From fe53cbc5a39852a7e98d9993e617d49b61055b66 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Sat, 6 Apr 2019 18:53:05 -0400 Subject: ext4: remove incorrect comment for NEXT_ORPHAN() The comment above NEXT_ORPHAN() was meant for ext4_encrypted_inode(), which was moved by commit a7550b30ab70 ("ext4 crypto: migrate into vfs's crypto engine") but the comment was accidentally left in place. Since ext4_encrypted_inode() has now been removed, just remove the comment. Signed-off-by: Eric Biggers Signed-off-by: Theodore Ts'o Reviewed-by: Jan Kara --- fs/ext4/ext4.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 82ffdacdc7fa..2a2e6ed9aab4 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1592,9 +1592,6 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei) #define EXT4_SB(sb) (sb) #endif -/* - * Returns true if the inode is inode is encrypted - */ #define NEXT_ORPHAN(inode) EXT4_I(inode)->i_dtime /* -- cgit v1.2.3 From c83ad55eaa91c8e85dd8cc3b7b3485fac45ef7bf Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Thu, 25 Apr 2019 14:05:42 -0400 Subject: ext4: include charset encoding information in the superblock Support for encoding is considered an incompatible feature, since it has potential to create collisions of file names in existing filesystems. If the feature flag is not enabled, the entire filesystem will operate on opaque byte sequences, respecting the original behavior. The s_encoding field stores a magic number indicating the encoding format and version used globally by file and directory names in the filesystem. The s_encoding_flags defines policies for using the charset encoding, like how to handle invalid sequences. The magic number is mapped to the exact charset table, but the mapping is specific to ext4. Since we don't have any commitment to support old encodings, the only encoding I am supporting right now is utf8-12.1.0. The current implementation prevents the user from enabling encoding and per-directory encryption on the same filesystem at the same time. The incompatibility between these features lies in how we do efficient directory searches when we cannot be sure the encryption of the user provided fname will match the actual hash stored in the disk without decrypting every directory entry, because of normalization cases. My quickest solution is to simply block the concurrent use of these features for now, and enable it later, once we have a better solution. Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Theodore Ts'o --- fs/ext4/ext4.h | 21 +++++++++++++- fs/ext4/super.c | 85 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 105 insertions(+), 1 deletion(-) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 2a2e6ed9aab4..c1504c471fef 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1313,7 +1313,9 @@ struct ext4_super_block { __u8 s_first_error_time_hi; __u8 s_last_error_time_hi; __u8 s_pad[2]; - __le32 s_reserved[96]; /* Padding to the end of the block */ + __le16 s_encoding; /* Filename charset encoding */ + __le16 s_encoding_flags; /* Filename charset encoding flags */ + __le32 s_reserved[95]; /* Padding to the end of the block */ __le32 s_checksum; /* crc32c(superblock) */ }; @@ -1338,6 +1340,16 @@ struct ext4_super_block { /* Number of quota types we support */ #define EXT4_MAXQUOTAS 3 +#define EXT4_ENC_UTF8_12_1 1 + +/* + * Flags for ext4_sb_info.s_encoding_flags. + */ +#define EXT4_ENC_STRICT_MODE_FL (1 << 0) + +#define ext4_has_strict_mode(sbi) \ + (sbi->s_encoding_flags & EXT4_ENC_STRICT_MODE_FL) + /* * fourth extended-fs super-block data in memory */ @@ -1387,6 +1399,10 @@ struct ext4_sb_info { struct kobject