文章目录
socket
socket是进程通信方式之一,可以用于本地两个进程,也可以用于远程两台机器上的进程进行通信。
socket基本操作
socket函数用于创建创建一个socket描述符(socket descriptor),它唯一标识一个socket。
int socket(int domain, int type, int protocol);
参数 | 意义 |
---|---|
domain | 即协议域,又称为协议族(family)。常用的协议族有,AF_INET、AF_INET6、AF_LOCAL(或称AF_UNIX,Unix域socket)、AF_ROUTE等等。协议族决定了socket的地址类型,在通信中必须采用对应的地址,如AF_INET决定了要用ipv4地址(32位的)与端口号(16位的)的组合、AF_UNIX决定了要用一个绝对路径名作为地址。 |
type | 指定socket类型。常用的socket类型有,SOCK_STREAM、SOCK_DGRAM、SOCK_RAW、SOCK_PACKET、SOCK_SEQPACKET等等 |
protocol | 指定协议。常用的协议有,IPPROTO_TCP、IPPTOTO_UDP、IPPROTO_SCTP、IPPROTO_TIPC等,它们分别对应TCP传输协议、UDP传输协议、STCP传输协议、TIPC传输协议 |
分层框架
struct net_proto_family
net_proto_family表示地址协议簇,用于创建不同地址簇的接口,向用户空间提供创建socket接口。
不同协议簇模块调用sock_register注册协议族,保存到net_families全局数组中。
支持协议簇如下:
/* Supported address families. */
#define AF_UNSPEC 0
#define AF_UNIX 1 /* Unix domain sockets */
#define AF_LOCAL 1 /* POSIX name for AF_UNIX */
#define AF_INET 2 /* Internet IP Protocol */
#define AF_AX25 3 /* Amateur Radio AX.25 */
#define AF_IPX 4 /* Novell IPX */
#define AF_APPLETALK 5 /* AppleTalk DDP */
#define AF_NETROM 6 /* Amateur Radio NET/ROM */
#define AF_BRIDGE 7 /* Multiprotocol bridge */
#define AF_ATMPVC 8 /* ATM PVCs */
#define AF_X25 9 /* Reserved for X.25 project */
#define AF_INET6 10 /* IP version 6 */
#define AF_ROSE 11 /* Amateur Radio X.25 PLP */
#define AF_DECnet 12 /* Reserved for DECnet project */
#define AF_NETBEUI 13 /* Reserved for 802.2LLC project*/
#define AF_SECURITY 14 /* Security callback pseudo AF */
#define AF_KEY 15 /* PF_KEY key management API */
#define AF_NETLINK 16
#define AF_ROUTE AF_NETLINK /* Alias to emulate 4.4BSD */
#define AF_PACKET 17 /* Packet family */
#define AF_ASH 18 /* Ash */
#define AF_ECONET 19 /* Acorn Econet */
#define AF_ATMSVC 20 /* ATM SVCs */
#define AF_RDS 21 /* RDS sockets */
#define AF_SNA 22 /* Linux SNA Project (nutters!) */
#define AF_IRDA 23 /* IRDA sockets */
#define AF_PPPOX 24 /* PPPoX sockets */
#define AF_WANPIPE 25 /* Wanpipe API Sockets */
#define AF_LLC 26 /* Linux LLC */
#define AF_CAN 29 /* Controller Area Network */
#define AF_TIPC 30 /* TIPC sockets */
#define AF_BLUETOOTH 31 /* Bluetooth sockets */
#define AF_IUCV 32 /* IUCV sockets */
#define AF_RXRPC 33 /* RxRPC sockets */
#define AF_ISDN 34 /* mISDN sockets */
#define AF_PHONET 35 /* Phonet sockets */
#define AF_IEEE802154 36 /* IEEE802154 sockets */
#define AF_CAIF 37 /* CAIF sockets */
#define AF_ALG 38 /* Algorithm sockets */
#define AF_NFC 39 /* NFC sockets */
#define AF_VSOCK 40 /* vSockets */
#define AF_MAX 41 /* For now.. */
/* Protocol families, same as address families. */
#define PF_UNSPEC AF_UNSPEC
#define PF_UNIX AF_UNIX
#define PF_LOCAL AF_LOCAL
#define PF_INET AF_INET
#define PF_AX25 AF_AX25
#define PF_IPX AF_IPX
#define PF_APPLETALK AF_APPLETALK
#define PF_NETROM AF_NETROM
#define PF_BRIDGE AF_BRIDGE
#define PF_ATMPVC AF_ATMPVC
#define PF_X25 AF_X25
#define PF_INET6 AF_INET6
#define PF_ROSE AF_ROSE
#define PF_DECnet AF_DECnet
#define PF_NETBEUI AF_NETBEUI
