diff options
author | Dr. David Alan Gilbert <linux@treblig.org> | 2023-08-17 01:22:30 +0100 |
---|---|---|
committer | Steve French <stfrench@microsoft.com> | 2023-08-30 08:55:51 -0500 |
commit | 089f7f591348ca3325639f541fa4f78d9540dab5 (patch) | |
tree | c93e2cbef2728217c8789dfbf4cc0acff58386f8 /fs/nls | |
parent | 9e74938954749ecc3e0da63d0e211238ad4b2425 (diff) |
fs/smb: Swing unicode common code from smb->NLS
Swing most of the inline functions and unicode tables into nls
from the copy in smb/server. This is UCS-2 rather than most
of the rest of the code in NLS, but it currently seems like the
best place for it.
The actual unicode.c implementations vary much more between server
and client so they're unmoved.
Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Reviewed-by: Dave Kleikamp <dave.kleikamp@oracle.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
Diffstat (limited to 'fs/nls')
-rw-r--r-- | fs/nls/Kconfig | 8 | ||||
-rw-r--r-- | fs/nls/Makefile | 1 | ||||
-rw-r--r-- | fs/nls/nls_ucs2_utils.c | 146 | ||||
-rw-r--r-- | fs/nls/nls_ucs2_utils.h | 297 |
4 files changed, 452 insertions, 0 deletions
diff --git a/fs/nls/Kconfig b/fs/nls/Kconfig index c7857e36adbb..a0d0e2f7ec83 100644 --- a/fs/nls/Kconfig +++ b/fs/nls/Kconfig @@ -617,4 +617,12 @@ config NLS_UTF8 input/output character sets. Say Y here for the UTF-8 encoding of the Unicode/ISO9646 universal character set. +config NLS_UCS2_UTILS + tristate "NLS UCS-2 UTILS" + help + Set of older UCS-2 conversion utilities and tables used by some + filesystems including SMB/CIFS. This includes upper case conversion + tables. This will automatically be selected when the filesystem + that uses it is selected. + endif # NLS diff --git a/fs/nls/Makefile b/fs/nls/Makefile index ac54db297128..5062c699d041 100644 --- a/fs/nls/Makefile +++ b/fs/nls/Makefile @@ -54,3 +54,4 @@ obj-$(CONFIG_NLS_MAC_INUIT) += mac-inuit.o obj-$(CONFIG_NLS_MAC_ROMANIAN) += mac-romanian.o obj-$(CONFIG_NLS_MAC_ROMAN) += mac-roman.o obj-$(CONFIG_NLS_MAC_TURKISH) += mac-turkish.o +obj-$(CONFIG_NLS_UCS2_UTILS) += nls_ucs2_utils.o diff --git a/fs/nls/nls_ucs2_utils.c b/fs/nls/nls_ucs2_utils.c new file mode 100644 index 000000000000..a69781c54dd8 --- /dev/null +++ b/fs/nls/nls_ucs2_utils.c @@ -0,0 +1,146 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Some of the source code in this file came from fs/cifs/uniupr.h + * Copyright (c) International Business Machines Corp., 2000,2002 + * + * Some of the source code in this file came from fs/cifs/cifs_unicode.c + * + * Copyright (c) International Business Machines Corp., 2000,2009 + * Modified by Steve French (sfrench@us.ibm.com) + * Modified by Namjae Jeon (linkinjeon@kernel.org) + * + */ +#include <linux/fs.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <asm/unaligned.h> +#include "nls_ucs2_utils.h" + +MODULE_LICENSE("GPL"); + +/* + * Latin upper case + */ +signed char NlsUniUpperTable[512] = { + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 000-00f */ + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 010-01f */ + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 020-02f */ + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 030-03f */ + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 040-04f */ + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 