s_kobj; struct completion s_kobj_unregister; struct super_block *s_sb; +#ifdef CONFIG_UNICODE + struct unicode_map *s_encoding; + __u16 s_encoding_flags; +#endif /* Journaling */ struct journal_s *s_journal; @@ -1660,6 +1676,7 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei) #define EXT4_FEATURE_INCOMPAT_LARGEDIR 0x4000 /* >2GB or 3-lvl htree */ #define EXT4_FEATURE_INCOMPAT_INLINE_DATA 0x8000 /* data in inode */ #define EXT4_FEATURE_INCOMPAT_ENCRYPT 0x10000 +#define EXT4_FEATURE_INCOMPAT_CASEFOLD 0x20000 extern void ext4_update_dynamic_rev(struct super_block *sb); @@ -1753,6 +1770,7 @@ EXT4_FEATURE_INCOMPAT_FUNCS(csum_seed, CSUM_SEED) EXT4_FEATURE_INCOMPAT_FUNCS(largedir, LARGEDIR) EXT4_FEATURE_INCOMPAT_FUNCS(inline_data, INLINE_DATA) EXT4_FEATURE_INCOMPAT_FUNCS(encrypt, ENCRYPT) +EXT4_FEATURE_INCOMPAT_FUNCS(casefold, CASEFOLD) #define EXT2_FEATURE_COMPAT_SUPP EXT4_FEATURE_COMPAT_EXT_ATTR #define EXT2_FEATURE_INCOMPAT_SUPP (EXT4_FEATURE_INCOMPAT_FILETYPE| \ @@ -1780,6 +1798,7 @@ EXT4_FEATURE_INCOMPAT_FUNCS(encrypt, ENCRYPT) EXT4_FEATURE_INCOMPAT_MMP | \ EXT4_FEATURE_INCOMPAT_INLINE_DATA | \ EXT4_FEATURE_INCOMPAT_ENCRYPT | \ + EXT4_FEATURE_INCOMPAT_CASEFOLD | \ EXT4_FEATURE_INCOMPAT_CSUM_SEED | \ EXT4_FEATURE_INCOMPAT_LARGEDIR) #define EXT4_FEATURE_RO_COMPAT_SUPP (EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \ diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 184944d4d8d1..c1b02c3a5a68 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -42,6 +42,7 @@ #include #include #include +#include #include #include @@ -1054,6 +1055,9 @@ static void ext4_put_super(struct super_block *sb) crypto_free_shash(sbi->s_chksum_driver); kfree(sbi->s_blockgroup_lock); fs_put_dax(sbi->s_daxdev); +#ifdef CONFIG_UNICODE + utf8_unload(sbi->s_encoding); +#endif kfree(sbi); } @@ -1750,6 +1754,36 @@ static const struct mount_opts { {Opt_err, 0, 0} }; +#ifdef CONFIG_UNICODE +static const struct ext4_sb_encodings { + __u16 magic; + char *name; + char *version; +} ext4_sb_encoding_map[] = { + {EXT4_ENC_UTF8_12_1, "utf8", "12.1.0"}, +}; + +static int ext4_sb_read_encoding(const struct ext4_super_block *es, + const struct ext4_sb_encodings **encoding, + __u16 *flags) +{ + __u16 magic = le16_to_cpu(es->s_encoding); + int i; + + for (i = 0; i < ARRAY_SIZE(ext4_sb_encoding_map); i++) + if (magic == ext4_sb_encoding_map[i].magic) + break; + + if (i >= ARRAY_SIZE(ext4_sb_encoding_map)) + return -EINVAL; + + *encoding = &ext4_sb_encoding_map[i]; + *flags = le16_to_cpu(es->s_encoding_flags); + + return 0; +} +#endif + static int handle_mount_opt(struct super_block *sb, char *opt, int token, substring_t *args, unsigned long *journal_devnum, unsigned int *journal_ioprio, int is_remount) @@ -2880,6 +2914,15 @@ static int ext4_feature_set_ok(struct super_block *sb, int readonly) return 0; } +#ifndef CONFIG_UNICODE + if (ext4_has_feature_casefold(sb)) { + ext4_msg(sb, KERN_ERR, + "Filesystem with casefold feature cannot be " + "mounted without CONFIG_UNICODE"); + return 0; + } +#endif + if (readonly) return 1; @@ -3770,6 +3813,43 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) &journal_ioprio, 0)) goto failed_mount; +#ifdef CONFIG_UNICODE + if (ext4_has_feature_casefold(sb) && !sbi->s_encoding) { + const struct ext4_sb_encodings *encoding_info; + struct unicode_map *encoding; + __u16 encoding_flags; + + if (ext4_has_feature_encrypt(sb)) { + ext4_msg(sb, KERN_ERR, + "Can't mount with encoding and encryption"); + goto failed_mount; + } + + if (ext4_sb_read_encoding(es, &encoding_info, + &encoding_flags)) { + ext4_msg(sb, KERN_ERR, + "Encoding requested by superblock is