#define PF_SECURITY AF_SECURITY
#define PF_KEY AF_KEY
#define PF_NETLINK AF_NETLINK
#define PF_ROUTE AF_ROUTE
#define PF_PACKET AF_PACKET
#define PF_ASH AF_ASH
#define PF_ECONET AF_ECONET
#define PF_ATMSVC AF_ATMSVC
#define PF_RDS AF_RDS
#define PF_SNA AF_SNA
#define PF_IRDA AF_IRDA
#define PF_PPPOX AF_PPPOX
#define PF_WANPIPE AF_WANPIPE
#define PF_LLC AF_LLC
#define PF_CAN AF_CAN
#define PF_TIPC AF_TIPC
#define PF_BLUETOOTH AF_BLUETOOTH
#define PF_IUCV AF_IUCV
#define PF_RXRPC AF_RXRPC
#define PF_ISDN AF_ISDN
#define PF_PHONET AF_PHONET
#define PF_IEEE802154 AF_IEEE802154
#define PF_CAIF AF_CAIF
#define PF_ALG AF_ALG
#define PF_NFC AF_NFC
#define PF_VSOCK AF_VSOCK
#define PF_MAX AF_MAX
struct proto
struct proto 表示不同协议的管理结构,向下面向协议。通过proto_register接口注册到proto_list管理链表,同时创建kmem_cache slab进行缓存管理。
inet协议簇中有tcp_prot,udp_prot,raw_prot,ping_prot
/* Networking protocol blocks we attach to sockets.
* socket layer -> transport layer interface
* transport -> network interface is defined by struct inet_proto
*/
struct proto {
void (*close)(struct sock *sk,
long timeout);
int (*connect)(struct sock *sk,
struct sockaddr *uaddr,
int addr_len);
int (*disconnect)(struct sock *sk, int flags);
struct sock * (*accept)(struct sock *sk, int flags, int *err);
int (*ioctl)(struct sock *sk, int cmd,
unsigned long arg);
int (*init)(struct sock *sk);
void (*destroy)(struct sock *sk);
void (*shutdown)(struct sock *sk, int how);
int (*setsockopt)(struct sock *sk, int level,
int optname, char __user *optval,
unsigned int optlen);
int (*getsockopt)(struct sock *sk, int level,
int optname, char __user *optval,
int __user *option);
#ifdef CONFIG_COMPAT
int (*compat_setsockopt)(struct sock *sk,
int level,
int optname, char __user *optval,
unsigned int optlen);
int (*compat_getsockopt)(struct sock *sk,
int level,
int optname, char __user *optval,
int __user *option);
int (*compat_ioctl)(struct sock *sk,
unsigned int cmd, unsigned long arg);
#endif
int (*sendmsg)(struct kiocb *iocb, struct sock *sk,
struct msghdr *msg, size_t len);
int (*recvmsg)(struct kiocb *iocb, struct sock *sk,
struct msghdr *msg,
size_t len, int noblock, int flags,
int *addr_len);
int (*sendpage)(struct sock *sk, struct page *page,
int offset, size_t size, int flags);
int (*bind)(struct sock *sk,
struct sockaddr *uaddr, int addr_len);
int (*backlog_rcv) (struct sock *sk,
struct sk_buff *skb);
void (*release_cb)(struct sock *sk);
/* Keeping track of sk's, looking them up, and port selection methods. */
void (*hash)(struct sock *sk);
void (*unhash)(struct sock *sk);
void (*rehash)(struct sock *sk);
int (*get_port)(struct sock *sk, unsigned short snum);
void (*clear_sk)(struct sock *sk, int size);
/* Keeping track of sockets in use */
#ifdef CONFIG_PROC_FS
unsigned int inuse_idx;
#endif
/* Memory pressure */
void (*enter_memory_pressure)(struct sock *sk);
atomic_long_t *memory_allocated; /* Current allocated memory. */
struct percpu_counter *sockets_allocated; /* Current number of sockets. */
/*
* Pressure flag: try to collapse.
