[PATCH 8/9] xfs: add xfs_nameops for utf8 and utf8+casefold.
Ben Myers
bpm at sgi.com
Thu Sep 11 15:49:26 CDT 2014
From: Olaf Weber <olaf at sgi.com>
The xfs_utf8_nameops use the nfkdi normalization when comparing filenames,
and are installed if the utf8bit is set in the super block.
The xfs_utf8_ci_nameops use the nfkdicf normalization when comparing
filenames, and are installed if both the utf8bit and the borgbit are set
in the superblock.
Normalized filenames are not stored on disk. Normalization will fail if a
filename is not valid UTF-8, in which case the filename is treated as an
opaque blob.
Signed-off-by: Olaf Weber <olaf at sgi.com>
---
fs/xfs/Makefile | 1 +
fs/xfs/libxfs/xfs_dir2.c | 16 +++-
fs/xfs/xfs_iops.c | 2 +-
fs/xfs/xfs_utf8.c | 242 +++++++++++++++++++++++++++++++++++++++++++++++
fs/xfs/xfs_utf8.h | 25 +++++
5 files changed, 281 insertions(+), 5 deletions(-)
create mode 100644 fs/xfs/xfs_utf8.c
create mode 100644 fs/xfs/xfs_utf8.h
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 0f7b300..5cc10f5 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -88,6 +88,7 @@ xfs-y += xfs_aops.o \
xfs_symlink.o \
xfs_sysfs.o \
xfs_trans.o \
+ xfs_utf8.o \
xfs_xattr.o \
kmem.o \
uuid.o
diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c
index 84e5ca9..651ff94 100644
--- a/fs/xfs/libxfs/xfs_dir2.c
+++ b/fs/xfs/libxfs/xfs_dir2.c
@@ -35,6 +35,7 @@
#include "xfs_error.h"
#include "xfs_trace.h"
#include "xfs_dinode.h"
+#include "xfs_utf8.h"
struct xfs_name xfs_name_dotdot = { (unsigned char *)"..", 2, XFS_DIR3_FT_DIR };
@@ -156,10 +157,17 @@ xfs_da_mount(
(uint)sizeof(xfs_da_node_entry_t);
dageo->magicpct = (dageo->blksize * 37) / 100;
- if (xfs_sb_version_hasasciici(&mp->m_sb))
- mp->m_dirnameops = &xfs_ascii_ci_nameops;
- else
- mp->m_dirnameops = &xfs_default_nameops;
+ if (xfs_sb_version_hasutf8(&mp->m_sb)) {
+ if (xfs_sb_version_hasasciici(&mp->m_sb))
+ mp->m_dirnameops = &xfs_utf8_ci_nameops;
+ else
+ mp->m_dirnameops = &xfs_utf8_nameops;
+ } else {
+ if (xfs_sb_version_hasasciici(&mp->m_sb))
+ mp->m_dirnameops = &xfs_ascii_ci_nameops;
+ else
+ mp->m_dirnameops = &xfs_default_nameops;
+ }
return 0;
}
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index cea3d64..fbfb1bb 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -1257,7 +1257,7 @@ xfs_setup_inode(
break;
case S_IFDIR:
lockdep_set_class(&ip->i_lock.mr_lock, &xfs_dir_ilock_class);
- if (xfs_sb_version_hasasciici(&XFS_M(inode->i_sb)->m_sb))
+ if (xfs_sb_version_hasci(&XFS_M(inode->i_sb)->m_sb))
inode->i_op = &xfs_dir_ci_inode_operations;
else
inode->i_op = &xfs_dir_inode_operations;
diff --git a/fs/xfs/xfs_utf8.c b/fs/xfs/xfs_utf8.c
new file mode 100644
index 0000000..7c18e43
--- /dev/null
+++ b/fs/xfs/xfs_utf8.c
@@ -0,0 +1,242 @@
+/*
+ * Copyright (c) 2014 SGI.
