diff options
Diffstat (limited to 'fs/f2fs/node.c')
-rw-r--r-- | fs/f2fs/node.c | 1384 |
1 files changed, 882 insertions, 502 deletions
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index e7b8e2b35e22..494947d282d5 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/node.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/f2fs_fs.h> @@ -23,28 +20,28 @@ #include "trace.h" #include <trace/events/f2fs.h> -#define on_build_free_nids(nmi) mutex_is_locked(&(nm_i)->build_lock) +#define on_f2fs_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; static struct kmem_cache *nat_entry_set_slab; +static struct kmem_cache *fsync_node_entry_slab; /* * Check whether the given nid is within node id range. */ -int check_nid_range(struct f2fs_sb_info *sbi, nid_t nid) +int f2fs_check_nid_range(struct f2fs_sb_info *sbi, nid_t nid) { if (unlikely(nid < F2FS_ROOT_INO(sbi) || nid >= NM_I(sbi)->max_nid)) { set_sbi_flag(sbi, SBI_NEED_FSCK); - f2fs_msg(sbi->sb, KERN_WARNING, - "%s: out-of-range nid=%x, run fsck to fix.", - __func__, nid); + f2fs_warn(sbi, "%s: out-of-range nid=%x, run fsck to fix.", + __func__, nid); return -EFSCORRUPTED; } return 0; } -bool available_free_memory(struct f2fs_sb_info *sbi, int type) +bool f2fs_available_free_memory(struct f2fs_sb_info *sbi, int type) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct sysinfo val; @@ -61,7 +58,7 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type) * give 25%, 25%, 50%, 50%, 50% memory for each components respectively */ if (type == FREE_NIDS) { - mem_size = (nm_i->nid_cnt[FREE_NID_LIST] * + 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) { @@ -78,7 +75,7 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type) } else if (type == INO_ENTRIES) { int i; - for (i = 0; i <= UPDATE_INO; i++) + for (i = 0; i < MAX_INO_ENTRY; i++) mem_size += sbi->im[i].ino_num * sizeof(struct ino_entry); mem_size >>= PAGE_SHIFT; @@ -89,6 +86,10 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type) 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; @@ -98,44 +99,35 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type) static void clear_node_page_dirty(struct page *page) { - struct address_space *mapping = page->mapping; - unsigned int long flags; - if (PageDirty(page)) { - spin_lock_irqsave(&mapping->tree_lock, flags); - radix_tree_tag_clear(&mapping->page_tree, - page_index(page), - PAGECACHE_TAG_DIRTY); - spin_unlock_irqrestore(&mapping->tree_lock, flags); - + f2fs_clear_radix_tree_dirty_tag(page); clear_page_dirty_for_io(page); - dec_page_count(F2FS_M_SB(mapping), F2FS_DIRTY_NODES); + dec_page_count(F2FS_P_SB(page), F2FS_DIRTY_NODES); } ClearPageUptodate(page); } static struct page *get_current_nat_page(struct f2fs_sb_info *sbi, nid_t nid) { - pgoff_t index = current_nat_addr(sbi, nid); - return get_meta_page(sbi, index); + return f2fs_get_meta_page_nofail(sbi, current_nat_addr(sbi, nid)); } static struct page *get_next_nat_page(struct f2fs_sb_info *sbi, nid_t nid) { struct page *src_page; struct page *dst_page; - pgoff_t src_off; pgoff_t dst_off; void *src_addr; void *dst_addr; struct f2fs_nm_info *nm_i = NM_I(sbi); - src_off = current_nat_addr(sbi, nid); - dst_off = next_nat_addr(sbi, src_off); + dst_off = next_nat_addr(sbi, current_nat_addr(sbi, nid)); /* get current nat block page with lock */ - src_page = get_meta_page(sbi, src_off); - dst_page = grab_meta_page(sbi, dst_off); + src_page = get_current_nat_page(sbi, nid); + if (IS_ERR(src_page)) + return src_page; + dst_page = f2fs_grab_meta_page(sbi, dst_off); f2fs_bug_on(sbi, PageDirty(src_page)); src_addr = page_address(src_page); @@ -149,9 +141,61 @@ static struct page *get_next_nat_page(struct f2fs_sb_info *sbi, nid_t nid) 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); + + spin_lock(&nm_i->nat_list_lock); + list_add_tail(&ne->list, &nm_i->nat_entries); + spin_unlock(&nm_i->nat_list_lock); + + 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); + struct nat_entry *ne; + + ne = radix_tree_lookup(&nm_i->nat_root, n); + + /* for recent accessed nat entry, move it to tail of lru list */ + if (ne && !get_nat_flag(ne, IS_DIRTY)) { + spin_lock(&nm_i->nat_list_lock); + if (!list_empty(&ne->list)) + list_move_tail(&ne->list, &nm_i->nat_entries); + spin_unlock(&nm_i->nat_list_lock); + } + + return ne; } static unsigned int __gang_lookup_nat_cache(struct f2fs_nm_info *nm_i, @@ -162,14 +206,13 @@ static unsigned int __gang_lookup_nat_cache(struct f2fs_nm_info *nm_i, static void __del_from_nat_cache(struct f2fs_nm_info *nm_i, struct nat_entry *e) { - 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; @@ -184,24 +227,50 @@ static void __set_nat_cache_dirty(struct f2fs_nm_info *nm_i, head->entry_cnt = 0; f2fs_radix_tree_insert(&nm_i->nat_set_root, set, head); } + return head; +} + +static void __set_nat_cache_dirty(struct f2fs_nm_info *nm_i, + struct nat_entry *ne) +{ + struct nat_entry_set *head; + bool new_ne = nat_get_blkaddr(ne) == NEW_ADDR; + + 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++; - head->entry_cnt++; set_nat_flag(ne, IS_DIRTY, true); refresh_list: - if (nat_get_blkaddr(ne) == NEW_ADDR) + spin_lock(&nm_i->nat_list_lock); + if (new_ne) list_del_init(&ne->list); else list_move_tail(&ne->list, &head->entry_list); + spin_unlock(&nm_i->nat_list_lock); } static void __clear_nat_cache_dirty(struct f2fs_nm_info *nm_i, struct nat_entry_set *set, struct nat_entry *ne) { + spin_lock(&nm_i->nat_list_lock); list_move_tail(&ne->list, &nm_i->nat_entries); + spin_unlock(&nm_i->nat_list_lock); + set_nat_flag(ne, IS_DIRTY, false); set->entry_cnt--; nm_i->dirty_nat_cnt--; @@ -214,7 +283,73 @@ static unsigned int __gang_lookup_nat_set(struct f2fs_nm_info *nm_i, start, nr); } -int need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid) +bool f2fs_in_warm_node_list(struct f2fs_sb_info *sbi, struct page *page) +{ + return NODE_MAPPING(sbi) == page->mapping && + IS_DNODE(page) && is_cold_node(page); +} + +void f2fs_init_fsync_node_info(struct f2fs_sb_info *sbi) +{ + spin_lock_init(&sbi->fsync_node_lock); + INIT_LIST_HEAD(&sbi->fsync_node_list); + sbi->fsync_seg_id = 0; + sbi->fsync_node_num = 0; +} + +static unsigned int f2fs_add_fsync_node_entry(struct f2fs_sb_info *sbi, + struct page *page) +{ + struct fsync_node_entry *fn; + unsigned long flags; + unsigned int seq_id; + + fn = f2fs_kmem_cache_alloc(fsync_node_entry_slab, GFP_NOFS); + + get_page(page); + fn->page = page; + INIT_LIST_HEAD(&fn->list); + + spin_lock_irqsave(&sbi->fsync_node_lock, flags); + list_add_tail(&fn->list, &sbi->fsync_node_list); + fn->seq_id = sbi->fsync_seg_id++; + seq_id = fn->seq_id; + sbi->fsync_node_num++; + spin_unlock_irqrestore(&sbi->fsync_node_lock, flags); + + return seq_id; +} + +void f2fs_del_fsync_node_entry(struct f2fs_sb_info *sbi, struct page *page) +{ + struct fsync_node_entry *fn; + unsigned long flags; + + spin_lock_irqsave(&sbi->fsync_node_lock, flags); + list_for_each_entry(fn, &sbi->fsync_node_list, list) { + if (fn->page == page) { + list_del(&fn->list); + sbi->fsync_node_num--; + spin_unlock_irqrestore(&sbi->fsync_node_lock, flags); + kmem_cache_free(fsync_node_entry_slab, fn); + put_page(page); + return; + } + } + spin_unlock_irqrestore(&sbi->fsync_node_lock, flags); + f2fs_bug_on(sbi, 1); +} + +void f2fs_reset_fsync_node_info(struct f2fs_sb_info *sbi) +{ + unsigned long