diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2019-09-21 14:26:33 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2019-09-21 14:26:33 -0700 |
commit | fbc246a12aac27f7b25a37f9398bb3bc552cec92 (patch) | |
tree | 4b28f91eeda2c6d7d4db86e7c97fca2d305b6706 /fs/f2fs | |
parent | 7ce1e15d9a85a2b589a68a04afb2b2ded109b680 (diff) | |
parent | fbbf779989d2ef9a51daaa4e53c0b2ecc8c55c4e (diff) | |
download | linux-fbc246a12aac27f7b25a37f9398bb3bc552cec92.tar.bz2 |
Merge tag 'f2fs-for-5.4' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs
Pull f2fs updates from Jaegeuk Kim:
"In this round, we introduced casefolding support in f2fs, and fixed
various bugs in individual features such as IO alignment,
checkpoint=disable, quota, and swapfile.
Enhancement:
- support casefolding w/ enhancement in ext4
- support fiemap for directory
- support FS_IO_GET|SET_FSLABEL
Bug fix:
- fix IO stuck during checkpoint=disable
- avoid infinite GC loop
- fix panic/overflow related to IO alignment feature
- fix livelock in swap file
- fix discard command leak
- disallow dio for atomic_write"
* tag 'f2fs-for-5.4' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (51 commits)
f2fs: add a condition to detect overflow in f2fs_ioc_gc_range()
f2fs: fix to add missing F2FS_IO_ALIGNED() condition
f2fs: fix to fallback to buffered IO in IO aligned mode
f2fs: fix to handle error path correctly in f2fs_map_blocks
f2fs: fix extent corrupotion during directIO in LFS mode
f2fs: check all the data segments against all node ones
f2fs: Add a small clarification to CONFIG_FS_F2FS_FS_SECURITY
f2fs: fix inode rwsem regression
f2fs: fix to avoid accessing uninitialized field of inode page in is_alive()
f2fs: avoid infinite GC loop due to stale atomic files
f2fs: Fix indefinite loop in f2fs_gc()
f2fs: convert inline_data in prior to i_size_write
f2fs: fix error path of f2fs_convert_inline_page()
f2fs: add missing documents of reserve_root/resuid/resgid
f2fs: fix flushing node pages when checkpoint is disabled
f2fs: enhance f2fs_is_checkpoint_ready()'s readability
f2fs: clean up __bio_alloc()'s parameter
f2fs: fix wrong error injection path in inc_valid_block_count()
f2fs: fix to writeout dirty inode during node flush
f2fs: optimize case-insensitive lookups
...
Diffstat (limited to 'fs/f2fs')
-rw-r--r-- | fs/f2fs/Kconfig | 5 | ||||
-rw-r--r-- | fs/f2fs/data.c | 104 | ||||
-rw-r--r-- | fs/f2fs/debug.c | 4 | ||||
-rw-r--r-- | fs/f2fs/dir.c | 184 | ||||
-rw-r--r-- | fs/f2fs/f2fs.h | 47 | ||||
-rw-r--r-- | fs/f2fs/file.c | 162 | ||||
-rw-r--r-- | fs/f2fs/gc.c | 27 | ||||
-rw-r--r-- | fs/f2fs/hash.c | 37 | ||||
-rw-r--r-- | fs/f2fs/inline.c | 18 | ||||
-rw-r--r-- | fs/f2fs/inode.c | 11 | ||||
-rw-r--r-- | fs/f2fs/namei.c | 54 | ||||
-rw-r--r-- | fs/f2fs/node.c | 57 | ||||
-rw-r--r-- | fs/f2fs/segment.c | 135 | ||||
-rw-r--r-- | fs/f2fs/segment.h | 12 | ||||
-rw-r--r-- | fs/f2fs/super.c | 156 | ||||
-rw-r--r-- | fs/f2fs/sysfs.c | 23 | ||||
-rw-r--r-- | fs/f2fs/xattr.c | 6 |
17 files changed, 839 insertions, 203 deletions
diff --git a/fs/f2fs/Kconfig b/fs/f2fs/Kconfig index 110a38ca5d53..652fd2e2b23d 100644 --- a/fs/f2fs/Kconfig +++ b/fs/f2fs/Kconfig @@ -2,6 +2,7 @@ config F2FS_FS tristate "F2FS filesystem support" depends on BLOCK + select NLS select CRYPTO select CRYPTO_CRC32 select F2FS_FS_XATTR if FS_ENCRYPTION @@ -60,7 +61,9 @@ config F2FS_FS_SECURITY Security Models (LSMs) accepted by AppArmor, SELinux, Smack and TOMOYO Linux. This option enables an extended attribute handler for file security labels in the f2fs filesystem, so that it requires enabling - the extended attribute support in advance. + the extended attribute support in advance. In particular you need this + option if you use the setcap command to assign initial process capabi- + lities to executables (the security.* extended attributes). If you are not using a security module, say N. diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 54cad80acb7d..5755e897a5f0 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -283,26 +283,25 @@ static bool __same_bdev(struct f2fs_sb_info *sbi, /* * Low-level block read/write IO operations. */ -static struct bio *__bio_alloc(struct f2fs_sb_info *sbi, block_t blk_addr, - struct writeback_control *wbc, - int npages, bool is_read, - enum page_type type, enum temp_type temp) +static struct bio *__bio_alloc(struct f2fs_io_info *fio, int npages) { + struct f2fs_sb_info *sbi = fio->sbi; struct bio *bio; bio = f2fs_bio_alloc(sbi, npages, true); - f2fs_target_device(sbi, blk_addr, bio); - if (is_read) { + f2fs_target_device(sbi, fio->new_blkaddr, bio); + if (is_read_io(fio->op)) { 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 = f2fs_io_type_to_rw_hint(sbi, type, temp); + bio->bi_write_hint = f2fs_io_type_to_rw_hint(sbi, + fio->type, fio->temp); } - if (wbc) - wbc_init_bio(wbc, bio); + if (fio->io_wbc) + wbc_init_bio(fio->io_wbc, bio); return bio; } @@ -319,6 +318,9 @@ static inline void __submit_bio(struct f2fs_sb_info *sbi, if (test_opt(sbi, LFS) && current->plug) blk_finish_plug(current->plug); + if (F2FS_IO_ALIGNED(sbi)) + goto submit_io; + start = bio->bi_iter.bi_size >> F2FS_BLKSIZE_BITS; start %= F2FS_IO_SIZE(sbi); @@ -485,8 +487,7 @@ int f2fs_submit_page_bio(struct f2fs_io_info *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), fio->type, fio->temp); + bio = __bio_alloc(fio, 1); if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) { bio_put(bio); @@ -505,6 +506,43 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio) return 0; } +static bool page_is_mergeable(struct f2fs_sb_info *sbi, struct bio *bio, + block_t last_blkaddr, block_t cur_blkaddr) +{ + if (last_blkaddr + 1 != cur_blkaddr) + return false; + return __same_bdev(sbi, cur_blkaddr, bio); +} + +static bool io_type_is_mergeable(struct f2fs_bio_info *io, + struct f2fs_io_info *fio) +{ + if (io->fio.op != fio->op) + return false; + return io->fio.op_flags == fio->op_flags; +} + +static bool io_is_mergeable(struct f2fs_sb_info *sbi, struct bio *bio, + struct f2fs_bio_info *io, + struct f2fs_io_info *fio, + block_t last_blkaddr, + block_t cur_blkaddr) +{ + if (F2FS_IO_ALIGNED(sbi) && (fio->type == DATA || fio->type == NODE)) { + unsigned int filled_blocks = + F2FS_BYTES_TO_BLK(bio->bi_iter.bi_size); + unsigned int io_size = F2FS_IO_SIZE(sbi); + unsigned int left_vecs = bio->bi_max_vecs - bio->bi_vcnt; + + /* IOs in bio is aligned and left space of vectors is not enough */ + if (!(filled_blocks % io_size) && left_vecs < io_size) + return false; + } + if (!page_is_mergeable(sbi, bio, last_blkaddr, cur_blkaddr)) + return false; + return io_type_is_mergeable(io, fio); +} + int f2fs_merge_page_bio(struct f2fs_io_info *fio) { struct bio *bio = *fio->bio; @@ -518,15 +556,14 @@ int f2fs_merge_page_bio(struct f2fs_io_info *fio) trace_f2fs_submit_page_bio(page, fio); f2fs_trace_ios(fio, 0); - if (bio && (*fio->last_block + 1 != fio->new_blkaddr || - !__same_bdev(fio->sbi, fio->new_blkaddr, bio))) { + if (bio && !page_is_mergeable(fio->sbi, bio, *fio->last_block, + fio->new_blkaddr)) { __submit_bio(fio->sbi, bio, fio->type); bio = NULL; } alloc_new: if (!bio) { - bio = __bio_alloc(fio->sbi, fio->new_blkaddr, fio->io_wbc, - BIO_MAX_PAGES, false, fio->type, fio->temp); + bio = __bio_alloc(fio, BIO_MAX_PAGES); bio_set_op_attrs(bio, fio->op, fio->op_flags); } @@ -592,21 +629,19 @@ next: inc_page_count(sbi, WB_DATA_TYPE(bio_page)); - if (io->bio && (io->last_block_in_bio != fio->new_blkaddr - 1 || - (io->fio.op != fio->op || io->fio.op_flags != fio->op_flags) || - !