diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index e5d6ee61ff48..0b202e00d93f 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -603,9 +603,9 @@ int ext4_claim_free_clusters(struct ext4_sb_info *sbi, } /** - * ext4_should_retry_alloc() + * ext4_should_retry_alloc() - check if a block allocation should be retried * @sb: super block - * @retries number of attemps has been made + * @retries: number of attemps has been made * * ext4_should_retry_alloc() is called when ENOSPC is returned, and if * it is profitable to retry the operation, this function will wait diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index c7843b149a1e..86054f31fe4d 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -33,6 +33,9 @@ static int ext4_dx_readdir(struct file *, struct dir_context *); /** + * is_dx_dir() - check if a directory is using htree indexing + * @inode: directory inode + * * Check if the given dir-inode refers to an htree-indexed directory * (or a directory which could potentially get converted to use htree * indexing). @@ -109,7 +112,6 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; struct buffer_head *bh = NULL; - int dir_has_error = 0; struct fscrypt_str fstr = FSTR_INIT(NULL, 0); if (IS_ENCRYPTED(inode)) { @@ -145,8 +147,6 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) return err; } - offset = ctx->pos & (sb->s_blocksize - 1); - while (ctx->pos < inode->i_size) { struct ext4_map_blocks map; @@ -155,9 +155,18 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) goto errout; } cond_resched(); + offset = ctx->pos & (sb->s_blocksize - 1); map.m_lblk = ctx->pos >> EXT4_BLOCK_SIZE_BITS(sb); map.m_len = 1; err = ext4_map_blocks(NULL, inode, &map, 0); + if (err == 0) { + /* m_len should never be zero but let's avoid + * an infinite loop if it somehow is */ + if (map.m_len == 0) + map.m_len = 1; + ctx->pos += map.m_len * sb->s_blocksize; + continue; + } if (err > 0) { pgoff_t index = map.m_pblk >> (PAGE_SHIFT - inode->i_blkbits); @@ -176,13 +185,6 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) } if (!bh) { - if (!dir_has_error) { - EXT4_ERROR_FILE(file, 0, - "directory contains a " - "hole at offset %llu", - (unsigned long long) ctx->pos); - dir_has_error = 1; - } /* corrupt size? Maybe no more blocks to read */ if (ctx->pos > inode->i_blocks << 9) break; @@ -192,8 +194,7 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) /* Check the checksum */ if (!buffer_verified(bh) && - !ext4_dirent_csum_verify(inode, - (struct ext4_dir_entry *)bh->b_data)) { + !ext4_dirblock_csum_verify(inode, bh)) { EXT4_ERROR_FILE(file, 0, "directory fails checksum " "at offset %llu", (unsigned long long)ctx->pos); @@ -674,7 +675,7 @@ static int ext4_d_compare(const struct dentry *dentry, unsigned int len, return memcmp(str, name->name, len); } - return ext4_ci_compare(dentry->d_parent->d_inode, name, &qstr); + return ext4_ci_compare(dentry->d_parent->d_inode, name, &qstr, false); } static int ext4_d_hash(const struct dentry *dentry, struct qstr *str) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 1cb67859e051..bf660aa7a9e0 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -421,7 +421,8 @@ struct flex_groups { EXT4_PROJINHERIT_FL | EXT4_CASEFOLD_FL) /* Flags that are appropriate for regular files (all but dir-specific ones). */ -#define EXT4_REG_FLMASK (~(EXT4_DIRSYNC_FL | EXT4_TOPDIR_FL | EXT4_CASEFOLD_FL)) +#define EXT4_REG_FLMASK (~(EXT4_DIRSYNC_FL | EXT4_TOPDIR_FL | EXT4_CASEFOLD_FL |\ + EXT4_PROJINHERIT_FL)) /* Flags that are appropriate for non-directories/regular files. */ #define EXT4_OTHER_FLMASK (EXT4_NODUMP_FL | EXT4_NOATIME_FL) @@ -2077,6 +2078,9 @@ struct ext4_filename { #ifdef CONFIG_FS_ENCRYPTION struct fscrypt_str crypto_buf; #endif +#ifdef CONFIG_UNICODE + struct fscrypt_str cf_name; +#endif }; #define fname_name(p) ((p)->disk_name.name) @@ -2302,6 +2306,12 @@ extern unsigned ext4_free_clusters_after_init(struct super_block *sb, struct ext4_group_desc *gdp); ext4_fsblk_t ext4_inode_to_goal_block(struct inode *); +#ifdef CONFIG_UNICODE +extern void ext4_fname_setup_ci_filename(struct inode *dir, + const struct qstr *iname, + struct fscrypt_str *fname); +#endif + #ifdef CONFIG_FS_ENCRYPTION static inline void ext4_fname_from_fscrypt_name(struct ext4_filename *dst, const struct fscrypt_name *src) @@ -2328,6 +2338,10 @@ static inline int ext4_fname_setup_filename(struct inode *dir, return err; ext4_fname_from_fscrypt_name(fname, &name); + +#ifdef CONFIG_UNICODE + ext4_fname_setup_ci_filename(dir, iname, &fname->cf_name); +#endif return 0; } @@ -2343,6 +2357,10 @@ static inline int ext4_fname_prepare_lookup(struct inode *dir, return err; ext4_fname_from_fscrypt_name(fname, &name); + +#ifdef CONFIG_UNICODE + ext4_fname_setup_ci_filename(dir, &dentry->d_name, &fname->cf_name); +#endif return 0; } @@ -2356,6 +2374,11 @@ static inline void ext4_fname_free_filename(struct ext4_filename *fname) fname->crypto_buf.name = NULL; fname->usr_fname = NULL; fname->disk_name.name = NULL; + +#ifdef CONFIG_UNICODE + kfree(fname->cf_name.name); + fname->cf_name.name = NULL; +#endif } #else /* !CONFIG_FS_ENCRYPTION */ static inline int ext4_fname_setup_filename(struct inode *dir, @@ -2366,6 +2389,11 @@ static inline int ext4_fname_setup_filename(struct inode *dir, fname->usr_fname = iname; fname->disk_name.name = (unsigned char *) iname->name; fname->disk_name.len = iname->len; + +#ifdef CONFIG_UNICODE + ext4_fname_setup_ci_filename(dir, iname, &fname->cf_name); +#endif + return 0; } @@ -2376,7 +2404,13 @@ static inline int ext4_fname_prepare_lookup(struct inode *dir, return ext4_fname_setup_filename(dir, &dentry->d_name, 1, fname); } -static inline void ext4_fname_free_filename(struct ext4_filename *fname) { } +static inline void ext4_fname_free_filename(struct ext4_filename *fname) +{ +#ifdef CONFIG_UNICODE + kfree(fname->cf_name.name); + fname->cf_name.name = NULL; +#endif +} #endif /* !CONFIG_FS_ENCRYPTION */ /* dir.c */ @@ -2568,8 +2602,8 @@ extern int ext4_ext_migrate(struct inode *); extern int ext4_ind_migrate(struct inode *inode); /* namei.c */ -extern int ext4_dirent_csum_verify(struct inode *inode, - struct ext4_dir_entry *dirent); +extern int ext4_dirblock_csum_verify(struct inode *inode, + struct buffer_head *bh); extern int ext4_orphan_add(handle_t *, struct inode *); extern int ext4_orphan_del(handle_t *, struct inode *); extern int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash, @@ -3070,11 +3104,11 @@ extern int ext4_try_create_inline_dir(handle_t *handle, extern int ext4_read_inline_dir(struct file *filp, struct dir_context *ctx, int *has_inline_data); -extern int htree_inlinedir_to_tree(struct file *dir_file, - struct inode *dir, ext4_lblk_t block, - struct dx_hash_info *hinfo, - __u32 start_hash, __u32 start_minor_hash, - int *has_inline_data); +extern int ext4_inlinedir_to_tree(struct file *dir_file, + struct inode *dir, ext4_lblk_t