diff -drupN a/fs/f2fs/node.c b/fs/f2fs/node.c --- a/fs/f2fs/node.c 2018-08-06 17:23:04.000000000 +0300 +++ b/fs/f2fs/node.c 2022-06-12 05:28:14.000000000 +0300 @@ -19,10 +19,11 @@ #include "f2fs.h" #include "node.h" #include "segment.h" +#include "xattr.h" #include "trace.h" #include -#define on_build_free_nids(nmi) mutex_is_locked(&nm_i->build_lock) +#define on_build_free_nids(nmi) mutex_is_locked(&(nm_i)->build_lock) static struct kmem_cache *nat_entry_slab; static struct kmem_cache *free_nid_slab; @@ -45,8 +46,8 @@ bool available_free_memory(struct f2fs_s * give 25%, 25%, 50%, 50%, 50% memory for each components respectively */ if (type == FREE_NIDS) { - mem_size = (nm_i->fcnt * sizeof(struct free_nid)) >> - PAGE_SHIFT; + mem_size = (nm_i->nid_cnt[FREE_NID] * + sizeof(struct free_nid)) >> PAGE_SHIFT; res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2); } else if (type == NAT_ENTRIES) { mem_size = (nm_i->nat_cnt * sizeof(struct nat_entry)) >> @@ -62,9 +63,10 @@ bool available_free_memory(struct f2fs_s } else if (type == INO_ENTRIES) { int i; - for (i = 0; i <= UPDATE_INO; i++) - mem_size += (sbi->im[i].ino_num * - sizeof(struct ino_entry)) >> PAGE_SHIFT; + for (i = 0; i < MAX_INO_ENTRY; i++) + mem_size += sbi->im[i].ino_num * + sizeof(struct ino_entry); + mem_size >>= PAGE_SHIFT; res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1); } else if (type == EXTENT_CACHE) { mem_size = (atomic_read(&sbi->total_ext_tree) * @@ -72,6 +74,10 @@ bool available_free_memory(struct f2fs_s atomic_read(&sbi->total_ext_node) * sizeof(struct extent_node)) >> PAGE_SHIFT; res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1); + } else if (type == INMEM_PAGES) { + /* it allows 20% / total_ram for inmemory pages */ + mem_size = get_pages(sbi, F2FS_INMEM_PAGES); + res = mem_size < (val.totalram / 5); } else { if (!sbi->sb->s_bdi->wb.dirty_exceeded) return true; @@ -132,6 +138,42 @@ static struct page *get_next_nat_page(st return dst_page; } +static struct nat_entry *__alloc_nat_entry(nid_t nid, bool no_fail) +{ + struct nat_entry *new; + + if (no_fail) + new = f2fs_kmem_cache_alloc(nat_entry_slab, GFP_F2FS_ZERO); + else + new = kmem_cache_alloc(nat_entry_slab, GFP_F2FS_ZERO); + if (new) { + nat_set_nid(new, nid); + nat_reset_flag(new); + } + return new; +} + +static void __free_nat_entry(struct nat_entry *e) +{ + kmem_cache_free(nat_entry_slab, e); +} + +/* must be locked by nat_tree_lock */ +static struct nat_entry *__init_nat_entry(struct f2fs_nm_info *nm_i, + struct nat_entry *ne, struct f2fs_nat_entry *raw_ne, bool no_fail) +{ + if (no_fail) + f2fs_radix_tree_insert(&nm_i->nat_root, nat_get_nid(ne), ne); + else if (radix_tree_insert(&nm_i->nat_root, nat_get_nid(ne), ne)) + return NULL; + + if (raw_ne) + node_info_from_raw_nat(&ne->ni, raw_ne); + list_add_tail(&ne->list, &nm_i->nat_entries); + nm_i->nat_cnt++; + return ne; +} + static struct nat_entry *__lookup_nat_cache(struct f2fs_nm_info *nm_i, nid_t n) { return radix_tree_lookup(&nm_i->nat_root, n); @@ -148,18 +190,15 @@ static void __del_from_nat_cache(struct list_del(&e->list); radix_tree_delete(&nm_i->nat_root, nat_get_nid(e)); nm_i->nat_cnt--; - kmem_cache_free(nat_entry_slab, e); + __free_nat_entry(e); } -static void __set_nat_cache_dirty(struct f2fs_nm_info *nm_i, - struct nat_entry *ne) +static struct nat_entry_set *__grab_nat_entry_set(struct f2fs_nm_info *nm_i, + struct nat_entry *ne) { nid_t set = NAT_BLOCK_OFFSET(ne->ni.nid); struct nat_entry_set *head; - if (get_nat_flag(ne, IS_DIRTY)) - return; - head = radix_tree_lookup(&nm_i->nat_set_root, set); if (!head) { head = f2fs_kmem_cache_alloc(nat_entry_set_slab, GFP_NOFS); @@ -170,25 +209,48 @@ static void __set_nat_cache_dirty(struct head->entry_cnt = 0; f2fs_radix_tree_insert(&nm_i->nat_set_root, set, head); } - list_move_tail(&ne->list, &head->entry_list); - nm_i->dirty_nat_cnt++; - head->entry_cnt++; - set_nat_flag(ne, IS_DIRTY, true); + return head; } -static void __clear_nat_cache_dirty(struct f2fs_nm_info *nm_i, +static void __set_nat_cache_dirty(struct f2fs_nm_info *nm_i, struct nat_entry *ne) { - nid_t set = NAT_BLOCK_OFFSET(ne->ni.nid); struct nat_entry_set *head; + bool new_ne = nat_get_blkaddr(ne) == NEW_ADDR; - head = radix_tree_lookup(&nm_i->nat_set_root, set); - if (head) { - list_move_tail(&ne->list, &nm_i->nat_entries); - set_nat_flag(ne, IS_DIRTY, false); - head->entry_cnt--; - nm_i->dirty_nat_cnt--; - } + if (!new_ne) + head = __grab_nat_entry_set(nm_i, ne); + + /* + * update entry_cnt in below condition: + * 1. update NEW_ADDR to valid block address; + * 2. update old block address to new one; + */ + if (!new_ne && (get_nat_flag(ne, IS_PREALLOC) || + !get_nat_flag(ne, IS_DIRTY))) + head->entry_cnt++; + + set_nat_flag(ne, IS_PREALLOC, new_ne); + + if (get_nat_flag(ne, IS_DIRTY)) + goto refresh_list; + + nm_i->dirty_nat_cnt++; + set_nat_flag(ne, IS_DIRTY, true); +refresh_list: + if (new_ne) + list_del_init(&ne->list); + else + list_move_tail(&ne->list, &head->entry_list); +} + +static void __clear_nat_cache_dirty(struct f2fs_nm_info *nm_i, + struct nat_entry_set *set, struct nat_entry *ne) +{ + list_move_tail(&ne->list, &nm_i->nat_entries); + set_nat_flag(ne, IS_DIRTY, false); + set->entry_cnt--; + nm_i->dirty_nat_cnt--; } static unsigned int __gang_lookup_nat_set(struct f2fs_nm_info *nm_i, @@ -245,35 +307,29 @@ bool need_inode_block_update(struct f2fs return need_update; } -static struct nat_entry *grab_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid) -{ - struct nat_entry *new; - - new = f2fs_kmem_cache_alloc(nat_entry_slab, GFP_NOFS); - f2fs_radix_tree_insert(&nm_i->nat_root, nid, new); - memset(new, 0, sizeof(struct nat_entry)); - nat_set_nid(new, nid); - nat_reset_flag(new); - list_add_tail(&new->list, &nm_i->nat_entries); - nm_i->nat_cnt++; - return new; -} - +/* must be locked by nat_tree_lock */ static void cache_nat_entry(struct f2fs_sb_info *sbi, nid_t nid, struct f2fs_nat_entry *ne) { struct f2fs_nm_info *nm_i = NM_I(sbi); - struct nat_entry *e; + struct nat_entry *new, *e; + new = __alloc_nat_entry(nid, false); + if (!new) + return; + + down_write(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, nid); - if (!e) { - e = grab_nat_entry(nm_i, nid); - node_info_from_raw_nat(&e->ni, ne); - } else { - f2fs_bug_on(sbi, nat_get_ino(e) != ne->ino || - nat_get_blkaddr(e) != ne->block_addr || + if (!e) + e = __init_nat_entry(nm_i, new, ne, false); + else + f2fs_bug_on(sbi, nat_get_ino(e) != le32_to_cpu(ne->ino) || + nat_get_blkaddr(e) != + le32_to_cpu(ne->block_addr) || nat_get_version(e) != ne->version); - } + up_write(&nm_i->nat_tree_lock); + if (e != new) + __free_nat_entry(new); } static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, @@ -281,11 +337,12 @@ static void set_node_addr(struct f2fs_sb { struct f2fs_nm_info *nm_i = NM_I(sbi); struct nat_entry *e; + struct nat_entry *new = __alloc_nat_entry(ni->nid, true); down_write(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, ni->nid); if (!e) { - e = grab_nat_entry(nm_i, ni->nid); + e = __init_nat_entry(nm_i, new, NULL, true); copy_node_info(&e->ni, ni); f2fs_bug_on(sbi, ni->blk_addr == NEW_ADDR); } else if (new_blkaddr == NEW_ADDR) { @@ -297,6 +354,9 @@ static void set_node_addr(struct f2fs_sb copy_node_info(&e->ni, ni); f2fs_bug_on(sbi, ni->blk_addr != NULL_ADDR); } + /* let's free early to reduce memory consumption */ + if (e != new) + __free_nat_entry(new); /* sanity check */ f2fs_bug_on(sbi, nat_get_blkaddr(e) != ni->blk_addr); @@ -312,10 +372,6 @@ static void set_node_addr(struct f2fs_sb if (nat_get_blkaddr(e) != NEW_ADDR && new_blkaddr == NULL_ADDR) { unsigned char version = nat_get_version(e); nat_set_version(e, inc_node_version(version)); - - /* in order to reuse the nid */ - if (nm_i->next_scan_nid > ni->nid) - nm_i->next_scan_nid = ni->nid; } /* change address */ @@ -367,6 +423,7 @@ void get_node_info(struct f2fs_sb_info * struct page *page = NULL; struct f2fs_nat_entry ne; struct nat_entry *e; + pgoff_t index; int i; ni->nid = nid; @@ -392,21 +449,23 @@ void get_node_info(struct f2fs_sb_info * node_info_from_raw_nat(ni, &ne); } up_read(&curseg->journal_rwsem); - if (i >= 0) + if (i >= 0) { + up_read(&nm_i->nat_tree_lock); goto cache; + } /* Fill node_info from nat page */ - page = get_current_nat_page(sbi, start_nid); + index = current_nat_addr(sbi, nid); + up_read(&nm_i->nat_tree_lock); + + page = get_meta_page(sbi, index); nat_blk = (struct f2fs_nat_block *)page_address(page); ne = nat_blk->entries[nid - start_nid]; node_info_from_raw_nat(ni, &ne); f2fs_put_page(page, 1); cache: - up_read(&nm_i->nat_tree_lock); /* cache nat entry */ - down_write(&nm_i->nat_tree_lock); cache_nat_entry(sbi, nid, &ne); - up_write(&nm_i->nat_tree_lock); } /* @@ -535,7 +594,7 @@ static int get_node_path(struct inode *i level = 3; goto got; } else { - BUG(); + return -E2BIG; } got: return level; @@ -559,6 +618,8 @@ int get_dnode_of_data(struct dnode_of_da int err = 0; level = get_node_path(dn->inode, index, offset, noffset); + if (level < 0) + return level; nids[0] = dn->inode->i_ino; npage[0] = dn->inode_page; @@ -594,7 +655,7 @@ int get_dnode_of_data(struct dnode_of_da } dn->nid = nids[i]; - npage[i] = new_node_page(dn, noffset[i], NULL); + npage[i] = new_node_page(dn, noffset[i]); if (IS_ERR(npage[i])) { alloc_nid_failed(sbi, nids[i]); err = PTR_ERR(npage[i]); @@ -635,7 +696,8 @@ int get_dnode_of_data(struct dnode_of_da dn->nid = nids[level]; dn->ofs_in_node = offset[level]; dn->node_page = npage[level]; - dn->data_blkaddr = datablock_addr(dn->node_page, dn->ofs_in_node); + dn->data_blkaddr = datablock_addr(dn->inode, + dn->node_page, dn->ofs_in_node); return 0; release_pages: @@ -659,15 +721,10 @@ static void truncate_node(struct dnode_o struct node_info ni; get_node_info(sbi, dn->nid, &ni); - if (dn->inode->i_blocks == 0) { - f2fs_bug_on(sbi, ni.blk_addr != NULL_ADDR); - goto invalidate; - } - f2fs_bug_on(sbi, ni.blk_addr == NULL_ADDR); /* Deallocate node address */ invalidate_blocks(sbi, ni.blk_addr); - dec_valid_node_count(sbi, dn->inode); + dec_valid_node_count(sbi, dn->inode, dn->nid == dn->inode->i_ino); set_node_addr(sbi, &ni, NULL_ADDR, false); if (dn->nid == dn->inode->i_ino) { @@ -675,7 +732,7 @@ static void truncate_node(struct dnode_o dec_valid_inode_count(sbi); f2fs_inode_synced(dn->inode); } -invalidate: + clear_node_page_dirty(dn->node_page); set_sbi_flag(sbi, SBI_IS_DIRTY); @@ -861,6 +918,8 @@ int truncate_inode_blocks(struct inode * trace_f2fs_truncate_inode_blocks_enter(inode, from); level = get_node_path(inode, from, offset, noffset); + if (level < 0) + return level; page = get_node_page(sbi, inode->i_ino); if (IS_ERR(page)) { @@ -941,7 +1000,8 @@ fail: return err > 0 ? 0 : err; } -int truncate_xattr_node(struct inode *inode, struct page *page) +/* caller must lock inode page */ +int truncate_xattr_node(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); nid_t nid = F2FS_I(inode)->i_xattr_nid; @@ -957,13 +1017,7 @@ int truncate_xattr_node(struct inode *in f2fs_i_xnid_write(inode, 0); - /* need to do checkpoint during fsync */ - F2FS_I(inode)->xattr_ver = cur_cp_version(F2FS_CKPT(sbi)); - - set_new_dnode(&dn, inode, page, npage, nid); - - if (page) - dn.inode_page_locked = true; + set_new_dnode(&dn, inode, NULL, npage, nid); truncate_node(&dn); return 0; } @@ -982,7 +1036,7 @@ int remove_inode_page(struct inode *inod if (err) return err; - err = truncate_xattr_node(inode, dn.inode_page); + err = truncate_xattr_node(inode); if (err) { f2fs_put_dnode(&dn); return err; @@ -995,7 +1049,7 @@ int remove_inode_page(struct inode *inod /* 0 is possible, after f2fs_new_inode() has failed */ f2fs_bug_on(F2FS_I_SB(inode), - inode->i_blocks != 0 && inode->i_blocks != 1); + inode->i_blocks != 0 && inode->i_blocks != 8); /* will put inode & node pages */ truncate_node(&dn); @@ -1010,14 +1064,13 @@ struct page *new_inode_page(struct inode set_new_dnode(&dn, inode, NULL, NULL, inode->i_ino); /* caller should f2fs_put_page(page, 1); */ - return new_node_page(&dn, 0, NULL); + return new_node_page(&dn, 0); } -struct page *new_node_page(struct dnode_of_data *dn, - unsigned int ofs, struct page *ipage) +struct page *new_node_page(struct dnode_of_data *dn, unsigned int ofs) { struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); - struct node_info old_ni, new_ni; + struct node_info new_ni; struct page *page; int err; @@ -1028,22 +1081,23 @@ struct page *new_node_page(struct dnode_ if (!page) return ERR_PTR(-ENOMEM); - if (unlikely(!inc_valid_node_count(sbi, dn->inode))) { - err = -ENOSPC; + if (unlikely((err = inc_valid_node_count(sbi, dn->inode, !ofs)))) goto fail; - } - - get_node_info(sbi, dn->nid, &old_ni); - /* Reinitialize old_ni with new node page */ - f2fs_bug_on(sbi, old_ni.blk_addr != NULL_ADDR); - new_ni = old_ni; +#ifdef CONFIG_F2FS_CHECK_FS + get_node_info(sbi, dn->nid, &new_ni); + f2fs_bug_on(sbi, new_ni.blk_addr != NULL_ADDR); +#endif + new_ni.nid = dn->nid; new_ni.ino = dn->inode->i_ino; + new_ni.blk_addr = NULL_ADDR; + new_ni.flag = 0; + new_ni.version = 0; set_node_addr(sbi, &new_ni, NEW_ADDR, false); f2fs_wait_on_page_writeback(page, NODE, true); fill_node_footer(page, dn->nid, dn->inode->i_ino, ofs, true); - set_cold_node(dn->inode, page); + set_cold_node(page, S_ISDIR(dn->inode->i_mode)); if (!PageUptodate(page)) SetPageUptodate(page); if (set_page_dirty(page)) @@ -1134,11 +1188,12 @@ repeat: if (!page) return ERR_PTR(-ENOMEM); - err = read_node_page(page, READ_SYNC); + err = read_node_page(page, 0); if (err < 0) { f2fs_put_page(page, 1); return ERR_PTR(err); } else if (err == LOCKED_PAGE) { + err = 0; goto page_hit; } @@ -1152,15 +1207,27 @@ repeat: goto repeat; } - if (unlikely(!PageUptodate(page))) + if (unlikely(!PageUptodate(page))) { + err = -EIO; + goto out_err; + } + + if (!f2fs_inode_chksum_verify(sbi, page)) { + err = -EBADMSG; goto out_err; + } page_hit: if(unlikely(nid != nid_of_node(page))) { - f2fs_bug_on(sbi, 1); - ClearPageUptodate(page); + f2fs_msg(sbi->sb, KERN_WARNING, "inconsistent node block, " + "nid:%lu, node_footer[nid:%u,ino:%u,ofs:%u,cpver:%llu,blkaddr:%u]", + nid, nid_of_node(page), ino_of_node(page), + ofs_of_node(page), cpver_of_node(page), + next_blkaddr_of_node(page)); + err = -EINVAL; out_err: + ClearPageUptodate(page); f2fs_put_page(page, 1); - return ERR_PTR(-EIO); + return ERR_PTR(err); } return page; } @@ -1189,7 +1256,8 @@ static void flush_inline_data(struct f2f if (!inode) return; - page = pagecache_get_page(inode->i_mapping, 0, FGP_LOCK|FGP_NOWAIT, 0); + page = f2fs_pagecache_get_page(inode->i_mapping, 0, + FGP_LOCK|FGP_NOWAIT, 0); if (!page) goto iput_out; @@ -1204,6 +1272,7 @@ static void flush_inline_data(struct f2f ret = f2fs_write_inline_data(inode, page); inode_dec_dirty_pages(inode); + remove_dirty_inode(inode); if (ret) set_page_dirty(page); page_out: @@ -1212,37 +1281,6 @@ iput_out: iput(inode); } -void move_node_page(struct page *node_page, int gc_type) -{ - if (gc_type == FG_GC) { - struct f2fs_sb_info *sbi = F2FS_P_SB(node_page); - struct writeback_control wbc = { - .sync_mode = WB_SYNC_ALL, - .nr_to_write = 1, - .for_reclaim = 0, - }; - - set_page_dirty(node_page); - f2fs_wait_on_page_writeback(node_page, NODE, true); - - f2fs_bug_on(sbi, PageWriteback(node_page)); - if (!clear_page_dirty_for_io(node_page)) - goto out_page; - - if (NODE_MAPPING(sbi)->a_ops->writepage(node_page, &wbc)) - unlock_page(node_page); - goto release_page; - } else { - /* set page dirty and write it */ - if (!PageWriteback(node_page)) - set_page_dirty(node_page); - } -out_page: - unlock_page(node_page); -release_page: - f2fs_put_page(node_page, 0); -} - static struct page *last_fsync_dnode(struct f2fs_sb_info *sbi, nid_t ino) { pgoff_t index, end; @@ -1303,16 +1341,141 @@ continue_unlock: return last_page; } +static int __write_node_page(struct page *page, bool atomic, bool *submitted, + struct writeback_control *wbc, bool do_balance, + enum iostat_type io_type) +{ + struct f2fs_sb_info *sbi = F2FS_P_SB(page); + nid_t nid; + struct node_info ni; + struct f2fs_io_info fio = { + .sbi = sbi, + .ino = ino_of_node(page), + .type = NODE, + .op = REQ_OP_WRITE, + .op_flags = wbc_to_write_flags(wbc), + .page = page, + .encrypted_page = NULL, + .submitted = false, + .io_type = io_type, + .io_wbc = wbc, + }; + + trace_f2fs_writepage(page, NODE); + + if (unlikely(f2fs_cp_error(sbi))) { + dec_page_count(sbi, F2FS_DIRTY_NODES); + unlock_page(page); + return 0; + } + + if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) + goto redirty_out; + + /* get old block addr of this node page */ + nid = nid_of_node(page); + f2fs_bug_on(sbi, page->index != nid); + + if (wbc->for_reclaim) { + if (!down_read_trylock(&sbi->node_write)) + goto redirty_out; + } else { + down_read(&sbi->node_write); + } + + get_node_info(sbi, nid, &ni); + + /* This page is already truncated */ + if (unlikely(ni.blk_addr == NULL_ADDR)) { + ClearPageUptodate(page); + dec_page_count(sbi, F2FS_DIRTY_NODES); + up_read(&sbi->node_write); + unlock_page(page); + return 0; + } + + if (atomic && !test_opt(sbi, NOBARRIER)) + fio.op_flags |= REQ_PREFLUSH | REQ_FUA; + + set_page_writeback(page); + ClearPageError(page); + fio.old_blkaddr = ni.blk_addr; + write_node_page(nid, &fio); + set_node_addr(sbi, &ni, fio.new_blkaddr, is_fsync_dnode(page)); + dec_page_count(sbi, F2FS_DIRTY_NODES); + up_read(&sbi->node_write); + + if (wbc->for_reclaim) { + f2fs_submit_merged_write_cond(sbi, page->mapping->host, 0, + page->index, NODE); + submitted = NULL; + } + + unlock_page(page); + + if (unlikely(f2fs_cp_error(sbi))) { + f2fs_submit_merged_write(sbi, NODE); + submitted = NULL; + } + if (submitted) + *submitted = fio.submitted; + + if (do_balance) + f2fs_balance_fs(sbi, false); + return 0; + +redirty_out: + redirty_page_for_writepage(wbc, page); + return AOP_WRITEPAGE_ACTIVATE; +} + +void move_node_page(struct page *node_page, int gc_type) +{ + if (gc_type == FG_GC) { + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL, + .nr_to_write = 1, + .for_reclaim = 0, + }; + + set_page_dirty(node_page); + f2fs_wait_on_page_writeback(node_page, NODE, true); + + f2fs_bug_on(F2FS_P_SB(node_page), PageWriteback(node_page)); + if (!clear_page_dirty_for_io(node_page)) + goto out_page; + + if (__write_node_page(node_page, false, NULL, + &wbc, false, FS_GC_NODE_IO)) + unlock_page(node_page); + goto release_page; + } else { + /* set page dirty and write it */ + if (!PageWriteback(node_page)) + set_page_dirty(node_page); + } +out_page: + unlock_page(node_page); +release_page: + f2fs_put_page(node_page, 0); +} + +static int f2fs_write_node_page(struct page *page, + struct writeback_control *wbc) +{ + return __write_node_page(page, false, NULL, wbc, false, FS_NODE_IO); +} + int fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode, struct writeback_control *wbc, bool atomic) { pgoff_t index, end; + pgoff_t last_idx = ULONG_MAX; struct pagevec pvec; int ret = 0; struct page *last_page = NULL; bool marked = false; nid_t ino = inode->i_ino; - int nwritten = 0; if (atomic) { last_page = last_fsync_dnode(sbi, ino); @@ -1334,11 +1497,13 @@ retry: for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; + bool submitted = false; if (unlikely(f2fs_cp_error(sbi))) { f2fs_put_page(last_page, 0); pagevec_release(&pvec); - return -EIO; + ret = -EIO; + goto out; } if (!IS_DNODE(page) || !is_cold_node(page)) @@ -1364,6 +1529,9 @@ continue_unlock: f2fs_wait_on_page_writeback(page, NODE, true); BUG_ON(PageWriteback(page)); + set_fsync_mark(page, 0); + set_dentry_mark(page, 0); + if (!atomic || page == last_page) { set_fsync_mark(page, 1); if (IS_INODE(page)) { @@ -1381,13 +1549,16 @@ continue_unlock: if (!clear_page_dirty_for_io(page)) goto continue_unlock; - ret = NODE_MAPPING(sbi)->a_ops->writepage(page, wbc); + ret = __write_node_page(page, atomic && + page == last_page, + &submitted, wbc, true, + FS_NODE_IO); if (ret) { unlock_page(page); f2fs_put_page(last_page, 0); break; - } else { - nwritten++; + } else if (submitted) { + last_idx = page->index; } if (page == last_page) { @@ -1407,17 +1578,19 @@ continue_unlock: "Retry to write fsync mark: ino=%u, idx=%lx", ino, last_page->index); lock_page(last_page); + f2fs_wait_on_page_writeback(last_page, NODE, true); set_page_dirty(last_page); unlock_page(last_page); goto retry; } - - if (nwritten) - f2fs_submit_merged_bio_cond(sbi, NULL, NULL, ino, NODE, WRITE); +out: + if (last_idx != ULONG_MAX) + f2fs_submit_merged_write_cond(sbi, NULL, ino, last_idx, NODE); return ret ? -EIO: 0; } -int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc) +int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc, + bool do_balance, enum iostat_type io_type) { pgoff_t index, end; struct pagevec pvec; @@ -1441,12 +1614,7 @@ next_step: for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; - - if (unlikely(f2fs_cp_error(sbi))) { - pagevec_release(&pvec); - ret = -EIO; - goto out; - } + bool submitted = false; /* * flushing sequence with step: @@ -1494,9 +1662,11 @@ continue_unlock: set_fsync_mark(page, 0); set_dentry_mark(page, 0); - if (NODE_MAPPING(sbi)->a_ops->writepage(page, wbc)) + ret = __write_node_page(page, false, &submitted, + wbc, do_balance, io_type); + if (ret) unlock_page(page); - else + else if (submitted) nwritten++; if (--wbc->nr_to_write == 0) @@ -1515,9 +1685,12 @@ continue_unlock: step++; goto next_step; } -out: + if (nwritten) - f2fs_submit_merged_bio(sbi, NODE, WRITE); + f2fs_submit_merged_write(sbi, NODE); + + if (unlikely(f2fs_cp_error(sbi))) + return -EIO; return ret; } @@ -1560,72 +1733,6 @@ int wait_on_node_pages_writeback(struct return ret; } -static int f2fs_write_node_page(struct page *page, - struct writeback_control *wbc) -{ - struct f2fs_sb_info *sbi = F2FS_P_SB(page); - nid_t nid; - struct node_info ni; - struct f2fs_io_info fio = { - .sbi = sbi, - .type = NODE, - .op = REQ_OP_WRITE, - .op_flags = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : 0, - .page = page, - .encrypted_page = NULL, - }; - - trace_f2fs_writepage(page, NODE); - - if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) - goto redirty_out; - if (unlikely(f2fs_cp_error(sbi))) - goto redirty_out; - - /* get old block addr of this node page */ - nid = nid_of_node(page); - f2fs_bug_on(sbi, page->index != nid); - - if (wbc->for_reclaim) { - if (!down_read_trylock(&sbi->node_write)) - goto redirty_out; - } else { - down_read(&sbi->node_write); - } - - get_node_info(sbi, nid, &ni); - - /* This page is already truncated */ - if (unlikely(ni.blk_addr == NULL_ADDR)) { - ClearPageUptodate(page); - dec_page_count(sbi, F2FS_DIRTY_NODES); - up_read(&sbi->node_write); - unlock_page(page); - return 0; - } - - set_page_writeback(page); - fio.old_blkaddr = ni.blk_addr; - write_node_page(nid, &fio); - set_node_addr(sbi, &ni, fio.new_blkaddr, is_fsync_dnode(page)); - dec_page_count(sbi, F2FS_DIRTY_NODES); - up_read(&sbi->node_write); - - if (wbc->for_reclaim) - f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, NODE, WRITE); - - unlock_page(page); - - if (unlikely(f2fs_cp_error(sbi))) - f2fs_submit_merged_bio(sbi, NODE, WRITE); - - return 0; - -redirty_out: - redirty_page_for_writepage(wbc, page); - return AOP_WRITEPAGE_ACTIVATE; -} - static int f2fs_write_node_pages(struct address_space *mapping, struct writeback_control *wbc) { @@ -1633,6 +1740,9 @@ static int f2fs_write_node_pages(struct struct blk_plug plug; long diff; + if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) + goto skip_write; + /* balancing f2fs's metadata in background */ f2fs_balance_fs_bg(sbi); @@ -1645,7 +1755,7 @@ static int f2fs_write_node_pages(struct diff = nr_pages_to_write(sbi, NODE, wbc); wbc->sync_mode = WB_SYNC_NONE; blk_start_plug(&plug); - sync_node_pages(sbi, wbc); + sync_node_pages(sbi, wbc, true, FS_NODE_IO); blk_finish_plug(&plug); wbc->nr_to_write = max((long)0, wbc->nr_to_write - diff); return 0; @@ -1663,7 +1773,7 @@ static int f2fs_set_node_page_dirty(stru if (!PageUptodate(page)) SetPageUptodate(page); if (!PageDirty(page)) { - f2fs_set_page_dirty_nobuffers(page); + __set_page_dirty_nobuffers(page); inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_NODES); SetPagePrivate(page); f2fs_trace_pid(page); @@ -1692,70 +1802,165 @@ static struct free_nid *__lookup_free_ni return radix_tree_lookup(&nm_i->free_nid_root, n); } -static void __del_from_free_nid_list(struct f2fs_nm_info *nm_i, - struct free_nid *i) +static int __insert_free_nid(struct f2fs_sb_info *sbi, + struct free_nid *i, enum nid_state state) { - list_del(&i->list); + struct f2fs_nm_info *nm_i = NM_I(sbi); + + int err = radix_tree_insert(&nm_i->free_nid_root, i->nid, i); + if (err) + return err; + + f2fs_bug_on(sbi, state != i->state); + nm_i->nid_cnt[state]++; + if (state == FREE_NID) + list_add_tail(&i->list, &nm_i->free_nid_list); + return 0; +} + +static void __remove_free_nid(struct f2fs_sb_info *sbi, + struct free_nid *i, enum nid_state state) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + + f2fs_bug_on(sbi, state != i->state); + nm_i->nid_cnt[state]--; + if (state == FREE_NID) + list_del(&i->list); radix_tree_delete(&nm_i->free_nid_root, i->nid); } -static int add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build) +static void __move_free_nid(struct f2fs_sb_info *sbi, struct free_nid *i, + enum nid_state org_state, enum nid_state dst_state) { struct f2fs_nm_info *nm_i = NM_I(sbi); - struct free_nid *i; - struct nat_entry *ne; - if (!available_free_memory(sbi, FREE_NIDS)) - return -1; + f2fs_bug_on(sbi, org_state != i->state); + i->state = dst_state; + nm_i->nid_cnt[org_state]--; + nm_i->nid_cnt[dst_state]++; + + switch (dst_state) { + case PREALLOC_NID: + list_del(&i->list); + break; + case FREE_NID: + list_add_tail(&i->list, &nm_i->free_nid_list); + break; + default: + BUG_ON(1); + } +} + +static void update_free_nid_bitmap(struct f2fs_sb_info *sbi, nid_t nid, + bool set, bool build) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + unsigned int nat_ofs = NAT_BLOCK_OFFSET(nid); + unsigned int nid_ofs = nid - START_NID(nid); + + if (!test_bit_le(nat_ofs, nm_i->nat_block_bitmap)) + return; + + if (set) { + if (test_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs])) + return; + __set_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs]); + nm_i->free_nid_count[nat_ofs]++; + } else { + if (!test_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs])) + return; + __clear_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs]); + if (!build) + nm_i->free_nid_count[nat_ofs]--; + } +} + +/* return if the nid is recognized as free */ +static bool add_free_nid(struct f2fs_sb_info *sbi, + nid_t nid, bool build, bool update) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + struct free_nid *i, *e; + struct nat_entry *ne; + int err = -EINVAL; + bool ret = false; /* 0 nid should not be used */ if (unlikely(nid == 0)) - return 0; + return false; + + i = f2fs_kmem_cache_alloc(free_nid_slab, GFP_NOFS); + i->nid = nid; + i->state = FREE_NID; + + radix_tree_preload(GFP_NOFS | __GFP_NOFAIL); + + spin_lock(&nm_i->nid_list_lock); if (build) { - /* do not add allocated nids */ + /* + * Thread A Thread B + * - f2fs_create + * - f2fs_new_inode + * - alloc_nid + * - __insert_nid_to_list(PREALLOC_NID) + * - f2fs_balance_fs_bg + * - build_free_nids + * - __build_free_nids + * - scan_nat_page + * - add_free_nid + * - __lookup_nat_cache + * - f2fs_add_link + * - init_inode_metadata + * - new_inode_page + * - new_node_page + * - set_node_addr + * - alloc_nid_done + * - __remove_nid_from_list(PREALLOC_NID) + * - __insert_nid_to_list(FREE_NID) + */ ne = __lookup_nat_cache(nm_i, nid); if (ne && (!get_nat_flag(ne, IS_CHECKPOINTED) || nat_get_blkaddr(ne) != NULL_ADDR)) - return 0; - } - - i = f2fs_kmem_cache_alloc(free_nid_slab, GFP_NOFS); - i->nid = nid; - i->state = NID_NEW; + goto err_out; - if (radix_tree_preload(GFP_NOFS)) { - kmem_cache_free(free_nid_slab, i); - return 0; + e = __lookup_free_nid_list(nm_i, nid); + if (e) { + if (e->state == FREE_NID) + ret = true; + goto err_out; + } } - - spin_lock(&nm_i->free_nid_list_lock); - if (radix_tree_insert(&nm_i->free_nid_root, i->nid, i)) { - spin_unlock(&nm_i->free_nid_list_lock); - radix_tree_preload_end(); - kmem_cache_free(free_nid_slab, i); - return 0; + ret = true; + err = __insert_free_nid(sbi, i, FREE_NID); +err_out: + if (update) { + update_free_nid_bitmap(sbi, nid, ret, build); + if (!build) + nm_i->available_nids++; } - list_add_tail(&i->list, &nm_i->free_nid_list); - nm_i->fcnt++; - spin_unlock(&nm_i->free_nid_list_lock); + spin_unlock(&nm_i->nid_list_lock); radix_tree_preload_end(); - return 1; + + if (err) + kmem_cache_free(free_nid_slab, i); + return ret; } -static void remove_free_nid(struct f2fs_nm_info *nm_i, nid_t nid) +static void remove_free_nid(struct f2fs_sb_info *sbi, nid_t nid) { + struct f2fs_nm_info *nm_i = NM_I(sbi); struct free_nid *i; bool need_free = false; - spin_lock(&nm_i->free_nid_list_lock); + spin_lock(&nm_i->nid_list_lock); i = __lookup_free_nid_list(nm_i, nid); - if (i && i->state == NID_NEW) { - __del_from_free_nid_list(nm_i, i); - nm_i->fcnt--; + if (i && i->state == FREE_NID) { + __remove_free_nid(sbi, i, FREE_NID); need_free = true; } - spin_unlock(&nm_i->free_nid_list_lock); + spin_unlock(&nm_i->nid_list_lock); if (need_free) kmem_cache_free(free_nid_slab, i); @@ -1767,36 +1972,106 @@ static void scan_nat_page(struct f2fs_sb struct f2fs_nm_info *nm_i = NM_I(sbi); struct f2fs_nat_block *nat_blk = page_address(nat_page); block_t blk_addr; + unsigned int nat_ofs = NAT_BLOCK_OFFSET(start_nid); int i; + __set_bit_le(nat_ofs, nm_i->nat_block_bitmap); + i = start_nid % NAT_ENTRY_PER_BLOCK; for (; i < NAT_ENTRY_PER_BLOCK; i++, start_nid++) { - if (unlikely(start_nid >= nm_i->max_nid)) break; blk_addr = le32_to_cpu(nat_blk->entries[i].block_addr); f2fs_bug_on(sbi, blk_addr == NEW_ADDR); if (blk_addr == NULL_ADDR) { - if (add_free_nid(sbi, start_nid, true) < 0) - break; + add_free_nid(sbi, start_nid, true, true); + } else { + spin_lock(&NM_I(sbi)->nid_list_lock); + update_free_nid_bitmap(sbi, start_nid, false, true); + spin_unlock(&NM_I(sbi)->nid_list_lock); } } } -void build_free_nids(struct f2fs_sb_info *sbi) +static void scan_curseg_cache(struct f2fs_sb_info *sbi) { - struct f2fs_nm_info *nm_i = NM_I(sbi); struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA); struct f2fs_journal *journal = curseg->journal; + int i; + + down_read(&curseg->journal_rwsem); + for (i = 0; i < nats_in_cursum(journal); i++) { + block_t addr; + nid_t nid; + + addr = le32_to_cpu(nat_in_journal(journal, i).block_addr); + nid = le32_to_cpu(nid_in_journal(journal, i)); + if (addr == NULL_ADDR) + add_free_nid(sbi, nid, true, false); + else + remove_free_nid(sbi, nid); + } + up_read(&curseg->journal_rwsem); +} + +static void scan_free_nid_bits(struct f2fs_sb_info *sbi) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + unsigned int i, idx; + nid_t nid; + + down_read(&nm_i->nat_tree_lock); + + for (i = 0; i < nm_i->nat_blocks; i++) { + if (!test_bit_le(i, nm_i->nat_block_bitmap)) + continue; + if (!nm_i->free_nid_count[i]) + continue; + for (idx = 0; idx < NAT_ENTRY_PER_BLOCK; idx++) { + idx = find_next_bit_le(nm_i->free_nid_bitmap[i], + NAT_ENTRY_PER_BLOCK, idx); + if (idx >= NAT_ENTRY_PER_BLOCK) + break; + + nid = i * NAT_ENTRY_PER_BLOCK + idx; + add_free_nid(sbi, nid, true, false); + + if (nm_i->nid_cnt[FREE_NID] >= MAX_FREE_NIDS) + goto out; + } + } +out: + scan_curseg_cache(sbi); + + up_read(&nm_i->nat_tree_lock); +} + +static void __build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); int i = 0; nid_t nid = nm_i->next_scan_nid; + if (unlikely(nid >= nm_i->max_nid)) + nid = 0; + /* Enough entries */ - if (nm_i->fcnt >= NAT_ENTRY_PER_BLOCK) + if (nm_i->nid_cnt[FREE_NID] >= NAT_ENTRY_PER_BLOCK) + return; + + if (!sync && !available_free_memory(sbi, FREE_NIDS)) return; + if (!mount) { + /* try to find free nids in free_nid_bitmap */ + scan_free_nid_bits(sbi); + + if (nm_i->nid_cnt[FREE_NID] >= NAT_ENTRY_PER_BLOCK) + return; + } + /* readahead nat pages to be scanned */ ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES, META_NAT, true); @@ -1804,10 +2079,13 @@ void build_free_nids(struct f2fs_sb_info down_read(&nm_i->nat_tree_lock); while (1) { - struct page *page = get_current_nat_page(sbi, nid); + if (!test_bit_le(NAT_BLOCK_OFFSET(nid), + nm_i->nat_block_bitmap)) { + struct page *page = get_current_nat_page(sbi, nid); - scan_nat_page(sbi, page, nid); - f2fs_put_page(page, 1); + scan_nat_page(sbi, page, nid); + f2fs_put_page(page, 1); + } nid += (NAT_ENTRY_PER_BLOCK - (nid % NAT_ENTRY_PER_BLOCK)); if (unlikely(nid >= nm_i->max_nid)) @@ -1821,24 +2099,21 @@ void build_free_nids(struct f2fs_sb_info nm_i->next_scan_nid = nid; /* find free nids from current sum_pages */ - down_read(&curseg->journal_rwsem); - for (i = 0; i < nats_in_cursum(journal); i++) { - block_t addr; + scan_curseg_cache(sbi); - addr = le32_to_cpu(nat_in_journal(journal, i).block_addr); - nid = le32_to_cpu(nid_in_journal(journal, i)); - if (addr == NULL_ADDR) - add_free_nid(sbi, nid, true); - else - remove_free_nid(nm_i, nid); - } - up_read(&curseg->journal_rwsem); up_read(&nm_i->nat_tree_lock); ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nm_i->next_scan_nid), nm_i->ra_nid_pages, META_NAT, false); } +void build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount) +{ + mutex_lock(&NM_I(sbi)->build_lock); + __build_free_nids(sbi, sync, mount); + mutex_unlock(&NM_I(sbi)->build_lock); +} + /* * If this function returns success, caller can obtain a new nid * from second parameter of this function. @@ -1850,34 +2125,37 @@ bool alloc_nid(struct f2fs_sb_info *sbi, struct free_nid *i = NULL; retry: #ifdef CONFIG_F2FS_FAULT_INJECTION - if (time_to_inject(sbi, FAULT_ALLOC_NID)) + if (time_to_inject(sbi, FAULT_ALLOC_NID)) { + f2fs_show_injection_info(FAULT_ALLOC_NID); return false; + } #endif - if (unlikely(sbi->total_valid_node_count + 1 > nm_i->available_nids)) - return false; + spin_lock(&nm_i->nid_list_lock); - spin_lock(&nm_i->free_nid_list_lock); + if (unlikely(nm_i->available_nids == 0)) { + spin_unlock(&nm_i->nid_list_lock); + return false; + } /* We should not use stale free nids created by build_free_nids */ - if (nm_i->fcnt && !on_build_free_nids(nm_i)) { + if (nm_i->nid_cnt[FREE_NID] && !on_build_free_nids(nm_i)) { f2fs_bug_on(sbi, list_empty(&nm_i->free_nid_list)); - list_for_each_entry(i, &nm_i->free_nid_list, list) - if (i->state == NID_NEW) - break; - - f2fs_bug_on(sbi, i->state != NID_NEW); + i = list_first_entry(&nm_i->free_nid_list, + struct free_nid, list); *nid = i->nid; - i->state = NID_ALLOC; - nm_i->fcnt--; - spin_unlock(&nm_i->free_nid_list_lock); + + __move_free_nid(sbi, i, FREE_NID, PREALLOC_NID); + nm_i->available_nids--; + + update_free_nid_bitmap(sbi, *nid, false, false); + + spin_unlock(&nm_i->nid_list_lock); return true; } - spin_unlock(&nm_i->free_nid_list_lock); + spin_unlock(&nm_i->nid_list_lock); /* Let's scan nat pages and its caches to get free nids */ - mutex_lock(&nm_i->build_lock); - build_free_nids(sbi); - mutex_unlock(&nm_i->build_lock); + build_free_nids(sbi, true, false); goto retry; } @@ -1889,11 +2167,11 @@ void alloc_nid_done(struct f2fs_sb_info struct f2fs_nm_info *nm_i = NM_I(sbi); struct free_nid *i; - spin_lock(&nm_i->free_nid_list_lock); + spin_lock(&nm_i->nid_list_lock); i = __lookup_free_nid_list(nm_i, nid); - f2fs_bug_on(sbi, !i || i->state != NID_ALLOC); - __del_from_free_nid_list(nm_i, i); - spin_unlock(&nm_i->free_nid_list_lock); + f2fs_bug_on(sbi, !i); + __remove_free_nid(sbi, i, PREALLOC_NID); + spin_unlock(&nm_i->nid_list_lock); kmem_cache_free(free_nid_slab, i); } @@ -1910,17 +2188,22 @@ void alloc_nid_failed(struct f2fs_sb_inf if (!nid) return; - spin_lock(&nm_i->free_nid_list_lock); + spin_lock(&nm_i->nid_list_lock); i = __lookup_free_nid_list(nm_i, nid); - f2fs_bug_on(sbi, !i || i->state != NID_ALLOC); + f2fs_bug_on(sbi, !i); + if (!available_free_memory(sbi, FREE_NIDS)) { - __del_from_free_nid_list(nm_i, i); + __remove_free_nid(sbi, i, PREALLOC_NID); need_free = true; } else { - i->state = NID_NEW; - nm_i->fcnt++; + __move_free_nid(sbi, i, PREALLOC_NID, FREE_NID); } - spin_unlock(&nm_i->free_nid_list_lock); + + nm_i->available_nids++; + + update_free_nid_bitmap(sbi, nid, true, false); + + spin_unlock(&nm_i->nid_list_lock); if (need_free) kmem_cache_free(free_nid_slab, i); @@ -1932,24 +2215,23 @@ int try_to_free_nids(struct f2fs_sb_info struct free_nid *i, *next; int nr = nr_shrink; - if (nm_i->fcnt <= MAX_FREE_NIDS) + if (nm_i->nid_cnt[FREE_NID] <= MAX_FREE_NIDS) return 0; if (!mutex_trylock(&nm_i->build_lock)) return 0; - spin_lock(&nm_i->free_nid_list_lock); + spin_lock(&nm_i->nid_list_lock); list_for_each_entry_safe(i, next, &nm_i->free_nid_list, list) { - if (nr_shrink <= 0 || nm_i->fcnt <= MAX_FREE_NIDS) + if (nr_shrink <= 0 || + nm_i->nid_cnt[FREE_NID] <= MAX_FREE_NIDS) break; - if (i->state == NID_ALLOC) - continue; - __del_from_free_nid_list(nm_i, i); + + __remove_free_nid(sbi, i, FREE_NID); kmem_cache_free(free_nid_slab, i); - nm_i->fcnt--; nr_shrink--; } - spin_unlock(&nm_i->free_nid_list_lock); + spin_unlock(&nm_i->nid_list_lock); mutex_unlock(&nm_i->build_lock); return nr - nr_shrink; @@ -1966,13 +2248,15 @@ void recover_inline_xattr(struct inode * f2fs_bug_on(F2FS_I_SB(inode), IS_ERR(ipage)); ri = F2FS_INODE(page); - if (!(ri->i_inline & F2FS_INLINE_XATTR)) { + if (ri->i_inline & F2FS_INLINE_XATTR) { + set_inode_flag(inode, FI_INLINE_XATTR); + } else { clear_inode_flag(inode, FI_INLINE_XATTR); goto update_inode; } - dst_addr = inline_xattr_addr(ipage); - src_addr = inline_xattr_addr(page); + dst_addr = inline_xattr_addr(inode, ipage); + src_addr = inline_xattr_addr(inode, page); inline_size = inline_xattr_size(inode); f2fs_wait_on_page_writeback(ipage, NODE, true); @@ -1982,38 +2266,46 @@ update_inode: f2fs_put_page(ipage, 1); } -void recover_xattr_data(struct inode *inode, struct page *page, block_t blkaddr) +int recover_xattr_data(struct inode *inode, struct page *page) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); nid_t prev_xnid = F2FS_I(inode)->i_xattr_nid; - nid_t new_xnid = nid_of_node(page); + nid_t new_xnid; + struct dnode_of_data dn; struct node_info ni; + struct page *xpage; - /* 1: invalidate the previous xattr nid */ if (!prev_xnid) goto recover_xnid; - /* Deallocate node address */ + /* 1: invalidate the previous xattr nid */ get_node_info(sbi, prev_xnid, &ni); - f2fs_bug_on(sbi, ni.blk_addr == NULL_ADDR); invalidate_blocks(sbi, ni.blk_addr); - dec_valid_node_count(sbi, inode); + dec_valid_node_count(sbi, inode, false); set_node_addr(sbi, &ni, NULL_ADDR, false); recover_xnid: - /* 2: allocate new xattr nid */ - if (unlikely(!inc_valid_node_count(sbi, inode))) - f2fs_bug_on(sbi, 1); + /* 2: update xattr nid in inode */ + if (!alloc_nid(sbi, &new_xnid)) + return -ENOSPC; - remove_free_nid(NM_I(sbi), new_xnid); - get_node_info(sbi, new_xnid, &ni); - ni.ino = inode->i_ino; - set_node_addr(sbi, &ni, NEW_ADDR, false); - f2fs_i_xnid_write(inode, new_xnid); + set_new_dnode(&dn, inode, NULL, NULL, new_xnid); + xpage = new_node_page(&dn, XATTR_NODE_OFFSET); + if (IS_ERR(xpage)) { + alloc_nid_failed(sbi, new_xnid); + return PTR_ERR(xpage); + } - /* 3: update xattr blkaddr */ - refresh_sit_entry(sbi, NEW_ADDR, blkaddr); - set_node_addr(sbi, &ni, blkaddr, false); + alloc_nid_done(sbi, new_xnid); + update_inode_page(inode); + + /* 3: update and set xattr node page dirty */ + memcpy(F2FS_NODE(xpage), F2FS_NODE(page), VALID_XATTR_BLOCK_SIZE); + + set_page_dirty(xpage); + f2fs_put_page(xpage, 1); + + return 0; } int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page) @@ -2035,11 +2327,12 @@ retry: } /* Should not use this inode from free nid list */ - remove_free_nid(NM_I(sbi), ino); + remove_free_nid(sbi, ino); if (!PageUptodate(ipage)) SetPageUptodate(ipage); fill_node_footer(ipage, ino, ino, 0, true); + set_cold_node(page, false); src = F2FS_INODE(page); dst = F2FS_INODE(ipage); @@ -2049,12 +2342,25 @@ retry: dst->i_blocks = cpu_to_le64(1); dst->i_links = cpu_to_le32(1); dst->i_xattr_nid = 0; - dst->i_inline = src->i_inline & F2FS_INLINE_XATTR; + dst->i_inline = src->i_inline & (F2FS_INLINE_XATTR | F2FS_EXTRA_ATTR); + if (dst->i_inline & F2FS_EXTRA_ATTR) { + dst->i_extra_isize = src->i_extra_isize; + + if (f2fs_sb_has_flexible_inline_xattr(sbi->sb) && + F2FS_FITS_IN_INODE(src, le16_to_cpu(src->i_extra_isize), + i_inline_xattr_size)) + dst->i_inline_xattr_size = src->i_inline_xattr_size; + + if (f2fs_sb_has_project_quota(sbi->sb) && + F2FS_FITS_IN_INODE(src, le16_to_cpu(src->i_extra_isize), + i_projid)) + dst->i_projid = src->i_projid; + } new_ni = old_ni; new_ni.ino = ino; - if (unlikely(!inc_valid_node_count(sbi, NULL))) + if (unlikely(inc_valid_node_count(sbi, NULL, true))) WARN_ON(1); set_node_addr(sbi, &new_ni, NEW_ADDR, false); inc_valid_inode_count(sbi); @@ -2063,13 +2369,12 @@ retry: return 0; } -int restore_node_summary(struct f2fs_sb_info *sbi, +void restore_node_summary(struct f2fs_sb_info *sbi, unsigned int segno, struct f2fs_summary_block *sum) { struct f2fs_node *rn; struct f2fs_summary *sum_entry; block_t addr; - int bio_blocks = MAX_BIO_BLOCKS(sbi); int i, idx, last_offset, nrpages; /* scan the node segment */ @@ -2078,7 +2383,7 @@ int restore_node_summary(struct f2fs_sb_ sum_entry = &sum->entries[0]; for (i = 0; i < last_offset; i += nrpages, addr += nrpages) { - nrpages = min(last_offset - i, bio_blocks); + nrpages = min(last_offset - i, BIO_MAX_PAGES); /* readahead node pages */ ra_meta_pages(sbi, addr, nrpages, META_POR, true); @@ -2097,7 +2402,6 @@ int restore_node_summary(struct f2fs_sb_ invalidate_mapping_pages(META_MAPPING(sbi), addr, addr + nrpages); } - return 0; } static void remove_nats_in_journal(struct f2fs_sb_info *sbi) @@ -2117,9 +2421,22 @@ static void remove_nats_in_journal(struc ne = __lookup_nat_cache(nm_i, nid); if (!ne) { - ne = grab_nat_entry(nm_i, nid); - node_info_from_raw_nat(&ne->ni, &raw_ne); + ne = __alloc_nat_entry(nid, true); + __init_nat_entry(nm_i, ne, &raw_ne, true); + } + + /* + * if a free nat in journal has not been used after last + * checkpoint, we should remove it from available nids, + * since later we will add it again. + */ + if (!get_nat_flag(ne, IS_DIRTY) && + le32_to_cpu(raw_ne.block_addr) == NULL_ADDR) { + spin_lock(&nm_i->nid_list_lock); + nm_i->available_nids--; + spin_unlock(&nm_i->nid_list_lock); } + __set_nat_cache_dirty(nm_i, ne); } update_nats_in_cursum(journal, -i); @@ -2144,8 +2461,41 @@ add_out: list_add_tail(&nes->set_list, head); } +static void __update_nat_bits(struct f2fs_sb_info *sbi, nid_t start_nid, + struct page *page) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + unsigned int nat_index = start_nid / NAT_ENTRY_PER_BLOCK; + struct f2fs_nat_block *nat_blk = page_address(page); + int valid = 0; + int i = 0; + + if (!enabled_nat_bits(sbi, NULL)) + return; + + if (nat_index == 0) { + valid = 1; + i = 1; + } + for (; i < NAT_ENTRY_PER_BLOCK; i++) { + if (nat_blk->entries[i].block_addr != NULL_ADDR) + valid++; + } + if (valid == 0) { + __set_bit_le(nat_index, nm_i->empty_nat_bits); + __clear_bit_le(nat_index, nm_i->full_nat_bits); + return; + } + + __clear_bit_le(nat_index, nm_i->empty_nat_bits); + if (valid == NAT_ENTRY_PER_BLOCK) + __set_bit_le(nat_index, nm_i->full_nat_bits); + else + __clear_bit_le(nat_index, nm_i->full_nat_bits); +} + static void __flush_nat_entry_set(struct f2fs_sb_info *sbi, - struct nat_entry_set *set) + struct nat_entry_set *set, struct cp_control *cpc) { struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA); struct f2fs_journal *journal = curseg->journal; @@ -2160,7 +2510,8 @@ static void __flush_nat_entry_set(struct * #1, flush nat entries to journal in current hot data summary block. * #2, flush nat entries to nat page. */ - if (!__has_cursum_space(journal, set->entry_cnt, NAT_JOURNAL)) + if (enabled_nat_bits(sbi, cpc) || + !__has_cursum_space(journal, set->entry_cnt, NAT_JOURNAL)) to_journal = false; if (to_journal) { @@ -2177,8 +2528,7 @@ static void __flush_nat_entry_set(struct nid_t nid = nat_get_nid(ne); int offset; - if (nat_get_blkaddr(ne) == NEW_ADDR) - continue; + f2fs_bug_on(sbi, nat_get_blkaddr(ne) == NEW_ADDR); if (to_journal) { offset = lookup_journal_in_cursum(journal, @@ -2191,26 +2541,34 @@ static void __flush_nat_entry_set(struct } raw_nat_from_node_info(raw_ne, &ne->ni); nat_reset_flag(ne); - __clear_nat_cache_dirty(NM_I(sbi), ne); - if (nat_get_blkaddr(ne) == NULL_ADDR) - add_free_nid(sbi, nid, false); + __clear_nat_cache_dirty(NM_I(sbi), set, ne); + if (nat_get_blkaddr(ne) == NULL_ADDR) { + add_free_nid(sbi, nid, false, true); + } else { + spin_lock(&NM_I(sbi)->nid_list_lock); + update_free_nid_bitmap(sbi, nid, false, false); + spin_unlock(&NM_I(sbi)->nid_list_lock); + } } - if (to_journal) + if (to_journal) { up_write(&curseg->journal_rwsem); - else + } else { + __update_nat_bits(sbi, start_nid, page); f2fs_put_page(page, 1); + } - f2fs_bug_on(sbi, set->entry_cnt); - - radix_tree_delete(&NM_I(sbi)->nat_set_root, set->set); - kmem_cache_free(nat_entry_set_slab, set); + /* Allow dirty nats by node block allocation in write_begin */ + if (!set->entry_cnt) { + radix_tree_delete(&NM_I(sbi)->nat_set_root, set->set); + kmem_cache_free(nat_entry_set_slab, set); + } } /* * This function is called during the checkpointing process. */ -void flush_nat_entries(struct f2fs_sb_info *sbi) +void flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA); @@ -2231,7 +2589,8 @@ void flush_nat_entries(struct f2fs_sb_in * entries, remove all entries from journal and merge them * into nat entry set. */ - if (!__has_cursum_space(journal, nm_i->dirty_nat_cnt, NAT_JOURNAL)) + if (enabled_nat_bits(sbi, cpc) || + !