { + if (cpc->reason != CP_PAUSE) + return 0; + f2fs_msg(sbi->sb, KERN_WARNING, + "Start checkpoint disabled!"); + } mutex_lock(&sbi->cp_mutex); if (!is_sbi_flag_set(sbi, SBI_IS_DIRTY) && - (cpc->reason == CP_FASTBOOT || cpc->reason == CP_SYNC || - (cpc->reason == CP_DISCARD && !sbi->discard_blks))) + ((cpc->reason & CP_FASTBOOT) || (cpc->reason & CP_SYNC) || + ((cpc->reason & CP_DISCARD) && !sbi->discard_blks))) goto out; - if (unlikely(f2fs_cp_error(sbi))) + if (unlikely(f2fs_cp_error(sbi))) { + err = -EIO; goto out; - if (f2fs_readonly(sbi->sb)) + } + if (f2fs_readonly(sbi->sb)) { + err = -EROFS; goto out; + } trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "start block_ops"); - if (block_operations(sbi)) + err = block_operations(sbi); + if (err) goto out; trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish block_ops"); - f2fs_submit_merged_bio(sbi, DATA, WRITE); - f2fs_submit_merged_bio(sbi, NODE, WRITE); - f2fs_submit_merged_bio(sbi, META, WRITE); + f2fs_flush_merged_writes(sbi); + + /* this is the case of multiple fstrims without any changes */ + if (cpc->reason & CP_DISCARD) { + if (!f2fs_exist_trim_candidates(sbi, cpc)) { + unblock_operations(sbi); + goto out; + } + + if (NM_I(sbi)->dirty_nat_cnt == 0 && + SIT_I(sbi)->dirty_sentries == 0 && + prefree_segments(sbi) == 0) { + f2fs_flush_sit_entries(sbi, cpc); + f2fs_clear_prefree_segments(sbi, cpc); + unblock_operations(sbi); + goto out; + } + } /* * update checkpoint pack index @@ -1129,27 +1559,35 @@ void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) ckpt->checkpoint_ver = cpu_to_le64(++ckpt_ver); /* write cached NAT/SIT entries to NAT/SIT area */ - flush_nat_entries(sbi); - flush_sit_entries(sbi, cpc); + err = f2fs_flush_nat_entries(sbi, cpc); + if (err) + goto stop; - /* unlock all the fs_lock[] in do_checkpoint() */ - do_checkpoint(sbi, cpc); + f2fs_flush_sit_entries(sbi, cpc); + /* unlock all the fs_lock[] in do_checkpoint() */ + err = do_checkpoint(sbi, cpc); + if (err) + f2fs_release_discard_addrs(sbi); + else + f2fs_clear_prefree_segments(sbi, cpc); +stop: unblock_operations(sbi); stat_inc_cp_count(sbi->stat_info); - if (cpc->reason == CP_RECOVERY) + if (cpc->reason & CP_RECOVERY) f2fs_msg(sbi->sb, KERN_NOTICE, "checkpoint: version = %llx", ckpt_ver); /* do checkpoint periodically */ - sbi->cp_expires = round_jiffies_up(jiffies + HZ * sbi->cp_interval); + f2fs_update_time(sbi, CP_TIME); + trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish checkpoint"); out: mutex_unlock(&sbi->cp_mutex); - trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish checkpoint"); + return err; } -void init_ino_entry_info(struct f2fs_sb_info *sbi) +void f2fs_init_ino_entry_info(struct f2fs_sb_info *sbi) { int i; @@ -1167,23 +1605,23 @@ void init_ino_entry_info(struct f2fs_sb_info *sbi) F2FS_ORPHANS_PER_BLOCK; } -int __init create_checkpoint_caches(void) +int __init f2fs_create_checkpoint_caches(void) { ino_entry_slab = f2fs_kmem_cache_create("f2fs_ino_entry", sizeof(struct ino_entry)); if (!ino_entry_slab) return -ENOMEM; - inode_entry_slab = f2fs_kmem_cache_create("f2fs_inode_entry", + f2fs_inode_entry_slab = f2fs_kmem_cache_create("f2fs_inode_entry", sizeof(struct inode_entry)); - if (!inode_entry_slab) { + if (!f2fs_inode_entry_slab) { kmem_cache_destroy(ino_entry_slab); return -ENOMEM; } return 0; } -void destroy_checkpoint_caches(void) +void f2fs_destroy_checkpoint_caches(void) { kmem_cache_destroy(ino_entry_slab); - kmem_cache_destroy(inode_entry_slab); + kmem_cache_destroy(f2fs_inode_entry_slab); } |