diff options
Diffstat (limited to 'fs/f2fs/node.c')
-rw-r--r-- | fs/f2fs/node.c | 1809 |
1 files changed, 1263 insertions, 546 deletions
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 44b8afef43d9..b06e270b0fbe 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -19,9 +19,10 @@ #include "f2fs.h" #include "node.h" #include "segment.h" +#include "trace.h" #include <trace/events/f2fs.h> -#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; @@ -31,22 +32,50 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct sysinfo val; + unsigned long avail_ram; unsigned long mem_size = 0; bool res = false; si_meminfo(&val); - /* give 25%, 25%, 50% memory for each components respectively */ + + /* only uses low memory */ + avail_ram = val.totalram - val.totalhigh; + + /* + * give 25%, 25%, 50%, 50%, 50% memory for each components respectively + */ if (type == FREE_NIDS) { - mem_size = (nm_i->fcnt * sizeof(struct free_nid)) >> 12; - res = mem_size < ((val.totalram * nm_i->ram_thresh / 100) >> 2); + mem_size = (nm_i->nid_cnt[FREE_NID_LIST] * + 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)) >> 12; - res = mem_size < ((val.totalram * nm_i->ram_thresh / 100) >> 2); + mem_size = (nm_i->nat_cnt * sizeof(struct nat_entry)) >> + PAGE_SHIFT; + res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2); + if (excess_cached_nats(sbi)) + res = false; } else if (type == DIRTY_DENTS) { if (sbi->sb->s_bdi->dirty_exceeded) return false; mem_size = get_pages(sbi, F2FS_DIRTY_DENTS); - res = mem_size < ((val.totalram * nm_i->ram_thresh / 100) >> 1); + res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1); + } 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); + 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) * + sizeof(struct extent_tree) + + 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 (!sbi->sb->s_bdi->dirty_exceeded) + return true; } return res; } @@ -95,7 +124,7 @@ static struct page *get_next_nat_page(struct f2fs_sb_info *sbi, nid_t nid) src_addr = page_address(src_page); dst_addr = page_address(dst_page); - memcpy(dst_addr, src_addr, PAGE_CACHE_SIZE); + memcpy(dst_addr, src_addr, PAGE_SIZE); set_page_dirty(dst_page); f2fs_put_page(src_page, 1); @@ -131,20 +160,16 @@ static void __set_nat_cache_dirty(struct f2fs_nm_info *nm_i, if (get_nat_flag(ne, IS_DIRTY)) return; -retry: + head = radix_tree_lookup(&nm_i->nat_set_root, set); if (!head) { - head = f2fs_kmem_cache_alloc(nat_entry_set_slab, GFP_ATOMIC); + head = f2fs_kmem_cache_alloc(nat_entry_set_slab, GFP_NOFS); INIT_LIST_HEAD(&head->entry_list); INIT_LIST_HEAD(&head->set_list); head->set = set; head->entry_cnt = 0; - - if (radix_tree_insert(&nm_i->nat_set_root, set, head)) { - cond_resched(); - goto retry; - } + f2fs_radix_tree_insert(&nm_i->nat_set_root, set, head); } list_move_tail(&ne->list, &head->entry_list); nm_i->dirty_nat_cnt++; @@ -153,18 +178,12 @@ retry: } static void __clear_nat_cache_dirty(struct f2fs_nm_info *nm_i, - struct nat_entry *ne) + struct nat_entry_set *set, struct nat_entry *ne) { - nid_t set = ne->ni.nid / NAT_ENTRY_PER_BLOCK; - struct nat_entry_set *head; - - 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--; - } + 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, @@ -174,32 +193,35 @@ static unsigned int __gang_lookup_nat_set(struct f2fs_nm_info *nm_i, start, nr); } -bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid) +int need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct nat_entry *e; - bool is_cp = true; + bool need = false; - read_lock(&nm_i->nat_tree_lock); + down_read(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, nid); - if (e && !get_nat_flag(e, IS_CHECKPOINTED)) - is_cp = false; - read_unlock(&nm_i->nat_tree_lock); - return is_cp; + if (e) { + if (!get_nat_flag(e, IS_CHECKPOINTED) && + !get_nat_flag(e, HAS_FSYNCED_INODE)) + need = true; + } + up_read(&nm_i->nat_tree_lock); + return need; } -bool has_fsynced_inode(struct f2fs_sb_info *sbi, nid_t ino) +bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct nat_entry *e; - bool fsynced = false; + bool is_cp = true; - read_lock(&nm_i->nat_tree_lock); - e = __lookup_nat_cache(nm_i, ino); - if (e && get_nat_flag(e, HAS_FSYNCED_INODE)) - fsynced = true; - read_unlock(&nm_i->nat_tree_lock); - return fsynced; + down_read(&nm_i->nat_tree_lock); + e = __lookup_nat_cache(nm_i, nid); + if (e && !get_nat_flag(e, IS_CHECKPOINTED)) + is_cp = false; + up_read(&nm_i->nat_tree_lock); + return is_cp; } bool need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino) @@ -208,27 +230,34 @@ bool need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino) struct nat_entry *e; bool need_update = true; - read_lock(&nm_i->nat_tree_lock); + down_read(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, ino); if (e && get_nat_flag(e, HAS_LAST_FSYNC) && (get_nat_flag(e, IS_CHECKPOINTED) || get_nat_flag(e, HAS_FSYNCED_INODE))) need_update = false; - read_unlock(&nm_i->nat_tree_lock); + up_read(&nm_i->nat_tree_lock); return need_update; } -static struct nat_entry *grab_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid) +static struct nat_entry *grab_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid, + bool no_fail) { struct nat_entry *new; - new = kmem_cache_alloc(nat_entry_slab, GFP_ATOMIC); - if (!new) - return NULL; - if (radix_tree_insert(&nm_i->nat_root, nid, new)) { - kmem_cache_free(nat_entry_slab, new); - return NULL; + if (no_fail) { + new = f2fs_kmem_cache_alloc(nat_entry_slab, GFP_NOFS); + f2fs_radix_tree_insert(&nm_i->nat_root, nid, new); + } else { + new = kmem_cache_alloc(nat_entry_slab, GFP_NOFS); + if (!new) + return NULL; + if (radix_tree_insert(&nm_i->nat_root, nid, new)) { + kmem_cache_free(nat_entry_slab, new); + return NULL; + } } + memset(new, 0, sizeof(struct nat_entry)); nat_set_nid(new, nid); nat_reset_flag(new); @@ -237,22 +266,23 @@ static struct nat_entry *grab_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid) return new; } -static void cache_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid, +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; -retry: - write_lock(&nm_i->nat_tree_lock); + e = __lookup_nat_cache(nm_i, nid); if (!e) { - e = grab_nat_entry(nm_i, nid); - if (!e) { - write_unlock(&nm_i->nat_tree_lock); - goto retry; - } - node_info_from_raw_nat(&e->ni, ne); + e = grab_nat_entry(nm_i, nid, false); + if (e) + node_info_from_raw_nat(&e->ni, ne); + } 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); } - write_unlock(&nm_i->nat_tree_lock); } static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, @@ -260,16 +290,12 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, { struct f2fs_nm_info *nm_i = NM_I(sbi); struct nat_entry *e; -retry: - write_lock(&nm_i->nat_tree_lock); + + 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); - if (!e) { - write_unlock(&nm_i->nat_tree_lock); - goto retry; - } - e->ni = *ni; + e = grab_nat_entry(nm_i, ni->nid, true); + copy_node_info(&e->ni, ni); f2fs_bug_on(sbi, ni->blk_addr == NEW_ADDR); } else