block, + struct dx_hash_info *hinfo, + __u32 start_hash, __u32 start_minor_hash, + int *has_inline_data); extern struct buffer_head *ext4_find_inline_entry(struct inode *dir, struct ext4_filename *fname, struct ext4_dir_entry_2 **res_dir, @@ -3113,14 +3147,13 @@ extern struct ext4_dir_entry_2 *ext4_init_dot_dotdot(struct inode *inode, struct ext4_dir_entry_2 *de, int blocksize, int csum_size, unsigned int parent_ino, int dotdot_real_len); -extern void initialize_dirent_tail(struct ext4_dir_entry_tail *t, - unsigned int blocksize); -extern int ext4_handle_dirty_dirent_node(handle_t *handle, - struct inode *inode, - struct buffer_head *bh); +extern void ext4_initialize_dirent_tail(struct buffer_head *bh, + unsigned int blocksize); +extern int ext4_handle_dirty_dirblock(handle_t *handle, struct inode *inode, + struct buffer_head *bh); extern int ext4_ci_compare(const struct inode *parent, - const struct qstr *name, - const struct qstr *entry); + const struct qstr *fname, + const struct qstr *entry, bool quick); #define S_SHIFT 12 static const unsigned char ext4_type_by_mode[(S_IFMT >> S_SHIFT) + 1] = { diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index 75a5309f2231..ef8fcf7d0d3b 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -361,20 +361,20 @@ static inline int ext4_journal_force_commit(journal_t *journal) } static inline int ext4_jbd2_inode_add_write(handle_t *handle, - struct inode *inode) + struct inode *inode, loff_t start_byte, loff_t length) { if (ext4_handle_valid(handle)) - return jbd2_journal_inode_add_write(handle, - EXT4_I(inode)->jinode); + return jbd2_journal_inode_ranged_write(handle, + EXT4_I(inode)->jinode, start_byte, length); return 0; } static inline int ext4_jbd2_inode_add_wait(handle_t *handle, - struct inode *inode) + struct inode *inode, loff_t start_byte, loff_t length) { if (ext4_handle_valid(handle)) - return jbd2_journal_inode_add_wait(handle, - EXT4_I(inode)->jinode); + return jbd2_journal_inode_ranged_wait(handle, + EXT4_I(inode)->jinode, start_byte, length); return 0; } diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index d40ed940001e..92266a2da7d6 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -5676,8 +5676,8 @@ out_mutex: } /** - * ext4_swap_extents - Swap extents between two inodes - * + * ext4_swap_extents() - Swap extents between two inodes + * @handle: handle for this transaction * @inode1: First inode * @inode2: Second inode * @lblk1: Start block for first inode diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c index 023a3eb3afa3..7521de2dcf3a 100644 --- a/fs/ext4/extents_status.c +++ b/fs/ext4/extents_status.c @@ -1317,7 +1317,6 @@ static int es_do_reclaim_extents(struct ext4_inode_info *ei, ext4_lblk_t end, es = __es_tree_search(&tree->root, ei->i_es_shrink_lblk); if (!es) goto out_wrap; - node = &es->rb_node; while (*nr_to_scan > 0) { if (es->es_lblk > end) { ei->i_es_shrink_lblk = end + 1; diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 2c5baa5e8291..f4a24a46245e 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -165,6 +165,10 @@ static ssize_t ext4_write_checks(struct kiocb *iocb, struct iov_iter *from) ret = generic_write_checks(iocb, from); if (ret <= 0) return ret; + + if (unlikely(IS_IMMUTABLE(inode))) + return -EPERM; + /* * If we have encountered a bitmap-format file, the size limit * is smaller than s_maxbytes, which is for extent-mapped files. diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index 2024d3fa5504..36699a131168 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -294,14 +294,12 @@ static int ext4_blks_to_allocate(Indirect *branch, int k, unsigned int blks, } /** - * ext4_alloc_branch - allocate and set up a chain of blocks. - * @handle: handle for this transaction - * @inode: owner - * @indirect_blks: number of allocated indirect blocks - * @blks: number of allocated direct blocks - * @goal: preferred place for allocation - * @offsets: offsets (in the blocks) to store the pointers to next. - * @branch: place to store the chain in. + * ext4_alloc_branch() - allocate and set up a chain of blocks + * @handle: handle for this transaction + * @ar: structure describing the allocation request + * @indirect_blks: number of allocated indirect blocks + * @offsets: offsets (in the blocks) to store the pointers to next. + * @branch: place to store the chain in. * * This function allocates blocks, zeroes out all but the last one, * links them into chain and (if we are synchronous) writes them to disk. @@ -396,15 +394,11 @@ failed: } /** - * ext4_splice_branch - splice the allocated branch onto inode. + * ext4_splice_branch() - splice the allocated branch onto inode. * @handle: handle for this transaction - * @inode: owner - * @block: (logical) number of block we are adding - * @chain: chain of indirect blocks (with a missing link - see - * ext4_alloc_branch) + * @ar: structure describing the allocation request * @where: location of missing link * @num: number of indirect blocks we are adding - * @blks: number of direct blocks we are adding * * This function fills the missing link and does all housekeeping needed in * inode (->i_blocks, etc.). In case of success we end up with the full diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index f73bc3925282..88cdf3c90bd1 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -1132,7 +1132,6 @@ static int ext4_finish_convert_inline_dir(handle_t *handle, { int err, csum_size = 0, header_size = 0; struct ext4_dir_entry_2 *de; - struct ext4_dir_entry_tail *t; void *target = dir_block->b_data; /* @@ -1158,13 +1157,11 @@ static int ext4_finish_convert_inline_dir(handle_t *handle, inline_size - EXT4_INLINE_DOTDOT_SIZE + header_size, inode->i_sb->s_blocksize - csum_size); - if (csum_size) { - t = EXT4_DIRENT_TAIL(dir_block->b_data, - inode->i_sb->s_blocksize); - initialize_dirent_tail(t, inode->i_sb->s_blocksize); - } + if (csum_size) + ext4_initialize_dirent_tail(dir_block, + inode->i_sb->s_blocksize); set_buffer_uptodate(dir_block); - err = ext4_handle_dirty_dirent_node(handle, inode, dir_block); + err = ext4_handle_dirty_dirblock(handle, inode, dir_block); if (err) return err; set_buffer_verified(dir_block); @@ -1327,11 +1324,11 @@ out: * inlined dir. It returns the number directory entries loaded * into the tree. If there is an error it is returned in err. */ -int htree_inlinedir_to_tree(struct file *dir_file, - struct inode *dir, ext4_lblk_t block, - struct dx_hash_info *hinfo, - __u32 start_hash, __u32 start_minor_hash, - int *has_inline_data) +int ext4_inlinedir_to_tree(struct file *dir_file, + struct inode *dir, ext4_lblk_t block, + struct dx_hash_info *hinfo, + __u32 start_hash, __u32 start_minor_hash, + int *has_inline_data) { int err = 0, count = 0; unsigned int parent_ino; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index f65357735a1a..420fe3deed39 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -731,10 +731,16 @@ out_sem: !