注：
當用戶態進程發送數據時，調用sendmsg實現，其調用內核netlink_sendmsg函數完成，新建了sk_buff,然後給其cb私有緩存中保存了源地址信息，然後把數據拷貝到sk_buff中[nlmsghdr頭部已經附在數據部分前面，作為數據部分了]然後利用netlink_unicast發送出去
而當內核態發送時，新建了一個sk_buff，頭部填寫了nlmsghdr[利用了nlmsg_put實現]結構信息，然後是數據部分，而且給其cb私有部分NETLINK_CB(skb_1)填寫了本地信息，然後利用netlink_unicast發送出去
netlink結構體簡析
netlink的實現主要在/net/netlink/af_netlink.c文件中，結構如下:
1 內核中的netlink協議類型,AF_NETLINK為netlink協議族
#define NETLINK_ROUTE 0 /* Routing/device hook */
#define NETLINK_UNUSED 1 /* Unused number */
#define NETLINK_USERSOCK 2 /* Reserved for user mode socket protocols */
#define NETLINK_FIREWALL 3 /* Firewalling hook */
#define NETLINK_INET_DIAG 4 /* INET socket monitoring */
#define NETLINK_NFLOG 5 /* netfilter/iptables ULOG */
#define NETLINK_XFRM 6 /* ipsec */
#define NETLINK_SELINUX 7 /* SELinux event notifications */
#define NETLINK_ISCSI 8 /* Open-iSCSI */
#define NETLINK_AUDIT 9 /* auditing */
#define NETLINK_FIB_LOOKUP 10
#define NETLINK_CONNECTOR 11
#define NETLINK_NETFILTER 12 /* netfilter subsystem */
#define NETLINK_IP6_FW 13
#define NETLINK_DNRTMSG 14 /* DECnet routing messages */
#define NETLINK_KOBJECT_UEVENT 15 /* Kernel messages to userspace */
#define NETLINK_GENERIC 16
/* leave room for NETLINK_DM (DM Events) */
#define NETLINK_SCSITRANSPORT 18 /* SCSI Transports */
#define NETLINK_ECRYPTFS 19
#define MAX_LINKS 32
2 netlink 地址格式
struct sockaddr_nl
{
sa_family_t nl_family; /* AF_NETLINK */
unsigned short nl_pad; /* zero */
__u32 nl_pid; /* port ID */
__u32 nl_groups; /* multicast groups mask */
};
3 netlink消息頭
struct nlmsghdr
{
__u32 nlmsg_len; /* Length of message including header */
__u16 nlmsg_type; /* Message content */
__u16 nlmsg_flags; /* Additional flags */
__u32 nlmsg_seq; /* Sequence number */
__u32 nlmsg_pid; /* Sending process port ID */
};
4 netlink 套接字結構
struct netlink_sock {
/* struct sock has to be the first member of netlink_sock */
struct sock sk;
u32 pid; //內核自己的pid，=0
u32 dst_pid;
u32 dst_group;對方的組
u32 flags;
u32 subscriptions;
u32 ngroups;組數量
unsigned long *groups;組號
unsigned long state;
wait_queue_head_t wait; 進程在接收數據包時等待隊列
struct netlink_callback *cb;
struct mutex *cb_mutex;
struct mutex cb_def_mutex;
void (*netlink_rcv)(struct sk_buff *skb); //內核態接收到用戶態信息後的處理函數
struct module *module;
};
5 skb_buff結構中對應的netlink相關的信息
內核態存儲自己發送地址等信息，在數據報傳到用戶態後，用戶態可能要獲取其中信息
struct netlink_skb_parms
{
struct ucred creds; /* Skb credentials */
__u32 pid;
__u32 dst_group;
kernel_cap_t eff_cap;
__u32 loginuid; /* Login (audit) uid */
__u32 sessionid; /* Session id (audit) */
__u32 sid; /* SELinux security id */
};
#define NETLINK_CB(skb) (*(struct netlink_skb_parms*)&((skb)->cb))
6 內核中所有的netlink套接字存儲在一個全局的哈新表中，該結構定義如下
static struct netlink_table *nl_table;其中每個協議對應一個哈希表，所有的同一種協議的數據報散列在同哈希表中
下面為一種協議所連接的哈希表結構：
struct netlink_table {
struct nl_pid_hash hash; // 根據pid進行HASH的netlink sock鏈表, 相當於客戶端鏈表
struct hlist_head mc_list; // 多播的sock鏈表
unsigned long *listeners; // 監聽者標志
unsigned int nl_nonroot;
unsigned int groups; // 每個netlink的協議類型可以定義多個組, 8的倍數,最小是32
struct module *module;
int registered;
};
最大可有MAX_LINKS(32)個表，處理不同協議類型的netlink套接口, 注意由於是自身的通信, 本機同時作為服務器和客戶端, 服務端需要一個套接口對應, 每個客戶端也要有一個套接口對應, 多個客戶端的套接口形成一個鏈表.