unknown"); + goto failed_mount; + } + + encoding = utf8_load(encoding_info->version); + if (IS_ERR(encoding)) { + ext4_msg(sb, KERN_ERR, + "can't mount with superblock charset: %s-%s " + "not supported by the kernel. flags: 0x%x.", + encoding_info->name, encoding_info->version, + encoding_flags); + goto failed_mount; + } + ext4_msg(sb, KERN_INFO,"Using encoding defined by superblock: " + "%s-%s with flags 0x%hx", encoding_info->name, + encoding_info->version?:"\b", encoding_flags); + + sbi->s_encoding = encoding; + sbi->s_encoding_flags = encoding_flags; + } +#endif + if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) { printk_once(KERN_WARNING "EXT4-fs: Warning: mounting " "with data=journal disables delayed " @@ -4586,6 +4666,11 @@ failed_mount2: failed_mount: if (sbi->s_chksum_driver) crypto_free_shash(sbi->s_chksum_driver); + +#ifdef CONFIG_UNICODE + utf8_unload(sbi->s_encoding); +#endif + #ifdef CONFIG_QUOTA for (i = 0; i < EXT4_MAXQUOTAS; i++) kfree(sbi->s_qf_names[i]); -- cgit v1.2.3 From b886ee3e778ec2ad43e276fd378ab492cf6819b7 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Thu, 25 Apr 2019 14:12:08 -0400 Subject: ext4: Support case-insensitive file name lookups This patch implements the actual support for case-insensitive file name lookups in ext4, based on the feature bit and the encoding stored in the superblock. A filesystem that has the casefold feature set is able to configure directories with the +F (EXT4_CASEFOLD_FL) attribute, enabling lookups to succeed in that directory in a case-insensitive fashion, i.e: match a directory entry even if the name used by userspace is not a byte per byte match with the disk name, but is an equivalent case-insensitive version of the Unicode string. This operation is called a case-insensitive file name lookup. The feature is configured as an inode attribute applied to directories and inherited by its children. This attribute can only be enabled on empty directories for filesystems that support the encoding feature, thus preventing collision of file names that only differ by case. * dcache handling: For a +F directory, Ext4 only stores the first equivalent name dentry used in the dcache. This is done to prevent unintentional duplication of dentries in the dcache, while also allowing the VFS code to quickly find the right entry in the cache despite which equivalent string was used in a previous lookup, without having to resort to ->lookup(). d_hash() of casefolded directories is implemented as the hash of the casefolded string, such that we always have a well-known bucket for all the equivalencies of the same string. d_compare() uses the utf8_strncasecmp() infrastructure, which handles the comparison of equivalent, same case, names as well. For now, negative lookups are not inserted in the dcache, since they would need to be invalidated anyway, because we can't trust missing file dentries. This is bad for performance but requires some leveraging of the vfs layer to fix. We can live without that for now, and so does everyone else. * on-disk data: Despite using a specific version of the name as the internal representation within the dcache, the name stored and fetched from the disk is a byte-per-byte match with what the user requested, making this implementation 'name-preserving'. i.e. no actual information is lost when writing to storage. DX is supported by modifying the hashes used in +F directories to make them case/encoding-aware. The new disk hashes are calculated as the hash of the full casefolded string, instead of the string directly. This allows us to efficiently search for file names in the htree without