public inbox for linux-xfs@vger.kernel.org
 help / color / mirror / Atom feed
From: Ben Myers <bpm@sgi.com>
To: linux-fsdevel@vger.kernel.org
Cc: olaf@sgi.com, xfs@oss.sgi.com
Subject: [PATCH 32/35] xfsprogs: add utf8 support to mkfs.xfs
Date: Fri, 3 Oct 2014 17:15:55 -0500	[thread overview]
Message-ID: <20141003221555.GF1865@sgi.com> (raw)
In-Reply-To: <20141003214758.GY1865@sgi.com>

From: Mark Tinguely <tinguely@sgi.com>

Set the utf-8 feature bit.

Signed-off-by: Mark Tinguely <tinguely@sgi.com>
Signed-off-by: Ben Myers <bpm@sgi.com>

[v2: add support for utf8version. -bpm]
---
 man/man8/mkfs.xfs.8 |  9 ++++-
 mkfs/xfs_mkfs.c     | 98 +++++++++++++++++++++++++++++++++++++++++++++++++++--
 mkfs/xfs_mkfs.h     |  3 +-
 3 files changed, 105 insertions(+), 5 deletions(-)

diff --git a/man/man8/mkfs.xfs.8 b/man/man8/mkfs.xfs.8
index ad9ff3d..aa43cf5 100644
--- a/man/man8/mkfs.xfs.8
+++ b/man/man8/mkfs.xfs.8
@@ -558,7 +558,7 @@ any power of 2 size from the filesystem block size up to 65536.
 .IP
 The
 .B version=ci
-option enables ASCII only case-insensitive filename lookup and version
+option enables ASCII or UTF-8 case-insensitive filename lookup and version
 2 directories. Filenames are case-preserving, that is, the names
 are stored in directories using the case they were created with.
 .IP
@@ -582,6 +582,13 @@ When CRCs are enabled via
 the ftype functionality is always enabled. This feature can not be turned
 off for such filesystem configurations.
 .IP
+.TP
+.BI utf8[= value ]
+This is used to enable the UTF-8 character set support. The
+.I value
+is either 0 or 1, with 1 signifying that UTF-8 character support is to be
+enabled. If the value is omitted, 1 is assumed.
+.IP
 .RE
 .TP
 .BI \-p " protofile"
diff --git a/mkfs/xfs_mkfs.c b/mkfs/xfs_mkfs.c
index c85258a..8cf5f9a 100644
--- a/mkfs/xfs_mkfs.c
+++ b/mkfs/xfs_mkfs.c
@@ -25,6 +25,7 @@
 #include <disk/volume.h>
 #endif
 #include "xfs_mkfs.h"
+#include <xfs/utf8norm.h>
 
 /*
  * Device topology information.
@@ -149,6 +150,8 @@ char	*nopts[] = {
 	"version",
 #define	N_FTYPE		3
 	"ftype",
+#define	N_UTF8		4
+	"utf8",
 	NULL,
 };
 
@@ -958,6 +961,11 @@ main(
 	int			nsflag;
 	int			nvflag;
 	int			nci;
+	unsigned int		utf8;
+	unsigned int		utf8_major;
+	unsigned int		utf8_minor;
+	unsigned int		utf8_revision;
+	char			utf8_version_string[10];
 	int			Nflag;
 	int			discard = 1;
 	char			*p;
@@ -984,6 +992,7 @@ main(
 	int			lazy_sb_counters;
 	int			crcs_enabled;
 	int			finobt;
+	int			ret;
 
