linux-f2fs-devel.lists.sourceforge.net archive mirror
 help / color / mirror / Atom feed
From: Christoph Hellwig <hch@lst.de>
To: Gabriel Krisman Bertazi <krisman@collabora.com>
Cc: linux-fsdevel@vger.kernel.org, linux-ext4@vger.kernel.org,
	Shreeya Patel <shreeya.patel@collabora.com>,
	linux-f2fs-devel@lists.sourceforge.net
Subject: [f2fs-dev] [PATCH 05/11] unicode: pass a UNICODE_AGE() tripple to utf8_load
Date: Wed, 15 Sep 2021 09:00:00 +0200	[thread overview]
Message-ID: <20210915070006.954653-6-hch@lst.de> (raw)
In-Reply-To: <20210915070006.954653-1-hch@lst.de>

Don't bother with pointless string parsing when the caller can just pass
the version in the format that the core expects.  Also remove the
fallback to the latest version that none of the callers actually uses.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/ext4/super.c            | 18 +++++++++-----
 fs/f2fs/super.c            | 18 +++++++++-----
 fs/unicode/utf8-core.c     | 50 ++++----------------------------------
 fs/unicode/utf8-norm.c     | 11 ++-------
 fs/unicode/utf8-selftest.c | 15 ++++++------
 fs/unicode/utf8n.h         | 14 ++---------
 include/linux/unicode.h    | 25 ++++++++++++++++++-
 7 files changed, 65 insertions(+), 86 deletions(-)

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 7401a181878e5..da4e307d7599f 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -2012,9 +2012,9 @@ static const struct mount_opts {
 static const struct ext4_sb_encodings {
 	__u16 magic;
 	char *name;
-	char *version;
+	unsigned int version;
 } ext4_sb_encoding_map[] = {
-	{EXT4_ENC_UTF8_12_1, "utf8", "12.1.0"},
+	{EXT4_ENC_UTF8_12_1, "utf8", UNICODE_AGE(12, 1, 0)},
 };
 
 static const struct ext4_sb_encodings *
@@ -4160,15 +4160,21 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		encoding = utf8_load(encoding_info->version);
 		if (IS_ERR(encoding)) {
 			ext4_msg(sb, KERN_ERR,
-				 "can't mount with superblock charset: %s-%s "
+				 "can't mount with superblock charset: %s-%u.%u.%u "
 				 "not supported by the kernel. flags: 0x%x.",
-				 encoding_info->name, encoding_info->version,
+				 encoding_info->name,
+				 unicode_major(encoding_info->version),
+				 unicode_minor(encoding_info->version),
+				 unicode_rev(encoding_info->version),
 				 encoding_flags);
 			goto failed_mount;
 		}
 		ext4_msg(sb, KERN_INFO,"Using encoding defined by superblock: "
-			 "%s-%s with flags 0x%hx", encoding_info->name,
-			 encoding_info->version?:"\b", encoding_flags);
+			 "%s-%u.%u.%u with flags 0x%hx", encoding_info->name,
+			 unicode_major(encoding_info->version),
+			 unicode_minor(encoding_info->version),
+			 unicode_rev(encoding_info->version),
+			 encoding_flags);
 
 		sb->s_encoding = encoding;
 		sb->s_encoding_flags = encoding_flags;
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 4c457100f18ea..3029f71bf2b74 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -259,9 +259,9 @@ void f2fs_printk(struct f2fs_sb_info *sbi, const char *fmt, ...)
 static const struct f2fs_sb_encodings {
 	__u16 magic;
 	char *name;
-	char *version;
+	unsigned int version;
 } f2fs_sb_encoding_map[] = {
-	{F2FS_ENC_UTF8_12_1, "utf8", "12.1.0"},
+	{F2FS_ENC_UTF8_12_1, "utf8", UNICODE_AGE(12, 1, 0)},
 };
 
