diff options
Diffstat (limited to 'net/core/sock.c')
| -rw-r--r-- | net/core/sock.c | 712 |
1 files changed, 354 insertions, 358 deletions
diff --git a/net/core/sock.c b/net/core/sock.c index cb48fa0e124..792ae39804a 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -361,8 +361,8 @@ int sock_setsockopt(struct socket *sock, int level, int optname, } #endif - if(optlen<sizeof(int)) - return(-EINVAL); + if (optlen < sizeof(int)) + return -EINVAL; if (get_user(val, (int __user *)optval)) return -EFAULT; @@ -371,265 +371,263 @@ int sock_setsockopt(struct socket *sock, int level, int optname, lock_sock(sk); - switch(optname) - { - case SO_DEBUG: - if(val && !capable(CAP_NET_ADMIN)) - { - ret = -EACCES; - } - else if (valbool) - sock_set_flag(sk, SOCK_DBG); - else - sock_reset_flag(sk, SOCK_DBG); - break; - case SO_REUSEADDR: - sk->sk_reuse = valbool; - break; - case SO_TYPE: - case SO_ERROR: - ret = -ENOPROTOOPT; - break; - case SO_DONTROUTE: - if (valbool) - sock_set_flag(sk, SOCK_LOCALROUTE); - else - sock_reset_flag(sk, SOCK_LOCALROUTE); - break; - case SO_BROADCAST: - sock_valbool_flag(sk, SOCK_BROADCAST, valbool); - break; - case SO_SNDBUF: - /* Don't error on this BSD doesn't and if you think - about it this is right. Otherwise apps have to - play 'guess the biggest size' games. RCVBUF/SNDBUF - are treated in BSD as hints */ - - if (val > sysctl_wmem_max) - val = sysctl_wmem_max; + switch(optname) { + case SO_DEBUG: + if (val && !capable(CAP_NET_ADMIN)) { + ret = -EACCES; + } + else if (valbool) + sock_set_flag(sk, SOCK_DBG); + else + sock_reset_flag(sk, SOCK_DBG); + break; + case SO_REUSEADDR: + sk->sk_reuse = valbool; + break; + case SO_TYPE: + case SO_ERROR: + ret = -ENOPROTOOPT; + break; + case SO_DONTROUTE: + if (valbool) + sock_set_flag(sk, SOCK_LOCALROUTE); + else + sock_reset_flag(sk, SOCK_LOCALROUTE); + break; + case SO_BROADCAST: + sock_valbool_flag(sk, SOCK_BROADCAST, valbool); + break; + case SO_SNDBUF: + /* Don't error on this BSD doesn't and if you think + about it this is right. Otherwise apps have to + play 'guess the biggest size' games. RCVBUF/SNDBUF + are treated in BSD as hints */ + + if (val > sysctl_wmem_max) + val = sysctl_wmem_max; set_sndbuf: - sk->sk_userlocks |= SOCK_SNDBUF_LOCK; - if ((val * 2) < SOCK_MIN_SNDBUF) - sk->sk_sndbuf = SOCK_MIN_SNDBUF; - else - sk->sk_sndbuf = val * 2; + sk->sk_userlocks |= SOCK_SNDBUF_LOCK; + if ((val * 2) < SOCK_MIN_SNDBUF) + sk->sk_sndbuf = SOCK_MIN_SNDBUF; + else + sk->sk_sndbuf = val * 2; - /* - * Wake up sending tasks if we - * upped the value. - */ - sk->sk_write_space(sk); - break; + /* + * Wake up sending tasks if we + * upped the value. + */ + sk->sk_write_space(sk); + break; - case SO_SNDBUFFORCE: - if (!capable(CAP_NET_ADMIN)) { - ret = -EPERM; - break; - } - goto set_sndbuf; + case SO_SNDBUFFORCE: + if (!capable(CAP_NET_ADMIN)) { + ret = -EPERM; + break; + } + goto set_sndbuf; - case SO_RCVBUF: - /* Don't error on this BSD doesn't and if you think - about it this is right. Otherwise apps have to - play 'guess the biggest size' games. RCVBUF/SNDBUF - are treated in BSD as hints */ + case SO_RCVBUF: + /* Don't error on this BSD doesn't and if you think + about it this is right. Otherwise apps have to + play 'guess the biggest size' games. RCVBUF/SNDBUF + are treated in BSD as hints */ - if (val > sysctl_rmem_max) - val = sysctl_rmem_max; + if (val > sysctl_rmem_max) + val = sysctl_rmem_max; set_rcvbuf: - sk->sk_userlocks |= SOCK_RCVBUF_LOCK; - /* - * We double it on the way in to account for - * "struct sk_buff" etc. overhead. Applications - * assume that the SO_RCVBUF setting they make will - * allow that much actual data to be received on that - * socket. - * - * Applications are unaware that "struct sk_buff" and - * other overheads allocate from the receive buffer - * during socket buffer allocation. - * - * And after considering the possible alternatives, - * returning the value we actually used in getsockopt - * is the most desirable behavior. - */ - if ((val * 2) < SOCK_MIN_RCVBUF) - sk->sk_rcvbuf = SOCK_MIN_RCVBUF; - else - sk->sk_rcvbuf = val * 2; + sk->sk_userlocks |= SOCK_RCVBUF_LOCK; + /* + * We double it on the way in to account for + * "struct sk_buff" etc. overhead. Applications + * assume that the SO_RCVBUF setting they make will + * allow that much actual data to be received on that + * socket. + * + * Applications are unaware that "struct sk_buff" and + * other overheads allocate from the receive buffer + * during socket buffer allocation. + * + * And after considering the possible alternatives, + * returning the value we actually used in getsockopt + * is the most desirable behavior. + */ + if ((val * 2) < SOCK_MIN_RCVBUF) + sk->sk_rcvbuf = SOCK_MIN_RCVBUF; + else + sk->sk_rcvbuf = val * 2; + break; + + case SO_RCVBUFFORCE: + if (!capable(CAP_NET_ADMIN)) { + ret = -EPERM; break; + } + goto set_rcvbuf; - case SO_RCVBUFFORCE: - if (!capable(CAP_NET_ADMIN)) { - ret = -EPERM; - break; - } - goto set_rcvbuf; - - case SO_KEEPALIVE: + case SO_KEEPALIVE: #ifdef CONFIG_INET - if (sk->sk_protocol == IPPROTO_TCP) - tcp_set_keepalive(sk, valbool); + if (sk->sk_protocol == IPPROTO_TCP) + tcp_set_keepalive(sk, valbool); #endif - sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool); - break; - - case SO_OOBINLINE: - sock_valbool_flag(sk, SOCK_URGINLINE, valbool); + sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool); + break; + + case SO_OOBINLINE: + sock_valbool_flag(sk, SOCK_URGINLINE, valbool); + break; + + case SO_NO_CHECK: + sk->sk_no_check = valbool; + break; + + case SO_PRIORITY: + if ((val >= 0 && val <= 6) || capable(CAP_NET_ADMIN)) + sk->sk_priority = val; + else + ret = -EPERM; + break; + + case SO_LINGER: + if (optlen < sizeof(ling)) { + ret = -EINVAL; /* 1003.1g */ break; - - case SO_NO_CHECK: - sk->sk_no_check = valbool; - break; - - case SO_PRIORITY: - if ((val >= 0 && val <= 6) || capable(CAP_NET_ADMIN)) - sk->sk_priority = val; - else - ret = -EPERM; + } + if (copy_from_user(&ling,optval,sizeof(ling))) { + ret = -EFAULT; break; - - case