It does not make any sense to set hsb->nls_io (NLS iocharset used between
VFS and hfs driver) when hsb->nls_disk (NLS codepage used between hfs
driver and disk) is not set.
Reverse engineering driver code shown what is doing in this special case:
When codepage was not defined but iocharset was then
hfs driver copied 8bit character from disk directly to
16bit unicode wchar_t type. Which means it did conversion
from Latin1 (ISO-8859-1) to Unicode because first 256
Unicode code points matches 8bit ISO-8859-1 codepage table.
So when iocharset was specified and codepage not, then
codepage used implicit value "iso8859-1".
So when hsb->nls_disk is not set and hsb->nls_io is then explicitly set
hsb->nls_disk to "iso8859-1".
Such setup is obviously incompatible with Mac OS systems as they do not
support iso8859-1 encoding for hfs. So print warning into dmesg about this
fact.
After this change hsb->nls_disk is always set, so remove code paths for
case when hsb->nls_disk was not set as they are not needed anymore.
Signed-off-by: Pali Rohár <pali@xxxxxxxxxx>
---
fs/hfs/super.c | 31 +++++++++++++++++++++++++++++++
fs/hfs/trans.c | 38 ++++++++++++++------------------------
2 files changed, 45 insertions(+), 24 deletions(-)
diff --git a/fs/hfs/super.c b/fs/hfs/super.c
index 12d9bae39363..86bc46746c7f 100644
--- a/fs/hfs/super.c
+++ b/fs/hfs/super.c
@@ -351,6 +351,37 @@ static int parse_options(char *options, struct hfs_sb_info *hsb)
}
}
+ if (hsb->nls_io && !hsb->nls_disk) {
+ /*
+ * Previous version of hfs driver did something unexpected:
+ * When codepage was not defined but iocharset was then
+ * hfs driver copied 8bit character from disk directly to
+ * 16bit unicode wchar_t type. Which means it did conversion
+ * from Latin1 (ISO-8859-1) to Unicode because first 256
+ * Unicode code points matches 8bit ISO-8859-1 codepage table.
+ * So when iocharset was specified and codepage not, then
+ * codepage used implicit value "iso8859-1".
+ *
+ * To not change this previous default behavior as some users
+ * may depend on it, we load iso8859-1 NLS table explicitly
+ * to simplify code and make it more reable what happens.
+ *
+ * In context of hfs driver it is really strange to use
+ * ISO-8859-1 codepage table for storing data to disk, but
+ * nothing forbids it. Just it is highly incompatible with
+ * Mac OS systems. So via pr_warn() inform user that this
+ * is not probably what he wants.
+ */
+ pr_warn("iocharset was specified but codepage not, "
+ "using default codepage=iso8859-1\n");
+ pr_warn("this default codepage=iso8859-1 is incompatible with "
+ "Mac OS systems and may be changed in the future");
+ hsb->nls_disk = load_nls("iso8859-1");
+ if (!hsb->nls_disk) {
+ pr_err("unable to load iso8859-1 codepage\n");
+ return 0;
+ }
+ }
if (hsb->nls_disk && !hsb->nls_io) {
hsb->nls_io = load_nls_default();
if (!hsb->nls_io) {
diff --git a/fs/hfs/trans.c b/fs/hfs/trans.c
index 39f5e343bf4d..c75682c61b06 100644
--- a/fs/hfs/trans.c
+++ b/fs/hfs/trans.c
@@ -48,18 +48,13 @@ int hfs_mac2asc(struct super_block *sb, char *out, const struct hfs_name *in)
wchar_t ch;
while (srclen > 0) {
- if (nls_disk) {
- size = nls_disk->char2uni(src, srclen, &ch);
- if (size <= 0) {
- ch = '?';
- size = 1;
- }
- src += size;
- srclen -= size;
- } else {
- ch = *src++;
- srclen--;
+ size = nls_disk->char2uni(src, srclen, &ch);
+ if (size <= 0) {
+ ch = '?';
+ size = 1;
}
+ src += size;
+ srclen -= size;
if (ch == '/')
ch = ':';
size = nls_io->uni2char(ch, dst, dstlen);
@@ -119,20 +114,15 @@ void hfs_asc2mac(struct super_block *sb, struct hfs_name *out, const struct qstr
srclen -= size;
if (ch == ':')
ch = '/';
- if (nls_disk) {
- size = nls_disk->uni2char(ch, dst, dstlen);
- if (size < 0) {
- if (size == -ENAMETOOLONG)
- goto out;
- *dst = '?';
- size = 1;
- }
- dst += size;
- dstlen -= size;
- } else {
- *dst++ = ch > 0xff ? '?' : ch;
- dstlen--;
+ size = nls_disk->uni2char(ch, dst, dstlen);
+ if (size < 0) {
+ if (size == -ENAMETOOLONG)
+ goto out;
+ *dst = '?';
+ size = 1;
}
+ dst += size;
+ dstlen -= size;
}
} else {
char ch;
--
2.20.1