struct nl_pid_hash {
struct hlist_head *table; // 鏈表節點，每個桶中協議的sock連入其中，根據哈希值可得確定的sock
unsigned long rehash_time; // 重新計算HASH的時間間隔
unsigned int mask;
unsigned int shift;
unsigned int entries; // 鏈表節點數
unsigned int max_shift; // 最大冪值
u32 rnd; // 隨機數
};
7 一些與netlink相關的宏
#define NLMSG_ALIGNTO 4
#define NLMSG_ALIGN(len) ( ((len)+NLMSG_ALIGNTO-1) & ~(NLMSG_ALIGNTO-1) )
#define NLMSG_HDRLEN ((int) NLMSG_ALIGN(sizeof(struct nlmsghdr)))
#define NLMSG_LENGTH(len) ((len)+NLMSG_ALIGN(NLMSG_HDRLEN))
#define NLMSG_SPACE(len) NLMSG_ALIGN(NLMSG_LENGTH(len)) 含len長度數據+nlmsghdr的總長度
#define NLMSG_DATA(nlh) ((void*)(((char*)nlh) + NLMSG_LENGTH(0))) 獲nlmsghdr頭部之後的數據
#define NLMSG_NEXT(nlh,len) ((len) -= NLMSG_ALIGN((nlh)->nlmsg_len), \
(struct nlmsghdr*)(((char*)(nlh)) + NLMSG_ALIGN((nlh)->nlmsg_len)))
#define NLMSG_OK(nlh,len) ((len) >= (int)sizeof(struct nlmsghdr) && \
(nlh)->nlmsg_len >= sizeof(struct nlmsghdr) && \
(nlh)->nlmsg_len <= (len))
#define NLMSG_PAYLOAD(nlh,len) ((nlh)->nlmsg_len - NLMSG_SPACE((len)))
8 netlink的函數操作集合[掛載於socket->ops結構中]
static const struct proto_ops netlink_ops = {
.family = PF_NETLINK,
.owner = THIS_MODULE,
.release = netlink_release,
.bind = netlink_bind,
.connect = netlink_connect,
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = netlink_getname,
.poll = datagram_poll,
.ioctl = sock_no_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.setsockopt = netlink_setsockopt,
.getsockopt = netlink_getsockopt,
.sendmsg = netlink_sendmsg, netlink 套接字實際的發送和接受函數
.recvmsg = netlink_recvmsg,
.mmap = sock_no_mmap,
.sendpage = sock_no_sendpage,
};
函數跟蹤分析
1 內核中創建netlink函數
建立socket、sock結構並初始化
/*
* We export these functions to other modules. They provide a
* complete set of kernel non-blocking support for message
* queueing.
*/
struct sock *
netlink_kernel_create(struct net *net, int unit, unsigned int groups,
void (*input)(struct sk_buff *skb),struct mutex *cb_mutex, struct module *module)
{
struct socket *sock;
struct sock *sk;
struct netlink_sock *nlk;
unsigned long *listeners = NULL;
BUG_ON(!nl_table);
if (unit < 0 || unit >= MAX_LINKS)
return NULL;
if (sock_create_lite(PF_NETLINK, SOCK_DGRAM, unit, &sock)) //創建socket結構
return NULL;
/*
* We have to just have a reference on the net from sk, but don't
* get_net it. Besides, we cannot get and then put the net here.
* So we create one inside init_net and the move it to net.
