diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs index d870b5514d15..540553c933b6 100644 --- a/Documentation/ABI/testing/sysfs-fs-f2fs +++ b/Documentation/ABI/testing/sysfs-fs-f2fs @@ -192,3 +192,14 @@ Date: November 2017 Contact: "Sheng Yong" Description: Controls readahead inode block in readdir. + +What: /sys/fs/f2fs//extension_list +Date: Feburary 2018 +Contact: "Chao Yu" +Description: + Used to control configure extension list: + - Query: cat /sys/fs/f2fs//extension_list + - Add: echo '[h/c]extension' > /sys/fs/f2fs//extension_list + - Del: echo '[h/c]!extension' > /sys/fs/f2fs//extension_list + - [h] means add/del hot file extension + - [c] means add/del cold file extension diff --git a/Documentation/filesystems/f2fs.txt b/Documentation/filesystems/f2fs.txt index 13c2ff034348..12a147c9f87f 100644 --- a/Documentation/filesystems/f2fs.txt +++ b/Documentation/filesystems/f2fs.txt @@ -174,6 +174,23 @@ offgrpjquota Turn off group journelled quota. offprjjquota Turn off project journelled quota. quota Enable plain user disk quota accounting. noquota Disable all plain disk quota option. +whint_mode=%s Control which write hints are passed down to block + layer. This supports "off", "user-based", and + "fs-based". In "off" mode (default), f2fs does not pass + down hints. In "user-based" mode, f2fs tries to pass + down hints given by users. And in "fs-based" mode, f2fs + passes down hints with its policy. +alloc_mode=%s Adjust block allocation policy, which supports "reuse" + and "default". +fsync_mode=%s Control the policy of fsync. Currently supports "posix" + and "strict". In "posix" mode, which is default, fsync + will follow POSIX semantics and does a light operation + to improve the filesystem performance. In "strict" mode, + fsync will be heavy and behaves in line with xfs, ext4 + and btrfs, where xfstest generic/342 will pass, but the + performance will regress. +test_dummy_encryption Enable dummy encryption, which provides a fake fscrypt + context. The fake fscrypt context is used by xfstests. ================================================================================ DEBUGFS ENTRIES @@ -611,3 +628,63 @@ algorithm. In order to identify whether the data in the victim segment are valid or not, F2FS manages a bitmap. Each bit represents the validity of a block, and the bitmap is composed of a bit stream covering whole blocks in main area. + +Write-hint Policy +----------------- + +1) whint_mode=off. F2FS only passes down WRITE_LIFE_NOT_SET. + +2) whint_mode=user-based. F2FS tries to pass down hints given by +users. + +User F2FS Block +---- ---- ----- + META WRITE_LIFE_NOT_SET + HOT_NODE " + WARM_NODE " + COLD_NODE " +*ioctl(COLD) COLD_DATA WRITE_LIFE_EXTREME +*extension list " " + +-- buffered io +WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME +WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT +WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET +WRITE_LIFE_NONE " " +WRITE_LIFE_MEDIUM " " +WRITE_LIFE_LONG " " + +-- direct io +WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME +WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT +WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET +WRITE_LIFE_NONE " WRITE_LIFE_NONE +WRITE_LIFE_MEDIUM " WRITE_LIFE_MEDIUM +WRITE_LIFE_LONG " WRITE_LIFE_LONG + +3) whint_mode=fs-based. F2FS passes down hints with its policy. + +User F2FS Block +---- ---- ----- + META WRITE_LIFE_MEDIUM; + HOT_NODE WRITE_LIFE_NOT_SET + WARM_NODE " + COLD_NODE WRITE_LIFE_NONE +ioctl(COLD) COLD_DATA WRITE_LIFE_EXTREME +extension list " " + +-- buffered io +WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME +WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT +WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_LONG +WRITE_LIFE_NONE " " +WRITE_LIFE_MEDIUM " " +WRITE_LIFE_LONG " " + +-- direct io +WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME +WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT +WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET +WRITE_LIFE_NONE " WRITE_LIFE_NONE +WRITE_LIFE_MEDIUM " WRITE_LIFE_MEDIUM +WRITE_LIFE_LONG " WRITE_LIFE_LONG diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 512dca8abc7d..bf779461df13 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -68,6 +68,7 @@ static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index, .old_blkaddr = index, .new_blkaddr = index, .encrypted_page = NULL, + .is_meta = is_meta, }; if (unlikely(!is_meta)) @@ -162,6 +163,7 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, .op_flags = sync ? (REQ_META | REQ_PRIO) : REQ_RAHEAD, .encrypted_page = NULL, .in_list = false, + .is_meta = (type != META_POR), }; struct blk_plug plug; @@ -569,13 +571,8 @@ static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) struct node_info ni; int err = acquire_orphan_inode(sbi); - if (err) { - set_sbi_flag(sbi, SBI_NEED_FSCK); - f2fs_msg(sbi->sb, KERN_WARNING, - "%s: orphan failed (ino=%x), run fsck to fix.", - __func__, ino); - return err; - } + if (err) + goto err_out; __add_ino_entry(sbi, ino, 0, ORPHAN_INO); @@ -589,6 +586,11 @@ static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) return PTR_ERR(inode); } + err = dquot_initialize(inode); + if (err) + goto err_out; + + dquot_initialize(inode); clear_nlink(inode); /* truncate all the data during iput */ @@ -598,14 +600,18 @@ static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) /* ENOMEM was fully retried in f2fs_evict_inode. */ if (ni.blk_addr != NULL_ADDR) { - set_sbi_flag(sbi, SBI_NEED_FSCK); - f2fs_msg(sbi->sb, KERN_WARNING, - "%s: orphan failed (ino=%x) by kernel, retry mount.", - __func__, ino); - return -EIO; + err = -EIO; + goto err_out; } __remove_ino_entry(sbi, ino, ORPHAN_INO); return 0; + +err_out: + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_msg(sbi->sb, KERN_WARNING, + "%s: orphan failed (ino=%x), run fsck to fix.", + __func__, ino); + return err; } int recover_orphan_inodes(struct f2fs_sb_info *sbi) @@ -1136,6 +1142,8 @@ static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc) if (cpc->reason & CP_TRIMMED) __set_ckpt_flags(ckpt, CP_TRIMMED_FLAG); + else + __clear_ckpt_flags(ckpt, CP_TRIMMED_FLAG); if (cpc->reason & CP_UMOUNT) __set_ckpt_flags(ckpt, CP_UMOUNT_FLAG); @@ -1162,6 +1170,39 @@ static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc) spin_unlock_irqrestore(&sbi->cp_lock, flags); } +static void commit_checkpoint(struct f2fs_sb_info *sbi, + void *src, block_t blk_addr) +{ + struct writeback_control wbc = { + .for_reclaim = 0, + }; + + /* + * pagevec_lookup_tag and lock_page again will take + * some extra time. Therefore, update_meta_pages and + * sync_meta_pages are combined in this function. + */ + struct page *page = grab_meta_page(sbi, blk_addr); + int err; + + memcpy(page_address(page), src, PAGE_SIZE); + set_page_dirty(page); + + f2fs_wait_on_page_writeback(page, META, true); + f2fs_bug_on(sbi, PageWriteback(page)); + if (unlikely(!clear_page_dirty_for_io(page))) + f2fs_bug_on(sbi, 1); + + /* writeout cp pack 2 page */ + err = __f2fs_write_meta_page(page, &wbc, FS_CP_META_IO); + f2fs_bug_on(sbi, err); + + f2fs_put_page(page, 0); + + /* submit checkpoint (with barrier if NOBARRIER is not set) */ + f2fs_submit_merged_write(sbi, META_FLUSH); +} + static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) { struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); @@ -1264,16 +1305,6 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) } } - /* need to wait for end_io results */ - wait_on_all_pages_writeback(sbi); - 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++); @@ -1301,26 +1332,26 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) start_blk += NR_CURSEG_NODE_TYPE; } - /* writeout checkpoint block */ - update_meta_page(sbi, ckpt, start_blk); + /* update user_block_counts */ + sbi->last_valid_block_count = sbi->total_valid_block_count; + percpu_counter_set(&sbi->alloc_valid_block_count, 0); - /* wait for previous submitted node/meta pages writeback */ + /* Here, we have one bio having CP pack except cp pack 2 page */ + sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO); + + /* wait for previous submitted meta pages writeback */ wait_on_all_pages_writeback(sbi); if (unlikely(f2fs_cp_error(sbi))) return -EIO; - filemap_fdatawait_range(NODE_MAPPING(sbi), 0, LLONG_MAX); - filemap_fdatawait_range(META_MAPPING(sbi), 0, LLONG_MAX); + /* flush all device cache */ + err = f2fs_flush_device_cache(sbi); + if (err) + return err; - /* update user_block_counts */ - sbi->last_valid_block_count = sbi->total_valid_block_count; - percpu_counter_set(&sbi->alloc_valid_block_count, 0); - - /* Here, we only have one bio having CP pack */ - sync_meta_pages(sbi, META_FLUSH, LONG_MAX, FS_CP_META_IO); - - /* wait for previous submitted meta pages writeback */ + /* barrier and flush checkpoint cp pack 2 page if it can */ + commit_checkpoint(sbi, ckpt, start_blk); wait_on_all_pages_writeback(sbi); release_ino_entry(sbi, false); diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 7578ed1a85e0..db50686f5096 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -175,15 +175,22 @@ static bool __same_bdev(struct f2fs_sb_info *sbi, */ static struct bio *__bio_alloc(struct f2fs_sb_info *sbi, block_t blk_addr, struct writeback_control *wbc, - int npages, bool is_read) + int npages, bool is_read, + enum page_type type, enum temp_type temp) { struct bio *bio; bio = f2fs_bio_alloc(sbi, npages, true); f2fs_target_device(sbi, blk_addr, bio); - bio->bi_end_io = is_read ? f2fs_read_end_io : f2fs_write_end_io; - bio->bi_private = is_read ? NULL : sbi; + if (is_read) { + bio->bi_end_io = f2fs_read_end_io; + bio->bi_private = NULL; + } else { + bio->bi_end_io = f2fs_write_end_io; + bio->bi_private = sbi; + bio->bi_write_hint = io_type_to_rw_hint(sbi, type, temp); + } if (wbc) wbc_init_bio(wbc, bio); @@ -196,13 +203,12 @@ static inline void __submit_bio(struct f2fs_sb_info *sbi, if (!is_read_io(bio_op(bio))) { unsigned int start; - if (f2fs_sb_mounted_blkzoned(sbi->sb) && - current->plug && (type == DATA || type == NODE)) - blk_finish_plug(current->plug); - if (type != DATA && type != NODE) goto submit_io; + if (f2fs_sb_has_blkzoned(sbi->sb) && current->plug) + blk_finish_plug(current->plug); + start = bio->bi_iter.bi_size >> F2FS_BLKSIZE_BITS; start %= F2FS_IO_SIZE(sbi); @@ -377,12 +383,13 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio) struct page *page = fio->encrypted_page ? fio->encrypted_page : fio->page; + verify_block_addr(fio, fio->new_blkaddr); trace_f2fs_submit_page_bio(page, fio); f2fs_trace_ios(fio, 0); /* Allocate a new bio */ bio = __bio_alloc(fio->sbi, fio->new_blkaddr, fio->io_wbc, - 1, is_read_io(fio->op)); + 1, is_read_io(fio->op), fio->type, fio->temp); if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) { bio_put(bio); @@ -422,8 +429,8 @@ next: } if (fio->old_blkaddr != NEW_ADDR) - verify_block_addr(sbi, fio->old_blkaddr); - verify_block_addr(sbi, fio->new_blkaddr); + verify_block_addr(fio, fio->old_blkaddr); + verify_block_addr(fio, fio->new_blkaddr); bio_page = fio->encrypted_page ? fio->encrypted_page : fio->page; @@ -445,7 +452,8 @@ alloc_new: goto out_fail; } io->bio = __bio_alloc(sbi, fio->new_blkaddr, fio->io_wbc, - BIO_MAX_PAGES, false); + BIO_MAX_PAGES, false, + fio->type, fio->temp); io->fio = *fio; } @@ -832,13 +840,6 @@ alloc: return 0; } -static inline bool __force_buffered_io(struct inode *inode, int rw) -{ - return (f2fs_encrypted_file(inode) || - (rw == WRITE && test_opt(F2FS_I_SB(inode), LFS)) || - F2FS_I_SB(inode)->s_ndevs); -} - int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from) { struct inode *inode = file_inode(iocb->ki_filp); @@ -870,7 +871,7 @@ int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from) if (direct_io) { map.m_seg_type = rw_hint_to_seg_type(iocb->ki_hint); - flag = __force_buffered_io(inode, WRITE) ? + flag = f2fs_force_buffered_io(inode, WRITE) ? F2FS_GET_BLOCK_PRE_AIO : F2FS_GET_BLOCK_PRE_DIO; goto map_blocks; @@ -1114,6 +1115,31 @@ out: return err; } +bool f2fs_overwrite_io(struct inode *inode, loff_t pos, size_t len) +{ + struct f2fs_map_blocks map; + block_t last_lblk; + int err; + + if (pos + len > i_size_read(inode)) + return false; + + map.m_lblk = F2FS_BYTES_TO_BLK(pos); + map.m_next_pgofs = NULL; + map.m_next_extent = NULL; + map.m_seg_type = NO_CHECK_TYPE; + last_lblk = F2FS_BLK_ALIGN(pos + len); + + while (map.m_lblk < last_lblk) { + map.m_len = last_lblk - map.m_lblk; + err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_DEFAULT); + if (err || map.m_len == 0) + return false; + map.m_lblk += map.m_len; + } + return true; +} + static int __get_data_block(struct inode *inode, sector_t iblock, struct buffer_head *bh, int create, int flag, pgoff_t *next_pgofs, int seg_type) @@ -2287,25 +2313,41 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct address_space *mapping = iocb->ki_filp->f_mapping; struct inode *inode = mapping->host; + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); size_t count = iov_iter_count(iter); loff_t offset = iocb->ki_pos; int rw = iov_iter_rw(iter); int err; + enum rw_hint hint = iocb->ki_hint; + int whint_mode = F2FS_OPTION(sbi).whint_mode; err = check_direct_IO(inode, iter, offset); if (err) return err; - if (__force_buffered_io(inode, rw)) + if (f2fs_force_buffered_io(inode, rw)) return 0; trace_f2fs_direct_IO_enter(inode, offset, count, rw); - down_read(&F2FS_I(inode)->dio_rwsem[rw]); + if (rw == WRITE && whint_mode == WHINT_MODE_OFF) + iocb->ki_hint = WRITE_LIFE_NOT_SET; + + if (!down_read_trylock(&F2FS_I(inode)->dio_rwsem[rw])) { + if (iocb->ki_flags & IOCB_NOWAIT) { + iocb->ki_hint = hint; + err = -EAGAIN; + goto out; + } + down_read(&F2FS_I(inode)->dio_rwsem[rw]); + } + err = blockdev_direct_IO(iocb, inode, iter, get_data_block_dio); up_read(&F2FS_I(inode)->dio_rwsem[rw]); if (rw == WRITE) { + if (whint_mode == WHINT_MODE_OFF) + iocb->ki_hint = hint; if (err > 0) { f2fs_update_iostat(F2FS_I_SB(inode), APP_DIRECT_IO, err); @@ -2315,6 +2357,7 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) } } +out: trace_f2fs_direct_IO_exit(inode, offset, count, rw, err); return err; diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index f00b5ed8c011..fe661274ff10 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -94,14 +94,12 @@ static struct f2fs_dir_entry *find_in_block(struct page *dentry_page, struct f2fs_dir_entry *de; struct f2fs_dentry_ptr d; - dentry_blk = (struct f2fs_dentry_block *)kmap(dentry_page); + dentry_blk = (struct f2fs_dentry_block *)page_address(dentry_page); make_dentry_ptr_block(NULL, &d, dentry_blk); de = find_target_dentry(fname, namehash, max_slots, &d); if (de) *res_page = dentry_page; - else - kunmap(dentry_page); return de; } @@ -287,7 +285,6 @@ ino_t f2fs_inode_by_name(struct inode *dir, const struct qstr *qstr, de = f2fs_find_entry(dir, qstr, page); if (de) { res = le32_to_cpu(de->ino); - f2fs_dentry_kunmap(dir, *page); f2fs_put_page(*page, 0); } @@ -302,7 +299,6 @@ void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de, f2fs_wait_on_page_writeback(page, type, true); de->ino = cpu_to_le32(inode->i_ino); set_de_type(de, inode->i_mode); - f2fs_dentry_kunmap(dir, page); set_page_dirty(page); dir->i_mtime = dir->i_ctime = current_time(dir); @@ -350,13 +346,11 @@ static int make_empty_dir(struct inode *inode, if (IS_ERR(dentry_page)) return PTR_ERR(dentry_page); - dentry_blk = kmap_atomic(dentry_page); + dentry_blk = page_address(dentry_page); make_dentry_ptr_block(NULL, &d, dentry_blk); do_make_empty_dir(inode, parent, &d); - kunmap_atomic(dentry_blk); - set_page_dirty(dentry_page); f2fs_put_page(dentry_page, 1); return 0; @@ -367,6 +361,7 @@ struct page *init_inode_metadata(struct inode *inode, struct inode *dir, struct page *dpage) { struct page *page; + int dummy_encrypt = DUMMY_ENCRYPTION_ENABLED(F2FS_I_SB(dir)); int err; if (is_inode_flag_set(inode, FI_NEW_INODE)) { @@ -393,7 +388,8 @@ struct page *init_inode_metadata(struct inode *inode, struct inode *dir, if (err) goto put_error; - if (f2fs_encrypted_inode(dir) && f2fs_may_encrypt(inode)) { + if ((f2fs_encrypted_inode(dir) || dummy_encrypt) && + f2fs_may_encrypt(inode)) { err = fscrypt_inherit_context(dir, inode, page, false); if (err) goto put_error; @@ -402,8 +398,6 @@ struct page *init_inode_metadata(struct inode *inode, struct inode *dir, page = get_node_page(F2FS_I_SB(dir), inode->i_ino); if (IS_ERR(page)) return page; - - set_cold_node(inode, page); } if (new_name) { @@ -547,13 +541,12 @@ start: if (IS_ERR(dentry_page)) return PTR_ERR(dentry_page); - dentry_blk = kmap(dentry_page); + dentry_blk = page_address(dentry_page); bit_pos = room_for_filename(&dentry_blk->dentry_bitmap, slots, NR_DENTRY_IN_BLOCK); if (bit_pos < NR_DENTRY_IN_BLOCK) goto add_dentry; - kunmap(dentry_page); f2fs_put_page(dentry_page, 1); } @@ -588,7 +581,6 @@ fail: if (inode) up_write(&F2FS_I(inode)->i_sem); - kunmap(dentry_page); f2fs_put_page(dentry_page, 1); return err; @@ -642,7 +634,6 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name, F2FS_I(dir)->task = NULL; } if (de) { - f2fs_dentry_kunmap(dir, page); f2fs_put_page(page, 0); err = -EEXIST; } else if (IS_ERR(page)) { @@ -713,7 +704,8 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page, f2fs_update_time(F2FS_I_SB(dir), REQ_TIME); - add_ino_entry(F2FS_I_SB(dir), dir->i_ino, TRANS_DIR_INO); + if (F2FS_OPTION(F2FS_I_SB(dir)).fsync_mode == FSYNC_MODE_STRICT) + add_ino_entry(F2FS_I_SB(dir), dir->i_ino, TRANS_DIR_INO); if (f2fs_has_inline_dentry(dir)) return f2fs_delete_inline_entry(dentry, page, dir, inode); @@ -730,7 +722,6 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page, bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap, NR_DENTRY_IN_BLOCK, 0); - kunmap(page); /* kunmap - pair of f2fs_find_entry */ set_page_dirty(page); dir->i_ctime = dir->i_mtime = current_time(dir); @@ -775,7 +766,7 @@ bool f2fs_empty_dir(struct inode *dir) return false; } - dentry_blk = kmap_atomic(dentry_page); + dentry_blk = page_address(dentry_page); if (bidx == 0) bit_pos = 2; else @@ -783,7 +774,6 @@ bool f2fs_empty_dir(struct inode *dir) bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap, NR_DENTRY_IN_BLOCK, bit_pos); - kunmap_atomic(dentry_blk); f2fs_put_page(dentry_page, 1); @@ -901,19 +891,17 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx) } } - dentry_blk = kmap(dentry_page); + dentry_blk = page_address(dentry_page); make_dentry_ptr_block(inode, &d, dentry_blk); err = f2fs_fill_dentries(ctx, &d, n * NR_DENTRY_IN_BLOCK, &fstr); if (err) { - kunmap(dentry_page); f2fs_put_page(dentry_page, 1); break; } - kunmap(dentry_page); f2fs_put_page(dentry_page, 1); } out_free: diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c index ff2352a0ed15..d5a861bf2b42 100644 --- a/fs/f2fs/extent_cache.c +++ b/fs/f2fs/extent_cache.c @@ -460,7 +460,7 @@ static struct extent_node *__insert_extent_tree(struct inode *inode, struct rb_node *insert_parent) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct rb_node **p = &et->root.rb_node; + struct rb_node **p; struct rb_node *parent = NULL; struct extent_node *en = NULL; @@ -706,6 +706,9 @@ void f2fs_drop_extent_tree(struct inode *inode) struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct extent_tree *et = F2FS_I(inode)->extent_tree; + if (!f2fs_may_extent_tree(inode)) + return; + set_inode_flag(inode, FI_NO_EXTENT); write_lock(&et->lock); diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 6300ac5bcbe4..1df7f10476d6 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -98,9 +98,10 @@ extern char *fault_name[FAULT_MAX]; #define F2FS_MOUNT_INLINE_XATTR_SIZE 0x00800000 #define F2FS_MOUNT_RESERVE_ROOT 0x01000000 -#define clear_opt(sbi, option) ((sbi)->mount_opt.opt &= ~F2FS_MOUNT_##option) -#define set_opt(sbi, option) ((sbi)->mount_opt.opt |= F2FS_MOUNT_##option) -#define test_opt(sbi, option) ((sbi)->mount_opt.opt & F2FS_MOUNT_##option) +#define F2FS_OPTION(sbi) ((sbi)->mount_opt) +#define clear_opt(sbi, option) (F2FS_OPTION(sbi).opt &= ~F2FS_MOUNT_##option) +#define set_opt(sbi, option) (F2FS_OPTION(sbi).opt |= F2FS_MOUNT_##option) +#define test_opt(sbi, option) (F2FS_OPTION(sbi).opt & F2FS_MOUNT_##option) #define ver_after(a, b) (typecheck(unsigned long long, a) && \ typecheck(unsigned long long, b) && \ @@ -113,7 +114,26 @@ typedef u32 block_t; /* typedef u32 nid_t; struct f2fs_mount_info { - unsigned int opt; + unsigned int opt; + int write_io_size_bits; /* Write IO size bits */ + block_t root_reserved_blocks; /* root reserved blocks */ + kuid_t s_resuid; /* reserved blocks for uid */ + kgid_t s_resgid; /* reserved blocks for gid */ + int active_logs; /* # of active logs */ + int inline_xattr_size; /* inline xattr size */ +#ifdef CONFIG_F2FS_FAULT_INJECTION + struct f2fs_fault_info fault_info; /* For fault injection */ +#endif +#ifdef CONFIG_QUOTA + /* Names of quota files with journalled quota */ + char *s_qf_names[MAXQUOTAS]; + int s_jquota_fmt; /* Format of quota to use */ +#endif + /* For which write hints are passed down to block layer */ + int whint_mode; + int alloc_mode; /* segment allocation policy */ + int fsync_mode; /* fsync policy */ + bool test_dummy_encryption; /* test dummy encryption */ }; #define F2FS_FEATURE_ENCRYPT 0x0001 @@ -125,6 +145,8 @@ struct f2fs_mount_info { #define F2FS_FEATURE_FLEXIBLE_INLINE_XATTR 0x0040 #define F2FS_FEATURE_QUOTA_INO 0x0080 #define F2FS_FEATURE_INODE_CRTIME 0x0100 +#define F2FS_FEATURE_LOST_FOUND 0x0200 +#define F2FS_FEATURE_VERITY 0x0400 /* reserved */ #define F2FS_HAS_FEATURE(sb, mask) \ ((F2FS_SB(sb)->raw_super->feature & cpu_to_le32(mask)) != 0) @@ -450,7 +472,7 @@ static inline void make_dentry_ptr_block(struct inode *inode, d->inode = inode; d->max = NR_DENTRY_IN_BLOCK; d->nr_bitmap = SIZE_OF_DENTRY_BITMAP; - d->bitmap = &t->dentry_bitmap; + d->bitmap = t->dentry_bitmap; d->dentry = t->dentry; d->filename = t->filename; } @@ -576,6 +598,8 @@ enum { #define FADVISE_ENCRYPT_BIT 0x04 #define FADVISE_ENC_NAME_BIT 0x08 #define FADVISE_KEEP_SIZE_BIT 0x10 +#define FADVISE_HOT_BIT 0x20 +#define FADVISE_VERITY_BIT 0x40 /* reserved */ #define file_is_cold(inode) is_file(inode, FADVISE_COLD_BIT) #define file_wrong_pino(inode) is_file(inode, FADVISE_LOST_PINO_BIT) @@ -590,6 +614,9 @@ enum { #define file_set_enc_name(inode) set_file(inode, FADVISE_ENC_NAME_BIT) #define file_keep_isize(inode) is_file(inode, FADVISE_KEEP_SIZE_BIT) #define file_set_keep_isize(inode) set_file(inode, FADVISE_KEEP_SIZE_BIT) +#define file_is_hot(inode) is_file(inode, FADVISE_HOT_BIT) +#define file_set_hot(inode) set_file(inode, FADVISE_HOT_BIT) +#define file_clear_hot(inode) clear_file(inode, FADVISE_HOT_BIT) #define DEF_DIR_LEVEL 0 @@ -637,6 +664,7 @@ struct f2fs_inode_info { kprojid_t i_projid; /* id for project quota */ int i_inline_xattr_size; /* inline xattr size */ struct timespec i_crtime; /* inode creation time */ + struct timespec i_disk_time[4]; /* inode disk times */ }; static inline void get_extent_info(struct extent_info *ext, @@ -743,7 +771,7 @@ struct f2fs_nm_info { unsigned int nid_cnt[MAX_NID_STATE]; /* the number of free node id */ spinlock_t nid_list_lock; /* protect nid lists ops */ struct mutex build_lock; /* lock for build free nids */ - unsigned char (*free_nid_bitmap)[NAT_ENTRY_BITMAP_SIZE]; + unsigned char **free_nid_bitmap; unsigned char *nat_block_bitmap; unsigned short *free_nid_count; /* free nid count of NAT block */ @@ -976,6 +1004,7 @@ struct f2fs_io_info { bool submitted; /* indicate IO submission */ int need_lock; /* indicate we need to lock cp_rwsem */ bool in_list; /* indicate fio is in io_list */ + bool is_meta; /* indicate borrow meta inode mapping or not */ enum iostat_type io_type; /* io type */ struct writeback_control *io_wbc; /* writeback control */ }; @@ -1037,10 +1066,34 @@ enum { MAX_TIME, }; +enum { + WHINT_MODE_OFF, /* not pass down write hints */ + WHINT_MODE_USER, /* try to pass down hints given by users */ + WHINT_MODE_FS, /* pass down hints with F2FS policy */ +}; + +enum { + ALLOC_MODE_DEFAULT, /* stay default */ + ALLOC_MODE_REUSE, /* reuse segments as much as possible */ +}; + +enum fsync_mode { + FSYNC_MODE_POSIX, /* fsync follows posix semantics */ + FSYNC_MODE_STRICT, /* fsync behaves in line with ext4 */ +}; + +#ifdef CONFIG_F2FS_FS_ENCRYPTION +#define DUMMY_ENCRYPTION_ENABLED(sbi) \ + (unlikely(F2FS_OPTION(sbi).test_dummy_encryption)) +#else +#define DUMMY_ENCRYPTION_ENABLED(sbi) (0) +#endif + struct f2fs_sb_info { struct super_block *sb; /* pointer to VFS super block */ struct proc_dir_entry *s_proc; /* proc