__same_bdev(sbi, fio->new_blkaddr, io->bio))) + if (io->bio && !io_is_mergeable(sbi, io->bio, io, fio, + io->last_block_in_bio, fio->new_blkaddr)) __submit_merged_bio(io); alloc_new: if (io->bio == NULL) { - if ((fio->type == DATA || fio->type == NODE) && + if (F2FS_IO_ALIGNED(sbi) && + (fio->type == DATA || fio->type == NODE) && fio->new_blkaddr & F2FS_IO_SIZE_MASK(sbi)) { dec_page_count(sbi, WB_DATA_TYPE(bio_page)); fio->retry = true; goto skip; } - io->bio = __bio_alloc(sbi, fio->new_blkaddr, fio->io_wbc, - BIO_MAX_PAGES, false, - fio->type, fio->temp); + io->bio = __bio_alloc(fio, BIO_MAX_PAGES); io->fio = *fio; } @@ -627,7 +662,7 @@ skip: goto next; out: if (is_sbi_flag_set(sbi, SBI_IS_SHUTDOWN) || - f2fs_is_checkpoint_ready(sbi)) + !f2fs_is_checkpoint_ready(sbi)) __submit_merged_bio(io); up_write(&io->io_rwsem); } @@ -1022,7 +1057,7 @@ alloc: if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO) invalidate_mapping_pages(META_MAPPING(sbi), old_blkaddr, old_blkaddr); - f2fs_set_data_blkaddr(dn); + f2fs_update_data_blkaddr(dn, dn->data_blkaddr); /* * i_size will be updated by direct_IO. Otherwise, we'll get stale @@ -1199,10 +1234,10 @@ next_block: if (test_opt(sbi, LFS) && flag == F2FS_GET_BLOCK_DIO && map->m_may_create) { err = __allocate_data_block(&dn, map->m_seg_type); - if (!err) { - blkaddr = dn.data_blkaddr; - set_inode_flag(inode, FI_APPEND_WRITE); - } + if (err) + goto sync_out; + blkaddr = dn.data_blkaddr; + set_inode_flag(inode, FI_APPEND_WRITE); } } else { if (create) { @@ -1407,7 +1442,7 @@ static int get_data_block_dio_write(struct inode *inode, sector_t iblock, return __get_data_block(inode, iblock, bh_result, create, F2FS_GET_BLOCK_DIO, NULL, f2fs_rw_hint_to_seg_type(inode->i_write_hint), - true); + IS_SWAPFILE(inode) ? false : true); } static int get_data_block_dio(struct inode *inode, sector_t iblock, @@ -1538,7 +1573,7 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, goto out; } - if (f2fs_has_inline_data(inode)) { + if (f2fs_has_inline_data(inode) || f2fs_has_inline_dentry(inode)) { ret = f2fs_inline_data_fiemap(inode, fieinfo, start, len); if (ret != -EAGAIN) goto out; @@ -1691,8 +1726,8 @@ zero_out: * This page will go to BIO. Do we need to send this * BIO off first? */ - if (bio && (*last_block_in_bio != block_nr - 1 || - !__same_bdev(F2FS_I_SB(inode), block_nr, bio))) { + if (bio && !page_is_mergeable(F2FS_I_SB(inode), bio, + *last_block_in_bio, block_nr)) { submit_and_realloc: __submit_bio(F2FS_I_SB(inode), bio, DATA); bio = NULL; @@ -2590,9 +2625,10 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping, trace_f2fs_write_begin(inode, pos, len, flags); - err = f2fs_is_checkpoint_ready(sbi); - if (err) + if (!f2fs_is_checkpoint_ready(sbi)) { + err = -ENOSPC; goto fail; + } if ((f2fs_is_atomic_file(inode) && !f2fs_available_free_memory(sbi, INMEM_PAGES)) || diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c index 7706049d23bf..9b0bedd82581 100644 --- a/fs/f2fs/debug.c +++ b/fs/f2fs/debug.c @@ -67,7 +67,7 @@ static void update_general_status(struct f2fs_sb_info *sbi) si->nr_rd_data = get_pages(sbi, F2FS_RD_DATA); si->nr_rd_node = get_pages(sbi, F2FS_RD_NODE); si->nr_rd_meta = get_pages(sbi, F2FS_RD_META); - if (SM_I(sbi) && SM_I(sbi)->fcc_info) { + if (SM_I(sbi)->fcc_info) { si->nr_flushed = atomic_read(&SM_I(sbi)->fcc_info->issued_flush); si->nr_flushing = @@ -75,7 +75,7 @@ static void update_general_status(struct f2fs_sb_info *sbi) si->flush_list_empty = llist_empty(&SM_I(sbi)->fcc_info->issue_list); } - if (SM_I(sbi) && SM_I(sbi)->dcc_info) { + if (SM_I(sbi)->dcc_info) { si->nr_discarded = atomic_read(&SM_I(sbi)->dcc_info->issued_discard); si->nr_discarding = diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index 85a1528f319f..4033778bcbbf 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -8,6 +8,7 @@ #include <linux/fs.h> #include <linux/f2fs_fs.h> #include <linux/sched/signal.h> +#include <linux/unicode.h> #include "f2fs.h" #include "node.h" #include "acl.h" @@ -81,7 +82,8 @@ static unsigned long dir_block_index(unsigned int level, return bidx; } -static struct f2fs_dir_entry *find_in_block(struct page *dentry_page, +static struct f2fs_dir_entry *find_in_block(struct inode *dir, + struct page *dentry_page, struct fscrypt_name *fname, f2fs_hash_t namehash, int *max_slots, @@ -93,7 +95,7 @@ static struct f2fs_dir_entry *find_in_block(struct page *dentry_page, dentry_blk = (struct f2fs_dentry_block *)page_address(dentry_page); - make_dentry_ptr_block(NULL, &d, dentry_blk); + make_dentry_ptr_block(dir, &d, dentry_blk); de = f2fs_find_target_dentry(fname, namehash, max_slots, &d); if (de) *res_page = dentry_page; @@ -101,14 +103,116 @@ static struct f2fs_dir_entry *find_in_block(struct page *dentry_page, return de; } +#ifdef CONFIG_UNICODE +/* + * Test whether a case-insensitive directory entry matches the filename + * being searched for. + * + * Returns: 0 if the directory entry matches, more than 0 if it + * doesn't match or less than zero on error. + */ +int f2fs_ci_compare(const struct inode *parent, const struct qstr *name, + const struct qstr *entry, bool quick) +{ + const struct f2fs_sb_info *sbi = F2FS_SB(parent->i_sb); + const struct unicode_map *um = sbi->s_encoding; + int ret; + + if (quick) + ret = utf8_strncasecmp_folded(um, name, entry); + else + ret = utf8_strncasecmp(um, name, entry); + + if (ret < 0) { + /* Handle invalid character sequence as either an error + * or as an opaque byte sequence. + */ + if (f2fs_has_strict_mode(sbi)) + return -EINVAL; + + if (name->len != entry->len) + return 1; + + return !!memcmp(name->name, entry->name, name->len); + } + + return ret; +} + +static void f2fs_fname_setup_ci_filename(struct inode *dir, + const struct qstr *iname, + struct fscrypt_str *cf_name) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(dir); + + if (!IS_CASEFOLDED(dir)) { + cf_name->name = NULL; + return; + } + + cf_name->name = f2fs_kmalloc(sbi, F2FS_NAME_LEN, GFP_NOFS); + if (!cf_name->name) + return; + + cf_name->len = utf8_casefold(sbi->s_encoding, + iname, cf_name->name, + F2FS_NAME_LEN); + if ((int)cf_name->len <= 0) { + kvfree(cf_name->name); + cf_name->name = NULL; + } +} +#endif + +static inline bool f2fs_match_name(struct f2fs_dentry_ptr *d, + struct f2fs_dir_entry *de, + struct fscrypt_name *fname, + struct fscrypt_str *cf_str, + unsigned long bit_pos, + f2fs_hash_t namehash) +{ +#ifdef CONFIG_UNICODE + struct inode *parent = d->inode; + struct f2fs_sb_info *sbi = F2FS_I_SB(parent); + struct qstr entry; +#endif + + if (de->hash_code != namehash) + return false; + +#ifdef CONFIG_UNICODE + entry.name = d->filename[bit_pos]; + entry.len = de->name_len; + + if (sbi->s_encoding && IS_CASEFOLDED(parent)) { + if (cf_str->name) { + struct qstr cf = {.name = cf_str->name, + .len = cf_str->len}; + return !f2fs_ci_compare(parent, &cf, &entry, true); + } + return !f2fs_ci_compare(parent, fname->usr_fname, &entry, + false); + } +#endif + if (fscrypt_match_name(fname, d->filename[bit_pos], + le16_to_cpu(de->name_len))) + return true; + return false; +} + struct f2fs_dir_entry *f2fs_find_target_dentry(struct fscrypt_name *fname, f2fs_hash_t namehash, int *max_slots, struct f2fs_dentry_ptr *d) { struct f2fs_dir_entry *de; + struct fscrypt_str cf_str = { .name = NULL, .len = 0 }; unsigned long bit_pos = 0; int max_len = 0; +#ifdef CONFIG_UNICODE + f2fs_fname_setup_ci_filename(d->inode, fname->usr_fname, &cf_str); +#endif + if (max_slots) *max_slots = 0; while (bit_pos < d->max) { @@ -125,9 +229,7 @@ struct f2fs_dir_entry *f2fs_find_target_dentry(struct fscrypt_name *fname, continue; } - if (de->hash_code == namehash && - fscrypt_match_name(fname, d->filename[bit_pos], - le16_to_cpu(de->name_len))) + if (f2fs_match_name(d, de, fname, &cf_str, bit_pos, namehash)) goto found; if (max_slots && max_len > *max_slots) @@ -141,6 +243,10 @@ struct f2fs_dir_entry *f2fs_find_target_dentry(struct fscrypt_name *fname, found: if (max_slots && max_len > *max_slots) *max_slots = max_len; + +#ifdef CONFIG_UNICODE + kvfree(cf_str.name); +#endif return de; } @@ -157,7 +263,7 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir, struct f2fs_dir_entry *de = NULL; bool room = false; int max_slots; - f2fs_hash_t namehash = f2fs_dentry_hash(&name, fname); + f2fs_hash_t namehash = f2fs_dentry_hash(dir, &name, fname); nbucket = dir_buckets(level, F2FS_I(dir)->i_dir_level); nblock = bucket_blocks(level); @@ -179,8 +285,8 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir, } } - de = find_in_block(dentry_page, fname, namehash, &max_slots, - res_page); + de = find_in_block(dir, dentry_page, fname, namehash, + &max_slots, res_page); if (de) break; @@ -250,6 +356,14 @@ struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir, struct fscrypt_name fname; int err; +#ifdef CONFIG_UNICODE + if (f2fs_has_strict_mode(F2FS_I_SB(dir)) && IS_CASEFOLDED(dir) && + utf8_validate(F2FS_I_SB(dir)->s_encoding, child)) { + *res_page = ERR_PTR(-EINVAL); + return NULL; + } +#endif + err = fscrypt_setup_filename(dir, child, 1, &fname); if (err) { if (err == -ENOENT) @@ -504,7 +618,7 @@ int f2fs_add_regular_entry(struct inode *dir, const struct qstr *new_name, level = 0; slots = GET_DENTRY_SLOTS(new_name->len); - dentry_hash = f2fs_dentry_hash(new_name, NULL); + dentry_hash = f2fs_dentry_hash(dir, new_name, NULL); current_depth = F2FS_I(dir)->i_current_depth; if (F2FS_I(dir)->chash == dentry_hash) { @@ -568,6 +682,11 @@ add_dentry: if (inode) { f2fs_i_pino_write(inode, dir->i_ino); + + /* synchronize inode page's data from inode cache */ + if (is_inode_flag_set(inode, FI_NEW_INODE)) + f2fs_update_inode(inode, page); + f2fs_put_page(page, 1); } @@ -943,3 +1062,50 @@ const struct file_operations f2fs_dir_operations = { .compat_ioctl = f2fs_compat_ioctl, #endif }; + +#ifdef CONFIG_UNICODE +static int f2fs_d_compare(const struct dentry *dentry, unsigned int len, + const char *str, const struct qstr *name) +{ + struct qstr qstr = {.name = str, .len = len }; + + if (!IS_CASEFOLDED(dentry->d_parent->d_inode)) { + if (len != name->len) + return -1; + return memcmp(str, name, len); + } + + return f2fs_ci_compare(dentry->d_parent->d_inode, name, &qstr, false); +} + +static int f2fs_d_hash(const struct dentry *dentry, struct qstr *str) +{ + struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb); + const struct unicode_map *um = sbi->s_encoding; + unsigned char *norm; + int len, ret = 0; + + if (!IS_CASEFOLDED(dentry->d_inode)) + return 0; + + norm = f2fs_kmalloc(sbi, PATH_MAX, GFP_ATOMIC); + if (!norm) + return -ENOMEM; + + len = utf8_casefold(um, str, norm, PATH_MAX); + if (len < 0) { + if (f2fs_has_strict_mode(sbi)) + ret = -EINVAL; + goto out; + } + str->hash = full_name_hash(dentry, norm, len); +out: + kvfree(norm); + return ret; +} + +const struct dentry_operations f2fs_dentry_ops = { + .d_hash = f2fs_d_hash, + .d_compare = f2fs_d_compare, +}; +#endif diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 7c5f121edac5..4024790028aa 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -154,6 +154,7 @@ struct f2fs_mount_info { #define F2FS_FEATURE_LOST_FOUND 0x0200 #define F2FS_FEATURE_VERITY 0x0400 #define F2FS_FEATURE_SB_CHKSUM 0x0800 +#define F2FS_FEATURE_CASEFOLD 0x1000 #define __F2FS_HAS_FEATURE(raw_super, mask) \ ((raw_super->feature & cpu_to_le32(mask)) != 0) @@ -418,6 +419,9 @@ static inline bool __has_cursum_space(struct f2fs_journal *journal, #define F2FS_IOC_PRECACHE_EXTENTS _IO(F2FS_IOCTL_MAGIC, 15) #define F2FS_IOC_RESIZE_FS _IOW(F2FS_IOCTL_MAGIC, 16, __u64) +#define F2FS_IOC_GET_VOLUME_NAME FS_IOC_GETFSLABEL +#define F2FS_IOC_SET_VOLUME_NAME FS_IOC_SETFSLABEL + #define F2FS_IOC_SET_ENCRYPTION_POLICY FS_IOC_SET_ENCRYPTION_POLICY #define F2FS_IOC_GET_ENCRYPTION_POLICY FS_IOC_GET_ENCRYPTION_POLICY #define F2FS_IOC_GET_ENCRYPTION_PWSALT FS_IOC_GET_ENCRYPTION_PWSALT @@ -1172,6 +1176,10 @@ struct f2fs_sb_info { int valid_super_block; /* valid super block no */ unsigned long s_flag; /* flags for sbi */ struct mutex writepages; /* mutex for writepages() */ +#ifdef CONFIG_UNICODE + struct unicode_map *s_encoding; + __u16 s_encoding_flags; +#endif #ifdef CONFIG_BLK_DEV_ZONED unsigned int blocks_per_blkz; /* F2FS blocks per zone */ @@ -1643,6 +1651,7 @@ static inline void clear_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f) static inline void disable_nat_bits(struct f2fs_sb_info *sbi, bool lock) { unsigned long flags; + unsigned char *nat_bits; /* * In order to re-enable nat_bits we need to call fsck.f2fs by @@ -1653,10 +1662,12 @@ static inline void disable_nat_bits(struct f2fs_sb_info *sbi, bool lock) if (lock) spin_lock_irqsave(&sbi->cp_lock, flags); __clear_ckpt_flags(F2FS_CKPT(sbi), CP_NAT_BITS_FLAG); - kvfree(NM_I(sbi)->nat_bits); + nat_bits = NM_I(sbi)->nat_bits; NM_I(sbi)->nat_bits = NULL; if (lock) spin_unlock_irqrestore(&sbi->cp_lock, flags); + + kvfree(nat_bits); } static inline bool enabled_nat_bits(struct f2fs_sb_info *sbi, @@ -1763,7 +1774,7 @@ static inline int inc_valid_block_count(struct f2fs_sb_info *sbi, if (time_to_inject(sbi, FAULT_BLOCK)) { f2fs_show_injection_info(FAULT_BLOCK); release = *count; - goto enospc; + goto release_quota; } /* @@ -1808,6 +1819,7 @@ static inline int inc_valid_block_count(struct f2fs_sb_info *sbi, enospc: percpu_counter_sub(&sbi->alloc_valid_block_count, release); +release_quota: dquot_release_reservation_block(inode, release); return -ENOSPC; } @@ -2362,13 +2374,16 @@ static inline void f2fs_change_bit(unsigned int nr, char *addr) #define F2FS_INDEX_FL 0x00001000 /* hash-indexed directory */ #define F2FS_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */ #define F2FS_PROJINHERIT_FL 0x20000000 /* Create with parents projid */ +#define F2FS_CASEFOLD_FL 0x40000000 /* Casefolded file */ /* Flags that should be inherited by new inodes from their parent. */ #define F2FS_FL_INHERITED (F2FS_SYNC_FL | F2FS_NODUMP_FL | F2FS_NOATIME_FL | \ - F2FS_DIRSYNC_FL | F2FS_PROJINHERIT_FL) + F2FS_DIRSYNC_FL | F2FS_PROJINHERIT_FL | \ + F2FS_CASEFOLD_FL) /* Flags that are appropriate for regular files (all but dir-specific ones). */ -#define F2FS_REG_FLMASK (~(F2FS_DIRSYNC_FL | F2FS_PROJINHERIT_FL)) +#define F2FS_REG_FLMASK (~(F2FS_DIRSYNC_FL | F2FS_PROJINHERIT_FL | \ + F2FS_CASEFOLD_FL)) /* Flags that are appropriate for non-directories/regular files. */ #define F2FS_OTHER_FLMASK (F2FS_NODUMP_FL | F2FS_NOATIME_FL) @@ -2935,6 +2950,11 @@ int f2fs_update_extension_list(struct f2fs_sb_info *sbi, const char *name, bool hot, bool set); struct dentry *f2fs_get_parent(struct dentry *child); +extern int f2fs_ci_compare(const struct inode *parent, + const struct qstr *name, + const struct qstr *entry, + bool quick); + /* * dir.c */ @@ -2998,8 +3018,8 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi); /* * hash.c */ -f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info, - struct fscrypt_name *fname); +f2fs_hash_t f2fs_dentry_hash(const struct inode *dir, + const struct qstr *name_info, struct fscrypt_name *fname); /* * node.c @@ -3442,6 +3462,9 @@ static inline void f2fs_destroy_root_stats(void) { } #endif extern const struct file_operations f2fs_dir_operations; +#ifdef CONFIG_UNICODE +extern const struct dentry_operations f2fs_dentry_ops; +#endif extern const struct file_operations f2fs_file_operations; extern const struct inode_operations f2fs_file_inode_operations; extern const struct address_space_operations f2fs_dblock_aops; @@ -3576,6 +3599,7 @@ F2FS_FEATURE_FUNCS(inode_crtime, INODE_CRTIME); F2FS_FEATURE_FUNCS(lost_found, LOST_FOUND); F2FS_FEATURE_FUNCS(verity, VERITY); F2FS_FEATURE_FUNCS(sb_chksum, SB_CHKSUM); +F2FS_FEATURE_FUNCS(casefold, CASEFOLD); #ifdef CONFIG_BLK_DEV_ZONED static inline bool f2fs_blkz_is_seq(struct f2fs_sb_info *sbi, int devi, @@ -3694,11 +3718,14 @@ static inline bool f2fs_force_buffered_io(struct inode *inode, */ if (f2fs_sb_has_blkzoned(sbi)) return true; - if (test_opt(sbi, LFS) && (rw == WRITE) && - block_unaligned_IO(inode, iocb, iter)) - return true; + if (test_opt(sbi, LFS) && (rw == WRITE)) { + if (block_unaligned_IO(inode, iocb, iter)) + return true; + if (F2FS_IO_ALIGNED(sbi)) + return true; + } if (is_sbi_flag_set(F2FS_I_SB(inode), SBI_CP_DISABLED) && - !