diff options
author | Len Brown <len.brown@intel.com> | 2006-01-27 17:18:29 -0500 |
---|---|---|
committer | Len Brown <len.brown@intel.com> | 2006-01-27 17:18:29 -0500 |
commit | 292dd876ee765c478b27c93cc51e93a558ed58bf (patch) | |
tree | 5b740e93253295baee2a9c414a6c66d03d44a9ef /net/ipv4 | |
parent | d4ec6c7cc9a15a7a529719bc3b84f46812f9842e (diff) | |
parent | 9fdb62af92c741addbea15545f214a6e89460865 (diff) |
Pull release into acpica branch
Diffstat (limited to 'net/ipv4')
100 files changed, 1085 insertions, 4486 deletions
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index c54edd76de09..35e5f5999092 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -9,7 +9,7 @@ obj-y := route.o inetpeer.o protocol.o \ tcp.o tcp_input.o tcp_output.o tcp_timer.o tcp_ipv4.o \ tcp_minisocks.o tcp_cong.o \ datagram.o raw.o udp.o arp.o icmp.o devinet.o af_inet.o igmp.o \ - sysctl_net_ipv4.o fib_frontend.o fib_semantics.o netfilter.o + sysctl_net_ipv4.o fib_frontend.o fib_semantics.o obj-$(CONFIG_IP_FIB_HASH) += fib_hash.o obj-$(CONFIG_IP_FIB_TRIE) += fib_trie.o @@ -28,7 +28,7 @@ obj-$(CONFIG_IP_ROUTE_MULTIPATH_RR) += multipath_rr.o obj-$(CONFIG_IP_ROUTE_MULTIPATH_RANDOM) += multipath_random.o obj-$(CONFIG_IP_ROUTE_MULTIPATH_WRANDOM) += multipath_wrandom.o obj-$(CONFIG_IP_ROUTE_MULTIPATH_DRR) += multipath_drr.o -obj-$(CONFIG_NETFILTER) += netfilter/ +obj-$(CONFIG_NETFILTER) += netfilter.o netfilter/ obj-$(CONFIG_IP_VS) += ipvs/ obj-$(CONFIG_INET_DIAG) += inet_diag.o obj-$(CONFIG_IP_ROUTE_MULTIPATH_CACHED) += multipath.o diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 966a071a408c..97c276f95b35 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -79,6 +79,7 @@ #include <linux/string.h> #include <linux/sockios.h> #include <linux/net.h> +#include <linux/capability.h> #include <linux/fcntl.h> #include <linux/mm.h> #include <linux/interrupt.h> diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 37432088fe6d..accdefedfed7 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -79,6 +79,7 @@ #include <linux/string.h> #include <linux/kernel.h> #include <linux/sched.h> +#include <linux/capability.h> #include <linux/config.h> #include <linux/socket.h> #include <linux/sockios.h> diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 7b9bb28e2ee9..95b9d81ac488 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -32,6 +32,7 @@ #include <asm/uaccess.h> #include <asm/system.h> #include <linux/bitops.h> +#include <linux/capability.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 18f5e509281a..4e3d3811dea2 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -20,6 +20,7 @@ #include <asm/uaccess.h> #include <asm/system.h> #include <linux/bitops.h> +#include <linux/capability.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/sched.h> @@ -288,13 +289,13 @@ static int inet_check_attr(struct rtmsg *r, struct rtattr **rta) { int i; - for (i=1; i<=RTA_MAX; i++) { - struct rtattr *attr = rta[i-1]; + for (i=1; i<=RTA_MAX; i++, rta++) { + struct rtattr *attr = *rta; if (attr) { if (RTA_PAYLOAD(attr) < 4) return -EINVAL; if (i != RTA_MULTIPATH && i != RTA_METRICS) - rta[i-1] = (struct rtattr*)RTA_DATA(attr); + *rta = (struct rtattr*)RTA_DATA(attr); } } return 0; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index be5a519cd2f8..105039eb7629 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -899,8 +899,7 @@ static void icmp_address_reply(struct sk_buff *skb) u32 _mask, *mp; mp = skb_header_pointer(skb, 0, sizeof(_mask), &_mask); - if (mp == NULL) - BUG(); + BUG_ON(mp == NULL); for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) { if (*mp == ifa->ifa_mask && inet_ifa_match(rt->rt_src, ifa)) diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 34758118c10c..d8ce7133cd8f 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -233,7 +233,18 @@ static int is_in(struct ip_mc_list *pmc, struct ip_sf_list *psf, int type, case IGMPV3_MODE_IS_EXCLUDE: if (gdeleted || sdeleted) return 0; - return !(pmc->gsquery && !psf->sf_gsresp); + if (!(pmc->gsquery && !psf->sf_gsresp)) { + if (pmc->sfmode == MCAST_INCLUDE) + return 1; + /* don't include if this source is excluded + * in all filters + */ + if (psf->sf_count[MCAST_INCLUDE]) + return type == IGMPV3_MODE_IS_INCLUDE; + return pmc->sfcount[MCAST_EXCLUDE] == + psf->sf_count[MCAST_EXCLUDE]; + } + return 0; case IGMPV3_CHANGE_TO_INCLUDE: if (gdeleted || sdeleted) return 0; @@ -385,7 +396,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, struct igmpv3_report *pih; struct igmpv3_grec *pgr = NULL; struct ip_sf_list *psf, *psf_next, *psf_prev, **psf_list; - int scount, first, isquery, truncate; + int scount, stotal, first, isquery, truncate; if (pmc->multiaddr == IGMP_ALL_HOSTS) return skb; @@ -395,25 +406,13 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, truncate = type == IGMPV3_MODE_IS_EXCLUDE || type == IGMPV3_CHANGE_TO_EXCLUDE; + stotal = scount = 0; + psf_list = sdeleted ? &pmc->tomb : &pmc->sources; - if (!*psf_list) { - if (type == IGMPV3_ALLOW_NEW_SOURCES || - type == IGMPV3_BLOCK_OLD_SOURCES) - return skb; - if (pmc->crcount || isquery) { - /* make sure we have room for group header and at - * least one source. - */ - if (skb && AVAILABLE(skb) < sizeof(struct igmpv3_grec)+ - sizeof(__u32)) { - igmpv3_sendpack(skb); - skb = NULL; /* add_grhead will get a new one */ - } - skb = add_grhead(skb, pmc, type, &pgr); - } - return skb; - } + if (!*psf_list) + goto empty_source; + pih = skb ? (struct igmpv3_report *)skb->h.igmph : NULL; /* EX and TO_EX get a fresh packet, if needed */ @@ -426,7 +425,6 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, } } first = 1; - scount = 0; psf_prev = NULL; for (psf=*psf_list; psf; psf=psf_next) { u32 *psrc; @@ -460,7 +458,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, } psrc = (u32 *)skb_put(skb, sizeof(u32)); *psrc = psf->sf_inaddr; - scount++; + scount++; stotal++; if ((type == IGMPV3_ALLOW_NEW_SOURCES || type == IGMPV3_BLOCK_OLD_SOURCES) && psf->sf_crcount) { psf->sf_crcount--; @@ -475,6 +473,21 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, } psf_prev = psf; } + +empty_source: + if (!stotal) { + if (type == IGMPV3_ALLOW_NEW_SOURCES || + type == IGMPV3_BLOCK_OLD_SOURCES) + return skb; + if (pmc->crcount || isquery) { + /* make sure we have room for group header */ + if (skb && AVAILABLE(skb)<sizeof(struct igmpv3_grec)) { + igmpv3_sendpack(skb); + skb = NULL; /* add_grhead will get a new one */ + } + skb = add_grhead(skb, pmc, type, &pgr); + } + } if (pgr) pgr->grec_nsrcs = htons(scount); @@ -557,11 +570,11 @@ static void igmpv3_send_cr(struct in_device *in_dev) skb = add_grec(skb, pmc, dtype, 1, 1); } if (pmc->crcount) { - pmc->crcount--; if (pmc->sfmode == MCAST_EXCLUDE) { type = IGMPV3_CHANGE_TO_INCLUDE; skb = add_grec(skb, pmc, type, 1, 0); } + pmc->crcount--; if (pmc->crcount == 0) { igmpv3_clear_zeros(&pmc->tomb); igmpv3_clear_zeros(&pmc->sources); @@ -594,12 +607,12 @@ static void igmpv3_send_cr(struct in_device *in_dev) /* filter mode changes */ if (pmc->crcount) { - pmc->crcount--; if (pmc->sfmode == MCAST_EXCLUDE) type = IGMPV3_CHANGE_TO_EXCLUDE; else type = IGMPV3_CHANGE_TO_INCLUDE; skb = add_grec(skb, pmc, type, 0, 0); + pmc->crcount--; } spin_unlock_bh(&pmc->lock); } @@ -735,11 +748,43 @@ static void igmp_timer_expire(unsigned long data) ip_ma_put(im); } -static void igmp_marksources(struct ip_mc_list *pmc, int nsrcs, __u32 *srcs) +/* mark EXCLUDE-mode sources */ +static int igmp_xmarksources(struct ip_mc_list *pmc, int nsrcs, __u32 *srcs) +{ + struct ip_sf_list *psf; + int i, scount; + + scount = 0; + for (psf=pmc->sources; psf; psf=psf->sf_next) { + if (scount == nsrcs) + break; + for (i=0; i<nsrcs; i++) { + /* skip inactive filters */ + if (pmc->sfcount[MCAST_INCLUDE] || + pmc->sfcount[MCAST_EXCLUDE] != + psf->sf_count[MCAST_EXCLUDE]) + continue; + if (srcs[i] == psf->sf_inaddr) { + scount++; + break; + } + } + } + pmc->gsquery = 0; + if (scount == nsrcs) /* all sources excluded */ + return 0; + return 1; +} + +static int igmp_marksources(struct ip_mc_list *pmc, int nsrcs, __u32 *srcs) { struct ip_sf_list *psf; int i, scount; + if (pmc->sfmode == MCAST_EXCLUDE) + return igmp_xmarksources(pmc, nsrcs, srcs); + + /* mark INCLUDE-mode sources */ scount = 0; for (psf=pmc->sources; psf; psf=psf->sf_next) { if (scount == nsrcs) @@ -751,6 +796,12 @@ static void igmp_marksources(struct ip_mc_list *pmc, int nsrcs, __u32 *srcs) break; } } + if (!scount) { + pmc->gsquery = 0; + return 0; + } + pmc->gsquery = 1; + return 1; } static void igmp_heard_report(struct in_device *in_dev, u32 group) @@ -845,6 +896,8 @@ static void igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, */ read_lock(&in_dev->mc_list_lock); for (im=in_dev->mc_list; im!=NULL; im=im->next) { + int changed; + if (group && group != im->multiaddr) continue; if (im->multiaddr == IGMP_ALL_HOSTS) @@ -854,10 +907,11 @@ static void igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, im->gsquery = im->gsquery && mark; else im->gsquery = mark; - if (im->gsquery) - igmp_marksources(im, ntohs(ih3->nsrcs), ih3->srcs); + changed = !im->gsquery || + igmp_marksources(im, ntohs(ih3->nsrcs), ih3->srcs); spin_unlock_bh(&im->lock); - igmp_mod_timer(im, max_delay); + if (changed) + igmp_mod_timer(im, max_delay); } read_unlock(&in_dev->mc_list_lock); } @@ -975,7 +1029,7 @@ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im) * for deleted items allows change reports to use common code with * non-deleted or query-response MCA's. */ - pmc = (struct ip_mc_list *)kmalloc(sizeof(*pmc), GFP_KERNEL); + pmc = kmalloc(sizeof(*pmc), GFP_KERNEL); if (!pmc) return; memset(pmc, 0, sizeof(*pmc)); @@ -1155,7 +1209,7 @@ void ip_mc_inc_group(struct in_device *in_dev, u32 addr) } } - im = (struct ip_mc_list *)kmalloc(sizeof(*im), GFP_KERNEL); + im = kmalloc(sizeof(*im), GFP_KERNEL); if (!im) goto out; @@ -1476,7 +1530,7 @@ static int ip_mc_add1_src(struct ip_mc_list *pmc, int sfmode, psf_prev = psf; } if (!psf) { - psf = (struct ip_sf_list *)kmalloc(sizeof(*psf), GFP_ATOMIC); + psf = kmalloc(sizeof(*psf), GFP_ATOMIC); if (!psf) return -ENOBUFS; memset(psf, 0, sizeof(*psf)); @@ -1510,7 +1564,7 @@ static void sf_markstate(struct ip_mc_list *pmc) static int sf_setstate(struct ip_mc_list *pmc) { - struct ip_sf_list *psf; + struct ip_sf_list *psf, *dpsf; int mca_xcount = pmc->sfcount[MCAST_EXCLUDE]; int qrv = pmc->interface->mr_qrv; int new_in, rv; @@ -1522,8 +1576,46 @@ static int sf_setstate(struct ip_mc_list *pmc) !psf->sf_count[MCAST_INCLUDE]; } else new_in = psf->sf_count[MCAST_INCLUDE] != 0; - if (new_in != psf->sf_oldin) { - psf->sf_crcount = qrv; + if (new_in) { + if (!psf->sf_oldin) { + struct ip_sf_list *prev = 0; + + for (dpsf=pmc->tomb; dpsf; dpsf=dpsf->sf_next) { + if (dpsf->sf_inaddr == psf->sf_inaddr) + break; + prev = dpsf; + } + if (dpsf) { + if (prev) + prev->sf_next = dpsf->sf_next; + else + pmc->tomb = dpsf->sf_next; + kfree(dpsf); + } + psf->sf_crcount = qrv; + rv++; + } + } else if (psf->sf_oldin) { + + psf->sf_crcount = 0; + /* + * add or update "delete" records if an active filter + * is now inactive + */ + for (dpsf=pmc->tomb; dpsf; dpsf=dpsf->sf_next) + if (dpsf->sf_inaddr == psf->sf_inaddr) + break; + if (!dpsf) { + dpsf = (struct ip_sf_list *) + kmalloc(sizeof(*dpsf), GFP_ATOMIC); + if (!dpsf) + continue; + *dpsf = *psf; + /* pmc->lock held by callers */ + dpsf->sf_next = pmc->tomb; + pmc->tomb = dpsf; + } + dpsf->sf_crcount = qrv; rv++; } } @@ -1659,7 +1751,7 @@ int ip_mc_join_group(struct sock *sk , struct ip_mreqn *imr) err = -ENOBUFS; if (count >= sysctl_igmp_max_memberships) goto done; - iml = (struct ip_mc_socklist *)sock_kmalloc(sk,sizeof(*iml),GFP_KERNEL); + iml = sock_kmalloc(sk,sizeof(*iml),GFP_KERNEL); if (iml == NULL) goto done; @@ -1823,8 +1915,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct if (psl) count += psl->sl_max; - newpsl = (struct ip_sf_socklist *)sock_kmalloc(sk, - IP_SFLSIZE(count), GFP_KERNEL); + newpsl = sock_kmalloc(sk, IP_SFLSIZE(count), GFP_KERNEL); if (!newpsl) { err = -ENOBUFS; goto done; @@ -1907,8 +1998,8 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) goto done; } if (msf->imsf_numsrc) { - newpsl = (struct ip_sf_socklist *)sock_kmalloc(sk, - IP_SFLSIZE(msf->imsf_numsrc), GFP_KERNEL); + newpsl = sock_kmalloc(sk, IP_SFLSIZE(msf->imsf_numsrc), + GFP_KERNEL); if (!newpsl) { err = -ENOBUFS; goto done; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index c49908192047..457db99c76df 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -50,9 +50,10 @@ static struct sock *idiagnl; #define INET_DIAG_PUT(skb, attrtype, attrlen) \ RTA_DATA(__RTA_PUT(skb, attrtype, attrlen)) -static int inet_diag_fill(struct sk_buff *skb, struct sock *sk, - int ext, u32 pid, u32 seq, u16 nlmsg_flags, - const struct nlmsghdr *unlh) +static int inet_csk_diag_fill(struct sock *sk, + struct sk_buff *skb, + int ext, u32 pid, u32 seq, u16 nlmsg_flags, + const struct nlmsghdr *unlh) { const struct inet_sock *inet = inet_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); @@ -70,20 +71,22 @@ static int inet_diag_fill(struct sk_buff *skb, struct sock *sk, nlh->nlmsg_flags = nlmsg_flags; r = NLMSG_DATA(nlh); - if (sk->sk_state != TCP_TIME_WAIT) { - if (ext & (1 << (INET_DIAG_MEMINFO - 1))) - minfo = INET_DIAG_PUT(skb, INET_DIAG_MEMINFO, - sizeof(*minfo)); - if (ext & (1 << (INET_DIAG_INFO - 1))) - info = INET_DIAG_PUT(skb, INET_DIAG_INFO, - handler->idiag_info_size); - - if ((ext & (1 << (INET_DIAG_CONG - 1))) && icsk->icsk_ca_ops) { - size_t len = strlen(icsk->icsk_ca_ops->name); - strcpy(INET_DIAG_PUT(skb, INET_DIAG_CONG, len + 1), - icsk->icsk_ca_ops->name); - } + BUG_ON(sk->sk_state == TCP_TIME_WAIT); + + if (ext & (1 << (INET_DIAG_MEMINFO - 1))) + minfo = INET_DIAG_PUT(skb, INET_DIAG_MEMINFO, sizeof(*minfo)); + + if (ext & (1 << (INET_DIAG_INFO - 1))) + info = INET_DIAG_PUT(skb, INET_DIAG_INFO, + handler->idiag_info_size); + + if ((ext & (1 << (INET_DIAG_CONG - 1))) && icsk->icsk_ca_ops) { + const size_t len = strlen(icsk->icsk_ca_ops->name); + + strcpy(INET_DIAG_PUT(skb, INET_DIAG_CONG, len + 1), + icsk->icsk_ca_ops->name); } + r->idiag_family = sk->sk_family; r->idiag_state = sk->sk_state; r->idiag_timer = 0; @@ -93,37 +96,6 @@ static int inet_diag_fill(struct sk_buff *skb, struct sock *sk, r->id.idiag_cookie[0] = (u32)(unsigned long)sk; r->id.idiag_cookie[1] = (u32)(((unsigned long)sk >> 31) >> 1); - if (r->idiag_state == TCP_TIME_WAIT) { - const struct inet_timewait_sock *tw = inet_twsk(sk); - long tmo = tw->tw_ttd - jiffies; - if (tmo < 0) - tmo = 0; - - r->id.idiag_sport = tw->tw_sport; - r->id.idiag_dport = tw->tw_dport; - r->id.idiag_src[0] = tw->tw_rcv_saddr; - r->id.idiag_dst[0] = tw->tw_daddr; - r->idiag_state = tw->tw_substate; - r->idiag_timer = 3; - r->idiag_expires = (tmo * 1000 + HZ - 1) / HZ; - r->idiag_rqueue = 0; - r->idiag_wqueue = 0; - r->idiag_uid = 0; - r->idiag_inode = 0; -#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) - if (r->idiag_family == AF_INET6) { - const struct inet6_timewait_sock *tw6 = inet6_twsk(sk); - - ipv6_addr_copy((struct in6_addr *)r->id.idiag_src, - &tw6->tw_v6_rcv_saddr); - ipv6_addr_copy((struct in6_addr *)r->id.idiag_dst, - &tw6->tw_v6_daddr); - } -#endif - nlh->nlmsg_len = skb->tail - b; - return skb->len; - } - r->id.idiag_sport = inet->sport; r->id.idiag_dport = inet->dport; r->id.idiag_src[0] = inet->rcv_saddr; @@ -185,7 +157,75 @@ nlmsg_failure: return -1; } -static int inet_diag_get_exact(struct sk_buff *in_skb, const struct nlmsghdr *nlh) +static int inet_twsk_diag_fill(struct inet_timewait_sock *tw, + struct sk_buff *skb, int ext, u32 pid, + u32 seq, u16 nlmsg_flags, + const struct nlmsghdr *unlh) +{ + long tmo; + struct inet_diag_msg *r; + const unsigned char *previous_tail = skb->tail; + struct nlmsghdr *nlh = NLMSG_PUT(skb, pid, seq, + unlh->nlmsg_type, sizeof(*r)); + + r = NLMSG_DATA(nlh); + BUG_ON(tw->tw_state != TCP_TIME_WAIT); + + nlh->nlmsg_flags = nlmsg_flags; + + tmo = tw->tw_ttd - jiffies; + if (tmo < 0) + tmo = 0; + + r->idiag_family = tw->tw_family; + r->idiag_state = tw->tw_state; + r->idiag_timer = 0; + r->idiag_retrans = 0; + r->id.idiag_if = tw->tw_bound_dev_if; + r->id.idiag_cookie[0] = (u32)(unsigned long)tw; + r->id.idiag_cookie[1] = (u32)(((unsigned long)tw >> 31) >> 1); + r->id.idiag_sport = tw->tw_sport; + r->id.idiag_dport = tw->tw_dport; + r->id.idiag_src[0] = tw->tw_rcv_saddr; + r->id.idiag_dst[0] = tw->tw_daddr; + r->idiag_state = tw->tw_substate; + r->idiag_timer = 3; + r->idiag_expires = (tmo * 1000 + HZ - 1) / HZ; + r->idiag_rqueue = 0; + r->idiag_wqueue = 0; + r->idiag_uid = 0; + r->idiag_inode = 0; +#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) + if (tw->tw_family == AF_INET6) { + const struct inet6_timewait_sock *tw6 = + inet6_twsk((struct sock *)tw); + + ipv6_addr_copy((struct in6_addr *)r->id.idiag_src, + &tw6->tw_v6_rcv_saddr); + ipv6_addr_copy((struct in6_addr *)r->id.idiag_dst, + &tw6->tw_v6_daddr); + } +#endif + nlh->nlmsg_len = skb->tail - previous_tail; + return skb->len; +nlmsg_failure: + skb_trim(skb, previous_tail - skb->data); + return -1; +} + +static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, + int ext, u32 pid, u32 seq, u16 nlmsg_flags, + const struct nlmsghdr *unlh) +{ + if (sk->sk_state == TCP_TIME_WAIT) + return inet_twsk_diag_fill((struct inet_timewait_sock *)sk, + skb, ext, pid, seq, nlmsg_flags, + unlh); + return inet_csk_diag_fill(sk, skb, ext, pid, seq, nlmsg_flags, unlh); +} + +static int inet_diag_get_exact(struct sk_buff *in_skb, + const struct nlmsghdr *nlh) { int err; struct sock *sk; @@ -235,7 +275,7 @@ static int inet_diag_get_exact(struct sk_buff *in_skb, const struct nlmsghdr *nl if (!rep) goto out; - if (inet_diag_fill(rep, sk, req->idiag_ext, + if (sk_diag_fill(sk, rep, req->idiag_ext, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq, 0, nlh) <= 0) BUG(); @@ -283,7 +323,7 @@ static int bitstring_match(const u32 *a1, const u32 *a2, int bits) static int inet_diag_bc_run(const void *bc, int len, - const struct inet_diag_entry *entry) + const struct inet_diag_entry *entry) { while (len > 0) { int yes = 1; @@ -322,7 +362,7 @@ static int inet_diag_bc_run(const void *bc, int len, yes = 0; break; } - + if (cond->prefix_len == 0) break; @@ -331,7 +371,8 @@ static int inet_diag_bc_run(const void *bc, int len, else addr = entry->daddr; - if (bitstring_match(addr, cond->addr, cond->prefix_len)) + if (bitstring_match(addr, cond->addr, + cond->prefix_len)) break; if (entry->family == AF_INET6 && cond->family == AF_INET) { @@ -346,7 +387,7 @@ static int inet_diag_bc_run(const void *bc, int len, } } - if (yes) { + if (yes) { len -= op->yes; bc += op->yes; } else { @@ -407,14 +448,15 @@ static int inet_diag_bc_audit(const void *bytecode, int bytecode_len) default: return -EINVAL; } - bc += op->yes; + bc += op->yes; len -= op->yes; } return len == 0 ? 0 : -EINVAL; } -static int inet_diag_dump_sock(struct sk_buff *skb, struct sock *sk, - struct netlink_callback *cb) +static int inet_csk_diag_dump(struct sock *sk, + struct sk_buff *skb, + struct netlink_callback *cb) { struct inet_diag_req *r = NLMSG_DATA(cb->nlh); @@ -444,14 +486,50 @@ static int inet_diag_dump_sock(struct sk_buff *skb, struct sock *sk, return 0; } - return inet_diag_fill(skb, sk, r->idiag_ext, NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh); + return inet_csk_diag_fill(sk, skb, r->idiag_ext, + NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh); +} + +static int inet_twsk_diag_dump(struct inet_timewait_sock *tw, + struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct inet_diag_req *r = NLMSG_DATA(cb->nlh); + + if (cb->nlh->nlmsg_len > 4 + NLMSG_SPACE(sizeof(*r))) { + struct inet_diag_entry entry; + struct rtattr *bc = (struct rtattr *)(r + 1); + + entry.family = tw->tw_family; +#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) + if (tw->tw_family == AF_INET6) { + struct inet6_timewait_sock *tw6 = + inet6_twsk((struct sock *)tw); + entry.saddr = tw6->tw_v6_rcv_saddr.s6_addr32; + entry.daddr = tw6->tw_v6_daddr.s6_addr32; + } else +#endif + { + entry.saddr = &tw->tw_rcv_saddr; + entry.daddr = &tw->tw_daddr; + } + entry.sport = tw->tw_num; + entry.dport = ntohs(tw->tw_dport); + entry.userlocks = 0; + + if (!inet_diag_bc_run(RTA_DATA(bc), RTA_PAYLOAD(bc), &entry)) + return 0; + } + + return inet_twsk_diag_fill(tw, skb, r->idiag_ext, + NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh); } static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk, - struct request_sock *req, - u32 pid, u32 seq, - const struct nlmsghdr *unlh) + struct request_sock *req, u32 pid, u32 seq, + const struct nlmsghdr *unlh) { const struct inet_request_sock *ireq = inet_rsk(req); struct inet_sock *inet = inet_sk(sk); @@ -504,7 +582,7 @@ nlmsg_failure: } static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk, - struct netlink_callback *cb) + struct netlink_callback *cb) { struct inet_diag_entry entry; struct inet_diag_req *r = NLMSG_DATA(cb->nlh); @@ -556,7 +634,7 @@ static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk, inet6_rsk(req)->loc_addr.s6_addr32 : #endif &ireq->loc_addr; - entry.daddr = + entry.daddr = #if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) (entry.family == AF_INET6) ? inet6_rsk(req)->rmt_addr.s6_addr32 : @@ -599,7 +677,7 @@ static int inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) handler = inet_diag_table[cb->nlh->nlmsg_type]; BUG_ON(handler == NULL); hashinfo = handler->idiag_hashinfo; - + s_i = cb->args[1]; s_num = num = cb->args[2]; @@ -630,7 +708,7 @@ static int inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) cb->args[3] > 0) goto syn_recv; - if (inet_diag_dump_sock(skb, sk, cb) < 0) { + if (inet_csk_diag_dump(sk, skb, cb) < 0) { inet_listen_unlock(hashinfo); goto done; } @@ -672,7 +750,6 @@ skip_listen_ht: s_num = 0; read_lock_bh(&head->lock); - num = 0; sk_for_each(sk, node, &head->chain) { struct inet_sock *inet = inet_sk(sk); @@ -684,9 +761,10 @@ skip_listen_ht: if (r->id.idiag_sport != inet->sport && r->id.idiag_sport) goto next_normal; - if (r->id.idiag_dport != inet->dport && r->id.idiag_dport) + if (r->id.idiag_dport != inet->dport && + r->id.idiag_dport) goto next_normal; - if (inet_diag_dump_sock(skb, sk, cb) < 0) { + if (inet_csk_diag_dump(sk, skb, cb) < 0) { read_unlock_bh(&head->lock); goto done; } @@ -695,19 +773,20 @@ next_normal: } if (r->idiag_states & TCPF_TIME_WAIT) { - sk_for_each(sk, node, + struct inet_timewait_sock *tw; + + inet_twsk_for_each(tw, node, &hashinfo->ehash[i + hashinfo->ehash_size].chain) { - struct inet_sock *inet = inet_sk(sk); if (num < s_num) goto next_dying; - if (r->id.idiag_sport != inet->sport && + if (r->id.idiag_sport != tw->tw_sport && r->id.idiag_sport) goto next_dying; - if (r->id.idiag_dport != inet->dport && + if (r->id.idiag_dport != tw->tw_dport && r->id.idiag_dport) goto next_dying; - if (inet_diag_dump_sock(skb, sk, cb) < 0) { + if (inet_twsk_diag_dump(tw, skb, cb) < 0) { read_unlock_bh(&head->lock); goto done; } @@ -724,8 +803,7 @@ done: return skb->len; } -static __inline__ int -inet_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) +static inline int inet_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) { if (!(nlh->nlmsg_flags&NLM_F_REQUEST)) return 0; @@ -755,9 +833,8 @@ inet_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) } return netlink_dump_start(idiagnl, skb, nlh, inet_diag_dump, NULL); - } else { + } else return inet_diag_get_exact(skb, nlh); - } err_inval: return -EINVAL; @@ -766,15 +843,15 @@ err_inval: static inline void inet_diag_rcv_skb(struct sk_buff *skb) { - int err; - struct nlmsghdr * nlh; - if (skb->len >= NLMSG_SPACE(0)) { - nlh = (struct nlmsghdr *)skb->data; - if (nlh->nlmsg_len < sizeof(*nlh) || skb->len < nlh->nlmsg_len) + int err; + struct nlmsghdr *nlh = (struct nlmsghdr *)skb->data; + + if (nlh->nlmsg_len < sizeof(*nlh) || + skb->len < nlh->nlmsg_len) return; err = inet_diag_rcv_msg(skb, nlh); - if (err || nlh->nlmsg_flags & NLM_F_ACK) + if (err || nlh->nlmsg_flags & NLM_F_ACK) netlink_ack(skb, nlh, err); } } diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index ce5fe3f74a3d..2160874ce7aa 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -304,8 +304,7 @@ static void unlink_from_pool(struct inet_peer *p) /* look for a node to insert instead of p */ struct inet_peer *t; t = lookup_rightempty(p); - if (*stackptr[-1] != t) - BUG(); + BUG_ON(*stackptr[-1] != t); **--stackptr = t->avl_left; /* t is removed, t->v4daddr > x->v4daddr for any * x in p->avl_left subtree. @@ -314,8 +313,7 @@ static void unlink_from_pool(struct inet_peer *p) t->avl_left = p->avl_left; t->avl_right = p->avl_right; t->avl_height = p->avl_height; - if (delp[1] != &p->avl_left) - BUG(); + BUG_ON(delp[1] != &p->avl_left); delp[1] = &t->avl_left; /* was &p->avl_left */ } peer_avl_rebalance(stack, stackptr); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 912c42f57c79..abe23923e4e7 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -10,6 +10,7 @@ * */ +#include <linux/capability.h> #include <linux/config.h> #include <linux/module.h> #include <linux/types.h> @@ -188,7 +189,7 @@ static struct ip_tunnel * ipgre_tunnel_lookup(u32 remote, u32 local, u32 key) } if (ipgre_fb_tunnel_dev->flags&IFF_UP) - return ipgre_fb_tunnel_dev->priv; + return netdev_priv(ipgre_fb_tunnel_dev); return NULL; } @@ -278,7 +279,7 @@ static struct ip_tunnel * ipgre_tunnel_locate(struct ip_tunnel_parm *parms, int return NULL; dev->init = ipgre_tunnel_init; - nt = dev->priv; + nt = netdev_priv(dev); nt->parms = *parms; if (register_netdevice(dev) < 0) { @@ -286,9 +287,6 @@ static struct ip_tunnel * ipgre_tunnel_locate(struct ip_tunnel_parm *parms, int goto failed; } - nt = dev->priv; - nt->parms = *parms; - dev_hold(dev); ipgre_tunnel_link(nt); return nt; @@ -299,7 +297,7 @@ failed: static void ipgre_tunnel_uninit(struct net_device *dev) { - ipgre_tunnel_unlink((struct ip_tunnel*)dev->priv); + ipgre_tunnel_unlink(netdev_priv(dev)); dev_put(dev); } @@ -518,7 +516,7 @@ out: skb2->dst->ops->update_pmtu(skb2->dst, rel_info); rel_info = htonl(rel_info); } else if (type == ICMP_TIME_EXCEEDED) { - struct ip_tunnel *t = (struct ip_tunnel*)skb2->dev->priv; + struct ip_tunnel *t = netdev_priv(skb2->dev); if (t->parms.iph.ttl) { rel_type = ICMP_DEST_UNREACH; rel_code = ICMP_HOST_UNREACH; @@ -669,7 +667,7 @@ drop_nolock: static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { - struct ip_tunnel *tunnel = (struct ip_tunnel*)dev->priv; + struct ip_tunnel *tunnel = netdev_priv(dev); struct net_device_stats *stats = &tunnel->stat; struct iphdr *old_iph = skb->nh.iph; struct iphdr *tiph; @@ -832,6 +830,7 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) skb->h.raw = skb->nh.raw; skb->nh.raw = skb_push(skb, gre_hlen); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE|IPSKB_XFRM_TRANSFORMED); dst_release(skb->dst); skb->dst = &rt->u.dst; @@ -914,7 +913,7 @@ ipgre_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) t = ipgre_tunnel_locate(&p, 0); } if (t == NULL) - t = (struct ip_tunnel*)dev->priv; + t = netdev_priv(dev); memcpy(&p, &t->parms, sizeof(p)); if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) err = -EFAULT; @@ -954,7 +953,7 @@ ipgre_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) } else { unsigned nflags=0; - t = (struct ip_tunnel*)dev->priv; + t = netdev_priv(dev); if (MULTICAST(p.iph.daddr)) nflags = IFF_BROADCAST; @@ -1003,7 +1002,7 @@ ipgre_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) if ((t = ipgre_tunnel_locate(&p, 0)) == NULL) goto done; err = -EPERM; - if (t == ipgre_fb_tunnel_dev->priv) + if (t == netdev_priv(ipgre_fb_tunnel_dev)) goto done; dev = t->dev; } @@ -1020,12 +1019,12 @@ done: static struct net_device_stats *ipgre_tunnel_get_stats(struct net_device *dev) { - return &(((struct ip_tunnel*)dev->priv)->stat); + return &(((struct ip_tunnel*)netdev_priv(dev))->stat); } static int ipgre_tunnel_change_mtu(struct net_device *dev, int new_mtu) { - struct ip_tunnel *tunnel = (struct ip_tunnel*)dev->priv; + struct ip_tunnel *tunnel = netdev_priv(dev); if (new_mtu < 68 || new_mtu > 0xFFF8 - tunnel->hlen) return -EINVAL; dev->mtu = new_mtu; @@ -1065,7 +1064,7 @@ static int ipgre_tunnel_change_mtu(struct net_device *dev, int new_mtu) static int ipgre_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, void *daddr, void *saddr, unsigned len) { - struct ip_tunnel *t = (struct ip_tunnel*)dev->priv; + struct ip_tunnel *t = netdev_priv(dev); struct iphdr *iph = (struct iphdr *)skb_push(skb, t->hlen); u16 *p = (u16*)(iph+1); @@ -1092,7 +1091,7 @@ static int ipgre_header(struct sk_buff *skb, struct net_device *dev, unsigned sh static int ipgre_open(struct net_device *dev) { - struct ip_tunnel *t = (struct ip_tunnel*)dev->priv; + struct ip_tunnel *t = netdev_priv(dev); if (MULTICAST(t->parms.iph.daddr)) { struct flowi fl = { .oif = t->parms.link, @@ -1116,7 +1115,7 @@ static int ipgre_open(struct net_device *dev) static int ipgre_close(struct net_device *dev) { - struct ip_tunnel *t = (struct ip_tunnel*)dev->priv; + struct ip_tunnel *t = netdev_priv(dev); if (MULTICAST(t->parms.iph.daddr) && t->mlink) { struct in_device *in_dev = inetdev_by_index(t->mlink); if (in_dev) { @@ -1156,7 +1155,7 @@ static int ipgre_tunnel_init(struct net_device *dev) int mtu = ETH_DATA_LEN; int addend = sizeof(struct iphdr) + 4; - tunnel = (struct ip_tunnel*)dev->priv; + tunnel = netdev_priv(dev); iph = &tunnel->parms.iph; tunnel->dev = dev; @@ -1220,7 +1219,7 @@ static int ipgre_tunnel_init(struct net_device *dev) static int __init ipgre_fb_tunnel_init(struct net_device *dev) { - struct ip_tunnel *tunnel = (struct ip_tunnel*)dev->priv; + struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; tunnel->dev = dev; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index e45846ae570b..18d7fad474d7 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -185,7 +185,6 @@ int ip_call_ra_chain(struct sk_buff *skb) raw_rcv(last, skb2); } last = sk; - nf_reset(skb); } } @@ -204,10 +203,6 @@ static inline int ip_local_deliver_finish(struct sk_buff *skb) __skb_pull(skb, ihl); - /* Free reference early: we don't need it any more, and it may - hold ip_conntrack module loaded indefinitely. */ - nf_reset(skb); - /* Point into the IP datagram, just past the header. */ skb->h.raw = skb->data; @@ -232,10 +227,12 @@ static inline int ip_local_deliver_finish(struct sk_buff *skb) if ((ipprot = rcu_dereference(inet_protos[hash])) != NULL) { int ret; - if (!ipprot->no_policy && - !xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) { - kfree_skb(skb); - goto out; + if (!ipprot->no_policy) { + if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) { + kfree_skb(skb); + goto out; + } + nf_reset(skb); } ret = ipprot->handler(skb); if (ret < 0) { diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index d3f6c468faf4..9bebad07bf2e 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -11,6 +11,7 @@ * */ +#include <linux/capability.h> #include <linux/module.h> #include <linux/types.h> #include <asm/uaccess.h> diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 8b1c9bd0091e..3324fbfe528a 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -69,6 +69,7 @@ #include <net/ip.h> #include <net/protocol.h> #include <net/route.h> +#include <net/xfrm.h> #include <linux/skbuff.h> #include <net/sock.h> #include <net/arp.h> @@ -85,6 +86,8 @@ int sysctl_ip_default_ttl = IPDEFTTL; +static int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff*)); + /* Generate a checksum for an outgoing IP datagram. */ __inline__ void ip_send_check(struct iphdr *iph) { @@ -202,6 +205,11 @@ static inline int ip_finish_output2(struct sk_buff *skb) static inline int ip_finish_output(struct sk_buff *skb) { +#if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM) + /* Policy lookup after SNAT yielded a new policy */ + if (skb->dst->xfrm != NULL) + return xfrm4_output_finish(skb); +#endif if (skb->len > dst_mtu(skb->dst) && !(skb_shinfo(skb)->ufo_size || skb_shinfo(skb)->tso_size)) return ip_fragment(skb, ip_finish_output2); @@ -409,7 +417,7 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) * single device frame, and queue such a frame for sending. */ -int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff*)) +static int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff*)) { struct iphdr *iph; int raw = 0; @@ -1391,7 +1399,6 @@ void __init ip_init(void) #endif } -EXPORT_SYMBOL(ip_fragment); EXPORT_SYMBOL(ip_generic_getfrag); EXPORT_SYMBOL(ip_queue_xmit); EXPORT_SYMBOL(ip_send_check); diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 6986e11d65cc..2bf8d782f678 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -621,7 +621,7 @@ 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; @@ -778,7 +778,7 @@ 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; @@ -798,7 +798,7 @@ 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; diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 35571cff81c6..e5cbe72c6b80 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -93,6 +93,7 @@ */ +#include <linux/capability.h> #include <linux/config.h> #include <linux/module.h> #include <linux/types.h> @@ -244,7 +245,7 @@ static struct ip_tunnel * ipip_tunnel_locate(struct ip_tunnel_parm *parms, int c if (dev == NULL) return NULL; - nt = dev->priv; + nt = netdev_priv(dev); SET_MODULE_OWNER(dev); dev->init = ipip_tunnel_init; nt->parms = *parms; @@ -269,7 +270,7 @@ static void ipip_tunnel_uninit(struct net_device *dev) tunnels_wc[0] = NULL; write_unlock_bh(&ipip_lock); } else - ipip_tunnel_unlink((struct ip_tunnel*)dev->priv); + ipip_tunnel_unlink(netdev_priv(dev)); dev_put(dev); } @@ -443,7 +444,7 @@ out: skb2->dst->ops->update_pmtu(skb2->dst, rel_info); rel_info = htonl(rel_info); } else if (type == ICMP_TIME_EXCEEDED) { - struct ip_tunnel *t = (struct ip_tunnel*)skb2->dev->priv; + struct ip_tunnel *t = netdev_priv(skb2->dev); if (t->parms.iph.ttl) { rel_type = ICMP_DEST_UNREACH; rel_code = ICMP_HOST_UNREACH; @@ -514,7 +515,7 @@ out: static int ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { - struct ip_tunnel *tunnel = (struct ip_tunnel*)dev->priv; + struct ip_tunnel *tunnel = netdev_priv(dev); struct net_device_stats *stats = &tunnel->stat; struct iphdr *tiph = &tunnel->parms.iph; u8 tos = tunnel->parms.iph.tos; @@ -621,6 +622,7 @@ static int ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) skb->h.raw = skb->nh.raw; skb->nh.raw = skb_push(skb, sizeof(struct iphdr)); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE|IPSKB_XFRM_TRANSFORMED); dst_release(skb->dst); skb->dst = &rt->u.dst; @@ -673,7 +675,7 @@ ipip_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) t = ipip_tunnel_locate(&p, 0); } if (t == NULL) - t = (struct ip_tunnel*)dev->priv; + t = netdev_priv(dev); memcpy(&p, &t->parms, sizeof(p)); if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) err = -EFAULT; @@ -710,7 +712,7 @@ ipip_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) err = -EINVAL; break; } - t = (struct ip_tunnel*)dev->priv; + t = netdev_priv(dev); ipip_tunnel_unlink(t); t->parms.iph.saddr = p.iph.saddr; t->parms.iph.daddr = p.iph.daddr; @@ -764,7 +766,7 @@ done: static struct net_device_stats *ipip_tunnel_get_stats(struct net_device *dev) { - return &(((struct ip_tunnel*)dev->priv)->stat); + return &(((struct ip_tunnel*)netdev_priv(dev))->stat); } static int ipip_tunnel_change_mtu(struct net_device *dev, int new_mtu) @@ -799,7 +801,7 @@ static int ipip_tunnel_init(struct net_device *dev) struct ip_tunnel *tunnel; struct iphdr *iph; - tunnel = (struct ip_tunnel*)dev->priv; + tunnel = netdev_priv(dev); iph = &tunnel->parms.iph; tunnel->dev = dev; @@ -837,7 +839,7 @@ static int ipip_tunnel_init(struct net_device *dev) static int __init ipip_fb_tunnel_init(struct net_device *dev) { - struct ip_tunnel *tunnel = dev->priv; + struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; tunnel->dev = dev; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 9a5c0ce7ff35..5c94c222e3f3 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -33,6 +33,7 @@ #include <asm/uaccess.h> #include <linux/types.h> #include <linux/sched.h> +#include <linux/capability.h> #include <linux/errno.h> #include <linux/timer.h> #include <linux/mm.h> @@ -178,8 +179,8 @@ static int reg_vif_num = -1; static int reg_vif_xmit(struct sk_buff *skb, struct net_device *dev) { read_lock(&mrt_lock); - ((struct net_device_stats*)dev->priv)->tx_bytes += skb->len; - ((struct net_device_stats*)dev->priv)->tx_packets++; + ((struct net_device_stats*)netdev_priv(dev))->tx_bytes += skb->len; + ((struct net_device_stats*)netdev_priv(dev))->tx_packets++; ipmr_cache_report(skb, reg_vif_num, IGMPMSG_WHOLEPKT); read_unlock(&mrt_lock); kfree_skb(skb); @@ -188,7 +189,7 @@ static int reg_vif_xmit(struct sk_buff *skb, struct net_device *dev) static struct net_device_stats *reg_vif_get_stats(struct net_device *dev) { - return (struct net_device_stats*)dev->priv; + return (struct net_device_stats*)netdev_priv(dev); } static void reg_vif_setup(struct net_device *dev) @@ -1149,8 +1150,8 @@ static void ipmr_queue_xmit(struct sk_buff *skb, struct mfc_cache *c, int vifi) if (vif->flags & VIFF_REGISTER) { vif->pkt_out++; vif->bytes_out+=skb->len; - ((struct net_device_stats*)vif->dev->priv)->tx_bytes += skb->len; - ((struct net_device_stats*)vif->dev->priv)->tx_packets++; + ((struct net_device_stats*)netdev_priv(vif->dev))->tx_bytes += skb->len; + ((struct net_device_stats*)netdev_priv(vif->dev))->tx_packets++; ipmr_cache_report(skb, vifi, IGMPMSG_WHOLEPKT); kfree_skb(skb); return; @@ -1210,8 +1211,8 @@ static void ipmr_queue_xmit(struct sk_buff *skb, struct mfc_cache *c, int vifi) if (vif->flags & VIFF_TUNNEL) { ip_encap(skb, vif->local, vif->remote); /* FIXME: extra output firewall step used to be here. --RR */ - ((struct ip_tunnel *)vif->dev->priv)->stat.tx_packets++; - ((struct ip_tunnel *)vif->dev->priv)->stat.tx_bytes+=skb->len; + ((struct ip_tunnel *)netdev_priv(vif->dev))->stat.tx_packets++; + ((struct ip_tunnel *)netdev_priv(vif->dev))->stat.tx_bytes+=skb->len; } IPCB(skb)->flags |= IPSKB_FORWARDED; @@ -1467,8 +1468,8 @@ int pim_rcv_v1(struct sk_buff * skb) skb->pkt_type = PACKET_HOST; dst_release(skb->dst); skb->dst = NULL; - ((struct net_device_stats*)reg_dev->priv)->rx_bytes += skb->len; - ((struct net_device_stats*)reg_dev->priv)->rx_packets++; + ((struct net_device_stats*)netdev_priv(reg_dev))->rx_bytes += skb->len; + ((struct net_device_stats*)netdev_priv(reg_dev))->rx_packets++; nf_reset(skb); netif_rx(skb); dev_put(reg_dev); @@ -1522,8 +1523,8 @@ static int pim_rcv(struct sk_buff * skb) skb->ip_summed = 0; skb->pkt_type = PACKET_HOST; dst_release(skb->dst); - ((struct net_device_stats*)reg_dev->priv)->rx_bytes += skb->len; - ((struct net_device_stats*)reg_dev->priv)->rx_packets++; + ((struct net_device_stats*)netdev_priv(reg_dev))->rx_bytes += skb->len; + ((struct net_device_stats*)netdev_priv(reg_dev))->rx_packets++; skb->dst = NULL; nf_reset(skb); netif_rx(skb); diff --git a/net/ipv4/ipvs/ip_vs_ctl.c b/net/ipv4/ipvs/ip_vs_ctl.c index c935c5086d33..7f0288b25fa1 100644 --- a/net/ipv4/ipvs/ip_vs_ctl.c +++ b/net/ipv4/ipvs/ip_vs_ctl.c @@ -23,6 +23,7 @@ #include <linux/module.h> #include <linux/init.h> #include <linux/types.h> +#include <linux/capability.h> #include <linux/fs.h> #include <linux/sysctl.h> #include <linux/proc_fs.h> diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index ae0779d82c5d..52a3d7c57907 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -1,17 +1,11 @@ /* IPv4 specific functions of netfilter core */ - -#include <linux/config.h> -#ifdef CONFIG_NETFILTER - #include <linux/kernel.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv4.h> - -#include <linux/tcp.h> -#include <linux/udp.h> -#include <linux/icmp.h> -#include <net/route.h> #include <linux/ip.h> +#include <net/route.h> +#include <net/xfrm.h> +#include <net/ip.h> /* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */ int ip_route_me_harder(struct sk_buff **pskb) @@ -33,7 +27,6 @@ int ip_route_me_harder(struct sk_buff **pskb) #ifdef CONFIG_IP_ROUTE_FWMARK fl.nl_u.ip4_u.fwmark = (*pskb)->nfmark; #endif - fl.proto = iph->protocol; if (ip_route_output_key(&rt, &fl) != 0) return -1; @@ -60,6 +53,13 @@ int ip_route_me_harder(struct sk_buff **pskb) if ((*pskb)->dst->error) return -1; +#ifdef CONFIG_XFRM + if (!