* Technical note: it is used by multiple contexts non atomically.
* All the __sk_mem_schedule() is of this nature: accounting
* is strict, actions are advisory and have some latency.
*/
int *memory_pressure;
long *sysctl_mem;
int *sysctl_wmem;
int *sysctl_rmem;
int max_header;
bool no_autobind;
struct kmem_cache *slab;
unsigned int obj_size;
int slab_flags;
struct percpu_counter *orphan_count;
struct request_sock_ops *rsk_prot;
struct timewait_sock_ops *twsk_prot;
union {
struct inet_hashinfo *hashinfo;
struct udp_table *udp_table;
struct raw_hashinfo *raw_hash;
} h;
struct module *owner;
char name[32];
struct list_head node;
#ifdef SOCK_REFCNT_DEBUG
atomic_t socks;
#endif
#ifdef CONFIG_MEMCG_KMEM
/*
* cgroup specific init/deinit functions. Called once for all
* protocols that implement it, from cgroups populate function.
* This function has to setup any files the protocol want to
* appear in the kmem cgroup filesystem.
*/
int (*init_cgroup)(struct mem_cgroup *memcg,
struct cgroup_subsys *ss);
void (*destroy_cgroup)(struct mem_cgroup *memcg);
struct cg_proto *(*proto_cgroup)(struct mem_cgroup *memcg);
#endif
};
struct inet_protosw
struct inet_protosw为pf_inet地址簇中数据结构,管理用户空间socket接口和协议栈接口。
inet_protosw中prot 代表协议栈操作接口,ops代表着socket管理接口,通过inet_protosw把socket和协议栈联系起来了。
type代表socekt类型,protocol代表传输层协议类型,代表层面不同,可以看作对socket控制面管理,对协议数据面操作。
不同地址簇有不同的管理结构。
/* This is used to register socket interfaces for IP protocols. */
struct inet_protosw {
struct list_head list;
/* These two fields form the lookup key. */
unsigned short type; /* This is the 2nd argument to socket(2). */
unsigned short protocol; /* This is the L4 protocol number. */
struct proto *prot;
const struct proto_ops *ops;
char no_check; /* checksum on rcv/xmit/none? */
unsigned char flags; /* See INET_PROTOSW_* below. */
};
inetsw_array是pf_inet簇中所有的inet_protosw
inetsw链表用来管理所有的inet_protosw
static struct inet_protosw inetsw_array[] =
{
{
.type = SOCK_STREAM,
.protocol = IPPROTO_TCP,
.prot = &tcp_prot,
.ops = &inet_stream_ops,
.no_check = 0,
.flags = INET_PROTOSW_PERMANENT |
INET_PROTOSW_ICSK,
},
{
.type = SOCK_DGRAM,
.protocol = IPPROTO_UDP,
.prot = &udp_prot,
.ops = &inet_dgram_ops,
.no_check = UDP_CSUM_DEFAULT,
.flags = INET_PROTOSW_PERMANENT,
},
{
.type = SOCK_DGRAM,
.protocol = IPPROTO_ICMP,
.prot = &ping_prot,
.ops = &inet_dgram_ops,
.no_check = UDP_CSUM_DEFAULT,
.flags = INET_PROTOSW_REUSE,
},
{
.type = SOCK_RAW,
.protocol = IPPROTO_IP, /* wild card */
.prot = &raw_prot,
.ops = &inet_sockraw_ops,
.no_check = UDP_CSUM_DEFAULT,
.flags = INET_PROTOSW_REUSE,
}
};
ops 管理socket
struct proto_ops {
int family;
struct module *owner;
int (*release) (struct socket *sock);
int (*bind) (struct socket *sock,
struct sockaddr *myaddr,
int sockaddr_len);
int (*connect) (struct socket *sock,
struct sockaddr *vaddr,
int sockaddr_len, int flags);
int (*socketpair)(struct socket *sock1,
struct socket *sock2);
int (*accept) (struct socket *sock,
struct socket *newsock, int flags);
int (*getname) (struct socket *sock,
struct sockaddr *addr,
int *sockaddr_len, int peer);
unsigned int (*poll) (struct file *file, struct socket *sock,
struct poll_table_struct *wait);
int (*ioctl) (struct socket *sock, unsigned int cmd,
unsigned long arg);
#ifdef CONFIG_COMPAT
int (*compat_ioctl) (struct socket *sock, unsigned int cmd,
