Socket与系统调用深度分析

SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
{
    unsigned long a[AUDITSC_ARGS];
    unsigned long a0, a1;
    int err;
    unsigned int len;

    if (call < 1 || call > SYS_SENDMMSG)
        return -EINVAL;
    call = array_index_nospec(call, SYS_SENDMMSG + 1);

    len = nargs[call];
    if (len > sizeof(a))
        return -EINVAL;

    /* copy_from_user should be SMP safe. */
    if (copy_from_user(a, args, len))
        return -EFAULT;

    err = audit_socketcall(nargs[call] / sizeof(unsigned long), a);
    if (err)
        return err;

    a0 = a[0];
    a1 = a[1];

    switch (call) {
    case SYS_SOCKET:
        err = __sys_socket(a0, a1, a[2]);
        break;
    case SYS_BIND:
        err = __sys_bind(a0, (struct sockaddr __user *)a1, a[2]);
        break;
    case SYS_CONNECT:
        err = __sys_connect(a0, (struct sockaddr __user *)a1, a[2]);
        break;
    case SYS_LISTEN:
        err = __sys_listen(a0, a1);
        break;
    case SYS_ACCEPT:
        err = __sys_accept4(a0, (struct sockaddr __user *)a1,
                    (int __user *)a[2], 0);
        break;
    case SYS_GETSOCKNAME:
        err =
            __sys_getsockname(a0, (struct sockaddr __user *)a1,
                      (int __user *)a[2]);
        break;
    case SYS_GETPEERNAME:
        err =
            __sys_getpeername(a0, (struct sockaddr __user *)a1,
                      (int __user *)a[2]);
        break;
    case SYS_SOCKETPAIR:
        err = __sys_socketpair(a0, a1, a[2], (int __user *)a[3]);
        break;
    case SYS_SEND:
        err = __sys_sendto(a0, (void __user *)a1, a[2], a[3],
                   NULL, 0);
        break;
    case SYS_SENDTO:
        err = __sys_sendto(a0, (void __user *)a1, a[2], a[3],
                   (struct sockaddr __user *)a[4], a[5]);
        break;
    case SYS_RECV:
        err = __sys_recvfrom(a0, (void __user *)a1, a[2], a[3],
                     NULL, NULL);
        break;
    case SYS_RECVFROM:
        err = __sys_recvfrom(a0, (void __user *)a1, a[2], a[3],
                     (struct sockaddr __user *)a[4],
                     (int __user *)a[5]);
        break;
    case SYS_SHUTDOWN:
        err = __sys_shutdown(a0, a1);
        break;
    case SYS_SETSOCKOPT:
        err = __sys_setsockopt(a0, a1, a[2], (char __user *)a[3],
                       a[4]);
        break;
    case SYS_GETSOCKOPT:
        err =
            __sys_getsockopt(a0, a1, a[2], (char __user *)a[3],
                     (int __user *)a[4]);
        break;
    case SYS_SENDMSG:
        err = __sys_sendmsg(a0, (struct user_msghdr __user *)a1,
                    a[2], true);
        break;
    case SYS_SENDMMSG:
        err = __sys_sendmmsg(a0, (struct mmsghdr __user *)a1, a[2],
                     a[3], true);
        break;
    case SYS_RECVMSG:
        err = __sys_recvmsg(a0, (struct user_msghdr __user *)a1,
                    a[2], true);
        break;
    case SYS_RECVMMSG:
        if (IS_ENABLED(CONFIG_64BIT) || !IS_ENABLED(CONFIG_64BIT_TIME))
            err = __sys_recvmmsg(a0, (struct mmsghdr __user *)a1,
                         a[2], a[3],
                         (struct __kernel_timespec __user *)a[4],
                         NULL);
        else
            err = __sys_recvmmsg(a0, (struct mmsghdr __user *)a1,
                         a[2], a[3], NULL,
                         (struct old_timespec32 __user *)a[4]);
        break;
    case SYS_ACCEPT4:
        err = __sys_accept4(a0, (struct sockaddr __user *)a1,
                    (int __user *)a[2], a[3]);
        break;
    default:
        err = -EINVAL;
        break;
    }
    return err;
}

asmlinkage long sys_socket(int, int, int);

SYSCALL_DEFINE3(socket, int, family, int, type, int, protocol)
{
    int retval;
    struct socket *sock;
    int flags;
 
    
    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;
    /*
     * 获取套接字类型
     */
    type &= SOCK_TYPE_MASK;
 
    /*
     * 如果SOCK_NONBLOCK不等于O_NONBLOCK并且设置了SOCK_NONBLOCK
     * 标志，则将flags中的SOCK_NONBLOCK替换为O_NONBLOCK。
     */
    if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK))
        flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK;
 
    /*
     * 根据协议族类型和套接字类型创建套接字。
     */
    retval = sock_create(family, type, protocol, &sock);
    if (retval < 0)
        goto out;
 
    /*
     * 创建一个新的文件描述符，将新创建的
     * socket实例关联上去。
     */
    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;
}

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;

    /*
     *      Check protocol is in range
     */
    if (family < 0 || family >= NPROTO)
        return -EAFNOSUPPORT;
    if (type < 0 || type >= SOCK_MAX)
        return -EINVAL;

    /* Compatibility.