if (new_blkaddr == NEW_ADDR) { /* @@ -277,7 +303,7 @@ retry: * previous nat entry can be remained in nat cache. * So, reinitialize it with new information. */ - e->ni = *ni; + copy_node_info(&e->ni, ni); f2fs_bug_on(sbi, ni->blk_addr != NULL_ADDR); } @@ -295,6 +321,10 @@ retry: 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 */ @@ -304,23 +334,24 @@ retry: __set_nat_cache_dirty(nm_i, e); /* update fsync_mark if its inode nat entry is still alive */ - e = __lookup_nat_cache(nm_i, ni->ino); + if (ni->nid != ni->ino) + e = __lookup_nat_cache(nm_i, ni->ino); if (e) { if (fsync_done && ni->nid == ni->ino) set_nat_flag(e, HAS_FSYNCED_INODE, true); set_nat_flag(e, HAS_LAST_FSYNC, fsync_done); } - write_unlock(&nm_i->nat_tree_lock); + up_write(&nm_i->nat_tree_lock); } int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink) { struct f2fs_nm_info *nm_i = NM_I(sbi); + int nr = nr_shrink; - if (available_free_memory(sbi, NAT_ENTRIES)) + if (!down_write_trylock(&nm_i->nat_tree_lock)) return 0; - write_lock(&nm_i->nat_tree_lock); while (nr_shrink && !list_empty(&nm_i->nat_entries)) { struct nat_entry *ne; ne = list_first_entry(&nm_i->nat_entries, @@ -328,8 +359,8 @@ int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink) __del_from_nat_cache(nm_i, ne); nr_shrink--; } - write_unlock(&nm_i->nat_tree_lock); - return nr_shrink; + up_write(&nm_i->nat_tree_lock); + return nr - nr_shrink; } /* @@ -339,59 +370,121 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA); - struct f2fs_summary_block *sum = curseg->sum_blk; + struct f2fs_journal *journal = curseg->journal; nid_t start_nid = START_NID(nid); struct f2fs_nat_block *nat_blk; struct page *page = NULL; struct f2fs_nat_entry ne; struct nat_entry *e; + pgoff_t index; int i; - memset(&ne, 0, sizeof(struct f2fs_nat_entry)); ni->nid = nid; /* Check nat cache */ - read_lock(&nm_i->nat_tree_lock); + down_read(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, nid); if (e) { ni->ino = nat_get_ino(e); ni->blk_addr = nat_get_blkaddr(e); ni->version = nat_get_version(e); - } - read_unlock(&nm_i->nat_tree_lock); - if (e) + up_read(&nm_i->nat_tree_lock); return; + } + + memset(&ne, 0, sizeof(struct f2fs_nat_entry)); /* Check current segment summary */ - mutex_lock(&curseg->curseg_mutex); - i = lookup_journal_in_cursum(sum, NAT_JOURNAL, nid, 0); + down_read(&curseg->journal_rwsem); + i = lookup_journal_in_cursum(journal, NAT_JOURNAL, nid, 0); if (i >= 0) { - ne = nat_in_journal(sum, i); + ne = nat_in_journal(journal, i); node_info_from_raw_nat(ni, &ne); } - mutex_unlock(&curseg->curseg_mutex); - if (i >= 0) + up_read(&curseg->journal_rwsem); + 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: /* cache nat entry */ - cache_nat_entry(NM_I(sbi), nid, &ne); + down_write(&nm_i->nat_tree_lock); + cache_nat_entry(sbi, nid, &ne); + up_write(&nm_i->nat_tree_lock); +} + +/* + * readahead MAX_RA_NODE number of node pages. + */ +static void ra_node_pages(struct page *parent, int start, int n) +{ + struct f2fs_sb_info *sbi = F2FS_P_SB(parent); + struct blk_plug plug; + int i, end; + nid_t nid; + + blk_start_plug(&plug); + + /* Then, try readahead for siblings of the desired node */ + end = start + n; + end = min(end, NIDS_PER_BLOCK); + for (i = start; i < end; i++) { + nid = get_nid(parent, i, false); + ra_node_page(sbi, nid); + } + + blk_finish_plug(&plug); +} + +pgoff_t get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs) +{ + const long direct_index = ADDRS_PER_INODE(dn->inode); + const long direct_blks = ADDRS_PER_BLOCK; + const long indirect_blks = ADDRS_PER_BLOCK * NIDS_PER_BLOCK; + unsigned int skipped_unit = ADDRS_PER_BLOCK; + int cur_level = dn->cur_level; + int max_level = dn->max_level; + pgoff_t base = 0; + + if (!dn->max_level) + return pgofs + 1; + + while (max_level-- > cur_level) + skipped_unit *= NIDS_PER_BLOCK; + + switch (dn->max_level) { + case 3: + base += 2 * indirect_blks; + case 2: + base += 2 * direct_blks; + case 1: + base += direct_index; + break; + default: + f2fs_bug_on(F2FS_I_SB(dn->inode), 1); + } + + return ((pgofs - base) / skipped_unit + 1) * skipped_unit + base; } /* * The maximum depth is four. * Offset[0] will have raw inode offset. */ -static int get_node_path(struct f2fs_inode_info *fi, long block, +static int get_node_path(struct inode *inode, long block, int offset[4], unsigned int noffset[4]) { - const long direct_index = ADDRS_PER_INODE(fi); + const long direct_index = ADDRS_PER_INODE(inode); const long direct_blks = ADDRS_PER_BLOCK; const long dptrs_per_blk = NIDS_PER_BLOCK; const long indirect_blks = ADDRS_PER_BLOCK * NIDS_PER_BLOCK; @@ -472,14 +565,14 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode) { struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); struct page *npage[4]; - struct page *parent; + struct page *parent = NULL; int offset[4]; unsigned int noffset[4]; nid_t nids[4]; - int level, i; + int level, i = 0; int err = 0; - level = get_node_path(F2FS_I(dn->inode), index, offset, noffset); + level = get_node_path(dn->inode, index, offset, noffset); nids[0] = dn->inode->i_ino; npage[0] = dn->inode_page; @@ -489,6 +582,14 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode) if (IS_ERR(npage[0])) return PTR_ERR(npage[0]); } + + /* if inline_data is set, should not report any block indices */ + if (f2fs_has_inline_data(dn->inode) && index) { + err = -ENOENT; + f2fs_put_page(npage[0], 1); + goto release_out; + } + parent = npage[0]; if (level != 0) nids[1] = get_nid(parent, offset[0], true); @@ -558,6 +659,11 @@ release_pages: release_out: dn->inode_page = NULL; dn->node_page = NULL; + if (err == -ENOENT) { + dn->cur_level = i; + dn->max_level = level; + dn->ofs_in_node = offset[level]; + } return err; } @@ -581,12 +687,11 @@ static void truncate_node(struct dnode_of_data *dn) if (dn->nid == dn->inode->i_ino) { remove_orphan_inode(sbi, dn->nid); dec_valid_inode_count(sbi); - } else { - sync_inode_page(dn); + f2fs_inode_synced(dn->inode); } invalidate: clear_node_page_dirty(dn->node_page); - F2FS_SET_SB_DIRT(sbi); + set_sbi_flag(sbi, SBI_IS_DIRTY); f2fs_put_page(dn->node_page, 1); @@ -641,6 +746,8 @@ static int truncate_nodes(struct dnode_of_data *dn, unsigned int nofs, return PTR_ERR(page); } + ra_node_pages(page, ofs, NIDS_PER_BLOCK); + rn = F2FS_NODE(page); if (depth < 3) { for (i = ofs; i < NIDS_PER_BLOCK; i++, freed++) { @@ -651,7 +758,8 @@ static int truncate_nodes(struct dnode_of_data *dn, unsigned int nofs, ret = truncate_dnode(&rdn); if (ret < 0) goto out_err; - set_nid(page, i, 0, false); + if (set_nid(page, i, 0, false)) + dn->node_changed = true; } } else { child_nofs = nofs + ofs * (NIDS_PER_BLOCK + 1) + 1; @@ -664,7 +772,8 @@ static int truncate_nodes(struct dnode_of_data *dn, unsigned int nofs, rdn.nid = child_nid; ret = truncate_nodes(&rdn, child_nofs, 0, depth - 1); if (ret == (NIDS_PER_BLOCK + 1)) { - set_nid(page, i, 0, false); + if (set_nid(page, i, 0, false)) + dn->node_changed = true; child_nofs += ret; } else if (ret < 0 && ret != -ENOENT) { goto out_err; @@ -716,6 +825,8 @@ static int truncate_partial_nodes(struct dnode_of_data *dn, nid[i + 1] = get_nid(pages[i], offset[i + 1], false); } + ra_node_pages(pages[idx], offset[idx + 1], NIDS_PER_BLOCK); + /* free direct nodes linked to a partial indirect node */ for (i = offset[idx + 1]; i < NIDS_PER_BLOCK; i++) { child_nid = get_nid(pages[idx], i, false); @@ -725,7 +836,8 @@ static int truncate_partial_nodes(struct dnode_of_data *dn, err = truncate_dnode(dn); if (err < 0) goto fail; - set_nid(pages[idx], i, 0, false); + if (set_nid(pages[idx], i, 0, false)) + dn->node_changed = true; } if (offset[idx + 1] == 0) { @@ -762,8 +874,8 @@ int truncate_inode_blocks(struct inode *inode, pgoff_t from) trace_f2fs_truncate_inode_blocks_enter(inode, from); - level = get_node_path(F2FS_I(inode), from, offset, noffset); -restart: + level = get_node_path(inode, from, offset, noffset); + page = get_node_page(sbi, inode->i_ino); if (IS_ERR(page)) { trace_f2fs_truncate_inode_blocks_exit(inode, PTR_ERR(page)); @@ -827,11 +939,8 @@ skip_partial: if (offset[1] == 0 && ri->i_nid[offset[0] - NODE_DIR1_BLOCK]) { lock_page(page); - if (unlikely(page->mapping != NODE_MAPPING(sbi))) { - f2fs_put_page(page, 1); - goto restart; - } - f2fs_wait_on_page_writeback(page, NODE); + BUG_ON(page->mapping != NODE_MAPPING(sbi)); + f2fs_wait_on_page_writeback(page, NODE, true); ri->i_nid[offset[0] - NODE_DIR1_BLOCK] = 0; set_page_dirty(page); unlock_page(page); @@ -860,10 +969,7 @@ int truncate_xattr_node(struct inode *inode, struct page *page) if (IS_ERR(npage)) return PTR_ERR(npage); - F2FS_I(inode)->i_xattr_nid = 0; - - /* need to do checkpoint during fsync */ - F2FS_I(inode)->xattr_ver = cur_cp_version(F2FS_CKPT(sbi)); + f2fs_i_xnid_write(inode, 0); set_new_dnode(&dn, inode, page, npage, nid); @@ -877,17 +983,20 @@ int truncate_xattr_node(struct inode *inode, struct page *page) * Caller should grab and release a rwsem by calling f2fs_lock_op() and * f2fs_unlock_op(). */ -void remove_inode_page(struct inode *inode) +int remove_inode_page(struct inode *inode) { struct dnode_of_data dn; + int err; set_new_dnode(&dn, inode, NULL, NULL, inode->i_ino); - if (get_dnode_of_data(&dn, 0, LOOKUP_NODE)) - return; + err = get_dnode_of_data(&dn, 0, LOOKUP_NODE); + if (err) + return err; - if (truncate_xattr_node(inode, dn.inode_page)) { + err = truncate_xattr_node(inode, dn.inode_page); + if (err) { f2fs_put_dnode(&dn); - return; + return err; } /* remove potential inline_data blocks */ @@ -901,6 +1010,7 @@ void remove_inode_page(struct inode *inode) /* will put inode & node pages */ truncate_node(&dn); + return 0; } struct page *new_inode_page(struct inode *inode) @@ -918,14 +1028,14 @@ struct page *new_node_page(struct dnode_of_data *dn, unsigned int ofs, struct page *ipage) { 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; - if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC))) + if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC))) return ERR_PTR(-EPERM); - page = grab_cache_page(NODE_MAPPING(sbi), dn->nid); + page = f2fs_grab_cache_page(NODE_MAPPING(sbi), dn->nid, false); if (!page) return ERR_PTR(-ENOMEM); @@ -933,32 +1043,30 @@ struct page *new_node_page(struct dnode_of_data *dn, err = -ENOSPC; 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); + 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); - SetPageUptodate(page); - set_page_dirty(page); + if (!PageUptodate(page)) + SetPageUptodate(page); + if (set_page_dirty(page)) + dn->node_changed = true; if (f2fs_has_xattr_block(ofs)) - F2FS_I(dn->inode)->i_xattr_nid = dn->nid; + f2fs_i_xnid_write(dn->inode, dn->nid); - dn->node_page = page; - if (ipage) - update_inode(dn->inode, ipage); - else - sync_inode_page(dn); if (ofs == 0) inc_valid_inode_count(sbi); - return page; fail: @@ -970,25 +1078,33 @@ fail: /* * Caller should do after getting the following values. * 0: f2fs_put_page(page, 0) - * LOCKED_PAGE: f2fs_put_page(page, 1) - * error: nothing + * LOCKED_PAGE or error: f2fs_put_page(page, 1) */ -static int read_node_page(struct page *page, int rw) +static int read_node_page(struct page *page, int op_flags) { struct f2fs_sb_info *sbi = F2FS_P_SB(page); struct node_info ni; + struct f2fs_io_info fio = { + .sbi = sbi, + .type = NODE, + .op = REQ_OP_READ, + .op_flags = op_flags, + .page = page, + .encrypted_page = NULL, + }; + + if (PageUptodate(page)) + return LOCKED_PAGE; get_node_info(sbi, page->index, &ni); if (unlikely(ni.blk_addr == NULL_ADDR)) { - f2fs_put_page(page, 1); + ClearPageUptodate(page); return -ENOENT; } - if (PageUptodate(page)) - return LOCKED_PAGE; - - return f2fs_submit_page_bio(sbi, page, ni.blk_addr, rw); + fio.new_blkaddr = fio.old_blkaddr = ni.blk_addr; + return f2fs_submit_page_bio(&fio); } /* @@ -999,134 +1115,433 @@ void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid) struct page *apage; int err; - apage = find_get_page(NODE_MAPPING(sbi), nid); - if (apage && PageUptodate(apage)) { - f2fs_put_page(apage, 0); + if (!nid) + return; + f2fs_bug_on(sbi, check_nid_range(sbi, nid)); + + rcu_read_lock(); + apage = radix_tree_lookup(&NODE_MAPPING(sbi)->page_tree, nid); + rcu_read_unlock(); + if (apage) return; - } - f2fs_put_page(apage, 0); - apage = grab_cache_page(NODE_MAPPING(sbi), nid); + apage = f2fs_grab_cache_page(NODE_MAPPING(sbi), nid, false); if (!apage) return; - err = read_node_page(apage, READA); - if (err == 0) - f2fs_put_page(apage, 0); - else if (err == LOCKED_PAGE) - f2fs_put_page(apage, 1); + err = read_node_page(apage, REQ_RAHEAD); + f2fs_put_page(apage, err ? 1 : 0); } -struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid) +static struct page *__get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid, + struct page *parent, int start) { struct page *page; int err; + + if (!nid) + return ERR_PTR(-ENOENT); + f2fs_bug_on(sbi, check_nid_range(sbi, nid)); repeat: - page = grab_cache_page(NODE_MAPPING(sbi), nid); + page = f2fs_grab_cache_page(NODE_MAPPING(sbi), nid, false); if (!page) return ERR_PTR(-ENOMEM); - err = read_node_page(page, READ_SYNC); - if (err < 0) + err = read_node_page(page, 0); + if (err < 0) { + f2fs_put_page(page, 1); return ERR_PTR(err); - else if (err == LOCKED_PAGE) - goto got_it; + } else if (err == LOCKED_PAGE) { + goto page_hit; + } + + if (parent) + ra_node_pages(parent, start + 1, MAX_RA_NODE); lock_page(page); - if (unlikely(!PageUptodate(page) || nid != nid_of_node(page))) { - f2fs_put_page(page, 1); - return ERR_PTR(-EIO); - } + if (unlikely(page->mapping != NODE_MAPPING(sbi))) { f2fs_put_page(page, 1); goto repeat; } -got_it: + + if (unlikely(!PageUptodate(page))) + goto out_err; +page_hit: + if(unlikely(nid != nid_of_node(page))) { + f2fs_bug_on(sbi, 1); + ClearPageUptodate(page); +out_err: + f2fs_put_page(page, 1); + return ERR_PTR(-EIO); + } + mark_page_accessed(page); return page; } -/* - * Return a locked page for the desired node page. - * And, readahead MAX_RA_NODE number of node pages. - */ +struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid) +{ + return __get_node_page(sbi, nid, NULL, 0); +} + struct page *get_node_page_ra(struct page *parent, int start) { struct f2fs_sb_info *sbi = F2FS_P_SB(parent); - struct blk_plug plug; + nid_t nid = get_nid(parent, start, false); + + return __get_node_page(sbi, nid, parent, start); +} + +static void flush_inline_data(struct f2fs_sb_info *sbi, nid_t ino) +{ + struct inode *inode; struct page *page; - int err, i, end; - nid_t nid; + int ret; - /* First, try getting the desired direct node. */ - nid = get_nid(parent, start, false); - if (!nid) - return ERR_PTR(-ENOENT); -repeat: - page = grab_cache_page(NODE_MAPPING(sbi), nid); + /* should flush inline_data before evict_inode */ + inode = ilookup(sbi->sb, ino); + if (!inode) + return; + + page = find_get_page(inode->i_mapping, 0); if (!page) - return ERR_PTR(-ENOMEM); + goto iput_out; - err = read_node_page(page, READ_SYNC); - if (err < 0) - return ERR_PTR(err); - else if (err == LOCKED_PAGE) - goto page_hit; + if (!trylock_page(page)) + goto release_out; - blk_start_plug(&plug); + if (!PageUptodate(page)) + goto page_out; - /* Then, try readahead for siblings of the desired node */ - end = start + MAX_RA_NODE; - end = min(end, NIDS_PER_BLOCK); - for (i = start + 1; i < end; i++) { - nid = get_nid(parent, i, false); - if (!nid) - continue; - ra_node_page(sbi, nid); - } + if (!PageDirty(page)) + goto page_out; - blk_finish_plug(&plug); + if (!clear_page_dirty_for_io(page)) + goto page_out; - lock_page(page); - if (unlikely(page->mapping != NODE_MAPPING(sbi))) { - f2fs_put_page(page, 1); - goto repeat; + ret = f2fs_write_inline_data(inode, page); + inode_dec_dirty_pages(inode); + remove_dirty_inode(inode); + if (ret) + set_page_dirty(page); +page_out: + unlock_page(page); +release_out: + f2fs_put_page(page, 0); +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); } -page_hit: - if (unlikely(!PageUptodate(page))) { - f2fs_put_page(page, 1); - return ERR_PTR(-EIO); +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; + struct pagevec pvec; + struct page *last_page = NULL; + + pagevec_init(&pvec, 0); + index = 0; + end = ULONG_MAX; + + while (index <= end) { + int i, nr_pages; + nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index, + PAGECACHE_TAG_DIRTY, + min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1); + if (nr_pages == 0) + break; + + for (i = 0; i < nr_pages; i++) { + struct page *page = pvec.pages[i]; + + if (unlikely(f2fs_cp_error(sbi))) { + f2fs_put_page(last_page, 0); + pagevec_release(&pvec); + return ERR_PTR(-EIO); + } + + if (!IS_DNODE(page) || !is_cold_node(page)) + continue; + if (ino_of_node(page) != ino) + continue; + + lock_page(page); + + if (unlikely(page->mapping != NODE_MAPPING(sbi))) { +continue_unlock: + unlock_page(page); + continue; + } + if (ino_of_node(page) != ino) + goto continue_unlock; + + if (!PageDirty(page)) { + /* someone wrote it for us */ + goto continue_unlock; + } + + if (last_page) + f2fs_put_page(last_page, 0); + + get_page(page); + last_page = page; + unlock_page(page); + } + pagevec_release(&pvec); + cond_resched(); } - return page; + return last_page; } -void sync_inode_page(struct dnode_of_data *dn) +static int __write_node_page(struct page *page, bool atomic, bool *submitted, + struct writeback_control *wbc) { - if (IS_INODE(dn->node_page) || dn->inode_page == dn->node_page) { - update_inode(dn->inode, dn->node_page); - } else if (dn->inode_page) { - if (!dn->inode_page_locked) - lock_page(dn->inode_page); - update_inode(dn->inode, dn->inode_page); - if (!dn->inode_page_locked) - unlock_page(dn->inode_page); + 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_to_write_flags(wbc), + .page = page, + .encrypted_page = NULL, + .submitted = false, + }; + + 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 { - update_inode_page(dn->inode); + 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 |= WRITE_FLUSH_FUA; + + 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, page->mapping->host, 0, + page->index, NODE, WRITE); + submitted = NULL; + } + + unlock_page(page); + + if (unlikely(f2fs_cp_error(sbi))) { + f2fs_submit_merged_bio(sbi, NODE, WRITE); + submitted = NULL; + } + if (submitted) + *submitted = fio.submitted; + + return 0; + +redirty_out: + redirty_page_for_writepage(wbc, page); + return AOP_WRITEPAGE_ACTIVATE; +} + +static int f2fs_write_node_page(struct page *page, + struct writeback_control *wbc) +{ + return __write_node_page(page, false, NULL, wbc); +} + +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; + + if (atomic) { + last_page = last_fsync_dnode(sbi, ino); + if (IS_ERR_OR_NULL(last_page)) + return PTR_ERR_OR_ZERO(last_page); + } +retry: + pagevec_init(&pvec, 0); + index = 0; + end = ULONG_MAX; + + while (index <= end) { + int i, nr_pages; + nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index, + PAGECACHE_TAG_DIRTY, + min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1); + if (nr_pages == 0) + break; + + 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); + ret = -EIO; + goto out; + } + + if (!IS_DNODE(page) || !is_cold_node(page)) + continue; + if (ino_of_node(page) != ino) + continue; + + lock_page(page); + + if (unlikely(page->mapping != NODE_MAPPING(sbi))) { +continue_unlock: + unlock_page(page); + continue; + } + if (ino_of_node(page) != ino) + goto continue_unlock; + + if (!PageDirty(page) && page != last_page) { + /* someone wrote it for us */ + goto 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)) { + if (is_inode_flag_set(inode, + FI_DIRTY_INODE)) + update_inode(inode, page); + set_dentry_mark(page, + need_dentry_mark(sbi, ino)); + } + /* may be written by other thread */ + if (!PageDirty(page)) + set_page_dirty(page); + } + + if (!clear_page_dirty_for_io(page)) + goto continue_unlock; + + ret = __write_node_page(page, atomic && + page == last_page, + &submitted, wbc); + if (ret) { + unlock_page(page); + f2fs_put_page(last_page, 0); + break; + } else if (submitted) { + last_idx = page->index; + } + + if (page == last_page) { + f2fs_put_page(page, 0); + marked = true; + break; + } + } + pagevec_release(&pvec); + cond_resched(); + + if (ret || marked) + break; } + if (!ret && atomic && !marked) { + f2fs_msg(sbi->sb, KERN_DEBUG, + "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; + } +out: + if (last_idx != ULONG_MAX) + f2fs_submit_merged_bio_cond(sbi, NULL, ino, last_idx, + NODE, WRITE); + return ret ? -EIO: 0; } -int sync_node_pages(struct f2fs_sb_info *sbi, nid_t ino, - struct writeback_control *wbc) +int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc) { pgoff_t index, end; struct pagevec pvec; - int step = ino ? 