 static const struct f2fs_sb_encodings *
@@ -3847,15 +3847,21 @@ static int f2fs_setup_casefold(struct f2fs_sb_info *sbi)
 		encoding = utf8_load(encoding_info->version);
 		if (IS_ERR(encoding)) {
 			f2fs_err(sbi,
-				 "can't mount with superblock charset: %s-%s "
+				 "can't mount with superblock charset: %s-%u.%u.%u "
 				 "not supported by the kernel. flags: 0x%x.",
-				 encoding_info->name, encoding_info->version,
+				 encoding_info->name,
+				 unicode_major(encoding_info->version),
+				 unicode_minor(encoding_info->version),
+				 unicode_rev(encoding_info->version),
 				 encoding_flags);
 			return PTR_ERR(encoding);
 		}
 		f2fs_info(sbi, "Using encoding defined by superblock: "
-			 "%s-%s with flags 0x%hx", encoding_info->name,
-			 encoding_info->version?:"\b", encoding_flags);
+			 "%s-%u.%u.%u with flags 0x%hx", encoding_info->name,
+			 unicode_major(encoding_info->version),
+			 unicode_minor(encoding_info->version),
+			 unicode_rev(encoding_info->version),
+			 encoding_flags);
 
 		sbi->sb->s_encoding = encoding;
 		sbi->sb->s_encoding_flags = encoding_flags;
diff --git a/fs/unicode/utf8-core.c b/fs/unicode/utf8-core.c
index 86f42a078d99b..dca2865c3bee8 100644
--- a/fs/unicode/utf8-core.c
+++ b/fs/unicode/utf8-core.c
@@ -167,59 +167,19 @@ int utf8_normalize(const struct unicode_map *um, const struct qstr *str,
 	}
 	return -EINVAL;
 }
-
 EXPORT_SYMBOL(utf8_normalize);
 
-static int utf8_parse_version(const char *version, unsigned int *maj,
-			      unsigned int *min, unsigned int *rev)
+struct unicode_map *utf8_load(unsigned int version)
 {
-	substring_t args[3];
-	char version_string[12];
-	static const struct match_token token[] = {
-		{1, "%d.%d.%d"},
-		{0, NULL}
-	};
-
-	strncpy(version_string, version, sizeof(version_string));
-
-	if (match_token(version_string, token, args) != 1)
-		return -EINVAL;
-
-	if (match_int(&args[0], maj) || match_int(&args[1], min) ||
-	    match_int(&args[2], rev))
-		return -EINVAL;
+	struct unicode_map *um;
 
-	return 0;
-}
-
-struct unicode_map *utf8_load(const char *version)
-{
-	struct unicode_map *um = NULL;
-	int unicode_version;
-
-	if (version) {
-		unsigned int maj, min, rev;
-
-		if (utf8_parse_version(version, &maj, &min, &rev) < 0)
-			return ERR_PTR(-EINVAL);
-
-		if (!utf8version_is_supported(maj, min, rev))
-			return ERR_PTR(-EINVAL);
-
-		unicode_version = UNICODE_AGE(maj, min, rev);
-	} else {
-		unicode_version = utf8version_latest();
-		printk(KERN_WARNING"UTF-8 version not specified. "
-		       "Assuming latest supported version (%d.%d.%d).",
-		       (unicode_version >> 16) & 0xff,
-		       (unicode_version >> 8) & 0xff,
-		       (unicode_version & 0xff));
-	}
+	if (!utf8version_is_supported(version))
+		return ERR_PTR(-EINVAL);
 
 	um = kzalloc(sizeof(struct unicode_map), GFP_KERNEL);
 	if (!um)
 		return ERR_PTR(-ENOMEM);
-	um->version = unicode_version;
+	um->version = version;
 	return um;
 }
 EXPORT_SYMBOL(utf8_load);
diff --git a/fs/unicode/utf8-norm.c b/fs/unicode/utf8-norm.c
index 1d2d2e5b906ae..12abf89ae6eca 100644
--- a/fs/unicode/utf8-norm.c
+++ b/fs/unicode/utf8-norm.c
@@ -15,13 +15,12 @@ struct utf8data {
 #include "utf8data.h"
 #undef __INCLUDED_FROM_UTF8NORM_C__
 
-int utf8version_is_supported(u8 maj, u8 min, u8 rev)
+int utf8version_is_supported(unsigned int version)
 {
 	int i = ARRAY_SIZE(utf8agetab) - 1;
-	unsigned int sb_utf8version = UNICODE_AGE(maj, min, rev);
 
 	while (i >= 0 && utf8agetab[i] != 0) {
-		if (sb_utf8version == utf8agetab[i])
+		if (version == utf8agetab[i])
 			return 1;
 		i--;
 	}
@@ -29,12 +28,6 @@ int utf8version_is_supported(u8 maj, u8 min, u8 rev)
 }
 EXPORT_SYMBOL(utf8version_is_supported);
 
