diff options
Diffstat (limited to 'fs')
46 files changed, 1012 insertions, 718 deletions
diff --git a/fs/bcachefs/alloc_foreground.c b/fs/bcachefs/alloc_foreground.c index cabf866c7956..618d2ff0292e 100644 --- a/fs/bcachefs/alloc_foreground.c +++ b/fs/bcachefs/alloc_foreground.c @@ -496,12 +496,6 @@ again: for (alloc_cursor = max(alloc_cursor, bkey_start_offset(k.k)); alloc_cursor < k.k->p.offset; alloc_cursor++) { - ret = btree_trans_too_many_iters(trans); - if (ret) { - ob = ERR_PTR(ret); - break; - } - s->buckets_seen++; u64 bucket = alloc_cursor & ~(~0ULL << 56); diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c index cc4f0963c0c5..9138944c5ae6 100644 --- a/fs/bcachefs/fsck.c +++ b/fs/bcachefs/fsck.c @@ -283,6 +283,7 @@ static int reattach_inode(struct btree_trans *trans, struct bch_inode_unpacked *inode, u32 inode_snapshot) { + struct bch_fs *c = trans->c; struct bch_hash_info dir_hash; struct bch_inode_unpacked lostfound; char name_buf[20]; @@ -317,7 +318,7 @@ static int reattach_inode(struct btree_trans *trans, return ret; } - dir_hash = bch2_hash_info_init(trans->c, &lostfound); + dir_hash = bch2_hash_info_init(c, &lostfound); name = (struct qstr) QSTR(name_buf); @@ -330,8 +331,10 @@ static int reattach_inode(struct btree_trans *trans, inode->bi_subvol ?: inode->bi_inum, &dir_offset, STR_HASH_must_create); - if (ret) + if (ret) { + bch_err_msg(c, ret, "error creating dirent"); return ret; + } inode->bi_dir = lostfound.bi_inum; inode->bi_dir_offset = dir_offset; diff --git a/fs/bcachefs/journal_reclaim.c b/fs/bcachefs/journal_reclaim.c index d8a630742887..70b998d9f19c 100644 --- a/fs/bcachefs/journal_reclaim.c +++ b/fs/bcachefs/journal_reclaim.c @@ -206,6 +206,7 @@ void bch2_journal_space_available(struct journal *j) if (nr_online < metadata_replicas_required(c)) { struct printbuf buf = PRINTBUF; + buf.atomic++; prt_printf(&buf, "insufficient writeable journal devices available: have %u, need %u\n" "rw journal devs:", nr_online, metadata_replicas_required(c)); diff --git a/fs/bcachefs/mean_and_variance.h b/fs/bcachefs/mean_and_variance.h index 4fcf062dd22c..47e4a3c3d26e 100644 --- a/fs/bcachefs/mean_and_variance.h +++ b/fs/bcachefs/mean_and_variance.h @@ -111,11 +111,11 @@ static inline u128_u u128_shl(u128_u i, s8 shift) { u128_u r; - r.lo = i.lo << shift; + r.lo = i.lo << (shift & 63); if (shift < 64) - r.hi = (i.hi << shift) | (i.lo >> (64 - shift)); + r.hi = (i.hi << (shift & 63)) | (i.lo >> (-shift & 63)); else { - r.hi = i.lo << (shift - 64); + r.hi = i.lo << (-shift & 63); r.lo = 0; } return r; diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 5ae8045f4df4..19fa49cd9907 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -2150,5 +2150,5 @@ core_initcall(init_elf_binfmt); module_exit(exit_elf_binfmt); #ifdef CONFIG_BINFMT_ELF_KUNIT_TEST -#include "binfmt_elf_test.c" +#include "tests/binfmt_elf_kunit.c" #endif diff --git a/fs/exec.c b/fs/exec.c index a47d0e4c54f6..37f33212123c 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -2236,5 +2236,5 @@ fs_initcall(init_fs_exec_sysctls); #endif /* CONFIG_SYSCTL */ #ifdef CONFIG_EXEC_KUNIT_TEST -#include "exec_test.c" +#include "tests/exec_kunit.c" #endif diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 55d444bec5c0..bdd96329dddd 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -1186,6 +1186,11 @@ static void __prepare_cp_block(struct f2fs_sb_info *sbi) ckpt->valid_node_count = cpu_to_le32(valid_node_count(sbi)); ckpt->valid_inode_count = cpu_to_le32(valid_inode_count(sbi)); ckpt->next_free_nid = cpu_to_le32(last_nid); + + /* update user_block_counts */ + sbi->last_valid_block_count = sbi->total_valid_block_count; + percpu_counter_set(&sbi->alloc_valid_block_count, 0); + percpu_counter_set(&sbi->rf_node_block_count, 0); } static bool __need_flush_quota(struct f2fs_sb_info *sbi) @@ -1575,11 +1580,6 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) start_blk += NR_CURSEG_NODE_TYPE; } - /* update user_block_counts */ - sbi->last_valid_block_count = sbi->total_valid_block_count; - percpu_counter_set(&sbi->alloc_valid_block_count, 0); - percpu_counter_set(&sbi->rf_node_block_count, 0); - /* Here, we have one bio having CP pack except cp pack 2 page */ f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO); /* Wait for all dirty meta pages to be submitted for IO */ @@ -1718,6 +1718,7 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) } f2fs_restore_inmem_curseg(sbi); + f2fs_reinit_atgc_curseg(sbi); stat_inc_cp_count(sbi); stop: unblock_operations(sbi); diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c index 1ef82a546391..990b93689b46 100644 --- a/fs/f2fs/compress.c +++ b/fs/f2fs/compress.c @@ -1100,7 +1100,7 @@ retry: struct bio *bio = NULL; ret = f2fs_read_multi_pages(cc, &bio, cc->cluster_size, - &last_block_in_bio, false, true); + &last_block_in_bio, NULL, true); f2fs_put_rpages(cc); f2fs_destroy_compress_ctx(cc, true); if (ret) diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index b9b0debc6b3d..6457e5bca9c9 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -925,6 +925,7 @@ alloc_new: #ifdef CONFIG_BLK_DEV_ZONED static bool is_end_zone_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr) { + struct block_device *bdev = sbi->sb->s_bdev; int devi = 0; if (f2fs_is_multi_device(sbi)) { @@ -935,8 +936,9 @@ static bool is_end_zone_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr) return false; } blkaddr -= FDEV(devi).start_blk; + bdev = FDEV(devi).bdev; } - return bdev_is_zoned(FDEV(devi).bdev) && + return bdev_is_zoned(bdev) && f2fs_blkz_is_seq(sbi, devi, blkaddr) && (blkaddr % sbi->blocks_per_blkz == sbi->blocks_per_blkz - 1); } @@ -2067,12 +2069,17 @@ static inline loff_t f2fs_readpage_limit(struct inode *inode) return i_size_read(inode); } +static inline blk_opf_t f2fs_ra_op_flags(struct readahead_control *rac) +{ + return rac ? REQ_RAHEAD : 0; +} + static int f2fs_read_single_page(struct inode *inode, struct folio *folio, unsigned nr_pages, struct f2fs_map_blocks *map, struct bio **bio_ret, sector_t *last_block_in_bio, - bool is_readahead) + struct readahead_control *rac) { struct bio *bio = *bio_ret; const unsigned blocksize = blks_to_bytes(inode, 1); @@ -2148,7 +2155,7 @@ submit_and_realloc: } if (bio == NULL) { bio = f2fs_grab_read_bio(inode, block_nr, nr_pages, - is_readahead ? REQ_RAHEAD : 0, index, + f2fs_ra_op_flags(rac), index, false); if (IS_ERR(bio)) { ret = PTR_ERR(bio); @@ -2178,7 +2185,7 @@ out: #ifdef CONFIG_F2FS_FS_COMPRESSION int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret, unsigned nr_pages, sector_t *last_block_in_bio, - bool is_readahead, bool for_write) + struct readahead_control *rac, bool for_write) { struct dnode_of_data dn; struct inode *inode = cc->inode; @@ -2301,7 +2308,7 @@ submit_and_realloc: if (!bio) { bio = f2fs_grab_read_bio(inode, blkaddr, nr_pages, - is_readahead ? REQ_RAHEAD : 0, + f2fs_ra_op_flags(rac), page->index, for_write); if (IS_ERR(bio)) { ret = PTR_ERR(bio); @@ -2399,7 +2406,7 @@ static int f2fs_mpage_readpages(struct inode *inode, ret = f2fs_read_multi_pages(&cc, &bio, max_nr_pages, &last_block_in_bio, - rac != NULL, false); + rac, false); f2fs_destroy_compress_ctx(&cc, false); if (ret) goto set_error_page; @@ -2449,7 +2456,7 @@ next_page: ret = f2fs_read_multi_pages(&cc, &bio, max_nr_pages, &last_block_in_bio, - rac != NULL, false); + rac, false); f2fs_destroy_compress_ctx(&cc, false); } } @@ -2601,7 +2608,7 @@ bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio) return true; if (IS_NOQUOTA(inode)) return true; - if (f2fs_is_atomic_file(inode)) + if (f2fs_used_in_atomic_write(inode)) return true; /* rewrite low ratio compress data w/ OPU mode to avoid fragmentation */ if (f2fs_compressed_file(inode) && @@ -2688,7 +2695,7 @@ got_it: } /* wait for GCed page writeback via META_MAPPING */ - if (fio->post_read) + if (fio->meta_gc) f2fs_wait_on_block_writeback(inode, fio->old_blkaddr); /* @@ -2783,7 +2790,7 @@ int f2fs_write_single_data_page(struct page *page, int *submitted, .submitted = 0, .compr_blocks = compr_blocks, .need_lock = compr_blocks ? LOCK_DONE : LOCK_RETRY, - .post_read = f2fs_post_read_required(inode) ? 1 : 0, + .meta_gc = f2fs_meta_inode_gc_required(inode) ? 1 : 0, .io_type = io_type, .io_wbc = wbc, .bio = bio, diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c index 48048fa36427..fd1fc06359ee 100644 --- a/fs/f2fs/extent_cache.c +++ b/fs/f2fs/extent_cache.c @@ -19,33 +19,23 @@ #include "node.h" #include <trace/events/f2fs.h> -bool sanity_check_extent_cache(struct inode *inode) +bool sanity_check_extent_cache(struct inode *inode, struct page *ipage) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct f2fs_inode_info *fi = F2FS_I(inode); - struct extent_tree *et = fi->extent_tree[EX_READ]; - struct extent_info *ei; - - if (!et) - return true; + struct f2fs_extent *i_ext = &F2FS_INODE(ipage)->i_ext; + struct extent_info ei; - ei = &et->largest; - if (!ei->len) - return true; + get_read_extent_info(&ei, i_ext); - /* Let's drop, if checkpoint got corrupted. */ - if (is_set_ckpt_flags(sbi, CP_ERROR_FLAG)) { - ei->len = 0; - et->largest_updated = true; + if (!ei.len) return true; - } - if (!f2fs_is_valid_blkaddr(sbi, ei->blk, DATA_GENERIC_ENHANCE) || - !f2fs_is_valid_blkaddr(sbi, ei->blk + ei->len - 1, + if (!f2fs_is_valid_blkaddr(sbi, ei.blk, DATA_GENERIC_ENHANCE) || + !f2fs_is_valid_blkaddr(sbi, ei.blk + ei.len - 1, DATA_GENERIC_ENHANCE)) { f2fs_warn(sbi, "%s: inode (ino=%lx) extent info [%u, %u, %u] is incorrect, run fsck to fix", __func__, inode->i_ino, - ei->blk, ei->fofs, ei->len); + ei.blk, ei.fofs, ei.len); return false; } return true; @@ -394,24 +384,22 @@ void f2fs_init_read_extent_tree(struct inode *inode, struct page *ipage) if (!__may_extent_tree(inode, EX_READ)) { /* drop largest read extent */ - if (i_ext && i_ext->len) { + if (i_ext->len) { f2fs_wait_on_page_writeback(ipage, NODE, true, true); i_ext->len = 0; set_page_dirty(ipage); } - goto out; + set_inode_flag(inode, FI_NO_EXTENT); + return; } et = __grab_extent_tree(inode, EX_READ); - if (!i_ext || !i_ext->len) - goto out; - get_read_extent_info(&ei, i_ext); write_lock(&et->lock); - if (atomic_read(&et->node_cnt)) - goto unlock_out; + if (atomic_read(&et->node_cnt) || !ei.len) + goto skip; en = __attach_extent_node(sbi, et, &ei, NULL, &et->root.rb_root.rb_node, true); @@ -423,11 +411,13 @@ void f2fs_init_read_extent_tree(struct inode *inode, struct page *ipage) list_add_tail(&en->list, &eti->extent_list); spin_unlock(&eti->extent_lock); } -unlock_out: +skip: + /* Let's drop, if checkpoint got corrupted. */ + if (f2fs_cp_error(sbi)) { + et->largest.len = 0; + et->largest_updated = true; + } write_unlock(&et->lock); -out: - if (!F2FS_I(inode)->extent_tree[EX_READ]) - set_inode_flag(inode, FI_NO_EXTENT); } void f2fs_init_age_extent_tree(struct inode *inode) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 8a9d910aa552..ac19c61f0c3e 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -803,6 +803,7 @@ enum { FI_COW_FILE, /* indicate COW file */ FI_ATOMIC_COMMITTED, /* indicate atomic commit completed except disk sync */ FI_ATOMIC_REPLACE, /* indicate atomic replace */ + FI_OPENED_FILE, /* indicate file has been opened */ FI_MAX, /* max flag, never be used */ }; @@ -842,7 +843,11 @@ struct f2fs_inode_info { struct task_struct *atomic_write_task; /* store atomic write task */ struct extent_tree *extent_tree[NR_EXTENT_CACHES]; /* cached extent_tree entry */ - struct inode *cow_inode; /* copy-on-write inode for atomic write */ + union { + struct inode *cow_inode; /* copy-on-write inode for atomic write */ + struct inode *atomic_inode; + /* point to atomic_inode, available only for cow_inode */ + }; /* avoid racing between foreground op and gc */ struct f2fs_rwsem i_gc_rwsem[2]; @@ -1210,7 +1215,7 @@ struct f2fs_io_info { unsigned int in_list:1; /* indicate fio is in io_list */ unsigned int is_por:1; /* indicate IO is from recovery or not */ unsigned int encrypted:1; /* indicate file is encrypted */ - unsigned int post_read:1; /* require post read */ + unsigned int meta_gc:1; /* require meta inode GC */ enum iostat_type io_type; /* io type */ struct writeback_control *io_wbc; /* writeback control */ struct bio **bio; /* bio for ipu */ @@ -3222,21 +3227,15 @@ static inline bool f2fs_need_compress_data(struct inode *inode) return false; } -static inline unsigned int addrs_per_inode(struct inode *inode) +static inline unsigned int addrs_per_page(struct inode *inode, + bool is_inode) { - unsigned int addrs = CUR_ADDRS_PER_INODE(inode) - - get_inline_xattr_addrs(inode); + unsigned int addrs = is_inode ? (CUR_ADDRS_PER_INODE(inode) - + get_inline_xattr_addrs(inode)) : DEF_ADDRS_PER_BLOCK; - if (!f2fs_compressed_file(inode)) - return addrs; - return ALIGN_DOWN(addrs, F2FS_I(inode)->i_cluster_size); -} - -static inline unsigned int addrs_per_block(struct inode *inode) -{ - if (!f2fs_compressed_file(inode)) - return DEF_ADDRS_PER_BLOCK; - return ALIGN_DOWN(DEF_ADDRS_PER_BLOCK, F2FS_I(inode)->i_cluster_size); + if (f2fs_compressed_file(inode)) + return ALIGN_DOWN(addrs, F2FS_I(inode)->i_cluster_size); + return addrs; } static inline void *inline_xattr_addr(struct inode *inode, struct page *page) @@ -3706,6 +3705,7 @@ void f2fs_release_discard_addrs(struct f2fs_sb_info *sbi); int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra); bool f2fs_segment_has_free_slot(struct f2fs_sb_info *sbi, int segno); int f2fs_init_inmem_curseg(struct f2fs_sb_info *sbi); +int f2fs_reinit_atgc_curseg(struct f2fs_sb_info *sbi); void f2fs_save_inmem_curseg(struct f2fs_sb_info *sbi); void f2fs_restore_inmem_curseg(struct f2fs_sb_info *sbi); int f2fs_allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type, @@ -4163,7 +4163,7 @@ extern struct kmem_cache *f2fs_inode_entry_slab; * inline.c */ bool f2fs_may_inline_data(struct inode *inode); -bool f2fs_sanity_check_inline_data(struct inode *inode); +bool f2fs_sanity_check_inline_data(struct inode *inode, struct page *ipage); bool f2fs_may_inline_dentry(struct inode *inode); void f2fs_do_read_inline_data(struct folio *folio, struct page *ipage); void f2fs_truncate_inline_inode(struct inode *inode, @@ -4204,7 +4204,7 @@ void f2fs_leave_shrinker(struct f2fs_sb_info *sbi); /* * extent_cache.c */ -bool sanity_check_extent_cache(struct inode *inode); +bool sanity_check_extent_cache(struct inode *inode, struct page *ipage); void f2fs_init_extent_tree(struct inode *inode); void f2fs_drop_extent_tree(struct inode *inode); void f2fs_destroy_extent_node(struct inode *inode); @@ -4275,6 +4275,16 @@ static inline bool f2fs_post_read_required(struct inode *inode) f2fs_compressed_file(inode); } +static inline bool f2fs_used_in_atomic_write(struct inode *inode) +{ + return f2fs_is_atomic_file(inode) || f2fs_is_cow_file(inode); +} + +static inline bool f2fs_meta_inode_gc_required(struct inode *inode) +{ + return f2fs_post_read_required(inode) || f2fs_used_in_atomic_write(inode); +} + /* * compress.c */ @@ -4310,7 +4320,7 @@ void f2fs_update_read_extent_tree_range_compressed(struct inode *inode, unsigned int llen, unsigned int c_len); int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret, unsigned nr_pages, sector_t *last_block_in_bio, - bool is_readahead, bool for_write); + struct readahead_control *rac, bool for_write); struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc); void f2fs_decompress_end_io(struct decompress_io_ctx *dic, bool failed, bool in_task); @@ -4401,22 +4411,18 @@ static inline int set_compress_context(struct inode *inode) { #ifdef CONFIG_F2FS_FS_COMPRESSION struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct f2fs_inode_info *fi = F2FS_I(inode); - F2FS_I(inode)->i_compress_algorithm = - F2FS_OPTION(sbi).compress_algorithm; - F2FS_I(inode)->i_log_cluster_size = - F2FS_OPTION(sbi).compress_log_size; - F2FS_I(inode)->i_compress_flag = - F2FS_OPTION(sbi).compress_chksum ? - BIT(COMPRESS_CHKSUM) : 0; - F2FS_I(inode)->i_cluster_size = - BIT(F2FS_I(inode)->i_log_cluster_size); - if ((F2FS_I(inode)->i_compress_algorithm == COMPRESS_LZ4 || - F2FS_I(inode)->i_compress_algorithm == COMPRESS_ZSTD) && + fi->i_compress_algorithm = F2FS_OPTION(sbi).compress_algorithm; + fi->i_log_cluster_size = F2FS_OPTION(sbi).compress_log_size; + fi->i_compress_flag = F2FS_OPTION(sbi).compress_chksum ? + BIT(COMPRESS_CHKSUM) : 0; + fi->i_cluster_size = BIT(fi->i_log_cluster_size); + if ((fi->i_compress_algorithm == COMPRESS_LZ4 || + fi->i_compress_algorithm == COMPRESS_ZSTD) && F2FS_OPTION(sbi).compress_level) - F2FS_I(inode)->i_compress_level = - F2FS_OPTION(sbi).compress_level; - F2FS_I(inode)->i_flags |= F2FS_COMPR_FL; + fi->i_compress_level = F2FS_OPTION(sbi).compress_level; + fi->i_flags |= F2FS_COMPR_FL; set_inode_flag(inode, FI_COMPRESSED_FILE); stat_inc_compr_inode(inode); inc_compr_inode_stat(inode); @@ -4431,15 +4437,15 @@ static inline bool f2fs_disable_compressed_file(struct inode *inode) { struct f2fs_inode_info *fi = F2FS_I(inode); - f2fs_down_write(&F2FS_I(inode)->i_sem); + f2fs_down_write(&fi->i_sem); if (!f2fs_compressed_file(inode)) { - f2fs_up_write(&F2FS_I(inode)->i_sem); + f2fs_up_write(&fi->i_sem); return true; } if (f2fs_is_mmap_file(inode) || (S_ISREG(inode->i_mode) && F2FS_HAS_BLOCKS(inode))) { - f2fs_up_write(&F2FS_I(inode)->i_sem); + f2fs_up_write(&fi->i_sem); return false; } @@ -4448,7 +4454,7 @@ static inline bool f2fs_disable_compressed_file(struct inode *inode) clear_inode_flag(inode, FI_COMPRESSED_FILE); f2fs_mark_inode_dirty_sync(inode, true); - f2fs_up_write(&F2FS_I(inode)->i_sem); + f2fs_up_write(&fi->i_sem); return true; } diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index c1ad9b278c47..168f08507004 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -554,6 +554,42 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma) return 0; } +static int finish_preallocate_blocks(struct inode *inode) +{ + int ret; + + inode_lock(inode); + if (is_inode_flag_set(inode, FI_OPENED_FILE)) { + inode_unlock(inode); + return 0; + } + + if (!file_should_truncate(inode)) { + set_inode_flag(inode, FI_OPENED_FILE); + inode_unlock(inode); + return 0; + } + + f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + filemap_invalidate_lock(inode->i_mapping); + + truncate_setsize(inode, i_size_read(inode)); + ret = f2fs_truncate(inode); + + filemap_invalidate_unlock(inode->i_mapping); + f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + + if (!ret) + set_inode_flag(inode, FI_OPENED_FILE); + + inode_unlock(inode); + if (ret) + return ret; + + file_dont_truncate(inode); + return 0; +} + static int f2fs_file_open(struct inode *inode, struct file *filp) { int err = fscrypt_file_open(inode, filp); @@ -571,7 +607,11 @@ static int f2fs_file_open(struct inode *inode, struct file *filp) filp->f_mode |= FMODE_NOWAIT; filp->f_mode |= FMODE_CAN_ODIRECT; - return dquot_file_open(inode, filp); + err = dquot_file_open(inode, filp); + if (err) + return err; + + return finish_preallocate_blocks(inode); } void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count) @@ -825,6 +865,8 @@ static bool f2fs_force_buffered_io(struct inode *inode, int rw) return true; if (f2fs_compressed_file(inode)) return true; + if (f2fs_has_inline_data(inode)) + return true; /* disallow direct IO if any of devices has unaligned blksize */ if (f2fs_is_multi_device(sbi) && !sbi->aligned_blksize) @@ -937,6 +979,7 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); + struct f2fs_inode_info *fi = F2FS_I(inode); int err; if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) @@ -955,7 +998,7 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, return -EOPNOTSUPP; if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED) && !IS_ALIGNED(attr->ia_size, - F2FS_BLK_TO_BYTES(F2FS_I(inode)->i_cluster_size))) + F2FS_BLK_TO_BYTES(fi->i_cluster_size))) return -EINVAL; } @@ -1009,7 +1052,7 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, return err; } - f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + f2fs_down_write(&fi->i_gc_rwsem[WRITE]); filemap_invalidate_lock(inode->i_mapping); truncate_setsize(inode, attr->ia_size); @@ -1021,14 +1064,14 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, * larger than i_size. */ filemap_invalidate_unlock(inode->i_mapping); - f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + f2fs_up_write(&fi->i_gc_rwsem[WRITE]); if (err) return err; - spin_lock(&F2FS_I(inode)->i_size_lock); + spin_lock(&fi->i_size_lock); inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); - F2FS_I(inode)->last_disk_size = i_size_read(inode); - spin_unlock(&F2FS_I(inode)->i_size_lock); + fi->last_disk_size = i_size_read(inode); + spin_unlock(&fi->i_size_lock); } __setattr_copy(idmap, inode, attr); @@ -1038,7 +1081,7 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, if (is_inode_flag_set(inode, FI_ACL_MODE)) { if (!err) - inode->i_mode = F2FS_I(inode)->i_acl_mode; + inode->i_mode = fi->i_acl_mode; clear_inode_flag(inode, FI_ACL_MODE); } } @@ -1946,15 +1989,15 @@ static int f2fs_setflags_common(struct inode *inode, u32 iflags, u32 mask) if (err) return err; - f2fs_down_write(&F2FS_I(inode)->i_sem); + f2fs_down_write(&fi->i_sem); if (!f2fs_may_compress(inode) || (S_ISREG(inode->i_mode) && F2FS_HAS_BLOCKS(inode))) { - f2fs_up_write(&F2FS_I(inode)->i_sem); + f2fs_up_write(&fi->i_sem); return -EINVAL; } err = set_compress_context(inode); - f2fs_up_write(&F2FS_I(inode)->i_sem); + f2fs_up_write(&fi->i_sem); if (err) return err; @@ -2139,6 +2182,9 @@ static int f2fs_ioc_start_atomic_write(struct file *filp, bool truncate) set_inode_flag(fi->cow_inode, FI_COW_FILE); clear_inode_flag(fi->cow_inode, FI_INLINE_DATA); + + /* Set the COW inode's atomic_inode to the atomic inode */ + F2FS_I(fi->cow_inode)->atomic_inode = inode; } else { /* Reuse the already created COW inode */ ret = f2fs_do_truncate_blocks(fi->cow_inode, 0, true); @@ -3541,6 +3587,7 @@ next: static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); + struct f2fs_inode_info *fi = F2FS_I(inode); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); pgoff_t page_idx = 0, last_idx; unsigned int released_blocks = 0; @@ -3578,7 +3625,7 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg) if (ret) goto out; - if (!atomic_read(&F2FS_I(inode)->i_compr_blocks)) { + if (!atomic_read(&fi->i_compr_blocks)) { ret = -EPERM; goto out; } @@ -3587,7 +3634,7 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg) inode_set_ctime_current(inode); f2fs_mark_inode_dirty_sync(inode, true); - f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + f2fs_down_write(&fi->i_gc_rwsem[WRITE]); filemap_invalidate_lock(inode->i_mapping); last_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); @@ -3613,7 +3660,7 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg) end_offset = ADDRS_PER_PAGE(dn.node_page, inode); count = min(end_offset - dn.ofs_in_node, last_idx - page_idx); - count = round_up(count, F2FS_I(inode)->i_cluster_size); + count = round_up(count, fi->i_cluster_size); ret = release_compress_blocks(&dn, count); @@ -3629,7 +3676,7 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg) } filemap_invalidate_unlock(inode->i_mapping); - f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + f2fs_up_write(&fi->i_gc_rwsem[WRITE]); out: if (released_blocks) f2fs_update_time(sbi, REQ_TIME); @@ -3640,14 +3687,14 @@ out: if (ret >= 0) { ret = put_user(released_blocks, (u64 __user *)arg); } else if (released_blocks && - atomic_read(&F2FS_I(inode)->i_compr_blocks)) { + atomic_read(&fi->i_compr_blocks)) { set_sbi_flag(sbi, SBI_NEED_FSCK); f2fs_warn(sbi, "%s: partial blocks were released i_ino=%lx " "iblocks=%llu, released=%u, compr_blocks=%u, " "run fsck to fix.", __func__, inode->i_ino, inode->i_blocks, released_blocks, - atomic_read(&F2FS_I(inode)->i_compr_blocks)); + atomic_read(&fi->i_compr_blocks)); } return ret; @@ -3736,6 +3783,7 @@ next: static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); + struct f2fs_inode_info *fi = F2FS_I(inode); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); pgoff_t page_idx = 0, last_idx; unsigned int reserved_blocks = 0; @@ -3761,10 +3809,10 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg) goto unlock_inode; } - if (atomic_read(&F2FS_I(inode)->i_compr_blocks)) + if (atomic_read(&fi->i_compr_blocks)) goto unlock_inode; - f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + f2fs_down_write(&fi->i_gc_rwsem[WRITE]); filemap_invalidate_lock(inode->i_mapping); last_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); @@ -3790,7 +3838,7 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg) end_offset = ADDRS_PER_PAGE(dn.node_page, inode); count = min(end_offset - dn.ofs_in_node, last_idx - page_idx); - count = round_up(count, F2FS_I(inode)->i_cluster_size); + count = round_up(count, fi->i_cluster_size); ret = reserve_compress_blocks(&dn, count, &reserved_blocks); @@ -3805,7 +3853,7 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg) } filemap_invalidate_unlock(inode->i_mapping); - f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + f2fs_up_write(&fi->i_gc_rwsem[WRITE]); if (!ret) { clear_inode_flag(inode, FI_COMPRESS_RELEASED); @@ -3821,14 +3869,14 @@ unlock_inode: if (!ret) { ret = put_user(reserved_blocks, (u64 __user *)arg); } else if (reserved_blocks && - atomic_read(&F2FS_I(inode)->i_compr_blocks)) { + atomic_read(&fi->i_compr_blocks)) { set_sbi_flag(sbi, SBI_NEED_FSCK); f2fs_warn(sbi, "%s: partial blocks were reserved i_ino=%lx " "iblocks=%llu, reserved=%u, compr_blocks=%u, " "run fsck to fix.", __func__, inode->i_ino, inode->i_blocks, reserved_blocks, - atomic_read(&F2FS_I(inode)->i_compr_blocks)); + atomic_read(&fi->i_compr_blocks)); } return ret; @@ -3891,7 +3939,9 @@ static int f2fs_sec_trim_file(struct file *filp, unsigned long arg) IS_ENCRYPTED(inode) && f2fs_is_multi_device(sbi))) return -EOPNOTSUPP; - file_start_write(filp); + ret = mnt_want_write_file(filp); + if (ret) + return ret; inode_lock(inode); if (f2fs_is_atomic_file(inode) || f2fs_compressed_file(inode) || @@ -4017,7 +4067,7 @@ out: f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); err: inode_unlock(inode); - file_end_write(filp); + mnt_drop_write_file(filp); return ret; } @@ -4052,6 +4102,7 @@ static int f2fs_ioc_get_compress_option(struct file *filp, unsigned long arg) static int f2fs_ioc_set_compress_option(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); + struct f2fs_inode_info *fi = F2FS_I(inode); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_comp_option option; int ret = 0; @@ -4071,7 +4122,9 @@ static int f2fs_ioc_set_compress_option(struct file *filp, unsigned long arg) option.algorithm >= COMPRESS_MAX) return -EINVAL; - file_start_write(filp); + ret = mnt_want_write_file(filp); + if (ret) + return ret; inode_lock(inode); f2fs_down_write(&F2FS_I(inode)->i_sem); @@ -4090,27 +4143,27 @@ static int f2fs_ioc_set_compress_option(struct file *filp, unsigned long arg) goto out; } - F2FS_I(inode)->i_compress_algorithm = option.algorithm; - F2FS_I(inode)->i_log_cluster_size = option.log_cluster_size; - F2FS_I(inode)->i_cluster_size = BIT(option.log_cluster_size); + fi->i_compress_algorithm = option.algorithm; + fi->i_log_cluster_size = option.log_cluster_size; + fi->i_cluster_size = BIT(option.log_cluster_size); /* Set default level */ - if (F2FS_I(inode)->i_compress_algorithm == COMPRESS_ZSTD) - F2FS_I(inode)->i_compress_level = F2FS_ZSTD_DEFAULT_CLEVEL; + if (fi->i_compress_algorithm == COMPRESS_ZSTD) + fi->i_compress_level = F2FS_ZSTD_DEFAULT_CLEVEL; else - F2FS_I(inode)->i_compress_level = 0; + fi->i_compress_level = 0; /* Adjust mount option level */ if (option.algorithm == F2FS_OPTION(sbi).compress_algorithm && F2FS_OPTION(sbi).compress_level) - F2FS_I(inode)->i_compress_level = F2FS_OPTION(sbi).compress_level; + fi->i_compress_level = F2FS_OPTION(sbi).compress_level; f2fs_mark_inode_dirty_sync(inode, true); if (!f2fs_is_compress_backend_ready(inode)) f2fs_warn(sbi, "compression algorithm is successfully set, " "but current kernel doesn't support this algorithm."); out: - f2fs_up_write(&F2FS_I(inode)->i_sem); + f2fs_up_write(&fi->i_sem); inode_unlock(inode); - file_end_write(filp); + mnt_drop_write_file(filp); return ret; } @@ -4167,7 +4220,9 @@ static int f2fs_ioc_decompress_file(struct file *filp) f2fs_balance_fs(sbi, true); - file_start_write(filp); + ret = mnt_want_write_file(filp); + if (ret) + return ret; inode_lock(inode); if (!f2fs_is_compress_backend_ready(inode)) { @@ -4222,7 +4277,7 @@ static int f2fs_ioc_decompress_file(struct file *filp) f2fs_update_time(sbi, REQ_TIME); out: inode_unlock(inode); - file_end_write(filp); + mnt_drop_write_file(filp); return ret; } @@ -4244,7 +4299,9 @@ static int f2fs_ioc_compress_file(struct file *filp) f2fs_balance_fs(sbi, true); - file_start_write(filp); + ret = mnt_want_write_file(filp); + if (ret) + return ret; inode_lock(inode); if (!f2fs_is_compress_backend_ready(inode)) { @@ -4300,7 +4357,7 @@ static int f2fs_ioc_compress_file(struct file *filp) f2fs_update_time(sbi, REQ_TIME); out: inode_unlock(inode); - file_end_write(filp); + mnt_drop_write_file(filp); return ret; } diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 6066c6eecf41..724bbcb447d3 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -1171,7 +1171,8 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, static int ra_data_block(struct inode *inode, pgoff_t index) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct address_space *mapping = inode->i_mapping; + struct address_space *mapping = f2fs_is_cow_file(inode) ? + F2FS_I(inode)->atomic_inode->i_mapping : inode->i_mapping; struct dnode_of_data dn; struct page *page; struct f2fs_io_info fio = { @@ -1260,6 +1261,8 @@ put_page: static int move_data_block(struct inode *inode, block_t bidx, int gc_type, unsigned int segno, int off) { + struct address_space *mapping = f2fs_is_cow_file(inode) ? + F2FS_I(inode)->atomic_inode->i_mapping : inode->i_mapping; struct f2fs_io_info fio = { .sbi = F2FS_I_SB(inode), .ino = inode->i_ino, @@ -1282,7 +1285,7 @@ static int move_data_block(struct inode *inode, block_t bidx, CURSEG_ALL_DATA_ATGC : CURSEG_COLD_DATA; /* do not read out */ - page = f2fs_grab_cache_page(inode->i_mapping, bidx, false); + page = f2fs_grab_cache_page(mapping, bidx, false); if (!page) return -ENOMEM; @@ -1563,6 +1566,16 @@ next_step: continue; } + if (f2fs_has_inline_data(inode)) { + iput(inode); + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_err_ratelimited(sbi, + "inode %lx has both inline_data flag and " + "data block, nid=%u, ofs_in_node=%u", + inode->i_ino, dni.nid, ofs_in_node); + continue; + } + err = f2fs_gc_pinned_control(inode, gc_type, segno); if (err == -EAGAIN) { iput(inode); @@ -1579,7 +1592,7 @@ next_step: start_bidx = f2fs_start_bidx_of_node(nofs, inode) + ofs_in_node; - if (f2fs_post_read_required(inode)) { + if (f2fs_meta_inode_gc_required(inode)) { int err = ra_data_block(inode, start_bidx); f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); @@ -1630,7 +1643,7 @@ next_step: start_bidx = f2fs_start_bidx_of_node(nofs, inode) + ofs_in_node; - if (f2fs_post_read_required(inode)) + if (f2fs_meta_inode_gc_required(inode)) err = move_data_block(inode, start_bidx, gc_type, segno, off); else @@ -1638,7 +1651,7 @@ next_step: segno, off); if (!err && (gc_type == FG_GC || - f2fs_post_read_required(inode))) + f2fs_meta_inode_gc_required(inode))) submitted++; if (locked) { @@ -1742,7 +1755,6 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi, if (type != GET_SUM_TYPE((&sum->footer))) { f2fs_err(sbi, "Inconsistent segment (%u) type [%d, %d] in SSA and SIT", segno, type, GET_SUM_TYPE((&sum->footer))); - set_sbi_flag(sbi, SBI_NEED_FSCK); f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_CORRUPTED_SUMMARY); goto skip; diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index 7638d0d7b7ee..cca7d448e55c 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -16,7 +16,7 @@ static bool support_inline_data(struct inode *inode) { - if (f2fs_is_atomic_file(inode)) + if (f2fs_used_in_atomic_write(inode)) return false; if (!S_ISREG(inode->i_mode) && !S_ISLNK(inode->i_mode)) return false; @@ -33,11 +33,29 @@ bool f2fs_may_inline_data(struct inode *inode) return !f2fs_post_read_required(inode); } -bool f2fs_sanity_check_inline_data(struct inode *inode) +static bool inode_has_blocks(struct inode *inode, struct page *ipage) +{ + struct f2fs_inode *ri = F2FS_INODE(ipage); + int i; + + if (F2FS_HAS_BLOCKS(inode)) + return true; + + for (i = 0; i < DEF_NIDS_PER_INODE; i++) { + if (ri->i_nid[i]) + return true; + } + return false; +} + +bool f2fs_sanity_check_inline_data(struct inode *inode, struct page *ipage) { if (!f2fs_has_inline_data(inode)) return false; + if (inode_has_blocks(inode, ipage)) + return false; + if (!support_inline_data(inode)) return true; @@ -203,8 +221,10 @@ int f2fs_convert_inline_inode(struct inode *inode) struct page *ipage, *page; int err = 0; - if (!f2fs_has_inline_data(inode) || - f2fs_hw_is_readonly(sbi) || f2fs_readonly(sbi->sb)) + if (f2fs_hw_is_readonly(sbi) || f2fs_readonly(sbi->sb)) + return -EROFS; + + if (!f2fs_has_inline_data(inode)) return 0; err = f2fs_dquot_initialize(inode); diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 005dde72aff3..aef57172014f 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -29,6 +29,9 @@ void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync) if (is_inode_flag_set(inode, FI_NEW_INODE)) return; + if (f2fs_readonly(F2FS_I_SB(inode)->sb)) + return; + if (f2fs_inode_dirtied(inode, sync)) return; @@ -310,10 +313,6 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page) if (!sanity_check_compress_inode(inode, ri)) return false; } - } else if (f2fs_sb_has_flexible_inline_xattr(sbi)) { - f2fs_warn(sbi, "%s: corrupted inode ino=%lx, run fsck to fix.", - __func__, inode->i_ino); - return false; } if (!f2fs_sb_has_extra_attr(sbi)) { @@ -344,7 +343,7 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page) } } - if (f2fs_sanity_check_inline_data(inode)) { + if (f2fs_sanity_check_inline_data(inode, node_page)) { f2fs_warn(sbi, "%s: inode (ino=%lx, mode=%u) should not have inline_data, run fsck to fix", __func__, inode->i_ino, inode->i_mode); return false; @@ -508,16 +507,16 @@ static int do_read_inode(struct inode *inode) init_idisk_time(inode); - /* Need all the flag bits */ - f2fs_init_read_extent_tree(inode, node_page); - f2fs_init_age_extent_tree(inode); - - if (!sanity_check_extent_cache(inode)) { + if (!sanity_check_extent_cache(inode, node_page)) { f2fs_put_page(node_page, 1); f2fs_handle_error(sbi, ERROR_CORRUPTED_INODE); return -EFSCORRUPTED; } + /* Need all the flag bits */ + f2fs_init_read_extent_tree(inode, node_page); + f2fs_init_age_extent_tree(inode); + f2fs_put_page(node_page, 1); stat_inc_inline_xattr(inode); @@ -610,14 +609,6 @@ make_now: } f2fs_set_inode_flags(inode); - if (file_should_truncate(inode) && - !is_sbi_flag_set(sbi, SBI_POR_DOING)) { - ret = f2fs_truncate(inode); - if (ret) - goto bad_inode; - file_dont_truncate(inode); - } - unlock_new_inode(inode); trace_f2fs_iget(inode); return inode; @@ -645,8 +636,9 @@ retry: void f2fs_update_inode(struct inode *inode, struct page *node_page) { + struct f2fs_inode_info *fi = F2FS_I(inode); struct f2fs_inode *ri; - struct extent_tree *et = F2FS_I(inode)->extent_tree[EX_READ]; + struct extent_tree *et = fi->extent_tree[EX_READ]; f2fs_wait_on_page_writeback(node_page, NODE, true, true); set_page_dirty(node_page); @@ -656,7 +648,7 @@ void f2fs_update_inode(struct inode *inode, struct page *node_page) ri = F2FS_INODE(node_page); ri->i_mode = cpu_to_le16(inode->i_mode); - ri->i_advise = F2FS_I(inode)->i_advise; + ri->i_advise = fi->i_advise; ri->i_uid = cpu_to_le32(i_uid_read(inode)); ri->i_gid = cpu_to_le32(i_gid_read(inode)); ri->i_links = cpu_to_le32(inode->i_nlink); @@ -682,58 +674,49 @@ void f2fs_update_inode(struct inode *inode, struct page *node_page) ri->i_ctime_nsec = cpu_to_le32(inode_get_ctime_nsec(inode)); ri->i_mtime_nsec = cpu_to_le32(inode_get_mtime_nsec(inode)); if (S_ISDIR(inode->i_mode)) - ri->i_current_depth = - cpu_to_le32(F2FS_I(inode)->i_current_depth); + ri->i_current_depth = cpu_to_le32(fi->i_current_depth); else if (S_ISREG(inode->i_mode)) - ri->i_gc_failures = cpu_to_le16(F2FS_I(inode)->i_gc_failures); - ri->i_xattr_nid = cpu_to_le32(F2FS_I(inode)->i_xattr_nid); - ri->i_flags = cpu_to_le32(F2FS_I(inode)->i_flags); - ri->i_pino = cpu_to_le32(F2FS_I(inode)->i_pino); + ri->i_gc_failures = cpu_to_le16(fi->i_gc_failures); + ri->i_xattr_nid = cpu_to_le32(fi->i_xattr_nid); + ri->i_flags = cpu_to_le32(fi->i_flags); + ri->i_pino = cpu_to_le32(fi->i_pino); ri->i_generation = cpu_to_le32(inode->i_generation); - ri->i_dir_level = F2FS_I(inode)->i_dir_level; + ri->i_dir_level = fi->i_dir_level; if (f2fs_has_extra_attr(inode)) { - ri->i_extra_isize = cpu_to_le16(F2FS_I(inode)->i_extra_isize); + ri->i_extra_isize = cpu_to_le16(fi->i_extra_isize); if (f2fs_sb_has_flexible_inline_xattr(F2FS_I_SB(inode))) ri->i_inline_xattr_size = - cpu_to_le16(F2FS_I(inode)->i_inline_xattr_size); + cpu_to_le16(fi->i_inline_xattr_size); if (f2fs_sb_has_project_quota(F2FS_I_SB(inode)) && - F2FS_FITS_IN_INODE(ri, F2FS_I(inode)->i_extra_isize, - i_projid)) { + F2FS_FITS_IN_INODE(ri, fi->i_extra_isize, i_projid)) { projid_t i_projid; - i_projid = from_kprojid(&init_user_ns, - F2FS_I(inode)->i_projid); + i_projid = from_kprojid(&init_user_ns, fi->i_projid); ri->i_projid = cpu_to_le32(i_projid); } if (f2fs_sb_has_inode_crtime(F2FS_I_SB(inode)) && - F2FS_FITS_IN_INODE(ri, F2FS_I(inode)->i_extra_isize, - i_crtime)) { - ri->i_crtime = - cpu_to_le64(F2FS_I(inode)->i_crtime.tv_sec); - ri->i_crtime_nsec = - cpu_to_le32(F2FS_I(inode)->i_crtime.tv_nsec); + F2FS_FITS_IN_INODE(ri, fi->i_extra_isize, i_crtime)) { + ri->i_crtime = cpu_to_le64(fi->i_crtime.tv_sec); + ri->i_crtime_nsec = cpu_to_le32(fi->i_crtime.tv_nsec); } if (f2fs_sb_has_compression(F2FS_I_SB(inode)) && - F2FS_FITS_IN_INODE(ri, F2FS_I(inode)->i_extra_isize, + F2FS_FITS_IN_INODE(ri, fi->i_extra_isize, i_compress_flag)) { unsigned short compress_flag; - ri->i_compr_blocks = - cpu_to_le64(atomic_read( - &F2FS_I(inode)->i_compr_blocks)); - ri->i_compress_algorithm = - F2FS_I(inode)->i_compress_algorithm; - compress_flag = F2FS_I(inode)->i_compress_flag | - F2FS_I(inode)->i_compress_level << + ri->i_compr_blocks = cpu_to_le64( + atomic_read(&fi->i_compr_blocks)); + ri->i_compress_algorithm = fi->i_compress_algorithm; + compress_flag = fi->i_compress_flag | + fi->i_compress_level << COMPRESS_LEVEL_OFFSET; ri->i_compress_flag = cpu_to_le16(compress_flag); - ri->i_log_cluster_size = - F2FS_I(inode)->i_log_cluster_size; + ri->i_log_cluster_size = fi->i_log_cluster_size; } } @@ -813,8 +796,9 @@ void f2fs_evict_inode(struct inode *inode) f2fs_abort_atomic_write(inode, true); - if (fi->cow_inode) { + if (fi->cow_inode && f2fs_is_cow_file(fi->cow_inode)) { clear_inode_flag(fi->cow_inode, FI_COW_FILE); + F2FS_I(fi->cow_inode)->atomic_inode = NULL; iput(fi->cow_inode); fi->cow_inode = NULL; } diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 1ecde2b45e99..38b4750475db 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -221,6 +221,7 @@ static struct inode *f2fs_new_inode(struct mnt_idmap *idmap, const char *name) { struct f2fs_sb_info *sbi = F2FS_I_SB(dir); + struct f2fs_inode_info *fi; nid_t ino; struct inode *inode; bool nid_free = false; @@ -241,14 +242,15 @@ static struct inode *f2fs_new_inode(struct mnt_idmap *idmap, inode_init_owner(idmap, inode, dir, mode); + fi = F2FS_I(inode); inode->i_ino = ino; inode->i_blocks = 0; simple_inode_init_ts(inode); - F2FS_I(inode)->i_crtime = inode_get_mtime(inode); + fi->i_crtime = inode_get_mtime(inode); inode->i_generation = get_random_u32(); if (S_ISDIR(inode->i_mode)) - F2FS_I(inode)->i_current_depth = 1; + fi->i_current_depth = 1; err = insert_inode_locked(inode); if (err) { @@ -258,9 +260,9 @@ static struct inode *f2fs_new_inode(struct mnt_idmap *idmap, if (f2fs_sb_has_project_quota(sbi) && (F2FS_I(dir)->i_flags & F2FS_PROJINHERIT_FL)) - F2FS_I(inode)->i_projid = F2FS_I(dir)->i_projid; + fi->i_projid = F2FS_I(dir)->i_projid; else - F2FS_I(inode)->i_projid = make_kprojid(&init_user_ns, + fi->i_projid = make_kprojid(&init_user_ns, F2FS_DEF_PROJID); err = fscrypt_prepare_new_inode(dir, inode, &encrypt); @@ -278,7 +280,7 @@ static struct inode *f2fs_new_inode(struct mnt_idmap *idmap, if (f2fs_sb_has_extra_attr(sbi)) { set_inode_flag(inode, FI_EXTRA_ATTR); - F2FS_I(inode)->i_extra_isize = F2FS_TOTAL_EXTRA_ATTR_SIZE; + fi->i_extra_isize = F2FS_TOTAL_EXTRA_ATTR_SIZE; } if (test_opt(sbi, INLINE_XATTR)) @@ -296,15 +298,15 @@ static struct inode *f2fs_new_inode(struct mnt_idmap *idmap, f2fs_has_inline_dentry(inode)) { xattr_size = DEFAULT_INLINE_XATTR_ADDRS; } - F2FS_I(inode)->i_inline_xattr_size = xattr_size; + fi->i_inline_xattr_size = xattr_size; - F2FS_I(inode)->i_flags = + fi->i_flags = f2fs_mask_flags(mode, F2FS_I(dir)->i_flags & F2FS_FL_INHERITED); if (S_ISDIR(inode->i_mode)) - F2FS_I(inode)->i_flags |= F2FS_INDEX_FL; + fi->i_flags |= F2FS_INDEX_FL; - if (F2FS_I(inode)->i_flags & F2FS_PROJINHERIT_FL) + if (fi->i_flags & F2FS_PROJINHERIT_FL) set_inode_flag(inode, FI_PROJ_INHERIT); /* Check compression first. */ diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index 8712e264071f..9756f0f2b7f7 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -280,6 +280,7 @@ static void recover_inline_flags(struct inode *inode, struct f2fs_inode *ri) static int recover_inode(struct inode *inode, struct page *page) { struct f2fs_inode *raw = F2FS_INODE(page); + struct f2fs_inode_info *fi = F2FS_I(inode); char *name; int err; @@ -302,12 +303,12 @@ static int recover_inode(struct inode *inode, struct page *page) i_projid = (projid_t)le32_to_cpu(raw->i_projid); kprojid = make_kprojid(&init_user_ns, i_projid); - if (!projid_eq(kprojid, F2FS_I(inode)->i_projid)) { + if (!projid_eq(kprojid, fi->i_projid)) { err = f2fs_transfer_project_quota(inode, kprojid); if (err) return err; - F2FS_I(inode)->i_projid = kprojid; + fi->i_projid = kprojid; } } } @@ -320,10 +321,10 @@ static int recover_inode(struct inode *inode, struct page *page) inode_set_mtime(inode, le64_to_cpu(raw->i_mtime), le32_to_cpu(raw->i_mtime_nsec)); - F2FS_I(inode)->i_advise = raw->i_advise; - F2FS_I(inode)->i_flags = le32_to_cpu(raw->i_flags); + fi->i_advise = raw->i_advise; + fi->i_flags = le32_to_cpu(raw->i_flags); f2fs_set_inode_flags(inode); - F2FS_I(inode)->i_gc_failures = le16_to_cpu(raw->i_gc_failures); + fi->i_gc_failures = le16_to_cpu(raw->i_gc_failures); recover_inline_flags(inode, raw); diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index a0ce3d080f80..78c3198a6308 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -2784,11 +2784,19 @@ static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type) unsigned short seg_type = curseg->seg_type; sanity_check_seg_type(sbi, seg_type); - if (f2fs_need_rand_seg(sbi)) - return get_random_u32_below(MAIN_SECS(sbi) * SEGS_PER_SEC(sbi)); + if (__is_large_section(sbi)) { + if (f2fs_need_rand_seg(sbi)) { + unsigned int hint = GET_SEC_FROM_SEG(sbi, curseg->segno); - if (__is_large_section(sbi)) + if (GET_SEC_FROM_SEG(sbi, curseg->segno + 1) != hint) + return curseg->segno; + return get_random_u32_inclusive(curseg->segno + 1, + GET_SEG_FROM_SEC(sbi, hint + 1) - 1); + } return curseg->segno; + } else if (f2fs_need_rand_seg(sbi)) { + return get_random_u32_below(MAIN_SECS(sbi) * SEGS_PER_SEC(sbi)); + } /* inmem log may not locate on any segment after mount */ if (!curseg->inited) @@ -2931,12 +2939,12 @@ static int get_atssr_segment(struct f2fs_sb_info *sbi, int type, return ret; } -static int __f2fs_init_atgc_curseg(struct f2fs_sb_info *sbi) +static int __f2fs_init_atgc_curseg(struct f2fs_sb_info *sbi, bool force) { struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_ALL_DATA_ATGC); int ret = 0; - if (!sbi->am.atgc_enabled) + if (!sbi->am.atgc_enabled && !force) return 0; f2fs_down_read(&SM_I(sbi)->curseg_lock); @@ -2953,9 +2961,30 @@ static int __f2fs_init_atgc_curseg(struct f2fs_sb_info *sbi) f2fs_up_read(&SM_I(sbi)->curseg_lock); return ret; } + int f2fs_init_inmem_curseg(struct f2fs_sb_info *sbi) { - return __f2fs_init_atgc_curseg(sbi); + return __f2fs_init_atgc_curseg(sbi, false); +} + +int f2fs_reinit_atgc_curseg(struct f2fs_sb_info *sbi) +{ + int ret; + + if (!test_opt(sbi, ATGC)) + return 0; + if (sbi->am.atgc_enabled) + return 0; + if (le64_to_cpu(F2FS_CKPT(sbi)->elapsed_time) < + sbi->am.age_threshold) + return 0; + + ret = __f2fs_init_atgc_curseg(sbi, true); + if (!ret) { + sbi->am.atgc_enabled = true; + f2fs_info(sbi, "reenabled age threshold GC"); + } + return ret; } static void __f2fs_save_inmem_curseg(struct f2fs_sb_info *sbi, int type) @@ -3483,7 +3512,9 @@ static int __get_segment_type_6(struct f2fs_io_info *fio) if (page_private_gcing(fio->page)) { if (fio->sbi->am.atgc_enabled && (fio->io_type == FS_DATA_IO) && - (fio->sbi->gc_mode != GC_URGENT_HIGH)) + (fio->sbi->gc_mode != GC_URGENT_HIGH) && + __is_valid_data_blkaddr(fio->old_blkaddr) && + !is_inode_flag_set(inode, FI_OPU_WRITE)) return CURSEG_ALL_DATA_ATGC; else return CURSEG_COLD_DATA; @@ -3828,7 +3859,7 @@ int f2fs_inplace_write_data(struct f2fs_io_info *fio) goto drop_bio; } - if (fio->post_read) + if (fio->meta_gc) f2fs_truncate_meta_inode_pages(sbi, fio->new_blkaddr, 1); stat_inc_inplace_blocks(fio->sbi); @@ -3998,7 +4029,7 @@ void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr) struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct page *cpage; - if (!f2fs_post_read_required(inode)) + if (!f2fs_meta_inode_gc_required(inode)) return; if (!__is_valid_data_blkaddr(blkaddr)) @@ -4017,7 +4048,7 @@ void f2fs_wait_on_block_writeback_range(struct inode *inode, block_t blkaddr, struct f2fs_sb_info *sbi = F2FS_I_SB(inode); block_t i; - if (!f2fs_post_read_required(inode)) + if (!f2fs_meta_inode_gc_required(inode)) return; for (i = 0; i < len; i++) @@ -5187,7 +5218,8 @@ static int fix_curseg_write_pointer(struct f2fs_sb_info *sbi, int type) } /* Allocate a new section if it's not new. */ - if (cs->next_blkoff) { + if (cs->next_blkoff || + cs->segno != GET_SEG_FROM_SEC(sbi, GET_ZONE_FROM_SEC(sbi, cs_section))) { unsigned int old_segno = cs->segno, old_blkoff = cs->next_blkoff; f2fs_allocate_new_section(sbi, type, true); diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index e1c0f418aa11..bfc01a521cb9 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -347,7 +347,8 @@ static inline unsigned int get_ckpt_valid_blocks(struct f2fs_sb_info *sbi, unsigned int segno, bool use_section) { if (use_section && __is_large_section(sbi)) { - unsigned int start_segno = START_SEGNO(segno); + unsigned int secno = GET_SEC_FROM_SEG(sbi, segno); + unsigned int start_segno = GET_SEG_FROM_SEC(sbi, secno); unsigned int blocks = 0; int i; diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index df4cf31f93df..3959fd137cc9 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -151,8 +151,6 @@ enum { Opt_mode, Opt_fault_injection, Opt_fault_type, - Opt_lazytime, - Opt_nolazytime, Opt_quota, Opt_noquota, Opt_usrquota, @@ -229,8 +227,6 @@ static match_table_t f2fs_tokens = { {Opt_mode, "mode=%s"}, {Opt_fault_injection, "fault_injection=%u"}, {Opt_fault_type, "fault_type=%u"}, - {Opt_lazytime, "lazytime"}, - {Opt_nolazytime, "nolazytime"}, {Opt_quota, "quota"}, {Opt_noquota, "noquota"}, {Opt_usrquota, "usrquota"}, @@ -918,12 +914,6 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount) f2fs_info(sbi, "fault_type options not supported"); break; #endif - case Opt_lazytime: - sb->s_flags |= SB_LAZYTIME; - break; - case Opt_nolazytime: - sb->s_flags &= ~SB_LAZYTIME; - break; #ifdef CONFIG_QUOTA case Opt_quota: case Opt_usrquota: @@ -4481,6 +4471,7 @@ try_onemore: sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | (test_opt(sbi, POSIX_ACL) ? SB_POSIXACL : 0); super_set_uuid(sb, (void *) raw_super->uuid, sizeof(raw_super->uuid)); + super_set_sysfs_name_bdev(sb); sb->s_iflags |= SB_I_CGROUPWB; /* init f2fs-specific super block info */ diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index 09d3ecfaa4f1..fee7ee45ceaa 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -340,13 +340,13 @@ static ssize_t f2fs_sbi_show(struct f2fs_attr *a, if (!strcmp(a->attr.name, "ckpt_thread_ioprio")) { struct ckpt_req_control *cprc = &sbi->cprc_info; int class = IOPRIO_PRIO_CLASS(cprc->ckpt_thread_ioprio); - int data = IOPRIO_PRIO_DATA(cprc->ckpt_thread_ioprio); + int level = IOPRIO_PRIO_LEVEL(cprc->ckpt_thread_ioprio); if (class != IOPRIO_CLASS_RT && class != IOPRIO_CLASS_BE) return -EINVAL; return sysfs_emit(buf, "%s,%d\n", - class == IOPRIO_CLASS_RT ? "rt" : "be", data); + class == IOPRIO_CLASS_RT ? "rt" : "be", level); } #ifdef CONFIG_F2FS_FS_COMPRESSION @@ -450,7 +450,7 @@ out: const char *name = strim((char *)buf); struct ckpt_req_control *cprc = &sbi->cprc_info; int class; - long data; + long level; int ret; if (!strncmp(name, "rt,", 3)) @@ -461,13 +461,13 @@ out: return -EINVAL; name += 3; - ret = kstrtol(name, 10, &data); + ret = kstrtol(name, 10, &level); if (ret) return ret; - if (data >= IOPRIO_NR_LEVELS || data < 0) + if (level >= IOPRIO_NR_LEVELS || level < 0) return -EINVAL; - cprc->ckpt_thread_ioprio = IOPRIO_PRIO_VALUE(class, data); + cprc->ckpt_thread_ioprio = IOPRIO_PRIO_VALUE(class, level); if (test_opt(sbi, MERGE_CHECKPOINT)) { ret = set_task_ioprio(cprc->f2fs_issue_ckpt, cprc->ckpt_thread_ioprio); diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 3eb747d26924..2b532670a561 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -455,7 +455,7 @@ static int hostfs_read_folio(struct file *file, struct folio *folio) if (bytes_read < 0) ret = bytes_read; else - buffer = folio_zero_tail(folio, bytes_read, buffer); + buffer = folio_zero_tail(folio, bytes_read, buffer + bytes_read); kunmap_local(buffer); folio_end_read(folio, ret == 0); diff --git a/fs/jffs2/Kconfig b/fs/jffs2/Kconfig index 7c96bc107218..560187d61562 100644 --- a/fs/jffs2/Kconfig +++ b/fs/jffs2/Kconfig @@ -151,8 +151,9 @@ config JFFS2_RUBIN RUBINMIPS and DYNRUBIN compressors. Say 'N' if unsure. choice - prompt "JFFS2 default compression mode" if JFFS2_COMPRESSION_OPTIONS + prompt "JFFS2 default compression mode" default JFFS2_CMODE_PRIORITY + depends on JFFS2_COMPRESSION_OPTIONS depends on JFFS2_FS help You can set here the default compression mode of JFFS2 from diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c index cb3cda1390ad..5713994328cb 100644 --- a/fs/jfs/jfs_dmap.c +++ b/fs/jfs/jfs_dmap.c @@ -1626,6 +1626,8 @@ s64 dbDiscardAG(struct inode *ip, int agno, s64 minlen) } else if (rc == -ENOSPC) { /* search for next smaller log2 block */ l2nb = BLKSTOL2(nblocks) - 1; + if (unlikely(l2nb < 0)) + break; nblocks = 1LL << l2nb; } else { /* Trim any already allocated blocks */ diff --git a/fs/jfs/jfs_dtree.c b/fs/jfs/jfs_dtree.c index 031d8f570f58..5d3127ca68a4 100644 --- a/fs/jfs/jfs_dtree.c +++ b/fs/jfs/jfs_dtree.c @@ -834,6 +834,8 @@ int dtInsert(tid_t tid, struct inode *ip, * the full page. */ DT_GETSEARCH(ip, btstack->top, bn, mp, p, index); + if (p->header.freelist == 0) + return -EINVAL; /* * insert entry for new key diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c index 2ec35889ad24..1407feccbc2d 100644 --- a/fs/jfs/jfs_imap.c +++ b/fs/jfs/jfs_imap.c @@ -290,7 +290,7 @@ int diSync(struct inode *ipimap) int diRead(struct inode *ip) { struct jfs_sb_info *sbi = JFS_SBI(ip->i_sb); - int iagno, ino, extno, rc; + int iagno, ino, extno, rc, agno; struct inode *ipimap; struct dinode *dp; struct iag *iagp; @@ -339,8 +339,11 @@ int diRead(struct inode *ip) /* get the ag for the iag */ agstart = le64_to_cpu(iagp->agstart); + agno = BLKTOAG(agstart, JFS_SBI(ip->i_sb)); release_metapage(mp); + if (agno >= MAXAG || agno < 0) + return -EIO; rel_inode = (ino & (INOSPERPAGE - 1)); pageno = blkno >> sbi->l2nbperpage; diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c index 9609349e92e5..270808b6219b 100644 --- a/fs/jfs/jfs_logmgr.c +++ b/fs/jfs/jfs_logmgr.c @@ -1600,7 +1600,7 @@ void jfs_flush_journal(struct jfs_log *log, int wait) mp, sizeof(struct metapage), 0); print_hex_dump(KERN_ERR, "page: ", DUMP_PREFIX_ADDRESS, 16, - sizeof(long), mp->page, + sizeof(long), mp->folio, sizeof(struct page), 0); } else print_hex_dump(KERN_ERR, "tblock:", diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c index 961569c11159..df575a873ec6 100644 --- a/fs/jfs/jfs_metapage.c +++ b/fs/jfs/jfs_metapage.c @@ -4,6 +4,7 @@ * Portions Copyright (C) Christoph Hellwig, 2001-2002 */ +#include <linux/blkdev.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/module.h> @@ -46,9 +47,9 @@ static inline void __lock_metapage(struct metapage *mp) do { set_current_state(TASK_UNINTERRUPTIBLE); if (metapage_locked(mp)) { - unlock_page(mp->page); + folio_unlock(mp->folio); io_schedule(); - lock_page(mp->page); + folio_lock(mp->folio); } } while (trylock_metapage(mp)); __set_current_state(TASK_RUNNING); @@ -56,7 +57,7 @@ static inline void __lock_metapage(struct metapage *mp) } /* - * Must have mp->page locked + * Must have mp->folio locked */ static inline void lock_metapage(struct metapage *mp) { @@ -75,36 +76,36 @@ static mempool_t *metapage_mempool; struct meta_anchor { int mp_count; atomic_t io_count; + blk_status_t status; struct metapage *mp[MPS_PER_PAGE]; }; -#define mp_anchor(page) ((struct meta_anchor *)page_private(page)) -static inline struct metapage *page_to_mp(struct page *page, int offset) +static inline struct metapage *folio_to_mp(struct folio *folio, int offset) { - if (!PagePrivate(page)) + struct meta_anchor *anchor = folio->private; + + if (!anchor) return NULL; - return mp_anchor(page)->mp[offset >> L2PSIZE]; + return anchor->mp[offset >> L2PSIZE]; } -static inline int insert_metapage(struct page *page, struct metapage *mp) +static inline int insert_metapage(struct folio *folio, struct metapage *mp) { struct meta_anchor *a; int index; int l2mp_blocks; /* log2 blocks per metapage */ - if (PagePrivate(page)) - a = mp_anchor(page); - else { + a = folio->private; + if (!a) { a = kzalloc(sizeof(struct meta_anchor), GFP_NOFS); if (!a) return -ENOMEM; - set_page_private(page, (unsigned long)a); - SetPagePrivate(page); - kmap(page); + folio_attach_private(folio, a); + kmap(&folio->page); } if (mp) { - l2mp_blocks = L2PSIZE - page->mapping->host->i_blkbits; + l2mp_blocks = L2PSIZE - folio->mapping->host->i_blkbits; index = (mp->index >> l2mp_blocks) & (MPS_PER_PAGE - 1); a->mp_count++; a->mp[index] = mp; @@ -113,10 +114,10 @@ static inline int insert_metapage(struct page *page, struct metapage *mp) return 0; } -static inline void remove_metapage(struct page *page, struct metapage *mp) +static inline void remove_metapage(struct folio *folio, struct metapage *mp) { - struct meta_anchor *a = mp_anchor(page); - int l2mp_blocks = L2PSIZE - page->mapping->host->i_blkbits; + struct meta_anchor *a = folio->private; + int l2mp_blocks = L2PSIZE - folio->mapping->host->i_blkbits; int index; index = (mp->index >> l2mp_blocks) & (MPS_PER_PAGE - 1); @@ -126,48 +127,53 @@ static inline void remove_metapage(struct page *page, struct metapage *mp) a->mp[index] = NULL; if (--a->mp_count == 0) { kfree(a); - set_page_private(page, 0); - ClearPagePrivate(page); - kunmap(page); + folio_detach_private(folio); + kunmap(&folio->page); } } -static inline void inc_io(struct page *page) +static inline void inc_io(struct folio *folio) { - atomic_inc(&mp_anchor(page)->io_count); + struct meta_anchor *anchor = folio->private; + + atomic_inc(&anchor->io_count); } -static inline void dec_io(struct page *page, void (*handler) (struct page *)) +static inline void dec_io(struct folio *folio, blk_status_t status, + void (*handler)(struct folio *, blk_status_t)) { - if (atomic_dec_and_test(&mp_anchor(page)->io_count)) - handler(page); + struct meta_anchor *anchor = folio->private; + + if (anchor->status == BLK_STS_OK) + anchor->status = status; + + if (atomic_dec_and_test(&anchor->io_count)) + handler(folio, anchor->status); } #else -static inline struct metapage *page_to_mp(struct page *page, int offset) +static inline struct metapage *folio_to_mp(struct folio *folio, int offset) { - return PagePrivate(page) ? (struct metapage *)page_private(page) : NULL; + return folio->private; } -static inline int insert_metapage(struct page *page, struct metapage *mp) +static inline int insert_metapage(struct folio *folio, struct metapage *mp) { if (mp) { - set_page_private(page, (unsigned long)mp); - SetPagePrivate(page); - kmap(page); + folio_attach_private(folio, mp); + kmap(&folio->page); } return 0; } -static inline void remove_metapage(struct page *page, struct metapage *mp) +static inline void remove_metapage(struct folio *folio, struct metapage *mp) { - set_page_private(page, 0); - ClearPagePrivate(page); - kunmap(page); + folio_detach_private(folio); + kunmap(&folio->page); } -#define inc_io(page) do {} while(0) -#define dec_io(page, handler) handler(page) +#define inc_io(folio) do {} while(0) +#define dec_io(folio, status, handler) handler(folio, status) #endif @@ -218,12 +224,12 @@ void metapage_exit(void) kmem_cache_destroy(metapage_cache); } -static inline void drop_metapage(struct page *page, struct metapage *mp) +static inline void drop_metapage(struct folio *folio, struct metapage *mp) { if (mp->count || mp->nohomeok || test_bit(META_dirty, &mp->flag) || test_bit(META_io, &mp->flag)) return; - remove_metapage(page, mp); + remove_metapage(folio, mp); INCREMENT(mpStat.pagefree); free_metapage(mp); } @@ -257,23 +263,20 @@ static sector_t metapage_get_blocks(struct inode *inode, sector_t lblock, return lblock; } -static void last_read_complete(struct page *page) +static void last_read_complete(struct folio *folio, blk_status_t status) { - if (!PageError(page)) - SetPageUptodate(page); - unlock_page(page); + if (status) + printk(KERN_ERR "Read error %d at %#llx\n", status, + folio_pos(folio)); + + folio_end_read(folio, status == 0); } static void metapage_read_end_io(struct bio *bio) { - struct page *page = bio->bi_private; - - if (bio->bi_status) { - printk(KERN_ERR "metapage_read_end_io: I/O error\n"); - SetPageError(page); - } + struct folio *folio = bio->bi_private; - dec_io(page, last_read_complete); + dec_io(folio, bio->bi_status, last_read_complete); bio_put(bio); } @@ -299,13 +302,19 @@ static void remove_from_logsync(struct metapage *mp) LOGSYNC_UNLOCK(log, flags); } -static void last_write_complete(struct page *page) +static void last_write_complete(struct folio *folio, blk_status_t status) { struct metapage *mp; unsigned int offset; + if (status) { + int err = blk_status_to_errno(status); + printk(KERN_ERR "metapage_write_end_io: I/O error\n"); + mapping_set_error(folio->mapping, err); + } + for (offset = 0; offset < PAGE_SIZE; offset += PSIZE) { - mp = page_to_mp(page, offset); + mp = folio_to_mp(folio, offset); if (mp && test_bit(META_io, &mp->flag)) { if (mp->lsn) remove_from_logsync(mp); @@ -316,28 +325,25 @@ static void last_write_complete(struct page *page) * safe unless I have the page locked */ } - end_page_writeback(page); + folio_end_writeback(folio); } static void metapage_write_end_io(struct bio *bio) { - struct page *page = bio->bi_private; + struct folio *folio = bio->bi_private; - BUG_ON(!PagePrivate(page)); + BUG_ON(!folio->private); - if (bio->bi_status) { - printk(KERN_ERR "metapage_write_end_io: I/O error\n"); - SetPageError(page); - } - dec_io(page, last_write_complete); + dec_io(folio, bio->bi_status, last_write_complete); bio_put(bio); } -static int metapage_writepage(struct page *page, struct writeback_control *wbc) +static int metapage_write_folio(struct folio *folio, + struct writeback_control *wbc, void *unused) { struct bio *bio = NULL; int block_offset; /* block offset of mp within page */ - struct inode *inode = page->mapping->host; + struct inode *inode = folio->mapping->host; int blocks_per_mp = JFS_SBI(inode->i_sb)->nbperpage; int len; int xlen; @@ -353,14 +359,13 @@ static int metapage_writepage(struct page *page, struct writeback_control *wbc) int offset; int bad_blocks = 0; - page_start = (sector_t)page->index << - (PAGE_SHIFT - inode->i_blkbits); - BUG_ON(!PageLocked(page)); - BUG_ON(PageWriteback(page)); - set_page_writeback(page); + page_start = folio_pos(folio) >> inode->i_blkbits; + BUG_ON(!folio_test_locked(folio)); + BUG_ON(folio_test_writeback(folio)); + folio_start_writeback(folio); for (offset = 0; offset < PAGE_SIZE; offset += PSIZE) { - mp = page_to_mp(page, offset); + mp = folio_to_mp(folio, offset); if (!mp || !test_bit(META_dirty, &mp->flag)) continue; @@ -389,22 +394,20 @@ static int metapage_writepage(struct page *page, struct writeback_control *wbc) continue; } /* Not contiguous */ - if (bio_add_page(bio, page, bio_bytes, bio_offset) < - bio_bytes) - goto add_failed; + bio_add_folio_nofail(bio, folio, bio_bytes, bio_offset); /* * Increment counter before submitting i/o to keep * count from hitting zero before we're through */ - inc_io(page); + inc_io(folio); if (!bio->bi_iter.bi_size) goto dump_bio; submit_bio(bio); nr_underway++; bio = NULL; } else - inc_io(page); - xlen = (PAGE_SIZE - offset) >> inode->i_blkbits; + inc_io(folio); + xlen = (folio_size(folio) - offset) >> inode->i_blkbits; pblock = metapage_get_blocks(inode, lblock, &xlen); if (!pblock) { printk(KERN_ERR "JFS: metapage_get_blocks failed\n"); @@ -420,7 +423,7 @@ static int metapage_writepage(struct page *page, struct writeback_control *wbc) bio = bio_alloc(inode->i_sb->s_bdev, 1, REQ_OP_WRITE, GFP_NOFS); bio->bi_iter.bi_sector = pblock << (inode->i_blkbits - 9); bio->bi_end_io = metapage_write_end_io; - bio->bi_private = page; + bio->bi_private = folio; /* Don't call bio_add_page yet, we may add to this vec */ bio_offset = offset; @@ -430,8 +433,7 @@ static int metapage_writepage(struct page *page, struct writeback_control *wbc) next_block = lblock + len; } if (bio) { - if (bio_add_page(bio, page, bio_bytes, bio_offset) < bio_bytes) - goto add_failed; + bio_add_folio_nofail(bio, folio, bio_bytes, bio_offset); if (!bio->bi_iter.bi_size) goto dump_bio; @@ -439,50 +441,56 @@ static int metapage_writepage(struct page *page, struct writeback_control *wbc) nr_underway++; } if (redirty) - redirty_page_for_writepage(wbc, page); + folio_redirty_for_writepage(wbc, folio); - unlock_page(page); + folio_unlock(folio); if (bad_blocks) goto err_out; if (nr_underway == 0) - end_page_writeback(page); + folio_end_writeback(folio); return 0; -add_failed: - /* We should never reach here, since we're only adding one vec */ - printk(KERN_ERR "JFS: bio_add_page failed unexpectedly\n"); - goto skip; dump_bio: print_hex_dump(KERN_ERR, "JFS: dump of bio: ", DUMP_PREFIX_ADDRESS, 16, 4, bio, sizeof(*bio), 0); -skip: bio_put(bio); - unlock_page(page); - dec_io(page, last_write_complete); + folio_unlock(folio); + dec_io(folio, BLK_STS_OK, last_write_complete); err_out: while (bad_blocks--) - dec_io(page, last_write_complete); + dec_io(folio, BLK_STS_OK, last_write_complete); return -EIO; } +static int metapage_writepages(struct address_space *mapping, + struct writeback_control *wbc) +{ + struct blk_plug plug; + int err; + + blk_start_plug(&plug); + err = write_cache_pages(mapping, wbc, metapage_write_folio, NULL); + blk_finish_plug(&plug); + + return err; +} + static int metapage_read_folio(struct file *fp, struct folio *folio) { - struct page *page = &folio->page; - struct inode *inode = page->mapping->host; + struct inode *inode = folio->mapping->host; struct bio *bio = NULL; int block_offset; - int blocks_per_page = i_blocks_per_page(inode, page); + int blocks_per_page = i_blocks_per_folio(inode, folio); sector_t page_start; /* address of page in fs blocks */ sector_t pblock; int xlen; unsigned int len; int offset; - BUG_ON(!PageLocked(page)); - page_start = (sector_t)page->index << - (PAGE_SHIFT - inode->i_blkbits); + BUG_ON(!folio_test_locked(folio)); + page_start = folio_pos(folio) >> inode->i_blkbits; block_offset = 0; while (block_offset < blocks_per_page) { @@ -490,9 +498,9 @@ static int metapage_read_folio(struct file *fp, struct folio *folio) pblock = metapage_get_blocks(inode, page_start + block_offset, &xlen); if (pblock) { - if (!PagePrivate(page)) - insert_metapage(page, NULL); - inc_io(page); + if (!folio->private) + insert_metapage(folio, NULL); + inc_io(folio); if (bio) submit_bio(bio); @@ -501,11 +509,10 @@ static int metapage_read_folio(struct file *fp, struct folio *folio) bio->bi_iter.bi_sector = pblock << (inode->i_blkbits - 9); bio->bi_end_io = metapage_read_end_io; - bio->bi_private = page; + bio->bi_private = folio; len = xlen << inode->i_blkbits; offset = block_offset << inode->i_blkbits; - if (bio_add_page(bio, page, len, offset) < len) - goto add_failed; + bio_add_folio_nofail(bio, folio, len, offset); block_offset += xlen; } else block_offset++; @@ -513,15 +520,9 @@ static int metapage_read_folio(struct file *fp, struct folio *folio) if (bio) submit_bio(bio); else - unlock_page(page); + folio_unlock(folio); return 0; - -add_failed: - printk(KERN_ERR "JFS: bio_add_page failed unexpectedly\n"); - bio_put(bio); - dec_io(page, last_read_complete); - return -EIO; } static bool metapage_release_folio(struct folio *folio, gfp_t gfp_mask) @@ -531,7 +532,7 @@ static bool metapage_release_folio(struct folio *folio, gfp_t gfp_mask) int offset; for (offset = 0; offset < PAGE_SIZE; offset += PSIZE) { - mp = page_to_mp(&folio->page, offset); + mp = folio_to_mp(folio, offset); if (!mp) continue; @@ -546,7 +547,7 @@ static bool metapage_release_folio(struct folio *folio, gfp_t gfp_mask) } if (mp->lsn) remove_from_logsync(mp); - remove_metapage(&folio->page, mp); + remove_metapage(folio, mp); INCREMENT(mpStat.pagefree); free_metapage(mp); } @@ -565,7 +566,7 @@ static void metapage_invalidate_folio(struct folio *folio, size_t offset, const struct address_space_operations jfs_metapage_aops = { .read_folio = metapage_read_folio, - .writepage = metapage_writepage, + .writepages = metapage_writepages, .release_folio = metapage_release_folio, .invalidate_folio = metapage_invalidate_folio, .dirty_folio = filemap_dirty_folio, @@ -579,7 +580,7 @@ struct metapage *__get_metapage(struct inode *inode, unsigned long lblock, int l2bsize; struct address_space *mapping; struct metapage *mp = NULL; - struct page *page; + struct folio *folio; unsigned long page_index; unsigned long page_offset; @@ -610,22 +611,22 @@ struct metapage *__get_metapage(struct inode *inode, unsigned long lblock, } if (new && (PSIZE == PAGE_SIZE)) { - page = grab_cache_page(mapping, page_index); - if (!page) { - jfs_err("grab_cache_page failed!"); + folio = filemap_grab_folio(mapping, page_index); + if (IS_ERR(folio)) { + jfs_err("filemap_grab_folio failed!"); return NULL; } - SetPageUptodate(page); + folio_mark_uptodate(folio); } else { - page = read_mapping_page(mapping, page_index, NULL); - if (IS_ERR(page)) { + folio = read_mapping_folio(mapping, page_index, NULL); + if (IS_ERR(folio)) { jfs_err("read_mapping_page failed!"); return NULL; } - lock_page(page); + folio_lock(folio); } - mp = page_to_mp(page, page_offset); + mp = folio_to_mp(folio, page_offset); if (mp) { if (mp->logical_size != size) { jfs_error(inode->i_sb, @@ -651,16 +652,16 @@ struct metapage *__get_metapage(struct inode *inode, unsigned long lblock, mp = alloc_metapage(GFP_NOFS); if (!mp) goto unlock; - mp->page = page; + mp->folio = folio; mp->sb = inode->i_sb; mp->flag = 0; mp->xflag = COMMIT_PAGE; mp->count = 1; mp->nohomeok = 0; mp->logical_size = size; - mp->data = page_address(page) + page_offset; + mp->data = folio_address(folio) + page_offset; mp->index = lblock; - if (unlikely(insert_metapage(page, mp))) { + if (unlikely(insert_metapage(folio, mp))) { free_metapage(mp); goto unlock; } @@ -672,28 +673,27 @@ struct metapage *__get_metapage(struct inode *inode, unsigned long lblock, memset(mp->data, 0, PSIZE); } - unlock_page(page); + folio_unlock(folio); jfs_info("__get_metapage: returning = 0x%p data = 0x%p", mp, mp->data); return mp; unlock: - unlock_page(page); + folio_unlock(folio); return NULL; } void grab_metapage(struct metapage * mp) { jfs_info("grab_metapage: mp = 0x%p", mp); - get_page(mp->page); - lock_page(mp->page); + folio_get(mp->folio); + folio_lock(mp->folio); mp->count++; lock_metapage(mp); - unlock_page(mp->page); + folio_unlock(mp->folio); } -static int metapage_write_one(struct page *page) +static int metapage_write_one(struct folio *folio) { - struct folio *folio = page_folio(page); struct address_space *mapping = folio->mapping; struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL, @@ -707,7 +707,7 @@ static int metapage_write_one(struct page *page) if (folio_clear_dirty_for_io(folio)) { folio_get(folio); - ret = metapage_writepage(page, &wbc); + ret = metapage_write_folio(folio, &wbc, NULL); if (ret == 0) folio_wait_writeback(folio); folio_put(folio); @@ -722,71 +722,69 @@ static int metapage_write_one(struct page *page) void force_metapage(struct metapage *mp) { - struct page *page = mp->page; + struct folio *folio = mp->folio; jfs_info("force_metapage: mp = 0x%p", mp); set_bit(META_forcewrite, &mp->flag); clear_bit(META_sync, &mp->flag); - get_page(page); - lock_page(page); - set_page_dirty(page); - if (metapage_write_one(page)) + folio_get(folio); + folio_lock(folio); + folio_mark_dirty(folio); + if (metapage_write_one(folio)) jfs_error(mp->sb, "metapage_write_one() failed\n"); clear_bit(META_forcewrite, &mp->flag); - put_page(page); + folio_put(folio); } void hold_metapage(struct metapage *mp) { - lock_page(mp->page); + folio_lock(mp->folio); } void put_metapage(struct metapage *mp) { if (mp->count || mp->nohomeok) { /* Someone else will release this */ - unlock_page(mp->page); + folio_unlock(mp->folio); return; } - get_page(mp->page); + folio_get(mp->folio); mp->count++; lock_metapage(mp); - unlock_page(mp->page); + folio_unlock(mp->folio); release_metapage(mp); } void release_metapage(struct metapage * mp) { - struct page *page = mp->page; + struct folio *folio = mp->folio; jfs_info("release_metapage: mp = 0x%p, flag = 0x%lx", mp, mp->flag); - BUG_ON(!page); - - lock_page(page); + folio_lock(folio); unlock_metapage(mp); assert(mp->count); if (--mp->count || mp->nohomeok) { - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); return; } if (test_bit(META_dirty, &mp->flag)) { - set_page_dirty(page); + folio_mark_dirty(folio); if (test_bit(META_sync, &mp->flag)) { clear_bit(META_sync, &mp->flag); - if (metapage_write_one(page)) + if (metapage_write_one(folio)) jfs_error(mp->sb, "metapage_write_one() failed\n"); - lock_page(page); + folio_lock(folio); } } else if (mp->lsn) /* discard_metapage doesn't remove it */ remove_from_logsync(mp); /* Try to keep metapages from using up too much memory */ - drop_metapage(page, mp); + drop_metapage(folio, mp); - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); } void __invalidate_metapages(struct inode *ip, s64 addr, int len) @@ -798,7 +796,6 @@ void __invalidate_metapages(struct inode *ip, s64 addr, int len) struct address_space *mapping = JFS_SBI(ip->i_sb)->direct_inode->i_mapping; struct metapage *mp; - struct page *page; unsigned int offset; /* @@ -807,11 +804,12 @@ void __invalidate_metapages(struct inode *ip, s64 addr, int len) */ for (lblock = addr & ~(BlocksPerPage - 1); lblock < addr + len; lblock += BlocksPerPage) { - page = find_lock_page(mapping, lblock >> l2BlocksPerPage); - if (!page) + struct folio *folio = filemap_lock_folio(mapping, + lblock >> l2BlocksPerPage); + if (IS_ERR(folio)) continue; for (offset = 0; offset < PAGE_SIZE; offset += PSIZE) { - mp = page_to_mp(page, offset); + mp = folio_to_mp(folio, offset); if (!mp) continue; if (mp->index < addr) @@ -824,8 +822,8 @@ void __invalidate_metapages(struct inode *ip, s64 addr, int len) if (mp->lsn) remove_from_logsync(mp); } - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); } } diff --git a/fs/jfs/jfs_metapage.h b/fs/jfs/jfs_metapage.h index 4179f9df4deb..2e5015c2705b 100644 --- a/fs/jfs/jfs_metapage.h +++ b/fs/jfs/jfs_metapage.h @@ -24,7 +24,7 @@ struct metapage { wait_queue_head_t wait; /* implementation */ - struct page *page; + struct folio *folio; struct super_block *sb; unsigned int logical_size; @@ -90,14 +90,14 @@ static inline void discard_metapage(struct metapage *mp) static inline void metapage_nohomeok(struct metapage *mp) { - struct page *page = mp->page; - lock_page(page); + struct folio *folio = mp->folio; + folio_lock(folio); if (!mp->nohomeok++) { mark_metapage_dirty(mp); - get_page(page); - wait_on_page_writeback(page); + folio_get(folio); + folio_wait_writeback(folio); } - unlock_page(page); + folio_unlock(folio); } /* @@ -107,7 +107,7 @@ static inline void metapage_nohomeok(struct metapage *mp) static inline void metapage_wait_for_io(struct metapage *mp) { if (test_bit(META_io, &mp->flag)) - wait_on_page_writeback(mp->page); + folio_wait_writeback(mp->folio); } /* @@ -116,7 +116,7 @@ static inline void metapage_wait_for_io(struct metapage *mp) static inline void _metapage_homeok(struct metapage *mp) { if (!--mp->nohomeok) - put_page(mp->page); + folio_put(mp->folio); } static inline void metapage_homeok(struct metapage *mp) diff --git a/fs/jfs/xattr.c b/fs/jfs/xattr.c index 9987055293b3..2999ed5d83f5 100644 --- a/fs/jfs/xattr.c +++ b/fs/jfs/xattr.c @@ -797,7 +797,7 @@ ssize_t __jfs_getxattr(struct inode *inode, const char *name, void *data, size_t buf_size) { struct jfs_ea_list *ealist; - struct jfs_ea *ea; + struct jfs_ea *ea, *ealist_end; struct ea_buffer ea_buf; int xattr_size; ssize_t size; @@ -817,9 +817,16 @@ ssize_t __jfs_getxattr(struct inode *inode, const char *name, void *data, goto not_found; ealist = (struct jfs_ea_list *) ea_buf.xattr; + ealist_end = END_EALIST(ealist); /* Find the named attribute */ - for (ea = FIRST_EA(ealist); ea < END_EALIST(ealist); ea = NEXT_EA(ea)) + for (ea = FIRST_EA(ealist); ea < ealist_end; ea = NEXT_EA(ea)) { + if (unlikely(ea + 1 > ealist_end) || + unlikely(NEXT_EA(ea) > ealist_end)) { + size = -EUCLEAN; + goto release; + } + if ((namelen == ea->namelen) && memcmp(name, ea->name, namelen) == 0) { /* Found it */ @@ -834,6 +841,7 @@ ssize_t __jfs_getxattr(struct inode *inode, const char *name, void *data, memcpy(data, value, size); goto release; } + } not_found: size = -ENODATA; release: @@ -861,7 +869,7 @@ ssize_t jfs_listxattr(struct dentry * dentry, char *data, size_t buf_size) ssize_t size = 0; int xattr_size; struct jfs_ea_list *ealist; - struct jfs_ea *ea; + struct jfs_ea *ea, *ealist_end; struct ea_buffer ea_buf; down_read(&JFS_IP(inode)->xattr_sem); @@ -876,9 +884,16 @@ ssize_t jfs_listxattr(struct dentry * dentry, char *data, size_t buf_size) goto release; ealist = (struct jfs_ea_list *) ea_buf.xattr; + ealist_end = END_EALIST(ealist); /* compute required size of list */ - for (ea = FIRST_EA(ealist); ea < END_EALIST(ealist); ea = NEXT_EA(ea)) { + for (ea = FIRST_EA(ealist); ea < ealist_end; ea = NEXT_EA(ea)) { + if (unlikely(ea + 1 > ealist_end) || + unlikely(NEXT_EA(ea) > ealist_end)) { + size = -EUCLEAN; + goto release; + } + if (can_list(ea)) size += name_size(ea) + 1; } diff --git a/fs/ntfs3/attrib.c b/fs/ntfs3/attrib.c index 8e6bcdf99770..6ede3e924dec 100644 --- a/fs/ntfs3/attrib.c +++ b/fs/ntfs3/attrib.c @@ -231,7 +231,7 @@ int attr_make_nonresident(struct ntfs_inode *ni, struct ATTRIB *attr, struct ntfs_sb_info *sbi; struct ATTRIB *attr_s; struct MFT_REC *rec; - u32 used, asize, rsize, aoff, align; + u32 used, asize, rsize, aoff; bool is_data; CLST len, alen; char *next; @@ -252,10 +252,13 @@ int attr_make_nonresident(struct ntfs_inode *ni, struct ATTRIB *attr, rsize = le32_to_cpu(attr->res.data_size); is_data = attr->type == ATTR_DATA && !attr->name_len; - align = sbi->cluster_size; - if (is_attr_compressed(attr)) - align <<= COMPRESSION_UNIT; - len = (rsize + align - 1) >> sbi->cluster_bits; + /* len - how many clusters required to store 'rsize' bytes */ + if (is_attr_compressed(attr)) { + u8 shift = sbi->cluster_bits + NTFS_LZNT_CUNIT; + len = ((rsize + (1u << shift) - 1) >> shift) << NTFS_LZNT_CUNIT; + } else { + len = bytes_to_cluster(sbi, rsize); + } run_init(run); @@ -285,22 +288,21 @@ int attr_make_nonresident(struct ntfs_inode *ni, struct ATTRIB *attr, if (err) goto out2; } else if (!page) { - char *kaddr; + struct address_space *mapping = ni->vfs_inode.i_mapping; + struct folio *folio; - page = grab_cache_page(ni->vfs_inode.i_mapping, 0); - if (!page) { - err = -ENOMEM; + folio = __filemap_get_folio( + mapping, 0, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, + mapping_gfp_mask(mapping)); + if (IS_ERR(folio)) { + err = PTR_ERR(folio); goto out2; } - kaddr = kmap_atomic(page); - memcpy(kaddr, data, rsize); - memset(kaddr + rsize, 0, PAGE_SIZE - rsize); - kunmap_atomic(kaddr); - flush_dcache_page(page); - SetPageUptodate(page); - set_page_dirty(page); - unlock_page(page); - put_page(page); + folio_fill_tail(folio, 0, data, rsize); + folio_mark_uptodate(folio); + folio_mark_dirty(folio); + folio_unlock(folio); + folio_put(folio); } } @@ -670,7 +672,8 @@ pack_runs: goto undo_2; } - if (!is_mft) + /* keep runs for $MFT::$ATTR_DATA and $MFT::$ATTR_BITMAP. */ + if (ni->mi.rno != MFT_REC_MFT) run_truncate_head(run, evcn + 1); svcn = le64_to_cpu(attr->nres.svcn); @@ -972,6 +975,19 @@ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn, if (err) goto out; + /* Check for compressed frame. */ + err = attr_is_frame_compressed(ni, attr, vcn >> NTFS_LZNT_CUNIT, &hint); + if (err) + goto out; + + if (hint) { + /* if frame is compressed - don't touch it. */ + *lcn = COMPRESSED_LCN; + *len = hint; + err = -EOPNOTSUPP; + goto out; + } + if (!*len) { if (run_lookup_entry(run, vcn, lcn, len, NULL)) { if (*lcn != SPARSE_LCN || !new) @@ -1223,11 +1239,12 @@ undo1: goto out; } -int attr_data_read_resident(struct ntfs_inode *ni, struct page *page) +int attr_data_read_resident(struct ntfs_inode *ni, struct folio *folio) { u64 vbo; struct ATTRIB *attr; u32 data_size; + size_t len; attr = ni_find_attr(ni, NULL, NULL, ATTR_DATA, NULL, 0, NULL, NULL); if (!attr) @@ -1236,30 +1253,20 @@ int attr_data_read_resident(struct ntfs_inode *ni, struct page *page) if (attr->non_res) return E_NTFS_NONRESIDENT; - vbo = page->index << PAGE_SHIFT; + vbo = folio->index << PAGE_SHIFT; data_size = le32_to_cpu(attr->res.data_size); - if (vbo < data_size) { - const char *data = resident_data(attr); - char *kaddr = kmap_atomic(page); - u32 use = data_size - vbo; + if (vbo > data_size) + len = 0; + else + len = min(data_size - vbo, folio_size(folio)); - if (use > PAGE_SIZE) - use = PAGE_SIZE; - - memcpy(kaddr, data + vbo, use); - memset(kaddr + use, 0, PAGE_SIZE - use); - kunmap_atomic(kaddr); - flush_dcache_page(page); - SetPageUptodate(page); - } else if (!PageUptodate(page)) { - zero_user_segment(page, 0, PAGE_SIZE); - SetPageUptodate(page); - } + folio_fill_tail(folio, 0, resident_data(attr) + vbo, len); + folio_mark_uptodate(folio); return 0; } -int attr_data_write_resident(struct ntfs_inode *ni, struct page *page) +int attr_data_write_resident(struct ntfs_inode *ni, struct folio *folio) { u64 vbo; struct mft_inode *mi; @@ -1275,17 +1282,13 @@ int attr_data_write_resident(struct ntfs_inode *ni, struct page *page) return E_NTFS_NONRESIDENT; } - vbo = page->index << PAGE_SHIFT; + vbo = folio->index << PAGE_SHIFT; data_size = le32_to_cpu(attr->res.data_size); if (vbo < data_size) { char *data = resident_data(attr); - char *kaddr = kmap_atomic(page); - u32 use = data_size - vbo; + size_t len = min(data_size - vbo, folio_size(folio)); - if (use > PAGE_SIZE) - use = PAGE_SIZE; - memcpy(data + vbo, kaddr, use); - kunmap_atomic(kaddr); + memcpy_from_folio(data + vbo, folio, 0, len); mi->dirty = true; } ni->i_valid = data_size; @@ -1378,7 +1381,7 @@ int attr_wof_frame_info(struct ntfs_inode *ni, struct ATTRIB *attr, u32 voff; u8 bytes_per_off; char *addr; - struct page *page; + struct folio *folio; int i, err; __le32 *off32; __le64 *off64; @@ -1423,18 +1426,18 @@ int attr_wof_frame_info(struct ntfs_inode *ni, struct ATTRIB *attr, wof_size = le64_to_cpu(attr->nres.data_size); down_write(&ni->file.run_lock); - page = ni->file.offs_page; - if (!page) { - page = alloc_page(GFP_KERNEL); - if (!page) { + folio = ni->file.offs_folio; + if (!folio) { + folio = folio_alloc(GFP_KERNEL, 