*/
if (__netlink_create(&init_net, sock, cb_mutex, unit) < 0) 創建sock結構，並初始化
goto out_sock_release_nosk;
sk = sock->sk;
sk_change_net(sk, net);
if (groups < 32)
groups = 32;
listeners = kzalloc(NLGRPSZ(groups) + sizeof(struct listeners_rcu_head),
GFP_KERNEL);
if (!listeners)
goto out_sock_release;
sk->sk_data_ready = netlink_data_ready; //什麼都不做
if (input)
nlk_sk(sk)->netlink_rcv = input; //設置內核態的接受函數
if (netlink_insert(sk, net, 0))
goto out_sock_release;
nlk = nlk_sk(sk);取得sock嵌入的netlink_sock結構體
nlk->flags |= NETLINK_KERNEL_SOCKET;
netlink_table_grab();
if (!nl_table[unit].registered) {
nl_table[unit].groups = groups;
nl_table[unit].listeners = listeners;
nl_table[unit].cb_mutex = cb_mutex;
nl_table[unit].module = module;
nl_table[unit].registered = 1; 更新netlink_table結構體信息，每中協議對應一個netlink_table結構
} else {
kfree(listeners);
nl_table[unit].registered++;
}
netlink_table_ungrab();
return sk;
out_sock_release:
kfree(listeners);
netlink_kernel_release(sk);
return NULL;
out_sock_release_nosk:
sock_release(sock);
return NULL;
}
EXPORT_SYMBOL(netlink_kernel_create);
1.1 創建socket結構
int sock_create_lite(int family, int type, int protocol, struct socket **res)
{
int err;
struct socket *sock = NULL;
err = security_socket_create(family, type, protocol, 1); 空
if (err)
goto out;
sock = sock_alloc();
if (!sock) {
err = -ENOMEM;
goto out;
}
sock->type = type;
err = security_socket_post_create(sock, family, type, protocol, 1);//啥都不干
if (err)
goto out_release;
out:
*res = sock;
return err;
out_release:
sock_release(sock);
sock = NULL;
goto out;
}
1.2 創建sock結構並初始化
static int __netlink_create(struct net *net, struct socket *sock,
struct mutex *cb_mutex, int protocol)
{
struct sock *sk;
struct netlink_sock *nlk;
sock->ops = &netlink_ops;
sk = sk_alloc(net, PF_NETLINK, GFP_KERNEL, &netlink_proto);//struct proto沒用
if (!sk)
return -ENOMEM;
sock_init_data(sock, sk); // sk和sock初始化
nlk = nlk_sk(sk); 取得netlink_sock結構
if (cb_mutex)
nlk->cb_mutex = cb_mutex;
else {
nlk->cb_mutex = &nlk->cb_def_mutex;
mutex_init(nlk->cb_mutex);
}
init_waitqueue_head(&nlk->wait); //初始化等待隊列
sk->sk_destruct = netlink_sock_destruct;
sk->sk_protocol = protocol;
return 0;
}
1.2.1 sock結構和socket結構初始化過程
void sock_init_data(struct socket *sock, struct sock *sk)
{
skb_queue_head_init(&sk->sk_receive_queue);
skb_queue_head_init(&sk->sk_write_queue);
skb_queue_head_init(&sk->sk_error_queue);
#ifdef CONFIG_NET_DMA
skb_queue_head_init(&sk->sk_async_wait_queue);
#endif
sk->sk_send_head = NULL;
init_timer(&sk->sk_timer);
sk->sk_allocation = GFP_KERNEL;
sk->sk_rcvbuf = sysctl_rmem_default;
sk->sk_sndbuf = sysctl_wmem_default;
sk->sk_state = TCP_CLOSE;
sk_set_socket(sk, sock);
sock_set_flag(sk, SOCK_ZAPPED);
if (sock) {
sk->sk_type = sock->type;
sk->sk_sleep = &sock->wait;
sock->sk = sk;
} else
sk->sk_sleep = NULL;
rwlock_init(&sk->sk_dst_lock);
rwlock_init(&sk->sk_callback_lock);
lockdep_set_class_and_name(&sk->sk_callback_lock,
af_callback_keys + sk->sk_family,
af_family_clock_key_strings[sk->sk_family]);
sk->sk_state_change = sock_def_wakeup;
sk->sk_data_ready = sock_def_readable;
sk->sk_write_space = sock_def_write_space;
sk->sk_error_report = sock_def_error_report;
sk->sk_destruct = sock_def_destruct;
sk->sk_sndmsg_page = NULL;
sk->sk_sndmsg_off = 0;
sk->sk_peercred.pid = 0;
sk->sk_peercred.uid = -1;
sk->sk_peercred.gid = -1;
sk->sk_write_pending = 0;
sk->sk_rcvlowat = 1;
sk->sk_rcvtimeo = MAX_SCHEDULE_TIMEOUT;
sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT;
sk->sk_stamp = ktime_set(-1L, 0);
/*
* Before updating sk_refcnt, we must commit prior changes to memory
* (Documentation/RCU/rculist_nulls.txt for details)
*/
smp_wmb();
atomic_set(&sk->sk_refcnt, 1);
atomic_set(&sk->sk_drops, 0);
}
2 新建sk_buff結構,當內核態向用戶態發送信息時，必須得建新的sk_buff結構
static inline struct sk_buff *alloc_skb(unsigned int size,
gfp_t priority)
{
return __alloc_skb(size, priority, 0, -1);
}
/**
* __alloc_skb - allocate a network buffer
* @size: size to allocate
* @gfp_mask: allocation mask
* @fclone: allocate from fclone cache instead of head cache
* and allocate a cloned (child) skb
* @node: numa node to allocate memory on
*
* Allocate a new &sk_buff. The returned buffer has no headroom and a
* tail room of size bytes. The object has a reference count of one.
