# modinfo ip_tables
filename: /lib/modules/3.10.0-957.12.2.el7.x86_64/kernel/net/ipv4/netfilter/ip_tables.ko.xz
一、规则的显示
选择先来说明规则的显示,因为他涉及到的东东简单,而且又全面,了解了规则的显示,对于其它操作的了解就显得容易了。
iptables version 1.2.7
iptables有两条线:ipv4 和ipv6,这里只分析v4的,因为v6偶暂时还用不着,没有去看。
iptables_standardone.c
主函数:
int main(int argc, char *argv[])
{
int ret;
char *table = "filter"; /*默认的表是filter*/
iptc_handle_t handle = NULL;
program_name = "iptables";
program_version = IPTABLES_VERSION;
#ifdef NO_SHARED_LIBS
init_extensions();
#endif
/*进入命令行处理函数*/
ret = do_command(argc, argv, &table, &handle);
if (ret)
ret = iptc_commit(&handle);
if (!ret)
fprintf(stderr, "iptables: %s\n",
iptc_strerror(errno));
exit(!ret);
}
table表示表的名称,就是iptables -t 后面跟的那个,默认是"filter"
iptc_handle_t handle = NULL; 这个东东很重要,现在初始化NULL,后面他被用来存储一个表的所有规则的快照。
program_name = "iptables";
program_version = IPTABLES_VERSION;
设置名称和版本。
#ifdef NO_SHARED_LIBS
init_extensions();
#endif
iptables很多东东,是用共享库*.so的形式(我们安装会,可以在诸如/lib/iptables下边看到),如果不采用共享库,则进行一个初始化操作。我们假设是采用共享库的,忽略它。
然后就进入核心处理模块:
do_command(argc, argv, &table, &handle);
do_command 函数是整个系统的核心,负责处理整个用户的输入命令。函数首先对一些结构、变量进行初始化,初始化完毕后,进入while循环,分析用户输入的命令,设置相关的标志变量,然后根据相应标志,调用对应的处理函数。
struct ipt_entry fw, *e = NULL;
int invert = 0;
unsigned int nsaddrs = 0, ndaddrs = 0;
struct in_addr *saddrs = NULL, *daddrs = NULL;
int c, verbose = 0;
const char *chain = NULL;
const char *shostnetworkmask = NULL, *dhostnetworkmask = NULL;
const char *policy = NULL, *newname = NULL;
unsigned int rulenum = 0, options = 0, command = 0;
const char *pcnt = NULL, *bcnt = NULL;
int ret = 1;
struct iptables_match *m;
struct iptables_target *target = NULL;
struct iptables_target *t;
const char *jumpto = "";
char *protocol = NULL;
const char *modprobe = NULL;
/*初始化变量*/
memset(&fw, 0, sizeof(fw));
opts = original_opts;
global_option_offset = 0;
/* re-set optind to 0 in case do_command gets called
* a second time */
optind = 0;
/*初始化两个全局变量*/
/* clear mflags in case do_command gets called a second time
* (we clear the global list of all matches for security)*/
for (m = iptables_matches; m; m = m->next) {
m->mflags = 0;
m->used = 0;
}
for (t = iptables_targets; t; t = t->next) {
t->tflags = 0;
t->used = 0;
}
ps:开头一大堆的变量定义和初始化,可以在程序分析的时候看它们的作用,有两个全局结构变量很重要:iptables_matches和iptables_targets。现在来分析他们的作用会有一点困难,因为它们涉及到了太多方面的东东,这里,可以先把它们“想像成”用户空间用来读取内核规则的结构(当然,这有点错误)。
/*开始化析命令行*/
while ((c = getopt_long(argc, argv,
"-A:C:D:R:I:L::M:F::Z::N:X::E:P:Vh::o:p:s:d:j:i:fbvnt:m:xc:",
opts, NULL)) != -1)
{
}
这个while循环处理所有的用户输入,对应规则输出-L,有:
case 'L':
add_command(&command, CMD_LIST, CMD_ZERO,
invert);
if (optarg) chain = optarg;
else if (optind < argc && argv[optind][0] != '-'
&& argv[optind][0] != '!')
