X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=net%2Fipv4%2Fip_sockglue.c;h=57d4bae6f080a470b277a28b505b6e11d015ebc4;hb=97bf2856c6014879bd04983a3e9dfcdac1e7fe85;hp=39e435a454be8fd46c84826e510e6a2214ec02f8;hpb=9213980e6a70d8473e0ffd4b39ab5b6caaba9ff5;p=linux-2.6.git diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 39e435a45..57d4bae6f 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -17,7 +17,6 @@ * Mike McLagan : Routing by source */ -#include #include #include #include @@ -25,12 +24,12 @@ #include #include #include +#include #include #include #include #include -#include -#include +#include #include #include #include @@ -50,6 +49,7 @@ #define IP_CMSG_TOS 4 #define IP_CMSG_RECVOPTS 8 #define IP_CMSG_RETOPTS 16 +#define IP_CMSG_PASSSEC 32 /* * SOL_IP control messages. @@ -92,7 +92,7 @@ static void ip_cmsg_recv_opts(struct msghdr *msg, struct sk_buff *skb) } -void ip_cmsg_recv_retopts(struct msghdr *msg, struct sk_buff *skb) +static void ip_cmsg_recv_retopts(struct msghdr *msg, struct sk_buff *skb) { unsigned char optbuf[sizeof(struct ip_options) + 40]; struct ip_options * opt = (struct ip_options*)optbuf; @@ -109,10 +109,28 @@ void ip_cmsg_recv_retopts(struct msghdr *msg, struct sk_buff *skb) put_cmsg(msg, SOL_IP, IP_RETOPTS, opt->optlen, opt->__data); } +static void ip_cmsg_recv_security(struct msghdr *msg, struct sk_buff *skb) +{ + char *secdata; + u32 seclen, secid; + int err; + + err = security_socket_getpeersec_dgram(NULL, skb, &secid); + if (err) + return; + + err = security_secid_to_secctx(secid, &secdata, &seclen); + if (err) + return; + + put_cmsg(msg, SOL_IP, SCM_SECURITY, seclen, secdata); + security_release_secctx(secdata, seclen); +} + void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb) { - struct inet_opt *inet = inet_sk(skb->sk); + struct inet_sock *inet = inet_sk(skb->sk); unsigned flags = inet->cmsg_flags; /* Ordered by supposed usage frequency */ @@ -138,6 +156,11 @@ void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb) if (flags & 1) ip_cmsg_recv_retopts(msg, skb); + if ((flags>>=1) == 0) + return; + + if (flags & 1) + ip_cmsg_recv_security(msg, skb); } int ip_cmsg_send(struct msghdr *msg, struct ipcm_cookie *ipc) @@ -146,17 +169,14 @@ int ip_cmsg_send(struct msghdr *msg, struct ipcm_cookie *ipc) struct cmsghdr *cmsg; for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) { - if (cmsg->cmsg_len < sizeof(struct cmsghdr) || - (unsigned long)(((char*)cmsg - (char*)msg->msg_control) - + cmsg->cmsg_len) > msg->msg_controllen) { + if (!CMSG_OK(msg, cmsg)) return -EINVAL; - } if (cmsg->cmsg_level != SOL_IP) continue; switch (cmsg->cmsg_type) { case IP_RETOPTS: err = cmsg->cmsg_len - CMSG_ALIGN(sizeof(struct cmsghdr)); - err = ip_options_get(&ipc->opt, CMSG_DATA(cmsg), err < 40 ? err : 40, 0); + err = ip_options_get(&ipc->opt, CMSG_DATA(cmsg), err < 40 ? err : 40); if (err) return err; break; @@ -189,7 +209,7 @@ int ip_cmsg_send(struct msghdr *msg, struct ipcm_cookie *ipc) sent to multicast group to reach destination designated router. */ struct ip_ra_chain *ip_ra_chain; -rwlock_t ip_ra_lock = RW_LOCK_UNLOCKED; +DEFINE_RWLOCK(ip_ra_lock); int ip_ra_control(struct sock *sk, unsigned char on, void (*destructor)(struct sock *)) { @@ -205,8 +225,7 @@ int ip_ra_control(struct sock *sk, unsigned char on, void (*destructor)(struct s if (ra->sk == sk) { if (on) { write_unlock_bh(&ip_ra_lock); - if (new_ra) - kfree(new_ra); + kfree(new_ra); return -EADDRINUSE; } *rap = ra->next; @@ -235,9 +254,9 @@ int ip_ra_control(struct sock *sk, unsigned char on, void (*destructor)(struct s } void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err, - u16 port, u32 info, u8 *payload) + __be16 port, u32 info, u8 *payload) { - struct inet_opt *inet = inet_sk(sk); + struct inet_sock *inet = inet_sk(sk); struct sock_exterr_skb *serr; if (!inet->recverr) @@ -264,9 +283,9 @@ void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err, kfree_skb(skb); } -void ip_local_error(struct sock *sk, int err, u32 daddr, u16 port, u32 info) +void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 port, u32 info) { - struct inet_opt *inet = inet_sk(sk); + struct inet_sock *inet = inet_sk(sk); struct sock_exterr_skb *serr; struct iphdr *iph; struct sk_buff *skb; @@ -336,7 +355,7 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len) sin = (struct sockaddr_in *)msg->msg_name; if (sin) { sin->sin_family = AF_INET; - sin->sin_addr.s_addr = *(u32*)(skb->nh.raw + serr->addr_offset); + sin->sin_addr.s_addr = *(__be32*)(skb->nh.raw + serr->addr_offset); sin->sin_port = serr->port; memset(&sin->sin_zero, 0, sizeof(sin->sin_zero)); } @@ -345,7 +364,7 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len) sin = &errhdr.offender; sin->sin_family = AF_UNSPEC; if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP) { - struct inet_opt *inet = inet_sk(sk); + struct inet_sock *inet = inet_sk(sk); sin->sin_family = AF_INET; sin->sin_addr.s_addr = skb->nh.iph->saddr; @@ -363,14 +382,14 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len) err = copied; /* Reset and regenerate socket error */ - spin_lock_irq(&sk->sk_error_queue.lock); + spin_lock_bh(&sk->sk_error_queue.lock); sk->sk_err = 0; if ((skb2 = skb_peek(&sk->sk_error_queue)) != NULL) { sk->sk_err = SKB_EXT_ERR(skb2)->ee.ee_errno; - spin_unlock_irq(&sk->sk_error_queue.lock); + spin_unlock_bh(&sk->sk_error_queue.lock); sk->sk_error_report(sk); } else - spin_unlock_irq(&sk->sk_error_queue.lock); + spin_unlock_bh(&sk->sk_error_queue.lock); out_free_skb: kfree_skb(skb); @@ -384,20 +403,19 @@ out: * an IP socket. */ -int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, int optlen) +static int do_ip_setsockopt(struct sock *sk, int level, + int optname, char __user *optval, int optlen) { - struct inet_opt *inet = inet_sk(sk); + struct inet_sock *inet = inet_sk(sk); int val=0,err; - if (level != SOL_IP) - return -ENOPROTOOPT; - if (((1<= sizeof(int)) { @@ -428,11 +446,11 @@ int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, struct ip_options * opt = NULL; if (optlen > 40 || optlen < 0) goto e_inval; - err = ip_options_get(&opt, optval, optlen, 1); + err = ip_options_get_from_user(&opt, optval, optlen); if (err) break; - if (sk->sk_type == SOCK_STREAM) { - struct tcp_opt *tp = tcp_sk(sk); + if (inet->is_icsk) { + struct inet_connection_sock *icsk = inet_csk(sk); #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) if (sk->sk_family == PF_INET || (!((1 << sk->sk_state) & @@ -440,17 +458,16 @@ int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, inet->daddr != LOOPBACK4_IPV6)) { #endif if (inet->opt) - tp->ext_header_len -= inet->opt->optlen; + icsk->icsk_ext_hdr_len -= inet->opt->optlen; if (opt) - tp->ext_header_len += opt->optlen; - tcp_sync_mss(sk, tp->pmtu_cookie); + icsk->icsk_ext_hdr_len += opt->optlen; + icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie); #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) } #endif } opt = xchg(&inet->opt, opt); - if (opt) - kfree(opt); + kfree(opt); break; } case IP_PKTINFO: @@ -483,6 +500,12 @@ int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, else inet->cmsg_flags &= ~IP_CMSG_RETOPTS; break; + case IP_PASSSEC: + if (val) + inet->cmsg_flags |= IP_CMSG_PASSSEC; + else + inet->cmsg_flags &= ~IP_CMSG_PASSSEC; + break; case IP_TOS: /* This sets both TOS and Precedence */ if (sk->sk_type == SOCK_STREAM) { val &= ~3; @@ -617,7 +640,6 @@ int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, } case IP_MSFILTER: { - extern int sysctl_optmem_max; extern int sysctl_igmp_max_msf; struct ip_msfilter *msf; @@ -627,7 +649,7 @@ int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, err = -ENOBUFS; break; } - msf = (struct ip_msfilter *)kmalloc(optlen, GFP_KERNEL); + msf = kmalloc(optlen, GFP_KERNEL); if (msf == 0) { err = -ENOBUFS; break; @@ -680,11 +702,11 @@ int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, mreq.imr_address.s_addr = mreqs.imr_interface; mreq.imr_ifindex = 0; err = ip_mc_join_group(sk, &mreq); - if (err) + if (err && err != -EADDRINUSE) break; omode = MCAST_INCLUDE; add = 1; - } else /*IP_DROP_SOURCE_MEMBERSHIP */ { + } else /* IP_DROP_SOURCE_MEMBERSHIP */ { omode = MCAST_INCLUDE; add = 0; } @@ -757,8 +779,9 @@ int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, mreq.imr_address.s_addr = 0; mreq.imr_ifindex = greqs.gsr_interface; err = ip_mc_join_group(sk, &mreq); - if (err) + if (err && err != -EADDRINUSE) break; + greqs.gsr_interface = mreq.imr_ifindex; omode = MCAST_INCLUDE; add = 1; } else /* MCAST_LEAVE_SOURCE_GROUP */ { @@ -771,11 +794,10 @@ int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, } case MCAST_MSFILTER: { - extern int sysctl_optmem_max; extern int sysctl_igmp_max_msf; struct sockaddr_in *psin; - struct ip_msfilter *msf = 0; - struct group_filter *gsf = 0; + struct ip_msfilter *msf = NULL; + struct group_filter *gsf = NULL; int msize, i, ifindex; if (optlen < GROUP_FILTER_SIZE(0)) @@ -784,7 +806,7 @@ int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, err = -ENOBUFS; break; } - gsf = (struct group_filter *)kmalloc(optlen,GFP_KERNEL); + gsf = kmalloc(optlen,GFP_KERNEL); if (gsf == 0) { err = -ENOBUFS; break; @@ -804,7 +826,7 @@ int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, goto mc_msf_out; } msize = IP_MSFILTER_SIZE(gsf->gf_numsrc); - msf = (struct ip_msfilter *)kmalloc(msize,GFP_KERNEL); + msf = kmalloc(msize,GFP_KERNEL); if (msf == 0) { err = -ENOBUFS; goto mc_msf_out; @@ -828,14 +850,12 @@ int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, msf->imsf_slist[i] = psin->sin_addr.s_addr; } kfree(gsf); - gsf = 0; + gsf = NULL; err = ip_mc_msfilter(sk, msf, ifindex); mc_msf_out: - if (msf) - kfree(msf); - if (gsf) - kfree(gsf); + kfree(msf); + kfree(gsf); break; } case IP_ROUTER_ALERT: @@ -850,16 +870,14 @@ mc_msf_out: case IP_IPSEC_POLICY: case IP_XFRM_POLICY: + err = -EPERM; + if (!capable(CAP_NET_ADMIN)) + break; err = xfrm_user_policy(sk, optname, optval, optlen); break; default: -#ifdef CONFIG_NETFILTER - err = nf_setsockopt(sk, PF_INET, optname, optval, - optlen); -#else err = -ENOPROTOOPT; -#endif break; } release_sock(sk); @@ -870,14 +888,70 @@ e_inval: return -EINVAL; } +int ip_setsockopt(struct sock *sk, int level, + int optname, char __user *optval, int optlen) +{ + int err; + + if (level != SOL_IP) + return -ENOPROTOOPT; + + err = do_ip_setsockopt(sk, level, optname, optval, optlen); +#ifdef CONFIG_NETFILTER + /* we need to exclude all possible ENOPROTOOPTs except default case */ + if (err == -ENOPROTOOPT && optname != IP_HDRINCL && + optname != IP_IPSEC_POLICY && optname != IP_XFRM_POLICY +#ifdef CONFIG_IP_MROUTE + && (optname < MRT_BASE || optname > (MRT_BASE + 10)) +#endif + ) { + lock_sock(sk); + err = nf_setsockopt(sk, PF_INET, optname, optval, optlen); + release_sock(sk); + } +#endif + return err; +} + +#ifdef CONFIG_COMPAT +int compat_ip_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, int optlen) +{ + int err; + + if (level != SOL_IP) + return -ENOPROTOOPT; + + err = do_ip_setsockopt(sk, level, optname, optval, optlen); +#ifdef CONFIG_NETFILTER + /* we need to exclude all possible ENOPROTOOPTs except default case */ + if (err == -ENOPROTOOPT && optname != IP_HDRINCL && + optname != IP_IPSEC_POLICY && optname != IP_XFRM_POLICY +#ifdef CONFIG_IP_MROUTE + && (optname < MRT_BASE || optname > (MRT_BASE + 10)) +#endif + ) { + lock_sock(sk); + err = compat_nf_setsockopt(sk, PF_INET, optname, + optval, optlen); + release_sock(sk); + } +#endif + return err; +} + +EXPORT_SYMBOL(compat_ip_setsockopt); +#endif + /* * Get the options. Note for future reference. The GET of IP options gets the * _received_ ones. The set sets the _sent_ ones. */ -int ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) +static int do_ip_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) { - struct inet_opt *inet = inet_sk(sk); + struct inet_sock *inet = inet_sk(sk); int val; int len; @@ -937,6 +1011,9 @@ int ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval, case IP_RETOPTS: val = (inet->cmsg_flags & IP_CMSG_RETOPTS) != 0; break; + case IP_PASSSEC: + val = (inet->cmsg_flags & IP_CMSG_PASSSEC) != 0; + break; case IP_TOS: val = inet->tos; break; @@ -957,7 +1034,7 @@ int ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval, val = 0; dst = sk_dst_get(sk); if (dst) { - val = dst_pmtu(dst) - dst->header_len; + val = dst_mtu(dst); dst_release(dst); } if (!val) { @@ -1056,17 +1133,8 @@ int ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval, val = inet->freebind; break; default: -#ifdef CONFIG_NETFILTER - val = nf_getsockopt(sk, PF_INET, optname, optval, - &len); - release_sock(sk); - if (val >= 0) - val = put_user(len, optlen); - return val; -#else release_sock(sk); return -ENOPROTOOPT; -#endif } release_sock(sk); @@ -1087,9 +1155,68 @@ int ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval, return 0; } +int ip_getsockopt(struct sock *sk, int level, + int optname, char __user *optval, int __user *optlen) +{ + int err; + + err = do_ip_getsockopt(sk, level, optname, optval, optlen); +#ifdef CONFIG_NETFILTER + /* we need to exclude all possible ENOPROTOOPTs except default case */ + if (err == -ENOPROTOOPT && optname != IP_PKTOPTIONS +#ifdef CONFIG_IP_MROUTE + && (optname < MRT_BASE || optname > MRT_BASE+10) +#endif + ) { + int len; + + if(get_user(len,optlen)) + return -EFAULT; + + lock_sock(sk); + err = nf_getsockopt(sk, PF_INET, optname, optval, + &len); + release_sock(sk); + if (err >= 0) + err = put_user(len, optlen); + return err; + } +#endif + return err; +} + +#ifdef CONFIG_COMPAT +int compat_ip_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) +{ + int err = do_ip_getsockopt(sk, level, optname, optval, optlen); +#ifdef CONFIG_NETFILTER + /* we need to exclude all possible ENOPROTOOPTs except default case */ + if (err == -ENOPROTOOPT && optname != IP_PKTOPTIONS +#ifdef CONFIG_IP_MROUTE + && (optname < MRT_BASE || optname > MRT_BASE+10) +#endif + ) { + int len; + + if (get_user(len, optlen)) + return -EFAULT; + + lock_sock(sk); + err = compat_nf_getsockopt(sk, PF_INET, optname, optval, &len); + release_sock(sk); + if (err >= 0) + err = put_user(len, optlen); + return err; + } +#endif + return err; +} + +EXPORT_SYMBOL(compat_ip_getsockopt); +#endif + EXPORT_SYMBOL(ip_cmsg_recv); -#ifdef CONFIG_IP_SCTP_MODULE EXPORT_SYMBOL(ip_getsockopt); EXPORT_SYMBOL(ip_setsockopt); -#endif