flags; + + spin_lock_irqsave(&sbi->fsync_node_lock, flags); + sbi->fsync_seg_id = 0; + spin_unlock_irqrestore(&sbi->fsync_node_lock, flags); +} + +int f2fs_need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct nat_entry *e; @@ -231,7 +366,7 @@ int need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid) return need; } -bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid) +bool f2fs_is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct nat_entry *e; @@ -245,7 +380,7 @@ bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid) return is_cp; } -bool need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino) +bool f2fs_need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct nat_entry *e; @@ -261,49 +396,29 @@ bool need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino) return need_update; } -static struct nat_entry *grab_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid, - bool no_fail) -{ - struct nat_entry *new; - - 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); - 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, false); - if (e) - node_info_from_raw_nat(&e->ni, ne); - } else { + 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, @@ -311,11 +426,12 @@ 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; + 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, true); + 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) { @@ -327,6 +443,9 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, 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); @@ -334,22 +453,18 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, new_blkaddr == NULL_ADDR); f2fs_bug_on(sbi, nat_get_blkaddr(e) == NEW_ADDR && new_blkaddr == NEW_ADDR); - f2fs_bug_on(sbi, is_valid_data_blkaddr(sbi, nat_get_blkaddr(e)) && + f2fs_bug_on(sbi, __is_valid_data_blkaddr(nat_get_blkaddr(e)) && new_blkaddr == NEW_ADDR); /* increment version no as node is removed */ 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 */ nat_set_blkaddr(e, new_blkaddr); - if (!is_valid_data_blkaddr(sbi, new_blkaddr)) + if (!__is_valid_data_blkaddr(new_blkaddr)) set_nat_flag(e, IS_CHECKPOINTED, false); __set_nat_cache_dirty(nm_i, e); @@ -364,7 +479,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, up_write(&nm_i->nat_tree_lock); } -int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink) +int f2fs_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; @@ -372,13 +487,25 @@ int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink) if (!down_write_trylock(&nm_i->nat_tree_lock)) return 0; - while (nr_shrink && !list_empty(&nm_i->nat_entries)) { + spin_lock(&nm_i->nat_list_lock); + while (nr_shrink) { struct nat_entry *ne; + + if (list_empty(&nm_i->nat_entries)) + break; + ne = list_first_entry(&nm_i->nat_entries, struct nat_entry, list); + list_del(&ne->list); + spin_unlock(&nm_i->nat_list_lock); + __del_from_nat_cache(nm_i, ne); nr_shrink--; + + spin_lock(&nm_i->nat_list_lock); } + spin_unlock(&nm_i->nat_list_lock); + up_write(&nm_i->nat_tree_lock); return nr - nr_shrink; } @@ -386,7 +513,8 @@ int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink) /* * This function always returns success */ -void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni) +int f2fs_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); @@ -397,6 +525,7 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni) struct f2fs_nat_entry ne; struct nat_entry *e; pgoff_t index; + block_t blkaddr; int i; ni->nid = nid; @@ -409,14 +538,14 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni) ni->blk_addr = nat_get_blkaddr(e); ni->version = nat_get_version(e); up_read(&nm_i->nat_tree_lock); - return; + return 0; } memset(&ne, 0, sizeof(struct f2fs_nat_entry)); /* Check current segment summary */ down_read(&curseg->journal_rwsem); - i = lookup_journal_in_cursum(journal, NAT_JOURNAL, nid, 0); + i = f2fs_lookup_journal_in_cursum(journal, NAT_JOURNAL, nid, 0); if (i >= 0) { ne = nat_in_journal(journal, i); node_info_from_raw_nat(ni, &ne); @@ -431,22 +560,29 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni) index = current_nat_addr(sbi, nid); up_read(&nm_i->nat_tree_lock); - page = get_meta_page(sbi, index); + page = f2fs_get_meta_page(sbi, index); + if (IS_ERR(page)) + return PTR_ERR(page); + 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: + blkaddr = le32_to_cpu(ne.block_addr); + if (__is_valid_data_blkaddr(blkaddr) && + !f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE)) + return -EFAULT; + /* cache nat entry */ - down_write(&nm_i->nat_tree_lock); cache_nat_entry(sbi, nid, &ne); - up_write(&nm_i->nat_tree_lock); + return 0; } /* * readahead MAX_RA_NODE number of node pages. */ -static void ra_node_pages(struct page *parent, int start, int n) +static void f2fs_ra_node_pages(struct page *parent, int start, int n) { struct f2fs_sb_info *sbi = F2FS_P_SB(parent); struct blk_plug plug; @@ -460,18 +596,18 @@ static void ra_node_pages(struct page *parent, int start, int n) end = min(end, NIDS_PER_BLOCK); for (i = start; i < end; i++) { nid = get_nid(parent, i, false); - ra_node_page(sbi, nid); + f2fs_ra_node_page(sbi, nid); } blk_finish_plug(&plug); } -pgoff_t get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs) +pgoff_t f2fs_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; + const long direct_blks = ADDRS_PER_BLOCK(dn->inode); + const long indirect_blks = ADDRS_PER_BLOCK(dn->inode) * NIDS_PER_BLOCK; + unsigned int skipped_unit = ADDRS_PER_BLOCK(dn->inode); int cur_level = dn->cur_level; int max_level = dn->max_level; pgoff_t base = 0; @@ -505,9 +641,9 @@ static int get_node_path(struct inode *inode, long block, int offset[4], unsigned int noffset[4]) { const long direct_index = ADDRS_PER_INODE(inode); - const long direct_blks = ADDRS_PER_BLOCK; + const long direct_blks = ADDRS_PER_BLOCK(inode); const long dptrs_per_blk = NIDS_PER_BLOCK; - const long indirect_blks = ADDRS_PER_BLOCK * NIDS_PER_BLOCK; + const long indirect_blks = ADDRS_PER_BLOCK(inode) * NIDS_PER_BLOCK; const long dindirect_blks = indirect_blks * NIDS_PER_BLOCK; int n = 0; int level = 0; @@ -581,7 +717,7 @@ got: * f2fs_unlock_op() only if ro is not set RDONLY_NODE. * In the case of RDONLY_NODE, we don't need to care about mutex. */ -int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode) +int f2fs_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]; @@ -600,7 +736,7 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode) npage[0] = dn->inode_page; if (!npage[0]) { - npage[0] = get_node_page(sbi, nids[0]); + npage[0] = f2fs_get_node_page(sbi, nids[0]); if (IS_ERR(npage[0])) return PTR_ERR(npage[0]); } @@ -624,24 +760,24 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode) if (!nids[i] && mode == ALLOC_NODE) { /* alloc new node */ - if (!alloc_nid(sbi, &(nids[i]))) { + if (!f2fs_alloc_nid(sbi, &(nids[i]))) { err = -ENOSPC; goto release_pages; } dn->nid = nids[i]; - npage[i] = new_node_page(dn, noffset[i]); + npage[i] = f2fs_new_node_page(dn, noffset[i]); if (IS_ERR(npage[i])) { - alloc_nid_failed(sbi, nids[i]); + f2fs_alloc_nid_failed(sbi, nids[i]); err = PTR_ERR(npage[i]); goto release_pages; } set_nid(parent, offset[i - 1], nids[i], i == 1); - alloc_nid_done(sbi, nids[i]); + f2fs_alloc_nid_done(sbi, nids[i]); done = true; } else if (mode == LOOKUP_NODE_RA && i == level && level > 1) { - npage[i] = get_node_page_ra(parent, offset[i - 1]); + npage[i] = f2fs_get_node_page_ra(parent, offset[i - 1]); if (IS_ERR(npage[i])) { err = PTR_ERR(npage[i]); goto release_pages; @@ -656,7 +792,7 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode) } if (!done) { - npage[i] = get_node_page(sbi, nids[i]); + npage[i] = f2fs_get_node_page(sbi, nids[i]); if (IS_ERR(npage[i])) { err = PTR_ERR(npage[i]); f2fs_put_page(npage[0], 0); @@ -690,22 +826,24 @@ release_out: return err; } -static void truncate_node(struct dnode_of_data *dn) +static int truncate_node(struct dnode_of_data *dn) { struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); struct node_info ni; + int err; pgoff_t index; - get_node_info(sbi, dn->nid, &ni); - f2fs_bug_on(sbi, ni.blk_addr == NULL_ADDR); + err = f2fs_get_node_info(sbi, dn->nid, &ni); + if (err) + return err; /* Deallocate node address */ - invalidate_blocks(sbi, ni.blk_addr); + f2fs_invalidate_blocks(sbi, ni.blk_addr); 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) { - remove_orphan_inode(sbi, dn->nid); + f2fs_remove_orphan_inode(sbi, dn->nid); dec_valid_inode_count(sbi); f2fs_inode_synced(dn->inode); } @@ -721,17 +859,20 @@ static void truncate_node(struct dnode_of_data *dn) dn->node_page = NULL; trace_f2fs_truncate_node(dn->inode, dn->nid, ni.blk_addr); + + return 0; } static int truncate_dnode(struct dnode_of_data *dn) { struct page *page; + int err; if (dn->nid == 0) return 1; /* get direct node */ - page = get_node_page(F2FS_I_SB(dn->inode), dn->nid); + page = f2fs_get_node_page(F2FS_I_SB(dn->inode), dn->nid); if (IS_ERR(page) && PTR_ERR(page) == -ENOENT) return 1; else if (IS_ERR(page)) @@ -740,8 +881,11 @@ static int truncate_dnode(struct dnode_of_data *dn) /* Make dnode_of_data for parameter */ dn->node_page = page; dn->ofs_in_node = 0; - truncate_data_blocks(dn); - truncate_node(dn); + f2fs_truncate_data_blocks(dn); + err = truncate_node(dn); + if (err) + return err; + return 1; } @@ -761,13 +905,13 @@ static int truncate_nodes(struct dnode_of_data *dn, unsigned int nofs, trace_f2fs_truncate_nodes_enter(dn->inode, dn->nid, dn->data_blkaddr); - page = get_node_page(F2FS_I_SB(dn->inode), dn->nid); + page = f2fs_get_node_page(F2FS_I_SB(dn->inode), dn->nid); if (IS_ERR(page)) { trace_f2fs_truncate_nodes_exit(dn->inode, PTR_ERR(page)); return PTR_ERR(page); } - ra_node_pages(page, ofs, NIDS_PER_BLOCK); + f2fs_ra_node_pages(page, ofs, NIDS_PER_BLOCK); rn = F2FS_NODE(page); if (depth < 3) { @@ -806,7 +950,9 @@ static int truncate_nodes(struct dnode_of_data *dn, unsigned int nofs, if (!ofs) { /* remove current indirect node */ dn->node_page = page; - truncate_node(dn); + ret = truncate_node(dn); + if (ret) + goto out_err; freed++; } else { f2fs_put_page(page, 1); @@ -837,7 +983,7 @@ static int truncate_partial_nodes(struct dnode_of_data *dn, /* get indirect nodes in the path */ for (i = 0; i < idx + 1; i++) { /* reference count'll be increased */ - pages[i] = get_node_page(F2FS_I_SB(dn->inode), nid[i]); + pages[i] = f2fs_get_node_page(F2FS_I_SB(dn->inode), nid[i]); if (IS_ERR(pages[i])) { err = PTR_ERR(pages[i]); idx = i - 1; @@ -846,7 +992,7 @@ 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); + f2fs_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++) { @@ -864,7 +1010,9 @@ static int truncate_partial_nodes(struct dnode_of_data *dn, if (offset[idx + 1] == 0) { dn->node_page = pages[idx]; dn->nid = nid[idx]; - truncate_node(dn); + err = truncate_node(dn); + if (err) + goto fail; } else { f2fs_put_page(pages[idx], 1); } @@ -883,7 +1031,7 @@ fail: /* * All the block addresses of data and nodes should be nullified. */ -int truncate_inode_blocks(struct inode *inode, pgoff_t from) +int f2fs_truncate_inode_blocks(struct inode *inode, pgoff_t from) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); int err = 0, cont = 1; @@ -899,7 +1047,7 @@ int truncate_inode_blocks(struct inode *inode, pgoff_t from) if (level < 0) return level; - page = get_node_page(sbi, inode->i_ino); + page = f2fs_get_node_page(sbi, inode->i_ino); if (IS_ERR(page)) { trace_f2fs_truncate_inode_blocks_exit(inode, PTR_ERR(page)); return PTR_ERR(page); @@ -963,7 +1111,7 @@ skip_partial: ri->i_nid[offset[0] - NODE_DIR1_BLOCK]) { lock_page(page); BUG_ON(page->mapping != NODE_MAPPING(sbi)); - f2fs_wait_on_page_writeback(page, NODE, true); + f2fs_wait_on_page_writeback(page, NODE, true, true); ri->i_nid[offset[0] - NODE_DIR1_BLOCK] = 0; set_page_dirty(page); unlock_page(page); @@ -978,27 +1126,31 @@ fail: return err > 0 ? 0 : err; } -int truncate_xattr_node(struct inode *inode, struct page *page) +/* caller must lock inode page */ +int f2fs_truncate_xattr_node(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); nid_t nid = F2FS_I(inode)->i_xattr_nid; struct dnode_of_data dn; struct page *npage; + int err; if (!nid) return 0; - npage = get_node_page(sbi, nid); + npage = f2fs_get_node_page(sbi, nid); if (IS_ERR(npage)) return PTR_ERR(npage); - f2fs_i_xnid_write(inode, 0); + set_new_dnode(&dn, inode, NULL, npage, nid); + err = truncate_node(&dn); + if (err) { + f2fs_put_page(npage, 1); + return err; + } - set_new_dnode(&dn, inode, page, npage, nid); + f2fs_i_xnid_write(inode, 0); - if (page) - dn.inode_page_locked = true; - truncate_node(&dn); return 0; } @@ -1006,17 +1158,17 @@ 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(). */ -int remove_inode_page(struct inode *inode) +int f2fs_remove_inode_page(struct inode *inode) { struct dnode_of_data dn; int err; set_new_dnode(&dn, inode, NULL, NULL, inode->i_ino); - err = get_dnode_of_data(&dn, 0, LOOKUP_NODE); + err = f2fs_get_dnode_of_data(&dn, 0, LOOKUP_NODE); if (err) return err; - err = truncate_xattr_node(inode, dn.inode_page); + err = f2fs_truncate_xattr_node(inode); if (err) { f2fs_put_dnode(&dn); return err; @@ -1025,18 +1177,30 @@ int remove_inode_page(struct inode *inode) /* remove potential inline_data blocks */ if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) - truncate_data_blocks_range(&dn, 1); + f2fs_truncate_data_blocks_range(&dn, 1); /* 0 is possible, after f2fs_new_inode() has failed */ - f2fs_bug_on(F2FS_I_SB(inode), - inode->i_blocks != 0 && inode->i_blocks != 8); + if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) { + f2fs_put_dnode(&dn); + return -EIO; + } + + if (unlikely(inode->i_blocks != 0 && inode->i_blocks != 8)) { + f2fs_warn(F2FS_I_SB(inode), "Inconsistent i_blocks, ino:%lu, iblocks:%llu", + inode->i_ino, (unsigned long long)inode->i_blocks); + set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK); + } /* will put inode & node pages */ - truncate_node(&dn); + err = truncate_node(&dn); + if (err) { + f2fs_put_dnode(&dn); + return err; + } return 0; } -struct page *new_inode_page(struct inode *inode) +struct page *f2fs_new_inode_page(struct inode *inode) { struct dnode_of_data dn; @@ -1044,10 +1208,10 @@ struct page *new_inode_page(struct inode *inode) set_new_dnode(&dn, inode, NULL, NULL, inode->i_ino); /* caller should f2fs_put_page(page, 1); */ - return new_node_page(&dn, 0); + return f2fs_new_node_page(&dn, 0); } -struct page *new_node_page(struct dnode_of_data *dn, unsigned int ofs) +struct page *f2fs_new_node_page(struct dnode_of_data *dn, unsigned int ofs) { struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); struct node_info new_ni; @@ -1065,7 +1229,11 @@ struct page *new_node_page(struct dnode_of_data *dn, unsigned