chain = argv[optind++];
break;
add_command函数负责将命令标志变量command与令标志 CMD_LIST求&运算, CMD_ZERO只是一个附加的判断标志而已,invert);然后,从命令行中取得要显示的链名(如果有的话)。
与此相关的还有用t参数指定了表名:
case 't':
if (invert)
exit_error(PARAMETER_PROBLEM,
"unexpected ! flag before --table");
*table = argv[optind-1];
break;
即,如果有’t’参数,则取’t’后跟的表名:*table = argv[optind-1],否则,它应该是主函数中默认的filter表。
命令处理完毕后,即进入执行模块:
/*因为程序定义了共享库的话,iptables_matches/iptables_target这两个结构运行至此是NULL,并且target也是NULL,对于规则显示而言,这一部份的处理目前没有实际意义,回过头再来看这一段更易理解。final_check成员函数的作用是作最终的标志检查,如果检测失则,则退出*/
for (m = iptables_matches; m; m = m->next) {
if (!m->used)
continue;
m->final_check(m->mflags);
}
if (target)
target->final_check(target->tflags);
接着对参数作一些必要的合法性检查:
/* Fix me: must put inverse options checking here --MN */
if (optind < argc)
exit_error(PARAMETER_PROBLEM,
"unknown arguments found on commandline");
if (!command)
exit_error(PARAMETER_PROBLEM, "no command specified");
if (invert)
exit_error(PARAMETER_PROBLEM,
"nothing appropriate following !");
/*对于如果要进行(CMD_REPLACE | CMD_INSERT | CMD_DELETE | CMD_APPEND)处理来说,如果没有设置来源/目的地址及掩码,则给予它们一个默认值*/
if (command & (CMD_REPLACE | CMD_INSERT | CMD_DELETE | CMD_APPEND)) {
if (!(options & OPT_DESTINATION))
dhostnetworkmask = "0.0.0.0/0";
if (!(options & OPT_SOURCE))
shostnetworkmask = "0.0.0.0/0";
}
/*对来源/目的地址及掩码进行拆分,它们总是以 addr/mask的形式来出现的,根据’/’前面的字符串取得地址值,根据’/’后面的掩码位数,求得正确的掩码值,值得注意的是,同时要处理主机地址和网络地址的情况*/
if (shostnetworkmask)
parse_hostnetworkmask(shostnetworkmask, &saddrs,
&(fw.ip.smsk), &nsaddrs);
if (dhostnetworkmask)
parse_hostnetworkmask(dhostnetworkmask, &daddrs,
&(fw.ip.dmsk), &ndaddrs);
/*然后检查来源/目的网络地址的合法性*/
if ((nsaddrs > 1 || ndaddrs > 1) &&
(fw.ip.invflags & (IPT_INV_SRCIP | IPT_INV_DSTIP)))
exit_error(PARAMETER_PROBLEM, "! not allowed with multiple"
" source or destination IP addresses");
/*对命令行格式进行合法性检查*/
generic_opt_check(command, options);
如果前面只是热身的话,那么从现在开始,就进入实质性阶段了:
do_command函数最后一个参数handle,是一个指向了具体表,如filter、nat表的句柄,这里判断,如果handle为空,则调用iptc_init,根据table的名称,让handle指针指向相应的表的地址空间,也就是把对应表的所有信息从内核中取出来:
/* only allocate handle if we weren't called with a handle */
if (!*handle)
*handle = iptc_init(*table);
/*如果获取换败,将试着插入模块,再次获取*/
if (!*handle) {
/* try to insmod the module if iptc_init failed */
iptables_insmod("ip_tables", modprobe);
*handle = iptc_init(*table);
/*仍然失败,则退出*/
if (!*handle)
exit_error(VERSION_PROBLEM,
"can't initialize iptables table `%s': %s",
*table, iptc_strerror(errno));
/*继续进行一些简单的判断*/
if (command == CMD_APPEND
|| command == CMD_DELETE
|| command == CMD_INSERT
|| command == CMD_REPLACE) {
/*List命令不在判断之列,暂时不分析*/
}
/*判断命令标志,调用相关函数进行处理*/
switch (command) {
case CMD_LIST:
ret = list_entries(chain,
options&OPT_VERBOSE,
options&OPT_NUMERIC,
options&OPT_EXPANDED,
options&OPT_LINENUMBERS,
handle);
}
list_entries是规则显示的主要处理函数。
Options是显示的标志变量:
OPT_VERBOSE:对应-v
OPT_NUMERIC:对应-n
OPT_EXPANDED:对应-x
OPT_LINENUMBERS: -l
看来很简单,说了这么大一圈子,就是调用 iptc_init获取表的规则信息,调用list_entries函数显示规则。
1.1 表的查找
再回到iptc_init 函数上来,它根据表名,从内核获取对应的表的相关信息,handle是一个iptc_handle_t类型的指针,在libiptc.c中,有如下定义:
/* Transparent handle type. */