SO_LINGER: - if(optlen<sizeof(ling)) { - ret = -EINVAL; /* 1003.1g */ - break; - } - if (copy_from_user(&ling,optval,sizeof(ling))) { - ret = -EFAULT; - break; - } - if (!ling.l_onoff) - sock_reset_flag(sk, SOCK_LINGER); - else { + } + if (!ling.l_onoff) + sock_reset_flag(sk, SOCK_LINGER); + else { #if (BITS_PER_LONG == 32) - if ((unsigned int)ling.l_linger >= MAX_SCHEDULE_TIMEOUT/HZ) - sk->sk_lingertime = MAX_SCHEDULE_TIMEOUT; - else -#endif - sk->sk_lingertime = (unsigned int)ling.l_linger * HZ; - sock_set_flag(sk, SOCK_LINGER); - } - break; - - case SO_BSDCOMPAT: - sock_warn_obsolete_bsdism("setsockopt"); - break; - - case SO_PASSCRED: - if (valbool) - set_bit(SOCK_PASSCRED, &sock->flags); + if ((unsigned int)ling.l_linger >= MAX_SCHEDULE_TIMEOUT/HZ) + sk->sk_lingertime = MAX_SCHEDULE_TIMEOUT; else - clear_bit(SOCK_PASSCRED, &sock->flags); - break; - - case SO_TIMESTAMP: - if (valbool) { - sock_set_flag(sk, SOCK_RCVTSTAMP); - sock_enable_timestamp(sk); - } else - sock_reset_flag(sk, SOCK_RCVTSTAMP); - break; - - case SO_RCVLOWAT: - if (val < 0) - val = INT_MAX; - sk->sk_rcvlowat = val ? : 1; - break; +#endif + sk->sk_lingertime = (unsigned int)ling.l_linger * HZ; + sock_set_flag(sk, SOCK_LINGER); + } + break; + + case SO_BSDCOMPAT: + sock_warn_obsolete_bsdism("setsockopt"); + break; + + case SO_PASSCRED: + if (valbool) + set_bit(SOCK_PASSCRED, &sock->flags); + else + clear_bit(SOCK_PASSCRED, &sock->flags); + break; + + case SO_TIMESTAMP: + if (valbool) { + sock_set_flag(sk, SOCK_RCVTSTAMP); + sock_enable_timestamp(sk); + } else + sock_reset_flag(sk, SOCK_RCVTSTAMP); + break; + + case SO_RCVLOWAT: + if (val < 0) + val = INT_MAX; + sk->sk_rcvlowat = val ? : 1; + break; + + case SO_RCVTIMEO: + ret = sock_set_timeout(&sk->sk_rcvtimeo, optval, optlen); + break; + + case SO_SNDTIMEO: + ret = sock_set_timeout(&sk->sk_sndtimeo, optval, optlen); + break; - case SO_RCVTIMEO: - ret = sock_set_timeout(&sk->sk_rcvtimeo, optval, optlen); - break; +#ifdef CONFIG_NETDEVICES + case SO_BINDTODEVICE: + { + char devname[IFNAMSIZ]; - case SO_SNDTIMEO: - ret = sock_set_timeout(&sk->sk_sndtimeo, optval, optlen); + /* Sorry... */ + if (!capable(CAP_NET_RAW)) { + ret = -EPERM; break; + } -#ifdef CONFIG_NETDEVICES - case SO_BINDTODEVICE: - { - char devname[IFNAMSIZ]; + /* Bind this socket to a particular device like "eth0", + * as specified in the passed interface name. If the + * name is "" or the option length is zero the socket + * is not bound. + */ - /* Sorry... */ - if (!capable(CAP_NET_RAW)) { - ret = -EPERM; + if (!valbool) { + sk->sk_bound_dev_if = 0; + } else { + if (optlen > IFNAMSIZ - 1) + optlen = IFNAMSIZ - 1; + memset(devname, 0, sizeof(devname)); + if (copy_from_user(devname, optval, optlen)) { + ret = -EFAULT; break; } - /* Bind this socket to a particular device like "eth0", - * as specified in the passed interface name. If the - * name is "" or the option length is zero the socket - * is not bound. - */ + /* Remove any cached route for this socket. */ + sk_dst_reset(sk); - if (!valbool) { + if (devname[0] == '\0') { sk->sk_bound_dev_if = 0; } else { - if (optlen > IFNAMSIZ - 1) - optlen = IFNAMSIZ - 1; - memset(devname, 0, sizeof(devname)); - if (copy_from_user(devname, optval, optlen)) { - ret = -EFAULT; + struct net_device *dev = dev_get_by_name(devname); + if (!dev) { + ret = -ENODEV; break; } - - /* Remove any cached route for this socket. */ - sk_dst_reset(sk); - - if (devname[0] == '\0') { - sk->sk_bound_dev_if = 0; - } else { - struct net_device *dev = dev_get_by_name(devname); - if (!dev) { - ret = -ENODEV; - break; - } - sk->sk_bound_dev_if = dev->ifindex; - dev_put(dev); - } + sk->sk_bound_dev_if = dev->ifindex; + dev_put(dev); } - break; } + break; + } #endif - case SO_ATTACH_FILTER: - ret = -EINVAL; - if (optlen == sizeof(struct sock_fprog)) { - struct sock_fprog fprog; - - ret = -EFAULT; - if (copy_from_user(&fprog, optval, sizeof(fprog))) - break; - - ret = sk_attach_filter(&fprog, sk); - } - break; + case SO_ATTACH_FILTER: + ret = -EINVAL; + if (optlen == sizeof(struct sock_fprog)) { + struct sock_fprog fprog; - case SO_DETACH_FILTER: - rcu_read_lock_bh(); - filter = rcu_dereference(sk->sk_filter); - if (filter) { - rcu_assign_pointer(sk->sk_filter, NULL); - sk_filter_release(sk, filter); - rcu_read_unlock_bh(); + ret = -EFAULT; + if (copy_from_user(&fprog, optval, sizeof(fprog))) break; - } + + ret = sk_attach_filter(&fprog, sk); + } + break; + + case SO_DETACH_FILTER: + rcu_read_lock_bh(); + filter = rcu_dereference(sk->sk_filter); + if (filter) { + rcu_assign_pointer(sk->sk_filter, NULL); + sk_filter_release(sk, filter); rcu_read_unlock_bh(); - ret = -ENONET; break; + } + rcu_read_unlock_bh(); + ret = -ENONET; + break; - case SO_PASSSEC: - if (valbool) - set_bit(SOCK_PASSSEC, &sock->flags); - else - clear_bit(SOCK_PASSSEC, &sock->flags); - break; + case SO_PASSSEC: + if (valbool) + set_bit(SOCK_PASSSEC, &sock->flags); + else + clear_bit(SOCK_PASSSEC, &sock->flags); + break; /* We implement the SO_SNDLOWAT etc to not be settable (1003.1g 5.3) */ - default: - ret = -ENOPROTOOPT; - break; + default: + ret = -ENOPROTOOPT; + break; } release_sock(sk); return ret; @@ -641,8 +639,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, { struct sock *sk = sock->sk; - union - { + union { int val; struct linger ling; struct timeval tm; @@ -651,148 +648,148 @@ int sock_getsockopt(struct socket *sock, int level, int optname, unsigned int lv = sizeof(int); int len; - if(get_user(len,optlen)) + if (get_user(len, optlen)) return -EFAULT; - if(len < 0) + if (len < 0) return -EINVAL; - switch(optname) - { - case SO_DEBUG: - v.val = sock_flag(sk, SOCK_DBG); - break; - - case SO_DONTROUTE: - v.val = sock_flag(sk, SOCK_LOCALROUTE); - break; - - case SO_BROADCAST: - v.val = !!sock_flag(sk, SOCK_BROADCAST); - break; - - case SO_SNDBUF: - v.val = sk->sk_sndbuf; - break; - - case SO_RCVBUF: - v.val = sk->sk_rcvbuf; - break; - - case SO_REUSEADDR: - v.val = sk->sk_reuse; - break; - - case SO_KEEPALIVE: - v.val = !!sock_flag(sk, SOCK_KEEPOPEN); - break; - - case SO_TYPE: - v.val = sk->sk_type; - break; - - case SO_ERROR: - v.val = -sock_error(sk); - if(v.val==0) - v.val = xchg(&sk->sk_err_soft, 0); - break; - - case SO_OOBINLINE: - v.val = !!sock_flag(sk, SOCK_URGINLINE); - break; - - case SO_NO_CHECK: - v.val = sk->sk_no_check; - break; - - case SO_PRIORITY: - v.val = sk->sk_priority; - break; - - case SO_LINGER: - lv = sizeof(v.ling); - v.ling.l_onoff = !!sock_flag(sk, SOCK_LINGER); - v.ling.l_linger = sk->sk_lingertime / HZ; - break; - - case SO_BSDCOMPAT: - sock_warn_obsolete_bsdism("getsockopt"); - break; - - case SO_TIMESTAMP: - v.val = sock_flag(sk, SOCK_RCVTSTAMP); - break; - - case SO_RCVTIMEO: - lv=sizeof(struct timeval); - if (sk->sk_rcvtimeo == MAX_SCHEDULE_TIMEOUT) { - v.tm.tv_sec = 0; - v.tm.tv_usec = 0; - } else { - v.tm.tv_sec = sk->sk_rcvtimeo / HZ; - v.tm.tv_usec = ((sk->sk_rcvtimeo % HZ) * 1000000) / HZ; - } - break; + switch(optname) { + case SO_DEBUG: + v.val = sock_flag(sk, SOCK_DBG); + break; + + case SO_DONTROUTE: + v.val = sock_flag(sk, SOCK_LOCALROUTE); + break; + + case SO_BROADCAST: + v.val = !!sock_flag(sk, SOCK_BROADCAST); + break; + + case SO_SNDBUF: + v.val = sk->sk_sndbuf; + break; + + case SO_RCVBUF: + v.val = sk->sk_rcvbuf; + break; + + case SO_REUSEADDR: + v.val = sk->sk_reuse; + break; + + case SO_KEEPALIVE: + v.val = !!sock_flag(sk, SOCK_KEEPOPEN); + break; + + case SO_TYPE: + v.val = sk->sk_type; + break; + + case SO_ERROR: + v.val = -sock_error(sk); + if (v.val==0) + v.val = xchg(&sk->sk_err_soft, 0); + break; + + case SO_OOBINLINE: + v.val = !!sock_flag(sk, SOCK_URGINLINE); + break; + + case SO_NO_CHECK: + v.val = sk->sk_no_check; + break; + + case SO_PRIORITY: + v.val = sk->sk_priority; + break; + + case SO_LINGER: + lv = sizeof(v.ling); + v.ling.l_onoff = !!sock_flag(sk, SOCK_LINGER); + v.ling.l_linger = sk->sk_lingertime / HZ; + break; + + case SO_BSDCOMPAT: + sock_warn_obsolete_bsdism("getsockopt"); + break; + + case SO_TIMESTAMP: + v.val = sock_flag(sk, SOCK_RCVTSTAMP); + break; + + case SO_RCVTIMEO: + lv=sizeof(struct timeval); + if (sk->sk_rcvtimeo == MAX_SCHEDULE_TIMEOUT) { + v.tm.tv_sec = 0; + v.tm.tv_usec = 0; + } else { + v.tm.tv_sec = sk->sk_rcvtimeo / HZ; + v.tm.tv_usec = ((sk->sk_rcvtimeo % HZ) * 1000000) / HZ; + } + break; + + case SO_SNDTIMEO: + lv=sizeof(struct timeval); + if (sk->sk_sndtimeo == MAX_SCHEDULE_TIMEOUT) { + v.tm.tv_sec = 0; + v.tm.tv_usec = 0; + } else { + v.tm.tv_sec = sk->sk_sndtimeo / HZ; + v.tm.tv_usec = ((sk->sk_sndtimeo % HZ) * 1000000) / HZ; + } + break; - case SO_SNDTIMEO: - lv=sizeof(struct timeval); - if (sk->sk_sndtimeo == MAX_SCHEDULE_TIMEOUT) { - v.tm.tv_sec = 0; - v.tm.tv_usec = 0; - } else { - v.tm.tv_sec = sk->sk_sndtimeo / HZ; - v.tm.tv_usec = ((sk->sk_sndtimeo % HZ) * 1000000) / HZ; - } - break; + case SO_RCVLOWAT: + v.val = sk->sk_rcvlowat; + break; - case SO_RCVLOWAT: - v.val = sk->sk_rcvlowat; - break; + case SO_SNDLOWAT: + v.val=1; + break; - case SO_SNDLOWAT: - v.val=1; - break; + case SO_PASSCRED: + v.val = test_bit(SOCK_PASSCRED, &sock->flags) ? 