unsigned long arg);
#endif
int (*listen) (struct socket *sock, int len);
int (*shutdown) (struct socket *sock, int flags);
int (*setsockopt)(struct socket *sock, int level,
int optname, char __user *optval, unsigned int optlen);
int (*getsockopt)(struct socket *sock, int level,
int optname, char __user *optval, int __user *optlen);
#ifdef CONFIG_COMPAT
int (*compat_setsockopt)(struct socket *sock, int level,
int optname, char __user *optval, unsigned int optlen);
int (*compat_getsockopt)(struct socket *sock, int level,
int optname, char __user *optval, int __user *optlen);
#endif
int (*sendmsg) (struct kiocb *iocb, struct socket *sock,
struct msghdr *m, size_t total_len);
/* Notes for implementing recvmsg:
* ===============================
* msg->msg_namelen should get updated by the recvmsg handlers
* iff msg_name != NULL. It is by default 0 to prevent
* returning uninitialized memory to user space. The recvfrom
* handlers can assume that msg.msg_name is either NULL or has
* a minimum size of sizeof(struct sockaddr_storage).
*/
int (*recvmsg) (struct kiocb *iocb, struct socket *sock,
struct msghdr *m, size_t total_len,
int flags);
int (*mmap) (struct file *file, struct socket *sock,
struct vm_area_struct * vma);
ssize_t (*sendpage) (struct socket *sock, struct page *page,
int offset, size_t size, int flags);
ssize_t (*splice_read)(struct socket *sock, loff_t *ppos,
struct pipe_inode_info *pipe, size_t len, unsigned int flags);
int (*set_peek_off)(struct sock *sk, int val);
};
struct packet_type
前面介绍的inet_protosw,struct proto,struct proto_ops 表示用户空间到socket,协议proto之间的接口。
而struct packet_type 表示网络设备和协议之间的接口
dev_add_pack函数用于packet_type 注册,ptype_base或ptype_all 链表中。
struct packet_type {
__be16 type; /* This is really htons(ether_type). */
struct net_device *dev; /* NULL is wildcarded here */
int (*func) (struct sk_buff *,
struct net_device *,
struct packet_type *,
struct net_device *);
bool (*id_match)(struct packet_type *ptype,
struct sock *sk);
void *af_packet_priv;
struct list_head list;
};
例如,ip协议ip_packet_type
网卡驱动收到数据递交给设备抽象层,会检查协议类型,如果和type 匹配,则回调func 函数,传递数据到协议栈。
static struct packet_type ip_packet_type __read_mostly = {
.type = cpu_to_be16(ETH_P_IP),
.func = ip_rcv,
};
dev_add_pack(&ip_packet_type);
SYSCALL_DEFINE3(socket, int, family, int, type, int, protocol)
{
int retval;
struct socket *sock;
int flags;
/* Check the SOCK_* constants for consistency. */
BUILD_BUG_ON(SOCK_CLOEXEC != O_CLOEXEC);
BUILD_BUG_ON((SOCK_MAX | SOCK_TYPE_MASK) != SOCK_TYPE_MASK);
BUILD_BUG_ON(SOCK_CLOEXEC & SOCK_TYPE_MASK);
BUILD_BUG_ON(SOCK_NONBLOCK & SOCK_TYPE_MASK);
flags = type & ~SOCK_TYPE_MASK;
if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK))
return -EINVAL;
type &= SOCK_TYPE_MASK;
if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK))
flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK;
retval = sock_create(family, type, protocol, &sock);
if (retval < 0)
goto out;
retval = sock_map_fd(sock, flags & (O_CLOEXEC | O_NONBLOCK));
if (retval < 0)
goto out_release;
out:
/* It may be already another descriptor 8) Not kernel problem. */
return retval;
out_release:
sock_release(sock);
return retval;
}
static int __init inet_init(void)
{
struct inet_protosw *q;
struct list_head *r;
int rc = -EINVAL;