typedef struct iptc_handle *iptc_handle_t;
在Libip4tc中:
#define STRUCT_TC_HANDLE struct iptc_handle
在Libiptc.c中,可以找到STRUCT_TC_HANDLE的定义:
STRUCT_TC_HANDLE
{
/* Have changes been made? */
int changed;
/* Size in here reflects original state. */
STRUCT_GETINFO info;
struct counter_map *counter_map;
/* Array of hook names */
const char **hooknames;
/* Cached position of chain heads (NULL = no cache). */
unsigned int cache_num_chains;
unsigned int cache_num_builtins;
/* Rule iterator: terminal rule */
STRUCT_ENTRY *cache_rule_end;
/* Number in here reflects current state. */
unsigned int new_number;
STRUCT_GET_ENTRIES entries;
};
再来看看iptc_init函数,同样在在Libip4tc中,有如下定义:
#define TC_INIT iptc_init
在Libiptc.c中,可以看到函数的实现,基本上iptables与内核的交互,都是使用setsockopt函数来实现的,对于获取取规是信息来说,标志位是SO_GET_INFO,而从内核返回回来的规则信息是一个STRUCT_GETINFO结构:
TC_HANDLE_T TC_INIT(const char *tablename)
{
TC_HANDLE_T h;
STRUCT_GETINFO info;
unsigned int i;
int tmp;
socklen_t s;
iptc_fn = TC_INIT;
if (sockfd != -1)
close(sockfd);
/*为获取信息打开一个套接字接口*/
sockfd = socket(TC_AF, SOCK_RAW, IPPROTO_RAW);
if (sockfd < 0)
return NULL;
s = sizeof(info);
if (strlen(tablename) >= TABLE_MAXNAMELEN) {
errno = EINVAL;
return NULL;
}
strcpy(info.name, tablename);
/*获取规则信息*/
if (getsockopt(sockfd, TC_IPPROTO, SO_GET_INFO, &info, &s) < 0)
return NULL;
if ((h = alloc_handle(info.name, info.size, info.num_entries))
== NULL)
return NULL;
/* Too hard --RR */
#if 0
sprintf(pathname, "%s/%s", IPT_LIB_DIR, info.name);
dynlib = dlopen(pathname, RTLD_NOW);
if (!dynlib) {
errno = ENOENT;
return NULL;
}
h->hooknames = dlsym(dynlib, "hooknames");
if (!h->hooknames) {
errno = ENOENT;
return NULL;
}
#else
h->hooknames = hooknames;
#endif
/* Initialize current state */
h->info = info;
h->new_number = h->info.num_entries;
for (i = 0; i < h->info.num_entries; i++)
h->counter_map[i]
= ((struct counter_map){COUNTER_MAP_NORMAL_MAP, i});
h->entries.size = h->info.size;
tmp = sizeof(STRUCT_GET_ENTRIES) + h->info.size;
if (getsockopt(sockfd, TC_IPPROTO, SO_GET_ENTRIES, &h->entries,
&tmp) < 0) {
free(h);
return NULL;
}
CHECK(h);
return h;
}
函数为h分配空间,然后赋予相应的值。要理解这个函数,还需要了解STRUCT_GETINFO结构和分配内存空间的函数alloc_handle。
#define STRUCT_GETINFO struct ipt_getinfo
/* The argument to IPT_SO_GET_INFO */
struct ipt_getinfo
{
/* Which table: caller fills this in. */
char name[IPT_TABLE_MAXNAMELEN];
/* Kernel fills these in. */
/* Which hook entry points are valid: bitmask */
unsigned int valid_hooks;
/* Hook entry points: one per netfilter hook. */
unsigned int hook_entry[NF_IP_NUMHOOKS];
/* Underflow points. */
unsigned int underflow[NF_IP_NUMHOOKS];
/* Number of entries */
unsigned int num_entries;
/* Size of entries. */
unsigned int size;
};
/* Allocate handle of given size */
static TC_HANDLE_T
alloc_handle(const char *tablename, unsigned int size, unsigned int num_rules)
{
size_t len;
TC_HANDLE_T h;
len = sizeof(STRUCT_TC_HANDLE)
+ size
+ num_rules * sizeof(struct counter_map);
if ((h = malloc(len)) == NULL) {
errno = ENOMEM;
return NULL;
}
h->changed = 0;
h->cache_num_chains = 0;