-int utf8version_latest(void)
-{
-	return utf8vers;
-}
-EXPORT_SYMBOL(utf8version_latest);
-
 /*
  * UTF-8 valid ranges.
  *
diff --git a/fs/unicode/utf8-selftest.c b/fs/unicode/utf8-selftest.c
index 6fe8af7edccbb..37f33890e012f 100644
--- a/fs/unicode/utf8-selftest.c
+++ b/fs/unicode/utf8-selftest.c
@@ -235,7 +235,7 @@ static void check_utf8_nfdicf(void)
 static void check_utf8_comparisons(void)
 {
 	int i;
-	struct unicode_map *table = utf8_load("12.1.0");
+	struct unicode_map *table = utf8_load(UNICODE_AGE(12, 1, 0));
 
 	if (IS_ERR(table)) {
 		pr_err("%s: Unable to load utf8 %d.%d.%d. Skipping.\n",
@@ -269,18 +269,19 @@ static void check_utf8_comparisons(void)
 static void check_supported_versions(void)
 {
 	/* Unicode 7.0.0 should be supported. */
-	test(utf8version_is_supported(7, 0, 0));
+	test(utf8version_is_supported(UNICODE_AGE(7, 0, 0)));
 
 	/* Unicode 9.0.0 should be supported. */
-	test(utf8version_is_supported(9, 0, 0));
+	test(utf8version_is_supported(UNICODE_AGE(9, 0, 0)));
 
 	/* Unicode 1x.0.0 (the latest version) should be supported. */
-	test(utf8version_is_supported(latest_maj, latest_min, latest_rev));
+	test(utf8version_is_supported(
+		UNICODE_AGE(latest_maj, latest_min, latest_rev)));
 
 	/* Next versions don't exist. */
-	test(!utf8version_is_supported(13, 0, 0));
-	test(!utf8version_is_supported(0, 0, 0));
-	test(!utf8version_is_supported(-1, -1, -1));
+	test(!utf8version_is_supported(UNICODE_AGE(13, 0, 0)));
+	test(!utf8version_is_supported(UNICODE_AGE(0, 0, 0)));
+	test(!utf8version_is_supported(UNICODE_AGE(-1, -1, -1)));
 }
 
 static int __init init_test_ucd(void)
diff --git a/fs/unicode/utf8n.h b/fs/unicode/utf8n.h
index 0acd530c2c791..85a7bebf69275 100644
--- a/fs/unicode/utf8n.h
+++ b/fs/unicode/utf8n.h
@@ -11,19 +11,9 @@
 #include <linux/export.h>
 #include <linux/string.h>
 #include <linux/module.h>
+#include <linux/unicode.h>
 
-/* Encoding a unicode version number as a single unsigned int. */
-#define UNICODE_MAJ_SHIFT		(16)
-#define UNICODE_MIN_SHIFT		(8)
-
-#define UNICODE_AGE(MAJ, MIN, REV)			\
-	(((unsigned int)(MAJ) << UNICODE_MAJ_SHIFT) |	\
-	 ((unsigned int)(MIN) << UNICODE_MIN_SHIFT) |	\
-	 ((unsigned int)(REV)))
-
-/* Highest unicode version supported by the data tables. */
-extern int utf8version_is_supported(u8 maj, u8 min, u8 rev);
-extern int utf8version_latest(void);
+int utf8version_is_supported(unsigned int version);
 
 /*
  * Look for the correct const struct utf8data for a unicode version.
diff --git a/include/linux/unicode.h b/include/linux/unicode.h
index 0744f81c4b5fc..77bb915fd1f05 100644
--- a/include/linux/unicode.h
+++ b/include/linux/unicode.h
@@ -5,6 +5,29 @@
 #include <linux/init.h>
 #include <linux/dcache.h>
 