+ * All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_types.h"
+#include "xfs_bit.h"
+#include "xfs_log_format.h"
+#include "xfs_inum.h"
+#include "xfs_trans.h"
+#include "xfs_trans_resv.h"
+#include "xfs_sb.h"
+#include "xfs_ag.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+#include "xfs_dir2.h"
+#include "xfs_mount.h"
+#include "xfs_da_btree.h"
+#include "xfs_format.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_alloc_btree.h"
+#include "xfs_dinode.h"
+#include "xfs_inode.h"
+#include "xfs_inode_item.h"
+#include "xfs_bmap.h"
+#include "xfs_error.h"
+#include "xfs_trace.h"
+#include "xfs_utf8.h"
+#include <support/utf8norm.h>
+
+/*
+ * xfs nameops using nfkdi
+ */
+
+static xfs_dahash_t
+xfs_utf8_hashname(
+ const unsigned char *name,
+ int len)
+{
+ utf8data_t nfkdi;
+ struct utf8cursor u8c;
+ xfs_dahash_t hash;
+ int val;
+
+ nfkdi = utf8nfkdi(utf8version);
+ hash = 0;
+ if (utf8ncursor(&u8c, nfkdi, name, len) < 0)
+ goto blob;
+ while ((val = utf8byte(&u8c)) > 0)
+ hash = val ^ rol32(hash, 7);
+ /* In case of error treat the name as a binary blob. */
+ if (val == 0)
+ return hash;
+blob:
+ return xfs_da_hashname(name, len);
+}
+
+static int
+xfs_utf8_normhash(
+ struct xfs_da_args *args)
+{
+ utf8data_t nfkdi;
+ struct utf8cursor u8c;
+ unsigned char *norm;
+ ssize_t normlen;
+ int c;
+
+ nfkdi = utf8nfkdi(utf8version);
+ /* Failure to normalize is treated as a blob. */
+ if ((normlen = utf8nlen(nfkdi, args->name, args->namelen)) < 0)
+ goto blob;
+ if (utf8ncursor(&u8c, nfkdi, args->name, args->namelen) < 0)
+ goto blob;
+ if (!(norm = kmem_alloc(normlen + 1, KM_NOFS|KM_MAYFAIL)))
+ return -ENOMEM;
+ args->norm = norm;
+ args->normlen = normlen;
+ while ((c = utf8byte(&u8c)) > 0)
+ *norm++ = c;
+ if (c == 0) {
+ *norm = '\0';
+ args->hashval = xfs_da_hashname(args->norm, args->normlen);
+ return 0;
+ }
+ kmem_free(args->norm);
+blob:
+ args->norm = NULL;
+ args->normlen = -1;
+ args->hashval = xfs_da_hashname(args->name, args->namelen);
+ return 0;
+}
+
+static enum xfs_dacmp
+xfs_utf8_compname(
+ struct xfs_da_args *args,
+ const unsigned char *name,
+ int len)
+{
+ utf8data_t nfkdi;
+ struct utf8cursor u8c;
+ const unsigned char *norm;
+ int c;
+
+ ASSERT(args->norm || args->normlen == -1);
+
+ /* Check for an exact match first. */
+ if (args->namelen == len && memcmp(args->name, name, len) == 0)
+ return XFS_CMP_EXACT;
+ /* xfs_utf8_normhash() set args->normlen to -1 for a blob */
+ if (args->normlen < 0)
+ return XFS_CMP_DIFFERENT;
+ nfkdi = utf8nfkdi(utf8version);
+ if (utf8ncursor(&u8c, nfkdi, name, len) < 0)
+ return XFS_CMP_DIFFERENT;
+ norm = args->norm;
+ while ((c = utf8byte(&u8c)) > 0)
+ if (c != *norm++)
+ return XFS_CMP_DIFFERENT;
+ if (c < 0 || *norm != '\0')
+ return XFS_CMP_DIFFERENT;
+ return XFS_CMP_MATCH;
+}
+
+struct xfs_nameops xfs_utf8_nameops = {
+ .hashname = xfs_utf8_hashname,