* The return is the buffer. On a failure the return is %NULL.
*
* Buffers may only be allocated from interrupts using a @gfp_mask of
* %GFP_ATOMIC.
*/
struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
int fclone, int node)
{
struct kmem_cache *cache;
struct skb_shared_info *shinfo;
struct sk_buff *skb;
u8 *data;
cache = fclone ? skbuff_fclone_cache : skbuff_head_cache;
/* Get the HEAD */
skb = kmem_cache_alloc_node(cache, gfp_mask & ~__GFP_DMA, node);
if (!skb)
goto out;
size = SKB_DATA_ALIGN(size);
data = kmalloc_node_track_caller(size + sizeof(struct skb_shared_info),
gfp_mask, node); //返回新建空間首地址
if (!data)
goto nodata;
/*
* Only clear those fields we need to clear, not those that we will
* actually initialise below. Hence, don't put any more fields after
* the tail pointer in struct sk_buff!
*/
memset(skb, 0, offsetof(struct sk_buff, tail));
skb->truesize = size + sizeof(struct sk_buff);
atomic_set(&skb->users, 1);
skb->head = data;
skb->data = data;
skb_reset_tail_pointer(skb); //skb->tail = skb->data在剛開始時候
skb->end = skb->tail + size;
kmemcheck_annotate_bitfield(skb, flags1);
kmemcheck_annotate_bitfield(skb, flags2);
#ifdef NET_SKBUFF_DATA_USES_OFFSET
skb->mac_header = ~0U;
#endif
/* make sure we initialize shinfo sequentially */
shinfo = skb_shinfo(skb);該表skb_buff尾部結構信息
atomic_set(&shinfo->dataref, 1);
shinfo->nr_frags = 0;
shinfo->gso_size = 0;
shinfo->gso_segs = 0;
shinfo->gso_type = 0;
shinfo->ip6_frag_id = 0;
shinfo->tx_flags.flags = 0;
skb_frag_list_init(skb);
memset(&shinfo->hwtstamps, 0, sizeof(shinfo->hwtstamps));
if (fclone) {
struct sk_buff *child = skb + 1;
atomic_t *fclone_ref = (atomic_t *) (child + 1);
kmemcheck_annotate_bitfield(child, flags1);
kmemcheck_annotate_bitfield(child, flags2);
skb->fclone = SKB_FCLONE_ORIG;
atomic_set(fclone_ref, 1);
child->fclone = SKB_FCLONE_UNAVAILABLE;
}
out:
return skb;
nodata:
kmem_cache_free(cache, skb);
skb = NULL;
goto out;
}
3 釋放以使用完畢的sk_buff空間
/**
* kfree_skb - free an sk_buff
* @skb: buffer to free
*
* Drop a reference to the buffer and free it if the usage count has
* hit zero.
*/
void kfree_skb(struct sk_buff *skb)
{
if (unlikely(!skb))
return;
if (likely(atomic_read(&skb->users) == 1))
smp_rmb();
else if (likely(!atomic_dec_and_test(&skb->users)))
return;
trace_kfree_skb(skb, __builtin_return_address(0));
__kfree_skb(skb);
}
4 kernel向user發送的sk_buff信息中格式為: nlmsghdr+內容,所以在內核態分配好並初始化好sk_buff之後，可以利用nlmsg_put函數來填寫其nlmsghdr頭部[只是一些相關協議的信息，與地址等無關]
/**
* nlmsg_put - Add a new netlink message to an skb
* @skb: socket buffer to store message in
* @pid: netlink process id，for kernel ,pid=0
* @seq: sequence number of message
* @type: message type
* @payload: length of message payload 該數據信息可承載的實際數據大小
* @flags: message flags
*
* Returns NULL if the tailroom of the skb is insufficient to store
* the message header and payload.
