diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-11-16 12:10:21 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-11-16 12:10:21 -0800 |
commit | a02cd4229e298aadbe8f5cf286edee8058d87116 (patch) | |
tree | bf22338b0280b9c5d638c9277e9cb8d96d4746f9 /fs/f2fs/checkpoint.c | |
parent | 487e2c9f44c4b5ea23bfe87bb34679f7297a0bce (diff) | |
parent | ead710b7d82dc9e8184e10871c155a3ed8b3f673 (diff) |
Merge tag 'f2fs-for-4.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs
Pull f2fs updates from Jaegeuk Kim:
"In this round, we introduce sysfile-based quota support which is
required for Android by default. In addition, we allow that users are
able to reserve some blocks in runtime to mitigate performance drops
in low free space.
Enhancements:
- assign proper data segments according to write_hints given by user
- issue cache_flush on dirty devices only among multiple devices
- exploit cp_error flag and add more faults to enhance fault
injection test
- conduct more readaheads during f2fs_readdir
- add a range for discard commands
Bug fixes:
- fix zero stat->st_blocks when inline_data is set
- drop crypto key and free stale memory pointer while evict_inode is
failing
- fix some corner cases in free space and segment management
- fix wrong last_disk_size
This series includes lots of clean-ups and code enhancement in terms
of xattr operations, discard/flush command control. In addition, it
adds versatile debugfs entries to monitor f2fs status"
* tag 'f2fs-for-4.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (75 commits)
f2fs: deny accessing encryption policy if encryption is off
f2fs: inject fault in inc_valid_node_count
f2fs: fix to clear FI_NO_PREALLOC
f2fs: expose quota information in debugfs
f2fs: separate nat entry mem alloc from nat_tree_lock
f2fs: validate before set/clear free nat bitmap
f2fs: avoid opened loop codes in __add_ino_entry
f2fs: apply write hints to select the type of segments for buffered write
f2fs: introduce scan_curseg_cache for cleanup
f2fs: optimize the way of traversing free_nid_bitmap
f2fs: keep scanning until enough free nids are acquired
f2fs: trace checkpoint reason in fsync()
f2fs: keep isize once block is reserved cross EOF
f2fs: avoid race in between GC and block exchange
f2fs: save a multiplication for last_nid calculation
f2fs: fix summary info corruption
f2fs: remove dead code in update_meta_page
f2fs: remove unneeded semicolon
f2fs: don't bother with inode->i_version
f2fs: check curseg space before foreground GC
...
Diffstat (limited to 'fs/f2fs/checkpoint.c')
-rw-r--r-- | fs/f2fs/checkpoint.c | 64 |
1 files changed, 49 insertions, 15 deletions
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 0bb8e2c022d3..dd2e73e10857 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -29,7 +29,6 @@ struct kmem_cache *inode_entry_slab; void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io) { set_ckpt_flags(sbi, CP_ERROR_FLAG); - sbi->sb->s_flags |= MS_RDONLY; if (!end_io) f2fs_flush_merged_writes(sbi); } @@ -398,24 +397,23 @@ const struct address_space_operations f2fs_meta_aops = { #endif }; -static void __add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type) +static void __add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, + unsigned int devidx, int type) { struct inode_management *im = &sbi->im[type]; struct ino_entry *e, *tmp; tmp = f2fs_kmem_cache_alloc(ino_entry_slab, GFP_NOFS); -retry: + radix_tree_preload(GFP_NOFS | __GFP_NOFAIL); spin_lock(&im->ino_lock); e = radix_tree_lookup(&im->ino_root, ino); if (!e) { e = tmp; - if (radix_tree_insert(&im->ino_root, ino, e)) { - spin_unlock(&im->ino_lock); - radix_tree_preload_end(); - goto retry; - } + if (unlikely(radix_tree_insert(&im->ino_root, ino, e))) + f2fs_bug_on(sbi, 1); + memset(e, 0, sizeof(struct ino_entry)); e->ino = ino; @@ -423,6 +421,10 @@ retry: if (type != ORPHAN_INO) im->ino_num++; } + + if (type == FLUSH_INO) + f2fs_set_bit(devidx, (char *)&e->dirty_device); + spin_unlock(&im->ino_lock); radix_tree_preload_end(); @@ -451,7 +453,7 @@ static void __remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type) void add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type) { /* add new dirty ino entry into list */ - __add_ino_entry(sbi, ino, type); + __add_ino_entry(sbi, ino, 0, type); } void remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type) @@ -477,7 +479,7 @@ void release_ino_entry(struct f2fs_sb_info *sbi, bool all) struct ino_entry *e, *tmp; int i; - for (i = all ? ORPHAN_INO: APPEND_INO; i <= UPDATE_INO; i++) { + for (i = all ? ORPHAN_INO : APPEND_INO; i < MAX_INO_ENTRY; i++) { struct inode_management *im = &sbi->im[i]; spin_lock(&im->ino_lock); @@ -491,6 +493,27 @@ void release_ino_entry(struct f2fs_sb_info *sbi, bool all) } } +void set_dirty_device(struct f2fs_sb_info *sbi, nid_t ino, + unsigned int devidx, int type) +{ + __add_ino_entry(sbi, ino, devidx, type); +} + +bool is_dirty_device(struct f2fs_sb_info *sbi, nid_t ino, + unsigned int devidx, int type) +{ + struct inode_management *im = &sbi->im[type]; + struct ino_entry *e; + bool is_dirty = false; + + spin_lock(&im->ino_lock); + e = radix_tree_lookup(&im->ino_root, ino); + if (e && f2fs_test_bit(devidx, (char *)&e->dirty_device)) + is_dirty = true; + spin_unlock(&im->ino_lock); + return is_dirty; +} + int acquire_orphan_inode(struct f2fs_sb_info *sbi) { struct inode_management *im = &sbi->im[ORPHAN_INO]; @@ -527,7 +550,7 @@ void release_orphan_inode(struct f2fs_sb_info *sbi) void add_orphan_inode(struct inode *inode) { /* add new orphan ino entry into list */ - __add_ino_entry(F2FS_I_SB(inode), inode->i_ino, ORPHAN_INO); + __add_ino_entry(F2FS_I_SB(inode), inode->i_ino, 0, ORPHAN_INO); update_inode_page(inode); } @@ -551,7 +574,7 @@ static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) return err; } - __add_ino_entry(sbi, ino, ORPHAN_INO); + __add_ino_entry(sbi, ino, 0, ORPHAN_INO); inode = f2fs_iget_retry(sbi->sb, ino); if (IS_ERR(inode)) { @@ -587,6 +610,9 @@ int recover_orphan_inodes(struct f2fs_sb_info *sbi) block_t start_blk, orphan_blocks, i, j; unsigned int s_flags = sbi->sb->s_flags; int err = 0; +#ifdef CONFIG_QUOTA + int quota_enabled; +#endif if (!is_set_ckpt_flags(sbi, CP_ORPHAN_PRESENT_FLAG)) return 0; @@ -599,8 +625,9 @@ int recover_orphan_inodes(struct f2fs_sb_info *sbi) #ifdef CONFIG_QUOTA /* Needed for iput() to work correctly and not trash data */ sbi->sb->s_flags |= MS_ACTIVE; + /* Turn on quotas so that they are updated correctly */ - f2fs_enable_quota_files(sbi); + quota_enabled = f2fs_enable_quota_files(sbi, s_flags & MS_RDONLY); #endif start_blk = __start_cp_addr(sbi) + 1 + __cp_payload(sbi); @@ -628,7 +655,8 @@ int recover_orphan_inodes(struct f2fs_sb_info *sbi) out: #ifdef CONFIG_QUOTA /* Turn quotas off */ - f2fs_quota_off_umount(sbi->sb); + if (quota_enabled) + f2fs_quota_off_umount(sbi->sb); #endif sbi->sb->s_flags = s_flags; /* Restore MS_RDONLY status */ @@ -983,7 +1011,7 @@ int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi) update_inode_page(inode); iput(inode); } - }; + } return 0; } @@ -1143,6 +1171,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) struct super_block *sb = sbi->sb; struct curseg_info *seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE); u64 kbytes_written; + int err; /* Flush all the NAT/SIT pages */ while (get_pages(sbi, F2FS_DIRTY_META)) { @@ -1236,6 +1265,11 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) if (unlikely(f2fs_cp_error(sbi))) return -EIO; + /* flush all device cache */ + err = f2fs_flush_device_cache(sbi); + if (err) + return err; + /* write out checkpoint buffer at block 0 */ update_meta_page(sbi, ckpt, start_blk++); |