+#define UNICODE_MAJ_SHIFT		16
+#define UNICODE_MIN_SHIFT		8
+
+#define UNICODE_AGE(MAJ, MIN, REV)			\
+	(((unsigned int)(MAJ) << UNICODE_MAJ_SHIFT) |	\
+	 ((unsigned int)(MIN) << UNICODE_MIN_SHIFT) |	\
+	 ((unsigned int)(REV)))
+
+static inline u8 unicode_major(unsigned int age)
+{
+	return (age >> UNICODE_MAJ_SHIFT) & 0xff;
+}
+
+static inline u8 unicode_minor(unsigned int age)
+{
+	return (age >> UNICODE_MIN_SHIFT) & 0xff;
+}
+
+static inline u8 unicode_rev(unsigned int age)
+{
+	return age & 0xff;
+}
+
 struct unicode_map {
 	unsigned int version;
 };
@@ -29,7 +52,7 @@ int utf8_casefold(const struct unicode_map *um, const struct qstr *str,
 int utf8_casefold_hash(const struct unicode_map *um, const void *salt,
 		       struct qstr *str);
 
-struct unicode_map *utf8_load(const char *version);
+struct unicode_map *utf8_load(unsigned int version);
 void utf8_unload(struct unicode_map *um);
 
 #endif /* _LINUX_UNICODE_H */
-- 
2.30.2



_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

  parent reply	other threads:[~2021-09-15  7:04 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-09-15  6:59 [f2fs-dev] unicode cleanups, and split the data table into a separate module v2 Christoph Hellwig
2021-09-15  6:59 ` [f2fs-dev] [PATCH 01/11] ext4: simplify ext4_sb_read_encoding Christoph Hellwig
2021-09-15  6:59 ` [f2fs-dev] [PATCH 02/11] f2fs: simplify f2fs_sb_read_encoding Christoph Hellwig
2021-09-15  6:59 ` [f2fs-dev] [PATCH 03/11] unicode: remove the charset field from struct unicode_map Christoph Hellwig
2021-09-15  6:59 ` [f2fs-dev] [PATCH 04/11] unicode: mark the version field in struct unicode_map unsigned Christoph Hellwig
2021-09-15  7:00 ` Christoph Hellwig [this message]
2021-09-15  7:00 ` [f2fs-dev] [PATCH 06/11] unicode: remove the unused utf8{, n}age{min, max} functions Christoph Hellwig
2021-09-15  7:00 ` [f2fs-dev] [PATCH 07/11] unicode: simplify utf8len Christoph Hellwig
2021-09-15  7:00 ` [f2fs-dev] [PATCH 08/11] unicode: move utf8cursor to utf8-selftest.c Christoph Hellwig
2021-09-15  7:00 ` [f2fs-dev] [PATCH 09/11] unicode: cache the normalization tables in struct unicode_map Christoph Hellwig
2021-09-15  7:00 ` [f2fs-dev] [PATCH 10/11] unicode: Add utf8-data module Christoph Hellwig
2021-10-12 11:25   ` Gabriel Krisman Bertazi
2021-10-12 12:49     ` Christoph Hellwig
2021-10-12 14:40       ` Gabriel Krisman Bertazi
2021-10-26  7:45         ` Christoph Hellwig
2021-10-26 13:56           ` Gabriel Krisman Bertazi
     [not found]             ` <20211027090208.70e88aab@canb.auug.org.au>
2021-10-28  2:00               ` [f2fs-dev] Track unicode tree in linux-next (was Re: [PATCH 10/11] unicode: Add utf8-data module) Gabriel Krisman Bertazi
2021-09-15  7:00 ` [f2fs-dev] [PATCH 11/11] unicode: only export internal symbols for the selftests Christoph Hellwig
  -- strict thread matches above, loose matches on Subject: below --
2021-08-18 14:06 [f2fs-dev] unicode cleanups, and split the data table into a separate module Christoph Hellwig
2021-08-18 14:06 ` [f2fs-dev] [PATCH 05/11] unicode: pass a UNICODE_AGE() tripple to utf8_load Christoph Hellwig
2021-08-23 15:02   ` Gabriel Krisman Bertazi
2021-08-24  7:34     ` Christoph Hellwig
2021-09-06 22:13   ` Gabriel Krisman Bertazi
2021-09-06 22:16     ` Gabriel Krisman Bertazi
2021-09-08  6:19       ` Christoph Hellwig

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=20210915070006.954653-6-hch@lst.de \
    --to=hch@lst.de \
    --cc=krisman@collabora.com \
    --cc=linux-ext4@vger.kernel.org \
    --cc=linux-f2fs-devel@lists.sourceforge.net \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=shreeya.patel@collabora.com \
    /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 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).