(IPCB(*pskb)->flags & IPSKB_XFRM_TRANSFORMED) && + xfrm_decode_session(*pskb, &fl, AF_INET) == 0) + if (xfrm_lookup(&(*pskb)->dst, &fl, (*pskb)->sk, 0)) + return -1; +#endif + /* Change in oif may mean change in hh_len. */ hh_len = (*pskb)->dst->dev->hard_header_len; if (skb_headroom(*pskb) < hh_len) { @@ -78,6 +78,9 @@ int ip_route_me_harder(struct sk_buff **pskb) } EXPORT_SYMBOL(ip_route_me_harder); +void (*ip_nat_decode_session)(struct sk_buff *, struct flowi *); +EXPORT_SYMBOL(ip_nat_decode_session); + /* * Extra routing may needed on local out, as the QUEUE target never * returns control to the table. @@ -135,5 +138,3 @@ static void fini(void) module_init(init); module_exit(fini); - -#endif /* CONFIG_NETFILTER */ diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 88a60650e6b8..db783036e4d8 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -182,6 +182,7 @@ config IP_NF_QUEUE config IP_NF_IPTABLES tristate "IP tables support (required for filtering/masq/NAT)" + depends on NETFILTER_XTABLES help iptables is a general, extensible packet identification framework. The packet filtering and full NAT (masquerading, port forwarding, @@ -191,16 +192,6 @@ config IP_NF_IPTABLES To compile it as a module, choose M here. If unsure, say N. # The matches. -config IP_NF_MATCH_LIMIT - tristate "limit match support" - depends on IP_NF_IPTABLES - help - limit matching allows you to control the rate at which a rule can be - matched: mainly useful in combination with the LOG target ("LOG - target support", below) and to avoid some Denial of Service attacks. - - To compile it as a module, choose M here. If unsure, say N. - config IP_NF_MATCH_IPRANGE tristate "IP range match support" depends on IP_NF_IPTABLES @@ -210,37 +201,6 @@ config IP_NF_MATCH_IPRANGE To compile it as a module, choose M here. If unsure, say N. -config IP_NF_MATCH_MAC - tristate "MAC address match support" - depends on IP_NF_IPTABLES - help - MAC matching allows you to match packets based on the source - Ethernet address of the packet. - - To compile it as a module, choose M here. If unsure, say N. - -config IP_NF_MATCH_PKTTYPE - tristate "Packet type match support" - depends on IP_NF_IPTABLES - help - Packet type matching allows you to match a packet by - its "class", eg. BROADCAST, MULTICAST, ... - - Typical usage: - iptables -A INPUT -m pkttype --pkt-type broadcast -j LOG - - To compile it as a module, choose M here. If unsure, say N. - -config IP_NF_MATCH_MARK - tristate "netfilter MARK match support" - depends on IP_NF_IPTABLES - help - Netfilter mark matching allows you to match packets based on the - `nfmark' value in the packet. This can be set by the MARK target - (see below). - - To compile it as a module, choose M here. If unsure, say N. - config IP_NF_MATCH_MULTIPORT tristate "Multiple port match support" depends on IP_NF_IPTABLES @@ -301,15 +261,6 @@ config IP_NF_MATCH_AH_ESP To compile it as a module, choose M here. If unsure, say N. -config IP_NF_MATCH_LENGTH - tristate "LENGTH match support" - depends on IP_NF_IPTABLES - help - This option allows you to match the length of a packet against a - specific value or range of values. - - To compile it as a module, choose M here. If unsure, say N. - config IP_NF_MATCH_TTL tristate "TTL match support" depends on IP_NF_IPTABLES @@ -319,50 +270,6 @@ config IP_NF_MATCH_TTL To compile it as a module, choose M here. If unsure, say N. -config IP_NF_MATCH_TCPMSS - tristate "tcpmss match support" - depends on IP_NF_IPTABLES - help - This option adds a `tcpmss' match, which allows you to examine the - MSS value of TCP SYN packets, which control the maximum packet size - for that connection. - - To compile it as a module, choose M here. If unsure, say N. - -config IP_NF_MATCH_HELPER - tristate "Helper match support" - depends on IP_NF_IPTABLES - depends on IP_NF_CONNTRACK || NF_CONNTRACK_IPV4 - help - Helper matching allows you to match packets in dynamic connections - tracked by a conntrack-helper, ie. ip_conntrack_ftp - - To compile it as a module, choose M here. If unsure, say Y. - -config IP_NF_MATCH_STATE - tristate "Connection state match support" - depends on IP_NF_IPTABLES - depends on IP_NF_CONNTRACK || NF_CONNTRACK_IPV4 - help - Connection state matching allows you to match packets based on their - relationship to a tracked connection (ie. previous packets). This - is a powerful tool for packet classification. - - To compile it as a module, choose M here. If unsure, say N. - -config IP_NF_MATCH_CONNTRACK - tristate "Connection tracking match support" - depends on IP_NF_IPTABLES - depends on IP_NF_CONNTRACK || NF_CONNTRACK_IPV4 - help - This is a general conntrack match module, a superset of the state match. - - It allows matching on additional conntrack information, which is - useful in complex configurations, such as NAT gateways with multiple - internet links or tunnels. - - To compile it as a module, choose M here. If unsure, say N. - config IP_NF_MATCH_OWNER tristate "Owner match support" depends on IP_NF_IPTABLES @@ -372,15 +279,6 @@ config IP_NF_MATCH_OWNER To compile it as a module, choose M here. If unsure, say N. -config IP_NF_MATCH_PHYSDEV - tristate "Physdev match support" - depends on IP_NF_IPTABLES && BRIDGE_NETFILTER - help - Physdev packet matching matches against the physical bridge ports - the IP packet arrived on or will leave by. - - To compile it as a module, choose M here. If unsure, say N. - config IP_NF_MATCH_ADDRTYPE tristate 'address type match support' depends on IP_NF_IPTABLES @@ -391,75 +289,6 @@ config IP_NF_MATCH_ADDRTYPE If you want to compile it as a module, say M here and read <file:Documentation/modules.txt>. If unsure, say `N'. -config IP_NF_MATCH_REALM - tristate 'realm match support' - depends on IP_NF_IPTABLES - select NET_CLS_ROUTE - help - This option adds a `realm' match, which allows you to use the realm - key from the routing subsystem inside iptables. - - This match pretty much resembles the CONFIG_NET_CLS_ROUTE4 option - in tc world. - - If you want to compile it as a module, say M here and read - <file:Documentation/modules.txt>. If unsure, say `N'. - -config IP_NF_MATCH_SCTP - tristate 'SCTP protocol match support' - depends on IP_NF_IPTABLES - help - With this option enabled, you will be able to use the iptables - `sctp' match in order to match on SCTP source/destination ports - and SCTP chunk types. - - If you want to compile it as a module, say M here and read - <file:Documentation/modules.txt>. If unsure, say `N'. - -config IP_NF_MATCH_DCCP - tristate 'DCCP protocol match support' - depends on IP_NF_IPTABLES - help - With this option enabled, you will be able to use the iptables - `dccp' match in order to match on DCCP source/destination ports - and DCCP flags. - - If you want to compile it as a module, say M here and read - <file:Documentation/modules.txt>. If unsure, say `N'. - -config IP_NF_MATCH_COMMENT - tristate 'comment match support' - depends on IP_NF_IPTABLES - help - This option adds a `comment' dummy-match, which allows you to put - comments in your iptables ruleset. - - If you want to compile it as a module, say M here and read - <file:Documentation/modules.txt>. If unsure, say `N'. - -config IP_NF_MATCH_CONNMARK - tristate 'Connection mark match support' - depends on IP_NF_IPTABLES - depends on (IP_NF_CONNTRACK && IP_NF_CONNTRACK_MARK) || (NF_CONNTRACK_MARK && NF_CONNTRACK_IPV4) - help - This option adds a `connmark' match, which allows you to match the - connection mark value previously set for the session by `CONNMARK'. - - If you want to compile it as a module, say M here and read - <file:Documentation/modules.txt>. The module will be called - ipt_connmark.o. If unsure, say `N'. - -config IP_NF_MATCH_CONNBYTES - tristate 'Connection byte/packet counter match support' - depends on IP_NF_IPTABLES - depends on (IP_NF_CONNTRACK && IP_NF_CT_ACCT) || (NF_CT_ACCT && NF_CONNTRACK_IPV4) - help - This option adds a `connbytes' match, which allows you to match the - number of bytes and/or packets for each direction within a connection. - - If you want to compile it as a module, say M here and read - <file:Documentation/modules.txt>. If unsure, say `N'. - config IP_NF_MATCH_HASHLIMIT tristate 'hashlimit match support' depends on IP_NF_IPTABLES @@ -474,18 +303,15 @@ config IP_NF_MATCH_HASHLIMIT destination IP' or `500pps from any given source IP' with a single IPtables rule. -config IP_NF_MATCH_STRING - tristate 'string match support' - depends on IP_NF_IPTABLES - select TEXTSEARCH - select TEXTSEARCH_KMP - select TEXTSEARCH_BM - select TEXTSEARCH_FSM - help - This option adds a `string' match, which allows you to look for - pattern matchings in packets. +config IP_NF_MATCH_POLICY + tristate "IPsec policy match support" + depends on IP_NF_IPTABLES && XFRM + help + Policy matching allows you to match packets based on the + IPsec policy that was used during decapsulation/will + be used during encapsulation. - To compile it as a module, choose M here. If unsure, say N. + To compile it as a module, choose M here. If unsure, say N. # `filter', generic and specific targets config IP_NF_FILTER @@ -562,17 +388,6 @@ config IP_NF_TARGET_TCPMSS To compile it as a module, choose M here. If unsure, say N. -config IP_NF_TARGET_NFQUEUE - tristate "NFQUEUE Target Support" - depends on IP_NF_IPTABLES - help - This Target replaced the old obsolete QUEUE target. - - As opposed to QUEUE, it supports 65535 different queues, - not just one. - - To compile it as a module, choose M here. If unsure, say N. - # NAT + specific targets config IP_NF_NAT tristate "Full NAT" @@ -725,31 +540,6 @@ config IP_NF_TARGET_DSCP To compile it as a module, choose M here. If unsure, say N. -config IP_NF_TARGET_MARK - tristate "MARK target support" - depends on IP_NF_MANGLE - help - This option adds a `MARK' target, which allows you to create rules - in the `mangle' table which alter the netfilter mark (nfmark) field - associated with the packet prior to routing. This can change - the routing method (see `Use netfilter MARK value as routing - key') and can also be used by other subsystems to change their - behavior. - - To compile it as a module, choose M here. If unsure, say N. - -config IP_NF_TARGET_CLASSIFY - tristate "CLASSIFY target support" - depends on IP_NF_MANGLE - help - This option adds a `CLASSIFY' target, which enables the user to set - the priority of a packet. Some qdiscs can use this value for - classification, among these are: - - atm, cbq, dsmark, pfifo_fast, htb, prio - - To compile it as a module, choose M here. If unsure, say N. - config IP_NF_TARGET_TTL tristate 'TTL target support' depends on IP_NF_MANGLE @@ -764,19 +554,6 @@ config IP_NF_TARGET_TTL To compile it as a module, choose M here. If unsure, say N. -config IP_NF_TARGET_CONNMARK - tristate 'CONNMARK target support' - depends on IP_NF_MANGLE - depends on (IP_NF_CONNTRACK && IP_NF_CONNTRACK_MARK) || (NF_CONNTRACK_MARK && NF_CONNTRACK_IPV4) - help - This option adds a `CONNMARK' target, which allows one to manipulate - the connection mark value. Similar to the MARK target, but - affects the connection mark value rather than the packet mark value. - - If you want to compile it as a module, say M here and read - <file:Documentation/modules.txt>. The module will be called - ipt_CONNMARK.o. If unsure, say `N'. - config IP_NF_TARGET_CLUSTERIP tristate "CLUSTERIP target support (EXPERIMENTAL)" depends on IP_NF_MANGLE && EXPERIMENTAL @@ -800,23 +577,10 @@ config IP_NF_RAW If you want to compile it as a module, say M here and read <file:Documentation/modules.txt>. If unsure, say `N'. -config IP_NF_TARGET_NOTRACK - tristate 'NOTRACK target support' - depends on IP_NF_RAW - depends on IP_NF_CONNTRACK || NF_CONNTRACK_IPV4 - help - The NOTRACK target allows a select rule to specify - which packets *not* to enter the conntrack/NAT - subsystem with all the consequences (no ICMP error tracking, - no protocol helpers for the selected packets). - - If you want to compile it as a module, say M here and read - <file:Documentation/modules.txt>. If unsure, say `N'. - - # ARP tables config IP_NF_ARPTABLES tristate "ARP tables support" + depends on NETFILTER_XTABLES help arptables is a general, extensible packet identification framework. The ARP packet filtering and mangling (manipulation)subsystems diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index d0a447e520a2..e5c5b3202f02 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -46,15 +46,8 @@ obj-$(CONFIG_IP_NF_NAT) += iptable_nat.o obj-$(CONFIG_IP_NF_RAW) += iptable_raw.o # matches -obj-$(CONFIG_IP_NF_MATCH_HELPER) += ipt_helper.o -obj-$(CONFIG_IP_NF_MATCH_LIMIT) += ipt_limit.o obj-$(CONFIG_IP_NF_MATCH_HASHLIMIT) += ipt_hashlimit.o -obj-$(CONFIG_IP_NF_MATCH_SCTP) += ipt_sctp.o -obj-$(CONFIG_IP_NF_MATCH_DCCP) += ipt_dccp.o -obj-$(CONFIG_IP_NF_MATCH_MARK) += ipt_mark.o -obj-$(CONFIG_IP_NF_MATCH_MAC) += ipt_mac.o obj-$(CONFIG_IP_NF_MATCH_IPRANGE) += ipt_iprange.o -obj-$(CONFIG_IP_NF_MATCH_PKTTYPE) += ipt_pkttype.o obj-$(CONFIG_IP_NF_MATCH_MULTIPORT) += ipt_multiport.o obj-$(CONFIG_IP_NF_MATCH_OWNER) += ipt_owner.o obj-$(CONFIG_IP_NF_MATCH_TOS) += ipt_tos.o @@ -62,39 +55,25 @@ obj-$(CONFIG_IP_NF_MATCH_RECENT) += ipt_recent.o obj-$(CONFIG_IP_NF_MATCH_ECN) += ipt_ecn.o obj-$(CONFIG_IP_NF_MATCH_DSCP) += ipt_dscp.o obj-$(CONFIG_IP_NF_MATCH_AH_ESP) += ipt_ah.o ipt_esp.o -obj-$(CONFIG_IP_NF_MATCH_LENGTH) += ipt_length.o obj-$(CONFIG_IP_NF_MATCH_TTL) += ipt_ttl.o -obj-$(CONFIG_IP_NF_MATCH_STATE) += ipt_state.o -obj-$(CONFIG_IP_NF_MATCH_CONNMARK) += ipt_connmark.o -obj-$(CONFIG_IP_NF_MATCH_CONNTRACK) += ipt_conntrack.o -obj-$(CONFIG_IP_NF_MATCH_CONNBYTES) += ipt_connbytes.o -obj-$(CONFIG_IP_NF_MATCH_TCPMSS) += ipt_tcpmss.o -obj-$(CONFIG_IP_NF_MATCH_REALM) += ipt_realm.o obj-$(CONFIG_IP_NF_MATCH_ADDRTYPE) += ipt_addrtype.o -obj-$(CONFIG_IP_NF_MATCH_PHYSDEV) += ipt_physdev.o -obj-$(CONFIG_IP_NF_MATCH_COMMENT) += ipt_comment.o -obj-$(CONFIG_IP_NF_MATCH_STRING) += ipt_string.o +obj-$(CONFIG_IP_NF_MATCH_POLICY) += ipt_policy.o # targets obj-$(CONFIG_IP_NF_TARGET_REJECT) += ipt_REJECT.o obj-$(CONFIG_IP_NF_TARGET_TOS) += ipt_TOS.o obj-$(CONFIG_IP_NF_TARGET_ECN) += ipt_ECN.o obj-$(CONFIG_IP_NF_TARGET_DSCP) += ipt_DSCP.o -obj-$(CONFIG_IP_NF_TARGET_MARK) += ipt_MARK.o obj-$(CONFIG_IP_NF_TARGET_MASQUERADE) += ipt_MASQUERADE.o obj-$(CONFIG_IP_NF_TARGET_REDIRECT) += ipt_REDIRECT.o obj-$(CONFIG_IP_NF_TARGET_NETMAP) += ipt_NETMAP.o obj-$(CONFIG_IP_NF_TARGET_SAME) += ipt_SAME.o -obj-$(CONFIG_IP_NF_TARGET_CLASSIFY) += ipt_CLASSIFY.o obj-$(CONFIG_IP_NF_NAT_SNMP_BASIC) += ip_nat_snmp_basic.o obj-$(CONFIG_IP_NF_TARGET_LOG) += ipt_LOG.o -obj-$(CONFIG_IP_NF_TARGET_CONNMARK) += ipt_CONNMARK.o obj-$(CONFIG_IP_NF_TARGET_ULOG) += ipt_ULOG.o obj-$(CONFIG_IP_NF_TARGET_TCPMSS) += ipt_TCPMSS.o -obj-$(CONFIG_IP_NF_TARGET_NOTRACK) += ipt_NOTRACK.o obj-$(CONFIG_IP_NF_TARGET_CLUSTERIP) += ipt_CLUSTERIP.o obj-$(CONFIG_IP_NF_TARGET_TTL) += ipt_TTL.o -obj-$(CONFIG_IP_NF_TARGET_NFQUEUE) += ipt_NFQUEUE.o # generic ARP tables obj-$(CONFIG_IP_NF_ARPTABLES) += arp_tables.o diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index bba156304695..afe3d8f8177d 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -13,6 +13,7 @@ #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/netdevice.h> +#include <linux/capability.h> #include <linux/if_arp.h> #include <linux/kmod.h> #include <linux/vmalloc.h> @@ -23,6 +24,7 @@ #include <asm/uaccess.h> #include <asm/semaphore.h> +#include <linux/netfilter/x_tables.h> #include <linux/netfilter_arp/arp_tables.h> MODULE_LICENSE("GPL"); @@ -54,28 +56,9 @@ do { \ #else #define ARP_NF_ASSERT(x) #endif -#define SMP_ALIGN(x) (((x) + SMP_CACHE_BYTES-1) & ~(SMP_CACHE_BYTES-1)) -static DECLARE_MUTEX(arpt_mutex); - -#define ASSERT_READ_LOCK(x) ARP_NF_ASSERT(down_trylock(&arpt_mutex) != 