大家好，又见面了，我是你们的朋友全栈君。如果您正在找激活码,请点击查看最新教程,关注关注公众号 “全栈程序员社区” 获取激活教程,可能之前旧版本教程已经失效.最新Idea2022.1教程亲测有效,一键激活。
Jetbrains全系列IDE稳定放心使用
最近需要使用ipset，iptables，和netfilter，所以把三者的源代码看大概阅读了一遍。
前面我们学习过应用层ipset和netfilter模块之间通信是采用的netlink套接字
用户空间的ipset命令通过 libipset.so 这个库和内核通讯
一、ipset主流程
下面是我总结的主流程
二、用户层如何将创建set的名称和类型传递到内核层的
我们都知道ipset可以创建不同类型set，如”hash:ip”,”hash:ip,port”,”hash:net,port”等
从执行命令到内核态，其流程为
ipset命令行 -> libipset.so -> ip_set.ko内核模块 ->根据set类型选择ip_set_hash_ip.ko内核模块
那么应用层是如何解析set的命令和类型的，并且是如何将set名称和类型传递到内核态的呢？
ipset_parse_argv函数中去解析ipset的Create命令
ipset_parse_setname是解析刚创建ipet集合的名称
ipset_parse_typename是解析刚创建ipset集合的类型
ret = ipset_parse_setname(session, IPSET_SETNAME, arg0);函数是将将arg0的值传递了session的setname成员
因为我更关注set type类型，所以进入ipset_parse_typename函数
/* Find the corresponding type */
typename = ipset_typename_resolve(str);
通过注释可得知，ipset_typename_resolve是找到对应的set类型，大胆猜想下，命令行是“hash:ip”，通过“hash:ip”我们能够获取到typename类型名称
报告大哥，发现线索typelist链表，函数意思是遍历typelist链表，用ipset_match_typename()来匹配类型名称，匹配成功则返回类型名称。现在需要找到往typelist链表中添加元素的函数！！！
ipset_type_add函数！
ipset_type_add函数！
ipset_type_add函数！
重要的事情说三遍！看看它的英文注释，如下：
/**
* ipset_type_add – add (register) a userspace set type
* @type: pointer to the set type structure
*
* Add the given set type to the type list. The types
* are added sorted, in descending revision number.
*
* Returns 0 on success or a negative error code.
*/
添加一个用户态的set集合类型，ok，找到了，only you
何人在调用ipset_type_add函数？
打开ipset_hash_ip.c文件，找到其_init函数
看看ipset_hash_ip0结构体定义和初始化
/* Initial release */
static struct ipset_type ipset_hash_ip0 = {
.name = "hash:ip",
.alias = { "iphash", NULL },
.revision = 0,
.family = NFPROTO_IPSET_IPV46,
.dimension = IPSET_DIM_ONE,
.elem = {
[IPSET_DIM_ONE - 1] = {
.parse = ipset_parse_ip4_single6,
.print = ipset_print_ip,
.opt = IPSET_OPT_IP
},
},
.cmd = {
[IPSET_CREATE] = {
.args = {
IPSET_ARG_FAMILY,
/* Aliases */
IPSET_ARG_INET,
IPSET_ARG_INET6,
IPSET_ARG_HASHSIZE,
IPSET_ARG_MAXELEM,
IPSET_ARG_NETMASK,
IPSET_ARG_TIMEOUT,
/* Ignored options: backward compatibilty */
IPSET_ARG_PROBES,
IPSET_ARG_RESIZE,
IPSET_ARG_GC,
IPSET_ARG_NONE,
},
.need = 0,
.full = 0,
.help = "",
},
[IPSET_ADD] = {
.args = {
IPSET_ARG_TIMEOUT,
IPSET_ARG_NONE,
},
.need = IPSET_FLAG(IPSET_OPT_IP),
.full = IPSET_FLAG(IPSET_OPT_IP)
| IPSET_FLAG(IPSET_OPT_IP_TO),
.help = "IP",
},
[IPSET_DEL] = {
.args = {
IPSET_ARG_NONE,
},
.need = IPSET_FLAG(IPSET_OPT_IP),
.full = IPSET_FLAG(IPSET_OPT_IP)
| IPSET_FLAG(IPSET_OPT_IP_TO),
.help = "IP",
},
[IPSET_TEST] = {
.args = {
IPSET_ARG_NONE,
},
.need = IPSET_FLAG(IPSET_OPT_IP),
.full = IPSET_FLAG(IPSET_OPT_IP)
| IPSET_FLAG(IPSET_OPT_IP_TO),
.help = "IP",
},
},
.usage = "where depending on the INET family\n"
" IP is a valid IPv4 or IPv6 address (or hostname),\n"
" CIDR is a valid IPv4 or IPv6 CIDR prefix.\n"
" Adding/deleting multiple elements in IP/CIDR or FROM-TO form\n"
" is supported for IPv4.",
.description = "Initial revision",
};//
三、netlink套接字初始化
想使用netlink套接字，必然要先创建netlink套接字，应该有如下代码
skfd = socket(AF_NETLINK, SOCK_RAW, NETLINK_TEST);但是我并没有在ipset源代码中查找到。
后来在书上看到ipset源代码中是采用libmnl库来使用netlink套接字，使用ipset_mnl_init函数来进行初始化操作
static struct ipset_handle *
ipset_mnl_init(mnl_cb_t *cb_ctl, void *data)
{
struct ipset_handle *handle;
assert(cb_ctl);
assert(data);
handle = calloc(1, sizeof(*handle));
if (!handle)
return NULL;
handle->h = mnl_socket_open(NETLINK_NETFILTER);
if (!handle->h)
goto free_handle;
