All of lore.kernel.org
 help / color / mirror / Atom feed
From: Gabriel Krisman Bertazi <krisman@collabora.co.uk>
To: tytso@mit.edu
Cc: linux-ext4@vger.kernel.org,
	Gabriel Krisman Bertazi <krisman@collabora.co.uk>
Subject: [PATCH v3 07/23] nls: Implement NLS_STRICT_MODE flag
Date: Wed, 17 Oct 2018 16:55:08 -0400	[thread overview]
Message-ID: <20181017205524.23360-8-krisman@collabora.co.uk> (raw)
In-Reply-To: <20181017205524.23360-1-krisman@collabora.co.uk>

The flag NLS_STRICT_MODE indicates whether NLS should reject invalid
characters or ignore them.  Support for this relies on the .validate()
hook, which is implemented by each charset and states whether a given
string is valid within that charset.

Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.co.uk>
---
 fs/nls/nls_core.c   | 11 +++++++++++
 include/linux/nls.h | 25 +++++++++++++++++++++++++
 2 files changed, 36 insertions(+)

diff --git a/fs/nls/nls_core.c b/fs/nls/nls_core.c
index dfd7a5ab4320..493690459b88 100644
--- a/fs/nls/nls_core.c
+++ b/fs/nls/nls_core.c
@@ -20,6 +20,14 @@ extern struct nls_charset default_charset;
 static struct nls_charset *charsets = &default_charset;
 static DEFINE_SPINLOCK(nls_lock);
 
+static int nls_validate_flags(struct nls_table *table, unsigned int flags)
+{
+	if (flags & NLS_STRICT_MODE && !table->ops->validate)
+		return -1;
+
+	return 0;
+}
+
 static struct nls_table *nls_load_table(struct nls_charset *charset,
 					const char *version,
 					unsigned int flags)
@@ -37,6 +45,9 @@ static struct nls_table *nls_load_table(struct nls_charset *charset,
 	if (IS_ERR(tbl))
 		return tbl;
 
+	if (nls_validate_flags(tbl, flags) < 0)
+		return ERR_PTR(-EINVAL);
+
 	tbl->flags = flags;
 	return tbl;
 }
diff --git a/include/linux/nls.h b/include/linux/nls.h
index 91524bb4477b..9f61015a54bf 100644
--- a/include/linux/nls.h
+++ b/include/linux/nls.h
@@ -22,10 +22,22 @@ typedef u16 wchar_t;
 /* Arbitrary Unicode character */
 typedef u32 unicode_t;
 
+struct nls_table;
+
 struct nls_ops {
 	int (*uni2char) (wchar_t uni, unsigned char *out, int boundlen);
 	int (*char2uni) (const unsigned char *rawstring, int boundlen,
 			 wchar_t *uni);
+	/**
+	 * @validate:
+	 *
+	 * Returns 0 if the argument is a valid string in this charset.
+	 * Otherwise, return non-zero.
+	 *
+	 * This is required iff the charset supports strict mode.
+	 **/
+	int (*validate)(const struct nls_table *charset,
+			const unsigned char *str, size_t len);
 };
 
 struct nls_table {
@@ -59,6 +71,13 @@ enum utf16_endian {
 	UTF16_BIG_ENDIAN
 };
 
+#define NLS_STRICT_MODE			0x00000001
+
+static inline int IS_STRICT_MODE(const struct nls_table *charset)
+{
+	return (charset->flags & NLS_STRICT_MODE);
+}
+
 /* nls_base.c */
 extern int __register_nls(struct nls_charset *, struct module *);
 extern int unregister_nls(struct nls_charset *);
@@ -90,6 +109,12 @@ static inline int nls_char2uni(const struct nls_table *table,
 	return table->ops->char2uni(rawstring, boundlen, uni);
 }
 
