linux-cifs.vger.kernel.org archive mirror
 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>,
	"OGAWA Hirofumi" <hirofumi@mail.parknet.co.jp>,
	"Theodore Y . Ts'o" <tytso@mit.edu>,
	"Luis de Bethencourt" <luisbg@kernel.org>,
	"Salah Triki" <salah.triki@gmail.com>,
	"Andrew Morton" <akpm@linux-foundation.org>,
	"Dave Kleikamp" <shaggy@kernel.org>,
	"Anton Altaparmakov" <anton@tuxera.com>,
	"Pavel Machek" <pavel@ucw.cz>, "Marek Behún" <marek.behun@nic.cz>,
	"Christoph Hellwig" <hch@infradead.org>
Subject: [RFC PATCH 12/20] hfs: Do not use broken utf8 NLS table for iocharset=utf8 mount option
Date: Sun,  8 Aug 2021 18:24:45 +0200	[thread overview]
Message-ID: <20210808162453.1653-13-pali@kernel.org> (raw)
In-Reply-To: <20210808162453.1653-1-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 utf8_to_utf32() and utf32_to_utf8() which implements correct
encoding and decoding between Unicode code points and UTF-8 sequence.

When iochatset=utf8 is used then set hsb->nls_io 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/hfs/super.c | 33 ++++++++++++++++++++++-----------
 fs/hfs/trans.c | 24 ++++++++++++++++++++----
 2 files changed, 42 insertions(+), 15 deletions(-)

diff --git a/fs/hfs/super.c b/fs/hfs/super.c
index 86bc46746c7f..076308df41cf 100644
--- a/fs/hfs/super.c
+++ b/fs/hfs/super.c
@@ -149,10 +149,13 @@ static int hfs_show_options(struct seq_file *seq, struct dentry *root)
 		seq_printf(seq, ",part=%u", sbi->part);
 	if (sbi->session >= 0)
 		seq_printf(seq, ",session=%u", sbi->session);
-	if (sbi->nls_disk)
+	if (sbi->nls_disk) {
 		seq_printf(seq, ",codepage=%s", sbi->nls_disk->charset);
-	if (sbi->nls_io)
-		seq_printf(seq, ",iocharset=%s", sbi->nls_io->charset);
+		if (sbi->nls_io)
+			seq_printf(seq, ",iocharset=%s", sbi->nls_io->charset);
+		else
+			seq_puts(seq, ",iocharset=utf8");
+	}
 	if (sbi->s_quiet)
 		seq_printf(seq, ",quiet");
 	return 0;
@@ -225,6 +228,7 @@ static int parse_options(char *options, struct hfs_sb_info *hsb)
 	char *p;
 	substring_t args[MAX_OPT_ARGS];
 	int tmp, token;
+	int have_iocharset;
 
 	/* initialize the sb with defaults */
 	hsb->s_uid = current_uid();
@@ -239,6 +243,8 @@ static int parse_options(char *options, struct hfs_sb_info *hsb)
 	if (!options)
 		return 1;
 
+	have_iocharset = 0;
+
 	while ((p = strsep(&options, ",")) != NULL) {
 		if (!*p)
 			continue;
@@ -332,18 +338,22 @@ static int parse_options(char *options, struct hfs_sb_info *hsb)
 			kfree(p);
 			break;
 		case opt_iocharset:
-			if (hsb->nls_io) {
+			if (have_iocharset) {
 				pr_err("unable to change iocharset\n");
 				return 0;
 			}
 			p = match_strdup(&args[0]);
-			if (p)
-				hsb->nls_io = load_nls(p);
-			if (!hsb->nls_io) {
-				pr_err("unable to load iocharset \"%s\"\n", p);
-				kfree(p);
+			if (!p)
 				return 0;
+			if (strcmp(p, "utf8") != 0) {
+				hsb->nls_io = load_nls(p);
+				if (!hsb->nls_io) {
+					pr_err("unable to load iocharset \"%s\"\n", p);
+					kfree(p);
+					return 0;
+				}
 			}
+			have_iocharset = 1;
 			kfree(p);
 			break;
 		default:
@@ -351,7 +361,7 @@ static int parse_options(char *options, struct hfs_sb_info *hsb)
 		}
 	}
 