entry */ struct f2fs_super_block *raw_super; /* raw super block pointer */ + struct rw_semaphore sb_lock; /* lock for raw super block */ int valid_super_block; /* valid super block no */ unsigned long s_flag; /* flags for sbi */ @@ -1060,7 +1113,6 @@ struct f2fs_sb_info { struct f2fs_bio_info *write_io[NR_PAGE_TYPE]; /* for write bios */ struct mutex wio_mutex[NR_PAGE_TYPE - 1][NR_TEMP_TYPE]; /* bio ordering for NODE/DATA */ - int write_io_size_bits; /* Write IO size bits */ mempool_t *write_io_dummy; /* Dummy pages */ /* for checkpoint */ @@ -1110,9 +1162,7 @@ struct f2fs_sb_info { unsigned int total_node_count; /* total node block count */ unsigned int total_valid_node_count; /* valid node block count */ loff_t max_file_blocks; /* max block index of file */ - int active_logs; /* # of active logs */ int dir_level; /* directory level */ - int inline_xattr_size; /* inline xattr size */ unsigned int trigger_ssr_threshold; /* threshold to trigger ssr */ int readdir_ra; /* readahead inode in readdir */ @@ -1122,9 +1172,6 @@ struct f2fs_sb_info { block_t last_valid_block_count; /* for recovery */ block_t reserved_blocks; /* configurable reserved blocks */ block_t current_reserved_blocks; /* current reserved blocks */ - block_t root_reserved_blocks; /* root reserved blocks */ - kuid_t s_resuid; /* reserved blocks for uid */ - kgid_t s_resgid; /* reserved blocks for gid */ unsigned int nquota_files; /* # of quota sysfile */ @@ -1209,17 +1256,6 @@ struct f2fs_sb_info { /* Precomputed FS UUID checksum for seeding other checksums */ __u32 s_chksum_seed; - - /* For fault injection */ -#ifdef CONFIG_F2FS_FAULT_INJECTION - struct f2fs_fault_info fault_info; -#endif - -#ifdef CONFIG_QUOTA - /* Names of quota files with journalled quota */ - char *s_qf_names[MAXQUOTAS]; - int s_jquota_fmt; /* Format of quota to use */ -#endif }; #ifdef CONFIG_F2FS_FAULT_INJECTION @@ -1229,7 +1265,7 @@ struct f2fs_sb_info { __func__, __builtin_return_address(0)) static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type) { - struct f2fs_fault_info *ffi = &sbi->fault_info; + struct f2fs_fault_info *ffi = &F2FS_OPTION(sbi).fault_info; if (!ffi->inject_rate) return false; @@ -1586,13 +1622,13 @@ static inline bool __allow_reserved_blocks(struct f2fs_sb_info *sbi, return false; if (IS_NOQUOTA(inode)) return true; + if (uid_eq(F2FS_OPTION(sbi).s_resuid, current_fsuid())) + return true; + if (!gid_eq(F2FS_OPTION(sbi).s_resgid, GLOBAL_ROOT_GID) && + in_group_p(F2FS_OPTION(sbi).s_resgid)) + return true; if (capable(CAP_SYS_RESOURCE)) return true; - if (uid_eq(sbi->s_resuid, current_fsuid())) - return true; - if (!gid_eq(sbi->s_resgid, GLOBAL_ROOT_GID) && - in_group_p(sbi->s_resgid)) - return true; return false; } @@ -1627,7 +1663,7 @@ static inline int inc_valid_block_count(struct f2fs_sb_info *sbi, sbi->current_reserved_blocks; if (!__allow_reserved_blocks(sbi, inode)) - avail_user_block_count -= sbi->root_reserved_blocks; + avail_user_block_count -= F2FS_OPTION(sbi).root_reserved_blocks; if (unlikely(sbi->total_valid_block_count > avail_user_block_count)) { diff = sbi->total_valid_block_count - avail_user_block_count; @@ -1762,6 +1798,12 @@ static inline void *__bitmap_ptr(struct f2fs_sb_info *sbi, int flag) struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); int offset; + if (is_set_ckpt_flags(sbi, CP_LARGE_NAT_BITMAP_FLAG)) { + offset = (flag == SIT_BITMAP) ? + le32_to_cpu(ckpt->nat_ver_bitmap_bytesize) : 0; + return &ckpt->sit_nat_version_bitmap + offset; + } + if (__cp_payload(sbi) > 0) { if (flag == NAT_BITMAP) return &ckpt->sit_nat_version_bitmap; @@ -1828,7 +1870,7 @@ static inline int inc_valid_node_count(struct f2fs_sb_info *sbi, sbi->current_reserved_blocks + 1; if (!__allow_reserved_blocks(sbi, inode)) - valid_block_count += sbi->root_reserved_blocks; + valid_block_count += F2FS_OPTION(sbi).root_reserved_blocks; if (unlikely(valid_block_count > sbi->user_block_count)) { spin_unlock(&sbi->stat_lock); @@ -2399,12 +2441,6 @@ static inline int f2fs_has_inline_dentry(struct inode *inode) return is_inode_flag_set(inode, FI_INLINE_DENTRY); } -static inline void f2fs_dentry_kunmap(struct inode *dir, struct page *page) -{ - if (!f2fs_has_inline_dentry(dir)) - kunmap(page); -} - static inline int is_file(struct inode *inode, int type) { return F2FS_I(inode)->i_advise & type; @@ -2436,7 +2472,17 @@ static inline bool f2fs_skip_inode_update(struct inode *inode, int dsync) } if (!is_inode_flag_set(inode, FI_AUTO_RECOVER) || file_keep_isize(inode) || - i_size_read(inode) & PAGE_MASK) + i_size_read(inode) & ~PAGE_MASK) + return false; + + if (!timespec_equal(F2FS_I(inode)->i_disk_time, &inode->i_atime)) + return false; + if (!timespec_equal(F2FS_I(inode)->i_disk_time + 1, &inode->i_ctime)) + return false; + if (!timespec_equal(F2FS_I(inode)->i_disk_time + 2, &inode->i_mtime)) + return false; + if (!timespec_equal(F2FS_I(inode)->i_disk_time + 3, + &F2FS_I(inode)->i_crtime)) return false; down_read(&F2FS_I(inode)->i_sem); @@ -2446,9 +2492,9 @@ static inline bool f2fs_skip_inode_update(struct inode *inode, int dsync) return ret; } -static inline int f2fs_readonly(struct super_block *sb) +static inline bool f2fs_readonly(struct super_block *sb) { - return sb->s_flags & SB_RDONLY; + return sb_rdonly(sb); } static inline bool f2fs_cp_error(struct f2fs_sb_info *sbi) @@ -2596,6 +2642,8 @@ void handle_failed_inode(struct inode *inode); /* * namei.c */ +int update_extension_list(struct f2fs_sb_info *sbi, const char *name, + bool hot, bool set); struct dentry *f2fs_get_parent(struct dentry *child); /* @@ -2768,6 +2816,8 @@ void destroy_segment_manager(struct f2fs_sb_info *sbi); int __init create_segment_manager_caches(void); void destroy_segment_manager_caches(void); int rw_hint_to_seg_type(enum rw_hint hint); +enum rw_hint io_type_to_rw_hint(struct f2fs_sb_info *sbi, enum page_type type, + enum temp_type temp); /* * checkpoint.c @@ -2850,6 +2900,7 @@ int f2fs_release_page(struct page *page, gfp_t wait); int f2fs_migrate_page(struct address_space *mapping, struct page *newpage, struct page *page, enum migrate_mode mode); #endif +bool f2fs_overwrite_io(struct inode *inode, loff_t pos, size_t len); /* * gc.c @@ -3172,45 +3223,21 @@ static inline bool f2fs_bio_encrypted(struct bio *bio) return bio->bi_private != NULL; } -static inline int f2fs_sb_has_crypto(struct super_block *sb) -{ - return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_ENCRYPT); +#define F2FS_FEATURE_FUNCS(name, flagname) \ +static inline int f2fs_sb_has_##name(struct super_block *sb) \ +{ \ + return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_##flagname); \ } -static inline int f2fs_sb_mounted_blkzoned(struct super_block *sb) -{ - return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_BLKZONED); -} - -static inline int f2fs_sb_has_extra_attr(struct super_block *sb) -{ - return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_EXTRA_ATTR); -} - -static inline int f2fs_sb_has_project_quota(struct super_block *sb) -{ - return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_PRJQUOTA); -} - -static inline int f2fs_sb_has_inode_chksum(struct super_block *sb) -{ - return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_INODE_CHKSUM); -} - -static inline int f2fs_sb_has_flexible_inline_xattr(struct super_block *sb) -{ - return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_FLEXIBLE_INLINE_XATTR); -} - -static inline int f2fs_sb_has_quota_ino(struct super_block *sb) -{ - return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_QUOTA_INO); -} - -static inline int f2fs_sb_has_inode_crtime(struct super_block *sb) -{ - return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_INODE_CRTIME); -} +F2FS_FEATURE_FUNCS(encrypt, ENCRYPT); +F2FS_FEATURE_FUNCS(blkzoned, BLKZONED); +F2FS_FEATURE_FUNCS(extra_attr, EXTRA_ATTR); +F2FS_FEATURE_FUNCS(project_quota, PRJQUOTA); +F2FS_FEATURE_FUNCS(inode_chksum, INODE_CHKSUM); +F2FS_FEATURE_FUNCS(flexible_inline_xattr, FLEXIBLE_INLINE_XATTR); +F2FS_FEATURE_FUNCS(quota_ino, QUOTA_INO); +F2FS_FEATURE_FUNCS(inode_crtime, INODE_CRTIME); +F2FS_FEATURE_FUNCS(lost_found, LOST_FOUND); #ifdef CONFIG_BLK_DEV_ZONED static inline int get_blkz_type(struct f2fs_sb_info *sbi, @@ -3230,7 +3257,7 @@ static inline bool f2fs_discard_en(struct f2fs_sb_info *sbi) { struct request_queue *q = bdev_get_queue(sbi->sb->s_bdev); - return blk_queue_discard(q) || f2fs_sb_mounted_blkzoned(sbi->sb); + return blk_queue_discard(q) || f2fs_sb_has_blkzoned(sbi->sb); } static inline void set_opt_mode(struct f2fs_sb_info *sbi, unsigned int mt) @@ -3259,4 +3286,11 @@ static inline bool f2fs_may_encrypt(struct inode *inode) #endif } +static inline bool f2fs_force_buffered_io(struct inode *inode, int rw) +{ + return (f2fs_encrypted_file(inode) || + (rw == WRITE && test_opt(F2FS_I_SB(inode), LFS)) || + F2FS_I_SB(inode)->s_ndevs); +} + #endif diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 672a542e5464..6b94f19b3fa8 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -163,9 +163,10 @@ static inline enum cp_reason_type need_do_checkpoint(struct inode *inode) cp_reason = CP_NODE_NEED_CP; else if (test_opt(sbi, FASTBOOT)) cp_reason = CP_FASTBOOT_MODE; - else if (sbi->active_logs == 2) + else if (F2FS_OPTION(sbi).active_logs == 2) cp_reason = CP_SPEC_LOG_NUM; - else if (need_dentry_mark(sbi, inode->i_ino) && + else if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT && + need_dentry_mark(sbi, inode->i_ino) && exist_written_data(sbi, F2FS_I(inode)->i_pino, TRANS_DIR_INO)) cp_reason = CP_RECOVER_DIR; @@ -479,6 +480,9 @@ static int f2fs_file_open(struct inode *inode, struct file *filp) if (err) return err; + + filp->f_mode |= FMODE_NOWAIT; + return dquot_file_open(inode, filp); } @@ -569,7 +573,6 @@ truncate_out: int truncate_blocks(struct inode *inode, u64 from, bool lock) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - unsigned int blocksize = inode->i_sb->s_blocksize; struct dnode_of_data dn; pgoff_t free_from; int count = 0, err = 0; @@ -578,7 +581,7 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock) trace_f2fs_truncate_blocks_enter(inode, from); - free_from = (pgoff_t)F2FS_BYTES_TO_BLK(from + blocksize - 1); + free_from = (pgoff_t)F2FS_BLK_ALIGN(from); if (free_from >= sbi->max_file_blocks) goto free_partial; @@ -1348,8 +1351,12 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len, } out: - if (!(mode & FALLOC_FL_KEEP_SIZE) && i_size_read(inode) < new_size) - f2fs_i_size_write(inode, new_size); + if (new_size > i_size_read(inode)) { + if (mode & FALLOC_FL_KEEP_SIZE) + file_set_keep_isize(inode); + else + f2fs_i_size_write(inode, new_size); + } out_sem: up_write(&F2FS_I(inode)->i_mmap_sem); @@ -1711,6 +1718,8 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp) inode_lock(inode); + down_write(&F2FS_I(inode)->dio_rwsem[WRITE]); + if (f2fs_is_volatile_file(inode)) goto err_out; @@ -1729,6 +1738,7 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp) ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 1, false); } err_out: + up_write(&F2FS_I(inode)->dio_rwsem[WRITE]); inode_unlock(inode); mnt_drop_write_file(filp); return ret; @@ -1938,7 +1948,7 @@ static int f2fs_ioc_set_encryption_policy(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); - if (!f2fs_sb_has_crypto(inode->i_sb)) + if (!f2fs_sb_has_encrypt(inode->i_sb)) return -EOPNOTSUPP; f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); @@ -1948,7 +1958,7 @@ static int f2fs_ioc_set_encryption_policy(struct file *filp, unsigned long arg) static int f2fs_ioc_get_encryption_policy(struct file *filp, unsigned long arg) { - if (!f2fs_sb_has_crypto(file_inode(filp)->i_sb)) + if (!f2fs_sb_has_encrypt(file_inode(filp)->i_sb)) return -EOPNOTSUPP; return fscrypt_ioctl_get_policy(filp, (void __user *)arg); } @@ -1959,16 +1969,18 @@ static int f2fs_ioc_get_encryption_pwsalt(struct file *filp, unsigned long arg) struct f2fs_sb_info *sbi = F2FS_I_SB(inode); int err; - if (!f2fs_sb_has_crypto(inode->i_sb)) + if (!f2fs_sb_has_encrypt(inode->i_sb)) return -EOPNOTSUPP; - if (uuid_is_nonzero(sbi->raw_super->encrypt_pw_salt)) - goto got_it; - err = mnt_want_write_file(filp); if (err) return err; + down_write(&sbi->sb_lock); + + if (uuid_is_nonzero(sbi->raw_super->encrypt_pw_salt)) + goto got_it; + /* update