 	progname = basename(argv[0]);
 	setlocale(LC_ALL, "");
@@ -1004,6 +1013,7 @@ main(
 	logagno = logblocks = rtblocks = rtextblocks = 0;
 	Nflag = nlflag = nsflag = nvflag = nci = 0;
 	nftype = dirftype = 0;		/* inode type information in the dir */
+	utf8 = 0;			/* utf-8 support */
 	dirblocklog = dirblocksize = 0;
 	dirversion = XFS_DFL_DIR_VERSION;
 	qflag = 0;
@@ -1565,7 +1575,8 @@ _("cannot specify both crc and ftype\n"));
 					if (nvflag)
 						respec('n', nopts, N_VERSION);
 					if (!strcasecmp(value, "ci")) {
-						nci = 1; /* ASCII CI mode */
+						/* ASCII or UTF-8 CI mode */
+						nci = 1;
 					} else {
 						dirversion = atoi(value);
 						if (dirversion != 2)
@@ -1587,6 +1598,62 @@ _("cannot specify both crc and ftype\n"));
 					}
 					nftype = 1;
 					break;
+				case N_UTF8:
+					if (!value || *value == '\0')
+						value = "7.0.0";
+					ret = sscanf(value, "%d.%d.%d",
+							&utf8_major,
+							&utf8_minor,
+							&utf8_revision);
+					if (ret == 3) {
+						utf8 = UNICODE_AGE(
+							utf8_major,
+							utf8_minor,
+							utf8_revision);
+						if (!utf8version_is_supported(
+									utf8)) {
+							fprintf(stderr,
+_("utf8 version %d.%d.%d not supported\n"),
+							utf8_major,
+							utf8_minor,
+							utf8_revision);
+							usage();
+						}
+						break;
+					}
+					ret = sscanf(value, "%d.%d",
+							&utf8_major,
+							&utf8_minor);
+					if (ret == 2) {
+						utf8 = UNICODE_AGE(
+							utf8_major,
+							utf8_minor,
+							0);
+						if (!utf8version_is_supported(
+									utf8)) {
+							fprintf(stderr,
+_("utf8 version %d.%d not supported\n"),
+							utf8_major,
+							utf8_minor);
+							usage();
+						}
+						break;
+					}
+					ret = sscanf(value, "%d", &utf8_major);
+					if (ret == 1) {
+						utf8 = UNICODE_AGE(
+							utf8_major,
+							0, 0);
+						if (!utf8version_is_supported(
+									utf8)) {
+							fprintf(stderr,
+_("utf8 version %d not supported\n"),
+							utf8_major);
+							usage();
+						}
+						break;
+					}
+					/* fallthrough */
 				default:
 					unknown('n', value);
 				}
@@ -2460,7 +2527,8 @@ _("size %s specified for log subvolume is too large, maximum is %lld blocks\n"),
 	 */
 	sbp->sb_features2 = XFS_SB_VERSION2_MKFS(crcs_enabled, lazy_sb_counters,
 					attrversion == 2, !projid16bit, 0,
-					(!crcs_enabled && dirftype));
+					(!crcs_enabled && dirftype),
+					(!crcs_enabled && utf8));
 	sbp->sb_versionnum = XFS_SB_VERSION_MKFS(crcs_enabled, iaflag,
 					dsunit != 0,
 					logversion == 2, attrversion == 1,
@@ -2534,6 +2602,26 @@ _("size %s specified for log subvolume is too large, maximum is %lld blocks\n"),
 	if (crcs_enabled) {
 		sbp->sb_features_incompat = XFS_SB_FEAT_INCOMPAT_FTYPE;
 		dirftype = 1;
+		/* turn on the utf-8 support */
+		if (utf8)
+			sbp->sb_features_incompat |= XFS_SB_FEAT_INCOMPAT_UTF8;
+	}
+	if (utf8) {
+		int	major, minor, revision;
+
+		major = utf8 >> UNICODE_MAJ_SHIFT;
+		minor = (utf8 & 0xff00) >> UNICODE_MIN_SHIFT;
+		revision = utf8 & 0xff;
+
+		if (!revision && !minor)
+			sprintf(utf8_version_string, "%d", major);
+		else if (!revision)
+			sprintf(utf8_version_string, "%d.%d", major, minor);
+		else
+			sprintf(utf8_version_string, "%d.%d.%d",
+						major, minor, revision);
+	} else {
+		strcpy(utf8_version_string, "0");
 	}
 
