--- zzzz-none-000/linux-3.10.107/net/ipv4/ip_sockglue.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/net/ipv4/ip_sockglue.c 2021-02-04 17:41:59.000000000 +0000 @@ -37,6 +37,7 @@ #include #include #include +#include #if IS_ENABLED(CONFIG_IPV6) #include #endif @@ -45,18 +46,9 @@ #include #include -#define IP_CMSG_PKTINFO 1 -#define IP_CMSG_TTL 2 -#define IP_CMSG_TOS 4 -#define IP_CMSG_RECVOPTS 8 -#define IP_CMSG_RETOPTS 16 -#define IP_CMSG_PASSSEC 32 -#define IP_CMSG_ORIGDSTADDR 64 - /* * SOL_IP control messages. */ -#define PKTINFO_SKB_CB(__skb) ((struct in_pktinfo *)((__skb)->cb)) static void ip_cmsg_recv_pktinfo(struct msghdr *msg, struct sk_buff *skb) { @@ -105,6 +97,22 @@ put_cmsg(msg, SOL_IP, IP_RETOPTS, opt->optlen, opt->__data); } +static void ip_cmsg_recv_checksum(struct msghdr *msg, struct sk_buff *skb, + int tlen, int offset) +{ + __wsum csum = skb->csum; + + if (skb->ip_summed != CHECKSUM_COMPLETE) + return; + + if (offset != 0) { + int tend_off = skb_transport_offset(skb) + tlen; + csum = csum_sub(csum, skb_checksum(skb, tend_off, offset, 0)); + } + + put_cmsg(msg, SOL_IP, IP_CHECKSUM, sizeof(__wsum), &csum); +} + static void ip_cmsg_recv_security(struct msghdr *msg, struct sk_buff *skb) { char *secdata; @@ -145,61 +153,106 @@ put_cmsg(msg, SOL_IP, IP_ORIGDSTADDR, sizeof(sin), &sin); } -void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb) +void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb, + int tlen, int offset) { struct inet_sock *inet = inet_sk(skb->sk); unsigned int flags = inet->cmsg_flags; /* Ordered by supposed usage frequency */ - if (flags & 1) + if (flags & IP_CMSG_PKTINFO) { ip_cmsg_recv_pktinfo(msg, skb); - if ((flags >>= 1) == 0) - return; - if (flags & 1) + flags &= ~IP_CMSG_PKTINFO; + if (!flags) + return; + } + + if (flags & IP_CMSG_TTL) { ip_cmsg_recv_ttl(msg, skb); - if ((flags >>= 1) == 0) - return; - if (flags & 1) + flags &= ~IP_CMSG_TTL; + if (!flags) + return; + } + + if (flags & IP_CMSG_TOS) { ip_cmsg_recv_tos(msg, skb); - if ((flags >>= 1) == 0) - return; - if (flags & 1) + flags &= ~IP_CMSG_TOS; + if (!flags) + return; + } + + if (flags & IP_CMSG_RECVOPTS) { ip_cmsg_recv_opts(msg, skb); - if ((flags >>= 1) == 0) - return; - if (flags & 1) + flags &= ~IP_CMSG_RECVOPTS; + if (!flags) + return; + } + + if (flags & IP_CMSG_RETOPTS) { ip_cmsg_recv_retopts(msg, skb); - if ((flags >>= 1) == 0) - return; - if (flags & 1) + flags &= ~IP_CMSG_RETOPTS; + if (!flags) + return; + } + + if (flags & IP_CMSG_PASSSEC) { ip_cmsg_recv_security(msg, skb); - if ((flags >>= 1) == 0) - return; - if (flags & 1) + flags &= ~IP_CMSG_PASSSEC; + if (!flags) + return; + } + + if (flags & IP_CMSG_ORIGDSTADDR) { ip_cmsg_recv_dstaddr(msg, skb); + flags &= ~IP_CMSG_ORIGDSTADDR; + if (!flags) + return; + } + + if (flags & IP_CMSG_CHECKSUM) + ip_cmsg_recv_checksum(msg, skb, tlen, offset); } -EXPORT_SYMBOL(ip_cmsg_recv); +EXPORT_SYMBOL(ip_cmsg_recv_offset); -int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc) +int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc, + bool allow_ipv6) { - int err; + int err, val; struct cmsghdr *cmsg; - for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) { + for_each_cmsghdr(cmsg, msg) { if (!CMSG_OK(msg, cmsg)) return -EINVAL; +#if IS_ENABLED(CONFIG_IPV6) + if (allow_ipv6 && + cmsg->cmsg_level == SOL_IPV6 && + cmsg->cmsg_type == IPV6_PKTINFO) { + struct in6_pktinfo *src_info; + + if (cmsg->cmsg_len < CMSG_LEN(sizeof(*src_info))) + return -EINVAL; + src_info = (struct in6_pktinfo *)CMSG_DATA(cmsg); + if (!ipv6_addr_v4mapped(&src_info->ipi6_addr)) + return -EINVAL; + ipc->oif = src_info->ipi6_ifindex; + ipc->addr = src_info->ipi6_addr.s6_addr32[3]; + continue; + } +#endif if (cmsg->cmsg_level != SOL_IP) continue; switch (cmsg->cmsg_type) { case IP_RETOPTS: err = cmsg->cmsg_len - CMSG_ALIGN(sizeof(struct cmsghdr)); + + /* Our caller is responsible for freeing ipc->opt */ err = ip_options_get(net, &ipc->opt, CMSG_DATA(cmsg), err < 40 ? err : 40); if (err) @@ -215,6 +268,24 @@ ipc->addr = info->ipi_spec_dst.s_addr; break; } + case IP_TTL: + if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) + return -EINVAL; + val = *(int *)CMSG_DATA(cmsg); + if (val < 1 || val > 255) + return -EINVAL; + ipc->ttl = val; + break; + case IP_TOS: + if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) + return -EINVAL; + val = *(int *)CMSG_DATA(cmsg); + if (val < 0 || val > 255) + return -EINVAL; + ipc->tos = val; + ipc->priority = rt_tos2priority(ipc->tos); + break; + default: return -EINVAL; } @@ -269,7 +340,7 @@ } /* dont let ip_call_ra_chain() use sk again */ ra->sk = NULL; - rcu_assign_pointer(*rap, ra->next); + RCU_INIT_POINTER(*rap, ra->next); spin_unlock_bh(&ip_ra_lock); if (ra->destructor) @@ -284,14 +355,14 @@ return 0; } } - if (new_ra == NULL) { + if (!new_ra) { spin_unlock_bh(&ip_ra_lock); return -ENOBUFS; } new_ra->sk = sk; new_ra->destructor = destructor; - new_ra->next = ra; + RCU_INIT_POINTER(new_ra->next, ra); rcu_assign_pointer(*rap, new_ra); sock_hold(sk); spin_unlock_bh(&ip_ra_lock); @@ -320,7 +391,7 @@ skb_network_header(skb); serr->port = port; - if (skb_pull(skb, payload - skb->data) != NULL) { + if (skb_pull(skb, payload - skb->data)) { skb_reset_transport_header(skb); if (sock_queue_err_skb(sk, skb) == 0) return; @@ -365,14 +436,54 @@ kfree_skb(skb); } +/* For some errors we have valid addr_offset even with zero payload and + * zero port. Also, addr_offset should be supported if port is set. + */ +static inline bool ipv4_datagram_support_addr(struct sock_exterr_skb *serr) +{ + return serr->ee.ee_origin == SO_EE_ORIGIN_ICMP || + serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL || serr->port; +} + +/* IPv4 supports cmsg on all imcp errors and some timestamps + * + * Timestamp code paths do not initialize the fields expected by cmsg: + * the PKTINFO fields in skb->cb[]. Fill those in here. + */ +static bool ipv4_datagram_support_cmsg(const struct sock *sk, + struct sk_buff *skb, + int ee_origin) +{ + struct in_pktinfo *info; + + if (ee_origin == SO_EE_ORIGIN_ICMP) + return true; + + if (ee_origin == SO_EE_ORIGIN_LOCAL) + return false; + + /* Support IP_PKTINFO on tstamp packets if requested, to correlate + * timestamp with egress dev. Not possible for packets without dev + * or without payload (SOF_TIMESTAMPING_OPT_TSONLY). + */ + if ((!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_CMSG)) || + (!skb->dev)) + return false; + + info = PKTINFO_SKB_CB(skb); + info->ipi_spec_dst.s_addr = ip_hdr(skb)->saddr; + info->ipi_ifindex = skb->dev->ifindex; + return true; +} + /* * Handle MSG_ERRQUEUE */ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) { struct sock_exterr_skb *serr; - struct sk_buff *skb, *skb2; - struct sockaddr_in *sin; + struct sk_buff *skb; + DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name); struct { struct sock_extended_err ee; struct sockaddr_in offender; @@ -380,9 +491,11 @@ int err; int copied; + WARN_ON_ONCE(sk->sk_family == AF_INET6); + err = -EAGAIN; - skb = skb_dequeue(&sk->sk_error_queue); - if (skb == NULL) + skb = sock_dequeue_err_skb(sk); + if (!skb) goto out; copied = skb->len; @@ -390,7 +503,7 @@ msg->msg_flags |= MSG_TRUNC; copied = len; } - err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied); + err = skb_copy_datagram_msg(skb, 0, msg, copied); if (err) goto out_free_skb; @@ -398,8 +511,7 @@ serr = SKB_EXT_ERR(skb); - sin = (struct sockaddr_in *)msg->msg_name; - if (sin) { + if (sin && ipv4_datagram_support_addr(serr)) { sin->sin_family = AF_INET; sin->sin_addr.s_addr = *(__be32 *)(skb_network_header(skb) + serr->addr_offset); @@ -411,7 +523,8 @@ memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err)); sin = &errhdr.offender; memset(sin, 0, sizeof(*sin)); - if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP) { + + if (ipv4_datagram_support_cmsg(sk, skb, serr->ee.ee_origin)) { sin->sin_family = AF_INET; sin->sin_addr.s_addr = ip_hdr(skb)->saddr; if (inet_sk(sk)->cmsg_flags) @@ -425,17 +538,6 @@ msg->msg_flags |= MSG_ERRQUEUE; err = copied; - /* Reset and regenerate socket error */ - spin_lock_bh(&sk->sk_error_queue.lock); - sk->sk_err = 0; - skb2 = skb_peek(&sk->sk_error_queue); - if (skb2 != NULL) { - sk->sk_err = SKB_EXT_ERR(skb2)->ee.ee_errno; - spin_unlock_bh(&sk->sk_error_queue.lock); - sk->sk_error_report(sk); - } else - spin_unlock_bh(&sk->sk_error_queue.lock); - out_free_skb: kfree_skb(skb); out: @@ -447,12 +549,34 @@ * Socket option code for IP. This is the end of the line after any * TCP,UDP etc options on an IP socket. */ +static bool setsockopt_needs_rtnl(int optname) +{ + switch (optname) { + case IP_ADD_MEMBERSHIP: + case IP_ADD_SOURCE_MEMBERSHIP: + case IP_BLOCK_SOURCE: + case IP_DROP_MEMBERSHIP: + case IP_DROP_SOURCE_MEMBERSHIP: + case IP_MSFILTER: + case IP_UNBLOCK_SOURCE: + case MCAST_BLOCK_SOURCE: + case MCAST_MSFILTER: + case MCAST_JOIN_GROUP: + case MCAST_JOIN_SOURCE_GROUP: + case MCAST_LEAVE_GROUP: + case MCAST_LEAVE_SOURCE_GROUP: + case MCAST_UNBLOCK_SOURCE: + return true; + } + return false; +} static int do_ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen) { struct inet_sock *inet = inet_sk(sk); int val = 0, err; + bool needs_rtnl = setsockopt_needs_rtnl(optname); switch (optname) { case IP_PKTINFO: @@ -471,11 +595,13 @@ case IP_TRANSPARENT: case IP_MINTTL: case IP_NODEFRAG: + case IP_BIND_ADDRESS_NO_PORT: case IP_UNICAST_IF: case IP_MULTICAST_TTL: case IP_MULTICAST_ALL: case IP_MULTICAST_LOOP: case IP_RECVORIGDSTADDR: + case IP_CHECKSUM: if (optlen >= sizeof(int)) { if (get_user(val, (int __user *) optval)) return -EFAULT; @@ -494,6 +620,8 @@ return ip_mroute_setsockopt(sk, optname, optval, optlen); err = 0; + if (needs_rtnl) + rtnl_lock(); lock_sock(sk); switch (optname) { @@ -573,6 +701,19 @@ else inet->cmsg_flags &= ~IP_CMSG_ORIGDSTADDR; break; + case IP_CHECKSUM: + if (val) { + if (!(inet->cmsg_flags & IP_CMSG_CHECKSUM)) { + inet_inc_convert_csum(sk); + inet->cmsg_flags |= IP_CMSG_CHECKSUM; + } + } else { + if (inet->cmsg_flags & IP_CMSG_CHECKSUM) { + inet_dec_convert_csum(sk); + inet->cmsg_flags &= ~IP_CMSG_CHECKSUM; + } + } + break; case IP_TOS: /* This sets both TOS and Precedence */ if (sk->sk_type == SOCK_STREAM) { val &= ~INET_ECN_MASK; @@ -605,8 +746,11 @@ } inet->nodefrag = val ? 1 : 0; break; + case IP_BIND_ADDRESS_NO_PORT: + inet->bind_address_no_port = val ? 