superblock with uuid */ generate_random_uuid(sbi->raw_super->encrypt_pw_salt); @@ -1976,15 +1988,16 @@ static int f2fs_ioc_get_encryption_pwsalt(struct file *filp, unsigned long arg) if (err) { /* undo new data */ memset(sbi->raw_super->encrypt_pw_salt, 0, 16); - mnt_drop_write_file(filp); - return err; + goto out_err; } - mnt_drop_write_file(filp); got_it: if (copy_to_user((__u8 __user *)arg, sbi->raw_super->encrypt_pw_salt, 16)) - return -EFAULT; - return 0; + err = -EFAULT; +out_err: + up_write(&sbi->sb_lock); + mnt_drop_write_file(filp); + return err; } static int f2fs_ioc_gc(struct file *filp, unsigned long arg) @@ -2045,8 +2058,10 @@ static int f2fs_ioc_gc_range(struct file *filp, unsigned long arg) return ret; end = range.start + range.len; - if (range.start < MAIN_BLKADDR(sbi) || end >= MAX_BLKADDR(sbi)) - return -EINVAL; + if (range.start < MAIN_BLKADDR(sbi) || end >= MAX_BLKADDR(sbi)) { + ret = -EINVAL; + goto out; + } do_more: if (!range.sync) { if (!mutex_trylock(&sbi->gc_mutex)) { @@ -2885,25 +2900,54 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) return -EIO; - inode_lock(inode); + if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT)) + return -EINVAL; + + if (!inode_trylock(inode)) { + if (iocb->ki_flags & IOCB_NOWAIT) + return -EAGAIN; + inode_lock(inode); + } + ret = generic_write_checks(iocb, from); if (ret > 0) { + bool preallocated = false; + size_t target_size = 0; int err; if (iov_iter_fault_in_readable(from, iov_iter_count(from))) set_inode_flag(inode, FI_NO_PREALLOC); - err = f2fs_preallocate_blocks(iocb, from); - if (err) { - clear_inode_flag(inode, FI_NO_PREALLOC); - inode_unlock(inode); - return err; + if ((iocb->ki_flags & IOCB_NOWAIT) && + (iocb->ki_flags & IOCB_DIRECT)) { + if (!f2fs_overwrite_io(inode, iocb->ki_pos, + iov_iter_count(from)) || + f2fs_has_inline_data(inode) || + f2fs_force_buffered_io(inode, WRITE)) { + inode_unlock(inode); + return -EAGAIN; + } + + } else { + preallocated = true; + target_size = iocb->ki_pos + iov_iter_count(from); + + err = f2fs_preallocate_blocks(iocb, from); + if (err) { + clear_inode_flag(inode, FI_NO_PREALLOC); + inode_unlock(inode); + return err; + } } blk_start_plug(&plug); ret = __generic_file_write_iter(iocb, from); blk_finish_plug(&plug); clear_inode_flag(inode, FI_NO_PREALLOC); + /* if we couldn't write data, we should deallocate blocks. */ + if (preallocated && i_size_read(inode) < target_size) + f2fs_truncate(inode); + if (ret > 0) f2fs_update_iostat(F2FS_I_SB(inode), APP_WRITE_IO, ret); } diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index aa720cc44509..bfb7a4a3a929 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -76,14 +76,15 @@ static int gc_thread_func(void *data) * invalidated soon after by user update or deletion. * So, I'd like to wait some time to collect dirty segments. */ - if (!mutex_trylock(&sbi->gc_mutex)) - goto next; - if (gc_th->gc_urgent) { wait_ms = gc_th->urgent_sleep_time; + mutex_lock(&sbi->gc_mutex); goto do_gc; } + if (!mutex_trylock(&sbi->gc_mutex)) + goto next; + if (!is_idle(sbi)) { increase_sleep_time(gc_th, &wait_ms); mutex_unlock(&sbi->gc_mutex); @@ -161,12 +162,17 @@ static int select_gc_type(struct f2fs_gc_kthread *gc_th, int gc_type) { int gc_mode = (gc_type == BG_GC) ? GC_CB : GC_GREEDY; - if (gc_th && gc_th->gc_idle) { + if (!gc_th) + return gc_mode; + + if (gc_th->gc_idle) { if (gc_th->gc_idle == 1) gc_mode = GC_CB; else if (gc_th->gc_idle == 2) gc_mode = GC_GREEDY; } + if (gc_th->gc_urgent) + gc_mode = GC_GREEDY; return gc_mode; } @@ -188,11 +194,14 @@ static void select_policy(struct f2fs_sb_info *sbi, int gc_type, } /* we need to check every dirty segments in the FG_GC case */ - if (gc_type != FG_GC && p->max_search > sbi->max_victim_search) + if (gc_type != FG_GC && + (sbi->gc_thread && !sbi->gc_thread->gc_urgent) && + p->max_search > sbi->max_victim_search) p->max_search = sbi->max_victim_search; - /* let's select beginning hot/small space first */ - if (type == CURSEG_HOT_DATA || IS_NODESEG(type)) + /* let's select beginning hot/small space first in no_heap mode*/ + if (test_opt(sbi, NOHEAP) && + (type == CURSEG_HOT_DATA || IS_NODESEG(type))) p->offset = 0; else p->offset = SIT_I(sbi)->last_victim[p->gc_mode]; diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index 90e38d8ea688..3b77d6421218 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -369,7 +369,7 @@ static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage, f2fs_wait_on_page_writeback(page, DATA, true); zero_user_segment(page, MAX_INLINE_DATA(dir), PAGE_SIZE); - dentry_blk = kmap_atomic(page); + dentry_blk = page_address(page); make_dentry_ptr_inline(dir, &src, inline_dentry); make_dentry_ptr_block(dir, &dst, dentry_blk); @@ -386,7 +386,6 @@ static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage, memcpy(dst.dentry, src.dentry, SIZE_OF_DIR_ENTRY * src.max); memcpy(dst.filename, src.filename, src.max * F2FS_SLOT_LEN); - kunmap_atomic(dentry_blk); if (!PageUptodate(page)) SetPageUptodate(page); set_page_dirty(page); diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 205add3d0f3a..e0d9e8f27ed2 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -284,6 +284,10 @@ static int do_read_inode(struct inode *inode) fi->i_crtime.tv_nsec = le32_to_cpu(ri->i_crtime_nsec); } + F2FS_I(inode)->i_disk_time[0] = inode->i_atime; + F2FS_I(inode)->i_disk_time[1] = inode->i_ctime; + F2FS_I(inode)->i_disk_time[2] = inode->i_mtime; + F2FS_I(inode)->i_disk_time[3] = F2FS_I(inode)->i_crtime; f2fs_put_page(node_page, 1); stat_inc_inline_xattr(inode); @@ -328,7 +332,7 @@ make_now: inode->i_op = &f2fs_dir_inode_operations; inode->i_fop = &f2fs_dir_operations; inode->i_mapping->a_ops = &f2fs_dblock_aops; - mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_HIGH_ZERO); + inode_nohighmem(inode); } else if (S_ISLNK(inode->i_mode)) { if (f2fs_encrypted_inode(inode)) inode->i_op = &f2fs_encrypted_symlink_inode_operations; @@ -439,12 +443,15 @@ void update_inode(struct inode *inode, struct page *node_page) } __set_inode_rdev(inode, ri); - set_cold_node(inode, node_page); /* deleted inode */ if (inode->i_nlink == 0) clear_inline_node(node_page); + F2FS_I(inode)->i_disk_time[0] = inode->i_atime; + F2FS_I(inode)->i_disk_time[1] = inode->i_ctime; + F2FS_I(inode)->i_disk_time[2] = inode->i_mtime; + F2FS_I(inode)->i_disk_time[3] = F2FS_I(inode)->i_crtime; } void update_inode_page(struct inode *inode) diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index b68e7b03959f..d5098efe577c 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -78,7 +78,8 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode) set_inode_flag(inode, FI_NEW_INODE); /* If the directory encrypted, then we should encrypt the inode. */ - if (f2fs_encrypted_inode(dir) && f2fs_may_encrypt(inode)) + if ((f2fs_encrypted_inode(dir) || DUMMY_ENCRYPTION_ENABLED(sbi)) && + f2fs_may_encrypt(inode)) f2fs_set_encrypted_inode(inode); if (f2fs_sb_has_extra_attr(sbi->sb)) { @@ -97,7 +98,7 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode) if (f2fs_sb_has_flexible_inline_xattr(sbi->sb)) { f2fs_bug_on(sbi, !f2fs_has_extra_attr(inode)); if (f2fs_has_inline_xattr(inode)) - xattr_size = sbi->inline_xattr_size; + xattr_size = F2FS_OPTION(sbi).inline_xattr_size; /* Otherwise, will be 0 */ } else if (f2fs_has_inline_xattr(inode) || f2fs_has_inline_dentry(inode)) { @@ -142,7 +143,7 @@ fail_drop: return ERR_PTR(err); } -static int is_multimedia_file(const unsigned char *s, const char *sub) +static int is_extension_exist(const unsigned char *s, const char *sub) { size_t slen = strlen(s); size_t sublen = strlen(sub); @@ -168,19 +169,94 @@ static int is_multimedia_file(const unsigned char *s, const char *sub) /* * Set multimedia files as cold files for hot/cold data separation */ -static inline void set_cold_files(struct f2fs_sb_info *sbi, struct inode *inode, +static inline void set_file_temperature(struct f2fs_sb_info *sbi, struct inode *inode, const unsigned char *name) { - int i; - __u8 (*extlist)[8] = sbi->raw_super->extension_list; + __u8 (*extlist)[F2FS_EXTENSION_LEN] = sbi->raw_super->extension_list; + int i, cold_count, hot_count; - int count = le32_to_cpu(sbi->raw_super->extension_count); - for (i = 0; i < count; i++) { - if (is_multimedia_file(name, extlist[i])) { + down_read(&sbi->sb_lock); + + cold_count = le32_to_cpu(sbi->raw_super->extension_count); + hot_count = sbi->raw_super->hot_ext_count; + + for (i = 0; i < cold_count + hot_count; i++) { + if (!is_extension_exist(name, extlist[i])) + continue; + if (i < cold_count) file_set_cold(inode); - break; - } + else + file_set_hot(inode); + break; } + + up_read(&sbi->sb_lock); +} + +int update_extension_list(struct f2fs_sb_info *sbi, const char *name, + bool hot, bool set) +{ + __u8 (*extlist)[F2FS_EXTENSION_LEN] = sbi->raw_super->extension_list; + int cold_count = le32_to_cpu(sbi->raw_super->extension_count); + int hot_count = sbi->raw_super->hot_ext_count; + int total_count = cold_count + hot_count; + int start, count; + int i; + + if (set) { + if (total_count == F2FS_MAX_EXTENSION) + return -EINVAL; + } else { + if (!hot && !cold_count) + return -EINVAL; + if (hot && !hot_count) + return -EINVAL; + } + + if (hot) { + start = cold_count; + count = total_count; + } else { + start = 0; + count = cold_count; + } + + for (i = start; i < count; i++) { + if (strcmp(name, extlist[i])) + continue; + + if (set) + return -EINVAL; + + memcpy(extlist[i], extlist[i + 1], + F2FS_EXTENSION_LEN * (total_count - i - 1)); + memset(extlist[total_count - 1], 0, F2FS_EXTENSION_LEN); + if (hot) + sbi->raw_super->hot_ext_count = hot_count - 1; + else + sbi->raw_super->extension_count = + cpu_to_le32(cold_count - 1); + return 0; + } + + if (!set) + return -EINVAL; + + if (hot) { + strncpy(extlist[count], name, strlen(name)); + sbi->raw_super->hot_ext_count = hot_count + 1; + } else { + char buf[F2FS_MAX_EXTENSION][F2FS_EXTENSION_LEN]; + + memcpy(buf, &extlist[cold_count], + F2FS_EXTENSION_LEN * hot_count); + memset(extlist[cold_count], 0, F2FS_EXTENSION_LEN); + strncpy(extlist[cold_count], name, strlen(name)); + memcpy(&extlist[cold_count + 1], buf, + F2FS_EXTENSION_LEN * hot_count); + sbi->raw_super->extension_count = cpu_to_le32(cold_count + 1); + } + return 0; } static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode, @@ -203,7 +279,7 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode, return PTR_ERR(inode); if (!test_opt(sbi, DISABLE_EXT_IDENTIFY)) - set_cold_files(sbi, inode, dentry->d_name.name); + set_file_temperature(sbi, inode, dentry->d_name.name); inode->i_op = &f2fs_file_inode_operations; inode->i_fop = &f2fs_file_operations; @@ -317,7 +393,6 @@ static int __recover_dot_dentries(struct inode *dir, nid_t pino) de = f2fs_find_entry(dir, &dot, &page); if (de) { - f2fs_dentry_kunmap(dir, page); f2fs_put_page(page, 0); } else if (IS_ERR(page)) { err = PTR_ERR(page); @@ -329,14 +404,12 @@ static int __recover_dot_dentries(struct inode *dir, nid_t pino) } de = f2fs_find_entry(dir, &dotdot, &page); - if (de) { - f2fs_dentry_kunmap(dir, page); + if (de) f2fs_put_page(page, 0); - } else if (IS_ERR(page)) { + else if (IS_ERR(page)) err = PTR_ERR(page); - } else { + else err = __f2fs_add_link(dir, &dotdot, NULL, pino, S_IFDIR); - } out: if (!err) clear_inode_flag(dir, FI_INLINE_DOTS); @@ -377,7 +450,6 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry, } ino = le32_to_cpu(de->ino); - f2fs_dentry_kunmap(dir, page); f2fs_put_page(page, 0); inode = f2fs_iget(dir->i_sb, ino); @@ -452,7 +524,6 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry) err = acquire_orphan_inode(sbi); if (err) { f2fs_unlock_op(sbi); - f2fs_dentry_kunmap(dir, page); f2fs_put_page(page, 0); goto fail; } @@ -579,7 +650,7 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) inode->i_op = &f2fs_dir_inode_operations; inode->i_fop = &f2fs_dir_operations; inode->i_mapping->a_ops = &f2fs_dblock_aops; - mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_HIGH_ZERO); + inode_nohighmem(inode); set_inode_flag(inode, FI_INC_LINK); f2fs_lock_op(sbi); @@ -717,10 +788,12 @@ out: static int f2fs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) { - if (unlikely(f2fs_cp_error(F2FS_I_SB(dir)))) + struct f2fs_sb_info *sbi = F2FS_I_SB(dir); + + if (unlikely(f2fs_cp_error(sbi))) return -EIO; - if (f2fs_encrypted_inode(dir)) { + if (f2fs_encrypted_inode(dir) || DUMMY_ENCRYPTION_ENABLED(sbi)) { int err = fscrypt_get_encryption_info(dir); if (err) return err; @@ -893,16 +966,15 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, } if (old_dir_entry) { - if (old_dir != new_dir && !whiteout) { + if (old_dir != new_dir && !whiteout) f2fs_set_link(old_inode, old_dir_entry, old_dir_page, new_dir); - } else { - f2fs_dentry_kunmap(old_inode, old_dir_page); + else f2fs_put_page(old_dir_page, 0); - } f2fs_i_links_write(old_dir, false); } - add_ino_entry(sbi, new_dir->i_ino, TRANS_DIR_INO); + if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT) + add_ino_entry(sbi, new_dir->i_ino, TRANS_DIR_INO); f2fs_unlock_op(sbi); @@ -912,20 +984,15 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, put_out_dir: f2fs_unlock_op(sbi); - if (new_page) { - f2fs_dentry_kunmap(new_dir, new_page); + if (new_page) f2fs_put_page(new_page, 0); - } out_whiteout: if (whiteout) iput(whiteout); out_dir: - if (old_dir_entry) { - f2fs_dentry_kunmap(old_inode, old_dir_page); + if (old_dir_entry) f2fs_put_page(old_dir_page, 0); - } out_old: - f2fs_dentry_kunmap(old_dir, old_page); f2fs_put_page(old_page, 0); out: return err; @@ -1057,8 +1124,10 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, } f2fs_mark_inode_dirty_sync(new_dir, false); - add_ino_entry(sbi, old_dir->i_ino, TRANS_DIR_INO); - add_ino_entry(sbi, new_dir->i_ino, TRANS_DIR_INO); + if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT) { + add_ino_entry(sbi, old_dir->i_ino, TRANS_DIR_INO); + add_ino_entry(sbi, new_dir->i_ino, TRANS_DIR_INO); + } f2fs_unlock_op(sbi); @@ -1067,19 +1136,15 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, return 0; out_new_dir: if (new_dir_entry) { - f2fs_dentry_kunmap(new_inode, new_dir_page); f2fs_put_page(new_dir_page, 0); } out_old_dir: if (old_dir_entry) { - f2fs_dentry_kunmap(old_inode, old_dir_page); f2fs_put_page(old_dir_page, 0); } out_new: - f2fs_dentry_kunmap(new_dir, new_page); f2fs_put_page(new_page, 0); out_old: - f2fs_dentry_kunmap(old_dir, old_page); f2fs_put_page(old_page, 0); out: return err; diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 177c438e4a56..9a99243054ba 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -193,8 +193,8 @@ static void __del_from_nat_cache(struct f2fs_nm_info *nm_i, struct nat_entry *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; @@ -209,15 +209,36 @@ 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) + if (new_ne) list_del_init(&ne->list); else list_move_tail(&ne->list, &head->entry_list); @@ -1076,7 +1097,7 @@ struct page *new_node_page(struct dnode_of_data *dn, unsigned int ofs) f2fs_wait_on_page_writeback(page, NODE, true); fill_node_footer(page, dn->nid, dn->inode->i_ino, ofs, true); - set_cold_node(dn->inode, page); + set_cold_node(page, S_ISDIR(dn->inode->i_mode)); if (!PageUptodate(page)) SetPageUptodate(page); if (set_page_dirty(page)) @@ -2291,6 +2312,7 @@ retry: if (!PageUptodate(ipage)) SetPageUptodate(ipage); fill_node_footer(ipage, ino, ino, 0, true); + set_cold_node(page, false); src = F2FS_INODE(page); dst = F2FS_INODE(ipage); @@ -2580,8 +2602,7 @@ 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_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) @@ -2707,12 +2728,20 @@ 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 = f2fs_kvzalloc(sbi, nm_i->nat_blocks * - NAT_ENTRY_BITMAP_SIZE, GFP_KERNEL); + nm_i->free_nid_bitmap = f2fs_kzalloc(sbi, nm_i->nat_blocks * + sizeof(unsigned char *), GFP_KERNEL); if (!nm_i->free_nid_bitmap) return -ENOMEM; + for (i = 0; i < nm_i->nat_blocks; i++) { + nm_i->free_nid_bitmap[i] = f2fs_kvzalloc(sbi, + NAT_ENTRY_BITMAP_SIZE_ALIGNED, GFP_KERNEL); + if (!nm_i->free_nid_bitmap) + return -ENOMEM; + } + nm_i->nat_block_bitmap = f2fs_kvzalloc(sbi, nm_i->nat_blocks / 8, GFP_KERNEL); if (!nm_i->nat_block_bitmap) @@ -2803,7 +2832,13 @@ 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]); + kfree(nm_i->free_nid_bitmap); + } kvfree(nm_i->free_nid_count); kfree(nm_i->nat_bitmap); diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h index 081ef0d672bf..b95e49e4a928 100644 --- a/fs/f2fs/node.h +++ b/fs/f2fs/node.h @@ -44,6 +44,7 @@ enum { HAS_FSYNCED_INODE, /* is the inode fsynced before? */ HAS_LAST_FSYNC, /* has the latest node fsync mark? */ IS_DIRTY, /* this nat entry is dirty? */ + IS_PREALLOC, /* nat entry is preallocated */ }; /* @@ -422,12 +423,12 @@ static inline void clear_inline_node(struct page *page) ClearPageChecked(page); } -static inline void set_cold_node(struct inode *inode, struct page *page) +static inline void set_cold_node(struct page *page, bool is_dir) { struct f2fs_node *rn = F2FS_NODE(page); unsigned int flag = le32_to_cpu(rn->footer.flag); - if (S_ISDIR(inode->i_mode)) + if (is_dir) flag &= ~(0x1 << COLD_BIT_SHIFT); else flag |= (0x1 << COLD_BIT_SHIFT); diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index 337f3363f48f..1b23d3febe4c 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -144,7 +144,7 @@ static int recover_dentry(struct inode *inode, struct page *ipage, retry: de = __f2fs_find_entry(dir, &fname, &page); if (de && inode->i_ino == le32_to_cpu(de->ino)) - goto out_unmap_put; + goto out_put; if (de) { einode = f2fs_iget_retry(inode->i_sb, le32_to_cpu(de->ino)); @@ -153,19 +153,19 @@ retry: err = PTR_ERR(einode); if (err == -ENOENT) err = -EEXIST; - goto out_unmap_put; + goto out_put; } err = dquot_initialize(einode); if (err) { iput(einode); - goto out_unmap_put; + goto out_put; } err = acquire_orphan_inode(F2FS_I_SB(inode)); if (err) { iput(einode); - goto out_unmap_put; + goto out_put; } f2fs_delete_entry(de, page, dir, einode); iput(einode); @@ -180,8 +180,7 @@ retry: goto retry; goto out; -out_unmap_put: - f2fs_dentry_kunmap(dir, page); +out_put: f2fs_put_page(page, 0); out: if (file_enc_name(inode)) @@ -243,6 +242,9 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head, struct curseg_info *curseg; struct page *page = NULL; block_t blkaddr; + unsigned int loop_cnt = 0; + unsigned int free_blocks = sbi->user_block_count - + valid_user_blocks(sbi); int err = 0; /* get node pages in the current segment */ @@ -295,6 +297,17 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head, if (IS_INODE(page) && is_dent_dnode(page)) entry->last_dentry = blkaddr; next: + /* sanity check in order to detect looped node chain */ + if (++loop_cnt >= free_blocks || + blkaddr == next_blkaddr_of_node(page)) { + f2fs_msg(sbi->sb, KERN_NOTICE, + "%s: detect looped node chain, " + "blkaddr:%u, next:%u", + __func__, blkaddr, next_blkaddr_of_node(page)); + err = -EINVAL; + break; + } + /* check next segment */ blkaddr = next_blkaddr_of_node(page); f2fs_put_page(page, 1); diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index b16a8e6625aa..5854cc4e1d67 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -1411,12 +1411,11 @@ static int issue_discard_thread(void *data) if (kthread_should_stop()) return 0; - if (dcc->discard_wake) { + if (dcc->discard_wake) dcc->discard_wake = 0; - if (sbi->gc_thread && sbi->gc_thread->gc_urgent) - init_discard_policy(&dpolicy, - DPOLICY_FORCE, 1); - } + + if (sbi->gc_thread && sbi->gc_thread->gc_urgent) + init_discard_policy(&dpolicy, DPOLICY_FORCE, 1); sb_start_intwrite(sbi->sb); @@ -1485,7 +1484,7 @@ static int __issue_discard_async(struct f2fs_sb_info *sbi, struct block_device *bdev, block_t blkstart, block_t blklen) { #ifdef CONFIG_BLK_DEV_ZONED - if (f2fs_sb_mounted_blkzoned(sbi->sb) && + if (f2fs_sb_has_blkzoned(sbi->sb) && bdev_zoned_model(bdev) != BLK_ZONED_NONE) return __f2fs_issue_discard_zone(sbi, bdev, blkstart, blklen); #endif @@ -1683,7 +1682,7 @@ find_next: sbi->blocks_per_seg, cur_pos); len = next_pos - cur_pos; - if (f2fs_sb_mounted_blkzoned(sbi->sb) || + if (f2fs_sb_has_blkzoned(sbi->sb) || (force && len < cpc->trim_minlen)) goto skip; @@ -1727,7 +1726,7 @@ void init_discard_policy(struct discard_policy *dpolicy, } else if (discard_type == DPOLICY_FORCE) { dpolicy->min_interval = DEF_MIN_DISCARD_ISSUE_TIME; dpolicy->max_interval = DEF_MAX_DISCARD_ISSUE_TIME; - dpolicy->io_aware = true; + dpolicy->io_aware = false; } else if (discard_type == DPOLICY_FSTRIM) { dpolicy->io_aware = false; } else if (discard_type == DPOLICY_UMOUNT) { @@ -1863,7 +1862,7 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del) sbi->discard_blks--; /* don't overwrite by SSR to keep node chain */ - if (se->type == CURSEG_WARM_NODE) { + if (IS_NODESEG(se->type)) { if (!f2fs_test_and_set_bit(offset, se->ckpt_valid_map)) se->ckpt_valid_blocks++; } @@ -2164,11 +2163,17 @@ static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type) if (sbi->segs_per_sec != 1) return CURSEG_I(sbi, type)->segno; - if (type == CURSEG_HOT_DATA || IS_NODESEG(type)) + if (test_opt(sbi, NOHEAP) && + (type == CURSEG_HOT_DATA || IS_NODESEG(type))) return 0; if (SIT_I(sbi)->last_victim[ALLOC_NEXT]) return SIT_I(sbi)->last_victim[ALLOC_NEXT]; + + /* find segments from 0 to reuse freed segments */ + if (F2FS_OPTION(sbi).alloc_mode == ALLOC_MODE_REUSE) + return 0; + return CURSEG_I(sbi, type)->segno; } @@ -2455,6 +2460,101 @@ int rw_hint_to_seg_type(enum rw_hint hint) } } +/* This returns write hints for each segment type. This hints will be + * passed down to block layer. There are mapping tables which depend on + * the mount option 'whint_mode'. + * + * 1) whint_mode=off. F2FS only passes down WRITE_LIFE_NOT_SET. + * + * 2) whint_mode=user-based. F2FS tries to pass down hints given by users. + * + * User F2FS Block + * ---- ---- ----- + * META WRITE_LIFE_NOT_SET + * HOT_NODE " + * WARM_NODE " + * COLD_NODE " + * ioctl(COLD) COLD_DATA WRITE_LIFE_EXTREME + * extension list " " + * + * -- buffered io + * WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME + * WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT + * WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET + * WRITE_LIFE_NONE " " + * WRITE_LIFE_MEDIUM " " + * WRITE_LIFE_LONG " " + * + * -- direct io + * WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME + * WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT + * WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET + * WRITE_LIFE_NONE " WRITE_LIFE_NONE + * WRITE_LIFE_MEDIUM " WRITE_LIFE_MEDIUM + * WRITE_LIFE_LONG " WRITE_LIFE_LONG + * + * 3) whint_mode=fs-based. F2FS passes down hints with its policy. + * + * User F2FS Block + * ---- ---- ----- + * META WRITE_LIFE_MEDIUM; + * HOT_NODE WRITE_LIFE_NOT_SET + * WARM_NODE " + * COLD_NODE WRITE_LIFE_NONE + * ioctl(COLD) COLD_DATA WRITE_LIFE_EXTREME + * extension list " " + * + * -- buffered io + * WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME + * WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT + * WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_LONG + * WRITE_LIFE_NONE " " + * WRITE_LIFE_MEDIUM " " + * WRITE_LIFE_LONG " " + * + * -- direct io + * WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME + * WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT + * WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET + * WRITE_LIFE_NONE " WRITE_LIFE_NONE + * WRITE_LIFE_MEDIUM " WRITE_LIFE_MEDIUM + * WRITE_LIFE_LONG " WRITE_LIFE_LONG + */ + +enum rw_hint io_type_to_rw_hint(struct f2fs_sb_info *sbi, + enum page_type type, enum temp_type temp) +{ + if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_USER) { + if (type == DATA) { + if (temp == WARM) + return WRITE_LIFE_NOT_SET; + else if (temp == HOT) + return WRITE_LIFE_SHORT; + else if (temp == COLD) + return WRITE_LIFE_EXTREME; + } else { + return WRITE_LIFE_NOT_SET; + } + } else if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_FS) { + if (type == DATA) { + if (temp == WARM) + return WRITE_LIFE_LONG; + else if (temp == HOT) + return WRITE_LIFE_SHORT; + else if (temp == COLD) + return WRITE_LIFE_EXTREME; + } else if (type == NODE) { + if (temp == WARM || temp == HOT) + return WRITE_LIFE_NOT_SET; + else if (temp == COLD) + return WRITE_LIFE_NONE; + } else if (type == META) { + return WRITE_LIFE_MEDIUM; + } + } + return WRITE_LIFE_NOT_SET; +} + static int __get_segment_type_2(struct f2fs_io_info *fio) { if (fio->type == DATA) @@ -2487,7 +2587,8 @@ static int __get_segment_type_6(struct f2fs_io_info *fio) if (is_cold_data(fio->page) || file_is_cold(inode)) return CURSEG_COLD_DATA; - if (is_inode_flag_set(inode, FI_HOT_DATA)) + if (file_is_hot(inode) || + is_inode_flag_set(inode, FI_HOT_DATA)) return CURSEG_HOT_DATA; return rw_hint_to_seg_type(inode->i_write_hint); } else { @@ -2502,7 +2603,7 @@ static int __get_segment_type(struct f2fs_io_info *fio) { int type = 0; - switch (fio->sbi->active_logs) { + switch (F2FS_OPTION(fio->sbi).active_logs) { case 2: type = __get_segment_type_2(fio); break; @@ -2642,6 +2743,7 @@ void write_meta_page(struct f2fs_sb_info *sbi, struct page *page, struct f2fs_io_info fio = { .sbi = sbi, .type = META, + .temp = HOT, .op = REQ_OP_WRITE, .op_flags = REQ_SYNC | REQ_META | REQ_PRIO, .old_blkaddr = page->index, @@ -2688,8 +2790,15 @@ void write_data_page(struct dnode_of_data *dn, struct f2fs_io_info *fio) int rewrite_data_page(struct f2fs_io_info *fio) { int err; + struct f2fs_sb_info *sbi = fio->sbi; fio->new_blkaddr = fio->old_blkaddr; + /* i/o temperature is needed for passing down write hints */ + __get_segment_type(fio); + + f2fs_bug_on(sbi, !IS_DATASEG(get_seg_entry(sbi, + GET_SEGNO(sbi, fio->new_blkaddr))->type)); + stat_inc_inplace_blocks(fio->sbi); err = f2fs_submit_page_bio(fio); diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index f11c4bc82c78..3325d0769723 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -53,13 +53,19 @@ ((secno) == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno / \ (sbi)->segs_per_sec)) \ -#define MAIN_BLKADDR(sbi) (SM_I(sbi)->main_blkaddr) -#define SEG0_BLKADDR(sbi) (SM_I(sbi)->seg0_blkaddr) +#define MAIN_BLKADDR(sbi) \ + (SM_I(sbi) ? SM_I(sbi)->main_blkaddr : \ + le32_to_cpu(F2FS_RAW_SUPER(sbi)->main_blkaddr)) +#define SEG0_BLKADDR(sbi) \ + (SM_I(sbi) ? SM_I(sbi)->seg0_blkaddr : \ + le32_to_cpu(F2FS_RAW_SUPER(sbi)->segment0_blkaddr)) #define MAIN_SEGS(sbi) (SM_I(sbi)->main_segments) #define MAIN_SECS(sbi) ((sbi)->total_sections) -#define TOTAL_SEGS(sbi) (SM_I(sbi)->segment_count) +#define TOTAL_SEGS(sbi) \ + (SM_I(sbi) ? SM_I(sbi)->segment_count : \ + le32_to_cpu(F2FS_RAW_SUPER(sbi)->segment_count)) #define TOTAL_BLKS(sbi) (TOTAL_SEGS(sbi) << (sbi)->log_blocks_per_seg) #define MAX_BLKADDR(sbi) (SEG0_BLKADDR(sbi) + TOTAL_BLKS(sbi)) @@ -596,6 +602,8 @@ static inline int utilization(struct f2fs_sb_info *sbi) #define DEF_MIN_FSYNC_BLOCKS 8 #define DEF_MIN_HOT_BLOCKS 16 +#define SMALL_VOLUME_SEGMENTS (16 * 512) /* 16GB */ + enum { F2FS_IPU_FORCE, F2FS_IPU_SSR, @@ -630,10 +638,17 @@ static inline void check_seg_range(struct f2fs_sb_info *sbi, unsigned int segno) f2fs_bug_on(sbi, segno > TOTAL_SEGS(sbi) - 1); } -static inline void verify_block_addr(struct f2fs_sb_info *sbi, block_t blk_addr) +static inline void verify_block_addr(struct f2fs_io_info *fio, block_t blk_addr) { - BUG_ON(blk_addr < SEG0_BLKADDR(sbi) - || blk_addr >= MAX_BLKADDR(sbi)); + struct f2fs_sb_info *sbi = fio->sbi; + + if (PAGE_TYPE_OF_BIO(fio->type) == META && + (!is_read_io(fio->op) || fio->is_meta)) + BUG_ON(blk_addr < SEG0_BLKADDR(sbi) || + blk_addr >= MAIN_BLKADDR(sbi)); + else + BUG_ON(blk_addr < MAIN_BLKADDR(sbi) || + blk_addr >= MAX_BLKADDR(sbi)); } /* diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 8173ae688814..42d564c5ccd0 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -60,7 +60,7 @@ char *fault_name[FAULT_MAX] = { static void f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned int rate) { - struct f2fs_fault_info *ffi = &sbi->fault_info; + struct f2fs_fault_info *ffi = &F2FS_OPTION(sbi).fault_info; if (rate) { atomic_set(&ffi->inject_ops, 0); @@ -129,6 +129,10 @@ enum { Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, + Opt_whint, + Opt_alloc, + Opt_fsync, + Opt_test_dummy_encryption, Opt_err, }; @@ -182,6 +186,10 @@ static match_table_t f2fs_tokens = { {Opt_jqfmt_vfsold, "jqfmt=vfsold"}, {Opt_jqfmt_vfsv0, "jqfmt=vfsv0"}, {Opt_jqfmt_vfsv1, "jqfmt=vfsv1"}, + {Opt_whint, "whint_mode=%s"}, + {Opt_alloc, "alloc_mode=%s"}, + {Opt_fsync, "fsync_mode=%s"}, + {Opt_test_dummy_encryption, "test_dummy_encryption"}, {Opt_err, NULL}, }; @@ -202,21 +210,24 @@ static inline void limit_reserve_root(struct f2fs_sb_info *sbi) block_t limit = (sbi->user_block_count << 1) / 1000; /* limit is 0.2% */ - if (test_opt(sbi, RESERVE_ROOT) && sbi->root_reserved_blocks > limit) { - sbi->root_reserved_blocks = limit; + if (test_opt(sbi, RESERVE_ROOT) && + F2FS_OPTION(sbi).root_reserved_blocks > limit) { + F2FS_OPTION(sbi).root_reserved_blocks = limit; f2fs_msg(sbi->sb, KERN_INFO, "Reduce reserved blocks for root = %u", - sbi->root_reserved_blocks); + F2FS_OPTION(sbi).root_reserved_blocks); } if (!test_opt(sbi, RESERVE_ROOT) && - (!uid_eq(sbi->s_resuid, + (!uid_eq(F2FS_OPTION(sbi).s_resuid, make_kuid(&init_user_ns, F2FS_DEF_RESUID)) || - !gid_eq(sbi->s_resgid, + !gid_eq(F2FS_OPTION(sbi).s_resgid, make_kgid(&init_user_ns, F2FS_DEF_RESGID)))) f2fs_msg(sbi->sb, KERN_INFO, "Ignore s_resuid=%u, s_resgid=%u w/o reserve_root", - from_kuid_munged(&init_user_ns, sbi->s_resuid), - from_kgid_munged(&init_user_ns, sbi->s_resgid)); + from_kuid_munged(&init_user_ns, + F2FS_OPTION(sbi).s_resuid), + from_kgid_munged(&init_user_ns, + F2FS_OPTION(sbi).s_resgid)); } static void init_once(void *foo) @@ -236,7 +247,7 @@ static int f2fs_set_qf_name(struct super_block *sb, int qtype, char *qname; int ret = -EINVAL; - if (sb_any_quota_loaded(sb) && !sbi->s_qf_names[qtype]) { + if (sb_any_quota_loaded(sb) && !F2FS_OPTION(sbi).s_qf_names[qtype]) { f2fs_msg(sb, KERN_ERR, "Cannot change journaled " "quota options when quota turned on"); @@ -254,8 +265,8 @@ static int f2fs_set_qf_name(struct super_block *sb, int qtype, "Not enough memory for storing quotafile name"); return -EINVAL; } - if (sbi->s_qf_names[qtype]) { - if (strcmp(sbi->s_qf_names[qtype], qname) == 0) + if (F2FS_OPTION(sbi).s_qf_names[qtype]) { + if (strcmp(F2FS_OPTION(sbi).s_qf_names[qtype], qname) == 0) ret = 0; else f2fs_msg(sb, KERN_ERR, @@ -268,7 +279,7 @@ static int f2fs_set_qf_name(struct super_block *sb, int qtype, "quotafile must be on filesystem root"); goto errout; } - sbi->s_qf_names[qtype] = qname; + F2FS_OPTION(sbi).s_qf_names[qtype] = qname; set_opt(sbi, QUOTA); return 0; errout: @@ -280,13 +291,13 @@ static int f2fs_clear_qf_name(struct super_block *sb, int qtype) { struct f2fs_sb_info *sbi = F2FS_SB(sb); - if (sb_any_quota_loaded(sb) && sbi->s_qf_names[qtype]) { + if (sb_any_quota_loaded(sb) && F2FS_OPTION(sbi).s_qf_names[qtype]) { f2fs_msg(sb, KERN_ERR, "Cannot change journaled quota options" " when quota turned on"); return -EINVAL; } - kfree(sbi->s_qf_names[qtype]); - sbi->s_qf_names[qtype] = NULL; + kfree(F2FS_OPTION(sbi).s_qf_names[qtype]); + F2FS_OPTION(sbi).s_qf_names[qtype] = NULL; return 0; } @@ -302,15 +313,19 @@ static int f2fs_check_quota_options(struct f2fs_sb_info *sbi) "Cannot enable project quota enforcement."); return -1; } - if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA] || - sbi->s_qf_names[PRJQUOTA]) { - if (test_opt(sbi, USRQUOTA) && sbi->s_qf_names[USRQUOTA]) + if (F2FS_OPTION(sbi).s_qf_names[USRQUOTA] || + F2FS_OPTION(sbi).s_qf_names[GRPQUOTA] || + F2FS_OPTION(sbi).s_qf_names[PRJQUOTA]) { + if (test_opt(sbi, USRQUOTA) && + F2FS_OPTION(sbi).s_qf_names[USRQUOTA]) clear_opt(sbi, USRQUOTA); - if (test_opt(sbi, GRPQUOTA) && sbi->s_qf_names[GRPQUOTA]) + if (test_opt(sbi, GRPQUOTA) && + F2FS_OPTION(sbi).s_qf_names[GRPQUOTA]) clear_opt(sbi, GRPQUOTA); - if (test_opt(sbi, PRJQUOTA) && sbi->s_qf_names[PRJQUOTA]) + if (test_opt(sbi, PRJQUOTA) && + F2FS_OPTION(sbi).s_qf_names[PRJQUOTA]) clear_opt(sbi, PRJQUOTA); if (test_opt(sbi, GRPQUOTA) || test_opt(sbi, USRQUOTA) || @@ -320,19 +335,19 @@ static int f2fs_check_quota_options(struct f2fs_sb_info *sbi) return -1; } - if (!sbi->s_jquota_fmt) { + if (!F2FS_OPTION(sbi).s_jquota_fmt) { f2fs_msg(sbi->sb, KERN_ERR, "journaled quota format " "not specified"); return -1; } } - if (f2fs_sb_has_quota_ino(sbi->sb) && sbi->s_jquota_fmt) { + if (f2fs_sb_has_quota_ino(sbi->sb) && F2FS_OPTION(sbi).s_jquota_fmt) { f2fs_msg(sbi->sb, KERN_INFO, "QUOTA feature is enabled, so ignore jquota_fmt"); - sbi->s_jquota_fmt = 0; + F2FS_OPTION(sbi).s_jquota_fmt = 0; } - if (f2fs_sb_has_quota_ino(sbi->sb) && sb_rdonly(sbi->sb)) { + if (f2fs_sb_has_quota_ino(sbi->sb) && f2fs_readonly(sbi->sb)) { f2fs_msg(sbi->sb, KERN_INFO, "Filesystem with quota feature cannot be mounted RDWR " "without CONFIG_QUOTA"); @@ -403,14 +418,14 @@ static int parse_options(struct super_block *sb, char *options) q = bdev_get_queue(sb->s_bdev); if (blk_queue_discard(q)) { set_opt(sbi, DISCARD); - } else if (!f2fs_sb_mounted_blkzoned(sb)) { + } else if (!f2fs_sb_has_blkzoned(sb)) { f2fs_msg(sb, KERN_WARNING, "mounting with \"discard\" option, but " "the device does not support discard"); } break; case Opt_nodiscard: - if (f2fs_sb_mounted_blkzoned(sb)) { + if (f2fs_sb_has_blkzoned(sb)) { f2fs_msg(sb, KERN_WARNING, "discard is required for zoned block devices"); return -EINVAL; @@ -440,7 +455,7 @@ static int parse_options(struct super_block *sb, char *options) if (args->from && match_int(args, &arg)) return -EINVAL; set_opt(sbi, INLINE_XATTR_SIZE); - sbi->inline_xattr_size = arg; + F2FS_OPTION(sbi).inline_xattr_size = arg; break; #else case Opt_user_xattr: @@ -480,7 +495,7 @@ static int parse_options(struct super_block *sb, char *options) return -EINVAL; if (arg != 2 && arg != 4 && arg != NR_CURSEG_TYPE) return -EINVAL; - sbi->active_logs = arg; + F2FS_OPTION(sbi).active_logs = arg; break; case Opt_disable_ext_identify: set_opt(sbi, DISABLE_EXT_IDENTIFY); @@ -524,9 +539,9 @@ static int parse_options(struct super_block *sb, char *options) if (test_opt(sbi, RESERVE_ROOT)) { f2fs_msg(sb, KERN_INFO, "Preserve previous reserve_root=%u", - sbi->root_reserved_blocks); + F2FS_OPTION(sbi).root_reserved_blocks); } else { - sbi->root_reserved_blocks = arg; + F2FS_OPTION(sbi).root_reserved_blocks = arg; set_opt(sbi, RESERVE_ROOT); } break; @@ -539,7 +554,7 @@ static int parse_options(struct super_block *sb, char *options) "Invalid uid value %d", arg); return -EINVAL; } - sbi->s_resuid = uid; + F2FS_OPTION(sbi).s_resuid = uid; break; case Opt_resgid: if (args->from && match_int(args, &arg)) @@ -550,7 +565,7 @@ static int parse_options(struct super_block *sb, char *options) "Invalid gid value %d", arg); return -EINVAL; } - sbi->s_resgid = gid; + F2FS_OPTION(sbi).s_resgid = gid; break; case Opt_mode: name = match_strdup(&args[0]); @@ -559,7 +574,7 @@ static int parse_options(struct super_block *sb, char *options) return -ENOMEM; if (strlen(name) == 8 && !strncmp(name, "adaptive", 8)) { - if (f2fs_sb_mounted_blkzoned(sb)) { + if (f2fs_sb_has_blkzoned(sb)) { f2fs_msg(sb, KERN_WARNING, "adaptive mode is not allowed with " "zoned block device feature"); @@ -585,7 +600,7 @@ static int parse_options(struct super_block *sb, char *options) 1 << arg, BIO_MAX_PAGES); return -EINVAL; } - sbi->write_io_size_bits = arg; + F2FS_OPTION(sbi).write_io_size_bits = arg; break; case Opt_fault_injection: if (args->from && match_int(args, &arg)) @@ -646,13 +661,13 @@ static int parse_options(struct super_block *sb, char *options) return ret; break; case Opt_jqfmt_vfsold: - sbi->s_jquota_fmt = QFMT_VFS_OLD; + F2FS_OPTION(sbi).s_jquota_fmt = QFMT_VFS_OLD; break; case Opt_jqfmt_vfsv0: - sbi->s_jquota_fmt = QFMT_VFS_V0; + F2FS_OPTION(sbi).s_jquota_fmt = QFMT_VFS_V0; break; case Opt_jqfmt_vfsv1: - sbi->s_jquota_fmt = QFMT_VFS_V1; + F2FS_OPTION(sbi).s_jquota_fmt = QFMT_VFS_V1; break; case Opt_noquota: clear_opt(sbi, QUOTA); @@ -679,6 +694,73 @@ static int parse_options(struct super_block *sb, char *options) "quota operations not supported"); break; #endif + case Opt_whint: + name = match_strdup(&args[0]); + if (!name) + return -ENOMEM; + if (strlen(name) == 10 && + !strncmp(name, "user-based", 10)) { + F2FS_OPTION(sbi).whint_mode = WHINT_MODE_USER; + } else if (strlen(name) == 3 && + !strncmp(name, "off", 3)) { + F2FS_OPTION(sbi).whint_mode = WHINT_MODE_OFF; + } else if (strlen(name) == 8 && + !strncmp(name, "fs-based", 8)) { + F2FS_OPTION(sbi).whint_mode = WHINT_MODE_FS; + } else { + kfree(name); + return -EINVAL; + } + kfree(name); + break; + case Opt_alloc: + name = match_strdup(&args[0]); + if (!name) + return -ENOMEM; + + if (strlen(name) == 7 && + !strncmp(name, "default", 