0) -#define ASSERT_WRITE_LOCK(x) ARP_NF_ASSERT(down_trylock(&arpt_mutex) != 0) #include <linux/netfilter_ipv4/listhelp.h> -struct arpt_table_info { - unsigned int size; - unsigned int number; - unsigned int initial_entries; - unsigned int hook_entry[NF_ARP_NUMHOOKS]; - unsigned int underflow[NF_ARP_NUMHOOKS]; - void *entries[NR_CPUS]; -}; - -static LIST_HEAD(arpt_target); -static LIST_HEAD(arpt_tables); -#define SET_COUNTER(c,b,p) do { (c).bcnt = (b); (c).pcnt = (p); } while(0) -#define ADD_COUNTER(c,b,p) do { (c).bcnt += (b); (c).pcnt += (p); } while(0) - static inline int arp_devaddr_compare(const struct arpt_devaddr_info *ap, char *hdr_addr, int len) { @@ -222,9 +205,9 @@ static inline int arp_checkentry(const struct arpt_arp *arp) } static unsigned int arpt_error(struct sk_buff **pskb, - unsigned int hooknum, const struct net_device *in, const struct net_device *out, + unsigned int hooknum, const void *targinfo, void *userinfo) { @@ -253,6 +236,7 @@ unsigned int arpt_do_table(struct sk_buff **pskb, struct arpt_entry *e, *back; const char *indev, *outdev; void *table_base; + struct xt_table_info *private = table->private; /* ARP header, plus 2 device addresses, plus 2 IP addresses. */ if (!pskb_may_pull((*pskb), (sizeof(struct arphdr) + @@ -264,9 +248,9 @@ unsigned int arpt_do_table(struct sk_buff **pskb, outdev = out ? out->name : nulldevname; read_lock_bh(&table->lock); - table_base = (void *)table->private->entries[smp_processor_id()]; - e = get_entry(table_base, table->private->hook_entry[hook]); - back = get_entry(table_base, table->private->underflow[hook]); + table_base = (void *)private->entries[smp_processor_id()]; + e = get_entry(table_base, private->hook_entry[hook]); + back = get_entry(table_base, private->underflow[hook]); arp = (*pskb)->nh.arph; do { @@ -314,8 +298,8 @@ unsigned int arpt_do_table(struct sk_buff **pskb, * abs. verdicts */ verdict = t->u.kernel.target->target(pskb, - hook, in, out, + hook, t->data, userdata); @@ -340,106 +324,6 @@ unsigned int arpt_do_table(struct sk_buff **pskb, return verdict; } -/* - * These are weird, but module loading must not be done with mutex - * held (since they will register), and we have to have a single - * function to use try_then_request_module(). - */ - -/* Find table by name, grabs mutex & ref. Returns ERR_PTR() on error. */ -static inline struct arpt_table *find_table_lock(const char *name) -{ - struct arpt_table *t; - - if (down_interruptible(&arpt_mutex) != 0) - return ERR_PTR(-EINTR); - - list_for_each_entry(t, &arpt_tables, list) - if (strcmp(t->name, name) == 0 && try_module_get(t->me)) - return t; - up(&arpt_mutex); - return NULL; -} - - -/* Find target, grabs ref. Returns ERR_PTR() on error. */ -static inline struct arpt_target *find_target(const char *name, u8 revision) -{ - struct arpt_target *t; - int err = 0; - - if (down_interruptible(&arpt_mutex) != 0) - return ERR_PTR(-EINTR); - - list_for_each_entry(t, &arpt_target, list) { - if (strcmp(t->name, name) == 0) { - if (t->revision == revision) { - if (try_module_get(t->me)) { - up(&arpt_mutex); - return t; - } - } else - err = -EPROTOTYPE; /* Found something. */ - } - } - up(&arpt_mutex); - return ERR_PTR(err); -} - -struct arpt_target *arpt_find_target(const char *name, u8 revision) -{ - struct arpt_target *target; - - target = try_then_request_module(find_target(name, revision), - "arpt_%s", name); - if (IS_ERR(target) || !target) - return NULL; - return target; -} - -static int target_revfn(const char *name, u8 revision, int *bestp) -{ - struct arpt_target *t; - int have_rev = 0; - - list_for_each_entry(t, &arpt_target, list) { - if (strcmp(t->name, name) == 0) { - if (t->revision > *bestp) - *bestp = t->revision; - if (t->revision == revision) - have_rev =1; - } - } - return have_rev; -} - -/* Returns true or false (if no such extension at all) */ -static inline int find_revision(const char *name, u8 revision, - int (*revfn)(const char *, u8, int *), - int *err) -{ - int have_rev, best = -1; - - if (down_interruptible(&arpt_mutex) != 0) { - *err = -EINTR; - return 1; - } - have_rev = revfn(name, revision, &best); - up(&arpt_mutex); - - /* Nothing at all? Return 0 to try loading module. */ - if (best == -1) { - *err = -ENOENT; - return 0; - } - - *err = best; - if (!have_rev) - *err = -EPROTONOSUPPORT; - return 1; -} - - /* All zeroes == unconditional rule. */ static inline int unconditional(const struct arpt_arp *arp) { @@ -455,7 +339,7 @@ static inline int unconditional(const struct arpt_arp *arp) /* Figures out from what hook each rule can be called: returns 0 if * there are loops. Puts hook bitmask in comefrom. */ -static int mark_source_chains(struct arpt_table_info *newinfo, +static int mark_source_chains(struct xt_table_info *newinfo, unsigned int valid_hooks, void *entry0) { unsigned int hook; @@ -586,8 +470,8 @@ static inline int check_entry(struct arpt_entry *e, const char *name, unsigned i } t = arpt_get_target(e); - target = try_then_request_module(find_target(t->u.user.name, - t->u.user.revision), + target = try_then_request_module(xt_find_target(NF_ARP, t->u.user.name, + t->u.user.revision), "arpt_%s", t->u.user.name); if (IS_ERR(target) || !target) { duprintf("check_entry: `%s' not found\n", t->u.user.name); @@ -621,7 +505,7 @@ out: } static inline int check_entry_size_and_hooks(struct arpt_entry *e, - struct arpt_table_info *newinfo, + struct xt_table_info *newinfo, unsigned char *base, unsigned char *limit, const unsigned int *hook_entries, @@ -655,7 +539,7 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e, < 0 (not ARPT_RETURN). --RR */ /* Clear counters and comefrom */ - e->counters = ((struct arpt_counters) { 0, 0 }); + e->counters = ((struct xt_counters) { 0, 0 }); e->comefrom = 0; (*i)++; @@ -682,7 +566,7 @@ static inline int cleanup_entry(struct arpt_entry *e, unsigned int *i) */ static int translate_table(const char *name, unsigned int valid_hooks, - struct arpt_table_info *newinfo, + struct xt_table_info *newinfo, void *entry0, unsigned int size, unsigned int number, @@ -763,34 +647,9 @@ static int translate_table(const char *name, return ret; } -static struct arpt_table_info *replace_table(struct arpt_table *table, - unsigned int num_counters, - struct arpt_table_info *newinfo, - int *error) -{ - struct arpt_table_info *oldinfo; - - /* Do the substitution. */ - write_lock_bh(&table->lock); - /* Check inside lock: is the old number correct? */ - if (num_counters != table->private->number) { - duprintf("num_counters != table->private->number (%u/%u)\n", - num_counters, table->private->number); - write_unlock_bh(&table->lock); - *error = -EAGAIN; - return NULL; - } - oldinfo = table->private; - table->private = newinfo; - newinfo->initial_entries = oldinfo->initial_entries; - write_unlock_bh(&table->lock); - - return oldinfo; -} - /* Gets counters. */ static inline int add_entry_to_counter(const struct arpt_entry *e, - struct arpt_counters total[], + struct xt_counters total[], unsigned int *i) { ADD_COUNTER(total[*i], e->counters.bcnt, e->counters.pcnt); @@ -800,7 +659,7 @@ static inline int add_entry_to_counter(const struct arpt_entry *e, } static inline int set_entry_to_counter(const struct arpt_entry *e, - struct arpt_counters total[], + struct xt_counters total[], unsigned int *i) { SET_COUNTER(total[*i], e->counters.bcnt, e->counters.pcnt); @@ -809,8 +668,8 @@ static inline int set_entry_to_counter(const struct arpt_entry *e, return 0; } -static void get_counters(const struct arpt_table_info *t, - struct arpt_counters counters[]) +static void get_counters(const struct xt_table_info *t, + struct xt_counters counters[]) { unsigned int cpu; unsigned int i; @@ -848,7 +707,8 @@ static int copy_entries_to_user(unsigned int total_size, { unsigned int off, num, countersize; struct arpt_entry *e; - struct arpt_counters *counters; + struct xt_counters *counters; + struct xt_table_info *private = table->private; int ret = 0; void *loc_cpu_entry; @@ -856,18 +716,18 @@ static int copy_entries_to_user(unsigned int total_size, * (other than comefrom, which userspace doesn't care * about). */ - countersize = sizeof(struct arpt_counters) * table->private->number; - counters = vmalloc(countersize); + countersize = sizeof(struct xt_counters) * private->number; + counters = vmalloc_node(countersize, numa_node_id()); if (counters == NULL) return -ENOMEM; /* First, sum counters... */ write_lock_bh(&table->lock); - get_counters(table->private, counters); + get_counters(private, counters); write_unlock_bh(&table->lock); - loc_cpu_entry = table->private->entries[raw_smp_processor_id()]; + loc_cpu_entry = private->entries[raw_smp_processor_id()]; /* ... then copy entire thing ... */ if (copy_to_user(userptr, loc_cpu_entry, total_size) != 0) { ret = -EFAULT; @@ -910,75 +770,34 @@ static int get_entries(const struct arpt_get_entries *entries, int ret; struct arpt_table *t; - t = find_table_lock(entries->name); + t = xt_find_table_lock(NF_ARP, entries->name); if (t || !IS_ERR(t)) { + struct xt_table_info *private = t->private; duprintf("t->private->number = %u\n", - t->private->number); - if (entries->size == t->private->size) - ret = copy_entries_to_user(t->private->size, + private->number); + if (entries->size == private->size) + ret = copy_entries_to_user(private->size, t, uptr->entrytable); else { duprintf("get_entries: I've got %u not %u!\n", - t->private->size, - entries->size); + private->size, entries->size); ret = -EINVAL; } module_put(t->me); - up(&arpt_mutex); + xt_table_unlock(t); } else ret = t ? PTR_ERR(t) : -ENOENT; return ret; } -static void free_table_info(struct arpt_table_info *info) -{ - int cpu; - for_each_cpu(cpu) { - if (info->size <= PAGE_SIZE) - kfree(info->entries[cpu]); - else - vfree(info->entries[cpu]); - } - kfree(info); -} - -static struct arpt_table_info *alloc_table_info(unsigned int size) -{ - struct arpt_table_info *newinfo; - int cpu; - - newinfo = kzalloc(sizeof(struct arpt_table_info), GFP_KERNEL); - if (!newinfo) - return NULL; - - newinfo->size = size; - - for_each_cpu(cpu) { - if (size <= PAGE_SIZE) - newinfo->entries[cpu] = kmalloc_node(size, - GFP_KERNEL, - cpu_to_node(cpu)); - else - newinfo->entries[cpu] = vmalloc_node(size, - cpu_to_node(cpu)); - - if (newinfo->entries[cpu] == NULL) { - free_table_info(newinfo); - return NULL; - } - } - - return newinfo; -} - static int do_replace(void __user *user, unsigned int len) { int ret; struct arpt_replace tmp; struct arpt_table *t; - struct arpt_table_info *newinfo, *oldinfo; - struct arpt_counters *counters; + struct xt_table_info *newinfo, *oldinfo; + struct xt_counters *counters; void *loc_cpu_entry, *loc_cpu_old_entry; if (copy_from_user(&tmp, user, sizeof(tmp)) != 0) @@ -988,11 +807,7 @@ static int do_replace(void __user *user, unsigned int len) if (len != sizeof(tmp) + tmp.size) return -ENOPROTOOPT; - /* Pedantry: prevent them from hitting BUG() in vmalloc.c --RR */ - if ((SMP_ALIGN(tmp.size) >> PAGE_SHIFT) + 2 > num_physpages) - return -ENOMEM; - - newinfo = alloc_table_info(tmp.size); + newinfo = xt_alloc_table_info(tmp.size); if (!newinfo) return -ENOMEM; @@ -1004,7 +819,7 @@ static int do_replace(void __user *user, unsigned int len) goto free_newinfo; } - counters = vmalloc(tmp.num_counters * sizeof(struct arpt_counters)); + counters = vmalloc(tmp.num_counters * sizeof(struct xt_counters)); if (!counters) { ret = -ENOMEM; goto free_newinfo; @@ -1018,7 +833,7 @@ static int do_replace(void __user *user, unsigned int len) duprintf("arp_tables: Translated table\n"); - t = try_then_request_module(find_table_lock(tmp.name), + t = try_then_request_module(xt_find_table_lock(NF_ARP, tmp.name), "arptable_%s", tmp.name); if (!t || IS_ERR(t)) { ret = t ? PTR_ERR(t) : -ENOENT; @@ -1033,7 +848,7 @@ static int do_replace(void __user *user, unsigned int len) goto put_module; } - oldinfo = replace_table(t, tmp.num_counters, newinfo, &ret); + oldinfo = xt_replace_table(t, tmp.num_counters, newinfo, &ret); if (!oldinfo) goto put_module; @@ -1053,23 +868,23 @@ static int do_replace(void __user *user, unsigned int len) loc_cpu_old_entry = oldinfo->entries[raw_smp_processor_id()]; ARPT_ENTRY_ITERATE(loc_cpu_old_entry, oldinfo->size, cleanup_entry,NULL); - free_table_info(oldinfo); + xt_free_table_info(oldinfo); if (copy_to_user(tmp.counters, counters, - sizeof(struct arpt_counters) * tmp.num_counters) != 0) + sizeof(struct xt_counters) * tmp.num_counters) != 0) ret = -EFAULT; vfree(counters); - up(&arpt_mutex); + xt_table_unlock(t); return ret; put_module: module_put(t->me); - up(&arpt_mutex); + xt_table_unlock(t); free_newinfo_counters_untrans: ARPT_ENTRY_ITERATE(loc_cpu_entry, newinfo->size, cleanup_entry, NULL); free_newinfo_counters: vfree(counters); free_newinfo: - free_table_info(newinfo); + xt_free_table_info(newinfo); return ret; } @@ -1077,7 +892,7 @@ static int do_replace(void __user *user, unsigned int len) * and everything is OK. */ static inline int add_counter_to_entry(struct arpt_entry *e, - const struct arpt_counters addme[], + const struct xt_counters addme[], unsigned int *i) { @@ -1090,15 +905,16 @@ static inline int add_counter_to_entry(struct arpt_entry *e, static int do_add_counters(void __user *user, unsigned int len) { unsigned int i; - struct arpt_counters_info tmp, *paddc; + struct xt_counters_info tmp, *paddc; struct arpt_table *t; + struct xt_table_info *private; int ret = 0; void *loc_cpu_entry; if (copy_from_user(&tmp, user, sizeof(tmp)) != 0) return -EFAULT; - if (len != sizeof(tmp) + tmp.num_counters*sizeof(struct arpt_counters)) + if (len != sizeof(tmp) + tmp.num_counters*sizeof(struct xt_counters)) return -EINVAL; paddc = vmalloc(len); @@ -1110,29 +926,30 @@ static int do_add_counters(void __user *user, unsigned int len) goto free; } - t = find_table_lock(tmp.name); + t = xt_find_table_lock(NF_ARP, tmp.name); if (!t || IS_ERR(t)) { ret = t ? PTR_ERR(t) : -ENOENT; goto free; } write_lock_bh(&t->lock); - if (t->private->number != paddc->num_counters) { + private = t->private; + if (private->number != paddc->num_counters) { ret = -EINVAL; goto unlock_up_free; } i = 0; /* Choose the copy that is on our node */ - loc_cpu_entry = t->private->entries[smp_processor_id()]; + loc_cpu_entry = private->entries[smp_processor_id()]; ARPT_ENTRY_ITERATE(loc_cpu_entry, - t->private->size, + private->size, add_counter_to_entry, paddc->counters, &i); unlock_up_free: write_unlock_bh(&t->lock); - up(&arpt_mutex); + xt_table_unlock(t); module_put(t->me); free: vfree(paddc); @@ -1189,25 +1006,26 @@ static int do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len } name[ARPT_TABLE_MAXNAMELEN-1] = '\0'; - t = try_then_request_module(find_table_lock(name), + t = try_then_request_module(xt_find_table_lock(NF_ARP, name), "arptable_%s", name); if (t && !IS_ERR(t)) { struct arpt_getinfo info; + struct xt_table_info *private = t->private; info.valid_hooks = t->valid_hooks; - memcpy(info.hook_entry, t->private->hook_entry, + memcpy(info.hook_entry, private->hook_entry, sizeof(info.hook_entry)); - memcpy(info.underflow, t->private->underflow, + memcpy(info.underflow, private->underflow, sizeof(info.underflow)); - info.num_entries = t->private->number; - info.size = t->private->size; + info.num_entries = private->number; + info.size = private->size; strcpy(info.name, name); if (copy_to_user(user, &info, *len) != 0) ret = -EFAULT; else ret = 0; - up(&arpt_mutex); + xt_table_unlock(t); module_put(t->me); } else ret = t ? PTR_ERR(t) : -ENOENT; @@ -1232,7 +1050,7 @@ static int do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len } case ARPT_SO_GET_REVISION_TARGET: { - struct arpt_get_revision rev; + struct xt_get_revision rev; if (*len != sizeof(rev)) { ret = -EINVAL; @@ -1243,8 +1061,8 @@ static int do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len break; } - try_then_request_module(find_revision(rev.name, rev.revision, - target_revfn, &ret), + try_then_request_module(xt_find_revision(NF_ARP, rev.name, + rev.revision, 1, &ret), "arpt_%s", rev.name); break; } @@ -1257,38 +1075,16 @@ static int do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len return ret; } -/* Registration hooks for targets. */ -int arpt_register_target(struct arpt_target *target) -{ - int ret; - - ret = down_interruptible(&arpt_mutex); - if (ret != 0) - return ret; - - list_add(&target->list, &arpt_target); - up(&arpt_mutex); - - return ret; -} - -void arpt_unregister_target(struct arpt_target *target) -{ - down(&arpt_mutex); - LIST_DELETE(&arpt_target, target); - up(&arpt_mutex); -} - int arpt_register_table(struct arpt_table *table, const struct arpt_replace *repl) { int ret; - struct arpt_table_info *newinfo; - static struct arpt_table_info bootstrap + struct xt_table_info *newinfo; + static struct xt_table_info bootstrap = { 0, 0, 0, { 0 }, { 0 }, { } }; void *loc_cpu_entry; - newinfo = alloc_table_info(repl->size); + newinfo = xt_alloc_table_info(repl->size); if (!newinfo) { ret = -ENOMEM; return ret; @@ -1303,60 +1099,33 @@ int arpt_register_table(struct arpt_table *table, repl->num_entries, repl->hook_entry, repl->underflow); + duprintf("arpt_register_table: translate table gives %d\n", ret); if (ret != 0) { - free_table_info(newinfo); + xt_free_table_info(newinfo); return ret; } - ret = down_interruptible(&arpt_mutex); - if (ret != 0) { - free_table_info(newinfo); + if (xt_register_table(table, &bootstrap, newinfo) != 0) { + xt_free_table_info(newinfo); return ret; } - /* Don't autoload: we'd eat our tail... */ - if (list_named_find(&arpt_tables, table->name)) { - ret = -EEXIST; - goto free_unlock; - } - - /* Simplifies replace_table code. */ - table->private = &bootstrap; - if (!replace_table(table, 0, newinfo, &ret)) - goto free_unlock; - - duprintf("table->private->number = %u\n", - table->private->number); - - /* save number of initial entries */ - table->private->initial_entries = table->private->number; - - rwlock_init(&table->lock); - list_prepend(&arpt_tables, table); - - unlock: - up(&arpt_mutex); - return ret; - - free_unlock: - free_table_info(newinfo); - goto unlock; + return 0; } void arpt_unregister_table(struct arpt_table *table) { + struct xt_table_info *private; void *loc_cpu_entry; - down(&arpt_mutex); - LIST_DELETE(&arpt_tables, table); - up(&arpt_mutex); + private = xt_unregister_table(table); /* Decrease module usage counts and free resources */ - loc_cpu_entry = table->private->entries[raw_smp_processor_id()]; - ARPT_ENTRY_ITERATE(loc_cpu_entry, table->private->size, + loc_cpu_entry = private->entries[raw_smp_processor_id()]; + ARPT_ENTRY_ITERATE(loc_cpu_entry, private->size, cleanup_entry, NULL); - free_table_info(table->private); + xt_free_table_info(private); } /* The built-in targets: standard (NULL) and error. */ @@ -1379,52 +1148,15 @@ static struct nf_sockopt_ops arpt_sockopts = { .get = do_arpt_get_ctl, }; -#ifdef CONFIG_PROC_FS -static inline int print_name(const struct arpt_table *t, - off_t start_offset, char *buffer, int length, - off_t *pos, unsigned int *count) -{ - if ((*count)++ >= start_offset) { - unsigned int namelen; - - namelen = sprintf(buffer + *pos, "%s\n", t->name); - if (*pos + namelen > length) { - /* Stop iterating */ - return 1; - } - *pos += namelen; - } - return 0; -} - -static int arpt_get_tables(char *buffer, char **start, off_t offset, int length) -{ - off_t pos = 0; - unsigned int count = 0; - - if (down_interruptible(&arpt_mutex) != 0) - return 0; - - LIST_FIND(&arpt_tables, print_name, struct arpt_table *, - offset, buffer, length, &pos, &count); - - up(&arpt_mutex); - - /* `start' hack - see fs/proc/generic.c line ~105 */ - *start=(char *)((unsigned long)count-offset); - return pos; -} -#endif /*CONFIG_PROC_FS*/ - static int __init init(void) { int ret; + xt_proto_init(NF_ARP); + /* Noone else will be downing sem now, so we won't sleep */ - down(&arpt_mutex); - list_append(&arpt_target, &arpt_standard_target); - list_append(&arpt_target, &arpt_error_target); - up(&arpt_mutex); + xt_register_target(NF_ARP, &arpt_standard_target); + xt_register_target(NF_ARP, &arpt_error_target); /* Register setsockopt */ ret = nf_register_sockopt(&arpt_sockopts); @@ -1433,19 +1165,6 @@ static int __init init(void) return ret; } -#ifdef CONFIG_PROC_FS - { - struct proc_dir_entry *proc; - - proc = proc_net_create("arp_tables_names", 0, arpt_get_tables); - if (!proc) { - nf_unregister_sockopt(&arpt_sockopts); - return -ENOMEM; - } - proc->owner = THIS_MODULE; - } -#endif - printk("arp_tables: (C) 2002 David S. Miller\n"); return 0; } @@ -1453,16 +1172,12 @@ static int __init init(void) static void __exit fini(void) { nf_unregister_sockopt(&arpt_sockopts); -#ifdef CONFIG_PROC_FS - proc_net_remove("arp_tables_names"); -#endif + xt_proto_fini(NF_ARP); } EXPORT_SYMBOL(arpt_register_table); EXPORT_SYMBOL(arpt_unregister_table); EXPORT_SYMBOL(arpt_do_table); -EXPORT_SYMBOL(arpt_register_target); -EXPORT_SYMBOL(arpt_unregister_target); module_init(init); module_exit(fini); diff --git a/net/ipv4/netfilter/arpt_mangle.c b/net/ipv4/netfilter/arpt_mangle.c index 3e592ec86482..c97650a16a5b 100644 --- a/net/ipv4/netfilter/arpt_mangle.c +++ b/net/ipv4/netfilter/arpt_mangle.c @@ -8,8 +8,9 @@ MODULE_AUTHOR("Bart De Schuymer <bdschuym@pandora.be>"); MODULE_DESCRIPTION("arptables arp payload mangle target"); static unsigned int -target(struct sk_buff **pskb, unsigned int hooknum, const struct net_device *in, - const struct net_device *out, const void *targinfo, void *userinfo) +target(struct sk_buff **pskb, const struct net_device *in, + const struct net_device *out, unsigned int hooknum, const void *targinfo, + void *userinfo) { const struct arpt_mangle *mangle = targinfo; struct arphdr *arp; @@ -64,7 +65,7 @@ target(struct sk_buff **pskb, unsigned int hooknum, const struct net_device *in, } static int -checkentry(const char *tablename, const struct arpt_entry *e, void *targinfo, +checkentry(const char *tablename, const void *e, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) { const struct arpt_mangle *mangle = targinfo; diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c index 0d759f5a4ef0..f6ab45f48681 100644 --- a/net/ipv4/netfilter/arptable_filter.c +++ b/net/ipv4/netfilter/arptable_filter.c @@ -145,6 +145,7 @@ static struct arpt_table packet_filter = { .lock = RW_LOCK_UNLOCKED, .private = NULL, .me = THIS_MODULE, + .af = NF_ARP, }; /* The work comes in here from netfilter.c */ diff --git a/net/ipv4/netfilter/ip_conntrack_helper_pptp.c b/net/ipv4/netfilter/ip_conntrack_helper_pptp.c index 4108a5e12b3c..d716bba798f2 100644 --- a/net/ipv4/netfilter/ip_conntrack_helper_pptp.c +++ b/net/ipv4/netfilter/ip_conntrack_helper_pptp.c @@ -762,7 +762,7 @@ static struct ip_conntrack_helper pptp = { .help = conntrack_pptp_help }; -extern void __exit ip_ct_proto_gre_fini(void); +extern void ip_ct_proto_gre_fini(void); extern int __init ip_ct_proto_gre_init(void); /* ip_conntrack_pptp initialization */ diff --git a/net/ipv4/netfilter/ip_conntrack_proto_generic.c b/net/ipv4/netfilter/ip_conntrack_proto_generic.c index 88c3712bd251..f891308b5e4c 100644 --- a/net/ipv4/netfilter/ip_conntrack_proto_generic.c +++ b/net/ipv4/netfilter/ip_conntrack_proto_generic.c @@ -12,7 +12,7 @@ #include <linux/netfilter.h> #include <linux/netfilter_ipv4/ip_conntrack_protocol.h> -unsigned long ip_ct_generic_timeout = 600*HZ; +unsigned int ip_ct_generic_timeout = 600*HZ; static int generic_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, diff --git a/net/ipv4/netfilter/ip_conntrack_proto_gre.c b/net/ipv4/netfilter/ip_conntrack_proto_gre.c index 57956dee60c8..56794797d55b 100644 --- a/net/ipv4/netfilter/ip_conntrack_proto_gre.c +++ b/net/ipv4/netfilter/ip_conntrack_proto_gre.c @@ -32,6 +32,7 @@ #include <linux/in.h> #include <linux/list.h> #include <linux/seq_file.h> +#include <linux/interrupt.h> static DEFINE_RWLOCK(ip_ct_gre_lock); #define ASSERT_READ_LOCK(x) @@ -309,7 +310,10 @@ int __init ip_ct_proto_gre_init(void) return ip_conntrack_protocol_register(&gre); } -void __exit ip_ct_proto_gre_fini(void) +/* This cannot be __exit, as it is invoked from ip_conntrack_helper_pptp.c's + * init() code on errors. + */ +void ip_ct_proto_gre_fini(void) { struct list_head *pos, *n; diff --git a/net/ipv4/netfilter/ip_conntrack_proto_icmp.c b/net/ipv4/netfilter/ip_conntrack_proto_icmp.c index 30fc21d6165a..3021af0910f1 100644 --- a/net/ipv4/netfilter/ip_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/ip_conntrack_proto_icmp.c @@ -16,13 +16,12 @@ #include <linux/skbuff.h> #include <net/ip.h> #include <net/checksum.h> -#include <linux/netfilter.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_ipv4/ip_conntrack.h> #include <linux/netfilter_ipv4/ip_conntrack_core.h> #include <linux/netfilter_ipv4/ip_conntrack_protocol.h> -unsigned long ip_ct_icmp_timeout = 30*HZ; +unsigned int ip_ct_icmp_timeout = 30*HZ; #if 0 #define DEBUGP printk diff --git a/net/ipv4/netfilter/ip_conntrack_proto_sctp.c b/net/ipv4/netfilter/ip_conntrack_proto_sctp.c index 977fb59d4563..be602e8aeab0 100644 --- a/net/ipv4/netfilter/ip_conntrack_proto_sctp.c +++ b/net/ipv4/netfilter/ip_conntrack_proto_sctp.c @@ -16,6 +16,7 @@ #include <linux/types.h> #include <linux/sched.h> #include <linux/timer.h> +#include <linux/interrupt.h> #include <linux/netfilter.h> #include <linux/module.h> #include <linux/in.h> @@ -57,15 +58,15 @@ static const char *sctp_conntrack_names[] = { #define HOURS * 60 MINS #define DAYS * 24 HOURS -static unsigned long ip_ct_sctp_timeout_closed = 10 SECS; -static unsigned long ip_ct_sctp_timeout_cookie_wait = 3 SECS; -static unsigned long ip_ct_sctp_timeout_cookie_echoed = 3 SECS; -static unsigned long ip_ct_sctp_timeout_established = 5 DAYS; -static unsigned long ip_ct_sctp_timeout_shutdown_sent = 300 SECS / 1000; -static unsigned long ip_ct_sctp_timeout_shutdown_recd = 300 SECS / 1000; -static unsigned long ip_ct_sctp_timeout_shutdown_ack_sent = 3 SECS; +static unsigned int ip_ct_sctp_timeout_closed = 10 SECS; +static unsigned int ip_ct_sctp_timeout_cookie_wait = 3 SECS; +static unsigned int ip_ct_sctp_timeout_cookie_echoed = 3 SECS; +static unsigned int ip_ct_sctp_timeout_established = 5 DAYS; +static unsigned int ip_ct_sctp_timeout_shutdown_sent = 300 SECS / 1000; +static unsigned int ip_ct_sctp_timeout_shutdown_recd = 300 SECS / 1000; +static unsigned int ip_ct_sctp_timeout_shutdown_ack_sent = 3 SECS; -static const unsigned long * sctp_timeouts[] +static const unsigned int * sctp_timeouts[] = { NULL, /* SCTP_CONNTRACK_NONE */ &ip_ct_sctp_timeout_closed, /* SCTP_CONNTRACK_CLOSED */ &ip_ct_sctp_timeout_cookie_wait, /* SCTP_CONNTRACK_COOKIE_WAIT */ diff --git a/net/ipv4/netfilter/ip_conntrack_proto_tcp.c b/net/ipv4/netfilter/ip_conntrack_proto_tcp.c index e7fa29e576dc..e0dc37063545 100644 --- a/net/ipv4/netfilter/ip_conntrack_proto_tcp.c +++ b/net/ipv4/netfilter/ip_conntrack_proto_tcp.c @@ -32,7 +32,6 @@ #include <net/tcp.h> -#include <linux/netfilter.