diff options
author | Hin-Tak Leung <htl10@users.sourceforge.net> | 2014-06-06 14:36:21 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2014-06-06 16:08:09 -0700 |
commit | 017f8da43e92ddd9989884720b694a512e09ccce (patch) | |
tree | 2edff7cb8d45e6e859b91d8a7382799459f818f0 /fs/hfsplus | |
parent | 6d6bd94f4d83d70cdff67d0bf2a64ef6878216e7 (diff) | |
download | linux-017f8da43e92ddd9989884720b694a512e09ccce.tar.gz linux-017f8da43e92ddd9989884720b694a512e09ccce.tar.bz2 linux-017f8da43e92ddd9989884720b694a512e09ccce.zip |
hfsplus: fix worst-case unicode to char conversion of file names and attributes
This is a series of 3 patches which corrects issues in HFS+ concerning
the use of non-english file names and attributes. Names and attributes
are stored internally as UTF-16 units up to a fixed maximum size, and
convert to and from user-representation by NLS. The code incorrectly
assume that NLS string lengths are equal to unicode lengths, which is
only true for English ascii usage.
This patch (of 3):
The HFS Plus Volume Format specification (TN1150) states that file names
are stored internally as a maximum of 255 unicode characters, as defined
by The Unicode Standard, Version 2.0 [Unicode, Inc. ISBN
0-201-48345-9]. File names are converted by the NLS system on Linux
before presented to the user.
255 CJK characters converts to UTF-8 with 1 unicode character to up to 3
bytes, and to GB18030 with 1 unicode character to up to 4 bytes. Thus,
trying in a UTF-8 locale to list files with names of more than 85 CJK
characters results in:
$ ls /mnt
ls: reading directory /mnt: File name too long
The receiving buffer to hfsplus_uni2asc() needs to be 255 x
NLS_MAX_CHARSET_SIZE bytes, not 255 bytes as the code has always been.
Similar consideration applies to attributes, which are stored internally
as a maximum of 127 UTF-16BE units. See XNU source for an up-to-date
reference on attributes.
Strictly speaking, the maximum value of NLS_MAX_CHARSET_SIZE = 6 is not
attainable in the case of conversion to UTF-8, as going beyond 3 bytes
requires the use of surrogate pairs, i.e. consuming two input units.
Thanks Anton Altaparmakov for reviewing an earlier version of this
change.
This patch fixes all callers of hfsplus_uni2asc(), and also enables the
use of long non-English file names in HFS+. The getting and setting,
and general usage of long non-English attributes requires further
forthcoming work, in the following patches of this series.
[akpm@linux-foundation.org: fix build]
Signed-off-by: Hin-Tak Leung <htl10@users.sourceforge.net>
Reviewed-by: Anton Altaparmakov <anton@tuxera.com>
Cc: Vyacheslav Dubeyko <slava@dubeyko.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Sougata Santra <sougata@tuxera.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'fs/hfsplus')
-rw-r--r-- | fs/hfsplus/dir.c | 11 | ||||
-rw-r--r-- | fs/hfsplus/xattr.c | 15 |
2 files changed, 21 insertions, 5 deletions
diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c index bdec66522de3..fb07d260e692 100644 --- a/fs/hfsplus/dir.c +++ b/fs/hfsplus/dir.c @@ -12,6 +12,7 @@ #include <linux/fs.h> #include <linux/slab.h> #include <linux/random.h> +#include <linux/nls.h> #include "hfsplus_fs.h" #include "hfsplus_raw.h" @@ -127,7 +128,7 @@ static int hfsplus_readdir(struct file *file, struct dir_context *ctx) struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; int len, err; - char strbuf[HFSPLUS_MAX_STRLEN + 1]; + char *strbuf; hfsplus_cat_entry entry; struct hfs_find_data fd; struct hfsplus_readdir_data *rd; @@ -139,6 +140,11 @@ static int hfsplus_readdir(struct file *file, struct dir_context *ctx) err = hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd); if (err) return err; + strbuf = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_MAX_STRLEN + 1, GFP_KERNEL); + if (!strbuf) { + err = -ENOMEM; + goto out; + } hfsplus_cat_build_key(sb, fd.search_key, inode->i_ino, NULL); err = hfs_brec_find(&fd, hfs_find_rec_by_key); if (err) @@ -193,7 +199,7 @@ static int hfsplus_readdir(struct file *file, struct dir_context *ctx) hfs_bnode_read(fd.bnode, &entry, fd.entryoffset, fd.entrylength); type = be16_to_cpu(entry.type); - len = HFSPLUS_MAX_STRLEN; + len = NLS_MAX_CHARSET_SIZE * HFSPLUS_MAX_STRLEN; err = hfsplus_uni2asc(sb, &fd.key->cat.name, strbuf, &len); if (err) goto out; @@ -246,6 +252,7 @@ next: } memcpy(&rd->key, fd.key, sizeof(struct hfsplus_cat_key)); out: + kfree(strbuf); hfs_find_exit(&fd); return err; } diff --git a/fs/hfsplus/xattr.c b/fs/hfsplus/xattr.c index 4e27edc082a4..e2b3c9ea1c71 100644 --- a/fs/hfsplus/xattr.c +++ b/fs/hfsplus/xattr.c @@ -8,6 +8,7 @@ #include "hfsplus_fs.h" #include <linux/posix_acl_xattr.h> +#include <linux/nls.h> #include "xattr.h" #include "acl.h" @@ -645,8 +646,7 @@ ssize_t hfsplus_listxattr(struct dentry *dentry, char *buffer, size_t size) struct hfs_find_data fd; u16 key_len = 0; struct hfsplus_attr_key attr_key; - char strbuf[HFSPLUS_ATTR_MAX_STRLEN + - XATTR_MAC_OSX_PREFIX_LEN + 1] = {0}; + char *strbuf; int xattr_name_len; if ((!S_ISREG(inode->i_mode) && @@ -666,6 +666,13 @@ ssize_t hfsplus_listxattr(struct dentry *dentry, char *buffer, size_t size) return err; } + strbuf = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN + + XATTR_MAC_OSX_PREFIX_LEN + 1, GFP_KERNEL); + if (!strbuf) { + res = -ENOMEM; + goto out; + } + err = hfsplus_find_attr(inode->i_sb, inode->i_ino, NULL, &fd); if (err) { if (err == -ENOENT) { @@ -692,7 +699,7 @@ ssize_t hfsplus_listxattr(struct dentry *dentry, char *buffer, size_t size) if (be32_to_cpu(attr_key.cnid) != inode->i_ino) goto end_listxattr; - xattr_name_len = HFSPLUS_ATTR_MAX_STRLEN; + xattr_name_len = NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN; if (hfsplus_uni2asc(inode->i_sb, (const struct hfsplus_unistr *)&fd.key->attr.key_name, strbuf, &xattr_name_len)) { @@ -718,6 +725,8 @@ ssize_t hfsplus_listxattr(struct dentry *dentry, char *buffer, size_t size) } end_listxattr: + kfree(strbuf); +out: hfs_find_exit(&fd); return res; } |