7)) { + F2FS_OPTION(sbi).alloc_mode = ALLOC_MODE_DEFAULT; + } else if (strlen(name) == 5 && + !strncmp(name, "reuse", 5)) { + F2FS_OPTION(sbi).alloc_mode = ALLOC_MODE_REUSE; + } else { + kfree(name); + return -EINVAL; + } + kfree(name); + break; + case Opt_fsync: + name = match_strdup(&args[0]); + if (!name) + return -ENOMEM; + if (strlen(name) == 5 && + !strncmp(name, "posix", 5)) { + F2FS_OPTION(sbi).fsync_mode = FSYNC_MODE_POSIX; + } else if (strlen(name) == 6 && + !strncmp(name, "strict", 6)) { + F2FS_OPTION(sbi).fsync_mode = FSYNC_MODE_STRICT; + } else { + kfree(name); + return -EINVAL; + } + kfree(name); + break; + case Opt_test_dummy_encryption: +#ifdef CONFIG_F2FS_FS_ENCRYPTION + if (!f2fs_sb_has_encrypt(sb)) { + f2fs_msg(sb, KERN_ERR, "Encrypt feature is off"); + return -EINVAL; + } + + F2FS_OPTION(sbi).test_dummy_encryption = true; + f2fs_msg(sb, KERN_INFO, + "Test dummy encryption mode enabled"); +#else + f2fs_msg(sb, KERN_INFO, + "Test dummy encryption mount option ignored"); +#endif + break; default: f2fs_msg(sb, KERN_ERR, "Unrecognized mount option \"%s\" or missing value", @@ -699,14 +781,22 @@ static int parse_options(struct super_block *sb, char *options) } if (test_opt(sbi, INLINE_XATTR_SIZE)) { + if (!f2fs_sb_has_extra_attr(sb) || + !f2fs_sb_has_flexible_inline_xattr(sb)) { + f2fs_msg(sb, KERN_ERR, + "extra_attr or flexible_inline_xattr " + "feature is off"); + return -EINVAL; + } if (!test_opt(sbi, INLINE_XATTR)) { f2fs_msg(sb, KERN_ERR, "inline_xattr_size option should be " "set with inline_xattr option"); return -EINVAL; } - if (!sbi->inline_xattr_size || - sbi->inline_xattr_size >= DEF_ADDRS_PER_INODE - + if (!F2FS_OPTION(sbi).inline_xattr_size || + F2FS_OPTION(sbi).inline_xattr_size >= + DEF_ADDRS_PER_INODE - F2FS_TOTAL_EXTRA_ATTR_SIZE - DEF_INLINE_RESERVED_SIZE - DEF_MIN_INLINE_SIZE) { @@ -715,6 +805,12 @@ static int parse_options(struct super_block *sb, char *options) return -EINVAL; } } + + /* Not pass down write hints if the number of active logs is lesser + * than NR_CURSEG_TYPE. + */ + if (F2FS_OPTION(sbi).active_logs != NR_CURSEG_TYPE) + F2FS_OPTION(sbi).whint_mode = WHINT_MODE_OFF; return 0; } @@ -731,7 +827,6 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb) /* Initialize f2fs-specific inode info */ atomic_set(&fi->dirty_pages, 0); fi->i_current_depth = 1; - fi->i_advise = 0; init_rwsem(&fi->i_sem); INIT_LIST_HEAD(&fi->dirty_list); INIT_LIST_HEAD(&fi->gdirty_list); @@ -743,10 +838,6 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb) init_rwsem(&fi->i_mmap_sem); init_rwsem(&fi->i_xattr_sem); -#ifdef CONFIG_QUOTA - memset(&fi->i_dquot, 0, sizeof(fi->i_dquot)); - fi->i_reserved_quota = 0; -#endif /* Will be used by directory only */ fi->i_dir_level = F2FS_SB(sb)->dir_level; @@ -956,7 +1047,7 @@ static void f2fs_put_super(struct super_block *sb) mempool_destroy(sbi->write_io_dummy); #ifdef CONFIG_QUOTA for (i = 0; i < MAXQUOTAS; i++) - kfree(sbi->s_qf_names[i]); + kfree(F2FS_OPTION(sbi).s_qf_names[i]); #endif destroy_percpu_info(sbi); for (i = 0; i < NR_PAGE_TYPE; i++) @@ -1070,8 +1161,9 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_blocks = total_count - start_count; buf->f_bfree = user_block_count - valid_user_blocks(sbi) - sbi->current_reserved_blocks; - if (buf->f_bfree > sbi->root_reserved_blocks) - buf->f_bavail = buf->f_bfree - sbi->root_reserved_blocks; + if (buf->f_bfree > F2FS_OPTION(sbi).root_reserved_blocks) + buf->f_bavail = buf->f_bfree - + F2FS_OPTION(sbi).root_reserved_blocks; else buf->f_bavail = 0; @@ -1106,10 +1198,10 @@ static inline void f2fs_show_quota_options(struct seq_file *seq, #ifdef CONFIG_QUOTA struct f2fs_sb_info *sbi = F2FS_SB(sb); - if (sbi->s_jquota_fmt) { + if (F2FS_OPTION(sbi).s_jquota_fmt) { char *fmtname = ""; - switch (sbi->s_jquota_fmt) { + switch (F2FS_OPTION(sbi).s_jquota_fmt) { case QFMT_VFS_OLD: fmtname = "vfsold"; break; @@ -1123,14 +1215,17 @@ static inline void f2fs_show_quota_options(struct seq_file *seq, seq_printf(seq, ",jqfmt=%s", fmtname); } - if (sbi->s_qf_names[USRQUOTA]) - seq_show_option(seq, "usrjquota", sbi->s_qf_names[USRQUOTA]); + if (F2FS_OPTION(sbi).s_qf_names[USRQUOTA]) + seq_show_option(seq, "usrjquota", + F2FS_OPTION(sbi).s_qf_names[USRQUOTA]); - if (sbi->s_qf_names[GRPQUOTA]) - seq_show_option(seq, "grpjquota", sbi->s_qf_names[GRPQUOTA]); + if (F2FS_OPTION(sbi).s_qf_names[GRPQUOTA]) + seq_show_option(seq, "grpjquota", + F2FS_OPTION(sbi).s_qf_names[GRPQUOTA]); - if (sbi->s_qf_names[PRJQUOTA]) - seq_show_option(seq, "prjjquota", sbi->s_qf_names[PRJQUOTA]); + if (F2FS_OPTION(sbi).s_qf_names[PRJQUOTA]) + seq_show_option(seq, "prjjquota", + F2FS_OPTION(sbi).s_qf_names[PRJQUOTA]); #endif } @@ -1165,7 +1260,7 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) seq_puts(seq, ",noinline_xattr"); if (test_opt(sbi, INLINE_XATTR_SIZE)) seq_printf(seq, ",inline_xattr_size=%u", - sbi->inline_xattr_size); + F2FS_OPTION(sbi).inline_xattr_size); #endif #ifdef CONFIG_F2FS_FS_POSIX_ACL if (test_opt(sbi, POSIX_ACL)) @@ -1201,18 +1296,20 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) seq_puts(seq, "adaptive"); else if (test_opt(sbi, LFS)) seq_puts(seq, "lfs"); - seq_printf(seq, ",active_logs=%u", sbi->active_logs); + seq_printf(seq, ",active_logs=%u", F2FS_OPTION(sbi).active_logs); if (test_opt(sbi, RESERVE_ROOT)) seq_printf(seq, ",reserve_root=%u,resuid=%u,resgid=%u", - sbi->root_reserved_blocks, - from_kuid_munged(&init_user_ns, sbi->s_resuid), - from_kgid_munged(&init_user_ns, sbi->s_resgid)); + F2FS_OPTION(sbi).root_reserved_blocks, + from_kuid_munged(&init_user_ns, + F2FS_OPTION(sbi).s_resuid), + from_kgid_munged(&init_user_ns, + F2FS_OPTION(sbi).s_resgid)); if (F2FS_IO_SIZE_BITS(sbi)) seq_printf(seq, ",io_size=%uKB", F2FS_IO_SIZE_KB(sbi)); #ifdef CONFIG_F2FS_FAULT_INJECTION if (test_opt(sbi, FAULT_INJECTION)) seq_printf(seq, ",fault_injection=%u", - sbi->fault_info.inject_rate); + F2FS_OPTION(sbi).fault_info.inject_rate); #endif #ifdef CONFIG_QUOTA if (test_opt(sbi, QUOTA)) @@ -1225,15 +1322,37 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) seq_puts(seq, ",prjquota"); #endif f2fs_show_quota_options(seq, sbi->sb); + if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_USER) + seq_printf(seq, ",whint_mode=%s", "user-based"); + else if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_FS) + seq_printf(seq, ",whint_mode=%s", "fs-based"); +#ifdef CONFIG_F2FS_FS_ENCRYPTION + if (F2FS_OPTION(sbi).test_dummy_encryption) + seq_puts(seq, ",test_dummy_encryption"); +#endif + if (F2FS_OPTION(sbi).alloc_mode == ALLOC_MODE_DEFAULT) + seq_printf(seq, ",alloc_mode=%s", "default"); + else if (F2FS_OPTION(sbi).alloc_mode == ALLOC_MODE_REUSE) + seq_printf(seq, ",alloc_mode=%s", "reuse"); + + if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_POSIX) + seq_printf(seq, ",fsync_mode=%s", "posix"); + else if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT) + seq_printf(seq, ",fsync_mode=%s", "strict"); return 0; } static void default_options(struct f2fs_sb_info *sbi) { /* init some FS parameters */ - sbi->active_logs = NR_CURSEG_TYPE; - sbi->inline_xattr_size = DEFAULT_INLINE_XATTR_ADDRS; + F2FS_OPTION(sbi).active_logs = NR_CURSEG_TYPE; + F2FS_OPTION(sbi).inline_xattr_size = DEFAULT_INLINE_XATTR_ADDRS; + F2FS_OPTION(sbi).whint_mode = WHINT_MODE_OFF; + F2FS_OPTION(sbi).alloc_mode = ALLOC_MODE_DEFAULT; + F2FS_OPTION(sbi).fsync_mode = FSYNC_MODE_POSIX; + F2FS_OPTION(sbi).test_dummy_encryption = false; + sbi->readdir_ra = 1; set_opt(sbi, BG_GC); set_opt(sbi, INLINE_XATTR); @@ -1243,7 +1362,7 @@ static void default_options(struct f2fs_sb_info *sbi) set_opt(sbi, NOHEAP); sbi->sb->s_flags |= SB_LAZYTIME; set_opt(sbi, FLUSH_MERGE); - if (f2fs_sb_mounted_blkzoned(sbi->sb)) { + if (f2fs_sb_has_blkzoned(sbi->sb)) { set_opt_mode(sbi, F2FS_MOUNT_LFS); set_opt(sbi, DISCARD); } else { @@ -1270,16 +1389,11 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) struct f2fs_sb_info *sbi = F2FS_SB(sb); struct f2fs_mount_info org_mount_opt; unsigned long old_sb_flags; - int err, active_logs; + int err; bool need_restart_gc = false; bool need_stop_gc = false; bool no_extent_cache = !test_opt(sbi, EXTENT_CACHE); -#ifdef CONFIG_F2FS_FAULT_INJECTION - struct f2fs_fault_info ffi = sbi->fault_info; -#endif #ifdef CONFIG_QUOTA - int s_jquota_fmt; - char *s_qf_names[MAXQUOTAS]; int i, j; #endif @@ -1289,21 +1403,21 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) */ org_mount_opt = sbi->mount_opt; old_sb_flags = sb->s_flags; - active_logs = sbi->active_logs; #ifdef CONFIG_QUOTA - s_jquota_fmt = sbi->s_jquota_fmt; + org_mount_opt.s_jquota_fmt = F2FS_OPTION(sbi).s_jquota_fmt; for (i = 0; i < MAXQUOTAS; i++) { - if (sbi->s_qf_names[i]) { - s_qf_names[i] = kstrdup(sbi->s_qf_names[i], - GFP_KERNEL); - if (!s_qf_names[i]) { + if (F2FS_OPTION(sbi).s_qf_names[i]) { + org_mount_opt.s_qf_names[i] = + kstrdup(F2FS_OPTION(sbi).s_qf_names[i], + GFP_KERNEL); + if (!org_mount_opt.s_qf_names[i]) { for (j = 0; j < i; j++) - kfree(s_qf_names[j]); + kfree(org_mount_opt.s_qf_names[j]); return -ENOMEM; } } else { - s_qf_names[i] = NULL; + org_mount_opt.s_qf_names[i] = NULL; } } #endif @@ -1373,7 +1487,8 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) need_stop_gc = true; } - if (*flags & SB_RDONLY) { + if (*flags & SB_RDONLY || + F2FS_OPTION(sbi).whint_mode != org_mount_opt.whint_mode) { writeback_inodes_sb(sb, WB_REASON_SYNC); sync_inodes_sb(sb); @@ -1399,7 +1514,7 @@ skip: #ifdef CONFIG_QUOTA /* Release old quota file names */ for (i = 0; i < MAXQUOTAS; i++) - kfree(s_qf_names[i]); + kfree(org_mount_opt.s_qf_names[i]); #endif /* Update the POSIXACL Flag */ sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | @@ -1417,18 +1532,14 @@ restore_gc: } restore_opts: #ifdef CONFIG_QUOTA - sbi->s_jquota_fmt = s_jquota_fmt; + F2FS_OPTION(sbi).s_jquota_fmt = org_mount_opt.s_jquota_fmt; for (i = 0; i < MAXQUOTAS; i++) { - kfree(sbi->s_qf_names[i]); - sbi->s_qf_names[i] = s_qf_names[i]; + kfree(F2FS_OPTION(sbi).s_qf_names[i]); + F2FS_OPTION(sbi).s_qf_names[i] = org_mount_opt.s_qf_names[i]; } #endif sbi->mount_opt = org_mount_opt; - sbi->active_logs = active_logs; sb->s_flags = old_sb_flags; -#ifdef CONFIG_F2FS_FAULT_INJECTION - sbi->fault_info = ffi; -#endif return err; } @@ -1456,7 +1567,7 @@ static ssize_t f2fs_quota_read(struct super_block *sb, int type, char *data, while (toread > 0) { tocopy = min_t(unsigned long, sb->s_blocksize - offset, toread); repeat: - page = read_mapping_page(mapping, blkidx, NULL); + page = read_cache_page_gfp(mapping, blkidx, GFP_NOFS); if (IS_ERR(page)) { if (PTR_ERR(page) == -ENOMEM) { congestion_wait(BLK_RW_ASYNC, HZ/50); @@ -1550,8 +1661,8 @@ static qsize_t *f2fs_get_reserved_space(struct inode *inode) static int f2fs_quota_on_mount(struct f2fs_sb_info *sbi, int type) { - return dquot_quota_on_mount(sbi->sb, sbi->s_qf_names[type], - sbi->s_jquota_fmt, type); + return dquot_quota_on_mount(sbi->sb, F2FS_OPTION(sbi).s_qf_names[type], + F2FS_OPTION(sbi).s_jquota_fmt, type); } int f2fs_enable_quota_files(struct f2fs_sb_info *sbi, bool rdonly) @@ -1570,7 +1681,7 @@ int f2fs_enable_quota_files(struct f2fs_sb_info *sbi, bool rdonly) } for (i = 0; i < MAXQUOTAS; i++) { - if (sbi->s_qf_names[i]) { + if (F2FS_OPTION(sbi).s_qf_names[i]) { err = f2fs_quota_on_mount(sbi, i); if (!err) { enabled = 1; @@ -1797,11 +1908,28 @@ static int f2fs_get_context(struct inode *inode, void *ctx, size_t len) static int f2fs_set_context(struct inode *inode, const void *ctx, size_t len, void *fs_data) { + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + + /* + * Encrypting the root directory is not allowed because fsck + * expects lost+found directory to exist and remain unencrypted + * if LOST_FOUND feature is enabled. + * + */ + if (f2fs_sb_has_lost_found(sbi->sb) && + inode->i_ino == F2FS_ROOT_INO(sbi)) + return -EPERM; + return f2fs_setxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION, F2FS_XATTR_NAME_ENCRYPTION_CONTEXT, ctx, len, fs_data, XATTR_CREATE); } +static bool f2fs_dummy_context(struct inode *inode) +{ + return DUMMY_ENCRYPTION_ENABLED(F2FS_I_SB(inode)); +} + static unsigned f2fs_max_namelen(struct inode *inode) { return S_ISLNK(inode->i_mode) ? @@ -1812,6 +1940,7 @@ static const struct fscrypt_operations f2fs_cryptops = { .key_prefix = "f2fs:", .get_context = f2fs_get_context, .set_context = f2fs_set_context, + .dummy_context = f2fs_dummy_context, .empty_dir = f2fs_empty_dir, .max_namelen = f2fs_max_namelen, }; @@ -1894,7 +2023,6 @@ static int __f2fs_commit_super(struct buffer_head *bh, lock_buffer(bh); if (super) memcpy(bh->b_data + F2FS_SUPER_OFFSET, super, sizeof(*super)); - set_buffer_uptodate(bh); set_buffer_dirty(bh); unlock_buffer(bh); @@ -2181,6 +2309,8 @@ static void init_sb_info(struct f2fs_sb_info *sbi) sbi->dirty_device = 0; spin_lock_init(&sbi->dev_lock); + + init_rwsem(&sbi->sb_lock); } static int init_percpu_info(struct f2fs_sb_info *sbi) @@ -2206,7 +2336,7 @@ static int init_blkz_info(struct f2fs_sb_info *sbi, int devi) unsigned int n = 0; int err = -EIO; - if (!f2fs_sb_mounted_blkzoned(sbi->sb)) + if (!f2fs_sb_has_blkzoned(sbi->sb)) return 0; if (sbi->blocks_per_blkz && sbi->blocks_per_blkz != @@ -2334,7 +2464,7 @@ int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover) } /* write back-up superblock first */ - bh = sb_getblk(sbi->sb, sbi->valid_super_block ? 