BUILD_BUG_ON(sizeof(struct inet_skb_parm) > FIELD_SIZEOF(struct sk_buff, cb));
sysctl_local_reserved_ports = kzalloc(65536 / 8, GFP_KERNEL);
if (!sysctl_local_reserved_ports)
goto out;
rc = proto_register(&tcp_prot, 1);
if (rc)
goto out_free_reserved_ports;
rc = proto_register(&udp_prot, 1);
if (rc)
goto out_unregister_tcp_proto;
rc = proto_register(&raw_prot, 1);
if (rc)
goto out_unregister_udp_proto;
rc = proto_register(&ping_prot, 1);
if (rc)
goto out_unregister_raw_proto;
/*
* Tell SOCKET that we are alive...
*/
(void)sock_register(&inet_family_ops);
#ifdef CONFIG_SYSCTL
ip_static_sysctl_init();
#endif
tcp_prot.sysctl_mem = init_net.ipv4.sysctl_tcp_mem;
/*
* Add all the base protocols.
*/
if (inet_add_protocol(&icmp_protocol, IPPROTO_ICMP) < 0)
pr_crit("%s: Cannot add ICMP protocol\n", __func__);
if (inet_add_protocol(&udp_protocol, IPPROTO_UDP) < 0)
pr_crit("%s: Cannot add UDP protocol\n", __func__);
if (inet_add_protocol(&tcp_protocol, IPPROTO_TCP) < 0)
pr_crit("%s: Cannot add TCP protocol\n", __func__);
#ifdef CONFIG_IP_MULTICAST
if (inet_add_protocol(&igmp_protocol, IPPROTO_IGMP) < 0)
pr_crit("%s: Cannot add IGMP protocol\n", __func__);
#endif
/* Register the socket-side information for inet_create. */
for (r = &inetsw[0]; r < &inetsw[SOCK_MAX]; ++r)
INIT_LIST_HEAD(r);
for (q = inetsw_array; q < &inetsw_array[INETSW_ARRAY_LEN]; ++q)
inet_register_protosw(q);
/*
* Set the ARP module up
*/
arp_init();
/*
* Set the IP module up
*/
ip_init();
tcp_v4_init();
/* Setup TCP slab cache for open requests. */
tcp_init();
/* Setup UDP memory threshold */
udp_init();
/* Add UDP-Lite (RFC 3828) */
udplite4_register();
ping_init();
/*
* Set the ICMP layer up
*/
if (icmp_init() < 0)
panic("Failed to create the ICMP control socket.\n");
/*
* Initialise the multicast router
*/
#if defined(CONFIG_IP_MROUTE)
if (ip_mr_init())
pr_crit("%s: Cannot init ipv4 mroute\n", __func__);
#endif
/*
* Initialise per-cpu ipv4 mibs
*/
if (init_ipv4_mibs())
pr_crit("%s: Cannot init ipv4 mibs\n", __func__);
ipv4_proc_init();
ipfrag_init();
dev_add_pack(&ip_packet_type);
rc = 0;
out:
return rc;
out_unregister_raw_proto:
proto_unregister(&raw_prot);
out_unregister_udp_proto:
proto_unregister(&udp_prot);
out_unregister_tcp_proto:
proto_unregister(&tcp_prot);
out_free_reserved_ports:
kfree(sysctl_local_reserved_ports);
goto out;
}
fs_initcall(inet_init);
socket创建
前面介绍用户空间调用socket创建socket描述符
int socket(int domain, int type, int protocol);
\net\socket.c中定义了各个socket接口系统调用。
SYSCALL_DEFINE3(socket, int, family, int, type, int, protocol)
{
int retval;
struct socket *sock;
int flags;
/* 创建一个socket */
retval = sock_create(family, type, protocol, &sock);
/* 分配socket描述符 ,关联socekt文件结构 */
retval = sock_map_fd(sock, flags & (O_CLOEXEC | O_NONBLOCK));
out:
/* It may be already another descriptor 8) Not kernel problem. */
return retval;
}
int sock_create(int family, int type, int protocol, struct socket **res)
{
return __sock_create(current->nsproxy->net_ns, family, type, protocol, res, 0);
}
int __sock_create(struct net *net, int family, int type, int protocol,
struct socket **res, int kern)
{
int err;
struct socket *sock;
const struct net_proto_family *pf;
/*
* Allocate the socket and allow the family to set things up. if
* the protocol is 0, the family is instructed to select an appropriate
* default.