 	if (!qflag || Nflag) {
@@ -2544,6 +2632,7 @@ _("size %s specified for log subvolume is too large, maximum is %lld blocks\n"),
 		   "data     =%-22s bsize=%-6u blocks=%llu, imaxpct=%u\n"
 		   "         =%-22s sunit=%-6u swidth=%u blks\n"
 		   "naming   =version %-14u bsize=%-6u ascii-ci=%d ftype=%d\n"
+		   "         =%-22s utf8=%s\n"
 		   "log      =%-22s bsize=%-6d blocks=%lld, version=%d\n"
 		   "         =%-22s sectsz=%-5u sunit=%d blks, lazy-count=%d\n"
 		   "realtime =%-22s extsz=%-6d blocks=%lld, rtextents=%lld\n"),
@@ -2553,6 +2642,7 @@ _("size %s specified for log subvolume is too large, maximum is %lld blocks\n"),
 			"", blocksize, (long long)dblocks, imaxpct,
 			"", dsunit, dswidth,
 			dirversion, dirblocksize, nci, dirftype,
+			"", utf8_version_string,
 			logfile, 1 << blocklog, (long long)logblocks,
 			logversion, "", lsectorsize, lsunit, lazy_sb_counters,
 			rtfile, rtextblocks << blocklog,
@@ -2617,6 +2707,7 @@ _("size %s specified for log subvolume is too large, maximum is %lld blocks\n"),
 		sbp->sb_logsectlog = 0;
 		sbp->sb_logsectsize = 0;
 	}
+	sbp->sb_utf8version = utf8;
 
 	if (force_overwrite)
 		zero_old_xfs_structures(&xi, sbp);
@@ -3171,7 +3262,8 @@ usage( void )
 			    sunit=value|su=num,sectlog=n|sectsize=num,\n\
 			    lazy-count=0|1]\n\
 /* label */		[-L label (maximum 12 characters)]\n\
-/* naming */		[-n log=n|size=num,version=2|ci,ftype=0|1]\n\
+/* naming */		[-n log=n|size=num,version=2|ci,ftype=0|1\n\
+			    utf8=0|7]\n\
 /* no-op info only */	[-N]\n\
 /* prototype file */	[-p fname]\n\
 /* quiet */		[-q]\n\
diff --git a/mkfs/xfs_mkfs.h b/mkfs/xfs_mkfs.h
index 9df5f37..f40b284 100644
--- a/mkfs/xfs_mkfs.h
+++ b/mkfs/xfs_mkfs.h
@@ -37,13 +37,14 @@
 	0 ) : XFS_SB_VERSION_1 )
 
 #define XFS_SB_VERSION2_MKFS(crc, lazycount, attr2, projid32bit, parent, \
-			     ftype) (\
+			     ftype, utf8) (\
 	((lazycount) ? XFS_SB_VERSION2_LAZYSBCOUNTBIT : 0) |		\
 	((attr2) ? XFS_SB_VERSION2_ATTR2BIT : 0) |			\
 	((projid32bit) ? XFS_SB_VERSION2_PROJID32BIT : 0) |		\
 	((parent) ? XFS_SB_VERSION2_PARENTBIT : 0) |			\
 	((crc) ? XFS_SB_VERSION2_CRCBIT : 0) |				\
 	((ftype) ? XFS_SB_VERSION2_FTYPE : 0) |				\
+	((utf8) ? XFS_SB_VERSION2_UTF8BIT : 0) |			\
 	0 )
 
 #define	XFS_DFL_BLOCKSIZE_LOG	12		/* 4096 byte blocks */
-- 
1.7.12.4

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs

  parent reply	other threads:[~2014-10-03 22:15 UTC|newest]