(flags & EXT4_GET_BLOCKS_ZERO) && !ext4_is_quota_file(inode) && ext4_should_order_data(inode)) { + loff_t start_byte = + (loff_t)map->m_lblk << inode->i_blkbits; + loff_t length = (loff_t)map->m_len << inode->i_blkbits; + if (flags & EXT4_GET_BLOCKS_IO_SUBMIT) - ret = ext4_jbd2_inode_add_wait(handle, inode); + ret = ext4_jbd2_inode_add_wait(handle, inode, + start_byte, length); else - ret = ext4_jbd2_inode_add_write(handle, inode); + ret = ext4_jbd2_inode_add_write(handle, inode, + start_byte, length); if (ret) return ret; } @@ -4094,7 +4100,8 @@ static int __ext4_block_zero_page_range(handle_t *handle, err = 0; mark_buffer_dirty(bh); if (ext4_should_order_data(inode)) - err = ext4_jbd2_inode_add_write(handle, inode); + err = ext4_jbd2_inode_add_write(handle, inode, from, + length); } unlock: @@ -4579,6 +4586,7 @@ static int __ext4_get_inode_loc(struct inode *inode, struct buffer_head *bh; struct super_block *sb = inode->i_sb; ext4_fsblk_t block; + struct blk_plug plug; int inodes_per_block, inode_offset; iloc->bh = NULL; @@ -4667,6 +4675,7 @@ make_io: * If we need to do any I/O, try to pre-readahead extra * blocks from the inode table. */ + blk_start_plug(&plug); if (EXT4_SB(sb)->s_inode_readahead_blks) { ext4_fsblk_t b, end, table; unsigned num; @@ -4697,6 +4706,7 @@ make_io: get_bh(bh); bh->b_end_io = end_buffer_read_sync; submit_bh(REQ_OP_READ, REQ_META | REQ_PRIO, bh); + blk_finish_plug(&plug); wait_on_buffer(bh); if (!buffer_uptodate(bh)) { EXT4_ERROR_INODE_BLOCK(inode, block, @@ -5529,6 +5539,14 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) return -EIO; + if (unlikely(IS_IMMUTABLE(inode))) + return -EPERM; + + if (unlikely(IS_APPEND(inode) && + (ia_valid & (ATTR_MODE | ATTR_UID | + ATTR_GID | ATTR_TIMES_SET)))) + return -EPERM; + error = setattr_prepare(dentry, attr); if (error) return error; @@ -5580,7 +5598,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) if (attr->ia_valid & ATTR_SIZE) { handle_t *handle; loff_t oldsize = inode->i_size; - int shrink = (attr->ia_size <= inode->i_size); + int shrink = (attr->ia_size < inode->i_size); if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); @@ -5594,18 +5612,33 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) if (IS_I_VERSION(inode) && attr->ia_size != inode->i_size) inode_inc_iversion(inode); - if (ext4_should_order_data(inode) && - (attr->ia_size < inode->i_size)) { - error = ext4_begin_ordered_truncate(inode, + if (shrink) { + if (ext4_should_order_data(inode)) { + error = ext4_begin_ordered_truncate(inode, attr->ia_size); - if (error) - goto err_out; + if (error) + goto err_out; + } + /* + * Blocks are going to be removed from the inode. Wait + * for dio in flight. + */ + inode_dio_wait(inode); } + + down_write(&EXT4_I(inode)->i_mmap_sem); + + rc = ext4_break_layouts(inode); + if (rc) { + up_write(&EXT4_I(inode)->i_mmap_sem); + return rc; + } + if (attr->ia_size != inode->i_size) { handle = ext4_journal_start(inode, EXT4_HT_INODE, 3); if (IS_ERR(handle)) { error = PTR_ERR(handle); - goto err_out; + goto out_mmap_sem; } if (ext4_handle_valid(handle) && shrink) { error = ext4_orphan_add(handle, inode); @@ -5633,42 +5666,31 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) i_size_write(inode, attr->ia_size); up_write(&EXT4_I(inode)->i_data_sem); ext4_journal_stop(handle); - if (error) { - if (orphan && inode->i_nlink) - ext4_orphan_del(NULL, inode); - goto err_out; + if (error) + goto out_mmap_sem; + if (!shrink) { + pagecache_isize_extended(inode, oldsize, + inode->i_size); + } else if (ext4_should_journal_data(inode)) { + ext4_wait_for_tail_page_commit(inode); } } - if (!shrink) { - pagecache_isize_extended(inode, oldsize, inode->i_size); - } else { - /* - * Blocks are going to be removed from the inode. Wait - * for dio in flight. - */ - inode_dio_wait(inode); - } - if (orphan && ext4_should_journal_data(inode)) - ext4_wait_for_tail_page_commit(inode); - down_write(&EXT4_I(inode)->i_mmap_sem); - - rc = ext4_break_layouts(inode); - if (rc) { - up_write(&EXT4_I(inode)->i_mmap_sem); - error = rc; - goto err_out; - } /* * Truncate pagecache after we've waited for commit * in data=journal mode to make pages freeable. */ truncate_pagecache(inode, inode->i_size); - if (shrink) { + /* + * Call ext4_truncate() even if i_size didn't change to + * truncate possible preallocated blocks. + */ + if (attr->ia_size <= oldsize) { rc = ext4_truncate(inode); if (rc) error = rc; } +out_mmap_sem: up_write(&EXT4_I(inode)->i_mmap_sem); } @@ -6199,6 +6221,9 @@ vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf) get_block_t *get_block; int retries = 0; + if (unlikely(IS_IMMUTABLE(inode))) + return VM_FAULT_SIGBUS; + sb_start_pagefault(inode->i_sb); file_update_time(vma->vm_file); diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index e486e49b31ed..74648d42c69b 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -269,6 +269,29 @@ static int uuid_is_zero(__u8 u[16]) } #endif +/* + * If immutable is set and we are not clearing it, we're not allowed to change + * anything else in the inode. Don't error out if we're only trying to set + * immutable on an immutable file. + */ +static int ext4_ioctl_check_immutable(struct inode *inode, __u32 new_projid, + unsigned int flags) +{ + struct ext4_inode_info *ei = EXT4_I(inode); + unsigned int oldflags = ei->i_flags; + + if (!(oldflags & EXT4_IMMUTABLE_FL) || !(flags & EXT4_IMMUTABLE_FL)) + return 0; + + if ((oldflags & ~EXT4_IMMUTABLE_FL) != (flags & ~EXT4_IMMUTABLE_FL)) + return -EPERM; + if (ext4_has_feature_project(inode->i_sb) && + __kprojid_val(ei->i_projid) != new_projid) + return -EPERM; + + return 0; +} + static int ext4_ioctl_setflags(struct inode *inode, unsigned int flags) { @@ -340,6 +363,20 @@ static int ext4_ioctl_setflags(struct inode *inode, } } + /* + * Wait for all pending directio and then flush all the dirty pages + * for this file. The flush marks all the pages readonly, so any + * subsequent attempt to write to the file (particularly mmap pages) + * will come through the filesystem and fail. + */ + if (S_ISREG(inode->i_mode) && !IS_IMMUTABLE(inode) && + (flags & EXT4_IMMUTABLE_FL)) { + inode_dio_wait(inode); + err = filemap_write_and_wait(inode->i_mapping); + if (err) + goto flags_out; + } + handle = ext4_journal_start(inode, EXT4_HT_INODE, 1); if (IS_ERR(handle)) { err = PTR_ERR(handle); @@ -742,6 +779,8 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return ext4_ioc_getfsmap(sb, (void __user *)arg); case EXT4_IOC_GETFLAGS: flags = ei->i_flags & EXT4_FL_USER_VISIBLE; + if (S_ISREG(inode->i_mode)) + flags &= ~EXT4_PROJINHERIT_FL; return put_user(flags, (int __user *) arg); case EXT4_IOC_SETFLAGS: { int err; @@ -769,7 +808,11 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return err; inode_lock(inode); - err = ext4_ioctl_setflags(inode, flags); + err = ext4_ioctl_check_immutable(inode, + from_kprojid(&init_user_ns, ei->i_projid), + flags); + if (!err) + err = ext4_ioctl_setflags(inode, flags); inode_unlock(inode); mnt_drop_write_file(filp); return err; @@ -1139,6 +1182,9 @@ resizefs_out: goto out; flags = (ei->i_flags & ~EXT4_FL_XFLAG_VISIBLE) | (flags & EXT4_FL_XFLAG_VISIBLE); + err = ext4_ioctl_check_immutable(inode, fa.fsx_projid, flags); + if (err) + goto out; err = ext4_ioctl_setflags(inode, flags); if (err) goto out; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 99ba720dbb7a..a3e2767bdf2f 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -4696,8 +4696,9 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b, * ext4_free_blocks() -- Free given blocks and update quota * @handle: handle for this transaction * @inode: inode - * @block: start physical block to free - * @count: number of blocks to count + * @bh: optional buffer of the block to be freed + * @block: starting physical block to be freed + * @count: number of blocks to be freed * @flags: flags used by ext4_free_blocks */ void ext4_free_blocks(handle_t *handle, struct inode *inode, diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 1083a9f3f16a..30ce3dc69378 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -13,11 +13,10 @@ #include "ext4_extents.h" /** - * get_ext_path - Find an extent path for designated logical block number. - * - * @inode: an inode which is searched + * get_ext_path() - Find an extent path for designated logical block number. + * @inode: inode to be searched * @lblock: logical block number to find an extent path - * @path: pointer to an extent path pointer (for output) + * @ppath: pointer to an extent path pointer (for output) * * ext4_find_extent wrapper. Return 0 on success, or a negative error value * on failure. @@ -42,8 +41,9 @@ get_ext_path(struct inode *inode, ext4_lblk_t lblock, } /** - * ext4_double_down_write_data_sem - Acquire two inodes' write lock - * of i_data_sem + * ext4_double_down_write_data_sem() - write lock two inodes's i_data_sem + * @first: inode to be locked + * @second: inode to be locked * * Acquire write lock of i_data_sem of the two inodes */ @@ -390,7 +390,8 @@ data_copy: /* Even in case of data=writeback it is reasonable to pin * inode to transaction, to prevent unexpected data loss */ - *err = ext4_jbd2_inode_add_write(handle, orig_inode); + *err = ext4_jbd2_inode_add_write(handle, orig_inode, + (loff_t)orig_page_offset << PAGE_SHIFT, replaced_size); unlock_pages: unlock_page(pagep[0]); diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index cd01c4a67ffb..129029534075 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -82,8 +82,18 @@ static struct buffer_head *ext4_append(handle_t *handle, static int ext4_dx_csum_verify(struct inode *inode, struct ext4_dir_entry *dirent); +/* + * Hints to ext4_read_dirblock regarding whether we expect a directory + * block being read to be an index block, or a block containing + * directory entries (and if the latter, whether it was found via a + * logical block in an htree index block). This is used to control + * what sort of sanity checkinig ext4_read_dirblock() will do on the + * directory block read from the storage device. EITHER will means + * the caller doesn't know what kind of directory block will be read, + * so no specific verification will be done. + */ typedef enum { - EITHER, INDEX, DIRENT + EITHER, INDEX, DIRENT, DIRENT_HTREE } dirblock_type_t; #define ext4_read_dirblock(inode, block, type) \ @@ -109,11 +119,14 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode, return bh; } - if (!bh) { + if (!bh && (type == INDEX || type == DIRENT_HTREE)) { ext4_error_inode(inode, func, line, block, - "Directory hole found"); + "Directory hole found for htree %s block", + (type == INDEX) ? "index" : "leaf"); return ERR_PTR(-EFSCORRUPTED); } + if (!bh) + return NULL; dirent = (struct ext4_dir_entry *) bh->b_data; /* Determine whether or not we have an index block */ if (is_dx(inode)) { @@ -150,7 +163,7 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode, } } if (!is_dx_block) { - if (ext4_dirent_csum_verify(inode, dirent)) + if (ext4_dirblock_csum_verify(inode, bh)) set_buffer_verified(bh); else { ext4_error_inode(inode, func, line, block, @@ -280,9 +293,11 @@ static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname, struct inode *dir, struct inode *inode); /* checksumming functions */ -void initialize_dirent_tail(struct ext4_dir_entry_tail *t, - unsigned int blocksize) +void ext4_initialize_dirent_tail(struct buffer_head *bh, + unsigned int blocksize) { + struct ext4_dir_entry_tail *t = EXT4_DIRENT_TAIL(bh->b_data, blocksize); + memset(t, 0, sizeof(struct ext4_dir_entry_tail)); t->det_rec_len = ext4_rec_len_to_disk( sizeof(struct ext4_dir_entry_tail), blocksize); @@ -291,17 +306,17 @@ void initialize_dirent_tail(struct ext4_dir_entry_tail *t, /* Walk through a dirent block to find a checksum "dirent" at the tail */ static struct ext4_dir_entry_tail *get_dirent_tail(struct inode *inode, - struct ext4_dir_entry *de) + struct buffer_head *bh) { struct ext4_dir_entry_tail *t; #ifdef PARANOID struct ext4_dir_entry *d, *top; - d = de; - top = (struct ext4_dir_entry *)(((void *)de) + + d = (struct ext4_dir_entry *)bh->b_data; + top = (struct ext4_dir_entry *)(bh->b_data + (EXT4_BLOCK_SIZE(inode->i_sb) - - sizeof(struct ext4_dir_entry_tail))); + sizeof(struct ext4_dir_entry_tail))); while (d < top && d->rec_len) d = (struct ext4_dir_entry *)(((void *)d) + le16_to_cpu(d->rec_len)); @@ -311,7 +326,7 @@ static struct ext4_dir_entry_tail *get_dirent_tail(struct inode *inode, t = (struct ext4_dir_entry_tail *)d; #else - t = EXT4_DIRENT_TAIL(de, EXT4_BLOCK_SIZE(inode->i_sb)); + t = EXT4_DIRENT_TAIL(bh->b_data, EXT4_BLOCK_SIZE(inode->i_sb)); #endif if (t->det_reserved_zero1 || @@ -323,8 +338,7 @@ static struct ext4_dir_entry_tail *get_dirent_tail(struct inode *inode, return t; } -static __le32 ext4_dirent_csum(struct inode *inode, - struct ext4_dir_entry *dirent, int size) +static __le32 ext4_dirblock_csum(struct inode *inode, void *dirent, int size) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_inode_info *ei = EXT4_I(inode); @@ -344,49 +358,49 @@ static void __warn_no_space_for_csum(struct inode *inode, const char *func, "No space for directory leaf checksum. Please run e2fsck -D."); } -int ext4_dirent_csum_verify(struct inode *inode, struct ext4_dir_entry *dirent) +int ext4_dirblock_csum_verify(struct inode *inode, struct buffer_head *bh) { struct ext4_dir_entry_tail *t; if (!ext4_has_metadata_csum(inode->i_sb)) return 1; - t = get_dirent_tail(inode, dirent); + t = get_dirent_tail(inode, bh); if (!t) { warn_no_space_for_csum(inode); return 0; } - if (t->det_checksum != ext4_dirent_csum(inode, dirent, - (void *)t - (void *)dirent)) + if (t->det_checksum != ext4_dirblock_csum(inode, bh->b_data, + (char *)t - bh->b_data)) return 0; return 1; } -static void ext4_dirent_csum_set(struct