*/
/* 分配一个socekt结构 */
sock = sock_alloc();
sock->type = type;
/* 根据协议簇family 找到对应协议簇操作函数 ,前面介绍过 */
pf = rcu_dereference(net_families[family]);
/* 调用对应协议簇的操作函数创建sock ,给sock赋值 */
err = pf->create(net, sock, protocol, kern);
*res = sock;
return 0;
}
比如创建PF_INET协议簇类型的socket
static const struct net_proto_family inet_family_ops = {
.family = PF_INET,
.create = inet_create,
.owner = THIS_MODULE,
};
/*
* Create an inet socket.
*/
static int inet_create(struct net *net, struct socket *sock, int protocol,
int kern)
{
struct sock *sk;
struct inet_protosw *answer;
struct inet_sock *inet;
struct proto *answer_prot;
unsigned char answer_flags;
char answer_no_check;
int try_loading_module = 0;
int err;
sock->state = SS_UNCONNECTED;
/* Look for the requested type/protocol pair. */
lookup_protocol:
err = -ESOCKTNOSUPPORT;
rcu_read_lock();
先根据socket类型type找到inetsw结构,inetsw存储了上层socekt操作函数,和下层协议操作函数,是socekt层和协议层连接切换点。
list_for_each_entry_rcu(answer, &inetsw[sock->type], list) {
err = 0;
/* Check the non-wild match. */
/* 找到对应协议 */
if (protocol == answer->protocol) {
if (protocol != IPPROTO_IP)
break;
} else {
/* Check for the two wild cases. */
if (IPPROTO_IP == protocol) {
protocol = answer->protocol;
break;
}
if (IPPROTO_IP == answer->protocol)
break;
}
err = -EPROTONOSUPPORT;
}
/* 设置 操作 */
sock->ops = answer->ops;/* socket 控制面操作函数 */
answer_prot = answer->prot; /* 协议用户面操作函数,后续send write ioctrl等都会找到ops*/
answer_no_check = answer->no_check;
answer_flags = answer->flags;
rcu_read_unlock();
WARN_ON(answer_prot->slab == NULL);
/* 分配sock 结构,管理socket,并把socket控制操作函数赋值到sock结构中 */
sk = sk_alloc(net, PF_INET, GFP_KERNEL, answer_prot);
if (sk == NULL)
goto out;
err = 0;
sk->sk_no_check = answer_no_check;
if (INET_PROTOSW_REUSE & answer_flags)
sk->sk_reuse = SK_CAN_REUSE;
inet = inet_sk(sk);
inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0;
inet->nodefrag = 0;
if (SOCK_RAW == sock->type) {
inet->inet_num = protocol;
if (IPPROTO_RAW == protocol)
inet->hdrincl = 1;
}
if (ipv4_config.no_pmtu_disc)
inet->pmtudisc = IP_PMTUDISC_DONT;
else
inet->pmtudisc = IP_PMTUDISC_WANT;
inet->inet_id = 0;
/* 把sk放到socket中*/
sock_init_data(sock, sk);
sk->sk_destruct = inet_sock_destruct;
sk->sk_protocol = protocol;
sk->sk_backlog_rcv = sk->sk_prot->backlog_rcv;
inet->uc_ttl = -1;
inet->mc_loop = 1;
inet->mc_ttl = 1;
inet->mc_all = 1;
inet->mc_index = 0;
inet->mc_list = NULL;
inet->rcv_tos = 0;
sk_refcnt_debug_inc(sk);
if (inet->inet_num) {
/* It assumes that any protocol which allows
* the user to assign a number at socket
* creation time automatically
* shares.