2 : 0; - int nwritten = 0, wrote = 0; + int step = 0; + int nwritten = 0; + int ret = 0; pagevec_init(&pvec, 0); next_step: index = 0; - end = LONG_MAX; + end = ULONG_MAX; while (index <= end) { int i, nr_pages; @@ -1138,6 +1553,13 @@ next_step: for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; + bool submitted = false; + + if (unlikely(f2fs_cp_error(sbi))) { + pagevec_release(&pvec); + ret = -EIO; + goto out; + } /* * flushing sequence with step: @@ -1153,14 +1575,8 @@ next_step: if (step == 2 && (!IS_DNODE(page) || !is_cold_node(page))) continue; - - /* - * If an fsync mode, - * we should not skip writing node pages. - */ - if (ino && ino_of_node(page) == ino) - lock_page(page); - else if (!trylock_page(page)) +lock_node: + if (!trylock_page(page)) continue; if (unlikely(page->mapping != NODE_MAPPING(sbi))) { @@ -1168,37 +1584,34 @@ continue_unlock: unlock_page(page); continue; } - if (ino && ino_of_node(page) != ino) - goto continue_unlock; if (!PageDirty(page)) { /* someone wrote it for us */ goto continue_unlock; } + /* flush inline_data */ + if (is_inline_node(page)) { + clear_inline_node(page); + unlock_page(page); + flush_inline_data(sbi, ino_of_node(page)); + goto lock_node; + } + + f2fs_wait_on_page_writeback(page, NODE, true); + + BUG_ON(PageWriteback(page)); if (!clear_page_dirty_for_io(page)) goto continue_unlock; - /* called by fsync() */ - if (ino && IS_DNODE(page)) { - set_fsync_mark(page, 1); - if (IS_INODE(page)) { - if (!is_checkpointed_node(sbi, ino) && - !has_fsynced_inode(sbi, ino)) - set_dentry_mark(page, 1); - else - set_dentry_mark(page, 0); - } - nwritten++; - } else { - set_fsync_mark(page, 0); - set_dentry_mark(page, 0); - } + 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); + if (ret) unlock_page(page); - else - wrote++; + else if (submitted) + nwritten++; if (--wbc->nr_to_write == 0) break; @@ -1216,15 +1629,15 @@ continue_unlock: step++; goto next_step; } - - if (wrote) +out: + if (nwritten) f2fs_submit_merged_bio(sbi, NODE, WRITE); - return nwritten; + return ret; } int wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino) { - pgoff_t index = 0, end = LONG_MAX; + pgoff_t index = 0, end = ULONG_MAX; struct pagevec pvec; int ret2 = 0, ret = 0; @@ -1246,7 +1659,7 @@ int wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino) continue; if (ino && ino_of_node(page) == ino) { - f2fs_wait_on_page_writeback(page, NODE); + f2fs_wait_on_page_writeback(page, NODE, true); if (TestClearPageError(page)) ret = -EIO; } @@ -1264,65 +1677,13 @@ int wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino) 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; - block_t new_addr; - struct node_info ni; - struct f2fs_io_info fio = { - .type = NODE, - .rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE, - }; - - trace_f2fs_writepage(page, NODE); - - if (unlikely(sbi->por_doing)) - goto redirty_out; - if (unlikely(f2fs_cp_error(sbi))) - goto redirty_out; - - f2fs_wait_on_page_writeback(page, NODE); - - /* get old block addr of this node page */ - nid = nid_of_node(page); - f2fs_bug_on(sbi, page->index != nid); - - get_node_info(sbi, nid, &ni); - - /* This page is already truncated */ - if (unlikely(ni.blk_addr == NULL_ADDR)) { - dec_page_count(sbi, F2FS_DIRTY_NODES); - unlock_page(page); - return 0; - } - - if (wbc->for_reclaim) - goto redirty_out; - - down_read(&sbi->node_write); - set_page_writeback(page); - write_node_page(sbi, page, &fio, nid, ni.blk_addr, &new_addr); - set_node_addr(sbi, &ni, new_addr, is_fsync_dnode(page)); - dec_page_count(sbi, F2FS_DIRTY_NODES); - up_read(&sbi->node_write); - unlock_page(page); - 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) { struct f2fs_sb_info *sbi = F2FS_M_SB(mapping); + struct blk_plug plug; long diff; - trace_f2fs_writepages(mapping->host, wbc, NODE); - /* balancing f2fs's metadata in background */ f2fs_balance_fs_bg(sbi); @@ -1330,14 +1691,19 @@ static int f2fs_write_node_pages(struct address_space *mapping, if (get_pages(sbi, F2FS_DIRTY_NODES) < nr_pages_to_skip(sbi, NODE)) goto skip_write; + trace_f2fs_writepages(mapping->host, wbc, NODE); + diff = nr_pages_to_write(sbi, NODE, wbc); wbc->sync_mode = WB_SYNC_NONE; - sync_node_pages(sbi, 0, wbc); + blk_start_plug(&plug); + sync_node_pages(sbi, wbc); + blk_finish_plug(&plug); wbc->nr_to_write = max((long)0, wbc->nr_to_write - diff); return 0; skip_write: wbc->pages_skipped += get_pages(sbi, F2FS_DIRTY_NODES); + trace_f2fs_writepages(mapping->host, wbc, NODE); return 0; } @@ -1345,31 +1711,18 @@ static int f2fs_set_node_page_dirty(struct page *page) { trace_f2fs_set_page_dirty(page, NODE); - SetPageUptodate(page); + if (!PageUptodate(page)) + SetPageUptodate(page); if (!PageDirty(page)) { - __set_page_dirty_nobuffers(page); + f2fs_set_page_dirty_nobuffers(page); inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_NODES); SetPagePrivate(page); + f2fs_trace_pid(page); return 1; } return 0; } -static void f2fs_invalidate_node_page(struct page *page, unsigned int offset, - unsigned int length) -{ - struct inode *inode = page->mapping->host; - if (PageDirty(page)) - dec_page_count(F2FS_I_SB(inode), F2FS_DIRTY_NODES); - ClearPagePrivate(page); -} - -static int f2fs_release_node_page(struct page *page, gfp_t wait) -{ - ClearPagePrivate(page); - return 1; -} - /* * Structure of the f2fs node operations */ @@ -1377,8 +1730,11 @@ const struct address_space_operations f2fs_node_aops = { .writepage = f2fs_write_node_page, .writepages = f2fs_write_node_pages, .set_page_dirty = f2fs_set_node_page_dirty, - .invalidatepage = f2fs_invalidate_node_page, - .releasepage = f2fs_release_node_page, + .invalidatepage = f2fs_invalidate_page, + .releasepage = f2fs_release_page, +#ifdef CONFIG_F2FS_MIGRATION + .migratepage = f2fs_migrate_page, +#endif }; static struct free_nid *__lookup_free_nid_list(struct f2fs_nm_info *nm_i, @@ -1387,112 +1743,250 @@ static struct free_nid *__lookup_free_nid_list(struct f2fs_nm_info *nm_i, 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_nid_to_list(struct f2fs_sb_info *sbi, + struct free_nid *i, enum nid_list list, bool new) { + struct f2fs_nm_info *nm_i = NM_I(sbi); + + if (new) { + int err = radix_tree_insert(&nm_i->free_nid_root, i->nid, i); + if (err) + return err; + } + + f2fs_bug_on(sbi, list == FREE_NID_LIST ? i->state != NID_NEW : + i->state != NID_ALLOC); + nm_i->nid_cnt[list]++; + list_add_tail(&i->list, &nm_i->nid_list[list]); + return 0; +} + +static void __remove_nid_from_list(struct f2fs_sb_info *sbi, + struct free_nid *i, enum nid_list list, bool reuse) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + + f2fs_bug_on(sbi, list == FREE_NID_LIST ? i->state != NID_NEW : + i->state != NID_ALLOC); + nm_i->nid_cnt[list]--; list_del(&i->list); - radix_tree_delete(&nm_i->free_nid_root, i->nid); + if (!reuse) + 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) +/* return if the nid is recognized as free */ +static bool add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build) { struct f2fs_nm_info *nm_i = NM_I(sbi); - struct free_nid *i; + struct free_nid *i, *e; struct nat_entry *ne; - bool allocated = false; - - if (!available_free_memory(sbi, FREE_NIDS)) - return -1; + int err = -EINVAL; + bool ret = false; /* 0 nid should not be used */ if (unlikely(nid == 0)) - return 0; - - if (build) { - /* do