*/
static inline struct nlmsghdr *nlmsg_put(struct sk_buff *skb, u32 pid, u32 seq,
int type, int payload, int flags)
{
if (unlikely(skb_tailroom(skb) < nlmsg_total_size(payload)))
return NULL;
return __nlmsg_put(skb, pid, seq, type, payload, flags);
}
內核中填寫nlmsghdr頭部信息
static __inline__ struct nlmsghdr *
__nlmsg_put(struct sk_buff *skb, u32 pid, u32 seq, int type, int len, int flags)
{
struct nlmsghdr *nlh;
int size = NLMSG_LENGTH(len); size = len+aline_to_4(nlmsghdr)
nlh = (struct nlmsghdr*)skb_put(skb, NLMSG_ALIGN(size)); tail=data+nlmsg_align(size),返回data
nlh->nlmsg_type = type;
nlh->nlmsg_len = size;
nlh->nlmsg_flags = flags;
nlh->nlmsg_pid = pid;
nlh->nlmsg_seq = seq;
if (!__builtin_constant_p(size) || NLMSG_ALIGN(size) - size != 0)
memset(NLMSG_DATA(nlh) + len, 0, NLMSG_ALIGN(size) - size);
return nlh;
}
unsigned char *skb_put(struct sk_buff *skb, unsigned int len)
{
unsigned char *tmp = skb_tail_pointer(skb);
SKB_LINEAR_ASSERT(skb);
skb->tail += len;
skb->len += len;
if (unlikely(skb->tail > skb->end))
skb_over_panic(skb, len, __builtin_return_address(0));
return tmp;
}
5 內核態向用戶態發送信息的函數，pid指向用戶態的進程
int netlink_unicast(struct sock *ssk, struct sk_buff *skb,u32 pid, int nonblock)
{
struct sock *sk;
int err;
long timeo;
skb = netlink_trim(skb, gfp_any());
timeo = sock_sndtimeo(ssk, nonblock);
retry:
sk = netlink_getsockbypid(ssk, pid); 找到內核中對應該pid和SOCK_DGRAM協議的sock結構，掛載在哈希表中，這樣可以找到另一端的sock結構，另一端可以為：用戶態也可以為另一個內核端
if (IS_ERR(sk)) {
kfree_skb(skb);
return PTR_ERR(sk);
}
if (netlink_is_kernel(sk)) //另一端也為內核端，調用其netlink_sock的input函數接受
return netlink_unicast_kernel(sk, skb);
if (sk_filter(sk, skb)) {
err = skb->len;
kfree_skb(skb);
sock_put(sk);
return err;
}
err = netlink_attachskb(sk, skb, &timeo, ssk);
if (err == 1)
goto retry;
if (err)
return err;
return netlink_sendskb(sk, skb); //掛載到用戶態sock結構的receive_queue隊列中， 然後調用sk_data_ready函數，喚醒用戶態睡眠函數
}
EXPORT_SYMBOL(netlink_unicast);
5-0 netlink_getsockbypid
static struct sock *netlink_getsockbypid(struct sock *ssk, u32 pid)
{
struct sock *sock;
struct netlink_sock *nlk;
sock = netlink_lookup(sock_net(ssk), ssk->sk_protocol, pid);
if (!sock)
return ERR_PTR(-ECONNREFUSED);
/* Don't bother queuing skb if kernel socket has no input function */
nlk = nlk_sk(sock);
if (sock->sk_state == NETLINK_CONNECTED &&
nlk->dst_pid != nlk_sk(ssk)->pid) {
sock_put(sock);
return ERR_PTR(-ECONNREFUSED);
}
return sock;
}
查找主函數：
static inline struct sock *netlink_lookup(struct net *net, int protocol,//協議，可以自己定義
u32 pid)
{
struct nl_pid_hash *hash = &nl_table[protocol].hash;找到哈希表的頭
struct hlist_head *head;
struct sock *sk;
struct hlist_node *node;
read_lock(&nl_table_lock);
head = nl_pid_hashfn(hash, pid);根據pid散列值找到sock所在的鏈表
sk_for_each(sk, node, head) { 在鏈表中匹配
if (net_eq(sock_net(sk), net) && (nlk_sk(sk)->pid == pid)) {
sock_hold(sk);
goto found;
}
}
sk = NULL;
found:
read_unlock(&nl_table_lock);
return sk;
}
5-1 將sock和sk_buff綁定在一起
/*
* Attach a skb to a netlink socket.