050-05f */ + 0, -32, -32, -32, -32, -32, -32, -32, -32, -32, -32, + -32, -32, -32, -32, -32, /* 060-06f */ + -32, -32, -32, -32, -32, -32, -32, -32, -32, -32, + -32, 0, 0, 0, 0, 0, /* 070-07f */ + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 080-08f */ + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 090-09f */ + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 0a0-0af */ + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 0b0-0bf */ + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 0c0-0cf */ + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 0d0-0df */ + -32, -32, -32, -32, -32, -32, -32, -32, -32, -32, + -32, -32, -32, -32, -32, -32, /* 0e0-0ef */ + -32, -32, -32, -32, -32, -32, -32, 0, -32, -32, + -32, -32, -32, -32, -32, 121, /* 0f0-0ff */ + 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, /* 100-10f */ + 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, /* 110-11f */ + 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, /* 120-12f */ + 0, 0, 0, -1, 0, -1, 0, -1, 0, 0, -1, 0, -1, 0, -1, 0, /* 130-13f */ + -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, 0, -1, 0, -1, 0, -1, /* 140-14f */ + 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, /* 150-15f */ + 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, /* 160-16f */ + 0, -1, 0, -1, 0, -1, 0, -1, 0, 0, -1, 0, -1, 0, -1, 0, /* 170-17f */ + 0, 0, 0, -1, 0, -1, 0, 0, -1, 0, 0, 0, -1, 0, 0, 0, /* 180-18f */ + 0, 0, -1, 0, 0, 0, 0, 0, 0, -1, 0, 0, 0, 0, 0, 0, /* 190-19f */ + 0, -1, 0, -1, 0, -1, 0, 0, -1, 0, 0, 0, 0, -1, 0, 0, /* 1a0-1af */ + -1, 0, 0, 0, -1, 0, -1, 0, 0, -1, 0, 0, 0, -1, 0, 0, /* 1b0-1bf */ + 0, 0, 0, 0, 0, -1, -2, 0, -1, -2, 0, -1, -2, 0, -1, 0, /* 1c0-1cf */ + -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, -79, 0, -1, /* 1d0-1df */ + 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, /* 1e0-1ef */ + 0, 0, -1, -2, 0, -1, 0, 0, 0, -1, 0, -1, 0, -1, 0, -1, /* 1f0-1ff */ +}; +EXPORT_SYMBOL_GPL(NlsUniUpperTable); + +/* Upper case range - Greek */ +static signed char UniCaseRangeU03a0[47] = { + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, -38, -37, -37, -37, /* 3a0-3af */ + 0, -32, -32, -32, -32, -32, -32, -32, -32, -32, -32, -32, + -32, -32, -32, -32, /* 3b0-3bf */ + -32, -32, -31, -32, -32, -32, -32, -32, -32, -32, -32, -32, -64, + -63, -63, +}; + +/* Upper case range - Cyrillic */ +static signed char UniCaseRangeU0430[48] = { + -32, -32, -32, -32, -32, -32, -32, -32, -32, -32, -32, -32, + -32, -32, -32, -32, /* 430-43f */ + -32, -32, -32, -32, -32, -32, -32, -32, -32, -32, -32, -32, + -32, -32, -32, -32, /* 440-44f */ + 0, -80, -80, -80, -80, -80, -80, -80, -80, -80, -80, + -80, -80, 0, -80, -80, /* 450-45f */ +}; + +/* Upper case range - Extended cyrillic */ +static signed char UniCaseRangeU0490[61] = { + 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, /* 490-49f */ + 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, /* 4a0-4af */ + 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, /* 4b0-4bf */ + 0, 0, -1, 0, -1, 0, 0, 0, -1, 0, 0, 0, -1, +}; + +/* Upper case range - Extended latin and greek */ +static signed char UniCaseRangeU1e00[509] = { + 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, /* 1e00-1e0f */ + 