h->cache_chain_heads = NULL;
h->counter_map = (void *)h
+ sizeof(STRUCT_TC_HANDLE)
+ size;
strcpy(h->info.name, tablename);
strcpy(h->entries.name, tablename);
return h;
}
函数list_entries用于显示表下边的链:
/*显示某table下的chain*/
static int
list_entries(const ipt_chainlabel chain, int verbose, int numeric,
int expanded, int linenumbers, iptc_handle_t *handle)
{
int found = 0;
unsigned int format;
const char *this;
format = FMT_OPTIONS; /*设置输出格式*/
if (!verbose) /*详细输出模式,,对应-v ,显示匹配的包的数目,包的大小等*/
format |= FMT_NOCOUNTS;
else
format |= FMT_VIA;
if (numeric) /*对应-n,以数字的形式输出地址和端口*/
format |= FMT_NUMERIC;
if (!expanded) /*对应-x,expand numbers (display exact values)*/
format |= FMT_KILOMEGAGIGA;
if (linenumbers) /*输出行的编号*/
format |= FMT_LINENUMBERS;
for (this = iptc_first_chain(handle); /*遍历当前table的所有chain*/
this;
this = iptc_next_chain(handle))
{
const struct ipt_entry *i;
unsigned int num;
if (chain && strcmp(chain, this) != 0) /*匹配指定chain名,这里用chain &&,即若不指定chain,输出所有chain*/
continue;
if (found) printf("\n");
print_header(format, this, handle); /*输出标头*/
i = iptc_first_rule(this, handle); /*移至当前chain的第一条规则*/
num = 0;
while (i) {
print_firewall(i, /*输出当前规则*/
iptc_get_target(i, handle),
num++,
format,
*handle);
i = iptc_next_rule(i, handle); /*移至下一条规则*/
}
found = 1;
}
errno = ENOENT;
return found;
}
可见,在函数中,由iptc_first_chain和iptc_next_chain实现了遍历,iptc_first_rule和iptc_next_rule实现了链中规是的遍历,print_firewall函数在遍历到规则的时候,向终端输出防火墙规则,其第二个参数iptc_get_target又用于获取规则的target。
前面提到过,在内核中,handler指针指向了从内核中返回的对应的表的信息,handler对应的结构中,涉及到链的结构成员主要有两个:
struct chain_cache *cache_chain_heads;
struct chain_cache *cache_chain_iteration;
前者用于指向第一个链,后者指向当前链。而struct chain_cache的定义如下:
struct chain_cache
{
char name[TABLE_MAXNAMELEN]; /*链名*/
STRUCT_ENTRY *start; /*该链的第一条规则*/
STRUCT_ENTRY *end; /*该链的最后一条规则*/
};
理解了这两个成员,和结构struct chain_cache,再来理解链的遍历函数就不难了。所谓链的遍历,就是将handler对应成员的值取出来。
#define TC_FIRST_CHAIN iptc_first_chain
#define TC_NEXT_CHAIN iptc_next_chain
函数TC_FIRST_CHAIN用于返回第一个链:
/* Iterator functions to run through the chains. */
const char *
TC_FIRST_CHAIN(TC_HANDLE_T *handle)
{
/*链首为空,则返回NULL*/
if ((*handle)->cache_chain_heads == NULL
&& !populate_cache(*handle))
return NULL;
/*当前链的指针指向链表首部*/
(*handle)->cache_chain_iteration
= &(*handle)->cache_chain_heads[0];
/*返回链的名称*/
return (*handle)->cache_chain_iteration->name;
}
/* Iterator functions to run through the chains. Returns NULL at end. */
const char *
TC_NEXT_CHAIN(TC_HANDLE_T *handle)
{
/*很简单,用heads开始,用++就可以实现遍历了*/
(*handle)->cache_chain_iteration++;
if ((*handle)->cache_chain_iteration - (*handle)->cache_chain_heads
== (*handle)->cache_num_chains)
return NULL;
return (*handle)->cache_chain_iteration->name;
}
规则的遍历
当遍历到某个链的时候,接下来,就需要遍历当前链下的所有规则了,输出之了。前面叙述了链的遍历,那么规则的遍历,应该就是根据链的名称,找到对应的成员结构struct chain_cache ,这里面包含了当前链的第一条规则与最后一条规则的指针:
#define TC_FIRST_RULE iptc_first_rule
#define TC_NEXT_RULE iptc_next_rule
/* Get first rule in the given chain: NULL for empty chain. */
const STRUCT_ENTRY *
TC_FIRST_RULE(const char *chain, TC_HANDLE_T *handle)
{
struct chain_cache *c;