0: 1); + bh = sb_bread(sbi->sb, sbi->valid_super_block ? 0 : 1); if (!bh) return -EIO; err = __f2fs_commit_super(bh, F2FS_RAW_SUPER(sbi)); @@ -2345,7 +2475,7 @@ int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover) return err; /* write current valid superblock */ - bh = sb_getblk(sbi->sb, sbi->valid_super_block); + bh = sb_bread(sbi->sb, sbi->valid_super_block); if (!bh) return -EIO; err = __f2fs_commit_super(bh, F2FS_RAW_SUPER(sbi)); @@ -2413,7 +2543,7 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi) #ifdef CONFIG_BLK_DEV_ZONED if (bdev_zoned_model(FDEV(i).bdev) == BLK_ZONED_HM && - !f2fs_sb_mounted_blkzoned(sbi->sb)) { + !f2fs_sb_has_blkzoned(sbi->sb)) { f2fs_msg(sbi->sb, KERN_ERR, "Zoned block device feature not enabled\n"); return -EINVAL; @@ -2447,6 +2577,18 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi) return 0; } +static void f2fs_tuning_parameters(struct f2fs_sb_info *sbi) +{ + struct f2fs_sm_info *sm_i = SM_I(sbi); + + /* adjust parameters according to the volume size */ + if (sm_i->main_segments <= SMALL_VOLUME_SEGMENTS) { + F2FS_OPTION(sbi).alloc_mode = ALLOC_MODE_REUSE; + sm_i->dcc_info->discard_granularity = 1; + sm_i->ipu_policy = 1 << F2FS_IPU_FORCE; + } +} + static int f2fs_fill_super(struct super_block *sb, void *data, int silent) { struct f2fs_sb_info *sbi; @@ -2494,8 +2636,8 @@ try_onemore: sb->s_fs_info = sbi; sbi->raw_super = raw_super; - sbi->s_resuid = make_kuid(&init_user_ns, F2FS_DEF_RESUID); - sbi->s_resgid = make_kgid(&init_user_ns, F2FS_DEF_RESGID); + F2FS_OPTION(sbi).s_resuid = make_kuid(&init_user_ns, F2FS_DEF_RESUID); + F2FS_OPTION(sbi).s_resgid = make_kgid(&init_user_ns, F2FS_DEF_RESGID); /* precompute checksum seed for metadata */ if (f2fs_sb_has_inode_chksum(sb)) @@ -2508,7 +2650,7 @@ try_onemore: * devices, but mandatory for host-managed zoned block devices. */ #ifndef CONFIG_BLK_DEV_ZONED - if (f2fs_sb_mounted_blkzoned(sb)) { + if (f2fs_sb_has_blkzoned(sb)) { f2fs_msg(sb, KERN_ERR, "Zoned block device support is not enabled\n"); err = -EOPNOTSUPP; @@ -2724,7 +2866,7 @@ try_onemore: * Turn on quotas which were not enabled for read-only mounts if * filesystem has quota feature, so that they are updated correctly. */ - if (f2fs_sb_has_quota_ino(sb) && !sb_rdonly(sb)) { + if (f2fs_sb_has_quota_ino(sb) && !f2fs_readonly(sb)) { err = f2fs_enable_quotas(sb); if (err) { f2fs_msg(sb, KERN_ERR, @@ -2799,6 +2941,8 @@ skip_recovery: f2fs_join_shrinker(sbi); + f2fs_tuning_parameters(sbi); + f2fs_msg(sbi->sb, KERN_NOTICE, "Mounted with checkpoint version = %llx", cur_cp_version(F2FS_CKPT(sbi))); f2fs_update_time(sbi, CP_TIME); @@ -2807,7 +2951,7 @@ skip_recovery: free_meta: #ifdef CONFIG_QUOTA - if (f2fs_sb_has_quota_ino(sb) && !sb_rdonly(sb)) + if (f2fs_sb_has_quota_ino(sb) && !f2fs_readonly(sb)) f2fs_quota_off_umount(sbi->sb); #endif f2fs_sync_inode_meta(sbi); @@ -2851,7 +2995,7 @@ free_bio_info: free_options: #ifdef CONFIG_QUOTA for (i = 0; i < MAXQUOTAS; i++) - kfree(sbi->s_qf_names[i]); + kfree(F2FS_OPTION(sbi).s_qf_names[i]); #endif kfree(options); free_sb_buf: diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index d978c7b6ea04..f33a56d6e6dd 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -58,7 +58,7 @@ static unsigned char *__struct_ptr(struct f2fs_sb_info *sbi, int struct_type) #ifdef CONFIG_F2FS_FAULT_INJECTION else if (struct_type == FAULT_INFO_RATE || struct_type == FAULT_INFO_TYPE) - return (unsigned char *)&sbi->fault_info; + return (unsigned char *)&F2FS_OPTION(sbi).fault_info; #endif return NULL; } @@ -92,10 +92,10 @@ static ssize_t features_show(struct f2fs_attr *a, if (!sb->s_bdev->bd_part) return snprintf(buf, PAGE_SIZE, "0\n"); - if (f2fs_sb_has_crypto(sb)) + if (f2fs_sb_has_encrypt(sb)) len += snprintf(buf, PAGE_SIZE - len, "%s", "encryption"); - if (f2fs_sb_mounted_blkzoned(sb)) + if (f2fs_sb_has_blkzoned(sb)) len += snprintf(buf + len, PAGE_SIZE - len, "%s%s", len ? ", " : "", "blkzoned"); if (f2fs_sb_has_extra_attr(sb)) @@ -116,6 +116,9 @@ static ssize_t features_show(struct f2fs_attr *a, if (f2fs_sb_has_inode_crtime(sb)) len += snprintf(buf + len, PAGE_SIZE - len, "%s%s", len ? ", " : "", "inode_crtime"); + if (f2fs_sb_has_lost_found(sb)) + len += snprintf(buf + len, PAGE_SIZE - len, "%s%s", + len ? ", " : "", "lost_found"); len += snprintf(buf + len, PAGE_SIZE - len, "\n"); return len; } @@ -136,6 +139,27 @@ static ssize_t f2fs_sbi_show(struct f2fs_attr *a, if (!ptr) return -EINVAL; + if (!strcmp(a->attr.name, "extension_list")) { + __u8 (*extlist)[F2FS_EXTENSION_LEN] = + sbi->raw_super->extension_list; + int cold_count = le32_to_cpu(sbi->raw_super->extension_count); + int hot_count = sbi->raw_super->hot_ext_count; + int len = 0, i; + + len += snprintf(buf + len, PAGE_SIZE - len, + "cold file extenstion:\n"); + for (i = 0; i < cold_count; i++) + len += snprintf(buf + len, PAGE_SIZE - len, "%s\n", + extlist[i]); + + len += snprintf(buf + len, PAGE_SIZE - len, + "hot file extenstion:\n"); + for (i = cold_count; i < cold_count + hot_count; i++) + len += snprintf(buf + len, PAGE_SIZE - len, "%s\n", + extlist[i]); + return len; + } + ui = (unsigned int *)(ptr + a->offset); return snprintf(buf, PAGE_SIZE, "%u\n", *ui); @@ -154,6 +178,41 @@ static ssize_t f2fs_sbi_store(struct f2fs_attr *a, if (!ptr) return -EINVAL; + if (!strcmp(a->attr.name, "extension_list")) { + const char *name = strim((char *)buf); + bool set = true, hot; + + if (!strncmp(name, "[h]", 3)) + hot = true; + else if (!strncmp(name, "[c]", 3)) + hot = false; + else + return -EINVAL; + + name += 3; + + if (*name == '!') { + name++; + set = false; + } + + if (strlen(name) >= F2FS_EXTENSION_LEN) + return -EINVAL; + + down_write(&sbi->sb_lock); + + ret = update_extension_list(sbi, name, hot, set); + if (ret) + goto out; + + ret = f2fs_commit_super(sbi, false); + if (ret) + update_extension_list(sbi, name, hot, !set); +out: + up_write(&sbi->sb_lock); + return ret ? ret : count; + } + ui = (unsigned int *)(ptr + a->offset); ret = kstrtoul(skip_spaces(buf), 0, &t); @@ -166,7 +225,7 @@ static ssize_t f2fs_sbi_store(struct f2fs_attr *a, if (a->struct_type == RESERVED_BLOCKS) { spin_lock(&sbi->stat_lock); if (t > (unsigned long)(sbi->user_block_count - - sbi->root_reserved_blocks)) { + F2FS_OPTION(sbi).root_reserved_blocks)) { spin_unlock(&sbi->stat_lock); return -EINVAL; } @@ -236,6 +295,7 @@ enum feat_id { FEAT_FLEXIBLE_INLINE_XATTR, FEAT_QUOTA_INO, FEAT_INODE_CRTIME, + FEAT_LOST_FOUND, }; static ssize_t f2fs_feature_show(struct f2fs_attr *a, @@ -251,6 +311,7 @@ static ssize_t f2fs_feature_show(struct f2fs_attr *a, case FEAT_FLEXIBLE_INLINE_XATTR: case FEAT_QUOTA_INO: case FEAT_INODE_CRTIME: + case FEAT_LOST_FOUND: return snprintf(buf, PAGE_SIZE, "supported\n"); } return 0; @@ -307,6 +368,7 @@ F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, idle_interval, interval_time[REQ_TIME]); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, iostat_enable, iostat_enable); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, readdir_ra, readdir_ra); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_pin_file_thresh, gc_pin_file_threshold); +F2FS_RW_ATTR(F2FS_SBI, f2fs_super_block, extension_list, extension_list); #ifdef CONFIG_F2FS_FAULT_INJECTION F2FS_RW_ATTR(FAULT_INFO_RATE, f2fs_fault_info, inject_rate, inject_rate); F2FS_RW_ATTR(FAULT_INFO_TYPE, f2fs_fault_info, inject_type, inject_type); @@ -329,6 +391,7 @@ F2FS_FEATURE_RO_ATTR(inode_checksum, FEAT_INODE_CHECKSUM); F2FS_FEATURE_RO_ATTR(flexible_inline_xattr, FEAT_FLEXIBLE_INLINE_XATTR); F2FS_FEATURE_RO_ATTR(quota_ino, FEAT_QUOTA_INO); F2FS_FEATURE_RO_ATTR(inode_crtime, FEAT_INODE_CRTIME); +F2FS_FEATURE_RO_ATTR(lost_found, FEAT_LOST_FOUND); #define ATTR_LIST(name) (&f2fs_attr_##name.attr) static struct attribute *f2fs_attrs[] = { @@ -357,6 +420,7 @@ static struct attribute *f2fs_attrs[] = { ATTR_LIST(iostat_enable), ATTR_LIST(readdir_ra), ATTR_LIST(gc_pin_file_thresh), + ATTR_LIST(extension_list), #ifdef CONFIG_F2FS_FAULT_INJECTION ATTR_LIST(inject_rate), ATTR_LIST(inject_type), @@ -383,6 +447,7 @@ static struct attribute *f2fs_feat_attrs[] = { ATTR_LIST(flexible_inline_xattr), ATTR_LIST(quota_ino), ATTR_LIST(inode_crtime), + ATTR_LIST(lost_found), NULL, }; diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 58aecb60ea51..aa5db8b5521a 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -21,6 +21,7 @@ #define F2FS_BLKSIZE 4096 /* support only 4KB block */ #define F2FS_BLKSIZE_BITS 12 /* bits for F2FS_BLKSIZE */ #define F2FS_MAX_EXTENSION 64 /* # of extension entries */ +#define F2FS_EXTENSION_LEN 8 /* max size of extension */ #define F2FS_BLK_ALIGN(x) (((x) + F2FS_BLKSIZE - 1) >> F2FS_BLKSIZE_BITS) #define NULL_ADDR ((block_t)0) /* used as block_t addresses */ @@ -38,15 +39,14 @@ #define F2FS_MAX_QUOTAS 3 -#define F2FS_IO_SIZE(sbi) (1 << (sbi)->write_io_size_bits) /* Blocks */ -#define F2FS_IO_SIZE_KB(sbi) (1 << ((sbi)->write_io_size_bits + 2)) /* KB */ -#define F2FS_IO_SIZE_BYTES(sbi) (1 << ((sbi)->write_io_size_bits + 12)) /* B */ -#define F2FS_IO_SIZE_BITS(sbi) ((sbi)->write_io_size_bits) /* power of 2 */ +#define F2FS_IO_SIZE(sbi) (1 << F2FS_OPTION(sbi).write_io_size_bits) /* Blocks */ +#define F2FS_IO_SIZE_KB(sbi) (1 << (F2FS_OPTION(sbi).write_io_size_bits + 2)) /* KB */ +#define F2FS_IO_SIZE_BYTES(sbi) (1 << (F2FS_OPTION(sbi).write_io_size_bits + 12)) /* B */ +#define F2FS_IO_SIZE_BITS(sbi) (F2FS_OPTION(sbi).write_io_size_bits) /* power of 2 */ #define F2FS_IO_SIZE_MASK(sbi) (F2FS_IO_SIZE(sbi) - 1) /* This flag is used by node and meta inodes, and by recovery */ #define GFP_F2FS_ZERO (GFP_NOFS | __GFP_ZERO) -#define GFP_F2FS_HIGH_ZERO (GFP_NOFS | __GFP_ZERO | __GFP_HIGHMEM) /* * For further optimization on multi-head logs, on-disk layout supports maximum @@ -102,7 +102,7 @@ struct f2fs_super_block { __u8 uuid[16]; /* 128-bit uuid for volume */ __le16 volume_name[MAX_VOLUME_NAME]; /* volume name */ __le32 extension_count; /* # of extensions below */ - __u8 extension_list[F2FS_MAX_EXTENSION][8]; /* extension array */ + __u8 extension_list[F2FS_MAX_EXTENSION][F2FS_EXTENSION_LEN];/* extension array */ __le32 cp_payload; __u8 version[VERSION_LEN]; /* the kernel version */ __u8 init_version[VERSION_LEN]; /* the initial kernel version */ @@ -111,12 +111,14 @@ struct f2fs_super_block { __u8 encrypt_pw_salt[16]; /* Salt used for string2key algorithm */ struct f2fs_device devs[MAX_DEVICES]; /* device list */ __le32 qf_ino[F2FS_MAX_QUOTAS]; /* quota inode numbers */ - __u8 reserved[315]; /* valid reserved region */ + __u8 hot_ext_count; /* # of hot file extension */ + __u8 reserved[314]; /* valid reserved region */ } __packed; /* * For checkpoint */ +#define CP_LARGE_NAT_BITMAP_FLAG 0x00000400 #define CP_NOCRC_RECOVERY_FLAG 0x00000200 #define CP_TRIMMED_FLAG 0x00000100 #define CP_NAT_BITS_FLAG 0x00000080 @@ -303,6 +305,10 @@ struct f2fs_node { */ #define NAT_ENTRY_PER_BLOCK (PAGE_SIZE / sizeof(struct f2fs_nat_entry)) #define NAT_ENTRY_BITMAP_SIZE ((NAT_ENTRY_PER_BLOCK + 7) / 8) +#define NAT_ENTRY_BITMAP_SIZE_ALIGNED \ + ((NAT_ENTRY_BITMAP_SIZE + BITS_PER_LONG - 1) / \ + BITS_PER_LONG * BITS_PER_LONG) + struct f2fs_nat_entry { __u8 version; /* latest version of cached nat entry */