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, /* 1e10-1e1f */ + 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, /* 1e20-1e2f */ + 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, /* 1e30-1e3f */ + 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, /* 1e40-1e4f */ + 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, /* 1e50-1e5f */ + 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, /* 1e60-1e6f */ + 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, /* 1e70-1e7f */ + 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, /* 1e80-1e8f */ + 0, -1, 0, -1, 0, -1, 0, 0, 0, 0, 0, -59, 0, -1, 0, -1, /* 1e90-1e9f */ + 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, /* 1ea0-1eaf */ + 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, /* 1eb0-1ebf */ + 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, /* 1ec0-1ecf */ + 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, /* 1ed0-1edf */ + 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, /* 1ee0-1eef */ + 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, 0, 0, 0, 0, 0, /* 1ef0-1eff */ + 8, 8, 8, 8, 8, 8, 8, 8, 0, 0, 0, 0, 0, 0, 0, 0, /* 1f00-1f0f */ + 8, 8, 8, 8, 8, 8, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 1f10-1f1f */ + 8, 8, 8, 8, 8, 8, 8, 8, 0, 0, 0, 0, 0, 0, 0, 0, /* 1f20-1f2f */ + 8, 8, 8, 8, 8, 8, 8, 8, 0, 0, 0, 0, 0, 0, 0, 0, /* 1f30-1f3f */ + 8, 8, 8, 8, 8, 8, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 1f40-1f4f */ + 0, 8, 0, 8, 0, 8, 0, 8, 0, 0, 0, 0, 0, 0, 0, 0, /* 1f50-1f5f */ + 8, 8, 8, 8, 8, 8, 8, 8, 0, 0, 0, 0, 0, 0, 0, 0, /* 1f60-1f6f */ + 74, 74, 86, 86, 86, 86, 100, 100, 0, 0, 112, 112, + 126, 126, 0, 0, /* 1f70-1f7f */ + 8, 8, 8, 8, 8, 8, 8, 8, 0, 0, 0, 0, 0, 0, 0, 0, /* 1f80-1f8f */ + 8, 8, 8, 8, 8, 8, 8, 8, 0, 0, 0, 0, 0, 0, 0, 0, /* 1f90-1f9f */ + 8, 8, 8, 8, 8, 8, 8, 8, 0, 0, 0, 0, 0, 0, 0, 0, /* 1fa0-1faf */ + 8, 8, 0, 9, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 1fb0-1fbf */ + 0, 0, 0, 9, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 1fc0-1fcf */ + 8, 8, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 1fd0-1fdf */ + 8, 8, 0, 0, 0, 7, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 1fe0-1fef */ + 0, 0, 0, 9, 0, 0, 0, 0, 0, 0, 0, 0, 0, +}; + +/* Upper case range - Wide latin */ +static signed char UniCaseRangeUff40[27] = { + 0, -32, -32, -32, -32, -32, -32, -32, -32, -32, -32, + -32, -32, -32, -32, -32, /* ff40-ff4f */ + -32, -32, -32, -32, -32, -32, -32, -32, -32, -32, -32, +}; + +/* + * Upper Case Range + */ +const struct UniCaseRange NlsUniUpperRange[] = { + {0x03a0, 0x03ce, UniCaseRangeU03a0}, + {0x0430, 0x045f, UniCaseRangeU0430}, + {0x0490, 0x04cc, UniCaseRangeU0490}, + {0x1e00, 0x1ffc, UniCaseRangeU1e00}, + {0xff40, 0xff5a, UniCaseRangeUff40}, + {0} +}; +EXPORT_SYMBOL_GPL(NlsUniUpperRange); diff --git a/fs/nls/nls_ucs2_utils.h b/fs/nls/nls_ucs2_utils.h new file mode 100644 index 000000000000..3500596ea993 --- /dev/null +++ b/fs/nls/nls_ucs2_utils.h @@ -0,0 +1,297 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Some of the source code in this file came from fs/cifs/cifs_unicode.c + * and then via server/unicode.c + * cifs_unicode: Unicode kernel case support + * + * Function: + * Convert a unicode character to upper or lower case using + * compressed