1 : 0; + break; case IP_MTU_DISCOVER: - if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_PROBE) + if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_OMIT) goto e_inval; inet->pmtudisc = val; break; @@ -1015,27 +1159,33 @@ break; } release_sock(sk); + if (needs_rtnl) + rtnl_unlock(); return err; e_inval: release_sock(sk); + if (needs_rtnl) + rtnl_unlock(); return -EINVAL; } /** - * ipv4_pktinfo_prepare - transfert some info from rtable to skb + * ipv4_pktinfo_prepare - transfer some info from rtable to skb * @sk: socket * @skb: buffer * * To support IP_CMSG_PKTINFO option, we store rt_iif and specific * destination in skb->cb[] before dst drop. - * This way, receiver doesnt make cache line misses to read rtable. + * This way, receiver doesn't make cache line misses to read rtable. */ -void ipv4_pktinfo_prepare(struct sk_buff *skb) +void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb) { struct in_pktinfo *pktinfo = PKTINFO_SKB_CB(skb); + bool prepare = (inet_sk(sk)->cmsg_flags & IP_CMSG_PKTINFO) || + ipv6_sk_rxinfo(sk); - if (skb_rtable(skb)) { + if (prepare && skb_rtable(skb)) { pktinfo->ipi_ifindex = inet_iif(skb); pktinfo->ipi_spec_dst.s_addr = fib_compute_spec_dst(skb); } else { @@ -1112,11 +1262,22 @@ * the _received_ ones. The set sets the _sent_ ones. */ +static bool getsockopt_needs_rtnl(int optname) +{ + switch (optname) { + case IP_MSFILTER: + case MCAST_MSFILTER: + return true; + } + return false; +} + static int do_ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen, unsigned int flags) { struct inet_sock *inet = inet_sk(sk); - int val; + bool needs_rtnl = getsockopt_needs_rtnl(optname); + int val, err = 0; int len; if (level != SOL_IP) @@ -1130,6 +1291,8 @@ if (len < 0) return -EINVAL; + if (needs_rtnl) + rtnl_lock(); lock_sock(sk); switch (optname) { @@ -1181,6 +1344,9 @@ case IP_RECVORIGDSTADDR: val = (inet->cmsg_flags & IP_CMSG_ORIGDSTADDR) != 0; break; + case IP_CHECKSUM: + val = (inet->cmsg_flags & IP_CMSG_CHECKSUM) != 0; + break; case IP_TOS: val = inet->tos; break; @@ -1195,6 +1361,9 @@ case IP_NODEFRAG: val = inet->nodefrag; break; + case IP_BIND_ADDRESS_NO_PORT: + val = inet->bind_address_no_port; + break; case IP_MTU_DISCOVER: val = inet->pmtudisc; break; @@ -1241,39 +1410,35 @@ case IP_MSFILTER: { struct ip_msfilter msf; - int err; if (len < IP_MSFILTER_SIZE(0)) { - release_sock(sk); - return -EINVAL; + err = -EINVAL; + goto out; } if (copy_from_user(&msf, optval, IP_MSFILTER_SIZE(0))) { - release_sock(sk); - return -EFAULT; + err = -EFAULT; + goto out; } err = ip_mc_msfget(sk, &msf, (struct ip_msfilter __user *)optval, optlen); - release_sock(sk); - return err; + goto out; } case MCAST_MSFILTER: { struct group_filter gsf; - int err; if (len < GROUP_FILTER_SIZE(0)) { - release_sock(sk); - return -EINVAL; + err = -EINVAL; + goto out; } if (copy_from_user(&gsf, optval, GROUP_FILTER_SIZE(0))) { - release_sock(sk); - return -EFAULT; + err = -EFAULT; + goto out; } err = ip_mc_gsfget(sk, &gsf, (struct group_filter __user *)optval, optlen); - release_sock(sk); - return err; + goto out; } case IP_MULTICAST_ALL: val = inet->mc_all; @@ -1287,7 +1452,7 @@ if (sk->sk_type != SOCK_STREAM) return -ENOPROTOOPT; - msg.msg_control = optval; + msg.msg_control = (__force void *) optval; msg.msg_controllen = len; msg.msg_flags = flags; @@ -1340,6 +1505,12 @@ return -EFAULT; } return 0; + +out: + release_sock(sk); + if (needs_rtnl) + rtnl_unlock(); + return err; } int ip_getsockopt(struct sock *sk, int level,