最近的研究方向：Nginx
分类： LINUX
2016-09-14 11:32:56
在用户空间创建了一个socket后，返回值是一个文件描述符，下面分析一下创建socket时怎么和文件描述符联系的。在SYSCALL_DEFINE3(socket, int, family, int, type, int, protocol)最后调用sock_map_fd进行关联，其中返回的retval就是用户空间获取的文件描述符fd，sock就是调用sock_create创建成功的socket.
sock_map_fd()主要用于对socket的*file指针初始化，经过sock_map_fd()操作后，socket就通过其*file指针与VFS管理的文件进行了关联，便可以进行文件的各种操作，如read、write、lseek、ioctl等.
retval = sock_map_fd(sock, flags & (O_CLOEXEC | O_NONBLOCK));
static int sock_map_fd(struct socket *sock, int flags)
{
struct file *newfile;
int fd = get_unused_fd_flags(flags);//根据flags获取没有使用的fd，具体分析见1.2.1
if (unlikely(fd < 0))
return fd;
newfile = sock_alloc_file(sock, flags, NULL);
if (likely(!IS_ERR(newfile))) {
fd_install(fd, newfile);
return fd;
}
put_unused_fd(fd);
return PTR_ERR(newfile);
}
get_unused_fd_flags()函数调用__alloc_fd分配一个新的可用的fd
int __alloc_fd(struct files_struct *files,
unsigned start, unsigned end, unsigned flags)
{
unsigned int fd;
int error;
struct fdtable *fdt;
spin_lock(&files->file_lock);
repeat:
/*得到本进程的文件描述符表*/
fdt = files_fdtable(files);
fd = start;//从start开始，这里的start为0
/* files->next_fd为上一次查找确定的下一个可用空闲的文件描述符，这样可以提高获取的效率，如果fd小于files->next_fd的话就可以直接使用next_fd */
if (fd < files->next_fd)
fd = files->next_fd;
/*当fd小于目前进程支持的最大的描述符号，那么可以通过fds_bits位图，从fd位开始查找，找到下一个0位，即下一个空闲描述符。*/
if (fd < fdt->max_fds)
fd = find_next_zero_bit(fdt->open_fds, fdt->max_fds, fd);
/*
* N.B. For clone tasks sharing a files structure, this test
* will limit the total number of files that can be opened.
*/
error = -EMFILE;
if (fd >= end)
goto out;
/* 如需要则扩展文件描述符表 */
error = expand_files(files, fd);
if (error < 0)
goto out;
/*
* If we needed to expand the fs array we
* might have blocked - try again.
*/
if (error)
goto repeat;
/*
设置next_fd，用于下次加速查找空闲的fd。
当start大于next_fd时，不会设置next_fd以避免文件描述符的不连续
*/
if (start <= files->next_fd)
files->next_fd = fd + 1;
/* 将fd添加到已打开的文件描述符表中 */
__set_open_fd(fd, fdt);
if (flags & O_CLOEXEC)
__set_close_on_exec(fd, fdt);
else
__clear_close_on_exec(fd, fdt);
error = fd;
#if 1
/* Sanity check */
if (rcu_dereference_raw(fdt->fd[fd]) != NULL) {
printk(KERN_WARNING "alloc_fd: slot %d not NULL!\n", fd);
rcu_assign_pointer(fdt->fd[fd], NULL);
}
#endif
out:
spin_unlock(&files->file_lock);
return error;
}
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) {//这里的dname为空
name.name = dname;
name.len = strlen(name.name);
} else if (sock->sk) {
/*这里的name应该是TCP 根据struct proto tcp_prot */
name.name = sock->sk->sk_prot_creator->name;
name.len = strlen(name.name);
}
/*申请一个新的dentry,其中sock_mnt->mnt_sb在前面已经分析过了，是一个sock_fs_type文件系统挂载点，*/
path.dentry = d_alloc_pseudo(sock_mnt->mnt_sb, &name);
if (unlikely(!path.dentry))
return ERR_PTR(-ENOMEM);
path.mnt = mntget(sock_mnt);
/*将文件操作的函数绑定到inode,对于dentry是在sockfs_mount函数中sockfs_dentry_operations，该函数在sock_init是调用，在前面有分析 */
d_instantiate(path.dentry, SOCK_INODE(sock));
SOCK_INODE(sock)->i_fop = &socket_file_ops;
/*申请新的file，将path,file,关联起来*/
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;//sock->file和刚分配的file关联起来
file->f_flags = O_RDWR | (flags & O_NONBLOCK);//设置file的标志
file->private_data = sock;//file的私有数据指针指向sock.