       This uglymoron is moved from INET layer to here to avoid
       deadlock in module load. (避免模块加载死锁)
     */
    if (family == PF_INET && type == SOCK_PACKET) {
        pr_info_once("%s uses obsolete (PF_INET,SOCK_PACKET)\n",
                 current->comm);
        family = PF_PACKET;
    }
    /*检查权限，并考虑协议集、类型、协议，以及 socket 是在内核中创建还是在用户空间中创建*/
    err = security_socket_create(family, type, protocol, kern);
    if (err)
        return err;

    /*
     *    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.
     */
    sock = sock_alloc();
    if (!sock) {
        net_warn_ratelimited("socket: no more sockets\n");
        return -ENFILE;    /* Not exactly a match, but its the
                   closest posix thing */
    }

    sock->type = type;

#ifdef CONFIG_MODULES
    /* Attempt to load a protocol module if the find failed.
     *
     * 12/09/1996 Marcin: But! this makes REALLY only sense, if the user
     * requested real, full-featured networking support upon configuration.
     * Otherwise module support will break!
     */
    if (rcu_access_pointer(net_families[family]) == NULL)
        request_module("net-pf-%d", family);
#endif

    rcu_read_lock();
    pf = rcu_dereference(net_families[family]);
    err = -EAFNOSUPPORT;
    if (!pf)
        goto out_release;

    /*
     * We will call the ->create function, that possibly is in a loadable
     * module, so we have to bump that loadable module refcnt first.
     */
    if (!try_module_get(pf->owner))
        goto out_release;

    /* Now protected by module ref count */
    rcu_read_unlock();

    err = pf->create(net, sock, protocol, kern);
    if (err < 0)
        goto out_module_put;

    /*
     * Now to bump the refcnt of the [loadable] module that owns this
     * socket at sock_release time we decrement its refcnt.
     */
    if (!try_module_get(sock->ops->owner))
        goto out_module_busy;

    /*
     * Now that we‘re done with the ->create function, the [loadable]
     * module can have its refcnt decremented
     */
    module_put(pf->owner);
    err = security_socket_post_create(sock, family, type, protocol, kern);
    if (err)
        goto out_sock_release;
    *res = sock;

    return 0;

out_module_busy:
    err = -EAFNOSUPPORT;
out_module_put:
    sock->ops = NULL;
    module_put(pf->owner);
out_sock_release:
    sock_release(sock);
    return err;

out_release:
    rcu_read_unlock();
    goto out_sock_release;
}

struct socket *sock_alloc(void)
{
    struct inode *inode;
    struct socket *sock;

    inode = new_inode_pseudo(sock_mnt->mnt_sb);
    if (!inode)
        return NULL;

    sock = SOCKET_I(inode);//该宏根据返回的inode获取到分配的socket_alloc指针

    inode->i_ino = get_next_ino();
    inode->i_mode = S_IFSOCK | S_IRWXUGO;
    inode->i_uid = current_fsuid();//用户ID，在后面调用bind系统调用时会进行对比
    inode->i_gid = current_fsgid();//组ID
    inode->i_op = &sockfs_inode_ops;

    return sock;
}

pf = rcu_dereference(net_families[family]);

/*
 *    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;
    int try_loading_module = 0;
    int err;

    if (protocol < 0 || protocol >= IPPROTO_MAX)
        return -EINVAL;
    
    sock->state = SS_UNCONNECTED;
 
    /* Look for the requested type/protocol pair. */
lookup_protocol:
    err = -ESOCKTNOSUPPORT;
    rcu_read_lock();
    
    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;
    }
    
    if (unlikely(err)) {
        if (try_loading_module < 2) {
            rcu_read_unlock();
            /*
             * Be more specific, e.g. net-pf-2-proto-132-type-1
             * (net-pf-PF_INET-proto-IPPROTO_SCTP-type-SOCK_STREAM)
             */
            if (++try_loading_module == 1)
                request_module("net-pf-%d-proto-%d-type-%d",
                           PF_INET, protocol, sock->type);
            /*
             * Fall back to generic, e.g. net-pf-2-proto-132
             * (net-pf-PF_INET-proto-IPPROTO_SCTP)
             */
            else
                request_module("net-pf-%d-proto-%d",
                           PF_INET, protocol);
            goto lookup_protocol;
        } else
            goto out_rcu_unlock;
    }
 
    err = -EPERM;
    
    if (sock->type == SOCK_RAW && !kern &&
        !ns_capable(net->user_ns, CAP_NET_RAW))
        goto out_rcu_unlock;
    
    sock->ops = answer->ops;
    answer_prot = answer->prot;
    answer_flags = answer->flags;
    rcu_read_unlock();
 
    WARN_ON(!answer_prot->slab);
 
    err = -ENOBUFS;
    
    sk = sk_alloc(net, PF_INET, GFP_KERNEL, answer_prot);
    if (!sk)
        goto out;
 
    err = 0;
    
    
    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 (net->ipv4.sysctl_ip_no_pmtu_disc)
        inet->pmtudisc = IP_PMTUDISC_DONT;
    else
        inet->pmtudisc = IP_PMTUDISC_WANT;
 
    inet->inet_id = 0;
    
    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;
}