inode *inode, - struct ext4_dir_entry *dirent) +static void ext4_dirblock_csum_set(struct inode *inode, + struct buffer_head *bh) { struct ext4_dir_entry_tail *t; if (!ext4_has_metadata_csum(inode->i_sb)) return; - t = get_dirent_tail(inode, dirent); + t = get_dirent_tail(inode, bh); if (!t) { warn_no_space_for_csum(inode); return; } - t->det_checksum = ext4_dirent_csum(inode, dirent, - (void *)t - (void *)dirent); + t->det_checksum = ext4_dirblock_csum(inode, bh->b_data, + (char *)t - bh->b_data); } -int ext4_handle_dirty_dirent_node(handle_t *handle, - struct inode *inode, - struct buffer_head *bh) +int ext4_handle_dirty_dirblock(handle_t *handle, + struct inode *inode, + struct buffer_head *bh) { - ext4_dirent_csum_set(inode, (struct ext4_dir_entry *)bh->b_data); + ext4_dirblock_csum_set(inode, bh); return ext4_handle_dirty_metadata(handle, inode, bh); } @@ -980,7 +994,7 @@ static int htree_dirblock_to_tree(struct file *dir_file, dxtrace(printk(KERN_INFO "In htree dirblock_to_tree: block %lu\n", (unsigned long)block)); - bh = ext4_read_dirblock(dir, block, DIRENT); + bh = ext4_read_dirblock(dir, block, DIRENT_HTREE); if (IS_ERR(bh)) return PTR_ERR(bh); @@ -1090,10 +1104,10 @@ int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash, hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed; if (ext4_has_inline_data(dir)) { int has_inline_data = 1; - count = htree_inlinedir_to_tree(dir_file, dir, 0, - &hinfo, start_hash, - start_minor_hash, - &has_inline_data); + count = ext4_inlinedir_to_tree(dir_file, dir, 0, + &hinfo, start_hash, + start_minor_hash, + &has_inline_data); if (has_inline_data) { *next_hash = ~0; return count; @@ -1259,19 +1273,24 @@ static void dx_insert_block(struct dx_frame *frame, u32 hash, ext4_lblk_t block) #ifdef CONFIG_UNICODE /* * Test whether a case-insensitive directory entry matches the filename - * being searched for. + * being searched for. If quick is set, assume the name being looked up + * is already in the casefolded form. * * Returns: 0 if the directory entry matches, more than 0 if it * doesn't match or less than zero on error. */ int ext4_ci_compare(const struct inode *parent, const struct qstr *name, - const struct qstr *entry) + const struct qstr *entry, bool quick) { const struct ext4_sb_info *sbi = EXT4_SB(parent->i_sb); const struct unicode_map *um = sbi->s_encoding; int ret; - ret = utf8_strncasecmp(um, name, entry); + if (quick) + ret = utf8_strncasecmp_folded(um, name, entry); + else + ret = utf8_strncasecmp(um, name, entry); + if (ret < 0) { /* Handle invalid character sequence as either an error * or as an opaque byte sequence. @@ -1287,6 +1306,32 @@ int ext4_ci_compare(const struct inode *parent, const struct qstr *name, return ret; } + +void ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname, + struct fscrypt_str *cf_name) +{ + int len; + + if (!IS_CASEFOLDED(dir)) { + cf_name->name = NULL; + return; + } + + cf_name->name = kmalloc(EXT4_NAME_LEN, GFP_NOFS); + if (!cf_name->name) + return; + + len = utf8_casefold(EXT4_SB(dir->i_sb)->s_encoding, + iname, cf_name->name, + EXT4_NAME_LEN); + if (len <= 0) { + kfree(cf_name->name); + cf_name->name = NULL; + return; + } + cf_name->len = (unsigned) len; + +} #endif /* @@ -1313,8 +1358,15 @@ static inline bool ext4_match(const struct inode *parent, #endif #ifdef CONFIG_UNICODE - if (EXT4_SB(parent->i_sb)->s_encoding && IS_CASEFOLDED(parent)) - return (ext4_ci_compare(parent, fname->usr_fname, &entry) == 0); + if (EXT4_SB(parent->i_sb)->s_encoding && IS_CASEFOLDED(parent)) { + if (fname->cf_name.name) { + struct qstr cf = {.name = fname->cf_name.name, + .len = fname->cf_name.len}; + return !ext4_ci_compare(parent, &cf, &entry, true); + } + return !ext4_ci_compare(parent, fname->usr_fname, &entry, + false); + } #endif return fscrypt_match_name(&f, de->name, de->name_len); @@ -1484,8 +1536,7 @@ restart: if (!buffer_verified(bh) && !is_dx_internal_node(dir, block, (struct ext4_dir_entry *)bh->b_data) && - !ext4_dirent_csum_verify(dir, - (struct ext4_dir_entry *)bh->b_data)) { + !ext4_dirblock_csum_verify(dir, bh)) { EXT4_ERROR_INODE(dir, "checksumming directory " "block %lu", (unsigned long)block); brelse(bh); @@ -1586,7 +1637,7 @@ static struct buffer_head * ext4_dx_find_entry(struct inode *dir, return (struct buffer_head *) frame; do { block = dx_get_block(frame->at); - bh = ext4_read_dirblock(dir, block, DIRENT); + bh = ext4_read_dirblock(dir, block, DIRENT_HTREE); if (IS_ERR(bh)) goto errout; @@ -1769,7 +1820,6 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, char *data1 = (*bh)->b_data, *data2; unsigned split, move, size; struct ext4_dir_entry_2 *de = NULL, *de2; - struct ext4_dir_entry_tail *t; int csum_size = 0; int err = 0, i; @@ -1830,11 +1880,8 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, (char *) de2, blocksize); if (csum_size) { - t = EXT4_DIRENT_TAIL(data2, blocksize); - initialize_dirent_tail(t, blocksize); - - t = EXT4_DIRENT_TAIL(data1, blocksize); - initialize_dirent_tail(t, blocksize); + ext4_initialize_dirent_tail(*bh, blocksize); + ext4_initialize_dirent_tail(bh2, blocksize); } dxtrace(dx_show_leaf(dir, hinfo, (struct ext4_dir_entry_2 *) data1, @@ -1848,7 +1895,7 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, de = de2; } dx_insert_block(frame, hash2 + continued, newblock); - err = ext4_handle_dirty_dirent_node(handle, dir, bh2); + err = ext4_handle_dirty_dirblock(handle, dir, bh2); if (err) goto journal_error; err = ext4_handle_dirty_dx_node(handle, dir, frame->bh); @@ -1976,7 +2023,7 @@ static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname, inode_inc_iversion(dir); ext4_mark_inode_dirty(handle, dir); BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); - err = ext4_handle_dirty_dirent_node(handle, dir, bh); + err = ext4_handle_dirty_dirblock(handle, dir, bh); if (err) ext4_std_error(dir->i_sb, err); return 0; @@ -1995,8 +2042,7 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, struct dx_frame frames[EXT4_HTREE_LEVEL], *frame; struct dx_entry *entries; struct ext4_dir_entry_2 *de, *de2; - struct ext4_dir_entry_tail *t; - char *data1, *top; + char *data2, *top; unsigned len; int retval; unsigned blocksize; @@ -2036,21 +2082,18 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, return PTR_ERR(bh2); } ext4_set_inode_flag(dir, EXT4_INODE_INDEX); - data1 = bh2->b_data; + data2 = bh2->b_data; - memcpy (data1, de, len); - de = (struct ext4_dir_entry_2 *) data1; - top = data1 + len; + memcpy(data2, de, len); + de = (struct ext4_dir_entry_2 *) data2; + top = data2 + len; while ((char *)(de2 = ext4_next_entry(de, blocksize)) < top) de = de2; - de->rec_len = ext4_rec_len_to_disk(data1 + (blocksize - csum_size) - - (char *) de, - blocksize); + de->rec_len = ext4_rec_len_to_disk(data2 + (blocksize - csum_size) - + (char *) de, blocksize); - if (csum_size) { - t = EXT4_DIRENT_TAIL(data1, blocksize); - initialize_dirent_tail(t, blocksize); - } + if (csum_size) + ext4_initialize_dirent_tail(bh2, blocksize); /* Initialize the root; the dot dirents already exist */ de = (struct ext4_dir_entry_2 *) (&root->dotdot); @@ -2080,7 +2123,7 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, retval = ext4_handle_dirty_dx_node(handle, dir, frame->bh); if (retval) goto out_frames; - retval = ext4_handle_dirty_dirent_node(handle, dir, bh2); + retval = ext4_handle_dirty_dirblock(handle, dir, bh2); if (retval) goto out_frames; @@ -2120,7 +2163,6 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, struct inode *dir = d_inode(dentry->d_parent); struct buffer_head *bh = NULL; struct ext4_dir_entry_2 *de; - struct ext4_dir_entry_tail *t; struct super_block *sb; struct ext4_sb_info *sbi; struct ext4_filename fname; @@ -2170,6 +2212,11 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, blocks = dir->i_size >> sb->s_blocksize_bits; for (block = 0; block < blocks; block++) { bh = ext4_read_dirblock(dir, block, DIRENT); + if (bh == NULL) { + bh = ext4_bread(handle, dir, block, + EXT4_GET_BLOCKS_CREATE); + goto add_to_new_block; + } if (IS_ERR(bh)) { retval = PTR_ERR(bh); bh = NULL; @@ -2190,6 +2237,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, brelse(bh); } bh = ext4_append(handle, dir, &block); +add_to_new_block: if (IS_ERR(bh)) { retval = PTR_ERR(bh); bh = NULL; @@ -2199,10 +2247,8 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, de->inode = 0; de->rec_len = ext4_rec_len_to_disk(blocksize - csum_size, blocksize); - if (csum_size) { - t = EXT4_DIRENT_TAIL(bh->b_data, blocksize); - initialize_dirent_tail(t, blocksize); - } + if (csum_size) + ext4_initialize_dirent_tail(bh, blocksize); retval = add_dirent_to_buf(handle, &fname, dir, inode, de, bh); out: @@ -2234,7 +2280,7 @@ again: return PTR_ERR(frame); entries = frame->entries; at = frame->at; - bh = ext4_read_dirblock(dir, dx_get_block(frame->at), DIRENT); + bh = ext4_read_dirblock(dir, dx_get_block(frame->at), DIRENT_HTREE); if (IS_ERR(bh)) { err = PTR_ERR(bh); bh = NULL; @@ -2460,7 +2506,7 @@ static int ext4_delete_entry(handle_t *handle, goto out; BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); - err = ext4_handle_dirty_dirent_node(handle, dir, bh); + err = ext4_handle_dirty_dirblock(handle, dir, bh); if (unlikely(err)) goto out; @@ -2662,7 +2708,6 @@ static int ext4_init_new_dir(handle_t *handle, struct inode *dir, { struct buffer_head *dir_block = NULL; struct ext4_dir_entry_2 *de; - struct ext4_dir_entry_tail *t; ext4_lblk_t block = 0; unsigned int blocksize = dir->i_sb->s_blocksize; int csum_size = 0; @@ -2686,13 +2731,11 @@ static int ext4_init_new_dir(handle_t *handle, struct inode *dir, de = (struct ext4_dir_entry_2 *)dir_block->b_data; ext4_init_dot_dotdot(inode, de, blocksize, csum_size, dir->i_ino, 0); set_nlink(inode, 2); - if (csum_size) { - t = EXT4_DIRENT_TAIL(dir_block->b_data, blocksize); - initialize_dirent_tail(t, blocksize); - } + if (csum_size) + ext4_initialize_dirent_tail(dir_block, blocksize); BUFFER_TRACE(dir_block, "call ext4_handle_dirty_metadata"); - err = ext4_handle_dirty_dirent_node(handle, inode, dir_block); + err = ext4_handle_dirty_dirblock(handle, inode, dir_block); if (err) goto out; set_buffer_verified(dir_block); @@ -2782,7 +2825,10 @@ bool ext4_empty_dir(struct inode *inode) EXT4_ERROR_INODE(inode, "invalid size"); return true; } - bh = ext4_read_dirblock(inode, 0, EITHER); + /* The first directory block must not be a hole, + * so treat it as DIRENT_HTREE + */ + bh = ext4_read_dirblock(inode, 0, DIRENT_HTREE); if (IS_ERR(bh)) return true; @@ -2804,6 +2850,10 @@ bool ext4_empty_dir(struct inode *inode) brelse(bh); lblock = offset >> EXT4_BLOCK_SIZE_BITS(sb); bh = ext4_read_dirblock(inode, lblock, EITHER); + if (bh == NULL) { + offset += sb->s_blocksize; + continue; + } if (IS_ERR(bh)) return true; de = (struct ext4_dir_entry_2 *) bh->b_data; @@ -3369,7 +3419,10 @@ static struct buffer_head *ext4_get_first_dir_block(handle_t *handle, struct buffer_head *bh; if (!ext4_has_inline_data(inode)) { - bh = ext4_read_dirblock(inode, 0, EITHER); + /* The first directory block must not be a hole, so + * treat it as DIRENT_HTREE + */ + bh = ext4_read_dirblock(inode, 0, DIRENT_HTREE); if (IS_ERR(bh)) { *retval = PTR_ERR(bh); return NULL; @@ -3430,9 +3483,8 @@ static int ext4_rename_dir_finish(handle_t *handle, struct ext4_renament *ent, ent->inode, ent->dir_bh); } else { - retval = ext4_handle_dirty_dirent_node(handle, - ent->inode, - ent->dir_bh); + retval = ext4_handle_dirty_dirblock(handle, ent->inode, + ent->dir_bh); } } else { retval = ext4_mark_inode_dirty(handle, ent->inode); @@ -3462,8 +3514,7 @@ static int ext4_setent(handle_t *handle, struct ext4_renament *ent, ext4_mark_inode_dirty(handle, ent->dir); BUFFER_TRACE(ent->bh, "call ext4_handle_dirty_metadata"); if (!ent->inlined) { - retval = ext4_handle_dirty_dirent_node(handle, - ent->dir, ent->bh); + retval = ext4_handle_dirty_dirblock(handle, ent->dir, ent->bh); if (unlikely(retval)) { ext4_std_error(ent->dir->i_sb, retval); return retval; diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index 04b4f53f0659..b3cd7655a6ff 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -230,6 +230,7 @@ static struct attribute *ext4_attrs[] = { ATTR_LIST(journal_task), NULL, }; +ATTRIBUTE_GROUPS(ext4); /* Features this copy of ext4 supports */ EXT4_ATTR_FEATURE(lazy_itable_init); @@ -256,6 +257,7 @@ static struct attribute *ext4_feat_attrs[] = { ATTR_LIST(metadata_csum_seed), NULL, }; +ATTRIBUTE_GROUPS(ext4_feat); static void *calc_ptr(struct ext4_attr *a, struct ext4_sb_info *sbi) { @@ -374,13 +376,13 @@ static const struct sysfs_ops ext4_attr_ops = { }; static struct kobj_type ext4_sb_ktype = { - .default_attrs = ext4_attrs, + .default_groups = ext4_groups, .sysfs_ops = &ext4_attr_ops, .release = ext4_sb_release, }; static struct kobj_type ext4_feat_ktype = { - .default_attrs = ext4_feat_attrs, + .default_groups = ext4_feat_groups, .sysfs_ops = &ext4_attr_ops, .release = (void (*)(struct kobject *))kfree, }; diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index efd0ce9489ae..132fb92098c7 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -184,17 +184,18 @@ static int journal_wait_on_commit_record(journal_t *journal, /* * write the filemap data using writepage() address_space_operations. * We don't do block allocation here even for delalloc. We don't - * use writepages() because with dealyed allocation we may be doing + * use writepages() because with delayed allocation we may be doing * block allocation in writepages(). */ -static int journal_submit_inode_data_buffers(struct address_space *mapping) +static int journal_submit_inode_data_buffers(struct address_space *mapping, + loff_t dirty_start, loff_t dirty_end) { int ret; struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL, .nr_to_write = mapping->nrpages * 2, - .range_start = 0, - .range_end = i_size_read(mapping->host), + .range_start = dirty_start, + .range_end = dirty_end, }; ret = generic_writepages(mapping, &wbc); @@ -218,6 +219,9 @@ static int journal_submit_data_buffers(journal_t *journal, spin_lock(&journal->j_list_lock); list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) { + loff_t dirty_start = jinode->i_dirty_start; + loff_t dirty_end = jinode->i_dirty_end; + if (!