if (mnl_socket_bind(handle->h, 0, MNL_SOCKET_AUTOPID) < 0)
goto close_nl;
handle->portid = mnl_socket_get_portid(handle->h);
handle->cb_ctl = cb_ctl;
handle->data = data;
handle->seq = time(NULL);
return handle;
close_nl:
mnl_socket_close(handle->h);
free_handle:
free(handle);
return NULL;
}mnl_socket_open函数传递NETLINK_NETFILTER类型，创建netlink套接字
mnl_socket_bind绑定进程pid，此处传递的是MNL_SOCKET_AUTOPID
mnl_socket_get_portid 通过给定的netlink套接字获取netlink端口id
四、通过netlink函数和内核态进行交互
在同一个文件mnl.c中发现ipset_mnl_query函数，其中调用了mnl_socket_recvfrom和mnl_socket_sendto，和内核态进行通信
下面就是看下libmnl的api官方文档
static int
ipset_mnl_query(struct ipset_handle *handle, void *buffer, size_t len)
{
struct nlmsghdr *nlh = buffer;
int ret;
assert(handle);
assert(buffer);
nlh->nlmsg_seq = ++handle->seq;
#ifdef IPSET_DEBUG
ipset_debug_msg("sent", nlh, nlh->nlmsg_len);
#endif
if (mnl_socket_sendto(handle->h, nlh, nlh->nlmsg_len) < 0)
return -ECOMM;
ret = mnl_socket_recvfrom(handle->h, buffer, len);
#ifdef IPSET_DEBUG
ipset_debug_msg("received", buffer, ret);
#endif
while (ret > 0) {
ret = mnl_cb_run2(buffer, ret,
handle->seq, handle->portid,
handle->cb_ctl[NLMSG_MIN_TYPE],
handle->data,
handle->cb_ctl, NLMSG_MIN_TYPE);
D("nfln_cb_run2, ret: %d, errno %d", ret, errno);
if (ret <= 0)
break;
ret = mnl_socket_recvfrom(handle->h, buffer, len);
D("message received, ret: %d", ret);
}
return ret;
}
关于mnl_socket_recvfrom和mnl_socket_sendto和mnl_cb_run2函数的含义，请自行查找api
用户态和内核态通信，必然会遵循某种特定的规则，我们称之为通信规则
在ip_set.h文件中，有如下命令的定义
/* Message types and commands */
enum ipset_cmd {
IPSET_CMD_NONE,
IPSET_CMD_PROTOCOL, /* 1: Return protocol version */
IPSET_CMD_CREATE, /* 2: Create a new (empty) set */
IPSET_CMD_DESTROY, /* 3: Destroy a (empty) set */
IPSET_CMD_FLUSH, /* 4: Remove all elements from a set */
IPSET_CMD_RENAME, /* 5: Rename a set */
IPSET_CMD_SWAP, /* 6: Swap two sets */
IPSET_CMD_LIST, /* 7: List sets */
IPSET_CMD_SAVE, /* 8: Save sets */
IPSET_CMD_ADD, /* 9: Add an element to a set */
IPSET_CMD_DEL, /* 10: Delete an element from a set */
IPSET_CMD_TEST, /* 11: Test an element in a set */
IPSET_CMD_HEADER, /* 12: Get set header data only */
IPSET_CMD_TYPE, /* 13: Get set type */
IPSET_CMD_GET_BYNAME, /* 14: Get set index by name */
IPSET_CMD_GET_BYINDEX, /* 15: Get set name by index */
IPSET_MSG_MAX, /* Netlink message commands */
/* Commands in userspace: */
IPSET_CMD_RESTORE = IPSET_MSG_MAX, /* 16: Enter restore mode */
IPSET_CMD_HELP, /* 17: Get help */
IPSET_CMD_VERSION, /* 18: Get program version */
IPSET_CMD_QUIT, /* 19: Quit from interactive mode */
IPSET_CMD_MAX,
IPSET_CMD_COMMIT = IPSET_CMD_MAX, /* 20: Commit buffered commands */
};这里我们以IPSET_CMD_CREATE为例子，在内核代码（我的内核版本是3.10）搜索IPSET_CMD_CREATE
找到如下的结构体
static const struct nfnl_callback ip_set_netlink_subsys_cb[IPSET_MSG_MAX] = {
[IPSET_CMD_NONE] = {
.call = ip_set_none,
.attr_count = IPSET_ATTR_CMD_MAX,
},
[IPSET_CMD_CREATE] = {
.call = ip_set_create,
.attr_count = IPSET_ATTR_CMD_MAX,
.policy = ip_set_create_policy,
},
[IPSET_CMD_DESTROY] = {
.call = ip_set_destroy,
.attr_count = IPSET_ATTR_CMD_MAX,
.policy = ip_set_setname_policy,
},
[IPSET_CMD_FLUSH] = {
.call = ip_set_flush,
.attr_count = IPSET_ATTR_CMD_MAX,
.policy = ip_set_setname_policy,
},
}
上面标明IPSET_CMD_CREATE命令的处理函数为ip_set_create
此时从用户态发送命令到内核态
内核态响应用户态的命令
流程已经跑通了。
发布者：全栈程序员-站长，转载请注明出处：https://javaforall.net/185131.html原文链接：https://javaforall.net
