转自:http://qing.weibo.com/tag/unserialize
把复杂的数据类型压缩到一个字符串中
serialize() 把变量和它们的值编码成文本形式
unserialize() 恢复原先变量
$stooges = array('Moe','Larry','Curly'); $new = serialize($stooges); print_r($new); echo "<br />"; print_r(unserialize($new)); 结果: a:3:{i:0;s:3:"Moe";i:1;s:5:"Larry";i:2;s:5:"Curly";} Array ( [0] => Moe [1] => Larry [2] => Curly )
当把这些序列化的数据放在URL中在页面之间会传递时,需要对这些数据调用urlencode(),以确保在其中的URL元字符进行处理:
$shopping = array('Poppy seed bagel' => 2,'Plain Bagel' =>1,'Lox' =>4); echo '<a href="next.php?cart='.urlencode(serialize($shopping)).'">next</a>';
如果magic_quotes_gpc项是启用的,那么在URL、POST变量以及cookies中传递的数据在反序列化之前必须用stripslashes()进行处理:
$new_cart = unserialize(stripslashes($cart)); //如果magic_quotes_gpc开启 $new_cart = unserialize($cart);
$fp = fopen('/tmp/cart','w'); fputs($fp,addslashes(serialize($a))); fclose($fp); //如果magic_quotes_runtime开启 $new_cat = unserialize(stripslashes(file_get_contents('/tmp/cart'))); //如果magic_quotes_runtime关闭 $new_cat = unserialize(file_get_contents('/tmp/cart'));
mysql_query("insert into cart(id,data) values(1,'".addslashes(serialize($cart))."')"); $rs = mysql_query('select data from cart where id=1'); $ob = mysql_fetch_object($rs); //如果magic_quotes_runtime开启 $new_cart = unserialize(stripslashes($ob->data)); //如果magic_quotes_runtime关闭 $new_cart = unserialize($ob->data);
<?php //声明一个类 class dog { var $name; var $age; var $owner; function dog($in_name="unnamed",$in_age="0",$in_owner="unknown") { $this->name = $in_name; $this->age = $in_age; $this->owner = $in_owner; } function getage() { return ($this->age * 365); } function getowner() { return ($this->owner); } function getname() { return ($this->name); } } //实例化这个类 $ourfirstdog = new dog("Rover",12,"Lisa and Graham"); //用serialize函数将这个实例转化为一个序列化的字符串 $dogdisc = serialize($ourfirstdog); print $dogdisc; //$ourfirstdog 已经序列化为字符串 O:3:"dog":3:{s:4:"name";s:5:"Rover";s:3:"age";i:12;s:5:"owner";s:15:"Lisa and Graham";} /* ----------------------------------------------------------------------------------------- 在这里你可以将字符串 $dogdisc 存储到任何地方如 session,cookie,数据库,php文件 ----------------------------------------------------------------------------------------- */ //我们在此注销这个类 unset($ourfirstdog); ?> b.php <?php ?> <?php //声明一个类 class dog { var $name; var $age; var $owner; function dog($in_name="unnamed",$in_age="0",$in_owner="unknown") { $this->name = $in_name; $this->age = $in_age; $this->owner = $in_owner; } function getage() { return ($this->age * 365); } function getowner() { return ($this->owner); } function getname() { return ($this->name); } } /*还原操作 */ /* ----------------------------------------------------------------------------------------- 在这里将字符串 $dogdisc 从你存储的地方读出来如 session,cookie,数据库,php文件 ----------------------------------------------------------------------------------------- */ $dogdisc='O:3:"dog":3:{s:4:"name";s:5:"Rover";s:3:"age";i:12;s:5:"owner";s:15:"Lisa and Graham";}'; //我们在这里用 unserialize() 还原已经序列化的对象 $pet = unserialize($dogdisc); //此时的 $pet 已经是前面的 $ourfirstdog 对象了 //获得年龄和名字属性 $old = $pet->getage(); $name = $pet->getname(); //这个类此时无需实例化可以继续使用,而且属性和值都是保持在序列化之前的状态 print "Our first dog is called $name and is $old days old<br>"; ?>
序列化与反序列化语法解析不一致带来的安全隐患
. PHP string serialize() 相关源码分析
------------------------------------
static inline void php_var_serialize_string(smart_str *buf, char *str, int len) /* {{{ */ { smart_str_appendl(buf, "s:", 2); smart_str_append_long(buf, len); smart_str_appendl(buf, ":\"", 2); smart_str_appendl(buf, str, len); smart_str_appendl(buf, "\";", 2); }