1 : 0; + break; - case SO_PASSCRED: - v.val = test_bit(SOCK_PASSCRED, &sock->flags) ? 1 : 0; - break; + case SO_PEERCRED: + if (len > sizeof(sk->sk_peercred)) + len = sizeof(sk->sk_peercred); + if (copy_to_user(optval, &sk->sk_peercred, len)) + return -EFAULT; + goto lenout; - case SO_PEERCRED: - if (len > sizeof(sk->sk_peercred)) - len = sizeof(sk->sk_peercred); - if (copy_to_user(optval, &sk->sk_peercred, len)) - return -EFAULT; - goto lenout; - - case SO_PEERNAME: - { - char address[128]; - - if (sock->ops->getname(sock, (struct sockaddr *)address, &lv, 2)) - return -ENOTCONN; - if (lv < len) - return -EINVAL; - if (copy_to_user(optval, address, len)) - return -EFAULT; - goto lenout; - } + case SO_PEERNAME: + { + char address[128]; + + if (sock->ops->getname(sock, (struct sockaddr *)address, &lv, 2)) + return -ENOTCONN; + if (lv < len) + return -EINVAL; + if (copy_to_user(optval, address, len)) + return -EFAULT; + goto lenout; + } - /* Dubious BSD thing... Probably nobody even uses it, but - * the UNIX standard wants it for whatever reason... -DaveM - */ - case SO_ACCEPTCONN: - v.val = sk->sk_state == TCP_LISTEN; - break; + /* Dubious BSD thing... Probably nobody even uses it, but + * the UNIX standard wants it for whatever reason... -DaveM + */ + case SO_ACCEPTCONN: + v.val = sk->sk_state == TCP_LISTEN; + break; - case SO_PASSSEC: - v.val = test_bit(SOCK_PASSSEC, &sock->flags) ? 1 : 0; - break; + case SO_PASSSEC: + v.val = test_bit(SOCK_PASSSEC, &sock->flags) ? 1 : 0; + break; - case SO_PEERSEC: - return security_socket_getpeersec_stream(sock, optval, optlen, len); + case SO_PEERSEC: + return security_socket_getpeersec_stream(sock, optval, optlen, len); - default: - return(-ENOPROTOOPT); + default: + return -ENOPROTOOPT; } + if (len > lv) len = lv; if (copy_to_user(optval, &v, len)) @@ -1220,13 +1217,13 @@ static void __lock_sock(struct sock *sk) { DEFINE_WAIT(wait); - for(;;) { + for (;;) { prepare_to_wait_exclusive(&sk->sk_lock.wq, &wait, TASK_UNINTERRUPTIBLE); spin_unlock_bh(&sk->sk_lock.slock); schedule(); spin_lock_bh(&sk->sk_lock.slock); - if(!sock_owned_by_user(sk)) + if (!sock_owned_by_user(sk)) break; } finish_wait(&sk->sk_lock.wq, &wait); @@ -1258,7 +1255,7 @@ static void __release_sock(struct sock *sk) } while (skb != NULL); bh_lock_sock(sk); - } while((skb = sk->sk_backlog.head) != NULL); + } while ((skb = sk->sk_backlog.head) != NULL); } /** @@ -1420,7 +1417,7 @@ static void sock_def_write_space(struct sock *sk) /* Do not wake up a writer until he can make "significant" * progress. --DaveM */ - if((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) { + if ((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) { if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) wake_up_interruptible(sk->sk_sleep); @@ -1482,8 +1479,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) sock_set_flag(sk, SOCK_ZAPPED); - if(sock) - { + if (sock) { sk->sk_type = sock->type; sk->sk_sleep = &sock->wait; sock->sk = sk; |