Thread overview: 53+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-10-03 21:47 [RFC v3] Unicode/UTF-8 support for XFS Ben Myers
2014-10-03 21:50 ` [PATCH 01/16] lib: add unicode character database files Ben Myers
2014-10-03 21:51 ` [PATCH 02/16] scripts: add trie generator for UTF-8 Ben Myers
2014-10-03 21:54 ` [PATCH 03/16] lib: add supporting code " Ben Myers
2014-10-03 21:54 ` [PATCH 04/16] lib/utf8norm.c: reduce the size of utf8data[] Ben Myers
2014-10-05 21:52   ` Dave Chinner
2014-10-03 21:55 ` [PATCH 05/16] xfs: return the first match during case-insensitive lookup Ben Myers
2014-10-06 22:19   ` Dave Chinner
2014-10-09 15:42     ` Ben Myers
2014-10-09 20:38       ` Dave Chinner
2014-10-14 15:04         ` Ben Myers
2014-10-03 21:56 ` [PATCH 06/16] xfs: rename XFS_CMP_CASE to XFS_CMP_MATCH Ben Myers
2014-10-03 21:58 ` [PATCH 07/16] xfs: add xfs_nameops.normhash Ben Myers
2014-10-03 21:58 ` [PATCH 08/16] xfs: change interface of xfs_nameops.hashname Ben Myers
2014-10-06 22:17   ` Dave Chinner
2014-10-14 15:34     ` Ben Myers
2014-10-03 21:59 ` [PATCH 09/16] xfs: add a superblock feature bit to indicate UTF-8 support Ben Myers
2014-10-06 21:25   ` Dave Chinner
2014-10-09 15:26     ` Ben Myers
2014-10-03 22:00 ` [PATCH 10/16] xfs: store utf8version in the superblock Ben Myers
2014-10-06 21:53   ` Dave Chinner
2014-10-03 22:01 ` [PATCH 11/16] xfs: add xfs_nameops for utf8 and utf8+casefold Ben Myers
2014-10-06 22:10   ` Dave Chinner
2014-10-03 22:03 ` [PATCH 12/16] xfs: apply utf-8 normalization rules to user extended attribute names Ben Myers
2014-10-03 22:03 ` [PATCH 13/16] xfs: implement demand load of utf8norm.ko Ben Myers
2014-10-04  7:16   ` Christoph Hellwig
2014-10-09 15:19     ` Ben Myers
2014-10-03 22:04 ` [PATCH 14/16] xfs: rename XFS_IOC_FSGEOM to XFS_IOC_FSGEOM_V2 Ben Myers
2014-10-06 20:33   ` Dave Chinner
2014-10-06 20:38     ` Ben Myers
2014-10-03 22:05 ` [PATCH 15/16] xfs: xfs_fs_geometry returns a number of bytes to copy Ben Myers
2014-10-06 20:41   ` Dave Chinner
2014-10-03 22:05 ` [PATCH 16/16] xfs: add versioned fsgeom ioctl with utf8version field Ben Myers
2014-10-06 21:13   ` Dave Chinner
2014-10-03 22:06 ` [PATCH 17/35] xfsprogs: add unicode character database files Ben Myers
2014-10-03 22:07 ` [PATCH 18/35] xfsprogs: add trie generator for UTF-8 Ben Myers
2014-10-03 22:07 ` [PATCH 19/35] xfsprogs: add supporting code " Ben Myers
2014-10-03 22:08 ` [PATCH 20/35] xfsprogs: reduce the size of utf8data[] Ben Myers
2014-10-03 22:09 ` [PATCH 21/35] libxfs: return the first match during case-insensitive lookup Ben Myers
2014-10-03 22:09 ` [PATCH 22/35] libxfs: rename XFS_CMP_CASE to XFS_CMP_MATCH Ben Myers
2014-10-03 22:10 ` [PATCH 23/35] libxfs: add xfs_nameops.normhash Ben Myers
2014-10-03 22:11 ` [PATCH 24/35] libxfs: change interface of xfs_nameops.hashname Ben Myers
2014-10-03 22:11 ` [PATCH 25/35] libxfs: add a superblock feature bit to indicate UTF-8 support Ben Myers
2014-10-03 22:12 ` [PATCH 26/35] libxfs: store utf8version in the superblock Ben Myers
2014-10-03 22:13 ` [PATCH 27/35] libxfs: add xfs_nameops for utf8 and utf8+casefold Ben Myers
2014-10-03 22:13 ` [PATCH 28/35] libxfs: apply utf-8 normalization rules to user extended attribute names Ben Myers
2014-10-03 22:14 ` [PATCH 29/35] libxfs: rename XFS_IOC_FSGEOM to XFS_IOC_FSGEOM_V2 Ben Myers
2014-10-03 22:14 ` [PATCH 30/35] libxfs: add versioned fsgeom ioctl with utf8version field Ben Myers
2014-10-03 22:15 ` [PATCH 31/35] xfsprogs: add utf8 support to growfs Ben Myers
2014-10-03 22:15 ` Ben Myers [this message]
2014-10-03 22:16 ` [PATCH 33/35] xfsprogs: add utf8 support to xfs_repair Ben Myers
2014-10-03 22:16 ` [PATCH 34/35] xfsprogs: xfs_db support for sb_utf8version Ben Myers
2014-10-03 22:17 ` [PATCH 35/35] xfsprogs: add a test for utf8 support Ben Myers

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=20141003221555.GF1865@sgi.com \
    --to=bpm@sgi.com \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=olaf@sgi.com \
    --cc=xfs@oss.sgi.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