+static inline int nls_validate(const struct nls_table *t, const unsigned char *str,
+			       const size_t len)
+{
+	return t->ops->validate(t, str, len);
+}
+
 static inline const char *nls_charset_name(const struct nls_table *table)
 {
 	return table->charset->charset;
-- 
2.19.1

  parent reply	other threads:[~2018-10-18  4:53 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-10-17 20:55 [PATCH v3 00/23] Ext4 Encoding and Case-insensitive support Gabriel Krisman Bertazi
2018-10-17 20:55 ` [PATCH v3 01/23] nls: Wrap uni2char/char2uni callers Gabriel Krisman Bertazi
2018-10-17 20:55 ` [PATCH v3 02/23] nls: Wrap charset field access Gabriel Krisman Bertazi
2018-10-17 20:55 ` [PATCH v3 03/23] nls: Wrap charset hooks in ops structure Gabriel Krisman Bertazi
2018-10-17 20:55 ` [PATCH v3 04/23] nls: Split default charset from NLS core Gabriel Krisman Bertazi
2018-10-17 20:55 ` [PATCH v3 05/23] nls: Split struct nls_charset from struct nls_table Gabriel Krisman Bertazi
2018-10-17 20:55 ` [PATCH v3 06/23] nls: Add support for multiple versions of an encoding Gabriel Krisman Bertazi
2018-10-17 20:55 ` Gabriel Krisman Bertazi [this message]
2018-10-17 20:55 ` [PATCH v3 08/23] nls: Let charsets define the behavior of tolower/toupper Gabriel Krisman Bertazi
2018-10-17 20:55 ` [PATCH v3 09/23] nls: Add new interface for string comparisons Gabriel Krisman Bertazi
2018-10-17 20:55 ` [PATCH v3 10/23] nls: Add optional normalization and casefold hooks Gabriel Krisman Bertazi
2018-10-17 20:55 ` [PATCH v3 11/23] nls: ascii: Support validation and normalization operations Gabriel Krisman Bertazi
2018-10-17 20:55 ` [PATCH v3 12/23] nls: utf8n: Add unicode character database files Gabriel Krisman Bertazi
2018-10-17 20:55 ` [PATCH v3 13/23] scripts: add trie generator for UTF-8 Gabriel Krisman Bertazi
2018-10-17 20:55 ` [PATCH v3 14/23] nls: utf8: Move nls-utf8{,-core}.c Gabriel Krisman Bertazi
2018-10-17 20:55 ` [PATCH v3 15/23] nls: utf8: Introduce code for UTF-8 normalization Gabriel Krisman Bertazi
2018-10-17 20:55 ` [PATCH v3 16/23] nls: utf8n: reduce the size of utf8data[] Gabriel Krisman Bertazi
2018-10-17 20:55 ` [PATCH v3 17/23] nls: utf8: Integrate utf8 normalization code with utf8 charset Gabriel Krisman Bertazi
2018-10-17 20:55 ` [PATCH v3 18/23] nls: utf8: Introduce test module for normalized utf8 implementation Gabriel Krisman Bertazi
2018-10-17 20:55 ` [PATCH v3 19/23] ext4: Reserve superblock fields for encoding information Gabriel Krisman Bertazi
2018-10-17 20:55 ` [PATCH v3 20/23] ext4: Include encoding information in the superblock Gabriel Krisman Bertazi
2018-10-17 20:55 ` [PATCH v3 21/23] ext4: Support encoding-aware file name lookups Gabriel Krisman Bertazi
2018-10-17 20:55 ` [PATCH v3 22/23] ext4: Implement EXT4_CASEFOLD_FL flag Gabriel Krisman Bertazi
2018-10-17 20:55 ` [PATCH v3 23/23] docs: ext4.rst: Document encoding and case-insensitive Gabriel Krisman Bertazi

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=20181017205524.23360-8-krisman@collabora.co.uk \
    --to=krisman@collabora.co.uk \
    --cc=linux-ext4@vger.kernel.org \
    --cc=tytso@mit.edu \
    /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.