| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20221226142150.13324-16-pali@kernel.org>
Date: Mon, 26 Dec 2022 15:21:47 +0100
From: Pali Rohár <pali@...nel.org>
To: linux-fsdevel@...r.kernel.org,
linux-ntfs-dev@...ts.sourceforge.net, linux-cifs@...r.kernel.org,
jfs-discussion@...ts.sourceforge.net, linux-kernel@...r.kernel.org,
Alexander Viro <viro@...iv.linux.org.uk>,
Jan Kara <jack@...e.cz>, "Theodore Y . Ts'o" <tytso@....edu>,
Anton Altaparmakov <anton@...era.com>,
OGAWA Hirofumi <hirofumi@...l.parknet.co.jp>,
Luis de Bethencourt <luisbg@...nel.org>,
Salah Triki <salah.triki@...il.com>,
Steve French <sfrench@...ba.org>, Paulo Alcantara <pc@....nz>,
Ronnie Sahlberg <lsahlber@...hat.com>,
Shyam Prasad N <sprasad@...rosoft.com>,
Tom Talpey <tom@...pey.com>, Dave Kleikamp <shaggy@...nel.org>,
Andrew Morton <akpm@...ux-foundation.org>,
Pavel Machek <pavel@....cz>,
Christoph Hellwig <hch@...radead.org>,
Kari Argillander <kari.argillander@...il.com>,
Viacheslav Dubeyko <slava@...eyko.com>
Subject: [RFC PATCH v2 15/18] ntfs: Do not use broken utf8 NLS table for iocharset=utf8 mount option
NLS table for utf8 is broken and cannot be fixed.
So instead of broken utf8 nls functions char2uni() and uni2char() use
functions utf8s_to_utf16s() and utf16s_to_utf8s() which implements correct
conversion between UTF-16 and UTF-8.
These functions implements also correct processing of UTF-16 surrogate
pairs and therefore after this change ntfs driver would be able to correctly
handle also file names with 4-byte UTF-8 sequences.
When iochatset=utf8 is used then set vol->nls_map to NULL and use it for
distinguish between the fact if NLS table or native UTF-8 functions should
be used.
Signed-off-by: Pali Rohár <pali@...nel.org>
---
fs/ntfs/dir.c | 6 ++++--
fs/ntfs/inode.c | 5 ++++-
fs/ntfs/super.c | 41 ++++++++++++++++++++++++-----------------
fs/ntfs/unistr.c | 28 +++++++++++++++++++++++++---
4 files changed, 57 insertions(+), 23 deletions(-)
diff --git a/fs/ntfs/dir.c b/fs/ntfs/dir.c
index cd96083a12c8..035582b92aa2 100644
--- a/fs/ntfs/dir.c
+++ b/fs/ntfs/dir.c
@@ -1034,7 +1034,8 @@ static inline int ntfs_filldir(ntfs_volume *vol,
}
name_len = ntfs_ucstonls(vol, (ntfschar*)&ie->key.file_name.file_name,
ie->key.file_name.file_name_length, &name,
- NTFS_MAX_NAME_LEN * NLS_MAX_CHARSET_SIZE + 1);
+ NTFS_MAX_NAME_LEN *
+ (vol->nls_map ? NLS_MAX_CHARSET_SIZE : 4) + 1);
if (name_len <= 0) {
ntfs_warning(vol->sb, "Skipping unrepresentable inode 0x%llx.",
(long long)MREF_LE(ie->data.dir.indexed_file));
@@ -1118,7 +1119,8 @@ static int ntfs_readdir(struct file *file, struct dir_context *actor)
* Allocate a buffer to store the current name being processed
* converted to format determined by current NLS.