*/
inet->inet_sport = htons(inet->inet_num);
/* Add to protocol hash chains. */
sk->sk_prot->hash(sk);
}
if (sk->sk_prot->init) {
err = sk->sk_prot->init(sk);
if (err)
sk_common_release(sk);
}
out:
return err;
out_rcu_unlock:
rcu_read_unlock();
goto out;
}
static int sock_map_fd(struct socket *sock, int flags)
{
struct file *newfile;
int fd = get_unused_fd_flags(flags); /* 获取本进程空闲的fd */
if (unlikely(fd < 0))
return fd;
/* 分配一个socket的file*/
newfile = sock_alloc_file(sock, flags, NULL);
if (likely(!IS_ERR(newfile))) {
fd_install(fd, newfile); /* 关联文件和socekt,返回fd给用户空间 */
return fd;
}
put_unused_fd(fd);
return PTR_ERR(newfile);
}
struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname)
{
struct qstr name = { .name = "" };
struct path path;
struct file *file;
if (dname) {
name.name = dname;
name.len = strlen(name.name);
} else if (sock->sk) {
name.name = sock->sk->sk_prot_creator->name;
name.len = strlen(name.name);
}
path.dentry = d_alloc_pseudo(sock_mnt->mnt_sb, &name);
if (unlikely(!path.dentry))
return ERR_PTR(-ENOMEM);
path.mnt = mntget(sock_mnt);
d_instantiate(path.dentry, SOCK_INODE(sock));
SOCK_INODE(sock)->i_fop = &socket_file_ops; /* 文件inode ops为 socket_file_ops */
/* 文件file ops为 socket_file_ops */
file = alloc_file(&path, FMODE_READ | FMODE_WRITE,
&socket_file_ops);
if (unlikely(IS_ERR(file))) {
/* drop dentry, keep inode */
ihold(path.dentry->d_inode);
path_put(&path);
return file;
}
sock->file = file;
file->f_flags = O_RDWR | (flags & O_NONBLOCK);
/* socket结构指针 保存到private_data中 */
file->private_data = sock;
return file;
}
static const struct file_operations socket_file_ops = {
.owner = THIS_MODULE,
.llseek = no_llseek,
.aio_read = sock_aio_read,
.aio_write = sock_aio_write,
.poll = sock_poll,
.unlocked_ioctl = sock_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = compat_sock_ioctl,
#endif
.mmap = sock_mmap,
.open = sock_no_open, /* special open code to disallow open via /proc */
.release = sock_close,
.fasync = sock_fasync,
.sendpage = sock_sendpage,
.splice_write = generic_splice_sendpage,
.splice_read = sock_splice_read,
};
socekt结构
总结:socekt结构上用户空间提供接口,并通过ops管理sock控制面,以及通过sk_prot管理协议数据面
/**
* struct socket - general BSD socket
* @state: socket state (%SS_CONNECTED, etc)
* @type: socket type (%SOCK_STREAM, etc)
* @flags: socket flags (%SOCK_ASYNC_NOSPACE, etc)
* @ops: protocol specific socket operations
* @file: File back pointer for gc
* @sk: internal networking protocol agnostic socket representation
* @wq: wait queue for several uses
*/
struct socket {
socket_state state;
kmemcheck_bitfield_begin(type);
short type;
kmemcheck_bitfield_end(type);
unsigned long flags;
struct socket_wq __rcu *wq;
struct file *file;
struct sock *sk; //通过sk_prot管理协议数据面,比如send,recv等操作
const struct proto_ops *ops; //ops管理socket控制面
};