requiring the user to provide an exact name. * Dealing with invalid sequences: By default, when a invalid UTF-8 sequence is identified, ext4 will treat it as an opaque byte sequence, ignoring the encoding and reverting to the old behavior for that unique file. This means that case-insensitive file name lookup will not work only for that file. An optional bit can be set in the superblock telling the filesystem code and userspace tools to enforce the encoding. When that optional bit is set, any attempt to create a file name using an invalid UTF-8 sequence will fail and return an error to userspace. * Normalization algorithm: The UTF-8 algorithms used to compare strings in ext4 is implemented lives in fs/unicode, and is based on a previous version developed by SGI. It implements the Canonical decomposition (NFD) algorithm described by the Unicode specification 12.1, or higher, combined with the elimination of ignorable code points (NFDi) and full case-folding (CF) as documented in fs/unicode/utf8_norm.c. NFD seems to be the best normalization method for EXT4 because: - It has a lower cost than NFC/NFKC (which requires decomposing to NFD as an intermediary step) - It doesn't eliminate important semantic meaning like compatibility decompositions. Although: - This implementation is not completely linguistic accurate, because different languages have conflicting rules, which would require the specialization of the filesystem to a given locale, which brings all sorts of problems for removable media and for users who use more than one language. Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Theodore Ts'o --- fs/ext4/dir.c | 48 ++++++++++++++++++++++++ fs/ext4/ext4.h | 21 ++++++++--- fs/ext4/hash.c | 34 ++++++++++++++++- fs/ext4/ialloc.c | 2 +- fs/ext4/inline.c | 2 +- fs/ext4/inode.c | 4 +- fs/ext4/ioctl.c | 18 +++++++++ fs/ext4/namei.c | 107 +++++++++++++++++++++++++++++++++++++++++++++++------ fs/ext4/super.c | 6 +++ include/linux/fs.h | 2 + 10 files changed, 223 insertions(+), 21 deletions(-) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index 0ccd51f72048..884a6e776809 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -26,6 +26,7 @@ #include #include #include +#include #include "ext4.h" #include "xattr.h" @@ -660,3 +661,50 @@ const struct file_operations ext4_dir_operations = { .open = ext4_dir_open, .release = ext4_release_dir, }; + +#ifdef CONFIG_UNICODE +static int ext4_d_compare(const struct dentry *dentry, unsigned int len, + const char *str, const struct qstr *name) +{ + struct qstr qstr = {.name = str, .len = len }; + + if (!IS_CASEFOLDED(dentry->d_parent->d_inode)) { + if (len != name->len) + return -1; + return !memcmp(str, name, len); + } + + return ext4_ci_compare(dentry->d_parent->d_inode, name, &qstr); +} + +static int ext4_d_hash(const struct dentry *dentry, struct qstr *str) +{ + const struct ext4_sb_info *sbi = EXT4_SB(dentry->d_sb); + const struct unicode_map *um = sbi->s_encoding; + unsigned char *norm; + int len, ret = 0; + + if (!IS_CASEFOLDED(dentry->d_inode)) + return 0; + + norm = kmalloc(PATH_MAX, GFP_ATOMIC); + if (!norm) + return -ENOMEM; + + len = utf8_casefold(um, str, norm, PATH_MAX); + if (len < 0) { + if (ext4_has_strict_mode(sbi)) + ret = -EINVAL; + goto out; + } + str->hash = full_name_hash(dentry, norm, len); +out: + kfree(norm); + return ret; +} + +const struct dentry_operations ext4_dentry_ops = { + .d_hash = ext4_d_hash, + .d_compare = ext4_d_compare, +}; +#endif diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index c1504c471fef..c18ab748d20d 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -399,10 +399,11 @@ struct flex_groups { #define EXT4_EOFBLOCKS_FL 0x00400000 /* Blocks allocated beyond EOF */ #define EXT4_INLINE_DATA_FL 0x10000000 /* Inode has inline data. */ #define EXT4_PROJINHERIT_FL 0x20000000 /* Create with parents projid */ +#define EXT4_CASEFOLD_FL 0x40000000 /* Casefolded file */ #define EXT4_RESERVED_FL 0x80000000 /* reserved for ext4 lib */ -#define EXT4_FL_USER_VISIBLE 0x304BDFFF /* User visible flags */ -#define EXT4_FL_USER_MODIFIABLE 0x204BC0FF /* User modifiable flags */ +#define EXT4_FL_USER_VISIBLE 0x704BDFFF /* User visible flags */ +#define EXT4_FL_USER_MODIFIABLE 0x604BC0FF /* User modifiable flags */ /* Flags we can manipulate with through EXT4_IOC_FSSETXATTR */ #define EXT4_FL_XFLAG_VISIBLE (EXT4_SYNC_FL | \ @@ -417,10 +418,10 @@ struct flex_groups { EXT4_SYNC_FL | EXT4_NODUMP_FL | EXT4_NOATIME_FL |\ EXT4_NOCOMPR_FL | EXT4_JOURNAL_DATA_FL |\ EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL |\ - EXT4_PROJINHERIT_FL) + 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)) +#define EXT4_REG_FLMASK (~(EXT4_DIRSYNC_FL | EXT4_TOPDIR_FL | EXT4_CASEFOLD_FL)) /* Flags that are appropriate for non-directories/regular files. */ #define EXT4_OTHER_FLMASK (EXT4_NODUMP_FL | EXT4_NOATIME_FL) @@ -2393,8 +2394,8 @@ extern int ext4_check_all_de(struct inode *dir, struct buffer_head *bh, extern int ext4_sync_file(struct file *, loff_t, loff_t, int); /* hash.c */ -extern int ext4fs_dirhash(const char *name, int len, struct - dx_hash_info *hinfo); +extern int ext4fs_dirhash(const struct inode *dir, const char *name, int len, + struct dx_hash_info *hinfo); /* ialloc.c */ extern struct inode *__ext4_new_inode(handle_t *, struct inode *, umode_t, @@ -2990,6 +2991,10 @@ static inline void ext4_unlock_group(struct super_block *sb, /* dir.c */ extern const struct file_operations ext4_dir_operations; +#ifdef CONFIG_UNICODE +extern const struct dentry_operations ext4_dentry_ops; +#endif + /* file.c */ extern const struct inode_operations ext4_file_inode_operations; extern const struct file_operations ext4_file_operations; @@ -3082,6 +3087,10 @@ extern void initialize_dirent_tail(struct ext4_dir_entry_tail *t, extern int ext4_handle_dirty_dirent_node(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); + #define S_SHIFT 12 static const unsigned char ext4_type_by_mode[(S_IFMT >> S_SHIFT) + 1] = { [S_IFREG >> S_SHIFT] = EXT4_FT_REG_FILE, diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c index 46b24da33a28..d358bfcb6b3f 100644 --- a/fs/ext4/hash.c +++ b/fs/ext4/hash.c @@ -6,6 +6,7 @@ */ #include +#include #include #include #include "ext4.h" @@ -196,7 +197,8 @@ static void str2hashbuf_unsigned(const char *msg, int len, __u32 *buf, int num) * represented, and whether or not the returned hash is 32 bits or 64 * bits. 32 bit hashes will return 0 for the minor hash. */ -int ext4fs_dirhash(const char *name, int len, struct dx_hash_info *hinfo) +static int __ext4fs_dirhash(const char *name, int len, + struct dx_hash_info *hinfo) { __u32 hash; __u32 minor_hash = 0; @@ -268,3 +270,33 @@ int ext4fs_dirhash(const char *name, int len, struct dx_hash_info *hinfo) hinfo->minor_hash = minor_hash; return 0; } + +int ext4fs_dirhash(const struct inode *dir, const char *name, int len, + struct dx_hash_info *hinfo) +{ +#ifdef CONFIG_UNICODE + const struct unicode_map *um = EXT4_SB(dir->i_sb)->s_encoding; + int r, dlen; + unsigned char *buff; + struct qstr qstr = {.name = name, .len = len }; + + if (len && IS_CASEFOLDED(dir)) { + buff = kzalloc(sizeof(char) * PATH_MAX, GFP_KERNEL); + if (!buff) + return -ENOMEM; + + dlen = utf8_casefold(um, &qstr, buff, PATH_MAX); + if (dlen < 0) { + kfree(buff); + goto opaque_seq; + } + + r = __ext4fs_dirhash(buff, dlen, hinfo); + + kfree(buff); + return r; + } +opaque_seq: +#endif + return __ext4fs_dirhash(name, len, hinfo); +} diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index f3e17a8c84b4..764ff4c56233 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -455,7 +455,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent, if (qstr) { hinfo.hash_version = DX_HASH_HALF_MD4; hinfo.seed = sbi->s_hash_seed; - ext4fs_dirhash(qstr->name, qstr->len, &hinfo); + ext4fs_dirhash(parent, qstr->name, qstr->len, &hinfo); grp = hinfo.hash; } else grp = prandom_u32(); diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 56f6e1782d5f..f73bc3925282 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -1407,7 +1407,7 @@ int htree_inlinedir_to_tree(struct file *dir_file, } } - ext4fs_dirhash(de->name, de->name_len, hinfo); + ext4fs_dirhash(dir, de->name, de->name_len, hinfo); if ((hinfo->hash < start_hash) || ((hinfo->hash == start_hash) && (hinfo->minor_hash < start_minor_hash))) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 609c8366d029..82298c63ea6d 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4742,9 +4742,11 @@ void ext4_set_inode_flags(struct inode *inode) new_fl |= S_DAX; if (flags & EXT4_ENCRYPT_FL) new_fl |= S_ENCRYPTED; + if (flags & EXT4_CASEFOLD_FL) + new_fl |= S_CASEFOLD; inode_set_flags(inode, new_fl, S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC|S_DAX| - S_ENCRYPTED); + S_ENCRYPTED|S_CASEFOLD); } static blkcnt_t ext4_inode_blocks(struct ext4_inode *raw_inode, diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 20faa6a69238..7e85ecf0b849 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -278,6 +278,7 @@ static int ext4_ioctl_setflags(struct inode *inode, struct ext4_iloc iloc; unsigned int oldflags, mask, i; unsigned int jflag; + struct super_block *sb = inode->i_sb; /* Is it quota file? Do not allow user to mess with it */ if (ext4_is_quota_file(inode)) @@ -322,6 +323,23 @@ static int ext4_ioctl_setflags(struct inode *inode, goto flags_out; } + if ((flags ^ oldflags) & EXT4_CASEFOLD_FL) { + if (!ext4_has_feature_casefold(sb)) { + err = -EOPNOTSUPP; + goto flags_out; + } + + if (!S_ISDIR(inode->i_mode)) { + err = -ENOTDIR; + goto flags_out; + } + + if (!ext4_empty_dir(inode)) { + err = -ENOTEMPTY; + goto flags_out; + } + } + handle = ext4_journal_start(inode, EXT4_HT_INODE, 1); if (IS_ERR(handle)) { err = PTR_ERR(handle); diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 980166a8122a..e917830eae84 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -35,6 +35,7 @@ #include #include #include +#include #include "ext4.h" #include "ext4_jbd2.h" @@ -629,7 +630,7 @@ static struct stats dx_show_leaf(struct inode *dir, } if (!fscrypt_has_encryption_key(dir)) { /* Directory is not encrypted */ - ext4fs_dirhash(de->name, + ext4fs_dirhash(dir, de->name, de->name_len, &h); printk("%*.s:(U)%x.%u ", len, name, h.hash, @@ -662,8 +663,8 @@ static struct stats dx_show_leaf(struct inode *dir, name = fname_crypto_str.name; len = fname_crypto_str.len; } - ext4fs_dirhash(de->name, de->name_len, - &h); + ext4fs_dirhash(dir, de->name, + de->name_len, &h); printk("%*.s:(E)%x.%u ", len, name, h.hash, (unsigned) ((char *) de - base)); @@ -673,7 +674,7 @@ static struct stats dx_show_leaf(struct inode *dir, #else int len = de->name_len; char *name = de->name; - ext4fs_dirhash(de->name, de->name_len, &h); + ext4fs_dirhash(dir, de->name, de->name_len, &h); printk("%*.s:%x.