+ .normhash = xfs_utf8_normhash,
+ .compname = xfs_utf8_compname,
+};
+
+/*
+ * xfs nameops using nfkdicf
+ */
+
+static xfs_dahash_t
+xfs_utf8_ci_hashname(
+ const unsigned char *name,
+ int len)
+{
+ utf8data_t nfkdicf;
+ struct utf8cursor u8c;
+ xfs_dahash_t hash;
+ int val;
+
+ nfkdicf = utf8nfkdicf(utf8version);
+ hash = 0;
+ if (utf8ncursor(&u8c, nfkdicf, name, len) < 0)
+ goto blob;
+ while ((val = utf8byte(&u8c)) > 0)
+ hash = val ^ rol32(hash, 7);
+ /* In case of error treat the name as a binary blob. */
+ if (val == 0)
+ return hash;
+blob:
+ return xfs_da_hashname(name, len);
+}
+
+static int
+xfs_utf8_ci_normhash(
+ struct xfs_da_args *args)
+{
+ utf8data_t nfkdicf;
+ struct utf8cursor u8c;
+ unsigned char *norm;
+ ssize_t normlen;
+ int c;
+
+ nfkdicf = utf8nfkdicf(utf8version);
+ /* Failure to normalize is treated as a blob. */
+ if ((normlen = utf8nlen(nfkdicf, args->name, args->namelen)) < 0)
+ goto blob;
+ if (utf8ncursor(&u8c, nfkdicf, args->name, args->namelen) < 0)
+ goto blob;
+ if (!(norm = kmem_alloc(normlen + 1, KM_NOFS|KM_MAYFAIL)))
+ return -ENOMEM;
+ args->norm = norm;
+ args->normlen = normlen;
+ while ((c = utf8byte(&u8c)) > 0)
+ *norm++ = c;
+ if (c == 0) {
+ *norm = '\0';
+ args->hashval = xfs_da_hashname(args->norm, args->normlen);
+ return 0;
+ }
+ kmem_free(args->norm);
+blob:
+ args->norm = NULL;
+ args->normlen = -1;
+ args->hashval = xfs_da_hashname(args->name, args->namelen);
+ return 0;
+}
+
+static enum xfs_dacmp
+xfs_utf8_ci_compname(
+ struct xfs_da_args *args,
+ const unsigned char *name,
+ int len)
+{
+ utf8data_t nfkdicf;
+ struct utf8cursor u8c;
+ const unsigned char *norm;
+ int c;
+
+ ASSERT(args->norm || args->normlen == -1);
+
+ /* Check for an exact match first. */
+ if (args->namelen == len && memcmp(args->name, name, len) == 0)
+ return XFS_CMP_EXACT;
+ /* xfs_utf8_ci_normhash() set args->normlen to -1 for a blob */
+ if (args->normlen < 0)
+ return XFS_CMP_DIFFERENT;
+ nfkdicf = utf8nfkdicf(utf8version);
+ if (utf8ncursor(&u8c, nfkdicf, name, len) < 0)
+ return XFS_CMP_DIFFERENT;
+ norm = args->norm;
+ while ((c = utf8byte(&u8c)) > 0)
+ if (c != *norm++)
+ return XFS_CMP_DIFFERENT;
+ if (c < 0 || *norm != '\0')
+ return XFS_CMP_DIFFERENT;
+ return XFS_CMP_MATCH;
+}
+
+struct xfs_nameops xfs_utf8_ci_nameops = {
+ .hashname = xfs_utf8_ci_hashname,
+ .normhash = xfs_utf8_ci_normhash,
+ .compname = xfs_utf8_ci_compname,
+};
diff --git a/fs/xfs/xfs_utf8.h b/fs/xfs/xfs_utf8.h
new file mode 100644
index 0000000..97b6a91
--- /dev/null
+++ b/fs/xfs/xfs_utf8.h
@@ -0,0 +1,25 @@
+/*
+ * Copyright (c) 2014 SGI.
+ * All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+
+#ifndef XFS_UTF8_H
+#define XFS_UTF8_H
+
+extern struct xfs_nameops xfs_utf8_nameops;
+extern struct xfs_nameops xfs_utf8_ci_nameops;
+
+#endif /* XFS_UTF8_H */
--
1.7.12.4
More information about the xfs
mailing list