$str = 'ryatsyne'; var_dump(serialize($str)); // $str serialized string output // s:8:"ryatsyne";
ii. PHP string unserialize() 相关源码分析
---------------------------------------
unserialize() 函数对 string 的反序列化则分为两种,一种是对 `s:` 格式的序列化 string 进行处理:
switch (yych) { ... case 's': goto yy9; ... yy9: yych = *(YYMARKER = ++YYCURSOR); if (yych == ':') goto yy46; goto yy3; ... yy46: yych = *++YYCURSOR; if (yych == '+') goto yy47; if (yych <= '/') goto yy18; if (yych <= '9') goto yy48; goto yy18; yy47: yych = *++YYCURSOR; if (yych <= '/') goto yy18; if (yych >= ':') goto yy18; yy48: ++YYCURSOR; if ((YYLIMIT - YYCURSOR) < 2) YYFILL(2); yych = *YYCURSOR; if (yych <= '/') goto yy18; if (yych <= '9') goto yy48; if (yych >= ';') goto yy18; yych = *++YYCURSOR; if (yych != '"') goto yy18; ++YYCURSOR; { size_t len, maxlen; char *str; len = parse_uiv(start + 2); maxlen = max - YYCURSOR; if (maxlen < len) { *p = start + 2; return 0; } str = (char*)YYCURSOR; YYCURSOR += len; if (*(YYCURSOR) != '"') { *p = YYCURSOR; return 0; } // 确保格式为 s:x:"x" YYCURSOR += 2; *p = YYCURSOR; // 注意这里,*p 指针直接后移了两位,也就是说没有判断 " 后面是否为 ; INIT_PZVAL(*rval); ZVAL_STRINGL(*rval, str, len, 1); return 1;
static char *unserialize_str(const unsigned char **p, size_t *len, size_t maxlen) { size_t i, j; char *str = safe_emalloc(*len, 1, 1); unsigned char *end = *(unsigned char **)p+maxlen; if (end < *p) { efree(str); return NULL; } for (i = 0; i < *len; i++) { if (*p >= end) { efree(str); return NULL; } if (**p != '\\') { str[i] = (char)**p; } else { unsigned char ch = 0; for (j = 0; j < 2; j++) { (*p)++; if (**p >= '0' && **p <= '9') { ch = (ch << 4) + (**p -'0'); } else if (**p >= 'a' && **p <= 'f') { ch = (ch << 4) + (**p -'a'+10); } else if (**p >= 'A' && **p <= 'F') { ch = (ch << 4) + (**p -'A'+10); } else { efree(str); return NULL; } } str[i] = (char)ch; } (*p)++; } str[i] = 0; *len = i; return str; } // 上面的函数是对 \72\79\61\74\73\79\6e\65 这样十六进制形式字符串进行转换 ... switch (yych) { ... case 'S': goto yy10; // 处理过程与 s: 相同 if ((str = unserialize_str(&YYCURSOR, &len, maxlen)) == NULL) { return 0; } // 处理过程与 s: 相同
$str1 = 's:8:"ryatsyne";'; $str2 = 's:8:"ryatsyne"t'; $str3 = 'S:8:"\72\79\61\74\73\79\6e\65"'; var_dump(unserialize($str)); // $str1, $str2 and $str3 unserialized string output // ryatsyne;
iii. 语法解析处理不一致导致的安全隐患
-----------------------------
从上述分析过程可以看到 PHP 在反序列化 string 时没有严格按照序列化格式 s:x:"x"; 进行处理,没有对 " 后面的是否存在 ; 进行判断,同时增加了对十六进制形式字符串的处理,这样前后处理的不一致让人很费解,同时由于 PHP 手册中对此没有详细的说明,大部分程序员对此处理过程并不了解,这可能导致其在编码过程中出现疏漏,甚至导致严重的安全问题。
回到文章开头提到的 IPB 漏洞上,利用这个 funny feature of PHP 可以很容易的 bypass safeUnserialize() 函数的过滤:)
* mixed safe_unserialize(string $serialized) * Safely unserialize, that is only unserialize string, numbers and arrays, not objects * * @license Public Domain * @author dcz (at) phpbb-seo (dot) com */ static public function safeUnserialize( $serialized ) { // unserialize will return false for object declared with small cap o // as well as if there is any ws between O and : if ( is_string( $serialized ) && strpos( $serialized, "\0" ) === false ) { if ( strpos( $serialized, 'O:' ) === false ) { // the easy case, nothing to worry about // let unserialize do the job return @unserialize( $serialized ); } else if ( ! preg_match('/(^|;|{|})O:[+\-0-9]+:"/', $serialized ) ) { // in case we did have a string with O: in it, // but it was not a true serialized object return @unserialize( $serialized ); } } return false; } // a:1:{s:8:"ryatsyne"tO:8:"ryatsyne":0:{}} // 只要构造类似的序列化字符串就可以轻易突破这里的过滤了