int ofs) goto fail; #ifdef CONFIG_F2FS_CHECK_FS - get_node_info(sbi, dn->nid, &new_ni); + err = f2fs_get_node_info(sbi, dn->nid, &new_ni); + if (err) { + dec_valid_node_count(sbi, dn->inode, !ofs); + goto fail; + } f2fs_bug_on(sbi, new_ni.blk_addr != NULL_ADDR); #endif new_ni.nid = dn->nid; @@ -1075,9 +1243,9 @@ struct page *new_node_page(struct dnode_of_data *dn, unsigned int ofs) new_ni.version = 0; set_node_addr(sbi, &new_ni, NEW_ADDR, false); - f2fs_wait_on_page_writeback(page, NODE, true); + f2fs_wait_on_page_writeback(page, NODE, true, 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)) @@ -1113,13 +1281,22 @@ static int read_node_page(struct page *page, int op_flags) .page = page, .encrypted_page = NULL, }; + int err; - if (PageUptodate(page)) + if (PageUptodate(page)) { + if (!f2fs_inode_chksum_verify(sbi, page)) { + ClearPageUptodate(page); + return -EFSBADCRC; + } return LOCKED_PAGE; + } - get_node_info(sbi, page->index, &ni); + err = f2fs_get_node_info(sbi, page->index, &ni); + if (err) + return err; - if (unlikely(ni.blk_addr == NULL_ADDR)) { + if (unlikely(ni.blk_addr == NULL_ADDR) || + is_sbi_flag_set(sbi, SBI_IS_SHUTDOWN)) { ClearPageUptodate(page); return -ENOENT; } @@ -1131,14 +1308,14 @@ static int read_node_page(struct page *page, int op_flags) /* * Readahead a node page */ -void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid) +void f2fs_ra_node_page(struct f2fs_sb_info *sbi, nid_t nid) { struct page *apage; int err; if (!nid) return; - if (check_nid_range(sbi, nid)) + if (f2fs_check_nid_range(sbi, nid)) return; rcu_read_lock(); @@ -1163,7 +1340,7 @@ static struct page *__get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid, if (!nid) return ERR_PTR(-ENOENT); - if (check_nid_range(sbi, nid)) + if (f2fs_check_nid_range(sbi, nid)) return ERR_PTR(-EINVAL); repeat: page = f2fs_grab_cache_page(NODE_MAPPING(sbi), nid, false); @@ -1180,7 +1357,7 @@ repeat: } if (parent) - ra_node_pages(parent, start + 1, MAX_RA_NODE); + f2fs_ra_node_pages(parent, start + 1, MAX_RA_NODE); lock_page(page); @@ -1200,11 +1377,10 @@ repeat: } page_hit: if(unlikely(nid != nid_of_node(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)); + f2fs_warn(sbi, "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); @@ -1214,12 +1390,12 @@ out_err: return page; } -struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid) +struct page *f2fs_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 page *f2fs_get_node_page_ra(struct page *parent, int start) { struct f2fs_sb_info *sbi = F2FS_P_SB(parent); nid_t nid = get_nid(parent, start, false); @@ -1238,7 +1414,8 @@ static void flush_inline_data(struct f2fs_sb_info *sbi, nid_t ino) 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; @@ -1253,7 +1430,7 @@ static void flush_inline_data(struct f2fs_sb_info *sbi, nid_t ino) ret = f2fs_write_inline_data(inode, page); inode_dec_dirty_pages(inode); - remove_dirty_inode(inode); + f2fs_remove_dirty_inode(inode); if (ret) set_page_dirty(page); page_out: @@ -1262,54 +1439,19 @@ 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; + pgoff_t index; struct pagevec pvec; struct page *last_page = NULL; + int nr_pages; 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; + + while ((nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index, + PAGECACHE_TAG_DIRTY))) { + int i; for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; @@ -1355,13 +1497,14 @@ continue_unlock: static int __write_node_page(struct page *page, bool atomic, bool *submitted, struct writeback_control *wbc, bool do_balance, - enum iostat_type io_type) + enum iostat_type io_type, unsigned int *seq_id) { 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), @@ -1369,19 +1512,30 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted, .encrypted_page = NULL, .submitted = false, .io_type = io_type, + .io_wbc = wbc, }; + unsigned int seq; trace_f2fs_writepage(page, NODE); + if (unlikely(f2fs_cp_error(sbi))) + goto redirty_out; + if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) goto redirty_out; - if (unlikely(f2fs_cp_error(sbi))) + + if (!is_sbi_flag_set(sbi, SBI_CP_DISABLED) && + wbc->sync_mode == WB_SYNC_NONE && + IS_DNODE(page) && is_cold_node(page)) goto redirty_out; /* get old block addr of this node page */ nid = nid_of_node(page); f2fs_bug_on(sbi, page->index != nid); + if (f2fs_get_node_info(sbi, nid, &ni)) + goto redirty_out; + if (wbc->for_reclaim) { if (!down_read_trylock(&sbi->node_write)) goto redirty_out; @@ -1389,8 +1543,6 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted, 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); @@ -1401,7 +1553,8 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted, } if (__is_valid_data_blkaddr(ni.blk_addr) && - !f2fs_is_valid_blkaddr(sbi, ni.blk_addr, DATA_GENERIC)) { + !f2fs_is_valid_blkaddr(sbi, ni.blk_addr, + DATA_GENERIC_ENHANCE)) { up_read(&sbi->node_write); goto redirty_out; } @@ -1410,15 +1563,22 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted, fio.op_flags |= REQ_PREFLUSH | REQ_FUA; set_page_writeback(page); + ClearPageError(page); + + if (f2fs_in_warm_node_list(sbi, page)) { + seq = f2fs_add_fsync_node_entry(sbi, page); + if (seq_id) + *seq_id = seq; + } + fio.old_blkaddr = ni.blk_addr; - write_node_page(nid, &fio); + f2fs_do_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); + f2fs_submit_merged_write_cond(sbi, NULL, page, 0, NODE); submitted = NULL; } @@ -1440,22 +1600,63 @@ redirty_out: return AOP_WRITEPAGE_ACTIVATE; } +int f2fs_move_node_page(struct page *node_page, int gc_type) +{ + int err = 0; + + if (gc_type == FG_GC) { + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL, + .nr_to_write = 1, + .for_reclaim = 0, + }; + + f2fs_wait_on_page_writeback(node_page, NODE, true, true); + + set_page_dirty(node_page); + + if (!clear_page_dirty_for_io(node_page)) { + err = -EAGAIN; + goto out_page; + } + + if (__write_node_page(node_page, false, NULL, + &wbc, false, FS_GC_NODE_IO, NULL)) { + err = -EAGAIN; + 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); + return err; +} + 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); + return __write_node_page(page, false, NULL, wbc, false, + FS_NODE_IO, NULL); } -int fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode, - struct writeback_control *wbc, bool atomic) +int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode, + struct writeback_control *wbc, bool atomic, + unsigned int *seq_id) { - pgoff_t index, end; - pgoff_t last_idx = ULONG_MAX; + pgoff_t index; struct pagevec pvec; int ret = 0; struct page *last_page = NULL; bool marked = false; nid_t ino = inode->i_ino; + int nr_pages; + int nwritten = 0; if (atomic) { last_page = last_fsync_dnode(sbi, ino); @@ -1465,15 +1666,10 @@ int fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode, 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; + + while ((nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index, + PAGECACHE_TAG_DIRTY))) { + int i; for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; @@ -1506,8 +1702,7 @@ continue_unlock: goto continue_unlock; } - f2fs_wait_on_page_writeback(page, NODE, true); - BUG_ON(PageWriteback(page)); + f2fs_wait_on_page_writeback(page, NODE, true, true); set_fsync_mark(page, 0); set_dentry_mark(page, 0); @@ -1517,9 +1712,9 @@ continue_unlock: if (IS_INODE(page)) { if (is_inode_flag_set(inode, FI_DIRTY_INODE)) - update_inode(inode, page); + f2fs_update_inode(inode, page); set_dentry_mark(page, - need_dentry_mark(sbi, ino)); + f2fs_need_dentry_mark(sbi, ino)); } /* may be written by other thread */ if (!PageDirty(page)) @@ -1532,13 +1727,13 @@ continue_unlock: ret = __write_node_page(page, atomic && page == last_page, &submitted, wbc, true, - FS_NODE_IO); + FS_NODE_IO, seq_id); if (ret) { unlock_page(page); f2fs_put_page(last_page, 0); break; } else if (submitted) { - last_idx = page->index; + nwritten++; } if (page == last_page) { @@ -1554,52 +1749,91 @@ continue_unlock: break; } if (!ret && atomic && !marked) { - f2fs_msg(sbi->sb, KERN_DEBUG, - "Retry to write fsync mark: ino=%u, idx=%lx", - ino, last_page->index); + f2fs_debug(sbi, "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); + f2fs_wait_on_page_writeback(last_page, NODE, true, true); set_page_dirty(last_page); unlock_page(last_page); goto retry; } out: - if (last_idx != ULONG_MAX) - f2fs_submit_merged_write_cond(sbi, NULL, ino, last_idx, NODE); + if (nwritten) + f2fs_submit_merged_write_cond(sbi, NULL, NULL, ino, NODE); return ret ? -EIO: 0; } -int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc, +static int f2fs_match_ino(struct inode *inode, unsigned long ino, void *data) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + bool clean; + + if (inode->i_ino != ino) + return 0; + + if (!is_inode_flag_set(inode, FI_DIRTY_INODE)) + return 0; + + spin_lock(&sbi->inode_lock[DIRTY_META]); + clean = list_empty(&F2FS_I(inode)->gdirty_list); + spin_unlock(&sbi->inode_lock[DIRTY_META]); + + if (clean) + return 0; + + inode = igrab(inode); + if (!inode) + return 0; + return 1; +} + +static bool flush_dirty_inode(struct page *page) +{ + struct f2fs_sb_info *sbi = F2FS_P_SB(page); + struct inode *inode; + nid_t ino = ino_of_node(page); + + inode = find_inode_nowait(sbi->sb, ino, f2fs_match_ino, NULL); + if (!inode) + return false; + + f2fs_update_inode(inode, page); + unlock_page(page); + + iput(inode); + return true; +} + +int f2fs_sync_node_pages(struct f2fs_sb_info *sbi, + struct writeback_control *wbc, bool do_balance, enum iostat_type io_type) { - pgoff_t index, end; + pgoff_t index; struct pagevec pvec; int step = 0; int nwritten = 0; int ret = 0; + int nr_pages, done = 0; pagevec_init(&pvec, 0); next_step: 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; + + while (!done && (nr_pages = pagevec_lookup_tag(&pvec, + NODE_MAPPING(sbi), &index, PAGECACHE_TAG_DIRTY))) { + int i; for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; bool submitted = false; + bool may_dirty = true; - if (unlikely(f2fs_cp_error(sbi))) { - pagevec_release(&pvec); - ret = -EIO; - goto out; + /* give a priority to WB_SYNC threads */ + if (atomic_read(&sbi->wb_sync_req[NODE]) && + wbc->sync_mode == WB_SYNC_NONE) { + done = 1; + break; } /* @@ -1641,9 +1875,15 @@ continue_unlock: goto lock_node; } - f2fs_wait_on_page_writeback(page, NODE, true); + /* flush dirty inode */ + if (IS_INODE(page) && may_dirty) { + may_dirty = false; + if (flush_dirty_inode(page)) + goto lock_node; + } + + f2fs_wait_on_page_writeback(page, NODE, true, true); - BUG_ON(PageWriteback(page)); if (!clear_page_dirty_for_io(page)) goto continue_unlock; @@ -1651,7 +1891,7 @@ continue_unlock: set_dentry_mark(page, 0); ret = __write_node_page(page, false, &submitted, - wbc, do_balance, io_type); + wbc, do_balance, io_type, NULL); if (ret) unlock_page(page); else if (submitted) @@ -1670,51 +1910,61 @@ continue_unlock: } if (step < 2) { + if (!is_sbi_flag_set(sbi, SBI_CP_DISABLED) && + wbc->sync_mode == WB_SYNC_NONE && step == 1) + goto out; step++; goto next_step; } out: if (nwritten) f2fs_submit_merged_write(sbi, NODE); + + if (unlikely(f2fs_cp_error(sbi))) + return -EIO; return ret; } -int wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino) +int f2fs_wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, + unsigned int seq_id) { - pgoff_t index = 0, end = ULONG_MAX; - struct pagevec pvec; + struct fsync_node_entry *fn; + struct page *page; + struct list_head *head = &sbi->fsync_node_list; + unsigned long flags; + unsigned int cur_seq_id = 0; int ret2, ret = 0; - pagevec_init(&pvec, 0); - - while (index <= end) { - int i, nr_pages; - nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index, - PAGECACHE_TAG_WRITEBACK, - min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1); - if (nr_pages == 0) + while (seq_id && cur_seq_id < seq_id) { + spin_lock_irqsave(&sbi->fsync_node_lock, flags); + if (list_empty(head)) { + spin_unlock_irqrestore(&sbi->fsync_node_lock, flags); break; + } + fn = list_first_entry(head, struct fsync_node_entry, list); + if (fn->seq_id > seq_id) { + spin_unlock_irqrestore(&sbi->fsync_node_lock, flags); + break; + } + cur_seq_id = fn->seq_id; + page = fn->page; + get_page(page); + spin_unlock_irqrestore(&sbi->fsync_node_lock, flags); - for (i = 0; i < nr_pages; i++) { - struct page *page = pvec.pages[i]; + f2fs_wait_on_page_writeback(page, NODE, true, false); + if (TestClearPageError(page)) + ret = -EIO; - /* until radix tree lookup accepts end_index */ - if (unlikely(page->index > end)) - continue; + put_page(page); - if (ino && ino_of_node(page) == ino) { - f2fs_wait_on_page_writeback(page, NODE, true); - if (TestClearPageError(page)) - ret = -EIO; - } - } - pagevec_release(&pvec); - cond_resched(); + if (ret) + break; } ret2 = filemap_check_errors(NODE_MAPPING(sbi)); if (!ret) ret = ret2; + return ret; } @@ -1732,17 +1982,26 @@ static int f2fs_write_node_pages(struct address_space *mapping, f2fs_balance_fs_bg(sbi); /* collect a number of dirty node pages and write together */ - if (get_pages(sbi, F2FS_DIRTY_NODES) < nr_pages_to_skip(sbi, NODE)) + if (wbc->sync_mode != WB_SYNC_ALL && + get_pages(sbi, F2FS_DIRTY_NODES) < + nr_pages_to_skip(sbi, NODE)) + goto skip_write; + + if (wbc->sync_mode == WB_SYNC_ALL) + atomic_inc(&sbi->wb_sync_req[NODE]); + else if (atomic_read(&sbi->wb_sync_req[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; blk_start_plug(&plug); - sync_node_pages(sbi, wbc, true, FS_NODE_IO); + f2fs_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); + + if (wbc->sync_mode == WB_SYNC_ALL) + atomic_dec(&sbi->wb_sync_req[NODE]); return 0; skip_write: @@ -1757,10 +2016,14 @@ static int f2fs_set_node_page_dirty(struct page *page) if (!PageUptodate(page)) SetPageUptodate(page); +#ifdef CONFIG_F2FS_CHECK_FS + if (IS_INODE(page)) + f2fs_inode_chksum_set(F2FS_P_SB(page), page); +#endif 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_set_page_private(page, 0); f2fs_trace_pid(page); return 1; } @@ -1787,39 +2050,83 @@ 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 int __insert_nid_to_list(struct f2fs_sb_info *sbi, - struct free_nid *i, enum nid_list list, bool new) +static int __insert_free_nid(struct f2fs_sb_info *sbi, + struct free_nid *i, enum nid_state state) { 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; - } + 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]); + 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_nid_from_list(struct f2fs_sb_info *sbi, - struct free_nid *i, enum nid_list list, bool reuse) +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 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); + + 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; - 