* The caller must hold a reference to the destination socket. On error, the
* reference is dropped. The skb is not send to the destination, just all
* all error checks are performed and memory in the queue is reserved.
* Return values:
* < 0: error. skb freed, reference to sock dropped.
* 0: continue
* 1: repeat lookup - reference dropped while waiting for socket memory.
*/
int netlink_attachskb(struct sock *sk, struct sk_buff *skb,
long *timeo, struct sock *ssk)
{
struct netlink_sock *nlk;
nlk = nlk_sk(sk);
如果sock的接受緩沖區小於sock中接受隊列已提交的字節數，或者還有數據數據未被上層處理
if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||test_bit(0, &nlk->state)) {
DECLARE_WAITQUEUE(wait, current); 聲明等待隊列
if (!*timeo) {
if (!ssk || netlink_is_kernel(ssk))
netlink_overrun(sk);
sock_put(sk);
kfree_skb(skb);
return -EAGAIN;
}
__set_current_state(TASK_INTERRUPTIBLE);
add_wait_queue(&nlk->wait, &wait); 設置自身狀態，等待睡眠
if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
test_bit(0, &nlk->state)) &&
!sock_flag(sk, SOCK_DEAD))
*timeo = schedule_timeout(*timeo);
__set_current_state(TASK_RUNNING);
remove_wait_queue(&nlk->wait, &wait);
sock_put(sk);遞減sk引用次數
if (signal_pending(current)) {
kfree_skb(skb);
return sock_intr_errno(*timeo);
}
return 1; //重新將sk_buff放在客戶端sock上
}
skb_set_owner_r(skb, sk);
return 0;
}
改變sock->sk_rmem_alloc大小，以及skb->sk變量
static inline void skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
{
skb_orphan(skb);
skb->sk = sk;
skb->destructor = sock_rfree;
atomic_add(skb->truesize, &sk->sk_rmem_alloc);
sk_mem_charge(sk, skb->truesize);
}
5.2 內核態將數據發送出去
int netlink_sendskb(struct sock *sk, struct sk_buff *skb)
{
int len = skb->len;
skb_queue_tail(&sk->sk_receive_queue, skb);
sk->sk_data_ready(sk, len);喚醒等待進程，進行接受工作
sock_put(sk);
return len;
}
6 用戶態接受消息
此時內核態將數據發送到用戶態對應的sock的sk_receive_queue中，並且喚醒睡眠的進程
static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
struct msghdr *msg, size_t len,
int flags)
{//sock的io控制塊
struct sock_iocb *siocb = kiocb_to_siocb(kiocb);
struct scm_cookie scm;
struct sock *sk = sock->sk; 獲取用戶態進程的sock結構
struct netlink_sock *nlk = nlk_sk(sk);
int noblock = flags&MSG_DONTWAIT;
size_t copied;
struct sk_buff *skb, *data_skb;
int err;
if (flags&MSG_OOB)
return -EOPNOTSUPP;
copied = 0;
skb = skb_recv_datagram(sk, flags, noblock, &err);從等待隊列中接受一個數據包
if (skb == NULL)
goto out;
data_skb = skb;
#ifdef CONFIG_COMPAT_NETLINK_MESSAGES
if (unlikely(skb_shinfo(skb)->frag_list)) {
/*
* If this skb has a frag_list, then here that means that we
* will have to use the frag_list skb's data for compat tasks
* and the regular skb's data for normal (non-compat) tasks.
*
* If we need to send the compat skb, assign it to the
* 'data_skb' variable so that it will be used below for data
* copying. We keep 'skb' for everything else, including
* freeing both later.