*/
- name = kmalloc(NTFS_MAX_NAME_LEN * NLS_MAX_CHARSET_SIZE + 1, GFP_NOFS);
+ name = kmalloc(NTFS_MAX_NAME_LEN *
+ (vol->nls_map ? NLS_MAX_CHARSET_SIZE : 4) + 1, GFP_NOFS);
if (unlikely(!name)) {
err = -ENOMEM;
goto err_out;
diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c
index 2ab071c4560d..795b5495a897 100644
--- a/fs/ntfs/inode.c
+++ b/fs/ntfs/inode.c
@@ -2314,7 +2314,10 @@ int ntfs_show_options(struct seq_file *sf, struct dentry *root)
seq_printf(sf, ",fmask=0%o", vol->fmask);
seq_printf(sf, ",dmask=0%o", vol->dmask);
}
- seq_printf(sf, ",iocharset=%s", vol->nls_map->charset);
+ if (vol->nls_map)
+ seq_printf(sf, ",iocharset=%s", vol->nls_map->charset);
+ else
+ seq_puts(sf, ",iocharset=utf8");
if (NVolCaseSensitive(vol))
seq_printf(sf, ",case_sensitive");
if (NVolShowSystemFiles(vol))
diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c
index b4f26035e750..b15cd92a9dad 100644
--- a/fs/ntfs/super.c
+++ b/fs/ntfs/super.c
@@ -84,7 +84,7 @@ static int simple_getbool(char *s, bool *setval)
*
* Parse the recognized options in @opt for the ntfs volume described by @vol.
*/
-static bool parse_options(ntfs_volume *vol, char *opt)
+static bool parse_options(ntfs_volume *vol, char *opt, int remount)
{
char *p, *v, *ov;
static char *utf8 = "utf8";
@@ -95,6 +95,7 @@ static bool parse_options(ntfs_volume *vol, char *opt)
int mft_zone_multiplier = -1, on_errors = -1;
int show_sys_files = -1, case_sensitive = -1, disable_sparse = -1;
struct nls_table *nls_map = NULL;
+ int have_iocharset = 0;
/* I am lazy... (-8 */
#define NTFS_GETOPT_WITH_DEFAULT(option, variable, default_value) \
@@ -196,12 +197,16 @@ static bool parse_options(ntfs_volume *vol, char *opt)
goto needs_arg;
use_utf8:
unload_nls(nls_map);
- nls_map = load_nls(v);
- if (!nls_map) {
- ntfs_error(vol->sb, "NLS character set "
- "%s not found.", v);
- return false;
+ nls_map = NULL;
+ if (strcmp(v, "utf8") != 0) {
+ nls_map = load_nls(v);
+ if (!nls_map) {
+ ntfs_error(vol->sb, "NLS character set "
+ "%s not found.", v);
+ return false;
+ }
}
+ have_iocharset = 1;
} else if (!strcmp(p, "utf8")) {
bool val = false;
ntfs_warning(vol->sb, "Option utf8 is no longer "
@@ -241,25 +246,27 @@ static bool parse_options(ntfs_volume *vol, char *opt)
return false;
}
}
- if (nls_map) {
- if (vol->nls_map && vol->nls_map != nls_map) {
+ if (have_iocharset) {
+ if (remount && vol->nls_map != nls_map) {
ntfs_error(vol->sb, "Cannot change NLS character set "
"on remount.");
return false;
- } /* else (!vol->nls_map) */
- ntfs_debug("Using NLS character set %s.", nls_map->charset);
- vol->nls_map = nls_map;
- } else /* (!nls_map) */ {
- if (!vol->nls_map) {
+ } else if (!remount) {
+ ntfs_debug("Using NLS character set %s.",
+ nls_map ? nls_map->charset : "utf8");
+ vol->nls_map = nls_map;
+ }
+ } else if (!remount) {
+ if (strcmp(CONFIG_NLS_DEFAULT, "utf8") != 0) {
vol->nls_map = load_nls_default();
if (!vol->nls_map) {
ntfs_error(vol->sb, "Failed to load default "
"NLS character set.");
return false;
}
- ntfs_debug("Using default NLS character set (%s).",
- vol->nls_map->charset);
}
+ ntfs_debug("Using default NLS character set (%s).",
+ vol->nls_map ? vol->nls_map->charset : "utf8");
}
if (mft_zone_multiplier != -1) {
if (vol->mft_zone_multiplier && vol->mft_zone_multiplier !=
@@ -534,7 +541,7 @@ static int ntfs_remount(struct super_block *sb, int *flags, char *opt)
// TODO: Deal with *flags.