-	if (hsb->nls_io && !hsb->nls_disk) {
+	if (have_iocharset && !hsb->nls_disk) {
 		/*
 		 * Previous version of hfs driver did something unexpected:
 		 * When codepage was not defined but iocharset was then
@@ -382,7 +392,8 @@ static int parse_options(char *options, struct hfs_sb_info *hsb)
 			return 0;
 		}
 	}
-	if (hsb->nls_disk && !hsb->nls_io) {
+	if (hsb->nls_disk &&
+	    !have_iocharset && strcmp(CONFIG_NLS_DEFAULT, "utf8") != 0) {
 		hsb->nls_io = load_nls_default();
 		if (!hsb->nls_io) {
 			pr_err("unable to load default iocharset\n");
diff --git a/fs/hfs/trans.c b/fs/hfs/trans.c
index c75682c61b06..bff8e54003ab 100644
--- a/fs/hfs/trans.c
+++ b/fs/hfs/trans.c
@@ -44,7 +44,7 @@ int hfs_mac2asc(struct super_block *sb, char *out, const struct hfs_name *in)
 		srclen = HFS_NAMELEN;
 	dst = out;
 	dstlen = HFS_MAX_NAMELEN;
-	if (nls_io) {
+	if (nls_disk) {
 		wchar_t ch;
 
 		while (srclen > 0) {
@@ -57,7 +57,12 @@ int hfs_mac2asc(struct super_block *sb, char *out, const struct hfs_name *in)
 			srclen -= size;
 			if (ch == '/')
 				ch = ':';
-			size = nls_io->uni2char(ch, dst, dstlen);
+			if (nls_io)
+				size = nls_io->uni2char(ch, dst, dstlen);
+			else if (dstlen > 0)
+				size = utf32_to_utf8(ch, dst, dstlen);
+			else
+				size = -ENAMETOOLONG;
 			if (size < 0) {
 				if (size == -ENAMETOOLONG)
 					goto out;
@@ -101,11 +106,22 @@ void hfs_asc2mac(struct super_block *sb, struct hfs_name *out, const struct qstr
 	srclen = in->len;
 	dst = out->name;
 	dstlen = HFS_NAMELEN;
-	if (nls_io) {
+	if (nls_disk) {
 		wchar_t ch;
+		unicode_t u;
 
 		while (srclen > 0) {
-			size = nls_io->char2uni(src, srclen, &ch);
+			if (nls_io)
+				size = nls_io->char2uni(src, srclen, &ch);
+			else {
+				size = utf8_to_utf32(str, strlen, &u);
+				if (size >= 0) {
+					if (u <= MAX_WCHAR_T)
+						ch = u;
+					else
+						size = -EINVAL;
+				}
+			}
 			if (size < 0) {
 				ch = '?';
 				size = 1;
-- 
2.20.1


  parent reply	other threads:[~2021-08-08 16:25 UTC|newest]