%u ", len, name, h.hash, (unsigned) ((char *) de - base)); #endif @@ -762,7 +763,7 @@ dx_probe(struct ext4_filename *fname, struct inode *dir, hinfo->hash_version += EXT4_SB(dir->i_sb)->s_hash_unsigned; hinfo->seed = EXT4_SB(dir->i_sb)->s_hash_seed; if (fname && fname_name(fname)) - ext4fs_dirhash(fname_name(fname), fname_len(fname), hinfo); + ext4fs_dirhash(dir, fname_name(fname), fname_len(fname), hinfo); hash = hinfo->hash; if (root->info.unused_flags & 1) { @@ -1008,7 +1009,7 @@ static int htree_dirblock_to_tree(struct file *dir_file, /* silently ignore the rest of the block */ break; } - ext4fs_dirhash(de->name, de->name_len, hinfo); + ext4fs_dirhash(dir, de->name, de->name_len, hinfo); if ((hinfo->hash < start_hash) || ((hinfo->hash == start_hash) && (hinfo->minor_hash < start_minor_hash))) @@ -1197,7 +1198,7 @@ static int dx_make_map(struct inode *dir, struct ext4_dir_entry_2 *de, while ((char *) de < base + blocksize) { if (de->name_len && de->inode) { - ext4fs_dirhash(de->name, de->name_len, &h); + ext4fs_dirhash(dir, de->name, de->name_len, &h); map_tail--; map_tail->hash = h.hash; map_tail->offs = ((char *) de - base)>>2; @@ -1252,15 +1253,52 @@ static void dx_insert_block(struct dx_frame *frame, u32 hash, ext4_lblk_t block) dx_set_count(entries, count + 1); } +#ifdef CONFIG_UNICODE +/* + * Test whether a case-insensitive directory entry matches the filename + * being searched for. + * + * Returns: 0 if the directory entry matches, more than 0 if it + * doesn't match or less than zero on error. + */ +int ext4_ci_compare(const struct inode *parent, const struct qstr *name, + const struct qstr *entry) +{ + 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 (ret < 0) { + /* Handle invalid character sequence as either an error + * or as an opaque byte sequence. + */ + if (ext4_has_strict_mode(sbi)) + return -EINVAL; + + if (name->len != entry->len) + return 1; + + return !!memcmp(name->name, entry->name, name->len); + } + + return ret; +} +#endif + /* * Test whether a directory entry matches the filename being searched for. * * Return: %true if the directory entry matches, otherwise %false. */ -static inline bool ext4_match(const struct ext4_filename *fname, +static inline bool ext4_match(const struct inode *parent, + const struct ext4_filename *fname, const struct ext4_dir_entry_2 *de) { struct fscrypt_name f; +#ifdef CONFIG_UNICODE + const struct qstr entry = {.name = de->name, .len = de->name_len}; +#endif if (!de->inode) return false; @@ -1270,6 +1308,12 @@ static inline bool ext4_match(const struct ext4_filename *fname, #ifdef CONFIG_FS_ENCRYPTION f.crypto_buf = fname->crypto_buf; #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); +#endif + return fscrypt_match_name(&f, de->name, de->name_len); } @@ -1290,7 +1334,7 @@ int ext4_search_dir(struct buffer_head *bh, char *search_buf, int buf_size, /* this code is executed quadratically often */ /* do minimal checking `by hand' */ if ((char *) de + de->name_len <= dlimit && - ext4_match(fname, de)) { + ext4_match(dir, fname, de)) { /* found a match - just to be sure, do * a full check */ if (ext4_check_dir_entry(dir, NULL, de, bh, bh->b_data, @@ -1588,6 +1632,17 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi return ERR_PTR(-EPERM); } } + +#ifdef CONFIG_UNICODE + if (!inode && IS_CASEFOLDED(dir)) { + /* Eventually we want to call d_add_ci(dentry, NULL) + * for negative dentries in the encoding case as + * well. For now, prevent the negative dentry + * from being cached. + */ + return NULL; + } +#endif return d_splice_alias(inode, dentry); } @@ -1798,7 +1853,7 @@ int ext4_find_dest_de(struct inode *dir, struct inode *inode, if (ext4_check_dir_entry(dir, NULL, de, bh, buf, buf_size, offset)) return -EFSCORRUPTED; - if (ext4_match(fname, de)) + if (ext4_match(dir, fname, de)) return -EEXIST; nlen = EXT4_DIR_REC_LEN(de->name_len); rlen = ext4_rec_len_from_disk(de->rec_len, buf_size); @@ -1983,7 +2038,7 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, if (fname->hinfo.hash_version <= DX_HASH_TEA) fname->hinfo.hash_version += EXT4_SB(dir->i_sb)->s_hash_unsigned; fname->hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed; - ext4fs_dirhash(fname_name(fname), fname_len(fname), &fname->hinfo); + ext4fs_dirhash(dir, fname_name(fname), fname_len(fname), &fname->hinfo); memset(frames, 0, sizeof(frames)); frame = frames; @@ -2036,6 +2091,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, 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; int retval; int dx_fallback=0; @@ -2047,10 +2103,17 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, csum_size = sizeof(struct ext4_dir_entry_tail); sb = dir->i_sb; + sbi = EXT4_SB(sb); blocksize = sb->s_blocksize; if (!dentry->d_name.len) return -EINVAL; +#ifdef CONFIG_UNICODE + if (ext4_has_strict_mode(sbi) && IS_CASEFOLDED(dir) && + utf8_validate(sbi->s_encoding, &dentry->d_name)) + return -EINVAL; +#endif + retval = ext4_fname_setup_filename(dir, &dentry->d_name, 0, &fname); if (retval) return retval; @@ -2975,6 +3038,17 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry) ext4_update_dx_flag(dir); ext4_mark_inode_dirty(handle, dir); +#ifdef CONFIG_UNICODE + /* VFS negative dentries are incompatible with Encoding and + * Case-insensitiveness. Eventually we'll want avoid + * invalidating the dentries here, alongside with returning the + * negative dentries at ext4_lookup(), when it is better + * supported by the VFS for the CI case. + */ + if (IS_CASEFOLDED(dir)) + d_invalidate(dentry); +#endif + end_rmdir: brelse(bh); if (handle) @@ -3044,6 +3118,17 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry) inode->i_ctime = current_time(inode); ext4_mark_inode_dirty(handle, inode); +#ifdef CONFIG_UNICODE + /* VFS negative dentries are incompatible with Encoding and + * Case-insensitiveness. Eventually we'll want avoid + * invalidating the dentries here, alongside with returning the + * negative dentries at ext4_lookup(), when it is better + * supported by the VFS for the CI case. + */ + if (IS_CASEFOLDED(dir)) + d_invalidate(dentry); +#endif + end_unlink: brelse(bh); if (handle) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index c1b02c3a5a68..aeb6d22ea0ad 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -4484,6 +4484,12 @@ no_journal: iput(root); goto failed_mount4; } + +#ifdef CONFIG_UNICODE + if (sbi->s_encoding) + sb->s_d_op = &ext4_dentry_ops; +#endif + sb->s_root = d_make_root(root); if (!sb->s_root) { ext4_msg(sb, KERN_ERR, "get root dentry failed"); diff --git a/include/linux/fs.h b/include/linux/fs.h index 8b42df09b04c..6261090e605b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1953,6 +1953,7 @@ struct super_operations { #define S_DAX 0 /* Make all the DAX code disappear */ #endif #define S_ENCRYPTED 16384 /* Encrypted file (using fs/crypto/) */ +#define S_CASEFOLD 32768 /* Casefolded file */ /* * Note that nosuid etc flags are inode-specific: setting some file-system @@ -1993,6 +1994,7 @@ static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags #define IS_NOSEC(inode) ((inode)->i_flags & S_NOSEC) #define IS_DAX(inode) ((inode)->i_flags & S_DAX) #define IS_ENCRYPTED(inode) ((inode)->i_flags & S_ENCRYPTED) +#define IS_CASEFOLDED(inode) ((inode)->i_flags & S_CASEFOLD) #define IS_WHITEOUT(inode) (S_ISCHR(inode->i_mode) && \ (inode)->i_rdev == WHITEOUT_DEV) -- cgit v1.2.3