*/
if (flags & MSG_CMSG_COMPAT)
data_skb = skb_shinfo(skb)->frag_list;
}
#endif
msg->msg_namelen = 0;
copied = data_skb->len; 接收數據的長度
if (len < copied) { //如果用戶需要的長度小於數據報的長度，則丟棄剩余的數據包
msg->msg_flags |= MSG_TRUNC;
copied = len;
}
skb_reset_transport_header(data_skb); //將數據包從sk_buff中拷貝到msghdr結構中
err = skb_copy_datagram_iovec(data_skb, 0, msg->msg_iov, copied);
if (msg->msg_name) { 如果要求得到kernel的struct netlink_nl結構，那麼...
struct sockaddr_nl *addr = (struct sockaddr_nl *)msg->msg_name;
addr->nl_family = AF_NETLINK;
addr->nl_pad = 0;
addr->nl_pid = NETLINK_CB(skb).pid; //內核態自己的pid信息
addr->nl_groups = netlink_group_mask(NETLINK_CB(skb).dst_group);//發送分組
msg->msg_namelen = sizeof(*addr);
}
接收數據報信息標志，將消息頭拷貝到用戶空間
if (nlk->flags & NETLINK_RECV_PKTINFO)
netlink_cmsg_recv_pktinfo(msg, skb);
if (NULL == siocb->scm) {
memset(&scm, 0, sizeof(scm));
siocb->scm = &scm;
}
siocb->scm->creds = *NETLINK_CREDS(skb);
if (flags & MSG_TRUNC)
copied = data_skb->len;
skb_free_datagram(sk, skb); //釋放sk_buff數據報信息
if (nlk->cb && atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2)
netlink_dump(sk);
scm_recv(sock, msg, siocb->scm, flags);
out:
netlink_rcv_wake(sk);接受喚醒
return err ? : copied;
}
6.1 從sock->sk_receive_buf中摘除一個sk_buff結構
從sock等待隊列中摘除一個sk_buff結構：
struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags,
int *peeked, int *err)
{
struct sk_buff *skb;
long timeo;
/*
* Caller is allowed not to check sk->sk_err before skb_recv_datagram()
*/
int error = sock_error(sk);
if (error)
goto no_packet;
timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
do {
/* Again only user level code calls this function, so nothing
* interrupt level will suddenly eat the receive_queue.
*
* Look at current nfs client by the way...
* However, this function was corrent in any case. 8)
*/
unsigned long cpu_flags;
spin_lock_irqsave(&sk->sk_receive_queue.lock, cpu_flags);
skb = skb_peek(&sk->sk_receive_queue);
if (skb) {
*peeked = skb->peeked;
if (flags & MSG_PEEK) {
skb->peeked = 1;
atomic_inc(&skb->users);
} else
__skb_unlink(skb, &sk->sk_receive_queue);
}
spin_unlock_irqrestore(&sk->sk_receive_queue.lock, cpu_flags);
if (skb)
return skb;
/* User doesn't want to wait */
error = -EAGAIN;
if (!timeo)
goto no_packet;
} while (!wait_for_packet(sk, err, &timeo));
return NULL;
no_packet:
*err = error;
return NULL;
}
摘除過程：
static inline void __skb_unlink(struct sk_buff *skb, struct sk_buff_head *list)
{
struct sk_buff *next, *prev;
list->qlen--;
next = skb->next;
prev = skb->prev;
skb->next = skb->prev = NULL;
next->prev = prev;
prev->next = next;
}
6.2 將該sk_buff內容轉換為msghdr結構
內核態采用netlink_unicast函數發送數據，數據結構存儲為:nlmsghdr+data，內核發送即以這種方式組sk_buff
而用戶態采用sendmsg等格式，發送數據方式不是sk_buff，而是msghdr格式,該格式定義如下：
/*
* As we do 4.4BSD message passing we use a 4.4BSD message passing
* system, not 4.3. Thus msg_accrights(len) are now missing. They
* belong in an obscure libc emulation or the bin.
*/
struct msghdr { 位於linux/socket.h頭文件中
void * msg_name; /* Socket name */ 一般存儲對方(發送方的地址信息，即netlink_nl信息)
int msg_namelen; /* Length of name */
struct iovec * msg_iov; /* Data blocks */ 存儲來自對方的實際數據信息
__kernel_size_t msg_iovlen; /* Number of blocks */
void * msg_control; /* Per protocol magic (eg BSD file descriptor passing) */
__kernel_size_t msg_controllen; /* Length of cmsg list */
unsigned msg_flags;
};
該數據分組結構單元定義如下：
struct iovec
{
void __user * iov_base; /* BSD uses caddr_t (1003.1g requires void *) */
__kernel_size_t iov_len; /* Must be size_t (1003.1g) */
};
轉換函數如下定義：
/**
* skb_copy_datagram_iovec - Copy a datagram to an iovec.