not add allocated nids */ - read_lock(&nm_i->nat_tree_lock); - ne = __lookup_nat_cache(nm_i, nid); - if (ne && - (!get_nat_flag(ne, IS_CHECKPOINTED) || - nat_get_blkaddr(ne) != NULL_ADDR)) - allocated = true; - read_unlock(&nm_i->nat_tree_lock); - if (allocated) - return 0; - } + return false; i = f2fs_kmem_cache_alloc(free_nid_slab, GFP_NOFS); i->nid = nid; i->state = NID_NEW; - 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); - kmem_cache_free(free_nid_slab, i); - return 0; + if (radix_tree_preload(GFP_NOFS)) + goto err; + + spin_lock(&nm_i->nid_list_lock); + + if (build) { + /* + * Thread A Thread B + * - f2fs_create + * - f2fs_new_inode + * - alloc_nid + * - __insert_nid_to_list(ALLOC_NID_LIST) + * - 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(ALLOC_NID_LIST) + * - __insert_nid_to_list(FREE_NID_LIST) + */ + ne = __lookup_nat_cache(nm_i, nid); + if (ne && (!get_nat_flag(ne, IS_CHECKPOINTED) || + nat_get_blkaddr(ne) != NULL_ADDR)) + goto err_out; + + e = __lookup_free_nid_list(nm_i, nid); + if (e) { + if (e->state == NID_NEW) + ret = true; + goto err_out; + } } - list_add_tail(&i->list, &nm_i->free_nid_list); - nm_i->fcnt++; - spin_unlock(&nm_i->free_nid_list_lock); - return 1; + ret = true; + err = __insert_nid_to_list(sbi, i, FREE_NID_LIST, true); +err_out: + spin_unlock(&nm_i->nid_list_lock); + radix_tree_preload_end(); +err: + 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--; + __remove_nid_from_list(sbi, i, FREE_NID_LIST, false); 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); } +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) + __set_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs]); + else + __clear_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs]); + + if (set) + nm_i->free_nid_count[nat_ofs]++; + else if (!build) + nm_i->free_nid_count[nat_ofs]--; +} + static void scan_nat_page(struct f2fs_sb_info *sbi, struct page *nat_page, nid_t start_nid) { 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; + if (test_bit_le(nat_ofs, nm_i->nat_block_bitmap)) + return; + + __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++) { + bool freed = false; 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; + if (blk_addr == NULL_ADDR) + freed = add_free_nid(sbi, start_nid, true); + spin_lock(&NM_I(sbi)->nid_list_lock); + update_free_nid_bitmap(sbi, start_nid, freed, true); + spin_unlock(&NM_I(sbi)->nid_list_lock); + } +} + +static void scan_free_nid_bits(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; + unsigned int i, idx; + + 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++) { + nid_t nid; + + if (!test_bit_le(idx, nm_i->free_nid_bitmap[i])) + continue; + + nid = i * NAT_ENTRY_PER_BLOCK + idx; + add_free_nid(sbi, nid, true); + + if (nm_i->nid_cnt[FREE_NID_LIST] >= MAX_FREE_NIDS) + goto out; } } +out: + 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); + else + remove_free_nid(sbi, nid); + } + up_read(&curseg->journal_rwsem); + up_read(&nm_i->nat_tree_lock); } -static void build_free_nids(struct f2fs_sb_info *sbi) +static void __build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA); - struct f2fs_summary_block *sum = curseg->sum_blk; + struct f2fs_journal *journal = curseg->journal; 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_LIST] >= 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_LIST]) + return; + } + /* readahead nat pages to be scanned */ - ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES, META_NAT); + ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES, + META_NAT, true); + + down_read(&nm_i->nat_tree_lock); while (1) { struct page *page = get_current_nat_page(sbi, nid); @@ -1504,7 +1998,7 @@ static void build_free_nids(struct f2fs_sb_info *sbi) if (unlikely(nid >= nm_i->max_nid)) nid = 0; - if (i++ == FREE_NID_PAGES) + if (++i >= FREE_NID_PAGES) break; } @@ -1512,16 +2006,29 @@ static void build_free_nids(struct f2fs_sb_info *sbi) nm_i->next_scan_nid = nid; /* find free nids from current sum_pages */ - mutex_lock(&curseg->curseg_mutex); - for (i = 0; i < nats_in_cursum(sum); i++) { - block_t addr = le32_to_cpu(nat_in_journal(sum, i).block_addr); - nid = le32_to_cpu(nid_in_journal(sum, i)); + down_read(&curseg->journal_rwsem); + for (i = 0; i < nats_in_cursum(journal); i++) { + block_t addr; + + 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); + remove_free_nid(sbi, nid); } - mutex_unlock(&curseg->curseg_mutex); + 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); } /* @@ -1534,31 +2041,40 @@ bool alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid) struct f2fs_nm_info *nm_i = NM_I(sbi); struct free_nid *i = NULL; retry: - if (unlikely(sbi->total_valid_node_count + 1 > nm_i->available_nids)) +#ifdef CONFIG_F2FS_FAULT_INJECTION + if (time_to_inject(sbi, FAULT_ALLOC_NID)) { + f2fs_show_injection_info(FAULT_ALLOC_NID); return false; + } +#endif + 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)) { - 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); + if (nm_i->nid_cnt[FREE_NID_LIST] && !on_build_free_nids(nm_i)) { + f2fs_bug_on(sbi, list_empty(&nm_i->nid_list[FREE_NID_LIST])); + i = list_first_entry(&nm_i->nid_list[FREE_NID_LIST], + struct free_nid, list); *nid = i->nid; + + __remove_nid_from_list(sbi, i, FREE_NID_LIST, true); i->state = NID_ALLOC; - nm_i->fcnt--; - spin_unlock(&nm_i->free_nid_list_lock); + __insert_nid_to_list(sbi, i, ALLOC_NID_LIST, false); + 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; } @@ -1570,11 +2086,11 @@ void alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid) 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_nid_from_list(sbi, i, ALLOC_NID_LIST, false); + spin_unlock(&nm_i->nid_list_lock); kmem_cache_free(free_nid_slab, i); } @@ -1591,22 +2107,58 @@ void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid) 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_nid_from_list(sbi, i, ALLOC_NID_LIST, false); need_free = true; } else { + __remove_nid_from_list(sbi, i, ALLOC_NID_LIST, true); i->state = NID_NEW; - nm_i->fcnt++; + __insert_nid_to_list(sbi, i, FREE_NID_LIST, false); } - 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); } +int try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + struct free_nid *i, *next; + int nr = nr_shrink; + + if (nm_i->nid_cnt[FREE_NID_LIST] <= MAX_FREE_NIDS) + return 0; + + if (!mutex_trylock(&nm_i->build_lock)) + return 0; + + spin_lock(&nm_i->nid_list_lock); + list_for_each_entry_safe(i, next, &nm_i->nid_list[FREE_NID_LIST], + list) { + if (nr_shrink <= 0 || + nm_i->nid_cnt[FREE_NID_LIST] <= MAX_FREE_NIDS) + break; + + __remove_nid_from_list(sbi, i, FREE_NID_LIST, false); + kmem_cache_free(free_nid_slab, i); + nr_shrink--; + } + spin_unlock(&nm_i->nid_list_lock); + mutex_unlock(&nm_i->build_lock); + + return nr - nr_shrink; +} + void recover_inline_xattr(struct inode *inode, struct page *page) { void *src_addr, *dst_addr; @@ -1619,7 +2171,7 @@ void recover_inline_xattr(struct inode *inode, struct page *page) ri = F2FS_INODE(page); if (!