- if (!parse_options(vol, opt))
+ if (!parse_options(vol, opt, 1))
return -EINVAL;
ntfs_debug("Done.");
@@ -2732,7 +2739,7 @@ static int ntfs_fill_super(struct super_block *sb, void *opt, const int silent)
NVolSetSparseEnabled(vol);
/* Important to get the mount options dealt with now. */
- if (!parse_options(vol, (char*)opt))
+ if (!parse_options(vol, (char*)opt, 0))
goto err_out_now;
/* We support sector sizes up to the PAGE_SIZE. */
diff --git a/fs/ntfs/unistr.c b/fs/ntfs/unistr.c
index 75a7f73bccdd..c52141265f99 100644
--- a/fs/ntfs/unistr.c
+++ b/fs/ntfs/unistr.c
@@ -254,6 +254,17 @@ int ntfs_nlstoucs(const ntfs_volume *vol, const char *ins,
if (likely(ins)) {
ucs = kmem_cache_alloc(ntfs_name_cache, GFP_NOFS);
if (likely(ucs)) {
+ if (!nls) {
+ wc_len = utf8s_to_utf16s(ins, ins_len,
+ UTF16_LITTLE_ENDIAN,
+ (wchar_t *)ucs,
+ NTFS_MAX_NAME_LEN);
+ if (wc_len < 0 || wc_len >= NTFS_MAX_NAME_LEN)
+ goto name_err;
+ ucs[wc_len] = 0;
+ *outs = ucs;
+ return o;
+ }
for (i = o = 0; i < ins_len; i += wc_len) {
wc_len = nls->char2uni(ins + i, ins_len - i,
&wc);
@@ -283,7 +294,7 @@ int ntfs_nlstoucs(const ntfs_volume *vol, const char *ins,
if (wc_len < 0) {
ntfs_error(vol->sb, "Name using character set %s contains "
"characters that cannot be converted to "
- "Unicode.", nls->charset);
+ "Unicode.", nls ? nls->charset : "utf8");
i = -EILSEQ;
} else /* if (o >= NTFS_MAX_NAME_LEN) */ {
ntfs_error(vol->sb, "Name is too long (maximum length for a "
@@ -335,11 +346,22 @@ int ntfs_ucstonls(const ntfs_volume *vol, const ntfschar *ins,
goto conversion_err;
}
if (!ns) {
- ns_len = ins_len * NLS_MAX_CHARSET_SIZE;
+ ns_len = ins_len * (nls ? NLS_MAX_CHARSET_SIZE : 4);
ns = kmalloc(ns_len + 1, GFP_NOFS);
if (!ns)
goto mem_err_out;
}
+ if (!nls) {
+ o = utf16s_to_utf8s((const wchar_t *)ins, ins_len,
+ UTF16_LITTLE_ENDIAN, ns, ns_len);
+ if (o >= ns_len) {
+ wc = -ENAMETOOLONG;
+ goto conversion_err;
+ }
+ ns[o] = 0;
+ *outs = ns;
+ return o;
+ }
for (i = o = 0; i < ins_len; i++) {
retry: wc = nls->uni2char(le16_to_cpu(ins[i]), ns + o,
ns_len - o);
@@ -373,7 +395,7 @@ retry: wc = nls->uni2char(le16_to_cpu(ins[i]), ns + o,
ntfs_error(vol->sb, "Unicode name contains characters that cannot be "
"converted to character set %s. You might want to "
"try to use the mount option iocharset=utf8.",
- nls->charset);
+ nls ? nls->charset : "utf8");
if (ns != *outs)
kfree(ns);
if (wc != -ENAMETOOLONG)
--
2.20.1
Powered by blists - more mailing lists