Thread overview: 50+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-08-08 16:24 [RFC PATCH 00/20] fs: Remove usage of broken nls_utf8 and drop it Pali Rohár
2021-08-08 16:24 ` [RFC PATCH 01/20] fat: Fix iocharset=utf8 mount option Pali Rohár
2021-08-15  3:42   ` OGAWA Hirofumi
2021-08-15  9:42     ` Pali Rohár
2021-08-15 11:23       ` OGAWA Hirofumi
2021-08-23  3:51   ` Kari Argillander
2021-08-08 16:24 ` [RFC PATCH 02/20] hfsplus: Add iocharset= mount option as alias for nls= Pali Rohár
2021-08-09 17:51   ` Viacheslav Dubeyko
2021-08-09 20:49   ` Kari Argillander
2021-08-09 21:25     ` Pali Rohár
2021-08-08 16:24 ` [RFC PATCH 03/20] udf: Fix iocharset=utf8 mount option Pali Rohár
2021-08-12 14:17   ` Jan Kara
2021-08-12 15:51     ` Pali Rohár
2021-08-13 13:48       ` Jan Kara
2021-08-19  8:34         ` Pali Rohár
2021-08-19 10:41           ` Jan Kara
2021-08-08 16:24 ` [RFC PATCH 04/20] isofs: joliet: " Pali Rohár
2021-08-12 14:18   ` Jan Kara
2021-08-08 16:24 ` [RFC PATCH 05/20] ntfs: Undeprecate iocharset= " Pali Rohár
2021-08-09 20:52   ` Kari Argillander
2021-08-19  1:21   ` Kari Argillander
2021-08-19  8:12     ` Pali Rohár
2021-08-19 10:23       ` Kari Argillander
2021-08-19 22:04         ` Pali Rohár
2021-08-19 23:18           ` Kari Argillander
2021-08-08 16:24 ` [RFC PATCH 06/20] ntfs: Fix error processing when load_nls() fails Pali Rohár
2021-08-08 16:24 ` [RFC PATCH 07/20] befs: Fix printing iocharset= mount option Pali Rohár
2021-08-08 16:24 ` [RFC PATCH 08/20] befs: Rename enum value Opt_charset to Opt_iocharset to match " Pali Rohár
2021-08-08 16:24 ` [RFC PATCH 09/20] befs: Fix error processing when load_nls() fails Pali Rohár
2021-08-08 16:24 ` [RFC PATCH 10/20] befs: Allow to use native UTF-8 mode Pali Rohár
2021-08-08 16:24 ` [RFC PATCH 11/20] hfs: Explicitly set hsb->nls_disk when hsb->nls_io is set Pali Rohár
2021-08-09 17:31   ` Viacheslav Dubeyko
2021-08-09 17:37     ` Matthew Wilcox
2021-08-09 17:47       ` Pali Rohár
2021-08-09 20:43         ` Steve French
2021-08-09 18:00       ` Viacheslav Dubeyko
2021-08-08 16:24 ` Pali Rohár [this message]
2021-08-09 17:49   ` [RFC PATCH 12/20] hfs: Do not use broken utf8 NLS table for iocharset=utf8 mount option Viacheslav Dubeyko
2021-08-08 16:24 ` [RFC PATCH 13/20] hfsplus: " Pali Rohár
2021-08-09 17:42   ` Viacheslav Dubeyko
2021-08-08 16:24 ` [RFC PATCH 14/20] jfs: Remove custom iso8859-1 implementation Pali Rohár
2021-08-08 16:24 ` [RFC PATCH 15/20] jfs: Fix buffer overflow in jfs_strfromUCS_le() function Pali Rohár
2021-08-08 16:24 ` [RFC PATCH 16/20] jfs: Do not use broken utf8 NLS table for iocharset=utf8 mount option Pali Rohár
2021-08-08 16:24 ` [RFC PATCH 17/20] ntfs: " Pali Rohár
2021-08-08 16:24 ` [RFC PATCH 18/20] cifs: " Pali Rohár
2021-08-08 16:24 ` [RFC PATCH 19/20] cifs: Remove usage of load_nls_default() calls Pali Rohár
2021-08-08 16:24 ` [RFC PATCH 20/20] nls: Drop broken nls_utf8 module Pali Rohár
2021-09-03 21:26 ` [RFC PATCH 00/20] fs: Remove usage of broken nls_utf8 and drop it Kari Argillander
2021-09-03 21:37   ` Pali Rohár
2021-09-03 22:06     ` Kari Argillander

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=20210808162453.1653-13-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=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=luisbg@kernel.org \
    --cc=marek.behun@nic.cz \
    --cc=pavel@ucw.cz \
    --cc=salah.triki@gmail.com \
    --cc=shaggy@kernel.org \
    --cc=tytso@mit.edu \
    --cc=viro@zeniv.linux.org.uk \
    --subject='Re: [RFC PATCH 12/20] hfs: Do not use broken utf8 NLS table for iocharset=utf8 mount option' \
    /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

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).