(ri->i_inline & F2FS_INLINE_XATTR)) { - clear_inode_flag(F2FS_I(inode), FI_INLINE_XATTR); + clear_inode_flag(inode, FI_INLINE_XATTR); goto update_inode; } @@ -1627,25 +2179,25 @@ void recover_inline_xattr(struct inode *inode, struct page *page) src_addr = inline_xattr_addr(page); inline_size = inline_xattr_size(inode); - f2fs_wait_on_page_writeback(ipage, NODE); + f2fs_wait_on_page_writeback(ipage, NODE, true); memcpy(dst_addr, src_addr, inline_size); update_inode: update_inode(inode, ipage); 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, block_t blkaddr) { 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); 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); @@ -1653,21 +2205,27 @@ void recover_xattr_data(struct inode *inode, struct page *page, block_t blkaddr) set_node_addr(sbi, &ni, NULL_ADDR, false); recover_xnid: - /* 2: allocate new xattr nid */ + /* 2: update xattr nid in inode */ + remove_free_nid(sbi, new_xnid); + f2fs_i_xnid_write(inode, new_xnid); if (unlikely(!inc_valid_node_count(sbi, inode))) f2fs_bug_on(sbi, 1); + update_inode_page(inode); + + /* 3: update and set xattr node page dirty */ + xpage = grab_cache_page(NODE_MAPPING(sbi), new_xnid); + if (!xpage) + return -ENOMEM; + + memcpy(F2FS_NODE(xpage), F2FS_NODE(page), PAGE_SIZE); - 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(inode)->i_xattr_nid = new_xnid; + set_page_dirty(xpage); + f2fs_put_page(xpage, 1); - /* 3: update xattr blkaddr */ - refresh_sit_entry(sbi, NEW_ADDR, blkaddr); - set_node_addr(sbi, &ni, blkaddr, false); - - update_inode_page(inode); + return 0; } int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page) @@ -1681,15 +2239,18 @@ int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page) if (unlikely(old_ni.blk_addr != NULL_ADDR)) return -EINVAL; - - ipage = grab_cache_page(NODE_MAPPING(sbi), ino); - if (!ipage) - return -ENOMEM; +retry: + ipage = f2fs_grab_cache_page(NODE_MAPPING(sbi), ino, false); + if (!ipage) { + congestion_wait(BLK_RW_ASYNC, HZ/50); + goto retry; + } /* Should not use this inode from free nid list */ - remove_free_nid(NM_I(sbi), ino); + remove_free_nid(sbi, ino); - SetPageUptodate(ipage); + if (!PageUptodate(ipage)) + SetPageUptodate(ipage); fill_node_footer(ipage, ino, ino, 0, true); src = F2FS_INODE(page); @@ -1714,114 +2275,79 @@ int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page) return 0; } -/* - * ra_sum_pages() merge contiguous pages into one bio and submit. - * these pre-read pages are allocated in bd_inode's mapping tree. - */ -static int ra_sum_pages(struct f2fs_sb_info *sbi, struct page **pages, - int start, int nrpages) -{ - struct inode *inode = sbi->sb->s_bdev->bd_inode; - struct address_space *mapping = inode->i_mapping; - int i, page_idx = start; - struct f2fs_io_info fio = { - .type = META, - .rw = READ_SYNC | REQ_META | REQ_PRIO - }; - - for (i = 0; page_idx < start + nrpages; page_idx++, i++) { - /* alloc page in bd_inode for reading node summary info */ - pages[i] = grab_cache_page(mapping, page_idx); - if (!pages[i]) - break; - f2fs_submit_page_mbio(sbi, pages[i], page_idx, &fio); - } - - f2fs_submit_merged_bio(sbi, META, READ); - return i; -} - int 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; - struct inode *inode = sbi->sb->s_bdev->bd_inode; block_t addr; - int bio_blocks = MAX_BIO_BLOCKS(sbi); - struct page *pages[bio_blocks]; - int i, idx, last_offset, nrpages, err = 0; + int i, idx, last_offset, nrpages; /* scan the node segment */ last_offset = sbi->blocks_per_seg; addr = START_BLOCK(sbi, segno); sum_entry = &sum->entries[0]; - for (i = 0; !err && i < last_offset; i += nrpages, addr += nrpages) { - nrpages = min(last_offset - i, bio_blocks); + for (i = 0; i < last_offset; i += nrpages, addr += nrpages) { + nrpages = min(last_offset - i, BIO_MAX_PAGES); /* readahead node pages */ - nrpages = ra_sum_pages(sbi, pages, addr, nrpages); - if (!nrpages) - return -ENOMEM; - - for (idx = 0; idx < nrpages; idx++) { - if (err) - goto skip; - - lock_page(pages[idx]); - if (unlikely(!PageUptodate(pages[idx]))) { - err = -EIO; - } else { - rn = F2FS_NODE(pages[idx]); - sum_entry->nid = rn->footer.nid; - sum_entry->version = 0; - sum_entry->ofs_in_node = 0; - sum_entry++; - } - unlock_page(pages[idx]); -skip: - page_cache_release(pages[idx]); + ra_meta_pages(sbi, addr, nrpages, META_POR, true); + + for (idx = addr; idx < addr + nrpages; idx++) { + struct page *page = get_tmp_page(sbi, idx); + + rn = F2FS_NODE(page); + sum_entry->nid = rn->footer.nid; + sum_entry->version = 0; + sum_entry->ofs_in_node = 0; + sum_entry++; + f2fs_put_page(page, 1); } - invalidate_mapping_pages(inode->i_mapping, addr, + invalidate_mapping_pages(META_MAPPING(sbi), addr, addr + nrpages); } - return err; + return 0; } static void remove_nats_in_journal(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_summary_block *sum = curseg->sum_blk; + struct f2fs_journal *journal = curseg->journal; int i; - mutex_lock(&curseg->curseg_mutex); - for (i = 0; i < nats_in_cursum(sum); i++) { + down_write(&curseg->journal_rwsem); + for (i = 0; i < nats_in_cursum(journal); i++) { struct nat_entry *ne; struct f2fs_nat_entry raw_ne; - nid_t nid = le32_to_cpu(nid_in_journal(sum, i)); + nid_t nid = le32_to_cpu(nid_in_journal(journal, i)); - raw_ne = nat_in_journal(sum, i); -retry: - write_lock(&nm_i->nat_tree_lock); - ne = __lookup_nat_cache(nm_i, nid); - if (ne) - goto found; + raw_ne = nat_in_journal(journal, i); - ne = grab_nat_entry(nm_i, nid); + ne = __lookup_nat_cache(nm_i, nid); if (!ne) { - write_unlock(&nm_i->nat_tree_lock); - goto retry; + ne = grab_nat_entry(nm_i, nid, true); + node_info_from_raw_nat(&ne->ni, &raw_ne); + } + + /* + * 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); } - node_info_from_raw_nat(&ne->ni, &raw_ne); -found: + __set_nat_cache_dirty(nm_i, ne); - write_unlock(&nm_i->nat_tree_lock); } - update_nats_in_cursum(sum, -i); - mutex_unlock(&curseg->curseg_mutex); + update_nats_in_cursum(journal, -i); + up_write(&curseg->journal_rwsem); } static void __adjust_nat_entry_set(struct nat_entry_set *nes, @@ -1842,11 +2368,42 @@ 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; + + if (!enabled_nat_bits(sbi, NULL)) + return; + + for (i = 0; i < NAT_ENTRY_PER_BLOCK; i++) { + if (start_nid == 0 && i == 0) + valid++; + if (nat_blk->entries[i].block_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_summary_block *sum = curseg->sum_blk; + struct f2fs_journal *journal = curseg->journal; nid_t start_nid = set->set * NAT_ENTRY_PER_BLOCK; bool to_journal = true; struct f2fs_nat_block *nat_blk; @@ -1858,11 +2415,12 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi, * #1, flush nat entries to journal in current hot data summary block. * #2, flush nat entries to nat page. */ - if (!