Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756521Ab3DLMb2 (ORCPT ); Fri, 12 Apr 2013 08:31:28 -0400 Received: from mga11.intel.com ([192.55.52.93]:37038 "EHLO mga11.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755123Ab3DLMam (ORCPT ); Fri, 12 Apr 2013 08:30:42 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.87,462,1363158000"; d="scan'208";a="321404549" From: Andy Shevchenko To: Andrew Morton , linux-kernel@vger.kernel.org Cc: Andy Shevchenko , Samuel Thibault , Greg Kroah-Hartman , Jason Baron , Alexander Viro Subject: [PATCH 1/4] lib/string_helpers: introduce generic string_unescape Date: Fri, 12 Apr 2013 15:30:17 +0300 Message-Id: <1365769820-28953-1-git-send-email-andriy.shevchenko@linux.intel.com> X-Mailer: git-send-email 1.8.2.rc0.22.gb3600c3 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 9711 Lines: 385 There are several places in kernel where modules unescapes input to convert C-Style Escape Sequences into byte codes. The patch provides generic implementation of such approach. Test cases are also included into the patch. Signed-off-by: Andy Shevchenko Cc: Samuel Thibault Cc: Greg Kroah-Hartman Cc: Jason Baron Cc: Alexander Viro --- include/linux/string_helpers.h | 58 ++++++++++++++++++ lib/Kconfig.debug | 3 + lib/Makefile | 4 +- lib/string_helpers.c | 133 +++++++++++++++++++++++++++++++++++++++++ lib/test-string_helpers.c | 103 +++++++++++++++++++++++++++++++ 5 files changed, 300 insertions(+), 1 deletion(-) create mode 100644 lib/test-string_helpers.c diff --git a/include/linux/string_helpers.h b/include/linux/string_helpers.h index a3eb2f6..c18df71 100644 --- a/include/linux/string_helpers.h +++ b/include/linux/string_helpers.h @@ -13,4 +13,62 @@ enum string_size_units { int string_get_size(u64 size, enum string_size_units units, char *buf, int len); +#define UNESCAPE_SPACE 0x01 +#define UNESCAPE_OCTAL 0x02 +#define UNESCAPE_HEX 0x04 +#define UNESCAPE_SPECIAL 0x08 +#define UNESCAPE_ANY \ + (UNESCAPE_SPACE | UNESCAPE_OCTAL | UNESCAPE_HEX | UNESCAPE_SPECIAL) + +/** + * string_unescape - unquote characters in the given string + * @src: source buffer (escaped) + * @dst: destination buffer (unescaped) + * @size: size of the destination buffer (0 to unlimit) + * @flags: combination of the flags (bitwise OR): + * %UNESCAPE_SPACE: + * '\f' - form feed + * '\n' - new line + * '\r' - carriage return + * '\t' - horizontal tab + * '\v' - vertical tab + * %UNESCAPE_OCTAL: + * '\NNN' - byte with octal value NNN (1 to 3 digits) + * %UNESCAPE_HEX: + * '\xHH' - byte with hexadecimal value HH (1 to 2 digits) + * %UNESCAPE_SPECIAL: + * '\"' - double quote + * '\\' - backslash + * '\a' - alert (BEL) + * '\e' - escape + * %UNESCAPE_ANY: + * all previous together + * + * Returns amount of characters processed to the destination buffer excluding + * trailing '\0'. + * + * Due to size of output will be the same or smaller the translation could be + * done in place. + * + * Caller must provide valid source and destination pointers. Be aware that + * destination buffer will always be NULL-terminated. Source string must be + * NULL-terminated as well. + */ +int string_unescape(char *src, char *dst, size_t size, unsigned int flags); + +static inline int string_unescape_inplace(char *buf, unsigned int flags) +{ + return string_unescape(buf, buf, 0, flags); +} + +static inline int string_unescape_any(char *src, char *dst, size_t size) +{ + return string_unescape(src, dst, size, UNESCAPE_ANY); +} + +static inline int string_unescape_any_inplace(char *buf) +{ + return string_unescape_any(buf, buf, 0); +} + #endif diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index ae80518..770a422 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1481,5 +1481,8 @@ source "lib/Kconfig.kgdb" source "lib/Kconfig.kmemcheck" +config TEST_STRING_HELPERS + tristate "Test functions located in the string_helpers module at runtime" + config TEST_KSTRTOX tristate "Test kstrto*() family of functions at runtime" diff --git a/lib/Makefile b/lib/Makefile index 10facc6..370a1d6 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -23,8 +23,10 @@ lib-y += kobject.o klist.o obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \ bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o \ - string_helpers.o gcd.o lcm.o list_sort.o uuid.o flex_array.o \ + gcd.o lcm.o list_sort.o uuid.o flex_array.o \ bsearch.o find_last_bit.o find_next_bit.o llist.o memweight.o kfifo.o +obj-y += string_helpers.o +obj-$(CONFIG_TEST_STRING_HELPERS) += test-string_helpers.o obj-y += kstrtox.o obj-$(CONFIG_TEST_KSTRTOX) += test-kstrtox.o diff --git a/lib/string_helpers.c b/lib/string_helpers.c index 1cffc22..ed5c145 100644 --- a/lib/string_helpers.c +++ b/lib/string_helpers.c @@ -2,10 +2,12 @@ * Helpers for formatting and printing strings * * Copyright 31 August 2008 James Bottomley + * Copyright (C) 2013, Intel Corporation */ #include #include #include +#include #include /** @@ -66,3 +68,134 @@ int string_get_size(u64 size, const enum string_size_units units, return 0; } EXPORT_SYMBOL(string_get_size); + +static bool unescape_space(char **src, char **dst) +{ + char *p = *dst, *q = *src; + + switch (*q) { + case 'n': + *p = '\n'; + break; + case 'r': + *p = '\r'; + break; + case 't': + *p = '\t'; + break; + case 'v': + *p = '\v'; + break; + case 'f': + *p = '\f'; + break; + default: + return false; + } + *dst += 1; + *src += 1; + return true; +} + +static bool unescape_octal(char **src, char **dst) +{ + char *p = *dst, *q = *src; + u8 num; + + if (isodigit(*q) == 0) + return false; + + num = (*q++) & 7; + while (num < 32 && isodigit(*q) && (q - *src < 3)) { + num <<= 3; + num += (*q++) & 7; + } + *p = num; + *dst += 1; + *src = q; + return true; +} + +static bool unescape_hex(char **src, char **dst) +{ + char *p = *dst, *q = *src; + int digit; + u8 num; + + if (*q++ != 'x') + return false; + + num = digit = hex_to_bin(*q++); + if (digit < 0) + return false; + + digit = hex_to_bin(*q); + if (digit >= 0) { + q++; + num = (num << 4) | digit; + } + *p = num; + *dst += 1; + *src = q; + return true; +} + +static bool unescape_special(char **src, char **dst) +{ + char *p = *dst, *q = *src; + + switch (*q) { + case '\"': + *p = '\"'; + break; + case '\\': + *p = '\\'; + break; + case 'a': + *p = '\a'; + break; + case 'e': + *p = '\e'; + break; + default: + return false; + } + *dst += 1; + *src += 1; + return true; +} + +int string_unescape(char *src, char *dst, size_t size, unsigned int flags) +{ + char *out = dst; + + while (*src && --size) { + if (src[0] == '\\' && src[1] != '\0' && size > 1) { + src++; + size--; + + if (flags & UNESCAPE_SPACE && + unescape_space(&src, &out)) + continue; + + if (flags & UNESCAPE_OCTAL && + unescape_octal(&src, &out)) + continue; + + if (flags & UNESCAPE_HEX && + unescape_hex(&src, &out)) + continue; + + if (flags & UNESCAPE_SPECIAL && + unescape_special(&src, &out)) + continue; + + *out++ = '\\'; + } + *out++ = *src++; + } + *out = '\0'; + + return out - dst; +} +EXPORT_SYMBOL(string_unescape); diff --git a/lib/test-string_helpers.c b/lib/test-string_helpers.c new file mode 100644 index 0000000..6ac48de --- /dev/null +++ b/lib/test-string_helpers.c @@ -0,0 +1,103 @@ +/* + * Test cases for lib/string_helpers.c module. + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include + +struct test_string { + const char *in; + const char *out; + unsigned int flags; +}; + +static const struct test_string strings[] __initconst = { + { + .in = "\\f\\ \\n\\r\\t\\v", + .out = "\f\\ \n\r\t\v", + .flags = UNESCAPE_SPACE, + }, + { + .in = "\\40\\1\\387\\0064\\05\\040\\8a\\110\\777", + .out = " \001\00387\0064\005 \\8aH?7", + .flags = UNESCAPE_OCTAL, + }, + { + .in = "\\xv\\xa\\x2c\\xD\\x6f2", + .out = "\\xv\n,\ro2", + .flags = UNESCAPE_HEX, + }, + { + .in = "\\h\\\\\\\"\\a\\e\\", + .out = "\\h\\\"\a\e\\", + .flags = UNESCAPE_SPECIAL, + }, +}; + +static void __init test_string_unescape(unsigned int flags, bool inplace) +{ + char in[256]; + char out_test[256]; + char out_real[256]; + int i, p = 0, q_test = 0, q_real = sizeof(out_real); + + for (i = 0; i < ARRAY_SIZE(strings); i++) { + const char *s = strings[i].in; + int len = strlen(strings[i].in); + + /* Copy string to in buffer */ + memcpy(&in[p], s, len); + p += len; + + /* Copy expected result for given flags */ + if (flags & strings[i].flags) { + s = strings[i].out; + len = strlen(strings[i].out); + } + memcpy(&out_test[q_test], s, len); + q_test += len; + } + in[p++] = '\0'; + + /* Call string_unescape and compare result */ + if (inplace) { + memcpy(out_real, in, p); + if (flags == UNESCAPE_ANY) + q_real = string_unescape_any_inplace(out_real); + else + q_real = string_unescape_inplace(out_real, flags); + } else if (flags == UNESCAPE_ANY) { + q_real = string_unescape_any(in, out_real, q_real); + } else { + q_real = string_unescape(in, out_real, q_real, flags); + } + + if (q_real != q_test || memcmp(out_test, out_real, q_test)) { + pr_warn("Test failed: flags = %u\n", flags); + print_hex_dump(KERN_WARNING, "Input: ", + DUMP_PREFIX_NONE, 16, 1, in, p - 1, true); + print_hex_dump(KERN_WARNING, "Expected: ", + DUMP_PREFIX_NONE, 16, 1, out_test, q_test, true); + print_hex_dump(KERN_WARNING, "Got: ", + DUMP_PREFIX_NONE, 16, 1, out_real, q_real, true); + } +} + +static int __init test_string_helpers_init(void) +{ + unsigned int i; + + pr_info("Running tests...\n"); + for (i = 0; i < UNESCAPE_ANY + 1; i++) + test_string_unescape(i, false); + test_string_unescape(get_random_int() % (UNESCAPE_ANY + 1), true); + + return -EINVAL; +} +module_init(test_string_helpers_init); +MODULE_LICENSE("Dual BSD/GPL"); -- 1.8.2.rc0.22.gb3600c3 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/