0); + if (!folio) { err = -ENOMEM; goto out; } - page->index = -1; - ni->file.offs_page = page; + folio->index = -1; + ni->file.offs_folio = folio; } - lock_page(page); - addr = page_address(page); + folio_lock(folio); + addr = folio_address(folio); if (vbo[1]) { voff = vbo[1] & (PAGE_SIZE - 1); @@ -1450,7 +1453,8 @@ int attr_wof_frame_info(struct ntfs_inode *ni, struct ATTRIB *attr, do { pgoff_t index = vbo[i] >> PAGE_SHIFT; - if (index != page->index) { + if (index != folio->index) { + struct page *page = &folio->page; u64 from = vbo[i] & ~(u64)(PAGE_SIZE - 1); u64 to = min(from + PAGE_SIZE, wof_size); @@ -1463,10 +1467,10 @@ int attr_wof_frame_info(struct ntfs_inode *ni, struct ATTRIB *attr, err = ntfs_bio_pages(sbi, run, &page, 1, from, to - from, REQ_OP_READ); if (err) { - page->index = -1; + folio->index = -1; goto out1; } - page->index = index; + folio->index = index; } if (i) { @@ -1504,7 +1508,7 @@ int attr_wof_frame_info(struct ntfs_inode *ni, struct ATTRIB *attr, *ondisk_size = off[1] - off[0]; out1: - unlock_page(page); + folio_unlock(folio); out: up_write(&ni->file.run_lock); return err; @@ -1722,6 +1726,7 @@ repack: attr_b->nres.total_size = cpu_to_le64(total_size); inode_set_bytes(&ni->vfs_inode, total_size); + ni->ni_flags |= NI_FLAG_UPDATE_PARENT; mi_b->dirty = true; mark_inode_dirty(&ni->vfs_inode); @@ -2356,8 +2361,13 @@ int attr_insert_range(struct ntfs_inode *ni, u64 vbo, u64 bytes) mask = (sbi->cluster_size << attr_b->nres.c_unit) - 1; } - if (vbo > data_size) { - /* Insert range after the file size is not allowed. */ + if (vbo >= data_size) { + /* + * Insert range after the file size is not allowed. + * If the offset is equal to or greater than the end of + * file, an error is returned. For such operations (i.e., inserting + * a hole at the end of file), ftruncate(2) should be used. + */ return -EINVAL; } diff --git a/fs/ntfs3/bitmap.c b/fs/ntfs3/bitmap.c index c9eb01ccee51..cf4fe21a5039 100644 --- a/fs/ntfs3/bitmap.c +++ b/fs/ntfs3/bitmap.c @@ -1382,7 +1382,7 @@ int wnd_extend(struct wnd_bitmap *wnd, size_t new_bits) err = ntfs_vbo_to_lbo(sbi, &wnd->run, vbo, &lbo, &bytes); if (err) - break; + return err; bh = ntfs_bread(sb, lbo >> sb->s_blocksize_bits); if (!bh) diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c index 1937e8e612f8..fc6a8aa29e3a 100644 --- a/fs/ntfs3/dir.c +++ b/fs/ntfs3/dir.c @@ -272,9 +272,12 @@ out: return err == -ENOENT ? NULL : err ? ERR_PTR(err) : inode; } -static inline int ntfs_filldir(struct ntfs_sb_info *sbi, struct ntfs_inode *ni, - const struct NTFS_DE *e, u8 *name, - struct dir_context *ctx) +/* + * returns false if 'ctx' if full + */ +static inline bool ntfs_dir_emit(struct ntfs_sb_info *sbi, + struct ntfs_inode *ni, const struct NTFS_DE *e, + u8 *name, struct dir_context *ctx) { const struct ATTR_FILE_NAME *fname; unsigned long ino; @@ -284,29 +287,29 @@ static inline int ntfs_filldir(struct ntfs_sb_info *sbi, struct ntfs_inode *ni, fname = Add2Ptr(e, sizeof(struct NTFS_DE)); if (fname->type == FILE_NAME_DOS) - return 0; + return true; if (!mi_is_ref(&ni->mi, &fname->home)) - return 0; + return true; ino = ino_get(&e->ref); if (ino == MFT_REC_ROOT) - return 0; + return true; /* Skip meta files. Unless option to show metafiles is set. */ if (!sbi->options->showmeta && ntfs_is_meta_file(sbi, ino)) - return 0; + return true; if (sbi->options->nohidden && (fname->dup.fa & FILE_ATTRIBUTE_HIDDEN)) - return 0; + return true; name_len = ntfs_utf16_to_nls(sbi, fname->name, fname->name_len, name, PATH_MAX); if (name_len <= 0) { ntfs_warn(sbi->sb, "failed to convert name for inode %lx.", ino); - return 0; + return true; } /* @@ -326,7 +329,8 @@ static inline int ntfs_filldir(struct ntfs_sb_info *sbi, struct ntfs_inode *ni, * It does additional locks/reads just to get the type of name. * Should we use additional mount option to enable branch below? */ - if ((fname->dup.fa & FILE_ATTRIBUTE_REPARSE_POINT) && + if (((fname->dup.fa & FILE_ATTRIBUTE_REPARSE_POINT) || + fname->dup.ea_size) && ino != ni->mi.rno) { struct inode *inode = ntfs_iget5(sbi->sb, &e->ref, NULL); if (!IS_ERR_OR_NULL(inode)) { @@ -335,17 +339,20 @@ static inline int ntfs_filldir(struct ntfs_sb_info *sbi, struct ntfs_inode *ni, } } - return !dir_emit(ctx, (s8 *)name, name_len, ino, dt_type); + return dir_emit(ctx, (s8 *)name, name_len, ino, dt_type); } /* * ntfs_read_hdr - Helper function for ntfs_readdir(). + * + * returns 0 if ok. + * returns -EINVAL if directory is corrupted. + * returns +1 if 'ctx' is full. */ static int ntfs_read_hdr(struct ntfs_sb_info *sbi, struct ntfs_inode *ni, const struct INDEX_HDR *hdr, u64 vbo, u64 pos, u8 *name, struct dir_context *ctx) { - int err; const struct NTFS_DE *e; u32 e_size; u32 end = le32_to_cpu(hdr->used); @@ -353,12 +360,12 @@ static int ntfs_read_hdr(struct ntfs_sb_info *sbi, struct ntfs_inode *ni, for (;; off += e_size) { if (off + sizeof(struct NTFS_DE) > end) - return -1; + return -EINVAL; e = Add2Ptr(hdr, off); e_size = le16_to_cpu(e->size); if (e_size < sizeof(struct NTFS_DE) || off + e_size > end) - return -1; + return -EINVAL; if (de_is_last(e)) return 0; @@ -368,14 +375,15 @@ static int ntfs_read_hdr(struct ntfs_sb_info *sbi, struct ntfs_inode *ni, continue; if (le16_to_cpu(e->key_size) < SIZEOF_ATTRIBUTE_FILENAME) - return -1; + return -EINVAL; ctx->pos = vbo + off; /* Submit the name to the filldir callback. */ - err = ntfs_filldir(sbi, ni, e, name, ctx); - if (err) - return err; + if (!ntfs_dir_emit(sbi, ni, e, name, ctx)) { + /* ctx is full. */ + return +1; + } } } @@ -474,8 +482,6 @@ static int ntfs_readdir(struct file *file, struct dir_context *ctx) vbo = (u64)bit << index_bits; if (vbo >= i_size) { - ntfs_inode_err(dir, "Looks like your dir is corrupt"); - ctx->pos = eod; err = -EINVAL; goto out; } @@ -498,9 +504,16 @@ out: __putname(name); put_indx_node(node); - if (err == -ENOENT) { + if (err == 1) { + /* 'ctx' is full. */ + err = 0; + } else if (err == -ENOENT) { err = 0; ctx->pos = pos; + } else if (err < 0) { + if (err == -EINVAL) + ntfs_inode_err(dir, "directory corrupted"); + ctx->pos = eod; } return err; @@ -618,10 +631,12 @@ const struct file_operations ntfs_dir_operations = { #endif }; +#if IS_ENABLED(CONFIG_NTFS_FS) const struct file_operations ntfs_legacy_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, .iterate_shared = ntfs_readdir, .open = ntfs_file_open, }; +#endif // clang-format on diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index 2f903b6ce157..ca1ddc46bd86 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -13,6 +13,7 @@ #include <linux/compat.h> #include <linux/falloc.h> #include <linux/fiemap.h> +#include <linux/fileattr.h> #include "debug.h" #include "ntfs.h" @@ -48,6 +49,65 @@ static int ntfs_ioctl_fitrim(struct ntfs_sb_info *sbi, unsigned long arg) return 0; } +/* + * ntfs_fileattr_get - inode_operations::fileattr_get + */ +int ntfs_fileattr_get(struct dentry *dentry, struct fileattr *fa) +{ + struct inode *inode = d_inode(dentry); + struct ntfs_inode *ni = ntfs_i(inode); + u32 flags = 0; + + if (inode->i_flags & S_IMMUTABLE) + flags |= FS_IMMUTABLE_FL; + + if (inode->i_flags & S_APPEND) + flags |= FS_APPEND_FL; + + if (is_compressed(ni)) + flags |= FS_COMPR_FL; + + if (is_encrypted(ni)) + flags |= FS_ENCRYPT_FL; + + fileattr_fill_flags(fa, flags); + + return 0; +} + +/* + * ntfs_fileattr_set - inode_operations::fileattr_set + */ +int ntfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, + struct fileattr *fa) +{ + struct inode *inode = d_inode(dentry); + u32 flags = fa->flags; + unsigned int new_fl = 0; + + if (fileattr_has_fsx(fa)) + return -EOPNOTSUPP; + + if (flags & ~(FS_IMMUTABLE_FL | FS_APPEND_FL)) + return -EOPNOTSUPP; + + if (flags & FS_IMMUTABLE_FL) + new_fl |= S_IMMUTABLE; + + if (flags & FS_APPEND_FL) + new_fl |= S_APPEND; + + inode_set_flags(inode, new_fl, S_IMMUTABLE | S_APPEND); + + inode_set_ctime_current(inode); + mark_inode_dirty(inode); + + return 0; +} + +/* + * ntfs_ioctl - file_operations::unlocked_ioctl + */ long ntfs_ioctl(struct file *filp, u32 cmd, unsigned long arg) { struct inode *inode = file_inode(filp); @@ -77,20 +137,27 @@ int ntfs_getattr(struct mnt_idmap *idmap, const struct path *path, struct inode *inode = d_inode(path->dentry); struct ntfs_inode *ni = ntfs_i(inode); + stat->result_mask |= STATX_BTIME; + stat->btime = ni->i_crtime; + stat->blksize = ni->mi.sbi->cluster_size; /* 512, 1K, ..., 2M */ + + if (inode->i_flags & S_IMMUTABLE) + stat->attributes |= STATX_ATTR_IMMUTABLE; + + if (inode->i_flags & S_APPEND) + stat->attributes |= STATX_ATTR_APPEND; + if (is_compressed(ni)) stat->attributes |= STATX_ATTR_COMPRESSED; if (is_encrypted(ni)) stat->attributes |= STATX_ATTR_ENCRYPTED; - stat->attributes_mask |= STATX_ATTR_COMPRESSED | STATX_ATTR_ENCRYPTED; + stat->attributes_mask |= STATX_ATTR_COMPRESSED | STATX_ATTR_ENCRYPTED | + STATX_ATTR_IMMUTABLE | STATX_ATTR_APPEND; generic_fillattr(idmap, request_mask, inode, stat); - stat->result_mask |= STATX_BTIME; - stat->btime = ni->i_crtime; - stat->blksize = ni->mi.sbi->cluster_size; /* 512, 1K, ..., 2M */ - return 0; } @@ -196,9 +263,9 @@ static int ntfs_zero_range(struct inode *inode, u64 vbo, u64 vbo_to) PAGE_SIZE; iblock = page_off >> inode->i_blkbits; - folio = __filemap_get_folio(mapping, idx, - FGP_LOCK | FGP_ACCESSED | FGP_CREAT, - mapping_gfp_constraint(mapping, ~__GFP_FS)); + folio = __filemap_get_folio( + mapping, idx, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, + mapping_gfp_constraint(mapping, ~__GFP_FS)); if (IS_ERR(folio)) return PTR_ERR(folio); @@ -253,8 +320,7 @@ out: */ static int ntfs_file_mmap(struct file *file, struct vm_area_struct *vma) { - struct address_space *mapping = file->f_mapping; - struct inode *inode = mapping->host; + struct inode *inode = file_inode(file); struct ntfs_inode *ni = ntfs_i(inode); u64 from = ((u64)vma->vm_pgoff << PAGE_SHIFT); bool rw = vma->vm_flags & VM_WRITE; @@ -299,10 +365,7 @@ static int ntfs_file_mmap(struct file *file, struct vm_area_struct *vma) } if (ni->i_valid < to) { - if (!inode_trylock(inode)) { - err = -EAGAIN; - goto out; - } + inode_lock(inode); err = ntfs_extend_initialized_size(file, ni, ni->i_valid, to); inode_unlock(inode); @@ -431,7 +494,7 @@ static int ntfs_truncate(struct inode *inode, loff_t new_size) */ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len) { - struct inode *inode = file->f_mapping->host; + struct inode *inode = file_inode(file); struct address_space *mapping = inode->i_mapping; struct super_block *sb = inode->i_sb; struct ntfs_sb_info *sbi = sb->s_fs_info; @@ -744,7 +807,7 @@ out: static ssize_t ntfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; - struct inode *inode = file->f_mapping->host; + struct inode *inode = file_inode(file); struct ntfs_inode *ni = ntfs_i(inode); if (unlikely(ntfs3_forced_shutdown(inode->i_sb))) @@ -781,7 +844,7 @@ static ssize_t ntfs_file_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { - struct inode *inode = in->f_mapping->host; + struct inode *inode = file_inode(in); struct ntfs_inode *ni = ntfs_i(inode); if (unlikely(ntfs3_forced_shutdown(inode->i_sb))) @@ -824,23 +887,25 @@ static int ntfs_get_frame_pages(struct address_space *mapping, pgoff_t index, *frame_uptodate = true; for (npages = 0; npages < pages_per_frame; npages++, index++) { - struct page *page; + struct folio *folio; - page = find_or_create_page(mapping, index, gfp_mask); - if (!page) { + folio = __filemap_get_folio(mapping, index, + FGP_LOCK | FGP_ACCESSED | FGP_CREAT, + gfp_mask); + if (IS_ERR(folio)) { while (npages--) { - page = pages[npages]; - unlock_page(page); - put_page(page); + folio = page_folio(pages[npages]); + folio_unlock(folio); + folio_put(folio); } return -ENOMEM; } - if (!PageUptodate(page)) + if (!folio_test_uptodate(folio)) *frame_uptodate = false; - pages[npages] = page; + pages[npages] = &folio->page; } return 0; @@ -1075,8 +1140,7 @@ out: static ssize_t ntfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; - struct address_space *mapping = file->f_mapping; - struct inode *inode = mapping->host; + struct inode *inode = file_inode(file); ssize_t ret; int err; struct ntfs_inode *ni = ntfs_i(inode); @@ -1198,7 +1262,7 @@ static int ntfs_file_release(struct inode *inode, struct file *file) } /* - * ntfs_fiemap - file_operations::fiemap + * ntfs_fiemap - inode_operations::fiemap */ int ntfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len) @@ -1227,6 +1291,8 @@ const struct inode_operations ntfs_file_inode_operations = { .get_acl = ntfs_get_acl, .set_acl = ntfs_set_acl, .fiemap = ntfs_fiemap, + .fileattr_get = ntfs_fileattr_get, + .fileattr_set = ntfs_fileattr_set, }; const struct file_operations ntfs_file_operations = { @@ -1246,6 +1312,7 @@ const struct file_operations ntfs_file_operations = { .release = ntfs_file_release, }; +#if IS_ENABLED(CONFIG_NTFS_FS) const struct file_operations ntfs_legacy_file_operations = { .llseek = generic_file_llseek, .read_iter = ntfs_file_read_iter, @@ -1253,4 +1320,5 @@ const struct file_operations ntfs_legacy_file_operations = { .open = ntfs_file_open, .release = ntfs_file_release, }; +#endif // clang-format on diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c index 0008670939a4..a469c608a394 100644 --- a/fs/ntfs3/frecord.c +++ b/fs/ntfs3/frecord.c @@ -122,10 +122,10 @@ void ni_clear(struct ntfs_inode *ni) else { run_close(&ni->file.run); #ifdef CONFIG_NTFS3_LZX_XPRESS - if (ni->file.offs_page) { + if (ni->file.offs_folio) { /* On-demand allocated page for offsets. */ - put_page(ni->file.offs_page); - ni->file.offs_page = NULL; + folio_put(ni->file.offs_folio); + ni->file.offs_folio = NULL; } #endif } @@ -1501,7 +1501,7 @@ int ni_insert_nonresident(struct ntfs_inode *ni, enum ATTR_TYPE type, if (is_ext) { if (flags & ATTR_FLAG_COMPRESSED) - attr->nres.c_unit = COMPRESSION_UNIT; + attr->nres.c_unit = NTFS_LZNT_CUNIT; attr->nres.total_size = attr->nres.alloc_size; } @@ -1601,8 +1601,10 @@ int ni_delete_all(struct ntfs_inode *ni) asize = le32_to_cpu(attr->size); roff = le16_to_cpu(attr->nres.run_off); - if (roff > asize) + if (roff > asize) { + _ntfs_bad_inode(&ni->vfs_inode); return -EINVAL; + } /* run==1 means unpack and deallocate. */ run_unpack_ex(RUN_DEALLOCATE, sbi, ni->mi.rno, svcn, evcn, svcn, @@ -1897,6 +1899,47 @@ enum REPARSE_SIGN ni_parse_reparse(struct ntfs_inode *ni, struct ATTRIB *attr, } /* + * fiemap_fill_next_extent_k - a copy of fiemap_fill_next_extent + * but it accepts kernel address for fi_extents_start + */ +static int fiemap_fill_next_extent_k(struct fiemap_extent_info *fieinfo, + u64 logical, u64 phys, u64 len, u32 flags) +{ + struct fiemap_extent extent; + struct fiemap_extent __user *dest = fieinfo->fi_extents_start; + + /* only count the extents */ + if (fieinfo->fi_extents_max == 0) { + fieinfo->fi_extents_mapped++; + return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0; + } + + if (fieinfo->fi_extents_mapped >= fieinfo->fi_extents_max) + return 1; + + if (flags & FIEMAP_EXTENT_DELALLOC) + flags |= FIEMAP_EXTENT_UNKNOWN; + if (flags & FIEMAP_EXTENT_DATA_ENCRYPTED) + flags |= FIEMAP_EXTENT_ENCODED; + if (flags & (FIEMAP_EXTENT_DATA_TAIL | FIEMAP_EXTENT_DATA_INLINE)) + flags |= FIEMAP_EXTENT_NOT_ALIGNED; + + memset(&extent, 0, sizeof(extent)); + extent.fe_logical = logical; + extent.fe_physical = phys; + extent.fe_length = len; + extent.fe_flags = flags; + + dest += fieinfo->fi_extents_mapped; + memcpy(dest, &extent, sizeof(extent)); + + fieinfo->fi_extents_mapped++; + if (fieinfo->fi_extents_mapped == fieinfo->fi_extents_max) + return 1; + return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0; +} + +/* * ni_fiemap - Helper for file_fiemap(). * * Assumed ni_lock. @@ -1906,6 +1949,8 @@ int ni_fiemap(struct ntfs_inode *ni, struct fiemap_extent_info *fieinfo, __u64 vbo, __u64 len) { int err = 0; + struct fiemap_extent __user *fe_u = fieinfo->fi_extents_start; + struct fiemap_extent *fe_k = NULL; struct ntfs_sb_info *sbi = ni->mi.sbi; u8 cluster_bits = sbi->cluster_bits; struct runs_tree *run; @@ -1953,6 +1998,18 @@ int ni_fiemap(struct ntfs_inode *ni, struct fiemap_extent_info *fieinfo, goto out; } + /* + * To avoid lock problems replace pointer to user memory by pointer to kernel memory. + */ + fe_k = kmalloc_array(fieinfo->fi_extents_max, + sizeof(struct fiemap_extent), + GFP_NOFS | __GFP_ZERO); + if (!fe_k) { + err = -ENOMEM; + goto out; + } + fieinfo->fi_extents_start = fe_k; + end = vbo + len; alloc_size = le64_to_cpu(attr->nres.alloc_size); if (end > alloc_size) @@ -2041,8 +2098,9 @@ int ni_fiemap(struct ntfs_inode *ni, struct fiemap_extent_info *fieinfo, if (vbo + dlen >= end) flags |= FIEMAP_EXTENT_LAST; - err = fiemap_fill_next_extent(fieinfo, vbo, lbo, dlen, - flags); + err = fiemap_fill_next_extent_k(fieinfo, vbo, lbo, dlen, + flags); + if (err < 0) break; if (err == 1) { @@ -2062,7 +2120,8 @@ int ni_fiemap(struct ntfs_inode *ni, struct fiemap_extent_info *fieinfo, if (vbo + bytes >= end) flags |= FIEMAP_EXTENT_LAST; - err = fiemap_fill_next_extent(fieinfo, vbo, lbo, bytes, flags); + err = fiemap_fill_next_extent_k(fieinfo, vbo, lbo, bytes, + flags); if (err < 0) break; if (err == 1) { @@ -2075,7 +2134,19 @@ int ni_fiemap(struct ntfs_inode *ni, struct fiemap_extent_info *fieinfo, up_read(run_lock); + /* + * Copy to user memory out of lock + */ + if (copy_to_user(fe_u, fe_k, + fieinfo->fi_extents_max * + sizeof(struct fiemap_extent))) { + err = -EFAULT; + } + out: + /* Restore original pointer. */ + fieinfo->fi_extents_start = fe_u; + kfree(fe_k); return err; } @@ -2085,12 +2156,12 @@ out: * When decompressing, we typically obtain more than one page per reference. * We inject the additional pages into the page cache. */ -int ni_readpage_cmpr(struct ntfs_inode *ni, struct page *page) +int ni_readpage_cmpr(struct ntfs_inode *ni, struct folio *folio) { int err; struct ntfs_sb_info *sbi = ni->mi.sbi; - struct address_space *mapping = page->mapping; - pgoff_t index = page->index; + struct address_space *mapping = folio->mapping; + pgoff_t index = folio->index; u64 frame_vbo, vbo = (u64)index << PAGE_SHIFT; struct page **pages = NULL; /* Array of at most 16 pages. stack? */ u8 frame_bits; @@ -2100,7 +2171,8 @@ int ni_readpage_cmpr(struct ntfs_inode *ni, struct page *page) struct page *pg; if (vbo >= i_size_read(&ni->vfs_inode)) { - SetPageUptodate(page); + folio_zero_range(folio, 0, folio_size(folio)); + folio_mark_uptodate(folio); err = 0; goto out; } @@ -2124,7 +2196,7 @@ int ni_readpage_cmpr(struct ntfs_inode *ni, struct page *page) goto out; } - pages[idx] = page; + pages[idx] = &folio->page; index = frame_vbo >> PAGE_SHIFT; gfp_mask = mapping_gfp_mask(mapping); @@ -2143,9 +2215,6 @@ int ni_readpage_cmpr(struct ntfs_inode *ni, struct page *page) err = ni_read_frame(ni, frame_vbo, pages, pages_per_frame); out1: - if (err) - SetPageError(page); - for (i = 0; i < pages_per_frame; i++) { pg = pages[i]; if (i == idx || !pg) @@ -2157,7 +2226,7 @@ out1: out: /* At this point, err contains 0 or -EIO depending on the "critical" page. */ kfree(pages); - unlock_page(page); + folio_unlock(folio); return err; } @@ -2362,9 +2431,9 @@ remove_wof: /* Clear cached flag. */ ni->ni_flags &= ~NI_FLAG_COMPRESSED_MASK; - if (ni->file.offs_page) { - put_page(ni->file.offs_page); - ni->file.offs_page = NULL; + if (ni->file.offs_folio) { + folio_put(ni->file.offs_folio); + ni->file.offs_folio = NULL; } mapping->a_ops = &ntfs_aops; @@ -2718,7 +2787,6 @@ out: for (i = 0; i < pages_per_frame; i++) { pg = pages[i]; kunmap(pg); - ClearPageError(pg); SetPageUptodate(pg); } diff --git a/fs/ntfs3/fslog.c b/fs/ntfs3/fslog.c index d7807d255dfe..c64dd114ac65 100644 --- a/fs/ntfs3/fslog.c +++ b/fs/ntfs3/fslog.c @@ -724,7 +724,8 @@ static bool check_rstbl(const struct RESTART_TABLE *rt, size_t bytes) if (!rsize || rsize > bytes || rsize + sizeof(struct RESTART_TABLE) > bytes || bytes < ts || - le16_to_cpu(rt->total) > ne || ff > ts || lf > ts || + le16_to_cpu(rt->total) > ne || ff > ts - sizeof(__le32) || + lf > ts - sizeof(__le32) || (ff && ff < sizeof(struct RESTART_TABLE)) || (lf && lf < sizeof(struct RESTART_TABLE))) { return false; @@ -754,6 +755,9 @@ static bool check_rstbl(const struct RESTART_TABLE *rt, size_t bytes) return false; off = le32_to_cpu(*(__le32 *)Add2Ptr(rt, off)); + + if (off > ts - sizeof(__le32)) + return false; } return true; @@ -2992,7 +2996,7 @@ static struct ATTRIB *attr_create_nonres_log(struct ntfs_sb_info *sbi, if (is_ext) { attr->name_off = SIZEOF_NONRESIDENT_EX_LE; if (is_attr_compressed(attr)) - attr->nres.c_unit = COMPRESSION_UNIT; + attr->nres.c_unit = NTFS_LZNT_CUNIT; attr->nres.run_off = cpu_to_le16(SIZEOF_NONRESIDENT_EX + name_size); @@ -3722,6 +3726,8 @@ int log_replay(struct ntfs_inode *ni, bool *initialized) u64 rec_lsn, checkpt_lsn = 0, rlsn = 0; struct ATTR_NAME_ENTRY *attr_names = NULL; + u32 attr_names_bytes = 0; + u32 oatbl_bytes = 0; struct RESTART_TABLE *dptbl = NULL; struct RESTART_TABLE *trtbl = NULL; const struct RESTART_TABLE *rt; @@ -3736,6 +3742,7 @@ int log_replay(struct ntfs_inode *ni, bool *initialized) struct NTFS_RESTART *rst = NULL; struct lcb *lcb = NULL; struct OPEN_ATTR_ENRTY *oe; + struct ATTR_NAME_ENTRY *ane; struct TRANSACTION_ENTRY *tr; struct DIR_PAGE_ENTRY *dp; u32 i, bytes_per_attr_entry; @@ -3915,6 +3922,9 @@ check_restart_area: goto out; } + log->page_mask = log->page_size - 1; + log->page_bits = blksize_bits(log->page_size); + /* If the file size has shrunk then we won't mount it. */ if (log->l_size < le64_to_cpu(ra2->l_size)) { err = -EINVAL; @@ -4104,7 +4114,7 @@ process_log: /* Allocate and Read the Transaction Table. */ if (!rst->transact_table_len) - goto check_dirty_page_table; + goto check_dirty_page_table; /* reduce tab pressure. */ t64 = le64_to_cpu(rst->transact_table_lsn); err = read_log_rec_lcb(log, t64, lcb_ctx_prev, &lcb); @@ -4144,7 +4154,7 @@ process_log: check_dirty_page_table: /* The next record back should be the Dirty Pages Table. */ if (!rst->dirty_pages_len) - goto check_attribute_names; + goto check_attribute_names; /* reduce tab pressure. */ t64 = le64_to_cpu(rst->dirty_pages_table_lsn); err = read_log_rec_lcb(log, t64, lcb_ctx_prev, &lcb); @@ -4180,7 +4190,7 @@ check_dirty_page_table: /* Convert Ra version '0' into version '1'. */ if (rst->major_ver) - goto end_conv_1; + goto end_conv_1; /* reduce tab pressure. */ dp = NULL; while ((dp = enum_rstbl(dptbl, dp))) { @@ -4200,8 +4210,7 @@ end_conv_1: * remembering the oldest lsn values. */ if (sbi->cluster_size <= log->page_size) - goto trace_dp_table; - + goto trace_dp_table; /* reduce tab pressure. */ dp = NULL; while ((dp = enum_rstbl(dptbl, dp))) { struct DIR_PAGE_ENTRY *next = dp; @@ -4222,7 +4231,7 @@ trace_dp_table: check_attribute_names: /* The next record should be the Attribute Names. */ if (!rst->attr_names_len) - goto check_attr_table; + goto check_attr_table; /* reduce tab pressure. */ t64 = le64_to_cpu(rst->attr_names_lsn); err = read_log_rec_lcb(log, t64, lcb_ctx_prev, &lcb); @@ -4240,9 +4249,9 @@ check_attribute_names: } t32 = lrh_length(lrh); - rec_len -= t32; + attr_names_bytes = rec_len - t32; - attr_names = kmemdup(Add2Ptr(lrh, t32), rec_len, GFP_NOFS); + attr_names = kmemdup(Add2Ptr(lrh, t32), attr_names_bytes, GFP_NOFS); if (!attr_names) { err = -ENOMEM; goto out; @@ -4254,7 +4263,7 @@ check_attribute_names: check_attr_table: /* The next record should be the attribute Table. */ if (!rst->open_attr_len) - goto check_attribute_names2; + goto check_attribute_names2; /* reduce tab pressure. */ t64 = le64_to_cpu(rst->open_attr_table_lsn); err = read_log_rec_lcb(log, t64, lcb_ctx_prev, &lcb); @@ -4274,14 +4283,14 @@ check_attr_table: t16 = le16_to_cpu(lrh->redo_off); rt = Add2Ptr(lrh, t16); - t32 = rec_len - t16; + oatbl_bytes = rec_len - t16; - if (!check_rstbl(rt, t32)) { + if (!check_rstbl(rt, oatbl_bytes)) { err = -EINVAL; goto out; } - oatbl = kmemdup(rt, t32, GFP_NOFS); + oatbl = kmemdup(rt, oatbl_bytes, GFP_NOFS); if (!oatbl) { err = -ENOMEM; goto out; @@ -4314,17 +4323,40 @@ check_attr_table: lcb = NULL; check_attribute_names2: - if (rst->attr_names_len && oatbl) { - struct ATTR_NAME_ENTRY *ane = attr_names; - while (ane->off) { + if (attr_names && oatbl) { + off = 0; + for (;;) { + /* Check we can use attribute name entry 'ane'. */ + static_assert(sizeof(*ane) == 4); + if (off + sizeof(*ane) > attr_names_bytes) { + /* just ignore the rest. */ + break; + } + + ane = Add2Ptr(attr_names, off); + t16 = le16_to_cpu(ane->off); + if (!t16) { + /* this is the only valid exit. */ + break; + } + + /* Check we can use open attribute entry 'oe'. */ + if (t16 + sizeof(*oe) > oatbl_bytes) { + /* just ignore the rest. */ + break; + } + /* TODO: Clear table on exit! */ - oe = Add2Ptr(oatbl, le16_to_cpu(ane->off)); + oe = Add2Ptr(oatbl, t16); t16 = le16_to_cpu(ane->name_bytes); + off += t16 + sizeof(*ane); + if (off > attr_names_bytes) { + /* just ignore the rest. */ + break; + } oe->name_len = t16 / sizeof(short); oe->ptr = ane->name; oe->is_attr_name = 2; - ane = Add2Ptr(ane, - sizeof(struct ATTR_NAME_ENTRY) + t16); } } @@ -4520,7 +4552,6 @@ copy_lcns: } } goto next_log_record_analyze; - ; } case OpenNonresidentAttribute: @@ -4659,7 +4690,7 @@ end_log_records_enumerate: * table are not empty. */ if ((!dptbl || !dptbl->total) && (!trtbl || !trtbl->total)) - goto end_reply; + goto end_replay; sbi->flags |= NTFS_FLAGS_NEED_REPLAY; if (is_ro) @@ -5088,7 +5119,7 @@ undo_action_done: sbi->flags &= ~NTFS_FLAGS_NEED_REPLAY; -end_reply: +end_replay: err = 0; if (is_ro) diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c index 626d3f2c7e2d..0fa636038b4e 100644 --- a/fs/ntfs3/fsntfs.c +++ b/fs/ntfs3/fsntfs.c @@ -2650,8 +2650,8 @@ int ntfs_set_label(struct ntfs_sb_info *sbi, u8 *label, int len) { int err; struct ATTRIB *attr; + u32 uni_bytes; struct ntfs_inode *ni = sbi->volume.ni; - const u8 max_ulen = 0x80; /* TODO: use attrdef to get maximum length */ /* Allocate PATH_MAX bytes. */ struct cpu_str *uni = __getname(); @@ -2663,7 +2663,8 @@ int ntfs_set_label(struct ntfs_sb_info *sbi, u8 *label, int len) if (err < 0) goto out; - if (uni->len > max_ulen) { + uni_bytes = uni->len * sizeof(u16); + if (uni_bytes > NTFS_LABEL_MAX_LENGTH * sizeof(u16)) { ntfs_warn(sbi->sb, "new label is too long"); err = -EFBIG; goto out; @@ -2674,13 +2675,13 @@ int ntfs_set_label(struct ntfs_sb_info *sbi, u8 *label, int len) /* Ignore any errors. */ ni_remove_attr(ni, ATTR_LABEL, NULL, 0, false, NULL); - err = ni_insert_resident(ni, uni->len * sizeof(u16), ATTR_LABEL, NULL, - 0, &attr, NULL, NULL); + err = ni_insert_resident(ni, uni_bytes, ATTR_LABEL, NULL, 0, &attr, + NULL, NULL); if (err < 0) goto unlock_out; /* write new label in on-disk struct. */ - memcpy(resident_data(attr), uni->name, uni->len * sizeof(u16)); + memcpy(resident_data(attr), uni->name, uni_bytes); /* update cached value of current label. */ if (len >= ARRAY_SIZE(sbi->volume.label)) diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c index d0f15bbf78f6..9089c58a005c 100644 --- a/fs/ntfs3/index.c +++ b/fs/ntfs3/index.c @@ -978,7 +978,7 @@ static struct indx_node *indx_new(struct ntfs_index *indx, hdr->used = cpu_to_le32(eo + sizeof(struct NTFS_DE) + sizeof(u64)); de_set_vbn_le(e, *sub_vbn); - hdr->flags = 1; + hdr->flags = NTFS_INDEX_HDR_HAS_SUBNODES; } else { e->size = cpu_to_le16(sizeof(struct NTFS_DE)); hdr->used = cpu_to_le32(eo + sizeof(struct NTFS_DE)); @@ -1683,7 +1683,7 @@ static int indx_insert_into_root(struct ntfs_index *indx, struct ntfs_inode *ni, e->size = cpu_to_le16(sizeof(struct NTFS_DE) + sizeof(u64)); e->flags = NTFS_IE_HAS_SUBNODES | NTFS_IE_LAST; - hdr->flags = 1; + hdr->flags = NTFS_INDEX_HDR_HAS_SUBNODES; hdr->used = hdr->total = cpu_to_le32(new_root_size - offsetof(struct INDEX_ROOT, ihdr)); diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index 0f1664db94ad..6b0bdc474e76 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -18,7 +18,7 @@ #include "ntfs_fs.h" /* - * ntfs_read_mft - Read record and parses MFT. + * ntfs_read_mft - Read record and parse MFT. */ static struct inode *ntfs_read_mft(struct inode *inode, const struct cpu_str *name, @@ -441,10 +441,9 @@ end_enum: * Usually a hard links to directories are disabled. */ inode->i_op = &ntfs_dir_inode_operations; - if (is_legacy_ntfs(inode->i_sb)) - inode->i_fop = &ntfs_legacy_dir_operations; - else - inode->i_fop = &ntfs_dir_operations; + inode->i_fop = unlikely(is_legacy_ntfs(sb)) ? + &ntfs_legacy_dir_operations : + &ntfs_dir_operations; ni->i_valid = 0; } else if (S_ISLNK(mode)) { ni->std_fa &= ~FILE_ATTRIBUTE_DIRECTORY; @@ -454,10 +453,9 @@ end_enum: } else if (S_ISREG(mode)) { ni->std_fa &= ~FILE_ATTRIBUTE_DIRECTORY; inode->i_op = &ntfs_file_inode_operations; - if (is_legacy_ntfs(inode->i_sb)) - inode->i_fop = &ntfs_legacy_file_operations; - else - inode->i_fop = &ntfs_file_operations; + inode->i_fop = unlikely(is_legacy_ntfs(sb)) ? + &ntfs_legacy_file_operations : + &ntfs_file_operations; inode->i_mapping->a_ops = is_compressed(ni) ? &ntfs_aops_cmpr : &ntfs_aops; if (ino != MFT_REC_MFT) @@ -580,10 +578,11 @@ static noinline int ntfs_get_block_vbo(struct inode *inode, u64 vbo, bh->b_blocknr = RESIDENT_LCN; bh->b_size = block_size; if (!folio) { + /* direct io (read) or bmap call */ err = 0; } else { ni_lock(ni); - err = attr_data_read_resident(ni, &folio->page); + err = attr_data_read_resident(ni, folio); ni_unlock(ni); if (!err) @@ -710,25 +709,24 @@ static sector_t ntfs_bmap(struct address_space *mapping, sector_t block) static int ntfs_read_folio(struct file *file, struct folio *folio) { - struct page *page = &folio->page; int err; - struct address_space *mapping = page->mapping; + struct address_space *mapping = folio->mapping; struct inode *inode = mapping->host; struct ntfs_inode *ni = ntfs_i(inode); if (is_resident(ni)) { ni_lock(ni); - err = attr_data_read_resident(ni, page); + err = attr_data_read_resident(ni, folio); ni_unlock(ni); if (err != E_NTFS_NONRESIDENT) { - unlock_page(page); + folio_unlock(folio); return err; } } if (is_compressed(ni)) { ni_lock(ni); - err = ni_readpage_cmpr(ni, page); + err = ni_readpage_cmpr(ni, folio); ni_unlock(ni); return err; } @@ -872,7 +870,7 @@ static int ntfs_resident_writepage(struct folio *folio, return -EIO; ni_lock(ni); - ret = attr_data_write_resident(ni, &folio->page); + ret = attr_data_write_resident(ni, folio); ni_unlock(ni); if (ret != E_NTFS_NONRESIDENT) @@ -914,24 +912,25 @@ int ntfs_write_begin(struct file *file, struct address_space *mapping, *pagep = NULL; if (is_resident(ni)) { - struct page *page = - grab_cache_page_write_begin(mapping, pos >> PAGE_SHIFT); + struct folio *folio = __filemap_get_folio( + mapping, pos >> PAGE_SHIFT, FGP_WRITEBEGIN, + mapping_gfp_mask(mapping)); - if (!page) { - err = -ENOMEM; + if (IS_ERR(folio)) { + err = PTR_ERR(folio); goto out; } ni_lock(ni); - err = attr_data_read_resident(ni, page); + err = attr_data_read_resident(ni, folio); ni_unlock(ni); if (!err) { - *pagep = page; + *pagep = &folio->page; goto out; } - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); if (err != E_NTFS_NONRESIDENT) goto out; @@ -950,6 +949,7 @@ out: int ntfs_write_end(struct file *file, struct address_space *mapping, loff_t pos, u32 len, u32 copied, struct page *page, void *fsdata) { + struct folio *folio = page_folio(page); struct inode *inode = mapping->host; struct ntfs_inode *ni = ntfs_i(inode); u64 valid = ni->i_valid; @@ -958,26 +958,26 @@ int ntfs_write_end(struct file *file, struct address_space *mapping, loff_t pos, if (is_resident(ni)) { ni_lock(ni); - err = attr_data_write_resident(ni, page); + err = attr_data_write_resident(ni, folio); ni_unlock(ni); if (!err) { + struct buffer_head *head = folio_buffers(folio); dirty = true; - /* Clear any buffers in page. */ - if (page_has_buffers(page)) { - struct buffer_head *head, *bh; + /* Clear any buffers in folio. */ + if (head) { + struct buffer_head *bh = head; - bh = head = page_buffers(page); do { clear_buffer_dirty(bh); clear_buffer_mapped(bh); set_buffer_uptodate(bh); } while (head != (bh = bh->b_this_page)); } - SetPageUptodate(page); + folio_mark_uptodate(folio); err = copied; } - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); } else { err = generic_write_end(file, mapping, pos, len, copied, page, fsdata); @@ -1093,33 +1093,31 @@ int ntfs_flush_inodes(struct super_block *sb, struct inode *i1, if (!ret && i2) ret = writeback_inode(i2); if (!ret) - ret = sync_blockdev_nowait(sb->s_bdev); + ret = filemap_flush(sb->s_bdev_file->f_mapping); return ret; } -int inode_write_data(struct inode *inode, const void *data, size_t bytes) +/* + * Helper function to read file. + */ +int inode_read_data(struct inode *inode, void *data, size_t bytes) { pgoff_t idx; + struct address_space *mapping = inode->i_mapping; - /* Write non resident data. */ for (idx = 0; bytes; idx++) { size_t op = bytes > PAGE_SIZE ? PAGE_SIZE : bytes; - struct page *page = ntfs_map_page(inode->i_mapping, idx); + struct page *page = read_mapping_page(mapping, idx, NULL); + void *kaddr; if (IS_ERR(page)) return PTR_ERR(page); - lock_page(page); - WARN_ON(!PageUptodate(page)); - ClearPageUptodate(page); - - memcpy(page_address(page), data, op); - - flush_dcache_page(page); - SetPageUptodate(page); - unlock_page(page); + kaddr = kmap_atomic(page); + memcpy(data, kaddr, op); + kunmap_atomic(kaddr); - ntfs_unmap_page(page); + put_page(page); bytes -= op; data = Add2Ptr(data, PAGE_SIZE); @@ -1508,7 +1506,7 @@ int ntfs_create_inode(struct mnt_idmap *idmap, struct inode *dir, attr->size = cpu_to_le32(SIZEOF_NONRESIDENT_EX + 8); attr->name_off = SIZEOF_NONRESIDENT_EX_LE; attr->flags = ATTR_FLAG_COMPRESSED; - attr->nres.c_unit = COMPRESSION_UNIT; + attr->nres.c_unit = NTFS_LZNT_CUNIT; asize = SIZEOF_NONRESIDENT_EX + 8; } else { attr->size = cpu_to_le32(SIZEOF_NONRESIDENT + 8); @@ -1559,7 +1557,7 @@ int ntfs_create_inode(struct mnt_idmap *idmap, struct inode *dir, /* * Below function 'ntfs_save_wsl_perm' requires 0x78 bytes. - * It is good idea to keep extened attributes resident. + * It is good idea to keep extended attributes resident. */ if (asize + t16 + 0x78 + 8 > sbi->record_size) { CLST alen; @@ -1628,10 +1626,9 @@ int ntfs_create_inode(struct mnt_idmap *idmap, struct inode *dir, if (S_ISDIR(mode)) { inode->i_op = &ntfs_dir_inode_operations; - if (is_legacy_ntfs(inode->i_sb)) - inode->i_fop = &ntfs_legacy_dir_operations; - else - inode->i_fop = &ntfs_dir_operations; + inode->i_fop = unlikely(is_legacy_ntfs(sb)) ? + &ntfs_legacy_dir_operations : + &ntfs_dir_operations; } else if (S_ISLNK(mode)) { inode->i_op = &ntfs_link_inode_operations; inode->i_fop = NULL; @@ -1640,10 +1637,9 @@ int ntfs_create_inode(struct mnt_idmap *idmap, struct inode *dir, inode_nohighmem(inode); } else if (S_ISREG(mode)) { inode->i_op = &ntfs_file_inode_operations; - if (is_legacy_ntfs(inode->i_sb)) - inode->i_fop = &ntfs_legacy_file_operations; - else - inode->i_fop = &ntfs_file_operations; + inode->i_fop = unlikely(is_legacy_ntfs(sb)) ? + &ntfs_legacy_file_operations : + &ntfs_file_operations; inode->i_mapping->a_ops = is_compressed(ni) ? &ntfs_aops_cmpr : &ntfs_aops; init_rwsem(&ni->file.run_lock); @@ -1668,7 +1664,9 @@ int ntfs_create_inode(struct mnt_idmap *idmap, struct inode *dir, * The packed size of extended attribute is stored in direntry too. * 'fname' here points to inside new_de. */ - ntfs_save_wsl_perm(inode, &fname->dup.ea_size); + err = ntfs_save_wsl_perm(inode, &fname->dup.ea_size); + if (err) + goto out6; /* * update ea_size in file_name attribute too. @@ -1712,6 +1710,12 @@ int ntfs_create_inode(struct mnt_idmap *idmap, struct inode *dir, goto out2; out6: + attr = ni_find_attr(ni, NULL, NULL, ATTR_EA, NULL, 0, NULL, NULL); + if (attr && attr->non_res) { + /* Delete ATTR_EA, if non-resident. */ + attr_set_size(ni, ATTR_EA, NULL, 0, NULL, 0, NULL, false, NULL); + } + if (rp_inserted) ntfs_remove_reparse(sbi, IO_REPARSE_TAG_SYMLINK, &new_de->ref); @@ -2133,5 +2137,6 @@ const struct address_space_operations ntfs_aops = { const struct address_space_operations ntfs_aops_cmpr = { .read_folio = ntfs_read_folio, .readahead = ntfs_readahead, + .dirty_folio = block_dirty_folio, }; // clang-format on diff --git a/fs/ntfs3/namei.c b/fs/ntfs3/namei.c index 71498421ce60..f16d318c4372 100644 --- a/fs/ntfs3/namei.c +++ b/fs/ntfs3/namei.c @@ -112,9 +112,7 @@ static int ntfs_create(struct mnt_idmap *idmap, struct inode *dir, } /* - * ntfs_mknod - * - * inode_operations::mknod + * ntfs_mknod - inode_operations::mknod */ static int ntfs_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) @@ -509,6 +507,8 @@ const struct inode_operations ntfs_dir_inode_operations = { .getattr = ntfs_getattr, .listxattr = ntfs_listxattr, .fiemap = ntfs_fiemap, + .fileattr_get = ntfs_fileattr_get, + .fileattr_set = ntfs_fileattr_set, }; const struct inode_operations ntfs_special_inode_operations = { diff --git a/fs/ntfs3/ntfs.h b/fs/ntfs3/ntfs.h index 3d6143c7abc0..241f2ffdd920 100644 --- a/fs/ntfs3/ntfs.h +++ b/fs/ntfs3/ntfs.h @@ -82,9 +82,6 @@ typedef u32 CLST; #define RESIDENT_LCN ((CLST)-2) #define COMPRESSED_LCN ((CLST)-3) -#define COMPRESSION_UNIT 4 -#define COMPRESS_MAX_CLUSTER 0x1000 - enum RECORD_NUM { MFT_REC_MFT = 0, MFT_REC_MIRR = 1, @@ -696,14 +693,15 @@ static inline bool de_has_vcn_ex(const struct NTFS_DE *e) offsetof(struct ATTR_FILE_NAME, name) + \ NTFS_NAME_LEN * sizeof(short), 8) +#define NTFS_INDEX_HDR_HAS_SUBNODES cpu_to_le32(1) + struct INDEX_HDR { __le32 de_off; // 0x00: The offset from the start of this structure // to the first NTFS_DE. __le32 used; // 0x04: The size of this structure plus all // entries (quad-word aligned). __le32 total; // 0x08: The allocated size of for this structure plus all entries. - u8 flags; // 0x0C: 0x00 = Small directory, 0x01 = Large directory. - u8 res[3]; + __le32 flags; // 0x0C: 0x00 = Small directory, 0x01 = Large directory. // // de_off + used <= total @@ -751,7 +749,7 @@ static inline struct NTFS_DE *hdr_next_de(const struct INDEX_HDR *hdr, static inline bool hdr_has_subnode(const struct INDEX_HDR *hdr) { - return hdr->flags & 1; + return hdr->flags & NTFS_INDEX_HDR_HAS_SUBNODES; } struct INDEX_BUFFER { @@ -771,7 +769,7 @@ static inline bool ib_is_empty(const struct INDEX_BUFFER *ib) static inline bool ib_is_leaf(const struct INDEX_BUFFER *ib) { - return !(ib->ihdr.flags & 1); + return !(ib->ihdr.flags & NTFS_INDEX_HDR_HAS_SUBNODES); } /* Index root structure ( 0x90 ). */ @@ -1002,9 +1000,6 @@ struct REPARSE_POINT { static_assert(sizeof(struct REPARSE_POINT) == 0x18); -/* Maximum allowed size of the reparse data. */ -#define MAXIMUM_REPARSE_DATA_BUFFER_SIZE (16 * 1024) - /* * The value of the following constant needs to satisfy the following * conditions: diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index f9ed6d2b065d..e5255a251929 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -383,7 +383,7 @@ struct ntfs_inode { struct rw_semaphore run_lock; struct runs_tree run; #ifdef CONFIG_NTFS3_LZX_XPRESS - struct page *offs_page; + struct folio *offs_folio; #endif } file; }; @@ -434,8 +434,8 @@ int attr_set_size(struct ntfs_inode *ni, enum ATTR_TYPE type, struct ATTRIB **ret); int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn, CLST *len, bool *new, bool zero); -int attr_data_read_resident(struct ntfs_inode *ni, struct page *page); -int attr_data_write_resident(struct ntfs_inode *ni, struct page *page); +int attr_data_read_resident(struct ntfs_inode *ni, struct folio *folio); +int attr_data_write_resident(struct ntfs_inode *ni, struct folio *folio); int attr_load_runs_vcn(struct ntfs_inode *ni, enum ATTR_TYPE type, const __le16 *name, u8 name_len, struct runs_tree *run, CLST vcn); @@ -497,6 +497,9 @@ extern const struct file_operations ntfs_dir_operations; extern const struct file_operations ntfs_legacy_dir_operations; /* Globals from file.c */ +int ntfs_fileattr_get(struct dentry *dentry, struct fileattr *fa); +int ntfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, + struct fileattr *fa); int ntfs_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, u32 flags); int ntfs3_setattr(struct mnt_idmap *idmap, struct dentry *dentry, @@ -564,7 +567,7 @@ int ni_write_inode(struct inode *inode, int sync, const char *hint); #define _ni_write_inode(i, w) ni_write_inode(i, w, __func__) int ni_fiemap(struct ntfs_inode *ni, struct fiemap_extent_info *fieinfo, __u64 vbo, __u64 len); -int ni_readpage_cmpr(struct ntfs_inode *ni, struct page *page); +int ni_readpage_cmpr(struct ntfs_inode *ni, struct folio *folio); int ni_decompress_file(struct ntfs_inode *ni); int ni_read_frame(struct ntfs_inode *ni, u64 frame_vbo, struct page **pages, u32 pages_per_frame); @@ -716,7 +719,7 @@ int ntfs3_write_inode(struct inode *inode, struct writeback_control *wbc); int ntfs_sync_inode(struct inode *inode); int ntfs_flush_inodes(struct super_block *sb, struct inode *i1, struct inode *i2); -int inode_write_data(struct inode *inode, const void *data, size_t bytes); +int inode_read_data(struct inode *inode, void *data, size_t bytes); int ntfs_create_inode(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const struct cpu_str *uni, umode_t mode, dev_t dev, const char *symname, u32 size, @@ -910,22 +913,6 @@ static inline bool ntfs_is_meta_file(struct ntfs_sb_info *sbi, CLST rno) rno == sbi->usn_jrnl_no; } -static inline void ntfs_unmap_page(struct page *page) -{ - kunmap(page); - put_page(page); -} - -static inline struct page *ntfs_map_page(struct address_space *mapping, - unsigned long index) -{ - struct page *page = read_mapping_page(mapping, index, NULL); - - if (!IS_ERR(page)) - kmap(page); - return page; -} - static inline size_t wnd_zone_bit(const struct wnd_bitmap *wnd) { return wnd->zone_bit; @@ -1156,6 +1143,13 @@ static inline void le64_sub_cpu(__le64 *var, u64 val) *var = cpu_to_le64(le64_to_cpu(*var) - val); } +#if IS_ENABLED(CONFIG_NTFS_FS) bool is_legacy_ntfs(struct super_block *sb); +#else +static inline bool is_legacy_ntfs(struct super_block *sb) +{ + return false; +} +#endif #endif /* _LINUX_NTFS3_NTFS_FS_H */ diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c index c5b688c5f984..a8758b85803f 100644 --- a/fs/ntfs3/super.c +++ b/fs/ntfs3/super.c @@ -275,7 +275,7 @@ static const struct fs_parameter_spec ntfs_fs_parameters[] = { fsparam_flag_no("acl", Opt_acl), fsparam_string("iocharset", Opt_iocharset), fsparam_flag_no("prealloc", Opt_prealloc), - fsparam_flag_no("nocase", Opt_nocase), + fsparam_flag_no("case", Opt_nocase), {} }; // clang-format on @@ -464,7 +464,7 @@ static int ntfs3_volinfo(struct seq_file *m, void *o) struct super_block *sb = m->private; struct ntfs_sb_info *sbi = sb->s_fs_info; - seq_printf(m, "ntfs%d.%d\n%u\n%zu\n\%zu\n%zu\n%s\n%s\n", + seq_printf(m, "ntfs%d.%d\n%u\n%zu\n%zu\n%zu\n%s\n%s\n", sbi->volume.major_ver, sbi->volume.minor_ver, sbi->cluster_size, sbi->used.bitmap.nbits, sbi->mft.bitmap.nbits, @@ -1159,7 +1159,7 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) CLST vcn, lcn, len; struct ATTRIB *attr; const struct VOLUME_INFO *info; - u32 idx, done, bytes; + u32 done, bytes; struct ATTR_DEF_ENTRY *t; u16 *shared; struct MFT_REF ref; @@ -1201,7 +1201,7 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) /* * Load $Volume. This should be done before $LogFile - * 'cause 'sbi->volume.ni' is used 'ntfs_set_state'. + * 'cause 'sbi->volume.ni' is used in 'ntfs_set_state'. */ ref.low = cpu_to_le32(MFT_REC_VOL); ref.seq = cpu_to_le16(MFT_REC_VOL); @@ -1431,31 +1431,22 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) goto put_inode_out; } - for (done = idx = 0; done < bytes; done += PAGE_SIZE, idx++) { - unsigned long tail = bytes - done; - struct page *page = ntfs_map_page(inode->i_mapping, idx); - - if (IS_ERR(page)) { - err = PTR_ERR(page); - ntfs_err(sb, "Failed to read $AttrDef (%d).", err); - goto put_inode_out; - } - memcpy(Add2Ptr(t, done), page_address(page), - min(PAGE_SIZE, tail)); - ntfs_unmap_page(page); + /* Read the entire file. */ + err = inode_read_data(inode, sbi->def_table, bytes); + if (err) { + ntfs_err(sb, "Failed to read $AttrDef (%d).", err); + goto put_inode_out; + } - if (!idx && ATTR_STD != t->type) { - ntfs_err(sb, "$AttrDef is corrupted."); - err = -EINVAL; - goto put_inode_out; - } + if (ATTR_STD != t->type) { + ntfs_err(sb, "$AttrDef is corrupted."); + err = -EINVAL; + goto put_inode_out; } t += 1; sbi->def_entries = 1; done = sizeof(struct ATTR_DEF_ENTRY); - sbi->reparse.max_size = MAXIMUM_REPARSE_DATA_BUFFER_SIZE; - sbi->ea_max_size = 0x10000; /* default formatter value */ while (done + sizeof(struct ATTR_DEF_ENTRY) <= bytes) { u32 t32 = le32_to_cpu(t->type); @@ -1491,27 +1482,22 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) goto put_inode_out; } - for (idx = 0; idx < (0x10000 * sizeof(short) >> PAGE_SHIFT); idx++) { - const __le16 *src; - u16 *dst = Add2Ptr(sbi->upcase, idx << PAGE_SHIFT); - struct page *page = ntfs_map_page(inode->i_mapping, idx); - - if (IS_ERR(page)) { - err = PTR_ERR(page); - ntfs_err(sb, "Failed to read $UpCase (%d).", err); - goto put_inode_out; - } - - src = page_address(page); + /* Read the entire file. */ + err = inode_read_data(inode, sbi->upcase, 0x10000 * sizeof(short)); + if (err) { + ntfs_err(sb, "Failed to read $UpCase (%d).", err); + goto put_inode_out; + } #ifdef __BIG_ENDIAN - for (i = 0; i < PAGE_SIZE / sizeof(u16); i++) + { + const __le16 *src = sbi->upcase; + u16 *dst = sbi->upcase; + + for (i = 0; i < 0x10000; i++) *dst++ = le16_to_cpu(*src++); -#else - memcpy(dst, src, PAGE_SIZE); -#endif - ntfs_unmap_page(page); } +#endif shared = ntfs_set_shared(sbi->upcase, 0x10000 * sizeof(short)); if (shared && sbi->upcase != shared) { @@ -1847,10 +1833,8 @@ bool is_legacy_ntfs(struct super_block *sb) #else static inline void register_as_ntfs_legacy(void) {} static inline void unregister_as_ntfs_legacy(void) {} -bool is_legacy_ntfs(struct super_block *sb) { return false; } #endif - // clang-format on static int __init init_ntfs_fs(void) @@ -1876,8 +1860,7 @@ static int __init init_ntfs_fs(void) ntfs_inode_cachep = kmem_cache_create( "ntfs_inode_cache", sizeof(struct ntfs_inode), 0, - (SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT), - init_once); + (SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT), init_once); if (!ntfs_inode_cachep) { err = -ENOMEM; goto out1; diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c index 73785dece7a7..0703e1ae32b2 100644 --- a/fs/ntfs3/xattr.c +++ b/fs/ntfs3/xattr.c @@ -195,10 +195,8 @@ static ssize_t ntfs_list_ea(struct ntfs_inode *ni, char *buffer, { const struct EA_INFO *info; struct EA_FULL *ea_all = NULL; - const struct EA_FULL *ea; u32 off, size; int err; - int ea_size; size_t ret; err = ntfs_read_ea(ni, &ea_all, 0, &info); @@ -212,16 +210,18 @@ static ssize_t ntfs_list_ea(struct ntfs_inode *ni, char *buffer, /* Enumerate all xattrs. */ ret = 0; - for (off = 0; off + sizeof(struct EA_FULL) < size; off += ea_size) { - ea = Add2Ptr(ea_all, off); - ea_size = unpacked_ea_size(ea); + off = 0; + while (off + sizeof(struct EA_FULL) < size) { + const struct EA_FULL *ea = Add2Ptr(ea_all, off); + int ea_size = unpacked_ea_size(ea); + u8 name_len = ea->name_len; - if (!ea->name_len) + if (!name_len) break; - if (ea->name_len > ea_size) { + if (name_len > ea_size) { ntfs_set_state(ni->mi.sbi, NTFS_DIRTY_ERROR); - err = -EINVAL; /* corrupted fs */ + err = -EINVAL; /* corrupted fs. */ break; } @@ -230,16 +230,17 @@ static ssize_t ntfs_list_ea(struct ntfs_inode *ni, char *buffer, if (off + ea_size > size) break; - if (ret + ea->name_len + 1 > bytes_per_buffer) { + if (ret + name_len + 1 > bytes_per_buffer) { err = -ERANGE; goto out; } - memcpy(buffer + ret, ea->name, ea->name_len); - buffer[ret + ea->name_len] = 0; + memcpy(buffer + ret, ea->name, name_len); + buffer[ret + name_len] = 0; } - ret += ea->name_len + 1; + ret += name_len + 1; + off += ea_size; } out: diff --git a/fs/binfmt_elf_test.c b/fs/tests/binfmt_elf_kunit.c index 11d734fec366..11d734fec366 100644 --- a/fs/binfmt_elf_test.c +++ b/fs/tests/binfmt_elf_kunit.c diff --git a/fs/exec_test.c b/fs/tests/exec_kunit.c index 7c77d039680b..7c77d039680b 100644 --- a/fs/exec_test.c +++ b/fs/tests/exec_kunit.c |