return file;
}
Socket创建流程图
在分析中经常看到此种类型的强制转换inet = inet_sk(sk);，其中inet被定义为struct inet_sock *inet;结构体，我们看结构体的定义sock结构体的大小小于struct inet_sock，这样是无法进行强制类型转换的，但在实际分配的过程中sock分配的大小为tcp_sock的大小，而该结构足够大。
struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
struct proto *prot)
{
struct sock *sk;
sk = sk_prot_alloc(prot, priority | __GFP_ZERO, family);
if (sk) {
sk->sk_family = family;
/*
* See comment in struct sock definition to understand
* why we need sk_prot_creator -acme
*/
sk->sk_prot = sk->sk_prot_creator = prot;
sock_lock_init(sk);
sock_net_set(sk, get_net(net));
atomic_set(&sk->sk_wmem_alloc, 1);
sock_update_classid(sk);
sock_update_netprioidx(sk);
}
return sk;
}
static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority,
int family)
{
struct sock *sk;
struct kmem_cache *slab;
/*这里分配内存空间时，分为两种情况，第一种情况是从高速缓存上分配，第二种是普通的分配*/
slab = prot->slab;
if (slab != NULL) {
sk = kmem_cache_alloc(slab, priority & ~__GFP_ZERO);---------------------（1）
if (!sk)
return sk;
if (priority & __GFP_ZERO) {
if (prot->clear_sk)
prot->clear_sk(sk, prot->obj_size);
else
sk_prot_clear_nulls(sk, prot->obj_size);
}
} else
sk = kmalloc(prot->obj_size, priority);---------------------------（2）
if (sk != NULL) {
kmemcheck_annotate_bitfield(sk, flags);
if (security_sk_alloc(sk, family, priority))
goto out_free;
if (!try_module_get(prot->owner))
goto out_free_sec;
sk_tx_queue_clear(sk);
}
return sk;
out_free_sec:
security_sk_free(sk);
out_free:
if (slab != NULL)
kmem_cache_free(slab, sk);
else
kfree(sk);
return NULL;
}
（1）第一种情况：sk = kmem_cache_alloc(slab, priority & ~__GFP_ZERO) 这里的slap等于slab = prot->slab;也就是函数传递过来的struct proto *prot，再看一下这个结构体是怎么定义的？在inet_create函数中sk = sk_alloc(net, PF_INET, GFP_KERNEL, answer_prot);，这里的answer_prot为answer_prot = answer->prot;在看一下answer->prot是如何来的？
在inet_ctreate函数中通过遍历inetsw数组获取到struct inet_protosw *answer;
list_for_each_entry_rcu(answer, &inetsw[sock->type], list) {
err = 0;
/* Check the non-wild match. */
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;
}
其中inetsw的定义下面类型的数组，如果是SOCK_STREAM类型的socket，这里的prot = tcp_prot
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,
}
};
再看一下
struct proto tcp_prot = {
.name = "TCP",
.owner = THIS_MODULE,
.close = tcp_close,
.connect = tcp_v4_connect,
.disconnect = tcp_disconnect,
.accept = inet_csk_accept,
.ioctl = tcp_ioctl,
.init = tcp_v4_init_sock,
.destroy = tcp_v4_destroy_sock,
.shutdown = tcp_shutdown,
.setsockopt = tcp_setsockopt,
.getsockopt = tcp_getsockopt,
.recvmsg = tcp_recvmsg,
.sendmsg = tcp_sendmsg,
.sendpage = tcp_sendpage,
.backlog_rcv = tcp_v4_do_rcv,
.release_cb = tcp_release_cb,
.mtu_reduced = tcp_v4_mtu_reduced,
.hash = inet_hash,
.unhash = inet_unhash,
.get_port = inet_csk_get_port,
.enter_memory_pressure = tcp_enter_memory_pressure,
.stream_memory_free = tcp_stream_memory_free,
.sockets_allocated = &tcp_sockets_allocated,
.orphan_count = &tcp_orphan_count,
.memory_allocated = &tcp_memory_allocated,
.memory_pressure = &tcp_memory_pressure,
.sysctl_mem = sysctl_tcp_mem,
.sysctl_wmem = sysctl_tcp_wmem,
.sysctl_rmem = sysctl_tcp_rmem,
.max_header = MAX_TCP_HEADER,
.obj_size = sizeof(struct tcp_sock),
.slab_flags = SLAB_DESTROY_BY_RCU,
.twsk_prot = &tcp_timewait_sock_ops,
.rsk_prot = &tcp_request_sock_ops,
.h.hashinfo = &tcp_hashinfo,
.no_autobind = true,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_tcp_setsockopt,
.compat_getsockopt = compat_tcp_getsockopt,
#endif
#ifdef CONFIG_MEMCG_KMEM
.init_cgroup = tcp_init_cgroup,
.destroy_cgroup = tcp_destroy_cgroup,
.proto_cgroup = tcp_proto_cgroup,
#endif
};
在af_inet.c文件中的inet_init函数中的
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;
//该函数是注册tcp_prot，在该函数中对tcp_prot->slab进行内存分配
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
/*
* 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. 对inetsw进行初始化操作*/
for (r = &inetsw[0]; r < &inetsw[SOCK_MAX]; ++r)
INIT_LIST_HEAD(r);
/*将inetsw_array 加入到对于的inetsw链表中，就可以在inet_create 函数中进行遍历*/
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;
}
在proto_register函数中，主要是关注prot->slab进行了初始化。
int proto_register(struct proto *prot, int alloc_slab)
{
if (alloc_slab) {
prot->slab = kmem_cache_create(prot->name, prot->obj_size, 0,
SLAB_HWCACHE_ALIGN | prot->slab_flags,
NULL);// 这里的饿prot->obj_size为.obj_size = sizeof(struct tcp_sock),
if (prot->slab == NULL) {
pr_crit("%s: Can't create sock SLAB cache!\n",
prot->name);
goto out;
}
……………………..
}
（2）对于第二种情况，主要prot->obj_size，就是struct proto tcp_prot 中初始化的.obj_size = sizeof(struct tcp_sock)。sk = kmalloc(prot->obj_size, priority);---------------------------（2）
下面是五个相关的数据结构，tcp_sock结构体占用的空间是最大的，所以在分配内存空间时，都是分配的tcp_sock的大小，这样在后面进行强制转换的过程中可以保证正确。