c = find_label(chain, *handle); /*根据链名,返回对应的struct chain_cache结构*/
if (!c) { /*没有找到,返回NULL*/
errno = ENOENT;
return NULL;
}
/* Empty chain: single return/policy rule */
if (c->start == c->end) /*如果是空链*/
return NULL;
(*handle)->cache_rule_end = c->end;
return c->start; /*返回链的首条规则*/
}
/* Returns NULL when rules run out. */
const STRUCT_ENTRY *
TC_NEXT_RULE(const STRUCT_ENTRY *prev, TC_HANDLE_T *handle)
{
if ((void *)prev + prev->next_offset
== (void *)(*handle)->cache_rule_end)
return NULL;
return (void *)prev + prev->next_offset;
}
要更解TC_NEXT_RULE函数是如何实现查找下一条规则的,需要首先理解STRUCT_ENTRY结构:
#define STRUCT_ENTRY struct ipt_entry
ipt_entry结构用于存储链的规则,每一个包过滤规则可以分成两部份:条件和动作。前者在Netfilter中,称为match,后者称之为target。Match又分为两部份,一部份为一些基本的元素,如来源/目的地址,进/出网口,协议等,对应了struct ipt_ip,我们常常将其称为标准的match,另一部份match则以插件的形式存在,是动态可选择,也允许第三方开发的,常常称为扩展的match,如字符串匹配,p2p匹配等。同样,规则的target也是可扩展的。这样,一条规则占用的空间,可以分为:struct ipt_ip+n*match+n*target,(n表示了其个数,这里的match指的是可扩展的match部份)。基于此,规则对应的结构如下:
/* This structure defines each of the firewall rules. Consists of 3
parts which are 1) general IP header stuff 2) match specific
stuff 3) the target to perform if the rule matches */
struct ipt_entry
{
struct ipt_ip ip; /*标准的match部份*/
/* Mark with fields that we care about. */
unsigned int nfcache;
/* Size of ipt_entry + matches */
u_int16_t target_offset; /*target的开始位置,是sizeof(ipt_entry+n*match)*/
/* Size of ipt_entry + matches + target */
u_int16_t next_offset; /*下一条规则相对于本条规则的位置,是sizeof(ipt_entry)加上所有的match,以及所有的target*/
/* Back pointer */
unsigned int comefrom;
/* Packet and byte counters. */
struct ipt_counters counters;
/* The matches (if any), then the target. */
unsigned char elems[0];
};
有了这样的基础,就不难理解遍历规则中,寻找下一条规则语句:
return (void *)prev + prev->next_offset;
即是本条规则加上下一条规则的偏移值。
输出规则
print_firewall 函数用于规则的输出:
print_firewall(i, iptc_get_target(i, handle), num++,format,*handle);
i:当前的规则;
iptc_get_target(i, handle):用于规则的target部份的处理;
num:规则序号;
format:输出格式;
handler:表的信息;
/* e is called `fw' here for hysterical raisins */
static void
print_firewall(const struct ipt_entry *fw,
const char *targname,
unsigned int num,
unsigned int format,
const iptc_handle_t handle)
{
struct iptables_target *target = NULL;
const struct ipt_entry_target *t;
u_int8_t flags;
char buf[BUFSIZ];
if (!iptc_is_chain(targname, handle))
target = find_target(targname, TRY_LOAD);
else
target = find_target(IPT_STANDARD_TARGET, LOAD_MUST_SUCCEED);
t = ipt_get_target((struct ipt_entry *)fw);
flags = fw->ip.flags;
if (format & FMT_LINENUMBERS) /*输出行号*/
printf(FMT("%-4u ", "%u "), num+1);
if (!(format & FMT_NOCOUNTS)) { /*详细模式,列出计数器*/
print_num(fw->counters.pcnt, format); /*匹配当前规则的数据包个数*/
print_num(fw->counters.bcnt, format); /*--------------------大小*/
}
/*输出目标名称*/
if (!(format & FMT_NOTARGET)) /*目标名称,即拦截、通过等动作*/
printf(FMT("%-9s ", "%s "), targname);
/*输出协议名*/
fputc(fw->ip.invflags & IPT_INV_PROTO ? '!' : ' ', stdout);
{
char *pname = proto_to_name(fw->ip.proto, format&FMT_NUMERIC);
if (pname)
printf(FMT("%-5s", "%s "), pname);
else
printf(FMT("%-5hu", "%hu "), fw->ip.proto);