tables. + * + * Copyright (c) International Business Machines Corp., 2000,2009 + * + * + * Notes: + * These APIs are based on the C library functions. The semantics + * should match the C functions but with expanded size operands. + * + * The upper/lower functions are based on a table created by mkupr. + * This is a compressed table of upper and lower case conversion. + * + */ +#ifndef _NLS_UCS2_UTILS_H +#define _NLS_UCS2_UTILS_H + +#include <asm/byteorder.h> +#include <linux/types.h> +#include <linux/nls.h> +#include <linux/unicode.h> + +/* + * Windows maps these to the user defined 16 bit Unicode range since they are + * reserved symbols (along with \ and /), otherwise illegal to store + * in filenames in NTFS + */ +#define UNI_ASTERISK ((__u16)('*' + 0xF000)) +#define UNI_QUESTION ((__u16)('?' + 0xF000)) +#define UNI_COLON ((__u16)(':' + 0xF000)) +#define UNI_GRTRTHAN ((__u16)('>' + 0xF000)) +#define UNI_LESSTHAN ((__u16)('<' + 0xF000)) +#define UNI_PIPE ((__u16)('|' + 0xF000)) +#define UNI_SLASH ((__u16)('\\' + 0xF000)) + +#ifndef UNICASERANGE_DEFINED +struct UniCaseRange { + wchar_t start; + wchar_t end; + signed char *table; +}; +#endif /* UNICASERANGE_DEFINED */ + +#ifndef UNIUPR_NOUPPER +extern signed char NlsUniUpperTable[512]; +extern const struct UniCaseRange NlsUniUpperRange[]; +#endif /* UNIUPR_NOUPPER */ + +/* + * UniStrcat: Concatenate the second string to the first + * + * Returns: + * Address of the first string + */ +static inline wchar_t *UniStrcat(wchar_t *ucs1, const wchar_t *ucs2) +{ + wchar_t *anchor = ucs1; /* save a pointer to start of ucs1 */ + + while (*ucs1++) + /*NULL*/; /* To end of first string */ + ucs1--; /* Return to the null */ + while ((*ucs1++ = *ucs2++)) + /*NULL*/; /* copy string 2 over */ + return anchor; +} + +/* + * UniStrchr: Find a character in a string + * + * Returns: + * Address of first occurrence of character in string + * or NULL if the character is not in the string + */ +static inline wchar_t *UniStrchr(const wchar_t *ucs, wchar_t uc) +{ + while ((*ucs != uc) && *ucs) + ucs++; + + if (*ucs == uc) + return (wchar_t *)ucs; + return NULL; +} + +/* + * UniStrcmp: Compare two strings + * + * Returns: + * < 0: First string is less than second + * = 0: Strings are equal + * > 0: First string is greater than second + */ +static inline int UniStrcmp(const wchar_t *ucs1, const wchar_t *ucs2) +{ + while ((*ucs1 == *ucs2) && *ucs1) { + ucs1++; + ucs2++; + } + return (int)*ucs1 - (int)*ucs2; +} + +/* + * UniStrcpy: Copy a string + */ +static inline wchar_t *UniStrcpy(wchar_t *ucs1, const wchar_t *ucs2) +{ + wchar_t *anchor = ucs1; /* save the start of result string */ + + while ((*ucs1++ = *ucs2++)) + /*NULL*/; + return anchor; +} + +/* + * UniStrlen: Return the length of a string (in 16 bit Unicode chars not bytes) + */ +static inline size_t UniStrlen(const wchar_t *ucs1) +{ + int i = 0; + + while (*ucs1++) + i++; + return i; +} + +/* + * UniStrnlen: Return the length (in 16 bit Unicode chars not bytes) of a + * string (length limited) + */ +static inline size_t UniStrnlen(const wchar_t *ucs1, int maxlen) +{ + int i = 0; + + while (*ucs1++) { + i++; + if (i >= maxlen) + break; + } + return i; +} + +/* + * UniStrncat: Concatenate length limited string + */ +static inline wchar_t *UniStrncat(wchar_t *ucs1, const wchar_t *ucs2, size_t n) +{ + wchar_t *anchor = ucs1; /* save pointer to string 1 */ + + while (*ucs1++) + /*NULL*/; + ucs1--; /* point to null terminator of s1 */ + while (n-- && (*ucs1 = *ucs2)) { /* copy s2 after s1 */ + ucs1++; + ucs2++; + } + *ucs1 = 0; /* Null terminate the result */ + return anchor; +} + +/* + * UniStrncmp: Compare length limited string + */ +static inline int UniStrncmp(const wchar_t *ucs1, const wchar_t *ucs2, size_t n) +{ + if (!n) + return 0; /* Null strings are equal */ + while ((*ucs1 == *ucs2) && *ucs1 && --n) { + ucs1++; + ucs2++; + } + return (int)*ucs1 - (int)*ucs2; +} + +/* + * UniStrncmp_le: Compare length limited string - native to little-endian + */ +static inline int +UniStrncmp_le(const wchar_t *ucs1, const wchar_t *ucs2, size_t n) +{ + if (!n) + return 0; /* Null strings are equal */ + while ((*ucs1 == __le16_to_cpu(*ucs2)) && *ucs1 && --n) { + ucs1++; + ucs2++; + } + return (int)*ucs1 - (int)__le16_to_cpu(*ucs2); +} + +/* + * UniStrncpy: Copy length limited string with pad + */ +static inline wchar_t *UniStrncpy(wchar_t *ucs1, const wchar_t *ucs2, size_t n) +{ + wchar_t *anchor = ucs1; + + while (n-- && *ucs2) /* Copy the strings */ + *ucs1++ = *ucs2++; + + n++; + while (n--) /* Pad with nulls */ + *ucs1++ = 0; + return anchor; +} + +/* + * UniStrncpy_le: Copy length limited string with pad to little-endian + */ +static inline wchar_t *UniStrncpy_le(wchar_t *ucs1, const wchar_t *ucs2, size_t n) +{ + wchar_t *anchor = ucs1; + + while (n-- && *ucs2) /* Copy the strings */ + *ucs1++ = __le16_to_cpu(*ucs2++); + + n++; + while (n--) /* Pad with nulls */ + *ucs1++ = 0; + return anchor; +} + +/* + * UniStrstr: Find a string in a string + * + * Returns: + * Address of first match found + * NULL if no matching string is found + */ +static inline wchar_t *UniStrstr(const wchar_t *ucs1, const wchar_t *ucs2) +{ + const wchar_t *anchor1 = ucs1; + const wchar_t *anchor2 = ucs2; + + while (*ucs1) { + if (*ucs1 == *ucs2) { + /* Partial match found */ + ucs1++; + ucs2++; + } else { + if (!*ucs2) /* Match found */ + return (wchar_t *)anchor1; + ucs1 = ++anchor1; /* No match */ + ucs2 = anchor2; + } + } + + if (!*ucs2) /* Both end together */ + return (wchar_t *)anchor1; /* Match found */ + return NULL; /* No match */ +} + +#ifndef UNIUPR_NOUPPER +/* + * UniToupper: Convert a unicode character to upper case + */ +static inline wchar_t UniToupper(register wchar_t uc) +{ + register const struct UniCaseRange *rp; + + if (uc < sizeof(NlsUniUpperTable)) { + /* Latin characters */ + return uc + NlsUniUpperTable[uc]; /* Use base tables */ + } + + rp = NlsUniUpperRange; /* Use range tables */ + while (rp->start) { + if (uc < rp->start) /* Before start of range */ + return uc; /* Uppercase = input */ + if (uc <= rp->end) /* In range */ + return uc + rp->table[uc - rp->start]; + rp++; /* Try next range */ + } + return uc; /* Past last range */ +} + +/* + * UniStrupr: Upper case a unicode string + */ +static inline __le16 *UniStrupr(register __le16 *upin) +{ + register __le16 *up; + + up = upin; + while (*up) { /* For all characters */ + *up = cpu_to_le16(UniToupper(le16_to_cpu(*up))); + up++; + } + return upin; /* Return input pointer */ +} +#endif /* UNIUPR_NOUPPER */ + +#endif /* _NLS_UCS2_UTILS_H */ |