__has_cursum_space(journal, nm_i->dirty_nat_cnt, NAT_JOURNAL)) remove_nats_in_journal(sbi); while ((found = __gang_lookup_nat_set(nm_i, @@ -2245,11 +2604,85 @@ void flush_nat_entries(struct f2fs_sb_in /* flush dirty nats in nat entry set */ list_for_each_entry_safe(set, tmp, &sets, set_list) - __flush_nat_entry_set(sbi, set); + __flush_nat_entry_set(sbi, set, cpc); up_write(&nm_i->nat_tree_lock); + /* Allow dirty nats by node block allocation in write_begin */ +} - f2fs_bug_on(sbi, nm_i->dirty_nat_cnt); +static int __get_nat_bitmaps(struct f2fs_sb_info *sbi) +{ + struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); + struct f2fs_nm_info *nm_i = NM_I(sbi); + unsigned int nat_bits_bytes = nm_i->nat_blocks / BITS_PER_BYTE; + unsigned int i; + __u64 cp_ver = cur_cp_version(ckpt); + block_t nat_bits_addr; + + if (!enabled_nat_bits(sbi, NULL)) + return 0; + + nm_i->nat_bits_blocks = F2FS_BLK_ALIGN((nat_bits_bytes << 1) + 8); + nm_i->nat_bits = f2fs_kzalloc(sbi, + nm_i->nat_bits_blocks << F2FS_BLKSIZE_BITS, GFP_KERNEL); + if (!nm_i->nat_bits) + return -ENOMEM; + + nat_bits_addr = __start_cp_addr(sbi) + sbi->blocks_per_seg - + nm_i->nat_bits_blocks; + for (i = 0; i < nm_i->nat_bits_blocks; i++) { + struct page *page = get_meta_page(sbi, nat_bits_addr++); + + memcpy(nm_i->nat_bits + (i << F2FS_BLKSIZE_BITS), + page_address(page), F2FS_BLKSIZE); + f2fs_put_page(page, 1); + } + + cp_ver |= (cur_cp_crc(ckpt) << 32); + if (cpu_to_le64(cp_ver) != *(__le64 *)nm_i->nat_bits) { + disable_nat_bits(sbi, true); + return 0; + } + + nm_i->full_nat_bits = nm_i->nat_bits + 8; + nm_i->empty_nat_bits = nm_i->full_nat_bits + nat_bits_bytes; + + f2fs_msg(sbi->sb, KERN_NOTICE, "Found nat_bits in checkpoint"); + return 0; +} + +static inline void load_free_nid_bitmap(struct f2fs_sb_info *sbi) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + unsigned int i = 0; + nid_t nid, last_nid; + + if (!enabled_nat_bits(sbi, NULL)) + return; + + for (i = 0; i < nm_i->nat_blocks; i++) { + i = find_next_bit_le(nm_i->empty_nat_bits, nm_i->nat_blocks, i); + if (i >= nm_i->nat_blocks) + break; + + __set_bit_le(i, nm_i->nat_block_bitmap); + + nid = i * NAT_ENTRY_PER_BLOCK; + last_nid = nid + NAT_ENTRY_PER_BLOCK; + + spin_lock(&NM_I(sbi)->nid_list_lock); + for (; nid < last_nid; nid++) + update_free_nid_bitmap(sbi, nid, true, true); + spin_unlock(&NM_I(sbi)->nid_list_lock); + } + + for (i = 0; i < nm_i->nat_blocks; i++) { + i = find_next_bit_le(nm_i->full_nat_bits, nm_i->nat_blocks, i); + if (i >= nm_i->nat_blocks) + break; + + __set_bit_le(i, nm_i->nat_block_bitmap); + } } static int init_node_manager(struct f2fs_sb_info *sbi) @@ -2257,19 +2690,21 @@ static int init_node_manager(struct f2fs struct f2fs_super_block *sb_raw = F2FS_RAW_SUPER(sbi); struct f2fs_nm_info *nm_i = NM_I(sbi); unsigned char *version_bitmap; - unsigned int nat_segs, nat_blocks; + unsigned int nat_segs; + int err; nm_i->nat_blkaddr = le32_to_cpu(sb_raw->nat_blkaddr); /* segment_count_nat includes pair segment so divide to 2. */ nat_segs = le32_to_cpu(sb_raw->segment_count_nat) >> 1; - nat_blocks = nat_segs << le32_to_cpu(sb_raw->log_blocks_per_seg); - - nm_i->max_nid = NAT_ENTRY_PER_BLOCK * nat_blocks; + nm_i->nat_blocks = nat_segs << le32_to_cpu(sb_raw->log_blocks_per_seg); + nm_i->max_nid = NAT_ENTRY_PER_BLOCK * nm_i->nat_blocks; /* not used nids: 0, node, meta, (and root counted as valid node) */ - nm_i->available_nids = nm_i->max_nid - F2FS_RESERVED_NODE_NUM; - nm_i->fcnt = 0; + nm_i->available_nids = nm_i->max_nid - sbi->total_valid_node_count - + sbi->nquota_files - F2FS_RESERVED_NODE_NUM; + nm_i->nid_cnt[FREE_NID] = 0; + nm_i->nid_cnt[PREALLOC_NID] = 0; nm_i->nat_cnt = 0; nm_i->ram_thresh = DEF_RAM_THRESHOLD; nm_i->ra_nid_pages = DEF_RA_NID_PAGES; @@ -2282,7 +2717,7 @@ static int init_node_manager(struct f2fs INIT_LIST_HEAD(&nm_i->nat_entries); mutex_init(&nm_i->build_lock); - spin_lock_init(&nm_i->free_nid_list_lock); + spin_lock_init(&nm_i->nid_list_lock); init_rwsem(&nm_i->nat_tree_lock); nm_i->next_scan_nid = le32_to_cpu(sbi->ckpt->next_free_nid); @@ -2295,6 +2730,47 @@ static int init_node_manager(struct f2fs GFP_KERNEL); if (!nm_i->nat_bitmap) return -ENOMEM; + + err = __get_nat_bitmaps(sbi); + if (err) + return err; + +#ifdef CONFIG_F2FS_CHECK_FS + nm_i->nat_bitmap_mir = kmemdup(version_bitmap, nm_i->bitmap_size, + GFP_KERNEL); + if (!nm_i->nat_bitmap_mir) + return -ENOMEM; +#endif + + return 0; +} + +static int init_free_nid_cache(struct f2fs_sb_info *sbi) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + int i; + + nm_i->free_nid_bitmap = f2fs_kzalloc(sbi, nm_i->nat_blocks * + sizeof(unsigned char *), GFP_KERNEL); + if (!nm_i->free_nid_bitmap) + return -ENOMEM; + + for (i = 0; i < nm_i->nat_blocks; i++) { + nm_i->free_nid_bitmap[i] = f2fs_kvzalloc(sbi, + NAT_ENTRY_BITMAP_SIZE_ALIGNED, GFP_KERNEL); + if (!nm_i->free_nid_bitmap) + return -ENOMEM; + } + + nm_i->nat_block_bitmap = f2fs_kvzalloc(sbi, nm_i->nat_blocks / 8, + GFP_KERNEL); + if (!nm_i->nat_block_bitmap) + return -ENOMEM; + + nm_i->free_nid_count = f2fs_kvzalloc(sbi, nm_i->nat_blocks * + sizeof(unsigned short), GFP_KERNEL); + if (!nm_i->free_nid_count) + return -ENOMEM; return 0; } @@ -2302,7 +2778,8 @@ int build_node_manager(struct f2fs_sb_in { int err; - sbi->nm_info = kzalloc(sizeof(struct f2fs_nm_info), GFP_KERNEL); + sbi->nm_info = f2fs_kzalloc(sbi, sizeof(struct f2fs_nm_info), + GFP_KERNEL); if (!sbi->nm_info) return -ENOMEM; @@ -2310,7 +2787,14 @@ int build_node_manager(struct f2fs_sb_in if (err) return err; - build_free_nids(sbi); + err = init_free_nid_cache(sbi); + if (err) + return err; + + /* load free nid status from nat_bits table */ + load_free_nid_bitmap(sbi); + + build_free_nids(sbi, true, true); return 0; } @@ -2327,17 +2811,17 @@ void destroy_node_manager(struct f2fs_sb return; /* destroy free nid list */ - spin_lock(&nm_i->free_nid_list_lock); + spin_lock(&nm_i->nid_list_lock); list_for_each_entry_safe(i, next_i, &nm_i->free_nid_list, list) { - f2fs_bug_on(sbi, i->state == NID_ALLOC); - __del_from_free_nid_list(nm_i, i); - nm_i->fcnt--; - spin_unlock(&nm_i->free_nid_list_lock); + __remove_free_nid(sbi, i, FREE_NID); + spin_unlock(&nm_i->nid_list_lock); kmem_cache_free(free_nid_slab, i); - spin_lock(&nm_i->free_nid_list_lock); + spin_lock(&nm_i->nid_list_lock); } - f2fs_bug_on(sbi, nm_i->fcnt); - spin_unlock(&nm_i->free_nid_list_lock); + f2fs_bug_on(sbi, nm_i->nid_cnt[FREE_NID]); + f2fs_bug_on(sbi, nm_i->nid_cnt[PREALLOC_NID]); + f2fs_bug_on(sbi, !list_empty(&nm_i->free_nid_list)); + spin_unlock(&nm_i->nid_list_lock); /* destroy nat cache */ down_write(&nm_i->nat_tree_lock); @@ -2367,7 +2851,21 @@ void destroy_node_manager(struct f2fs_sb } up_write(&nm_i->nat_tree_lock); + kvfree(nm_i->nat_block_bitmap); + if (nm_i->free_nid_bitmap) { + int i; + + for (i = 0; i < nm_i->nat_blocks; i++) + kvfree(nm_i->free_nid_bitmap[i]); + kfree(nm_i->free_nid_bitmap); + } + kvfree(nm_i->free_nid_count); + kfree(nm_i->nat_bitmap); + kfree(nm_i->nat_bits); +#ifdef CONFIG_F2FS_CHECK_FS + kfree(nm_i->nat_bitmap_mir); +#endif sbi->nm_info = NULL; kfree(nm_i); }