}
/*输出选项字段*/
if (format & FMT_OPTIONS) {
if (format & FMT_NOTABLE)
fputs("opt ", stdout);
fputc(fw->ip.invflags & IPT_INV_FRAG ? '!' : '-', stdout); //#define IP_FW_INV_FRAG 0x0080 /* Invert the sense of IP_FW_F_FRAG. */
fputc(flags & IPT_F_FRAG ? 'f' : '-', stdout); //#define IP_FW_F_FRAG 0x0004 /* Set if rule is a fragment rule */
fputc(' ', stdout);
}
if (format & FMT_VIA) {
char iface[IFNAMSIZ+2];
if (fw->ip.invflags & IPT_INV_VIA_IN) { /*输入端口取反标志*/
iface[0] = '!'; /*设置取反标志符*/
iface[1] = '\0';
}
else iface[0] = '\0';
if (fw->ip.iniface[0] != '\0') {
strcat(iface, fw->ip.iniface);
}
else if (format & FMT_NUMERIC) strcat(iface, "*");
else strcat(iface, "any");
printf(FMT(" %-6s ","in %s "), iface); /*输出输入端口*/
if (fw->ip.invflags & IPT_INV_VIA_OUT) { /*输出端口取反标志*/
iface[0] = '!'; /*设置取反标志符*/
iface[1] = '\0';
}
else iface[0] = '\0';
if (fw->ip.outiface[0] != '\0') {
strcat(iface, fw->ip.outiface);
}
else if (format & FMT_NUMERIC) strcat(iface, "*");
else strcat(iface, "any");
printf(FMT("%-6s ","out %s "), iface); /*输出输出端口*/
} /*end print in/out interface */
/*输出源地址及掩码*/
fputc(fw->ip.invflags & IPT_INV_SRCIP ? '!' : ' ', stdout); /*源地址取反标志*/
if (fw->ip.smsk.s_addr == 0L && !(format & FMT_NUMERIC)) /*源地址为任意*/
printf(FMT("%-19s ","%s "), "anywhere");
else {
if (format & FMT_NUMERIC)
sprintf(buf, "%s", addr_to_dotted(&(fw->ip.src)));
else
sprintf(buf, "%s", addr_to_anyname(&(fw->ip.src)));
strcat(buf, mask_to_dotted(&(fw->ip.smsk)));
printf(FMT("%-19s ","%s "), buf);
}
/*输出目的地址及掩码*/
fputc(fw->ip.invflags & IPT_INV_DSTIP ? '!' : ' ', stdout);
if (fw->ip.dmsk.s_addr == 0L && !(format & FMT_NUMERIC))
printf(FMT("%-19s","-> %s"), "anywhere");
else {
if (format & FMT_NUMERIC)
sprintf(buf, "%s", addr_to_dotted(&(fw->ip.dst)));
else
sprintf(buf, "%s", addr_to_anyname(&(fw->ip.dst)));
strcat(buf, mask_to_dotted(&(fw->ip.dmsk)));
printf(FMT("%-19s","-> %s"), buf);
}
if (format & FMT_NOTABLE)
fputs(" ", stdout);
/*输出扩展的MATCH*/
IPT_MATCH_ITERATE(fw, print_match, &fw->ip, format & FMT_NUMERIC);
/*输出扩展的TARGET*/
if (target) {
if (target->print)
/* Print the target information. */
target->print(&fw->ip, t, format & FMT_NUMERIC);
} else if (t->u.target_size != sizeof(*t))
printf("[%u bytes of unknown target data] ",
t->u.target_size - sizeof(*t));
if (!(format & FMT_NONEWLINE))
fputc('\n', stdout);
}
函数分为三部份:
输出标准的match部份;
输出扩展的match部份,调用IPT_MATCH_ITERATE实现;
调用对应的target的print函数输出target部份。
match的输出
IPT_MATCH_ITERATE 宏用于实现扩展match的遍历。这个宏定义在内核include/Linux/Netfilter-ipv4/Ip_tables.h中:
#define IPT_MATCH_ITERATE(e, fn, args...) \
({ \
unsigned int __i; \
int __ret = 0; \
struct ipt_entry_match *__match; \
\
for (__i = sizeof(struct ipt_entry); \
__i < (e)->target_offset; \
__i += __match->u.match_size) { \
__match = (void *)(e) + __i; \
\
__ret = fn(__match , ## args); \ /*每找到一个match,就交由fn函数来处理,在print_firewall中,传递过来的是函数print_match*/
if (__ret != 0) \
break; \
} \
__ret; \
})