* @skb: buffer to copy
* @offset: offset in the buffer to start copying from
* @to: io vector to copy to
* @len: amount of data to copy from buffer to iovec
*
* Note: the iovec is modified during the copy.
*/
int skb_copy_datagram_iovec(const struct sk_buff *skb, int offset,
struct iovec *to, int len)
{
int start = skb_headlen(skb);
int i, copy = start - offset;
struct sk_buff *frag_iter;
trace_skb_copy_datagram_iovec(skb, len);
/* Copy header. */
if (copy > 0) {
if (copy > len)
copy = len;
if (memcpy_toiovec(to, skb->data + offset, copy))
goto fault;
if ((len -= copy) == 0)
return 0;
offset += copy;
}
/* Copy paged appendix. Hmm... why does this look so complicated? */
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
int end;
WARN_ON(start > offset + len);
end = start + skb_shinfo(skb)->frags[i].size;
if ((copy = end - offset) > 0) {
int err;
u8 *vaddr;
skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
struct page *page = frag->page;
if (copy > len)
copy = len;
vaddr = kmap(page);
err = memcpy_toiovec(to, vaddr + frag->page_offset +
offset - start, copy);
kunmap(page);
if (err)
goto fault;
if (!(len -= copy))
return 0;
offset += copy;
}
start = end;
}
skb_walk_frags(skb, frag_iter) {
int end;
WARN_ON(start > offset + len);
end = start + frag_iter->len;
if ((copy = end - offset) > 0) {
if (copy > len)
copy = len;
if (skb_copy_datagram_iovec(frag_iter,
offset - start,
to, copy))
goto fault;
if ((len -= copy) == 0)
return 0;
offset += copy;
}
start = end;
}
if (!len)
return 0;
fault:
return -EFAULT;
}
7 內核態接收用戶態發送的數據
static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
struct msghdr *msg, size_t len)
{
struct sock_iocb *siocb = kiocb_to_siocb(kiocb);
struct sock *sk = sock->sk;
struct netlink_sock *nlk = nlk_sk(sk);
struct sockaddr_nl *addr = msg->msg_name;/ /目的地址信息
u32 dst_pid;
u32 dst_group;
struct sk_buff *skb;
int err;
struct scm_cookie scm;
if (msg->msg_flags&MSG_OOB)
return -EOPNOTSUPP;
if (NULL == siocb->scm)
siocb->scm = &scm;
err = scm_send(sock, msg, siocb->scm);
if (err < 0)
return err;
if (msg->msg_namelen) {
if (addr->nl_family != AF_NETLINK)
return -EINVAL;
dst_pid = addr->nl_pid;
dst_group = ffs(addr->nl_groups);
if (dst_group && !netlink_capable(sock, NL_NONROOT_SEND))
return -EPERM;
} else {
dst_pid = nlk->dst_pid;
dst_group = nlk->dst_group;
}
if (!nlk->pid) {
err = netlink_autobind(sock);
if (err)
goto out;
}
err = -EMSGSIZE;
if (len > sk->sk_sndbuf - 32)
goto out;
err = -ENOBUFS;
skb = alloc_skb(len, GFP_KERNEL); 分配一個sk_buff結構，將msghdr結構轉化為sk_buff結構
if (skb == NULL)
goto out;
NETLINK_CB(skb).pid = nlk->pid; //填寫本地的pid信息
NETLINK_CB(skb).dst_group = dst_group;
NETLINK_CB(skb).loginuid = audit_get_loginuid(current);
NETLINK_CB(skb).sessionid = audit_get_sessionid(current);
security_task_getsecid(current, &(NETLINK_CB(skb).sid));
memcpy(NETLINK_CREDS(skb), &siocb->scm->creds, sizeof(struct ucred));
/* What can I do? Netlink is asynchronous, so that
we will have to save current capabilities to
check them, when this message will be delivered
to corresponding kernel module. --ANK (980802)
*/
err = -EFAULT; 數據拷貝進sk_buff中
if (memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len)) {
kfree_skb(skb);
goto out;
}
err = security_netlink_send(sk, skb);
if (err) {
kfree_skb(skb);
goto out;
}
if (dst_group) {
atomic_inc(&skb->users);
netlink_broadcast(sk, skb, dst_pid, dst_group, GFP_KERNEL);
}
err = netlink_unicast(sk, skb, dst_pid, msg->msg_flags&MSG_DONTWAIT);
out:
return err;
}