(inode->i_flags & S_SWAPFILE)) + !IS_SWAPFILE(inode)) return true; return false; diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 56efde9d3659..29bc0a542759 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -20,6 +20,7 @@ #include <linux/uio.h> #include <linux/uuid.h> #include <linux/file.h> +#include <linux/nls.h> #include "f2fs.h" #include "node.h" @@ -57,6 +58,11 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf) goto err; } + if (!f2fs_is_checkpoint_ready(sbi)) { + err = -ENOSPC; + goto err; + } + sb_start_pagefault(inode->i_sb); f2fs_bug_on(sbi, f2fs_has_inline_data(inode)); @@ -819,14 +825,24 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) } if (attr->ia_valid & ATTR_SIZE) { - bool to_smaller = (attr->ia_size <= i_size_read(inode)); + loff_t old_size = i_size_read(inode); + + if (attr->ia_size > MAX_INLINE_DATA(inode)) { + /* + * should convert inline inode before i_size_write to + * keep smaller than inline_data size with inline flag. + */ + err = f2fs_convert_inline_inode(inode); + if (err) + return err; + } down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); down_write(&F2FS_I(inode)->i_mmap_sem); truncate_setsize(inode, attr->ia_size); - if (to_smaller) + if (attr->ia_size <= old_size) err = f2fs_truncate(inode); /* * do not trim all blocks after i_size if target size is @@ -834,21 +850,11 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) */ up_write(&F2FS_I(inode)->i_mmap_sem); up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); - if (err) return err; - if (!to_smaller) { - /* should convert inline inode here */ - if (!f2fs_may_inline_data(inode)) { - err = f2fs_convert_inline_inode(inode); - if (err) - return err; - } - inode->i_mtime = inode->i_ctime = current_time(inode); - } - down_write(&F2FS_I(inode)->i_sem); + inode->i_mtime = inode->i_ctime = current_time(inode); F2FS_I(inode)->last_disk_size = i_size_read(inode); up_write(&F2FS_I(inode)->i_sem); } @@ -1041,7 +1047,7 @@ next_dnode: if (test_opt(sbi, LFS)) { f2fs_put_dnode(&dn); - return -ENOTSUPP; + return -EOPNOTSUPP; } /* do not invalidate this block address */ @@ -1578,6 +1584,8 @@ static long f2fs_fallocate(struct file *file, int mode, if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) return -EIO; + if (!f2fs_is_checkpoint_ready(F2FS_I_SB(inode))) + return -ENOSPC; /* f2fs only support ->fallocate for regular file */ if (!S_ISREG(inode->i_mode)) @@ -1669,6 +1677,13 @@ static int f2fs_setflags_common(struct inode *inode, u32 iflags, u32 mask) if (IS_NOQUOTA(inode)) return -EPERM; + if ((iflags ^ fi->i_flags) & F2FS_CASEFOLD_FL) { + if (!f2fs_sb_has_casefold(F2FS_I_SB(inode))) + return -EOPNOTSUPP; + if (!f2fs_empty_dir(inode)) + return -ENOTEMPTY; + } + fi->i_flags = iflags | (fi->i_flags & ~mask); if (fi->i_flags & F2FS_PROJINHERIT_FL) @@ -1703,6 +1718,7 @@ static const struct { { F2FS_INDEX_FL, FS_INDEX_FL }, { F2FS_DIRSYNC_FL, FS_DIRSYNC_FL }, { F2FS_PROJINHERIT_FL, FS_PROJINHERIT_FL }, + { F2FS_CASEFOLD_FL, FS_CASEFOLD_FL }, }; #define F2FS_GETTABLE_FS_FL ( \ @@ -1717,7 +1733,8 @@ static const struct { FS_ENCRYPT_FL | \ FS_INLINE_DATA_FL | \ FS_NOCOW_FL | \ - FS_VERITY_FL) + FS_VERITY_FL | \ + FS_CASEFOLD_FL) #define F2FS_SETTABLE_FS_FL ( \ FS_SYNC_FL | \ @@ -1726,7 +1743,8 @@ static const struct { FS_NODUMP_FL | \ FS_NOATIME_FL | \ FS_DIRSYNC_FL | \ - FS_PROJINHERIT_FL) + FS_PROJINHERIT_FL | \ + FS_CASEFOLD_FL) /* Convert f2fs on-disk i_flags to FS_IOC_{GET,SET}FLAGS flags */ static inline u32 f2fs_iflags_to_fsflags(u32 iflags) @@ -1825,6 +1843,8 @@ static int f2fs_ioc_getversion(struct file *filp, unsigned long arg) static int f2fs_ioc_start_atomic_write(struct file *filp) { struct inode *inode = file_inode(filp); + struct f2fs_inode_info *fi = F2FS_I(inode); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); int ret; if (!inode_owner_or_capable(inode)) @@ -1833,6 +1853,9 @@ static int f2fs_ioc_start_atomic_write(struct file *filp) if (!S_ISREG(inode->i_mode)) return -EINVAL; + if (filp->f_flags & O_DIRECT) + return -EINVAL; + ret = mnt_want_write_file(filp); if (ret) return ret; @@ -1864,6 +1887,12 @@ static int f2fs_ioc_start_atomic_write(struct file *filp) goto out; } + spin_lock(&sbi->inode_lock[ATOMIC_FILE]); + if (list_empty(&fi->inmem_ilist)) + list_add_tail(&fi->inmem_ilist, &sbi->inode_list[ATOMIC_FILE]); + spin_unlock(&sbi->inode_lock[ATOMIC_FILE]); + + /* add inode in inmem_list first and set atomic_file */ set_inode_flag(inode, FI_ATOMIC_FILE); clear_inode_flag(inode, FI_ATOMIC_REVOKE_REQUEST); up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); @@ -1905,11 +1934,8 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp) goto err_out; ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true); - if (!ret) { - clear_inode_flag(inode, FI_ATOMIC_FILE); - F2FS_I(inode)->i_gc_failures[GC_FAILURE_ATOMIC] = 0; - stat_dec_atomic_write(inode); - } + if (!ret) + f2fs_drop_inmem_pages(inode); } else { ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 1, false); } @@ -2295,9 +2321,9 @@ static int f2fs_ioc_gc_range(struct file *filp, unsigned long arg) return -EROFS; end = range.start + range.len; - if (range.start < MAIN_BLKADDR(sbi) || end >= MAX_BLKADDR(sbi)) { + if (end < range.start || range.start < MAIN_BLKADDR(sbi) || + end >= MAX_BLKADDR(sbi)) return -EINVAL; - } ret = mnt_want_write_file(filp); if (ret) @@ -2421,8 +2447,10 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi, map.m_lblk += map.m_len; } - if (!fragmented) + if (!fragmented) { + total = 0; goto out; + } sec_num = DIV_ROUND_UP(total, BLKS_PER_SEC(sbi)); @@ -2452,7 +2480,7 @@ do_map: if (!(map.m_flags & F2FS_MAP_FLAGS)) { map.m_lblk = next_pgofs; - continue; + goto check; } set_inode_flag(inode, FI_DO_DEFRAG); @@ -2476,8 +2504,8 @@ do_map: } map.m_lblk = idx; - - if (idx < pg_end && cnt < blk_per_seg) +check: + if (map.m_lblk < pg_end && cnt < blk_per_seg) goto do_map; clear_inode_flag(inode, FI_DO_DEFRAG); @@ -3141,10 +3169,74 @@ static int f2fs_ioc_measure_verity(struct file *filp, unsigned long arg) return fsverity_ioctl_measure(filp, (void __user *)arg); } +static int f2fs_get_volume_name(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + char *vbuf; + int count; + int err = 0; + + vbuf = f2fs_kzalloc(sbi, MAX_VOLUME_NAME, GFP_KERNEL); + if (!vbuf) + return -ENOMEM; + + down_read(&sbi->sb_lock); + count = utf16s_to_utf8s(sbi->raw_super->volume_name, + ARRAY_SIZE(sbi->raw_super->volume_name), + UTF16_LITTLE_ENDIAN, vbuf, MAX_VOLUME_NAME); + up_read(&sbi->sb_lock); + + if (copy_to_user((char __user *)arg, vbuf, + min(FSLABEL_MAX, count))) + err = -EFAULT; + + kvfree(vbuf); + return err; +} + +static int f2fs_set_volume_name(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + char *vbuf; + int err = 0; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + vbuf = strndup_user((const char __user *)arg, FSLABEL_MAX); + if (IS_ERR(vbuf)) + return PTR_ERR(vbuf); + + err = mnt_want_write_file(filp); + if (err) + goto out; + + down_write(&sbi->sb_lock); + + memset(sbi->raw_super->volume_name, 0, + sizeof(sbi->raw_super->volume_name)); + utf8s_to_utf16s(vbuf, strlen(vbuf), UTF16_LITTLE_ENDIAN, + sbi->raw_super->volume_name, + ARRAY_SIZE(sbi->raw_super->volume_name)); + + err = f2fs_commit_super(sbi, false); + + up_write(&sbi->sb_lock); + + mnt_drop_write_file(filp); +out: + kfree(vbuf); + return err; +} + long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { if (unlikely(f2fs_cp_error(F2FS_I_SB(file_inode(filp))))) return -EIO; + if (!f2fs_is_checkpoint_ready(F2FS_I_SB(file_inode(filp)))) + return -ENOSPC; switch (cmd) { case F2FS_IOC_GETFLAGS: @@ -3213,6 +3305,10 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return f2fs_ioc_enable_verity(filp, arg); case FS_IOC_MEASURE_VERITY: return f2fs_ioc_measure_verity(filp, arg); + case F2FS_IOC_GET_VOLUME_NAME: + return f2fs_get_volume_name(filp, arg); + case F2FS_IOC_SET_VOLUME_NAME: + return f2fs_set_volume_name(filp, arg); default: return -ENOTTY; } @@ -3229,16 +3325,12 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) goto out; } - if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT)) { - ret = -EINVAL; - goto out; - } - - if (!inode_trylock(inode)) { - if (iocb->ki_flags & IOCB_NOWAIT) { + if (iocb->ki_flags & IOCB_NOWAIT) { + if (!inode_trylock(inode)) { ret = -EAGAIN; goto out; } + } else { inode_lock(inode); } @@ -3334,6 +3426,8 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case F2FS_IOC_RESIZE_FS: case FS_IOC_ENABLE_VERITY: case FS_IOC_MEASURE_VERITY: + case F2FS_IOC_GET_VOLUME_NAME: + case F2FS_IOC_SET_VOLUME_NAME: break; default: return -ENOIOCTLCMD; diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 8974672db78f..5877bd729689 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -382,6 +382,16 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi, nsearched++; } +#ifdef CONFIG_F2FS_CHECK_FS + /* + * skip selecting the invalid segno (that is failed due to block + * validity check failure during GC) to avoid endless GC loop in + * such cases. + */ + if (test_bit(segno, sm->invalid_segmap)) + goto next; +#endif + secno = GET_SEC_FROM_SEG(sbi, segno); if (sec_usage_check(sbi, secno)) @@ -627,8 +637,21 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, source_blkaddr = datablock_addr(NULL, node_page, ofs_in_node); f2fs_put_page(node_page, 1); - if (source_blkaddr != blkaddr) + if (source_blkaddr != blkaddr) { +#ifdef CONFIG_F2FS_CHECK_FS + unsigned int segno = GET_SEGNO(sbi, blkaddr); + unsigned long offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr); + + if (unlikely(check_valid_map(sbi, segno, offset))) { + if (!test_and_set_bit(segno, SIT_I(sbi)->invalid_segmap)) { + f2fs_err(sbi, "mismatched blkaddr %u (source_blkaddr %u) in seg %u\n", + blkaddr, source_blkaddr, segno); + f2fs_bug_on(sbi, 1); + } + } +#endif return false; + } return true; } @@ -1303,7 +1326,7 @@ gc_more: round++; } - if (gc_type == FG_GC) + if (gc_type == FG_GC && seg_freed) sbi->cur_victim_sec = NULL_SEGNO; if (sync) diff --git a/fs/f2fs/hash.c b/fs/f2fs/hash.c index cc82f142f811..5bc4dcd8fc03 100644 --- a/fs/f2fs/hash.c +++ b/fs/f2fs/hash.c @@ -14,6 +14,7 @@ #include <linux/f2fs_fs.h> #include <linux/cryptohash.h> #include <linux/pagemap.h> +#include <linux/unicode.h> #include "f2fs.h" @@ -67,7 +68,7 @@ static void str2hashbuf(const unsigned char *msg, size_t len, *buf++ = pad; } -f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info, +static f2fs_hash_t __f2fs_dentry_hash(const struct qstr *name_info, struct fscrypt_name *fname) { __u32 hash; @@ -103,3 +104,37 @@ f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info, f2fs_hash = cpu_to_le32(hash & ~F2FS_HASH_COL_BIT); return f2fs_hash; } + +f2fs_hash_t f2fs_dentry_hash(const struct inode *dir, + const struct qstr *name_info, struct fscrypt_name *fname) +{ +#ifdef CONFIG_UNICODE + struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb); + const struct unicode_map *um = sbi->s_encoding; + int r, dlen; + unsigned char *buff; + struct qstr folded; + + if (!name_info->len || !IS_CASEFOLDED(dir)) + goto opaque_seq; + + buff = f2fs_kzalloc(sbi, sizeof(char) * PATH_MAX, GFP_KERNEL); + if (!buff) + return -ENOMEM; + + dlen = utf8_casefold(um, name_info, buff, PATH_MAX); + if (dlen < 0) { + kvfree(buff); + goto opaque_seq; + } + folded.name = buff; + folded.len = dlen; + r = __f2fs_dentry_hash(&folded, fname); + + kvfree(buff); + return r; + +opaque_seq: +#endif + return __f2fs_dentry_hash(name_info, fname); +} diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index 3613efca8c00..896db0416f0e 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -131,6 +131,7 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page) err = f2fs_get_node_info(fio.sbi, dn->nid, &ni); if (err) { + f2fs_truncate_data_blocks_range(dn, 1); f2fs_put_dnode(dn); return err; } @@ -320,7 +321,7 @@ struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir, return NULL; } - namehash = f2fs_dentry_hash(&name, fname); + namehash = f2fs_dentry_hash(dir, &name, fname); inline_dentry = inline_data_addr(dir, ipage); @@ -580,7 +581,7 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name, f2fs_wait_on_page_writeback(ipage, NODE, true, true); - name_hash = f2fs_dentry_hash(new_name, NULL); + name_hash = f2fs_dentry_hash(dir, new_name, NULL); f2fs_update_dentry(ino, mode, &d, new_name, name_hash, bit_pos); set_page_dirty(ipage); @@ -588,6 +589,11 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name, /* we don't need to mark_inode_dirty now */ if (inode) { f2fs_i_pino_write(inode, dir->i_ino); + + /* synchronize inode page's data from inode cache */ + if (is_inode_flag_set(inode, FI_NEW_INODE)) + f2fs_update_inode(inode, page); + f2fs_put_page(page, 1); } @@ -704,7 +710,13 @@ int f2fs_inline_data_fiemap(struct inode *inode, if (IS_ERR(ipage)) return PTR_ERR(ipage); - if (!f2fs_has_inline_data(inode)) { + if ((S_ISREG(inode->i_mode) || S_ISLNK(inode->i_mode)) && + !f2fs_has_inline_data(inode)) { + err = -EAGAIN; + goto out; + } + + if (S_ISDIR(inode->i_mode) && !f2fs_has_inline_dentry(inode)) { err = -EAGAIN; goto out; } diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 06da75d418e0..db4fec30c30d 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -48,9 +48,11 @@ void f2fs_set_inode_flags(struct inode *inode) new_fl |= S_ENCRYPTED; if (file_is_verity(inode)) new_fl |= S_VERITY; + if (flags & F2FS_CASEFOLD_FL) + new_fl |= S_CASEFOLD; inode_set_flags(inode, new_fl, S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC| - S_ENCRYPTED|S_VERITY); + S_ENCRYPTED|S_VERITY|S_CASEFOLD); } static void __get_inode_rdev(struct inode *inode, struct f2fs_inode *ri) @@ -616,7 +618,7 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc) if (!is_inode_flag_set(inode, FI_DIRTY_INODE)) return 0; - if (f2fs_is_checkpoint_ready(sbi)) + if (!f2fs_is_checkpoint_ready(sbi)) return -ENOSPC; /* @@ -695,7 +697,8 @@ retry: if (err) { f2fs_update_inode_page(inode); - set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); + if (dquot_initialize_needed(inode)) + set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); } sb_end_intwrite(inode->i_sb); no_delete: @@ -705,7 +708,7 @@ no_delete: stat_dec_inline_dir(inode); stat_dec_inline_inode(inode); - if (likely(!is_set_ckpt_flags(sbi, CP_ERROR_FLAG) && + if (likely(!f2fs_cp_error(sbi) && !is_sbi_flag_set(sbi, SBI_CP_DISABLED))) f2fs_bug_on(sbi, is_inode_flag_set(inode, FI_DIRTY_INODE)); else diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index c5b99042e6f2..4faf06e8bf89 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -272,9 +272,8 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode, if (unlikely(f2fs_cp_error(sbi))) return -EIO; - err = f2fs_is_checkpoint_ready(sbi); - if (err) - return err; + if (!f2fs_is_checkpoint_ready(sbi)) + return -ENOSPC; err = dquot_initialize(dir); if (err) @@ -321,9 +320,8 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir, if (unlikely(f2fs_cp_error(sbi))) return -EIO; - err = f2fs_is_checkpoint_ready(sbi); - if (err) - return err; + if (!f2fs_is_checkpoint_ready(sbi)) + return -ENOSPC; err = fscrypt_prepare_link(old_dentry, dir, dentry); if (err) @@ -489,6 +487,17 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry, goto out_iput; } out_splice: +#ifdef CONFIG_UNICODE + if (!inode && IS_CASEFOLDED(dir)) { + /* Eventually we want to call d_add_ci(dentry, NULL) + * for negative dentries in the encoding case as + * well. For now, prevent the negative dentry + * from being cached. + */ + trace_f2fs_lookup_end(dir, dentry, ino, err); + return NULL; + } +#endif new = d_splice_alias(inode, dentry); err = PTR_ERR_OR_ZERO(new); trace_f2fs_lookup_end(dir, dentry, ino, err); @@ -537,6 +546,16 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry) goto fail; } f2fs_delete_entry(de, page, dir, inode); +#ifdef CONFIG_UNICODE + /* VFS negative dentries are incompatible with Encoding and + * Case-insensitiveness. Eventually we'll want avoid + * invalidating the dentries here, alongside with returning the + * negative dentries at f2fs_lookup(), when it is better + * supported by the VFS for the CI case. + */ + if (IS_CASEFOLDED(dir)) + d_invalidate(dentry); +#endif f2fs_unlock_op(sbi); if (IS_DIRSYNC(dir)) @@ -571,9 +590,8 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry, if (unlikely(f2fs_cp_error(sbi))) return -EIO; - err = f2fs_is_checkpoint_ready(sbi); - if (err) - return err; + if (!f2fs_is_checkpoint_ready(sbi)) + return -ENOSPC; err = fscrypt_prepare_symlink(dir, symname, len, dir->i_sb->s_blocksize, &disk_link); @@ -703,9 +721,8 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry, if (unlikely(f2fs_cp_error(sbi))) return -EIO; - err = f2fs_is_checkpoint_ready(sbi); - if (err) - return err; + if (!f2fs_is_checkpoint_ready(sbi)) + return -ENOSPC; err = dquot_initialize(dir); if (err) @@ -804,6 +821,8 @@ static int f2fs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) if (unlikely(f2fs_cp_error(sbi))) return -EIO; + if (!f2fs_is_checkpoint_ready(sbi)) + return -ENOSPC; if (IS_ENCRYPTED(dir) || DUMMY_ENCRYPTION_ENABLED(sbi)) { int err = fscrypt_get_encryption_info(dir); @@ -840,9 +859,8 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, if (unlikely(f2fs_cp_error(sbi))) return -EIO; - err = f2fs_is_checkpoint_ready(sbi); - if (err) - return err; + if (!f2fs_is_checkpoint_ready(sbi)) + return -ENOSPC; if (is_inode_flag_set(new_dir, FI_PROJ_INHERIT) && (!projid_eq(F2FS_I(new_dir)->i_projid, @@ -1035,9 +1053,8 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, if (unlikely(f2fs_cp_error(sbi))) return -EIO; - err = f2fs_is_checkpoint_ready(sbi); - if (err) - return err; + if (!f2fs_is_checkpoint_ready(sbi)) + return -ENOSPC; if ((is_inode_flag_set(new_dir, FI_PROJ_INHERIT) && !projid_eq(F2FS_I(new_dir)->i_projid, @@ -1250,6 +1267,7 @@ const struct inode_operations