要理解这个宏,需要先了解规则的存储,前面提到过,因为match/target都是可变的,所以在内存中,采取了ip_entry+n*match+n*target,即在规则后,是连续的若干个match,而mathc后面,又是若干个target,在结构ip_entry中,成员u_int16_t target_offset;代表了target的偏移地址,即target的开始,match的结束。我们要查到当前规则对应的所有match,需要了解三个要素:
1、match从哪里开始:起始地址应该是 [当前规则地址+sizeof(struct ipt_entry)];
2、match从哪里结束:结束地址,应该是 [当前规则地址+target_offet];
3、每一个match的大小,在内核中,match对应的结构是ipt_entry_match,其成员u.match_size指明了当前match的大小;
这三点,对应了for循环:
for (__i = sizeof(struct ipt_entry); __i < (e)->target_offset; __i += __match->u.match_size)
这样,i就对应了某个match的偏移植,通过:
__match = (void *)(e) + __i;
就得到了match的地址。
再通过
__ret = fn(__match , ## args);
输出之。
fn函数是在print_firewall中,传递过来的是函数print_match。
static int
print_match(const struct ipt_entry_match *m,
const struct ipt_ip *ip,
int numeric)
{
/*根据match名称进行查找,返回一个iptables_match结构,然后调用其中封装的print函数输出该match的信息*/
struct iptables_match *match = find_match(m->u.user.name, TRY_LOAD);
if (match) {
if (match->print)
match->print(ip, m, numeric);
else
printf("%s ", match->name);
} else {
if (m->u.user.name[0])
printf("UNKNOWN match `%s' ", m->u.user.name);
}
/* Don't stop iterating. */
return 0;
}
这里涉及到两个重要的结构:
struct ipt_entry_match:在内核中用于存储扩展match信息
struct ipt_entry_match
{
union {
struct {
u_int16_t match_size;
/* Used by userspace */
char name[IPT_FUNCTION_MAXNAMELEN];
} user;
struct {
u_int16_t match_size;
/* Used inside the kernel */
struct ipt_match *match;
} kernel;
/* Total length */
u_int16_t match_size;
} u;
unsigned char data[0];
};
struct iptables_match:用于用户级的match存储:
/* Include file for additions: new matches and targets. */
struct iptables_match
{
/* Match链,初始为NULL */
struct iptables_match *next;
/* Match名,和核心模块加载类似,作为动态链接库存在的Iptables Extension的命名规则为libipt_'name'.so */
ipt_chainlabel name;
/*版本信息,一般设为NETFILTER_VERSION */
const char *version;
/* Match数据的大小,必须用IPT_ALIGN()宏指定对界*/
size_t size;
/*由于内核可能修改某些域,因此size可能与确切的用户数据不同,这时就应该把不会被改变的数据放在数据区的前面部分,而这里就应该填写被改变的数据区大小;一般来说,这个值和size相同*/
size_t userspacesize;
/*当iptables要求显示当前match的信息时(比如iptables-m ip_ext -h),就会调用这个函数,输出在iptables程序的通用信息之后. */
void (*help)(void);
/*初始化,在parse之前调用. */
void (*init)(struct ipt_entry_match *m, unsigned int *nfcache);
/*扫描并接收本match的命令行参数,正确接收时返回非0,flags用于保存状态信息*/
int (*parse)(int c, char **argv, int invert, unsigned int *flags,
const struct ipt_entry *entry,
unsigned int *nfcache,
struct ipt_entry_match **match);
/* 前面提到过这个函数,当命令行参数全部处理完毕以后调用,如果不正确,应该
退出(exit_error())*/
void (*final_check)(unsigned int flags);
/*当查询当前表中的规则时,显示使用了当前match的规则*/
void (*print)(const struct ipt_ip *ip,
const struct ipt_entry_match *match, int numeric);
/*按照parse允许的格式将本match的命令行参数输出到标准输出,用于iptables-save命令. */
void (*save)(const struct ipt_ip *ip,
const struct ipt_entry_match *match);
/* NULL结尾的参数列表,struct option与getopt(3)使用的结构相同*/
const struct option *extra_opts;
/* Ignore these men behind the curtain: */
unsigned int option_offset;
struct ipt_entry_match *m;
unsigned int mflags;
unsigned int used;
#ifdef NO_SHARED_LIBS
unsigned int loaded; /* simulate loading so options are merged properly */
#endif
};
理解了这两个结构后,再来看find_match函数:
然match是以可扩展的形式表现出来,那么,当然就需要find_match这样的函数将它们一一找出来了。
前面说过,在输出规则的函数中:
IPT_MATCH_ITERATE(fw, print_match, &fw->ip, format & FMT_NUMERIC);
用来遍历每一个match,找到了后,就调用print_match来输出。print_match是调用find_match来查找的:
struct iptables_match *
find_match(const char *name, enum ipt_tryload tryload)
{
struct iptables_match *ptr;
for (ptr = iptables_matches; ptr; ptr = ptr->next) {
if (strcmp(name, ptr->name) == 0)
break;
}
#ifndef NO_SHARED_LIBS
if (!ptr && tryload != DONT_LOAD) {
char path[sizeof(IPT_LIB_DIR) + sizeof("/libipt_.so")
+ strlen(name)];
sprintf(path, IPT_LIB_DIR "/libipt_%s.so", name);
if (dlopen(path, RTLD_NOW)) {
/* Found library. If it didn't register itself,
maybe they specified target as match. */
ptr = find_match(name, DONT_LOAD);
if (!ptr)
exit_error(PARAMETER_PROBLEM,
"Couldn't load match `%s'\n",
name);
} else if (tryload == LOAD_MUST_SUCCEED)
exit_error(PARAMETER_PROBLEM,
"Couldn't load match `%s':%s\n",
name, dlerror());
}
#else
if (ptr && !ptr->loaded) {
if (tryload != DONT_LOAD)
ptr->loaded = 1;
else
ptr = NULL;
}
if(!ptr && (tryload == LOAD_MUST_SUCCEED)) {
exit_error(PARAMETER_PROBLEM,
"Couldn't find match `%s'\n", name);
}
#endif
if (ptr)
ptr->used = 1;
return ptr;
}
分析这个函数,不从开头来看,先看这一段:
if (!ptr && tryload != DONT_LOAD) {
char path[sizeof(IPT_LIB_DIR) + sizeof("/libipt_.so")
+ strlen(name)];
sprintf(path, IPT_LIB_DIR "/libipt_%s.so", name);
if (dlopen(path, RTLD_NOW)) {
/* Found library. If it didn't register itself,
maybe they specified target as match. */
ptr = find_match(name, DONT_LOAD);
if (!ptr)
exit_error(PARAMETER_PROBLEM,
"Couldn't load match `%s'\n",
name);
} else if (tryload == LOAD_MUST_SUCCEED)
exit_error(PARAMETER_PROBLEM,
"Couldn't load match `%s':%s\n",
name, dlerror());
}
函数根据传递过来的match名称,从指定位置,加载对应的共享库,呵呵,这些共享库的源码,全部在Extensions目录下边:
如果加载它们,那么其_init函数就会被调用。这个初始化函数用来向iptables_match全局结构注册当前match的相关处理函数。(这样,我们可以写我们自己的用户空间的扩展match处理工具了)。注册好后,函数再来调用自己:
ptr = find_match(name, DONT_LOAD);
递归回来后,呵呵,就是开头那一段了,我们需要从已经注册好的全局结构中查找与当前match名称相同的iptables_match成员,因为该成员中封装了print函数,这样就可以顺利地输出来了:
比如,加载了libptc_tcp.so,它用来处理tcp的扩展,我们来看Extensions/libiptc_tcp.c:
static
struct iptables_match tcp
= { NULL,
"tcp",
IPTABLES_VERSION,
IPT_ALIGN(sizeof(struct ipt_tcp)),
IPT_ALIGN(sizeof(struct ipt_tcp)),
&help,
&init,
&parse,
&final_check,
&print,
&save,
opts };
void
_init(void)
{
register_match(&tcp);
}
构建了一个
iptables_match结构,其间有其对应的所有用户空间工具函数,如分析命令行、输出、保存……
然后,就调用register_match函数将其插入至全局结构iptables_match当中:
void
register_match(struct iptables_match *me)
{
struct iptables_match **i;
if (strcmp(me->version, program_version) != 0) {
fprintf(stderr, "%s: match `%s' v%s (I'm v%s).\n",
program_name, me->name, me->version, program_version);
exit(1);
}
if (find_match(me->name, DONT_LOAD)) {
fprintf(stderr, "%s: match `%s' already registered.\n",
program_name, me->name);
exit(1);
}
if (me->size != IPT_ALIGN(me->size)) {
fprintf(stderr, "%s: match `%s' has invalid size %u.\n",
program_name, me->name, me->size);
exit(1);
}
/* Append to list. */
for (i = &iptables_matches; *i; i = &(*i)->next);
me->next = NULL;
*i = me;
me->m = NULL;
me->mflags = 0;
}
函数就是一个建立链表的过程。不进一步分析了。