All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Pali Rohár" <pali@kernel.org>
To: linux-fsdevel@vger.kernel.org,
	linux-ntfs-dev@lists.sourceforge.net, linux-cifs@vger.kernel.org,
	jfs-discussion@lists.sourceforge.net,
	linux-kernel@vger.kernel.org,
	Alexander Viro <viro@zeniv.linux.org.uk>, Jan Kara <jack@suse.cz>,
	"Theodore Y . Ts'o" <tytso@mit.edu>,
	Anton Altaparmakov <anton@tuxera.com>,
	OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>,
	Luis de Bethencourt <luisbg@kernel.org>,
	Salah Triki <salah.triki@gmail.com>,
	Steve French <sfrench@samba.org>, Paulo Alcantara <pc@cjr.nz>,
	Ronnie Sahlberg <lsahlber@redhat.com>,
	Shyam Prasad N <sprasad@microsoft.com>,
	Tom Talpey <tom@talpey.com>, Dave Kleikamp <shaggy@kernel.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	Pavel Machek <pavel@ucw.cz>,
	Christoph Hellwig <hch@infradead.org>,
	Kari Argillander <kari.argillander@gmail.com>,
	Viacheslav Dubeyko <slava@dubeyko.com>
Subject: [RFC PATCH v2 15/18] ntfs: Do not use broken utf8 NLS table for iocharset=utf8 mount option
Date: Mon, 26 Dec 2022 15:21:47 +0100	[thread overview]
Message-ID: <20221226142150.13324-16-pali@kernel.org> (raw)
In-Reply-To: <20221226142150.13324-1-pali@kernel.org>

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@kernel.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


  parent reply	other threads:[~2022-12-26 14:23 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-12-26 14:21 [RFC PATCH v2 00/18] fs: Remove usage of broken nls_utf8 and drop it Pali Rohár
2022-12-26 14:21 ` [RFC PATCH v2 01/18] fat: Fix iocharset=utf8 mount option Pali Rohár
2023-01-10  9:17   ` OGAWA Hirofumi
2023-02-04 10:57     ` Pali Rohár
2023-02-08 10:10       ` OGAWA Hirofumi
2022-12-26 14:21 ` [RFC PATCH v2 02/18] hfsplus: Add iocharset= mount option as alias for nls= Pali Rohár
2022-12-26 14:21 ` [RFC PATCH v2 03/18] ntfs: Undeprecate iocharset= mount option Pali Rohár
2023-01-01 19:02   ` Kari Argillander
2023-01-01 19:06     ` Pali Rohár
2023-01-01 23:02       ` Pali Rohár
2022-12-26 14:21 ` [RFC PATCH v2 04/18] ntfs: Fix error processing when load_nls() fails Pali Rohár
2022-12-26 14:21 ` [RFC PATCH v2 05/18] befs: Fix printing iocharset= mount option Pali Rohár
2022-12-26 14:21 ` [RFC PATCH v2 06/18] befs: Rename enum value Opt_charset to Opt_iocharset to match " Pali Rohár
2022-12-26 14:21 ` [RFC PATCH v2 07/18] befs: Fix error processing when load_nls() fails Pali Rohár
2022-12-26 14:21 ` [RFC PATCH v2 08/18] befs: Allow to use native UTF-8 mode Pali Rohár
2022-12-26 14:21 ` [RFC PATCH v2 09/18] hfs: Explicitly set hsb->nls_disk when hsb->nls_io is set Pali Rohár
2022-12-26 14:21 ` [RFC PATCH v2 10/18] hfs: Do not use broken utf8 NLS table for iocharset=utf8 mount option Pali Rohár
2022-12-26 14:21 ` [RFC PATCH v2 11/18] hfsplus: " Pali Rohár
2022-12-26 14:21 ` [RFC PATCH v2 12/18] jfs: Remove custom iso8859-1 implementation Pali Rohár
2022-12-26 14:21 ` [RFC PATCH v2 13/18] jfs: Fix buffer overflow in jfs_strfromUCS_le() function Pali Rohár
2022-12-26 14:21 ` [RFC PATCH v2 14/18] jfs: Do not use broken utf8 NLS table for iocharset=utf8 mount option Pali Rohár
2022-12-26 14:21 ` Pali Rohár [this message]
2022-12-26 14:21 ` [RFC PATCH v2 16/18] cifs: " Pali Rohár
2022-12-26 14:21 ` [RFC PATCH v2 17/18] cifs: Remove usage of load_nls_default() calls Pali Rohár
2022-12-26 14:21 ` [RFC PATCH v2 18/18] nls: Drop broken nls_utf8 module Pali Rohár

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20221226142150.13324-16-pali@kernel.org \
    --to=pali@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=anton@tuxera.com \
    --cc=hch@infradead.org \
    --cc=hirofumi@mail.parknet.co.jp \
    --cc=jack@suse.cz \
    --cc=jfs-discussion@lists.sourceforge.net \
    --cc=kari.argillander@gmail.com \
    --cc=linux-cifs@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-ntfs-dev@lists.sourceforge.net \
    --cc=lsahlber@redhat.com \
    --cc=luisbg@kernel.org \
    --cc=pavel@ucw.cz \
    --cc=pc@cjr.nz \
    --cc=salah.triki@gmail.com \
    --cc=sfrench@samba.org \
    --cc=shaggy@kernel.org \
    --cc=slava@dubeyko.com \
    --cc=sprasad@microsoft.com \
    --cc=tom@talpey.com \
    --cc=tytso@mit.edu \
    --cc=viro@zeniv.linux.org.uk \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.