f2fs_dir_inode_operations = { #ifdef CONFIG_F2FS_FS_XATTR .listxattr = f2fs_listxattr, #endif + .fiemap = f2fs_fiemap, }; const struct inode_operations f2fs_symlink_inode_operations = { diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index a18b2a895771..8b66bc4c004b 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -1524,7 +1524,8 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted, if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) goto redirty_out; - if (wbc->sync_mode == WB_SYNC_NONE && + if (!is_sbi_flag_set(sbi, SBI_CP_DISABLED) && + wbc->sync_mode == WB_SYNC_NONE && IS_DNODE(page) && is_cold_node(page)) goto redirty_out; @@ -1762,6 +1763,47 @@ out: return ret ? -EIO: 0; } +static int f2fs_match_ino(struct inode *inode, unsigned long ino, void *data) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + bool clean; + + if (inode->i_ino != ino) + return 0; + + if (!is_inode_flag_set(inode, FI_DIRTY_INODE)) + return 0; + + spin_lock(&sbi->inode_lock[DIRTY_META]); + clean = list_empty(&F2FS_I(inode)->gdirty_list); + spin_unlock(&sbi->inode_lock[DIRTY_META]); + + if (clean) + return 0; + + inode = igrab(inode); + if (!inode) + return 0; + return 1; +} + +static bool flush_dirty_inode(struct page *page) +{ + struct f2fs_sb_info *sbi = F2FS_P_SB(page); + struct inode *inode; + nid_t ino = ino_of_node(page); + + inode = find_inode_nowait(sbi->sb, ino, f2fs_match_ino, NULL); + if (!inode) + return false; + + f2fs_update_inode(inode, page); + unlock_page(page); + + iput(inode); + return true; +} + int f2fs_sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc, bool do_balance, enum iostat_type io_type) @@ -1785,6 +1827,7 @@ next_step: for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; bool submitted = false; + bool may_dirty = true; /* give a priority to WB_SYNC threads */ if (atomic_read(&sbi->wb_sync_req[NODE]) && @@ -1832,6 +1875,13 @@ continue_unlock: goto lock_node; } + /* flush dirty inode */ + if (IS_INODE(page) && may_dirty) { + may_dirty = false; + if (flush_dirty_inode(page)) + goto lock_node; + } + f2fs_wait_on_page_writeback(page, NODE, true, true); if (!clear_page_dirty_for_io(page)) @@ -1860,7 +1910,8 @@ continue_unlock: } if (step < 2) { - if (wbc->sync_mode == WB_SYNC_NONE && step == 1) + if (!is_sbi_flag_set(sbi, SBI_CP_DISABLED) && + wbc->sync_mode == WB_SYNC_NONE && step == 1) goto out; step++; goto next_step; @@ -2964,7 +3015,7 @@ static int init_node_manager(struct f2fs_sb_info *sbi) /* not used nids: 0, node, meta, (and root counted as valid node) */ nm_i->available_nids = nm_i->max_nid - sbi->total_valid_node_count - - sbi->nquota_files - F2FS_RESERVED_NODE_NUM; + F2FS_RESERVED_NODE_NUM; nm_i->nid_cnt[FREE_NID] = 0; nm_i->nid_cnt[PREALLOC_NID] = 0; nm_i->nat_cnt = 0; diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index a661ac32e829..808709581481 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -185,8 +185,6 @@ bool f2fs_need_SSR(struct f2fs_sb_info *sbi) void f2fs_register_inmem_page(struct inode *inode, struct page *page) { - struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct f2fs_inode_info *fi = F2FS_I(inode); struct inmem_pages *new; f2fs_trace_pid(page); @@ -200,15 +198,11 @@ void f2fs_register_inmem_page(struct inode *inode, struct page *page) INIT_LIST_HEAD(&new->list); /* increase reference count with clean state */ - mutex_lock(&fi->inmem_lock); get_page(page); - list_add_tail(&new->list, &fi->inmem_pages); - spin_lock(&sbi->inode_lock[ATOMIC_FILE]); - if (list_empty(&fi->inmem_ilist)) - list_add_tail(&fi->inmem_ilist, &sbi->inode_list[ATOMIC_FILE]); - spin_unlock(&sbi->inode_lock[ATOMIC_FILE]); + mutex_lock(&F2FS_I(inode)->inmem_lock); + list_add_tail(&new->list, &F2FS_I(inode)->inmem_pages); inc_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES); - mutex_unlock(&fi->inmem_lock); + mutex_unlock(&F2FS_I(inode)->inmem_lock); trace_f2fs_register_inmem_page(page, INMEM); } @@ -330,19 +324,17 @@ void f2fs_drop_inmem_pages(struct inode *inode) mutex_lock(&fi->inmem_lock); __revoke_inmem_pages(inode, &fi->inmem_pages, true, false, true); - - if (list_empty(&fi->inmem_pages)) { - spin_lock(&sbi->inode_lock[ATOMIC_FILE]); - if (!list_empty(&fi->inmem_ilist)) - list_del_init(&fi->inmem_ilist); - spin_unlock(&sbi->inode_lock[ATOMIC_FILE]); - } mutex_unlock(&fi->inmem_lock); } clear_inode_flag(inode, FI_ATOMIC_FILE); fi->i_gc_failures[GC_FAILURE_ATOMIC] = 0; stat_dec_atomic_write(inode); + + spin_lock(&sbi->inode_lock[ATOMIC_FILE]); + if (!list_empty(&fi->inmem_ilist)) + list_del_init(&fi->inmem_ilist); + spin_unlock(&sbi->inode_lock[ATOMIC_FILE]); } void f2fs_drop_inmem_page(struct inode *inode, struct page *page) @@ -471,11 +463,6 @@ int f2fs_commit_inmem_pages(struct inode *inode) mutex_lock(&fi->inmem_lock); err = __f2fs_commit_inmem_pages(inode); - - spin_lock(&sbi->inode_lock[ATOMIC_FILE]); - if (!list_empty(&fi->inmem_ilist)) - list_del_init(&fi->inmem_ilist); - spin_unlock(&sbi->inode_lock[ATOMIC_FILE]); mutex_unlock(&fi->inmem_lock); clear_inode_flag(inode, FI_ATOMIC_COMMIT); @@ -501,7 +488,7 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need) if (need && excess_cached_nats(sbi)) f2fs_balance_fs_bg(sbi); - if (f2fs_is_checkpoint_ready(sbi)) + if (!f2fs_is_checkpoint_ready(sbi)) return; /* @@ -817,9 +804,13 @@ static void __remove_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno, if (test_and_clear_bit(segno, dirty_i->dirty_segmap[t])) dirty_i->nr_dirty[t]--; - if (get_valid_blocks(sbi, segno, true) == 0) + if (get_valid_blocks(sbi, segno, true) == 0) { clear_bit(GET_SEC_FROM_SEG(sbi, segno), dirty_i->victim_secmap); +#ifdef CONFIG_F2FS_CHECK_FS + clear_bit(segno, SIT_I(sbi)->invalid_segmap); +#endif + } } } @@ -2084,6 +2075,13 @@ static void destroy_discard_cmd_control(struct f2fs_sb_info *sbi) f2fs_stop_discard_thread(sbi); + /* + * Recovery can cache discard commands, so in error path of + * fill_super(), it needs to give a chance to handle them. + */ + if (unlikely(atomic_read(&dcc->discard_cmd_cnt))) + f2fs_issue_discard_timeout(sbi); + kvfree(dcc); SM_I(sbi)->dcc_info = NULL; } @@ -2156,9 +2154,11 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del) if (!f2fs_test_and_set_bit(offset, se->discard_map)) sbi->discard_blks--; - /* don't overwrite by SSR to keep node chain */ - if (IS_NODESEG(se->type) && - !is_sbi_flag_set(sbi, SBI_CP_DISABLED)) { + /* + * SSR should never reuse block which is checkpointed + * or newly invalidated. + */ + if (!is_sbi_flag_set(sbi, SBI_CP_DISABLED)) { if (!f2fs_test_and_set_bit(offset, se->ckpt_valid_map)) se->ckpt_valid_blocks++; } @@ -3116,12 +3116,14 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, f2fs_inode_chksum_set(sbi, page); } + if (F2FS_IO_ALIGNED(sbi)) + fio->retry = false; + if (add_list) { struct f2fs_bio_info *io; INIT_LIST_HEAD(&fio->list); fio->in_list = true; - fio->retry = false; io = sbi->write_io[fio->type] + fio->temp; spin_lock(&io->io_lock); list_add_tail(&fio->list, &io->io_list); @@ -3447,11 +3449,6 @@ static int read_compacted_summaries(struct f2fs_sb_info *sbi) seg_i = CURSEG_I(sbi, i); segno = le32_to_cpu(ckpt->cur_data_segno[i]); blk_off = le16_to_cpu(ckpt->cur_data_blkoff[i]); - if (blk_off > ENTRIES_IN_SUM) { - f2fs_bug_on(sbi, 1); - f2fs_put_page(page, 1); - return -EFAULT; - } seg_i->next_segno = segno; reset_curseg(sbi, i, 0); seg_i->alloc_type = ckpt->alloc_type[i]; @@ -3941,8 +3938,8 @@ static int build_sit_info(struct f2fs_sb_info *sbi) struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi); struct sit_info *sit_i; unsigned int sit_segs, start; - char *src_bitmap; - unsigned int bitmap_size; + char *src_bitmap, *bitmap; + unsigned int bitmap_size, main_bitmap_size, sit_bitmap_size; /* allocate memory for SIT information */ sit_i = f2fs_kzalloc(sbi, sizeof(struct sit_info), GFP_KERNEL); @@ -3958,33 +3955,37 @@ static int build_sit_info(struct f2fs_sb_info *sbi) if (!sit_i->sentries) return -ENOMEM; - bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi)); - sit_i->dirty_sentries_bitmap = f2fs_kvzalloc(sbi, bitmap_size, + main_bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi)); + sit_i->dirty_sentries_bitmap = f2fs_kvzalloc(sbi, main_bitmap_size, GFP_KERNEL); if (!sit_i->dirty_sentries_bitmap) return -ENOMEM; +#ifdef CONFIG_F2FS_CHECK_FS + bitmap_size = MAIN_SEGS(sbi) * SIT_VBLOCK_MAP_SIZE * 4; +#else + bitmap_size = MAIN_SEGS(sbi) * SIT_VBLOCK_MAP_SIZE * 3; +#endif + sit_i->bitmap = f2fs_kvzalloc(sbi, bitmap_size, GFP_KERNEL); + if (!sit_i->bitmap) + return -ENOMEM; + + bitmap = sit_i->bitmap; + for (start = 0; start < MAIN_SEGS(sbi); start++) { - sit_i->sentries[start].cur_valid_map - = f2fs_kzalloc(sbi, SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); - sit_i->sentries[start].ckpt_valid_map - = f2fs_kzalloc(sbi, SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); - if (!sit_i->sentries[start].cur_valid_map || - !sit_i->sentries[start].ckpt_valid_map) - return -ENOMEM; + sit_i->sentries[start].cur_valid_map = bitmap; + bitmap += SIT_VBLOCK_MAP_SIZE; + + sit_i->sentries[start].ckpt_valid_map = bitmap; + bitmap += SIT_VBLOCK_MAP_SIZE; #ifdef CONFIG_F2FS_CHECK_FS - sit_i->sentries[start].cur_valid_map_mir - = f2fs_kzalloc(sbi, SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); - if (!sit_i->sentries[start].cur_valid_map_mir) - return -ENOMEM; + sit_i->sentries[start].cur_valid_map_mir = bitmap; + bitmap += SIT_VBLOCK_MAP_SIZE; #endif - sit_i->sentries[start].discard_map - = f2fs_kzalloc(sbi, SIT_VBLOCK_MAP_SIZE, - GFP_KERNEL); - if (!sit_i->sentries[start].discard_map) - return -ENOMEM; + sit_i->sentries[start].discard_map = bitmap; + bitmap += SIT_VBLOCK_MAP_SIZE; } sit_i->tmp_map = f2fs_kzalloc(sbi, SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); @@ -4004,17 +4005,23 @@ static int build_sit_info(struct f2fs_sb_info *sbi) sit_segs = le32_to_cpu(raw_super->segment_count_sit) >> 1; /* setup SIT bitmap from ckeckpoint pack */ - bitmap_size = __bitmap_size(sbi, SIT_BITMAP); + sit_bitmap_size = __bitmap_size(sbi, SIT_BITMAP); src_bitmap = __bitmap_ptr(sbi, SIT_BITMAP); - sit_i->sit_bitmap = kmemdup(src_bitmap, bitmap_size, GFP_KERNEL); + sit_i->sit_bitmap = kmemdup(src_bitmap, sit_bitmap_size, GFP_KERNEL); if (!sit_i->sit_bitmap) return -ENOMEM; #ifdef CONFIG_F2FS_CHECK_FS - sit_i->sit_bitmap_mir = kmemdup(src_bitmap, bitmap_size, GFP_KERNEL); + sit_i->sit_bitmap_mir = kmemdup(src_bitmap, + sit_bitmap_size, GFP_KERNEL); if (!sit_i->sit_bitmap_mir) return -ENOMEM; + + sit_i->invalid_segmap = f2fs_kvzalloc(sbi, + main_bitmap_size, GFP_KERNEL); + if (!sit_i->invalid_segmap) + return -ENOMEM; #endif /* init SIT information */ @@ -4023,7 +4030,7 @@ static int build_sit_info(struct f2fs_sb_info *sbi) sit_i->sit_base_addr = le32_to_cpu(raw_super->sit_blkaddr); sit_i->sit_blocks = sit_segs << sbi->log_blocks_per_seg; sit_i->written_valid_blocks = 0; - sit_i->bitmap_size = bitmap_size; + sit_i->bitmap_size = sit_bitmap_size; sit_i->dirty_sentries = 0; sit_i->sents_per_block = SIT_ENTRY_PER_BLOCK; sit_i->elapsed_time = le64_to_cpu(sbi->ckpt->elapsed_time); @@ -4161,7 +4168,6 @@ static int build_sit_entries(struct f2fs_sb_info *sbi) if (start >= MAIN_SEGS(sbi)) { f2fs_err(sbi, "Wrong journal entry on segno %u", start); - set_sbi_flag(sbi, SBI_NEED_FSCK); err = -EFSCORRUPTED; break; } @@ -4201,7 +4207,6 @@ static int build_sit_entries(struct f2fs_sb_info *sbi) if (!err && total_node_blocks != valid_node_count(sbi)) { f2fs_err(sbi, "SIT is corrupted node# %u vs %u", total_node_blocks, valid_node_count(sbi)); - set_sbi_flag(sbi, SBI_NEED_FSCK); err = -EFSCORRUPTED; } @@ -4492,21 +4497,12 @@ static void destroy_free_segmap(struct f2fs_sb_info *sbi) static void destroy_sit_info(struct f2fs_sb_info *sbi) { struct sit_info *sit_i = SIT_I(sbi); - unsigned int start; if (!sit_i) return; - if (sit_i->sentries) { - for (start = 0; start < MAIN_SEGS(sbi); start++) { - kvfree(sit_i->sentries[start].cur_valid_map); -#ifdef CONFIG_F2FS_CHECK_FS - kvfree(sit_i->sentries[start].cur_valid_map_mir); -#endif - kvfree(sit_i->sentries[start].ckpt_valid_map); - kvfree(sit_i->sentries[start].discard_map); - } - } + if (sit_i->sentries) + kvfree(sit_i->bitmap); kvfree(sit_i->tmp_map); kvfree(sit_i->sentries); @@ -4517,6 +4513,7 @@ static void destroy_sit_info(struct f2fs_sb_info *sbi) kvfree(sit_i->sit_bitmap); #ifdef CONFIG_F2FS_CHECK_FS kvfree(sit_i->sit_bitmap_mir); + kvfree(sit_i->invalid_segmap); #endif kvfree(sit_i); } diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index b74602813a05..325781a1ae4d 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -226,9 +226,13 @@ struct sit_info { block_t sit_base_addr; /* start block address of SIT area */ block_t sit_blocks; /* # of blocks used by SIT area */ block_t written_valid_blocks; /* # of valid blocks in main area */ + char *bitmap; /* all bitmaps pointer */ char *sit_bitmap; /* SIT bitmap pointer */ #ifdef CONFIG_F2FS_CHECK_FS char *sit_bitmap_mir; /* SIT bitmap mirror */ + + /* bitmap of segments to be ignored by GC in case of errors */ + unsigned long *invalid_segmap; #endif unsigned int bitmap_size; /* SIT bitmap size */ @@ -582,13 +586,13 @@ static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi, reserved_sections(sbi) + needed); } -static inline int f2fs_is_checkpoint_ready(struct f2fs_sb_info *sbi) +static inline bool f2fs_is_checkpoint_ready(struct f2fs_sb_info *sbi) { if (likely(!is_sbi_flag_set(sbi, SBI_CP_DISABLED))) - return 0; + return true; if (likely(!has_not_enough_free_secs(sbi, 0, 0))) - return 0; - return -ENOSPC; + return true; + return false; } static inline bool excess_prefree_segs(struct f2fs_sb_info *sbi) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index f43befda0e1a..1443cee15863 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -23,6 +23,7 @@ #include <linux/f2fs_fs.h> #include <linux/sysfs.h> #include <linux/quota.h> +#include <linux/unicode.h> #include "f2fs.h" #include "node.h" @@ -222,6 +223,36 @@ void f2fs_printk(struct f2fs_sb_info *sbi, const char *fmt, ...) va_end(args); } +#ifdef CONFIG_UNICODE +static const struct f2fs_sb_encodings { + __u16 magic; + char *name; + char *version; +} f2fs_sb_encoding_map[] = { + {F2FS_ENC_UTF8_12_1, "utf8", "12.1.0"}, +}; + +static int f2fs_sb_read_encoding(const struct f2fs_super_block *sb, + const struct f2fs_sb_encodings **encoding, + __u16 *flags) +{ + __u16 magic = le16_to_cpu(sb->s_encoding); + int i; + + for (i = 0; i < ARRAY_SIZE(f2fs_sb_encoding_map); i++) + if (magic == f2fs_sb_encoding_map[i].magic) + break; + + if (i >= ARRAY_SIZE(f2fs_sb_encoding_map)) + return -EINVAL; + + *encoding = &f2fs_sb_encoding_map[i]; + *flags = le16_to_cpu(sb->s_encoding_flags); + + return 0; +} +#endif + static inline void limit_reserve_root(struct f2fs_sb_info *sbi) { block_t limit = min((sbi->user_block_count << 1) / 1000, @@ -798,6 +829,13 @@ static int parse_options(struct super_block *sb, char *options) return -EINVAL; } #endif +#ifndef CONFIG_UNICODE + if (f2fs_sb_has_casefold(sbi)) { + f2fs_err(sbi, + "Filesystem with casefold feature cannot be mounted without CONFIG_UNICODE"); + return -EINVAL; + } +#endif if (F2FS_IO_SIZE_BITS(sbi) && !test_opt(sbi, LFS)) { f2fs_err(sbi, "Should set mode=lfs with %uKB-sized IO", @@ -873,7 +911,21 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb) static int f2fs_drop_inode(struct inode *inode) { + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); int ret; + + /* + * during filesystem shutdown, if checkpoint is disabled, + * drop useless meta/node dirty pages. + */ + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { + if (inode->i_ino == F2FS_NODE_INO(sbi) || + inode->i_ino == F2FS_META_INO(sbi)) { + trace_f2fs_drop_inode(inode, 1); + return 1; + } + } + /* * This is to avoid a deadlock condition like below. * writeback_single_inode(inode) @@ -1091,6 +1143,9 @@ static void f2fs_put_super(struct super_block *sb) destroy_percpu_info(sbi); for (i = 0; i < NR_PAGE_TYPE; i++) kvfree(sbi->write_io[i]); +#ifdef CONFIG_UNICODE + utf8_unload(sbi->s_encoding); +#endif kvfree(sbi); } @@ -1216,8 +1271,7 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf) else buf->f_bavail = 0; - avail_node_count = sbi->total_node_count - sbi->nquota_files - - F2FS_RESERVED_NODE_NUM; + avail_node_count = sbi->total_node_count - F2FS_RESERVED_NODE_NUM; if (avail_node_count > user_block_count) { buf->f_files = user_block_count; @@ -1524,6 +1578,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) bool need_stop_gc = false; bool no_extent_cache = !test_opt(sbi, EXTENT_CACHE); bool disable_checkpoint = test_opt(sbi, DISABLE_CHECKPOINT); + bool no_io_align = !F2FS_IO_ALIGNED(sbi); bool checkpoint_changed; #ifdef CONFIG_QUOTA int i, j; @@ -1603,6 +1658,12 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) goto restore_opts; } + if (no_io_align == !!F2FS_IO_ALIGNED(sbi)) { + err = -EINVAL; + f2fs_warn(sbi, "switch io_bits option is not allowed"); + goto restore_opts; + } + if ((*flags & SB_RDONLY) && test_opt(sbi, DISABLE_CHECKPOINT)) { err = -EINVAL; f2fs_warn(sbi, "disabling checkpoint not compatible with read-only"); @@ -1981,6 +2042,12 @@ static int f2fs_quota_on(struct super_block *sb, int type, int format_id, struct inode *inode; int err; + /* if quota sysfile exists, deny enabling quota with specific file */ + if (f2fs_sb_has_quota_ino(F2FS_SB(sb))) { + f2fs_err(F2FS_SB(sb), "quota sysfile already exists"); + return -EBUSY; + } + err = f2fs_quota_sync(sb, type); if (err) return err; @@ -2000,7 +2067,7 @@ static int f2fs_quota_on(struct super_block *sb, int type, int format_id, return 0; } -static int f2fs_quota_off(struct super_block *sb, int type) +static int __f2fs_quota_off(struct super_block *sb, int type) { struct inode *inode = sb_dqopt(sb)->files[type]; int err; @@ -2026,13 +2093,30 @@ out_put: return err; } +static int f2fs_quota_off(struct super_block *sb, int type) +{ + struct f2fs_sb_info *sbi = F2FS_SB(sb); + int err; + + err = __f2fs_quota_off(sb, type); + + /* + * quotactl can shutdown journalled quota, result in inconsistence + * between quota record and fs data by following updates, tag the + * flag to let fsck be aware of it. + */ + if (is_journalled_quota(sbi)) + set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); + return err; +} + void f2fs_quota_off_umount(struct super_block *sb) { int type; int err; for (type = 0; type < MAXQUOTAS; type++) { - err = f2fs_quota_off(sb, type); + err = __f2fs_quota_off(sb, type); if (err) { int ret = dquot_quota_off(sb, type); @@ -2617,8 +2701,7 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi) } valid_node_count = le32_to_cpu(ckpt->valid_node_count); - avail_node_count = sbi->total_node_count - sbi->nquota_files - - F2FS_RESERVED_NODE_NUM; + avail_node_count = sbi->total_node_count - F2FS_RESERVED_NODE_NUM; if (valid_node_count > avail_node_count) { f2fs_err(sbi, "Wrong valid_node_count: %u, avail_node_count: %u", valid_node_count, avail_node_count); @@ -2657,10 +2740,10 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi) } } for (i = 0; i < NR_CURSEG_NODE_TYPE; i++) { - for (j = i; j < NR_CURSEG_DATA_TYPE; j++) { + for (j = 0; j < NR_CURSEG_DATA_TYPE; j++) { if (le32_to_cpu(ckpt->cur_node_segno[i]) == le32_to_cpu(ckpt->cur_data_segno[j])) { - f2fs_err(sbi, "Data segment (%u) and Data segment (%u) has the same segno: %u", + f2fs_err(sbi, "Node segment (%u) and Data segment (%u) has the same segno: %u", i, j, le32_to_cpu(ckpt->cur_node_segno[i])); return 1; @@ -3033,6 +3116,53 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi) return 0; } +static int f2fs_setup_casefold(struct f2fs_sb_info *sbi) +{ +#ifdef CONFIG_UNICODE + if (f2fs_sb_has_casefold(sbi) && !sbi->s_encoding) { + const struct f2fs_sb_encodings *encoding_info; + struct unicode_map *encoding; + __u16 encoding_flags; + + if (f2fs_sb_has_encrypt(sbi)) { + f2fs_err(sbi, + "Can't mount with encoding and encryption"); + return -EINVAL; + } + + if (f2fs_sb_read_encoding(sbi->raw_super, &encoding_info, + &encoding_flags)) { + f2fs_err(sbi, + "Encoding requested by superblock is unknown"); + return -EINVAL; + } + + encoding = utf8_load(encoding_info->version); + if (IS_ERR(encoding)) { + f2fs_err(sbi, + "can't mount with superblock charset: %s-%s " + "not supported by the kernel. flags: 0x%x.", + encoding_info->name, encoding_info->version, + encoding_flags); + return PTR_ERR(encoding); + } + f2fs_info(sbi, "Using encoding defined by superblock: " + "%s-%s with flags 0x%hx", encoding_info->name, + encoding_info->version?:"\b", encoding_flags); + + sbi->s_encoding = encoding; + sbi->s_encoding_flags = encoding_flags; + sbi->sb->s_d_op = &f2fs_dentry_ops; + } +#else + if (f2fs_sb_has_casefold(sbi)) { + f2fs_err(sbi, "Filesystem with casefold feature cannot be mounted without CONFIG_UNICODE"); + return -EINVAL; + } +#endif + return 0; +} + static void f2fs_tuning_parameters(struct f2fs_sb_info *sbi) { struct f2fs_sm_info *sm_i = SM_I(sbi); @@ -3129,6 +3259,10 @@ try_onemore: le32_to_cpu(raw_super->log_blocksize); sb->s_max_links = F2FS_LINK_MAX; + err = f2fs_setup_casefold(sbi); + if (err) + goto free_options; + #ifdef CONFIG_QUOTA sb->dq_op = &f2fs_quota_operations; sb->s_qcop = &f2fs_quotactl_ops; @@ -3207,7 +3341,7 @@ try_onemore: if (err) goto free_bio_info; - if (F2FS_IO_SIZE(sbi) > 1) { + if (F2FS_IO_ALIGNED(sbi)) { sbi->write_io_dummy = mempool_create_page_pool(2 * (F2FS_IO_SIZE(sbi) - 1), 0); if (!sbi->write_io_dummy) { @@ -3482,6 +3616,10 @@ free_percpu: free_bio_info: for (i = 0; i < NR_PAGE_TYPE; i++) kvfree(sbi->write_io[i]); + +#ifdef CONFIG_UNICODE + utf8_unload(sbi->s_encoding); +#endif free_options: #ifdef CONFIG_QUOTA for (i = 0; i < MAXQUOTAS; i++) diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index 0cd64f994068..b558b64a4c9c 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -10,6 +10,7 @@ #include <linux/proc_fs.h> #include <linux/f2fs_fs.h> #include <linux/seq_file.h> +#include <linux/unicode.h> #include "f2fs.h" #include "segment.h" @@ -81,6 +82,19 @@ static ssize_t unusable_show(struct f2fs_attr *a, (unsigned long long)unusable); } +static ssize_t encoding_show(struct f2fs_attr *a, + struct f2fs_sb_info *sbi, char *buf) +{ +#ifdef CONFIG_UNICODE + if (f2fs_sb_has_casefold(sbi)) + return snprintf(buf, PAGE_SIZE, "%s (%d.%d.%d)\n", + sbi->s_encoding->charset, + (sbi->s_encoding->version >> 16) & 0xff, + (sbi->s_encoding->version >> 8) & 0xff, + sbi->s_encoding->version & 0xff); +#endif + return snprintf(buf, PAGE_SIZE, "(none)"); +} static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) @@ -137,6 +151,9 @@ static ssize_t features_show(struct f2fs_attr *a, if (f2fs_sb_has_sb_chksum(sbi)) len += snprintf(buf + len, PAGE_SIZE - len, "%s%s", len ? ", " : "", "sb_checksum"); + if (f2fs_sb_has_casefold(sbi)) + len += snprintf(buf + len, PAGE_SIZE - len, "%s%s", + len ? ", " : "", "casefold"); len += snprintf(buf + len, PAGE_SIZE - len, "\n"); return len; } @@ -369,6 +386,7 @@ enum feat_id { FEAT_LOST_FOUND, FEAT_VERITY, FEAT_SB_CHECKSUM, + FEAT_CASEFOLD, }; static ssize_t f2fs_feature_show(struct f2fs_attr *a, @@ -387,6 +405,7 @@ static ssize_t f2fs_feature_show(struct f2fs_attr *a, case FEAT_LOST_FOUND: case FEAT_VERITY: case FEAT_SB_CHECKSUM: + case FEAT_CASEFOLD: return snprintf(buf, PAGE_SIZE, "supported\n"); } return 0; @@ -460,6 +479,7 @@ F2FS_GENERAL_RO_ATTR(lifetime_write_kbytes); F2FS_GENERAL_RO_ATTR(features); F2FS_GENERAL_RO_ATTR(current_reserved_blocks); F2FS_GENERAL_RO_ATTR(unusable); +F2FS_GENERAL_RO_ATTR(encoding); #ifdef CONFIG_FS_ENCRYPTION F2FS_FEATURE_RO_ATTR(encryption, FEAT_CRYPTO); @@ -479,6 +499,7 @@ F2FS_FEATURE_RO_ATTR(lost_found, FEAT_LOST_FOUND); F2FS_FEATURE_RO_ATTR(verity, FEAT_VERITY); #endif F2FS_FEATURE_RO_ATTR(sb_checksum, FEAT_SB_CHECKSUM); +F2FS_FEATURE_RO_ATTR(casefold, FEAT_CASEFOLD); #define ATTR_LIST(name) (&f2fs_attr_##name.attr) static struct attribute *f2fs_attrs[] = { @@ -523,6 +544,7 @@ static struct attribute *f2fs_attrs[] = { ATTR_LIST(features), ATTR_LIST(reserved_blocks), ATTR_LIST(current_reserved_blocks), + ATTR_LIST(encoding), NULL, }; ATTRIBUTE_GROUPS(f2fs); @@ -546,6 +568,7 @@ static struct attribute *f2fs_feat_attrs[] = { ATTR_LIST(verity), #endif ATTR_LIST(sb_checksum), + ATTR_LIST(casefold), NULL, }; ATTRIBUTE_GROUPS(f2fs_feat); diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index b32c45621679..181900af2576 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -21,6 +21,7 @@ #include <linux/posix_acl_xattr.h> #include "f2fs.h" #include "xattr.h" +#include "segment.h" static int f2fs_xattr_generic_get(const struct xattr_handler *handler, struct dentry *unused, struct inode *inode, @@ -729,6 +730,11 @@ int f2fs_setxattr(struct inode *inode, int index, const char *name, struct f2fs_sb_info *sbi = F2FS_I_SB(inode); int err; + if (unlikely(f2fs_cp_error(sbi))) + return -EIO; + if (!f2fs_is_checkpoint_ready(sbi)) + return -ENOSPC; + err = dquot_initialize(inode); if (err) return err; |