__has_cursum_space(sum, 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) { - mutex_lock(&curseg->curseg_mutex); + down_write(&curseg->journal_rwsem); } else { page = get_next_nat_page(sbi, start_nid); nat_blk = page_address(page); @@ -1879,30 +2437,38 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi, continue; if (to_journal) { - offset = lookup_journal_in_cursum(sum, + offset = lookup_journal_in_cursum(journal, NAT_JOURNAL, nid, 1); f2fs_bug_on(sbi, offset < 0); - raw_ne = &nat_in_journal(sum, offset); - nid_in_journal(sum, offset) = cpu_to_le32(nid); + raw_ne = &nat_in_journal(journal, offset); + nid_in_journal(journal, offset) = cpu_to_le32(nid); } else { raw_ne = &nat_blk->entries[nid - start_nid]; } raw_nat_from_node_info(raw_ne, &ne->ni); - - write_lock(&NM_I(sbi)->nat_tree_lock); nat_reset_flag(ne); - __clear_nat_cache_dirty(NM_I(sbi), ne); - write_unlock(&NM_I(sbi)->nat_tree_lock); - - if (nat_get_blkaddr(ne) == NULL_ADDR) + __clear_nat_cache_dirty(NM_I(sbi), set, ne); + if (nat_get_blkaddr(ne) == NULL_ADDR) { add_free_nid(sbi, nid, false); + spin_lock(&NM_I(sbi)->nid_list_lock); + NM_I(sbi)->available_nids++; + update_free_nid_bitmap(sbi, nid, true, false); + spin_unlock(&NM_I(sbi)->nid_list_lock); + } 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) - mutex_unlock(&curseg->curseg_mutex); - else + if (to_journal) { + up_write(&curseg->journal_rwsem); + } else { + __update_nat_bits(sbi, start_nid, page); f2fs_put_page(page, 1); + } + /* 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); @@ -1912,42 +2478,122 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi, /* * 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); - struct f2fs_summary_block *sum = curseg->sum_blk; - struct nat_entry_set *setvec[NATVEC_SIZE]; + struct f2fs_journal *journal = curseg->journal; + struct nat_entry_set *setvec[SETVEC_SIZE]; struct nat_entry_set *set, *tmp; unsigned int found; nid_t set_idx = 0; LIST_HEAD(sets); + if (!nm_i->dirty_nat_cnt) + return; + + down_write(&nm_i->nat_tree_lock); + /* * if there are no enough space in journal to store dirty nat * entries, remove all entries from journal and merge them * into nat entry set. */ - if (!__has_cursum_space(sum, 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); - if (!nm_i->dirty_nat_cnt) - return; - while ((found = __gang_lookup_nat_set(nm_i, - set_idx, NATVEC_SIZE, setvec))) { + set_idx, SETVEC_SIZE, setvec))) { unsigned idx; set_idx = setvec[found - 1]->set + 1; for (idx = 0; idx < found; idx++) __adjust_nat_entry_set(setvec[idx], &sets, - MAX_NAT_JENTRIES(sum)); + MAX_NAT_JENTRIES(journal)); } /* 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 */ +} + +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_BYTES_TO_BLK((nat_bits_bytes << 1) + 8 + + F2FS_BLKSIZE - 1); + nm_i->nat_bits = kzalloc(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; +} + +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; - f2fs_bug_on(sbi, nm_i->dirty_nat_cnt); + 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 = (i + 1) * 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) @@ -1955,31 +2601,36 @@ static int init_node_manager(struct f2fs_sb_info *sbi) 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 - + F2FS_RESERVED_NODE_NUM; + nm_i->nid_cnt[FREE_NID_LIST] = 0; + nm_i->nid_cnt[ALLOC_NID_LIST] = 0; nm_i->nat_cnt = 0; nm_i->ram_thresh = DEF_RAM_THRESHOLD; + nm_i->ra_nid_pages = DEF_RA_NID_PAGES; + nm_i->dirty_nats_ratio = DEF_DIRTY_NAT_RATIO_THRESHOLD; INIT_RADIX_TREE(&nm_i->free_nid_root, GFP_ATOMIC); - INIT_LIST_HEAD(&nm_i->free_nid_list); - INIT_RADIX_TREE(&nm_i->nat_root, GFP_ATOMIC); - INIT_RADIX_TREE(&nm_i->nat_set_root, GFP_ATOMIC); + INIT_LIST_HEAD(&nm_i->nid_list[FREE_NID_LIST]); + INIT_LIST_HEAD(&nm_i->nid_list[ALLOC_NID_LIST]); + INIT_RADIX_TREE(&nm_i->nat_root, GFP_NOIO); + INIT_RADIX_TREE(&nm_i->nat_set_root, GFP_NOIO); INIT_LIST_HEAD(&nm_i->nat_entries); mutex_init(&nm_i->build_lock); - spin_lock_init(&nm_i->free_nid_list_lock); - rwlock_init(&nm_i->nat_tree_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); nm_i->bitmap_size = __bitmap_size(sbi, NAT_BITMAP); @@ -1991,6 +2642,39 @@ static int init_node_manager(struct f2fs_sb_info *sbi) 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); + + nm_i->free_nid_bitmap = f2fs_kvzalloc(nm_i->nat_blocks * + NAT_ENTRY_BITMAP_SIZE, GFP_KERNEL); + if (!nm_i->free_nid_bitmap) + return -ENOMEM; + + nm_i->nat_block_bitmap = f2fs_kvzalloc(nm_i->nat_blocks / 8, + GFP_KERNEL); + if (!nm_i->nat_block_bitmap) + return -ENOMEM; + + nm_i->free_nid_count = f2fs_kvzalloc(nm_i->nat_blocks * + sizeof(unsigned short), GFP_KERNEL); + if (!nm_i->free_nid_count) + return -ENOMEM; return 0; } @@ -2006,7 +2690,14 @@ int build_node_manager(struct f2fs_sb_info *sbi) 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; } @@ -2015,6 +2706,7 @@ void destroy_node_manager(struct f2fs_sb_info *sbi) struct f2fs_nm_info *nm_i = NM_I(sbi); struct free_nid *i, *next_i; struct nat_entry *natvec[NATVEC_SIZE]; + struct nat_entry_set *setvec[SETVEC_SIZE]; nid_t nid = 0; unsigned int found; @@ -2022,31 +2714,56 @@ void destroy_node_manager(struct f2fs_sb_info *sbi) return; /* destroy free nid list */ - spin_lock(&nm_i->free_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); + spin_lock(&nm_i->nid_list_lock); + list_for_each_entry_safe(i, next_i, &nm_i->nid_list[FREE_NID_LIST], + list) { + __remove_nid_from_list(sbi, i, FREE_NID_LIST, false); + 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_LIST]); + f2fs_bug_on(sbi, nm_i->nid_cnt[ALLOC_NID_LIST]); + f2fs_bug_on(sbi, !list_empty(&nm_i->nid_list[ALLOC_NID_LIST])); + spin_unlock(&nm_i->nid_list_lock); /* destroy nat cache */ - write_lock(&nm_i->nat_tree_lock); + down_write(&nm_i->nat_tree_lock); while ((found = __gang_lookup_nat_cache(nm_i, nid, NATVEC_SIZE, natvec))) { unsigned idx; + nid = nat_get_nid(natvec[found - 1]) + 1; for (idx = 0; idx < found; idx++) __del_from_nat_cache(nm_i, natvec[idx]); } f2fs_bug_on(sbi, nm_i->nat_cnt); - write_unlock(&nm_i->nat_tree_lock); + + /* destroy nat set cache */ + nid = 0; + while ((found = __gang_lookup_nat_set(nm_i, + nid, SETVEC_SIZE, setvec))) { + unsigned idx; + + nid = setvec[found - 1]->set + 1; + for (idx = 0; idx < found; idx++) { + /* entry_cnt is not zero, when cp_error was occurred */ + f2fs_bug_on(sbi, !list_empty(&setvec[idx]->entry_list)); + radix_tree_delete(&nm_i->nat_set_root, setvec[idx]->set); + kmem_cache_free(nat_entry_set_slab, setvec[idx]); + } + } + up_write(&nm_i->nat_tree_lock); + + kvfree(nm_i->nat_block_bitmap); + kvfree(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); } @@ -2061,17 +2778,17 @@ int __init create_node_manager_caches(void) free_nid_slab = f2fs_kmem_cache_create("free_nid", sizeof(struct free_nid)); if (!free_nid_slab) - goto destory_nat_entry; + goto destroy_nat_entry; nat_entry_set_slab = f2fs_kmem_cache_create("nat_entry_set", sizeof(struct nat_entry_set)); if (!nat_entry_set_slab) - goto destory_free_nid; + goto destroy_free_nid; return 0; -destory_free_nid: +destroy_free_nid: kmem_cache_destroy(free_nid_slab); -destory_nat_entry: +destroy_nat_entry: kmem_cache_destroy(nat_entry_slab); fail: return -ENOMEM; |