(jinode->i_flags & JI_WRITE_DATA)) continue; mapping = jinode->i_vfs_inode->i_mapping; @@ -230,7 +234,8 @@ static int journal_submit_data_buffers(journal_t *journal, * only allocated blocks here. */ trace_jbd2_submit_inode_data(jinode->i_vfs_inode); - err = journal_submit_inode_data_buffers(mapping); + err = journal_submit_inode_data_buffers(mapping, dirty_start, + dirty_end); if (!ret) ret = err; spin_lock(&journal->j_list_lock); @@ -257,12 +262,16 @@ static int journal_finish_inode_data_buffers(journal_t *journal, /* For locking, see the comment in journal_submit_data_buffers() */ spin_lock(&journal->j_list_lock); list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) { + loff_t dirty_start = jinode->i_dirty_start; + loff_t dirty_end = jinode->i_dirty_end; + if (!(jinode->i_flags & JI_WAIT_DATA)) continue; jinode->i_flags |= JI_COMMIT_RUNNING; spin_unlock(&journal->j_list_lock); - err = filemap_fdatawait_keep_errors( - jinode->i_vfs_inode->i_mapping); + err = filemap_fdatawait_range_keep_errors( + jinode->i_vfs_inode->i_mapping, dirty_start, + dirty_end); if (!ret) ret = err; spin_lock(&journal->j_list_lock); @@ -282,6 +291,8 @@ static int journal_finish_inode_data_buffers(journal_t *journal, &jinode->i_transaction->t_inode_list); } else { jinode->i_transaction = NULL; + jinode->i_dirty_start = 0; + jinode->i_dirty_end = 0; } } spin_unlock(&journal->j_list_lock); diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 43df0c943229..953990eb70a9 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -66,9 +66,6 @@ EXPORT_SYMBOL(jbd2_journal_get_undo_access); EXPORT_SYMBOL(jbd2_journal_set_triggers); EXPORT_SYMBOL(jbd2_journal_dirty_metadata); EXPORT_SYMBOL(jbd2_journal_forget); -#if 0 -EXPORT_SYMBOL(journal_sync_buffer); -#endif EXPORT_SYMBOL(jbd2_journal_flush); EXPORT_SYMBOL(jbd2_journal_revoke); @@ -94,6 +91,8 @@ EXPORT_SYMBOL(jbd2_journal_try_to_free_buffers); EXPORT_SYMBOL(jbd2_journal_force_commit); EXPORT_SYMBOL(jbd2_journal_inode_add_write); EXPORT_SYMBOL(jbd2_journal_inode_add_wait); +EXPORT_SYMBOL(jbd2_journal_inode_ranged_write); +EXPORT_SYMBOL(jbd2_journal_inode_ranged_wait); EXPORT_SYMBOL(jbd2_journal_init_jbd_inode); EXPORT_SYMBOL(jbd2_journal_release_jbd_inode); EXPORT_SYMBOL(jbd2_journal_begin_ordered_truncate); @@ -203,7 +202,7 @@ loop: if (journal->j_flags & JBD2_UNMOUNT) goto end_loop; - jbd_debug(1, "commit_sequence=%d, commit_request=%d\n", + jbd_debug(1, "commit_sequence=%u, commit_request=%u\n", journal->j_commit_sequence, journal->j_commit_request); if (journal->j_commit_sequence != journal->j_commit_request) { @@ -324,7 +323,7 @@ static void journal_kill_thread(journal_t *journal) * IO is in progress. do_get_write_access() handles this. * * The function returns a pointer to the buffer_head to be used for IO. - * + * * * Return value: * <0: Error @@ -500,7 +499,7 @@ int __jbd2_log_start_commit(journal_t *journal, tid_t target) */ journal->j_commit_request = target; - jbd_debug(1, "JBD2: requesting commit %d/%d\n", + jbd_debug(1, "JBD2: requesting commit %u/%u\n", journal->j_commit_request, journal->j_commit_sequence); journal->j_running_transaction->t_requested = jiffies; @@ -513,7 +512,7 @@ int __jbd2_log_start_commit(journal_t *journal, tid_t target) WARN_ONCE(1, "JBD2: bad log_start_commit: %u %u %u %u\n", journal->j_commit_request, journal->j_commit_sequence, - target, journal->j_running_transaction ? + target, journal->j_running_transaction ? journal->j_running_transaction->t_tid : 0); return 0; } @@ -698,12 +697,12 @@ int jbd2_log_wait_commit(journal_t *journal, tid_t tid) #ifdef CONFIG_JBD2_DEBUG if (!tid_geq(journal->j_commit_request, tid)) { printk(KERN_ERR - "%s: error: j_commit_request=%d, tid=%d\n", + "%s: error: j_commit_request=%u, tid=%u\n", __func__, journal->j_commit_request, tid); } #endif while (tid_gt(tid, journal->j_commit_sequence)) { - jbd_debug(1, "JBD2: want %d, j_commit_sequence=%d\n", + jbd_debug(1, "JBD2: want %u, j_commit_sequence=%u\n", tid, journal->j_commit_sequence); read_unlock(&journal->j_state_lock); wake_up(&journal->j_wait_commit); @@ -944,7 +943,7 @@ int __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block) trace_jbd2_update_log_tail(journal, tid, block, freed); jbd_debug(1, - "Cleaning journal tail from %d to %d (offset %lu), " + "Cleaning journal tail from %u to %u (offset %lu), " "freeing %lu\n", journal->j_tail_sequence, tid, block, freed); @@ -1318,7 +1317,7 @@ static int journal_reset(journal_t *journal) */ if (sb->s_start == 0) { jbd_debug(1, "JBD2: Skipping superblock update on recovered sb " - "(start %ld, seq %d, errno %d)\n", + "(start %ld, seq %u, errno %d)\n", journal->j_tail, journal->j_tail_sequence, journal->j_errno); journal->j_flags |= JBD2_FLUSHED; @@ -1453,7 +1452,7 @@ static void jbd2_mark_journal_empty(journal_t *journal, int write_op) return; } - jbd_debug(1, "JBD2: Marking journal as empty (seq %d)\n", + jbd_debug(1, "JBD2: Marking journal as empty (seq %u)\n", journal->j_tail_sequence); sb->s_sequence = cpu_to_be32(journal->j_tail_sequence); @@ -2574,6 +2573,8 @@ void jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode) jinode->i_next_transaction = NULL; jinode->i_vfs_inode = inode; jinode->i_flags = 0; + jinode->i_dirty_start = 0; + jinode->i_dirty_end = 0; INIT_LIST_HEAD(&jinode->i_list); } diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 8ca4fddc705f..990e7b5062e7 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -2565,7 +2565,7 @@ void jbd2_journal_refile_buffer(journal_t *journal, struct journal_head *jh) * File inode in the inode list of the handle's transaction */ static int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *jinode, - unsigned long flags) + unsigned long flags, loff_t start_byte, loff_t end_byte) { transaction_t *transaction = handle->h_transaction; journal_t *journal; @@ -2577,26 +2577,17 @@ static int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *jinode, jbd_debug(4, "Adding inode %lu, tid:%d\n", jinode->i_vfs_inode->i_ino, transaction->t_tid); - /* - * First check whether inode isn't already on the transaction's - * lists without taking the lock. Note that this check is safe - * without the lock as we cannot race with somebody removing inode - * from the transaction. The reason is that we remove inode from the - * transaction only in journal_release_jbd_inode() and when we commit - * the transaction. We are guarded from the first case by holding - * a reference to the inode. We are safe against the second case - * because if jinode->i_transaction == transaction, commit code - * cannot touch the transaction because we hold reference to it, - * and if jinode->i_next_transaction == transaction, commit code - * will only file the inode where we want it. - */ - if ((jinode->i_transaction == transaction || - jinode->i_next_transaction == transaction) && - (jinode->i_flags & flags) == flags) - return 0; - spin_lock(&journal->j_list_lock); jinode->i_flags |= flags; + + if (jinode->i_dirty_end) { + jinode->i_dirty_start = min(jinode->i_dirty_start, start_byte); + jinode->i_dirty_end = max(jinode->i_dirty_end, end_byte); + } else { + jinode->i_dirty_start = start_byte; + jinode->i_dirty_end = end_byte; + } + /* Is inode already attached where we need it? */ if (jinode->i_transaction == transaction || jinode->i_next_transaction == transaction) @@ -2631,12 +2622,28 @@ done: int jbd2_journal_inode_add_write(handle_t *handle, struct jbd2_inode *jinode) { return jbd2_journal_file_inode(handle, jinode, - JI_WRITE_DATA | JI_WAIT_DATA); + JI_WRITE_DATA | JI_WAIT_DATA, 0, LLONG_MAX); } int jbd2_journal_inode_add_wait(handle_t *handle, struct jbd2_inode *jinode) { - return jbd2_journal_file_inode(handle, jinode, JI_WAIT_DATA); + return jbd2_journal_file_inode(handle, jinode, JI_WAIT_DATA, 0, + LLONG_MAX); +} + +int jbd2_journal_inode_ranged_write(handle_t *handle, + struct jbd2_inode *jinode, loff_t start_byte, loff_t length) +{ + return jbd2_journal_file_inode(handle, jinode, + JI_WRITE_DATA | JI_WAIT_DATA, start_byte, + start_byte + length - 1); +} + +int jbd2_journal_inode_ranged_wait(handle_t *handle, struct jbd2_inode *jinode, + loff_t start_byte, loff_t length) +{ + return jbd2_journal_file_inode(handle, jinode, JI_WAIT_DATA, + start_byte, start_byte + length - 1); } /* diff --git a/fs/unicode/utf8-core.c b/fs/unicode/utf8-core.c index 6afab4fdce90..71ca4d047d65 100644 --- a/fs/unicode/utf8-core.c +++ b/fs/unicode/utf8-core.c @@ -73,6 +73,34 @@ int utf8_strncasecmp(const struct unicode_map *um, } EXPORT_SYMBOL(utf8_strncasecmp); +/* String cf is expected to be a valid UTF-8 casefolded + * string. + */ +int utf8_strncasecmp_folded(const struct unicode_map *um, + const struct qstr *cf, + const struct qstr *s1) +{ + const struct utf8data *data = utf8nfdicf(um->version); + struct utf8cursor cur1; + int c1, c2; + int i = 0; + + if (utf8ncursor(&cur1, data, s1->name, s1->len) < 0) + return -EINVAL; + + do { + c1 = utf8byte(&cur1); + c2 = cf->name[i++]; + if (c1 < 0) + return -EINVAL; + if (c1 != c2) + return 1; + } while (c1); + + return 0; +} +EXPORT_SYMBOL(utf8_strncasecmp_folded); + int utf8_casefold(const struct unicode_map *um, const struct qstr *str, unsigned char *dest, size_t dlen) { diff --git a/include/linux/fs.h b/include/linux/fs.h index 850d056439ef..291c50500ca2 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2718,6 +2718,8 @@ extern int filemap_flush(struct address_space *); extern int filemap_fdatawait_keep_errors(struct address_space *mapping); extern int filemap_fdatawait_range(struct address_space *, loff_t lstart, loff_t lend); +extern int filemap_fdatawait_range_keep_errors(struct address_space *mapping, + loff_t start_byte, loff_t end_byte); static inline int filemap_fdatawait(struct address_space *mapping) { diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 5c04181b7c6d..df03825ad1a1 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -451,6 +451,22 @@ struct jbd2_inode { * @i_flags: Flags of inode [j_list_lock] */ unsigned long i_flags; + + /** + * @i_dirty_start: + * + * Offset in bytes where the dirty range for this inode starts. + * [j_list_lock] + */ + loff_t i_dirty_start; + + /** + * @i_dirty_end: + * + * Inclusive offset in bytes where the dirty range for this inode + * ends. [j_list_lock] + */ + loff_t i_dirty_end; }; struct jbd2_revoke_table_s; @@ -1357,7 +1373,6 @@ void jbd2_journal_set_triggers(struct buffer_head *, struct jbd2_buffer_trigger_type *type); extern int jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *); extern int jbd2_journal_forget (handle_t *, struct buffer_head *); -extern void journal_sync_buffer (struct buffer_head *); extern int jbd2_journal_invalidatepage(journal_t *, struct page *, unsigned int, unsigned int); extern int jbd2_journal_try_to_free_buffers(journal_t *, struct page *, gfp_t); @@ -1397,6 +1412,12 @@ extern int jbd2_journal_force_commit(journal_t *); extern int jbd2_journal_force_commit_nested(journal_t *); extern int jbd2_journal_inode_add_write(handle_t *handle, struct jbd2_inode *inode); extern int jbd2_journal_inode_add_wait(handle_t *handle, struct jbd2_inode *inode); +extern int jbd2_journal_inode_ranged_write(handle_t *handle, + struct jbd2_inode *inode, loff_t start_byte, + loff_t length); +extern int jbd2_journal_inode_ranged_wait(handle_t *handle, + struct jbd2_inode *inode, loff_t start_byte, + loff_t length); extern int jbd2_journal_begin_ordered_truncate(journal_t *journal, struct jbd2_inode *inode, loff_t new_size); extern void jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode); diff --git a/include/linux/unicode.h b/include/linux/unicode.h index aec2c6d800aa..990aa97d8049 100644 --- a/include/linux/unicode.h +++ b/include/linux/unicode.h @@ -17,6 +17,9 @@ int utf8_strncmp(const struct unicode_map *um, int utf8_strncasecmp(const struct unicode_map *um, const struct qstr *s1, const struct qstr *s2); +int utf8_strncasecmp_folded(const struct unicode_map *um, + const struct qstr *cf, + const struct qstr *s1); int utf8_normalize(const struct unicode_map *um, const struct qstr *str, unsigned char *dest, size_t dlen); diff --git a/mm/filemap.c b/mm/filemap.c index 01e7e0869bba..f1aa20ab8434 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -549,6 +549,28 @@ int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte, } EXPORT_SYMBOL(filemap_fdatawait_range); +/** + * filemap_fdatawait_range_keep_errors - wait for writeback to complete + * @mapping: address space structure to wait for + * @start_byte: offset in bytes where the range starts + * @end_byte: offset in bytes where the range ends (inclusive) + * + * Walk the list of under-writeback pages of the given address space in the + * given range and wait for all of them. Unlike filemap_fdatawait_range(), + * this function does not clear error status of the address space. + * + * Use this function if callers don't handle errors themselves. Expected + * call sites are system-wide / filesystem-wide data flushers: e.g. sync(2), + * fsfreeze(8) + */ +int filemap_fdatawait_range_keep_errors(struct address_space *mapping, + loff_t start_byte, loff_t end_byte) +{ + __filemap_fdatawait_range(mapping, start_byte, end_byte); + return filemap_check_and_keep_errors(mapping); +} +EXPORT_SYMBOL(filemap_fdatawait_range_keep_errors); + /** * file_fdatawait_range - wait for writeback to complete * @file: file pointing to address space structure to wait for