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); - if (!reuse) - radix_tree_delete(&nm_i->free_nid_root, i->nid); + 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) +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; @@ -1831,12 +2138,14 @@ static bool add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build) if (unlikely(nid == 0)) return false; + if (unlikely(f2fs_check_nid_range(sbi, nid))) + return false; + i = f2fs_kmem_cache_alloc(free_nid_slab, GFP_NOFS); i->nid = nid; - i->state = NID_NEW; + i->state = FREE_NID; - if (radix_tree_preload(GFP_NOFS)) - goto err; + radix_tree_preload(GFP_NOFS | __GFP_NOFAIL); spin_lock(&nm_i->nid_list_lock); @@ -1845,22 +2154,22 @@ static bool add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build) * Thread A Thread B * - f2fs_create * - f2fs_new_inode - * - alloc_nid - * - __insert_nid_to_list(ALLOC_NID_LIST) + * - f2fs_alloc_nid + * - __insert_nid_to_list(PREALLOC_NID) * - f2fs_balance_fs_bg - * - build_free_nids - * - __build_free_nids + * - f2fs_build_free_nids + * - __f2fs_build_free_nids * - scan_nat_page * - add_free_nid * - __lookup_nat_cache * - f2fs_add_link - * - init_inode_metadata - * - new_inode_page - * - new_node_page + * - f2fs_init_inode_metadata + * - f2fs_new_inode_page + * - f2fs_new_node_page * - set_node_addr - * - alloc_nid_done - * - __remove_nid_from_list(ALLOC_NID_LIST) - * - __insert_nid_to_list(FREE_NID_LIST) + * - f2fs_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) || @@ -1869,17 +2178,22 @@ static bool add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build) e = __lookup_free_nid_list(nm_i, nid); if (e) { - if (e->state == NID_NEW) + if (e->state == FREE_NID) ret = true; goto err_out; } } ret = true; - err = __insert_nid_to_list(sbi, i, FREE_NID_LIST, 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++; + } spin_unlock(&nm_i->nid_list_lock); radix_tree_preload_end(); -err: + if (err) kmem_cache_free(free_nid_slab, i); return ret; @@ -1893,8 +2207,8 @@ static void remove_free_nid(struct f2fs_sb_info *sbi, nid_t nid) spin_lock(&nm_i->nid_list_lock); i = __lookup_free_nid_list(nm_i, nid); - if (i && i->state == NID_NEW) { - __remove_nid_from_list(sbi, i, FREE_NID_LIST, false); + if (i && i->state == FREE_NID) { + __remove_free_nid(sbi, i, FREE_NID); need_free = true; } spin_unlock(&nm_i->nid_list_lock); @@ -1903,28 +2217,7 @@ static void remove_free_nid(struct f2fs_sb_info *sbi, nid_t nid) 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, +static int 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); @@ -1933,35 +2226,57 @@ static void scan_nat_page(struct f2fs_sb_info *sbi, 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) - 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); + + if (blk_addr == NEW_ADDR) + return -EINVAL; + + if (blk_addr == NULL_ADDR) { + 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); + } } + + return 0; } -static void scan_free_nid_bits(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); @@ -1971,72 +2286,73 @@ static void scan_free_nid_bits(struct f2fs_sb_info *sbi) 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; + 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); + add_free_nid(sbi, nid, true, false); - if (nm_i->nid_cnt[FREE_NID_LIST] >= MAX_FREE_NIDS) + if (nm_i->nid_cnt[FREE_NID] >= 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; + 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(sbi, nid); - } - up_read(&curseg->journal_rwsem); up_read(&nm_i->nat_tree_lock); } -static void __build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount) +static int __f2fs_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_journal *journal = curseg->journal; - int i = 0; + int i = 0, ret; nid_t nid = nm_i->next_scan_nid; if (unlikely(nid >= nm_i->max_nid)) nid = 0; /* Enough entries */ - if (nm_i->nid_cnt[FREE_NID_LIST] >= NAT_ENTRY_PER_BLOCK) - return; + if (nm_i->nid_cnt[FREE_NID] >= NAT_ENTRY_PER_BLOCK) + return 0; - if (!sync && !available_free_memory(sbi, FREE_NIDS)) - return; + if (!sync && !f2fs_available_free_memory(sbi, FREE_NIDS)) + return 0; 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; + if (nm_i->nid_cnt[FREE_NID] >= NAT_ENTRY_PER_BLOCK) + return 0; } /* readahead nat pages to be scanned */ - ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES, + f2fs_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); + if (!test_bit_le(NAT_BLOCK_OFFSET(nid), + nm_i->nat_block_bitmap)) { + struct page *page = get_current_nat_page(sbi, nid); + + if (IS_ERR(page)) { + ret = PTR_ERR(page); + } else { + ret = scan_nat_page(sbi, page, nid); + f2fs_put_page(page, 1); + } - scan_nat_page(sbi, page, nid); - f2fs_put_page(page, 1); + if (ret) { + up_read(&nm_i->nat_tree_lock); + f2fs_err(sbi, "NAT is corrupt, run fsck to fix it"); + return ret; + } + } nid += (NAT_ENTRY_PER_BLOCK - (nid % NAT_ENTRY_PER_BLOCK)); if (unlikely(nid >= nm_i->max_nid)) @@ -2050,29 +2366,25 @@ static void __build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount) 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(sbi, 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), + f2fs_ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nm_i->next_scan_nid), nm_i->ra_nid_pages, META_NAT, false); + + return 0; } -void build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount) +int f2fs_build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount) { + int ret; + mutex_lock(&NM_I(sbi)->build_lock); - __build_free_nids(sbi, sync, mount); + ret = __f2fs_build_free_nids(sbi, sync, mount); mutex_unlock(&NM_I(sbi)->build_lock); + + return ret; } /* @@ -2080,17 +2392,16 @@ void build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount) * from second parameter of this function. * The returned nid could be used ino as well as nid when inode is created. */ -bool alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid) +bool f2fs_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: -#ifdef CONFIG_F2FS_FAULT_INJECTION if (time_to_inject(sbi, FAULT_ALLOC_NID)) { - f2fs_show_injection_info(FAULT_ALLOC_NID); + f2fs_show_injection_info(sbi, FAULT_ALLOC_NID); return false; } -#endif + spin_lock(&nm_i->nid_list_lock); if (unlikely(nm_i->available_nids == 0)) { @@ -2098,16 +2409,14 @@ retry: return false; } - /* We should not use stale free nids created by build_free_nids */ - 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], + /* We should not use stale free nids created by f2fs_build_free_nids */ + if (nm_i->nid_cnt[FREE_NID] && !on_f2fs_build_free_nids(nm_i)) { + f2fs_bug_on(sbi, list_empty(&nm_i->free_nid_list)); + i = list_first_entry(&nm_i->free_nid_list, struct free_nid, list); *nid = i->nid; - __remove_nid_from_list(sbi, i, FREE_NID_LIST, true); - i->state = NID_ALLOC; - __insert_nid_to_list(sbi, i, ALLOC_NID_LIST, false); + __move_free_nid(sbi, i, FREE_NID, PREALLOC_NID); nm_i->available_nids--; update_free_nid_bitmap(sbi, *nid, false, false); @@ -2118,14 +2427,15 @@ retry: spin_unlock(&nm_i->nid_list_lock); /* Let's scan nat pages and its caches to get free nids */ - build_free_nids(sbi, true, false); - goto retry; + if (!f2fs_build_free_nids(sbi, true, false)) + goto retry; + return false; } /* - * alloc_nid() should be called prior to this function. + * f2fs_alloc_nid() should be called prior to this function. */ -void alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid) +void f2fs_alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct free_nid *i; @@ -2133,16 +2443,16 @@ void alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid) spin_lock(&nm_i->nid_list_lock); i = __lookup_free_nid_list(nm_i, nid); f2fs_bug_on(sbi, !i); - __remove_nid_from_list(sbi, i, ALLOC_NID_LIST, false); + __remove_free_nid(sbi, i, PREALLOC_NID); spin_unlock(&nm_i->nid_list_lock); kmem_cache_free(free_nid_slab, i); } /* - * alloc_nid() should be called prior to this function. + * f2fs_alloc_nid() should be called prior to this function. */ -void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid) +void f2fs_alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct free_nid *i; @@ -2155,13 +2465,11 @@ void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid) i = __lookup_free_nid_list(nm_i, nid); f2fs_bug_on(sbi, !i); - if (!available_free_memory(sbi, FREE_NIDS)) { - __remove_nid_from_list(sbi, i, ALLOC_NID_LIST, false); + if (!f2fs_available_free_memory(sbi, FREE_NIDS)) { + __remove_free_nid(sbi, i, PREALLOC_NID); need_free = true; } else { - __remove_nid_from_list(sbi, i, ALLOC_NID_LIST, true); - i->state = NID_NEW; - __insert_nid_to_list(sbi, i, FREE_NID_LIST, false); + __move_free_nid(sbi, i, PREALLOC_NID, FREE_NID); } nm_i->available_nids++; @@ -2174,26 +2482,25 @@ void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid) kmem_cache_free(free_nid_slab, i); } -int try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink) +int f2fs_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) + 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->nid_list_lock); - list_for_each_entry_safe(i, next, &nm_i->nid_list[FREE_NID_LIST], - list) { + list_for_each_entry_safe(i, next, &nm_i->free_nid_list, list) { if (nr_shrink <= 0 || - nm_i->nid_cnt[FREE_NID_LIST] <= MAX_FREE_NIDS) + nm_i->nid_cnt[FREE_NID] <= MAX_FREE_NIDS) break; - __remove_nid_from_list(sbi, i, FREE_NID_LIST, false); + __remove_free_nid(sbi, i, FREE_NID); kmem_cache_free(free_nid_slab, i); nr_shrink--; } @@ -2203,34 +2510,36 @@ int try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink) return nr - nr_shrink; } -void recover_inline_xattr(struct inode *inode, struct page *page) +void f2fs_recover_inline_xattr(struct inode *inode, struct page *page) { void *src_addr, *dst_addr; size_t inline_size; struct page *ipage; struct f2fs_inode *ri; - ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino); + ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino); 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); + f2fs_wait_on_page_writeback(ipage, NODE, true, true); memcpy(dst_addr, src_addr, inline_size); update_inode: - update_inode(inode, ipage); + f2fs_update_inode(inode, ipage); f2fs_put_page(ipage, 1); } -int recover_xattr_data(struct inode *inode, struct page *page, block_t blkaddr) +int f2fs_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; @@ -2238,31 +2547,34 @@ int recover_xattr_data(struct inode *inode, struct page *page, block_t blkaddr) struct dnode_of_data dn; struct node_info ni; struct page *xpage; + int err; if (!prev_xnid) goto recover_xnid; /* 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); + err = f2fs_get_node_info(sbi, prev_xnid, &ni); + if (err) + return err; + + f2fs_invalidate_blocks(sbi, ni.blk_addr); dec_valid_node_count(sbi, inode, false); set_node_addr(sbi, &ni, NULL_ADDR, false); recover_xnid: /* 2: update xattr nid in inode */ - if (!alloc_nid(sbi, &new_xnid)) + if (!f2fs_alloc_nid(sbi, &new_xnid)) return -ENOSPC; set_new_dnode(&dn, inode, NULL, NULL, new_xnid); - xpage = new_node_page(&dn, XATTR_NODE_OFFSET); + xpage = f2fs_new_node_page(&dn, XATTR_NODE_OFFSET); if (IS_ERR(xpage)) { - alloc_nid_failed(sbi, new_xnid); + f2fs_alloc_nid_failed(sbi, new_xnid); return PTR_ERR(xpage); } - alloc_nid_done(sbi, new_xnid); - update_inode_page(inode); + f2fs_alloc_nid_done(sbi, new_xnid); + f2fs_update_inode_page(inode); /* 3: update and set xattr node page dirty */ memcpy(F2FS_NODE(xpage), F2FS_NODE(page), VALID_XATTR_BLOCK_SIZE); @@ -2273,14 +2585,17 @@ recover_xnid: return 0; } -int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page) +int f2fs_recover_inode_page(struct f2fs_sb_info *sbi, struct page *page) { struct f2fs_inode *src, *dst; nid_t ino = ino_of_node(page); struct node_info old_ni, new_ni; struct page *ipage; + int err; - get_node_info(sbi, ino, &old_ni); + err = f2fs_get_node_info(sbi, ino, &old_ni); + if (err) + return err; if (unlikely(old_ni.blk_addr != NULL_ADDR)) return -EINVAL; @@ -2297,6 +2612,7 @@ retry: if (!PageUptodate(ipage)) SetPageUptodate(ipage); fill_node_footer(ipage, ino, ino, 0, true); + set_cold_node(ipage, false); src = F2FS_INODE(page); dst = F2FS_INODE(ipage); @@ -2309,10 +2625,23 @@ retry: 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_project_quota(sbi->sb) && + + if (f2fs_sb_has_flexible_inline_xattr(sbi) && + 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) && F2FS_FITS_IN_INODE(src, le16_to_cpu(src->i_extra_isize), i_projid)) dst->i_projid = src->i_projid; + + if (f2fs_sb_has_inode_crtime(sbi) && + F2FS_FITS_IN_INODE(src, le16_to_cpu(src->i_extra_isize), + i_crtime_nsec)) { + dst->i_crtime = src->i_crtime; + dst->i_crtime_nsec = src->i_crtime_nsec; + } } new_ni = old_ni; @@ -2327,7 +2656,7 @@ retry: return 0; } -int restore_node_summary(struct f2fs_sb_info *sbi, +int f2fs_restore_node_summary(struct f2fs_sb_info *sbi, unsigned int segno, struct f2fs_summary_block *sum) { struct f2fs_node *rn; @@ -2344,10 +2673,13 @@ int restore_node_summary(struct f2fs_sb_info *sbi, nrpages = min(last_offset - i, BIO_MAX_PAGES); /* readahead node pages */ - ra_meta_pages(sbi, addr, nrpages, META_POR, true); + f2fs_ra_meta_pages(sbi, addr, nrpages, META_POR, true); for (idx = addr; idx < addr + nrpages; idx++) { - struct page *page = get_tmp_page(sbi, idx); + struct page *page = f2fs_get_tmp_page(sbi, idx); + + if (IS_ERR(page)) + return PTR_ERR(page); rn = F2FS_NODE(page); sum_entry->nid = rn->footer.nid; @@ -2380,8 +2712,8 @@ static void remove_nats_in_journal(struct f2fs_sb_info *sbi) ne = __lookup_nat_cache(nm_i, nid); if (!ne) { - ne = grab_nat_entry(nm_i, nid, true); - node_info_from_raw_nat(&ne->ni, &raw_ne); + ne = __alloc_nat_entry(nid, true); + __init_nat_entry(nm_i, ne, &raw_ne, true); } /* @@ -2427,15 +2759,17 @@ static void __update_nat_bits(struct f2fs_sb_info *sbi, nid_t start_nid, unsigned int nat_index = start_nid / NAT_ENTRY_PER_BLOCK; struct f2fs_nat_block *nat_blk = page_address(page); int valid = 0; - int i; + int i = 0; 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) + if (nat_index == 0) { + valid = 1; + i = 1; + } + for (; i < NAT_ENTRY_PER_BLOCK; i++) { + if (le32_to_cpu(nat_blk->entries[i].block_addr) != NULL_ADDR) valid++; } if (valid == 0) { @@ -2451,7 +2785,7 @@ static void __update_nat_bits(struct f2fs_sb_info *sbi, nid_t start_nid, __clear_bit_le(nat_index, nm_i->full_nat_bits); } -static void __flush_nat_entry_set(struct f2fs_sb_info *sbi, +static int __flush_nat_entry_set(struct f2fs_sb_info *sbi, struct nat_entry_set *set, struct cp_control *cpc) { struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA); @@ -2475,6 +2809,9 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi, down_write(&curseg->journal_rwsem); } else { page = get_next_nat_page(sbi, start_nid); + if (IS_ERR(page)) + return PTR_ERR(page); + nat_blk = page_address(page); f2fs_bug_on(sbi, !nat_blk); } @@ -2488,7 +2825,7 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi, f2fs_bug_on(sbi, nat_get_blkaddr(ne) == NEW_ADDR); if (to_journal) { - offset = lookup_journal_in_cursum(journal, + offset = f2fs_lookup_journal_in_cursum(journal, NAT_JOURNAL, nid, 1); f2fs_bug_on(sbi, offset < 0); raw_ne = &nat_in_journal(journal, offset); @@ -2500,11 +2837,7 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi, nat_reset_flag(ne); __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); + add_free_nid(sbi, nid, false, true); } else { spin_lock(&NM_I(sbi)->nid_list_lock); update_free_nid_bitmap(sbi, nid, false, false); @@ -2524,12 +2857,13 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi, radix_tree_delete(&NM_I(sbi)->nat_set_root, set->set); kmem_cache_free(nat_entry_set_slab, set); } + return 0; } /* * This function is called during the checkpointing process. */ -void flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) +int f2fs_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); @@ -2539,9 +2873,17 @@ void flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) unsigned int found; nid_t set_idx = 0; LIST_HEAD(sets); + int err = 0; + + /* during unmount, let's flush nat_bits before checking dirty_nat_cnt */ + if (enabled_nat_bits(sbi, cpc)) { + down_write(&nm_i->nat_tree_lock); + remove_nats_in_journal(sbi); + up_write(&nm_i->nat_tree_lock); + } if (!nm_i->dirty_nat_cnt) - return; + return 0; down_write(&nm_i->nat_tree_lock); @@ -2564,11 +2906,16 @@ void flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) } /* flush dirty nats in nat entry set */ - list_for_each_entry_safe(set, tmp, &sets, set_list) - __flush_nat_entry_set(sbi, set, cpc); + list_for_each_entry_safe(set, tmp, &sets, set_list) { + err = __flush_nat_entry_set(sbi, set, cpc); + if (err) + break; + } up_write(&nm_i->nat_tree_lock); /* Allow dirty nats by node block allocation in write_begin */ + + return err; } static int __get_nat_bitmaps(struct f2fs_sb_info *sbi) @@ -2583,17 +2930,20 @@ static int __get_nat_bitmaps(struct f2fs_sb_info *sbi) 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); + 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++); + struct page *page; + + page = f2fs_get_meta_page(sbi, nat_bits_addr++); + if (IS_ERR(page)) + return PTR_ERR(page); memcpy(nm_i->nat_bits + (i << F2FS_BLKSIZE_BITS), page_address(page), F2FS_BLKSIZE); @@ -2609,7 +2959,7 @@ static int __get_nat_bitmaps(struct f2fs_sb_info *sbi) 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"); + f2fs_notice(sbi, "Found nat_bits in checkpoint"); return 0; } @@ -2630,7 +2980,7 @@ static inline void load_free_nid_bitmap(struct f2fs_sb_info *sbi) __set_bit_le(i, nm_i->nat_block_bitmap); nid = i * NAT_ENTRY_PER_BLOCK; - last_nid = (i + 1) * NAT_ENTRY_PER_BLOCK; + last_nid = nid + NAT_ENTRY_PER_BLOCK; spin_lock(&NM_I(sbi)->nid_list_lock); for (; nid < last_nid; nid++) @@ -2664,20 +3014,20 @@ static int init_node_manager(struct f2fs_sb_info *sbi) /* not used nids: 0, node, meta, (and root counted as valid node) */ 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; + 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; 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->nid_list[FREE_NID_LIST]); - INIT_LIST_HEAD(&nm_i->nid_list[ALLOC_NID_LIST]); + INIT_LIST_HEAD(&nm_i->free_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); + spin_lock_init(&nm_i->nat_list_lock); mutex_init(&nm_i->build_lock); spin_lock_init(&nm_i->nid_list_lock); @@ -2711,29 +3061,42 @@ static int init_node_manager(struct f2fs_sb_info *sbi) 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 = kvzalloc(nm_i->nat_blocks * - NAT_ENTRY_BITMAP_SIZE, GFP_KERNEL); + nm_i->free_nid_bitmap = + f2fs_kzalloc(sbi, array_size(sizeof(unsigned char *), + nm_i->nat_blocks), + GFP_KERNEL); if (!nm_i->free_nid_bitmap) return -ENOMEM; - nm_i->nat_block_bitmap = kvzalloc(nm_i->nat_blocks / 8, + for (i = 0; i < nm_i->nat_blocks; i++) { + nm_i->free_nid_bitmap[i] = f2fs_kvzalloc(sbi, + f2fs_bitmap_size(NAT_ENTRY_PER_BLOCK), GFP_KERNEL); + if (!nm_i->free_nid_bitmap[i]) + 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 = kvzalloc(nm_i->nat_blocks * - sizeof(unsigned short), GFP_KERNEL); + nm_i->free_nid_count = + f2fs_kvzalloc(sbi, array_size(sizeof(unsigned short), + nm_i->nat_blocks), + GFP_KERNEL); if (!nm_i->free_nid_count) return -ENOMEM; return 0; } -int build_node_manager(struct f2fs_sb_info *sbi) +int f2fs_build_node_manager(struct f2fs_sb_info *sbi) { 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; @@ -2748,11 +3111,10 @@ int build_node_manager(struct f2fs_sb_info *sbi) /* load free nid status from nat_bits table */ load_free_nid_bitmap(sbi); - build_free_nids(sbi, true, true); - return 0; + return f2fs_build_free_nids(sbi, true, true); } -void destroy_node_manager(struct f2fs_sb_info *sbi) +void f2fs_destroy_node_manager(struct f2fs_sb_info *sbi) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct free_nid *i, *next_i; @@ -2766,16 +3128,15 @@ void destroy_node_manager(struct f2fs_sb_info *sbi) /* destroy free nid list */ 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); + list_for_each_entry_safe(i, next_i, &nm_i->free_nid_list, list) { + __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->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])); + 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 */ @@ -2785,8 +3146,13 @@ void destroy_node_manager(struct f2fs_sb_info *sbi) unsigned idx; nid = nat_get_nid(natvec[found - 1]) + 1; - for (idx = 0; idx < found; idx++) + for (idx = 0; idx < found; idx++) { + spin_lock(&nm_i->nat_list_lock); + list_del(&natvec[idx]->list); + spin_unlock(&nm_i->nat_list_lock); + __del_from_nat_cache(nm_i, natvec[idx]); + } } f2fs_bug_on(sbi, nm_i->nat_cnt); @@ -2807,19 +3173,25 @@ void destroy_node_manager(struct f2fs_sb_info *sbi) up_write(&nm_i->nat_tree_lock); kvfree(nm_i->nat_block_bitmap); - kvfree(nm_i->free_nid_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]); + kvfree(nm_i->free_nid_bitmap); + } kvfree(nm_i->free_nid_count); - kfree(nm_i->nat_bitmap); - kfree(nm_i->nat_bits); + kvfree(nm_i->nat_bitmap); + kvfree(nm_i->nat_bits); #ifdef CONFIG_F2FS_CHECK_FS - kfree(nm_i->nat_bitmap_mir); + kvfree(nm_i->nat_bitmap_mir); #endif sbi->nm_info = NULL; - kfree(nm_i); + kvfree(nm_i); } -int __init create_node_manager_caches(void) +int __init f2fs_create_node_manager_caches(void) { nat_entry_slab = f2fs_kmem_cache_create("nat_entry", sizeof(struct nat_entry)); @@ -2835,8 +3207,15 @@ int __init create_node_manager_caches(void) sizeof(struct nat_entry_set)); if (!nat_entry_set_slab) goto destroy_free_nid; + + fsync_node_entry_slab = f2fs_kmem_cache_create("fsync_node_entry", + sizeof(struct fsync_node_entry)); + if (!fsync_node_entry_slab) + goto destroy_nat_entry_set; return 0; +destroy_nat_entry_set: + kmem_cache_destroy(nat_entry_set_slab); destroy_free_nid: kmem_cache_destroy(free_nid_slab); destroy_nat_entry: @@ -2845,8 +3224,9 @@ fail: return -ENOMEM; } -void destroy_node_manager_caches(void) +void f2fs_destroy_node_manager_caches(void) { + kmem_cache_destroy(fsync_node_entry_slab); kmem_cache_destroy(nat_entry_set_slab); kmem_cache_destroy(free_nid_slab); kmem_cache_destroy(nat_entry_slab); |