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_ipv4/ip_conntrack.h> #include <linux/netfilter_ipv4/ip_conntrack_protocol.h> @@ -85,21 +84,21 @@ static const char *tcp_conntrack_names[] = { #define HOURS * 60 MINS #define DAYS * 24 HOURS -unsigned long ip_ct_tcp_timeout_syn_sent = 2 MINS; -unsigned long ip_ct_tcp_timeout_syn_recv = 60 SECS; -unsigned long ip_ct_tcp_timeout_established = 5 DAYS; -unsigned long ip_ct_tcp_timeout_fin_wait = 2 MINS; -unsigned long ip_ct_tcp_timeout_close_wait = 60 SECS; -unsigned long ip_ct_tcp_timeout_last_ack = 30 SECS; -unsigned long ip_ct_tcp_timeout_time_wait = 2 MINS; -unsigned long ip_ct_tcp_timeout_close = 10 SECS; +unsigned int ip_ct_tcp_timeout_syn_sent = 2 MINS; +unsigned int ip_ct_tcp_timeout_syn_recv = 60 SECS; +unsigned int ip_ct_tcp_timeout_established = 5 DAYS; +unsigned int ip_ct_tcp_timeout_fin_wait = 2 MINS; +unsigned int ip_ct_tcp_timeout_close_wait = 60 SECS; +unsigned int ip_ct_tcp_timeout_last_ack = 30 SECS; +unsigned int ip_ct_tcp_timeout_time_wait = 2 MINS; +unsigned int ip_ct_tcp_timeout_close = 10 SECS; /* RFC1122 says the R2 limit should be at least 100 seconds. Linux uses 15 packets as limit, which corresponds to ~13-30min depending on RTO. */ -unsigned long ip_ct_tcp_timeout_max_retrans = 5 MINS; +unsigned int ip_ct_tcp_timeout_max_retrans = 5 MINS; -static const unsigned long * tcp_timeouts[] +static const unsigned int * tcp_timeouts[] = { NULL, /* TCP_CONNTRACK_NONE */ &ip_ct_tcp_timeout_syn_sent, /* TCP_CONNTRACK_SYN_SENT, */ &ip_ct_tcp_timeout_syn_recv, /* TCP_CONNTRACK_SYN_RECV, */ @@ -995,7 +994,7 @@ static int tcp_packet(struct ip_conntrack *conntrack, || (!test_bit(IPS_ASSURED_BIT, &conntrack->status) && conntrack->proto.tcp.last_index == TCP_ACK_SET)) && ntohl(th->ack_seq) == conntrack->proto.tcp.last_end) { - /* RST sent to invalid SYN or ACK we had let trough + /* RST sent to invalid SYN or ACK we had let through * at a) and c) above: * * a) SYN was in window then @@ -1006,7 +1005,7 @@ static int tcp_packet(struct ip_conntrack *conntrack, * segments we ignored. */ goto in_window; } - /* Just fall trough */ + /* Just fall through */ default: /* Keep compilers happy. */ break; diff --git a/net/ipv4/netfilter/ip_conntrack_proto_udp.c b/net/ipv4/netfilter/ip_conntrack_proto_udp.c index 46becbe4fe58..55b7d3210adf 100644 --- a/net/ipv4/netfilter/ip_conntrack_proto_udp.c +++ b/net/ipv4/netfilter/ip_conntrack_proto_udp.c @@ -15,12 +15,11 @@ #include <linux/udp.h> #include <linux/seq_file.h> #include <net/checksum.h> -#include <linux/netfilter.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_ipv4/ip_conntrack_protocol.h> -unsigned long ip_ct_udp_timeout = 30*HZ; -unsigned long ip_ct_udp_timeout_stream = 180*HZ; +unsigned int ip_ct_udp_timeout = 30*HZ; +unsigned int ip_ct_udp_timeout_stream = 180*HZ; static int udp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, diff --git a/net/ipv4/netfilter/ip_conntrack_standalone.c b/net/ipv4/netfilter/ip_conntrack_standalone.c index 7ba97783e741..833fcb4be5e7 100644 --- a/net/ipv4/netfilter/ip_conntrack_standalone.c +++ b/net/ipv4/netfilter/ip_conntrack_standalone.c @@ -544,28 +544,28 @@ extern int ip_conntrack_max; extern unsigned int ip_conntrack_htable_size; /* From ip_conntrack_proto_tcp.c */ -extern unsigned long ip_ct_tcp_timeout_syn_sent; -extern unsigned long ip_ct_tcp_timeout_syn_recv; -extern unsigned long ip_ct_tcp_timeout_established; -extern unsigned long ip_ct_tcp_timeout_fin_wait; -extern unsigned long ip_ct_tcp_timeout_close_wait; -extern unsigned long ip_ct_tcp_timeout_last_ack; -extern unsigned long ip_ct_tcp_timeout_time_wait; -extern unsigned long ip_ct_tcp_timeout_close; -extern unsigned long ip_ct_tcp_timeout_max_retrans; +extern unsigned int ip_ct_tcp_timeout_syn_sent; +extern unsigned int ip_ct_tcp_timeout_syn_recv; +extern unsigned int ip_ct_tcp_timeout_established; +extern unsigned int ip_ct_tcp_timeout_fin_wait; +extern unsigned int ip_ct_tcp_timeout_close_wait; +extern unsigned int ip_ct_tcp_timeout_last_ack; +extern unsigned int ip_ct_tcp_timeout_time_wait; +extern unsigned int ip_ct_tcp_timeout_close; +extern unsigned int ip_ct_tcp_timeout_max_retrans; extern int ip_ct_tcp_loose; extern int ip_ct_tcp_be_liberal; extern int ip_ct_tcp_max_retrans; /* From ip_conntrack_proto_udp.c */ -extern unsigned long ip_ct_udp_timeout; -extern unsigned long ip_ct_udp_timeout_stream; +extern unsigned int ip_ct_udp_timeout; +extern unsigned int ip_ct_udp_timeout_stream; /* From ip_conntrack_proto_icmp.c */ -extern unsigned long ip_ct_icmp_timeout; +extern unsigned int ip_ct_icmp_timeout; /* From ip_conntrack_proto_icmp.c */ -extern unsigned long ip_ct_generic_timeout; +extern unsigned int ip_ct_generic_timeout; /* Log invalid packets of a given protocol */ static int log_invalid_proto_min = 0; @@ -944,7 +944,7 @@ module_exit(fini); /* Some modules need us, but don't depend directly on any symbol. They should call this. */ -void need_ip_conntrack(void) +void need_conntrack(void) { } @@ -962,7 +962,7 @@ EXPORT_SYMBOL(ip_ct_get_tuple); EXPORT_SYMBOL(invert_tuplepr); EXPORT_SYMBOL(ip_conntrack_alter_reply); EXPORT_SYMBOL(ip_conntrack_destroyed); -EXPORT_SYMBOL(need_ip_conntrack); +EXPORT_SYMBOL(need_conntrack); EXPORT_SYMBOL(ip_conntrack_helper_register); EXPORT_SYMBOL(ip_conntrack_helper_unregister); EXPORT_SYMBOL(ip_ct_iterate_cleanup); diff --git a/net/ipv4/netfilter/ip_nat_helper_pptp.c b/net/ipv4/netfilter/ip_nat_helper_pptp.c index e546203f5662..ac004895781a 100644 --- a/net/ipv4/netfilter/ip_nat_helper_pptp.c +++ b/net/ipv4/netfilter/ip_nat_helper_pptp.c @@ -148,14 +148,14 @@ pptp_outbound_pkt(struct sk_buff **pskb, { struct ip_ct_pptp_master *ct_pptp_info = &ct->help.ct_pptp_info; struct ip_nat_pptp *nat_pptp_info = &ct->nat.help.nat_pptp_info; - - u_int16_t msg, *cid = NULL, new_callid; + u_int16_t msg, new_callid; + unsigned int cid_off; new_callid = htons(ct_pptp_info->pns_call_id); switch (msg = ntohs(ctlh->messageType)) { case PPTP_OUT_CALL_REQUEST: - cid = &pptpReq->ocreq.callID; + cid_off = offsetof(union pptp_ctrl_union, ocreq.callID); /* FIXME: ideally we would want to reserve a call ID * here. current netfilter NAT core is not able to do * this :( For now we use TCP source port. This breaks @@ -172,10 +172,10 @@ pptp_outbound_pkt(struct sk_buff **pskb, ct_pptp_info->pns_call_id = ntohs(new_callid); break; case PPTP_IN_CALL_REPLY: - cid = &pptpReq->icreq.callID; + cid_off = offsetof(union pptp_ctrl_union, icreq.callID); break; case PPTP_CALL_CLEAR_REQUEST: - cid = &pptpReq->clrreq.callID; + cid_off = offsetof(union pptp_ctrl_union, clrreq.callID); break; default: DEBUGP("unknown outbound packet 0x%04x:%s\n", msg, @@ -197,18 +197,15 @@ pptp_outbound_pkt(struct sk_buff **pskb, /* only OUT_CALL_REQUEST, IN_CALL_REPLY, CALL_CLEAR_REQUEST pass * down to here */ - - IP_NF_ASSERT(cid); - DEBUGP("altering call id from 0x%04x to 0x%04x\n", - ntohs(*cid), ntohs(new_callid)); + ntohs(*(u_int16_t *)pptpReq + cid_off), ntohs(new_callid)); /* mangle packet */ if (ip_nat_mangle_tcp_packet(pskb, ct, ctinfo, - (void *)cid - ((void *)ctlh - sizeof(struct pptp_pkt_hdr)), - sizeof(new_callid), - (char *)&new_callid, - sizeof(new_callid)) == 0) + cid_off + sizeof(struct pptp_pkt_hdr) + + sizeof(struct PptpControlHeader), + sizeof(new_callid), (char *)&new_callid, + sizeof(new_callid)) == 0) return NF_DROP; return NF_ACCEPT; @@ -299,31 +296,30 @@ pptp_inbound_pkt(struct sk_buff **pskb, union pptp_ctrl_union *pptpReq) { struct ip_nat_pptp *nat_pptp_info = &ct->nat.help.nat_pptp_info; - u_int16_t msg, new_cid = 0, new_pcid, *pcid = NULL, *cid = NULL; - - int ret = NF_ACCEPT, rv; + u_int16_t msg, new_cid = 0, new_pcid; + unsigned int pcid_off, cid_off = 0; new_pcid = htons(nat_pptp_info->pns_call_id); switch (msg = ntohs(ctlh->messageType)) { case PPTP_OUT_CALL_REPLY: - pcid = &pptpReq->ocack.peersCallID; - cid = &pptpReq->ocack.callID; + pcid_off = offsetof(union pptp_ctrl_union, ocack.peersCallID); + cid_off = offsetof(union pptp_ctrl_union, ocack.callID); break; case PPTP_IN_CALL_CONNECT: - pcid = &pptpReq->iccon.peersCallID; + pcid_off = offsetof(union pptp_ctrl_union, iccon.peersCallID); break; case PPTP_IN_CALL_REQUEST: /* only need to nat in case PAC is behind NAT box */ - break; + return NF_ACCEPT; case PPTP_WAN_ERROR_NOTIFY: - pcid = &pptpReq->wanerr.peersCallID; + pcid_off = offsetof(union pptp_ctrl_union, wanerr.peersCallID); break; case PPTP_CALL_DISCONNECT_NOTIFY: - pcid = &pptpReq->disc.callID; + pcid_off = offsetof(union pptp_ctrl_union, disc.callID); break; case PPTP_SET_LINK_INFO: - pcid = &pptpReq->setlink.peersCallID; + pcid_off = offsetof(union pptp_ctrl_union, setlink.peersCallID); break; default: @@ -345,35 +341,26 @@ pptp_inbound_pkt(struct sk_buff **pskb, * WAN_ERROR_NOTIFY, CALL_DISCONNECT_NOTIFY pass down here */ /* mangle packet */ - IP_NF_ASSERT(pcid); DEBUGP("altering peer call id from 0x%04x to 0x%04x\n", - ntohs(*pcid), ntohs(new_pcid)); - - rv = ip_nat_mangle_tcp_packet(pskb, ct, ctinfo, - (void *)pcid - ((void *)ctlh - sizeof(struct pptp_pkt_hdr)), - sizeof(new_pcid), (char *)&new_pcid, - sizeof(new_pcid)); - if (rv != NF_ACCEPT) - return rv; + ntohs(*(u_int16_t *)pptpReq + pcid_off), ntohs(new_pcid)); + + if (ip_nat_mangle_tcp_packet(pskb, ct, ctinfo, + pcid_off + sizeof(struct pptp_pkt_hdr) + + sizeof(struct PptpControlHeader), + sizeof(new_pcid), (char *)&new_pcid, + sizeof(new_pcid)) == 0) + return NF_DROP; if (new_cid) { - IP_NF_ASSERT(cid); DEBUGP("altering call id from 0x%04x to 0x%04x\n", - ntohs(*cid), ntohs(new_cid)); - rv = ip_nat_mangle_tcp_packet(pskb, ct, ctinfo, - (void *)cid - ((void *)ctlh - sizeof(struct pptp_pkt_hdr)), - sizeof(new_cid), - (char *)&new_cid, - sizeof(new_cid)); - if (rv != NF_ACCEPT) - return rv; + ntohs(*(u_int16_t *)pptpReq + cid_off), ntohs(new_cid)); + if (ip_nat_mangle_tcp_packet(pskb, ct, ctinfo, + cid_off + sizeof(struct pptp_pkt_hdr) + + sizeof(struct PptpControlHeader), + sizeof(new_cid), (char *)&new_cid, + sizeof(new_cid)) == 0) + return NF_DROP; } - - /* check for earlier return value of 'switch' above */ - if (ret != NF_ACCEPT) - return ret; - - /* great, at least we don't need to resize packets */ return NF_ACCEPT; } diff --git a/net/ipv4/netfilter/ip_nat_proto_gre.c b/net/ipv4/netfilter/ip_nat_proto_gre.c index f7cad7cf1aec..6c4899d8046a 100644 --- a/net/ipv4/netfilter/ip_nat_proto_gre.c +++ b/net/ipv4/netfilter/ip_nat_proto_gre.c @@ -151,42 +151,6 @@ gre_manip_pkt(struct sk_buff **pskb, return 1; } -/* print out a nat tuple */ -static unsigned int -gre_print(char *buffer, - const struct ip_conntrack_tuple *match, - const struct ip_conntrack_tuple *mask) -{ - unsigned int len = 0; - - if (mask->src.u.gre.key) - len += sprintf(buffer + len, "srckey=0x%x ", - ntohl(match->src.u.gre.key)); - - if (mask->dst.u.gre.key) - len += sprintf(buffer + len, "dstkey=0x%x ", - ntohl(match->src.u.gre.key)); - - return len; -} - -/* print a range of keys */ -static unsigned int -gre_print_range(char *buffer, const struct ip_nat_range *range) -{ - if (range->min.gre.key != 0 - || range->max.gre.key != 0xFFFF) { - if (range->min.gre.key == range->max.gre.key) - return sprintf(buffer, "key 0x%x ", - ntohl(range->min.gre.key)); - else - return sprintf(buffer, "keys 0x%u-0x%u ", - ntohl(range->min.gre.key), - ntohl(range->max.gre.key)); - } else - return 0; -} - /* nat helper struct */ static struct ip_nat_protocol gre = { .name = "GRE", @@ -194,8 +158,6 @@ static struct ip_nat_protocol gre = { .manip_pkt = gre_manip_pkt, .in_range = gre_in_range, .unique_tuple = gre_unique_tuple, - .print = gre_print, - .print_range = gre_print_range, #if defined(CONFIG_IP_NF_CONNTRACK_NETLINK) || \ defined(CONFIG_IP_NF_CONNTRACK_NETLINK_MODULE) .range_to_nfattr = ip_nat_port_range_to_nfattr, diff --git a/net/ipv4/netfilter/ip_nat_proto_icmp.c b/net/ipv4/netfilter/ip_nat_proto_icmp.c index 938719043999..31a3f4ccb99c 100644 --- a/net/ipv4/netfilter/ip_nat_proto_icmp.c +++ b/net/ipv4/netfilter/ip_nat_proto_icmp.c @@ -74,38 +74,6 @@ icmp_manip_pkt(struct sk_buff **pskb, return 1; } -static unsigned int -icmp_print(char *buffer, - const struct ip_conntrack_tuple *match, - const struct ip_conntrack_tuple *mask) -{ - unsigned int len = 0; - - if (mask->src.u.icmp.id) - len += sprintf(buffer + len, "id=%u ", - ntohs(match->src.u.icmp.id)); - - if (mask->dst.u.icmp.type) - len += sprintf(buffer + len, "type=%u ", - ntohs(match->dst.u.icmp.type)); - - if (mask->dst.u.icmp.code) - len += sprintf(buffer + len, "code=%u ", - ntohs(match->dst.u.icmp.code)); - - return len; -} - -static unsigned int -icmp_print_range(char *buffer, const struct ip_nat_range *range) -{ - if (range->min.icmp.id != 0 || range->max.icmp.id != 0xFFFF) - return sprintf(buffer, "id %u-%u ", - ntohs(range->min.icmp.id), - ntohs(range->max.icmp.id)); - else return 0; -} - struct ip_nat_protocol ip_nat_protocol_icmp = { .name = "ICMP", .protonum = IPPROTO_ICMP, @@ -113,8 +81,6 @@ struct ip_nat_protocol ip_nat_protocol_icmp = { .manip_pkt = icmp_manip_pkt, .in_range = icmp_in_range, .unique_tuple = icmp_unique_tuple, - .print = icmp_print, - .print_range = icmp_print_range, #if defined(CONFIG_IP_NF_CONNTRACK_NETLINK) || \ defined(CONFIG_IP_NF_CONNTRACK_NETLINK_MODULE) .range_to_nfattr = ip_nat_port_range_to_nfattr, diff --git a/net/ipv4/netfilter/ip_nat_proto_tcp.c b/net/ipv4/netfilter/ip_nat_proto_tcp.c index 1d381bf68574..a3d14079eba6 100644 --- a/net/ipv4/netfilter/ip_nat_proto_tcp.c +++ b/net/ipv4/netfilter/ip_nat_proto_tcp.c @@ -136,40 +136,6 @@ tcp_manip_pkt(struct sk_buff **pskb, return 1; } -static unsigned int -tcp_print(char *buffer, - const struct ip_conntrack_tuple *match, - const struct ip_conntrack_tuple *mask) -{ - unsigned int len = 0; - - if (mask->src.u.tcp.port) - len += sprintf(buffer + len, "srcpt=%u ", - ntohs(match->src.u.tcp.port)); - - - if (mask->dst.u.tcp.port) - len += sprintf(buffer + len, "dstpt=%u ", - ntohs(match->dst.u.tcp.port)); - - return len; -} - -static unsigned int -tcp_print_range(char *buffer, const struct ip_nat_range *range) -{ - if (range->min.tcp.port != 0 || range->max.tcp.port != 0xFFFF) { - if (range->min.tcp.port == range->max.tcp.port) - return sprintf(buffer, "port %u ", - ntohs(range->min.tcp.port)); - else - return sprintf(buffer, "ports %u-%u ", - ntohs(range->min.tcp.port), - ntohs(range->max.tcp.port)); - } - else return 0; -} - struct ip_nat_protocol ip_nat_protocol_tcp = { .name = "TCP", .protonum = IPPROTO_TCP, @@ -177,8 +143,6 @@ struct ip_nat_protocol ip_nat_protocol_tcp = { .manip_pkt = tcp_manip_pkt, .in_range = tcp_in_range, .unique_tuple = tcp_unique_tuple, - .print = tcp_print, - .print_range = tcp_print_range, #if defined(CONFIG_IP_NF_CONNTRACK_NETLINK) || \ defined(CONFIG_IP_NF_CONNTRACK_NETLINK_MODULE) .range_to_nfattr = ip_nat_port_range_to_nfattr, diff --git a/net/ipv4/netfilter/ip_nat_proto_udp.c b/net/ipv4/netfilter/ip_nat_proto_udp.c index c4906e1aa24a..ec6053fdc867 100644 --- a/net/ipv4/netfilter/ip_nat_proto_udp.c +++ b/net/ipv4/netfilter/ip_nat_proto_udp.c @@ -122,40 +122,6 @@ udp_manip_pkt(struct sk_buff **pskb, return 1; } -static unsigned int -udp_print(char *buffer, - const struct ip_conntrack_tuple *match, - const struct ip_conntrack_tuple *mask) -{ - unsigned int len = 0; - - if (mask->src.u.udp.port) - len += sprintf(buffer + len, "srcpt=%u ", - ntohs(match->src.u.udp.port)); - - - if (mask->dst.u.udp.port) - len += sprintf(buffer + len, "dstpt=%u ", - ntohs(match->dst.u.udp.port)); - - return len; -} - -static unsigned int -udp_print_range(char *buffer, const struct ip_nat_range *range) -{ - if (range->min.udp.port != 0 || range->max.udp.port != 0xFFFF) { - if (range->min.udp.port == range->max.udp.port) - return sprintf(buffer, "port %u ", - ntohs(range->min.udp.port)); - else - return sprintf(buffer, "ports %u-%u ", - ntohs(range->min.udp.port), - ntohs(range->max.udp.port)); - } - else return 0; -} - struct ip_nat_protocol ip_nat_protocol_udp = { .name = "UDP", .protonum = IPPROTO_UDP, @@ -163,8 +129,6 @@ struct ip_nat_protocol ip_nat_protocol_udp = { .manip_pkt = udp_manip_pkt, .in_range = udp_in_range, .unique_tuple = udp_unique_tuple, - .print = udp_print, - .print_range = udp_print_range, #if defined(CONFIG_IP_NF_CONNTRACK_NETLINK) || \ defined(CONFIG_IP_NF_CONNTRACK_NETLINK_MODULE) .range_to_nfattr = ip_nat_port_range_to_nfattr, diff --git a/net/ipv4/netfilter/ip_nat_proto_unknown.c b/net/ipv4/netfilter/ip_nat_proto_unknown.c index f0099a646a0b..3bf049517246 100644 --- a/net/ipv4/netfilter/ip_nat_proto_unknown.c +++ b/net/ipv4/netfilter/ip_nat_proto_unknown.c @@ -46,26 +46,10 @@ unknown_manip_pkt(struct sk_buff **pskb, return 1; } -static unsigned int -unknown_print(char *buffer, - const struct ip_conntrack_tuple *match, - const struct ip_conntrack_tuple *mask) -{ - return 0; -} - -static unsigned int -unknown_print_range(char *buffer, const struct ip_nat_range *range) -{ - return 0; -} - struct ip_nat_protocol ip_nat_unknown_protocol = { .name = "unknown", /* .me isn't set: getting a ref to this cannot fail. */ .manip_pkt = unknown_manip_pkt, .in_range = unknown_in_range, .unique_tuple = unknown_unique_tuple, - .print = unknown_print, - .print_range = unknown_print_range }; diff --git a/net/ipv4/netfilter/ip_nat_rule.c b/net/ipv4/netfilter/ip_nat_rule.c index cb66b8bddeb3..1de86282d232 100644 --- a/net/ipv4/netfilter/ip_nat_rule.c +++ b/net/ipv4/netfilter/ip_nat_rule.c @@ -95,6 +95,7 @@ static struct ipt_table nat_table = { .valid_hooks = NAT_VALID_HOOKS, .lock = RW_LOCK_UNLOCKED, .me = THIS_MODULE, + .af = AF_INET, }; /* Source NAT */ @@ -168,7 +169,7 @@ static unsigned int ipt_dnat_target(struct sk_buff **pskb, } static int ipt_snat_checkentry(const char *tablename, - const struct ipt_entry *e, + const void *entry, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) @@ -201,7 +202,7 @@ static int ipt_snat_checkentry(const char *tablename, } static int ipt_dnat_checkentry(const char *tablename, - const struct ipt_entry *e, + const void *entry, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) diff --git a/net/ipv4/netfilter/ip_nat_standalone.c b/net/ipv4/netfilter/ip_nat_standalone.c index f04111f74e09..ad438fb185b8 100644 --- a/net/ipv4/netfilter/ip_nat_standalone.c +++ b/net/ipv4/netfilter/ip_nat_standalone.c @@ -55,6 +55,44 @@ : ((hooknum) == NF_IP_LOCAL_IN ? "LOCAL_IN" \ : "*ERROR*"))) +#ifdef CONFIG_XFRM +static void nat_decode_session(struct sk_buff *skb, struct flowi *fl) +{ + struct ip_conntrack *ct; + struct ip_conntrack_tuple *t; + enum ip_conntrack_info ctinfo; + enum ip_conntrack_dir dir; + unsigned long statusbit; + + ct = ip_conntrack_get(skb, &ctinfo); + if (ct == NULL) + return; + dir = CTINFO2DIR(ctinfo); + t = &ct->tuplehash[dir].tuple; + + if (dir == IP_CT_DIR_ORIGINAL) + statusbit = IPS_DST_NAT; + else + statusbit = IPS_SRC_NAT; + + if (ct->status & statusbit) { + fl->fl4_dst = t->dst.ip; + if (t->dst.protonum == IPPROTO_TCP || + t->dst.protonum == IPPROTO_UDP) + fl->fl_ip_dport = t->dst.u.tcp.port; + } + + statusbit ^= IPS_NAT_MASK; + + if (ct->status & statusbit) { + fl->fl4_src = t->src.ip; + if (t->dst.protonum == IPPROTO_TCP || + t->dst.protonum == IPPROTO_UDP) + fl->fl_ip_sport = t->src.u.tcp.port; + } +} +#endif + static unsigned int ip_nat_fn(unsigned int hooknum, struct sk_buff **pskb, @@ -162,18 +200,20 @@ ip_nat_in(unsigned int hooknum, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - u_int32_t saddr, daddr; + struct ip_conntrack *ct; + enum ip_conntrack_info ctinfo; unsigned int ret; - saddr = (*pskb)->nh.iph->saddr; - daddr = (*pskb)->nh.iph->daddr; - ret = ip_nat_fn(hooknum, pskb, in, out, okfn); if (ret != NF_DROP && ret != NF_STOLEN - && ((*pskb)->nh.iph->saddr != saddr - || (*pskb)->nh.iph->daddr != daddr)) { - dst_release((*pskb)->dst); - (*pskb)->dst = NULL; + && (ct = ip_conntrack_get(*pskb, &ctinfo)) != NULL) { + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + + if (ct->tuplehash[dir].tuple.src.ip != + ct->tuplehash[!dir].tuple.dst.ip) { + dst_release((*pskb)->dst); + (*pskb)->dst = NULL; + } } return ret; } @@ -185,12 +225,30 @@ ip_nat_out(unsigned int hooknum, const struct net_device *out, int (*okfn)(struct sk_buff *)) { + struct ip_conntrack *ct; + enum ip_conntrack_info ctinfo; + unsigned int ret; + /* root is playing with raw sockets. */ if ((*pskb)->len < sizeof(struct iphdr) || (*pskb)->nh.iph->ihl * 4 < sizeof(struct iphdr)) return NF_ACCEPT; - return ip_nat_fn(hooknum, pskb, in, out, okfn); + ret = ip_nat_fn(hooknum, pskb, in, out, okfn); + if (ret != NF_DROP && ret != NF_STOLEN + && (ct = ip_conntrack_get(*pskb, &ctinfo)) != NULL) { + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + + if (ct->tuplehash[dir].tuple.src.ip != + ct->tuplehash[!dir].tuple.dst.ip +#ifdef CONFIG_XFRM + || ct->tuplehash[dir].tuple.src.u.all != + ct->tuplehash[!dir].tuple.dst.u.all +#endif + ) + return ip_route_me_harder(pskb) == 0 ? ret : NF_DROP; + } + return ret; } static unsigned int @@ -200,7 +258,8 @@ ip_nat_local_fn(unsigned int hooknum, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - u_int32_t saddr, daddr; + struct ip_conntrack *ct; + enum ip_conntrack_info ctinfo; unsigned int ret; /* root is playing with raw sockets. */ @@ -208,14 +267,20 @@ ip_nat_local_fn(unsigned int hooknum, || (*pskb)->nh.iph->ihl * 4 < sizeof(struct iphdr)) return NF_ACCEPT; - saddr = (*pskb)->nh.iph->saddr; - daddr = (*pskb)->nh.iph->daddr; - ret = ip_nat_fn(hooknum, pskb, in, out, okfn); if (ret != NF_DROP && ret != NF_STOLEN - && ((*pskb)->nh.iph->saddr != saddr - || (*pskb)->nh.iph->daddr != daddr)) - return ip_route_me_harder(pskb) == 0 ? ret : NF_DROP; + && (ct = ip_conntrack_get(*pskb, &ctinfo)) != NULL) { + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + + if (ct->tuplehash[dir].tuple.dst.ip != + ct->tuplehash[!dir].tuple.src.ip +#ifdef CONFIG_XFRM + || ct->tuplehash[dir].tuple.dst.u.all != + ct->tuplehash[dir].tuple.src.u.all +#endif + ) + return ip_route_me_harder(pskb) == 0 ? ret : NF_DROP; + } return ret; } @@ -299,14 +364,18 @@ static int init_or_cleanup(int init) { int ret = 0; - need_ip_conntrack(); + need_conntrack(); if (!init) goto cleanup; +#ifdef CONFIG_XFRM + BUG_ON(ip_nat_decode_session != NULL); + ip_nat_decode_session = nat_decode_session; +#endif ret = ip_nat_rule_init(); if (ret < 0) { printk("ip_nat_init: can't setup rules.\n"); - goto cleanup_nothing; + goto cleanup_decode_session; } ret = nf_register_hook(&ip_nat_in_ops); if (ret < 0) { @@ -354,7 +423,11 @@ static int init_or_cleanup(int init) nf_unregister_hook(&ip_nat_in_ops); cleanup_rule_init: ip_nat_rule_cleanup(); - cleanup_nothing: + cleanup_decode_session: +#ifdef CONFIG_XFRM + ip_nat_decode_session = NULL; + synchronize_net(); +#endif return ret; } diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 2a26d167e149..2371b2062c2d 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -2,7 +2,7 @@ * Packet matching code. * * Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling - * Copyright (C) 2000-2004 Netfilter Core Team <coreteam@netfilter.org> + * Copyright (C) 2000-2005 Netfilter Core Team <coreteam@netfilter.org> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -11,16 +11,17 @@ * 19 Jan 2002 Harald Welte <laforge@gnumonks.org> * - increase module usage count as soon as we have rules inside * a table + * 08 Oct 2005 Harald Welte <lafore@netfilter.org> + * - Generalize into "x_tables" layer and "{ip,ip6,arp}_tables" */ #include <linux/config.h> #include <linux/cache.h> +#include <linux/capability.h> #include <linux/skbuff.h> #include <linux/kmod.h> #include <linux/vmalloc.h> #include <linux/netdevice.h> #include <linux/module.h> -#include <linux/tcp.h> -#include <linux/udp.h> #include <linux/icmp.h> #include <net/ip.h> #include <asm/uaccess.h> @@ -29,6 +30,7 @@ #include <linux/err.h> #include <linux/cpumask.h> +#include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv4/ip_tables.h> MODULE_LICENSE("GPL"); @@ -61,14 +63,6 @@ do { \ #else #define IP_NF_ASSERT(x) #endif -#define SMP_ALIGN(x) (((x) + SMP_CACHE_BYTES-1) & ~(SMP_CACHE_BYTES-1)) - -static DECLARE_MUTEX(ipt_mutex); - -/* Must have mutex */ -#define ASSERT_READ_LOCK(x) IP_NF_ASSERT(down_trylock(&ipt_mutex) != 0) -#define ASSERT_WRITE_LOCK(x) IP_NF_ASSERT(down_trylock(&ipt_mutex) != 0) -#include <linux/netfilter_ipv4/listhelp.h> #if 0 /* All the better to debug you with... */ @@ -85,36 +79,6 @@ static DECLARE_MUTEX(ipt_mutex); Hence the start of any table is given by get_table() below. */ -/* The table itself */ -struct ipt_table_info -{ - /* Size per table */ - unsigned int size; - /* Number of entries: FIXME. --RR */ - unsigned int number; - /* Initial number of entries. Needed for module usage count */ - unsigned int initial_entries; - - /* Entry points and underflows */ - unsigned int hook_entry[NF_IP_NUMHOOKS]; - unsigned int underflow[NF_IP_NUMHOOKS]; - - /* ipt_entry tables: one per CPU */ - void *entries[NR_CPUS]; -}; - -static LIST_HEAD(ipt_target); -static LIST_HEAD(ipt_match); -static LIST_HEAD(ipt_tables); -#define SET_COUNTER(c,b,p) do { (c).bcnt = (b); (c).pcnt = (p); } while(0) -#define ADD_COUNTER(c,b,p) do { (c).bcnt += (b); (c).pcnt += (p); } while(0) - -#if 0 -#define down(x) do { printk("DOWN:%u:" #x "\n", __LINE__); down(x); } while(0) -#define down_interruptible(x) ({ int __r; printk("DOWNi:%u:" #x "\n", __LINE__); __r = down_interruptible(x); if (__r != 0) printk("ABORT-DOWNi:%u\n", __LINE__); __r; }) -#define up(x) do { printk("UP:%u:" #x "\n", __LINE__); up(x); } while(0) -#endif - /* Returns whether matches rule or not. */ static inline int ip_packet_match(const struct iphdr *ip, @@ -233,7 +197,8 @@ int do_match(struct ipt_entry_match *m, int *hotdrop) { /* Stop iteration if it doesn't match */ - if (!m->u.kernel.match->match(skb, in, out, m->data, offset, hotdrop)) + if (!m->u.kernel.match->match(skb, in, out, m->data, offset, + skb->nh.iph->ihl*4, hotdrop)) return 1; else return 0; @@ -264,6 +229,7 @@ ipt_do_table(struct sk_buff **pskb, const char *indev, *outdev; void *table_base; struct ipt_entry *e, *back; + struct xt_table_info *private = table->private; /* Initialization */ ip = (*pskb)->nh.iph; @@ -280,24 +246,11 @@ ipt_do_table(struct sk_buff **pskb, read_lock_bh(&table->lock); IP_NF_ASSERT(table->valid_hooks & (1 << hook)); - table_base = (void *)table->private->entries[smp_processor_id()]; - e = get_entry(table_base, table->private->hook_entry[hook]); - -#ifdef CONFIG_NETFILTER_DEBUG - /* Check noone else using our table */ - if (((struct ipt_entry *)table_base)->comefrom != 0xdead57ac - && ((struct ipt_entry *)table_base)->comefrom != 0xeeeeeeec) { - printk("ASSERT: CPU #%u, %s comefrom(%p) = %X\n", - smp_processor_id(), - table->name, - &((struct ipt_entry *)table_base)->comefrom, - ((struct ipt_entry *)table_base)->comefrom); - } - ((struct ipt_entry *)table_base)->comefrom = 0x57acc001; -#endif + table_base = (void *)private->entries[smp_processor_id()]; + e = get_entry(table_base, private->hook_entry[hook]); /* For return from builtin chain */ - back = get_entry(table_base, table->private->underflow[hook]); + back = get_entry(table_base, private->underflow[hook]); do { IP_NF_ASSERT(e); @@ -383,9 +336,6 @@ ipt_do_table(struct sk_buff **pskb, } } while (!hotdrop); -#ifdef CONFIG_NETFILTER_DEBUG - ((struct ipt_entry *)table_base)->comefrom = 0xdead57ac; -#endif read_unlock_bh(&table->lock); #ifdef DEBUG_ALLOW_ALL @@ -397,145 +347,6 @@ ipt_do_table(struct sk_buff **pskb, #endif } -/* - * These are weird, but module loading must not be done with mutex - * held (since they will register), and we have to have a single - * function to use try_then_request_module(). - */ - -/* Find table by name, grabs mutex & ref. Returns ERR_PTR() on error. */ -static inline struct ipt_table *find_table_lock(const char *name) -{ - struct ipt_table *t; - - if (down_interruptible(&ipt_mutex) != 0) - return ERR_PTR(-EINTR); - - list_for_each_entry(t, &ipt_tables, list) - if (strcmp(t->name, name) == 0 && try_module_get(t->me)) - return t; - up(&ipt_mutex); - return NULL; -} - -/* Find match, grabs ref. Returns ERR_PTR() on error. */ -static inline struct ipt_match *find_match(const char *name, u8 revision) -{ - struct ipt_match *m; - int err = 0; - - if (down_interruptible(&ipt_mutex) != 0) - return ERR_PTR(-EINTR); - - list_for_each_entry(m, &ipt_match, list) { - if (strcmp(m->name, name) == 0) { - if (m->revision == revision) { - if (try_module_get(m->me)) { - up(&ipt_mutex); - return m; - } - } else - err = -EPROTOTYPE; /* Found something. */ - } - } - up(&ipt_mutex); - return ERR_PTR(err); -} - -/* Find target, grabs ref. Returns ERR_PTR() on error. */ -static inline struct ipt_target *find_target(const char *name, u8 revision) -{ - struct ipt_target *t; - int err = 0; - - if (down_interruptible(&ipt_mutex) != 0) - return ERR_PTR(-EINTR); - - list_for_each_entry(t, &ipt_target, list) { - if (strcmp(t->name, name) == 0) { - if (t->revision == revision) { - if (try_module_get(t->me)) { - up(&ipt_mutex); - return t; - } - } else - err = -EPROTOTYPE; /* Found something. */ - } - } - up(&ipt_mutex); - return ERR_PTR(err); -} - -struct ipt_target *ipt_find_target(const char *name, u8 revision) -{ - struct ipt_target *target; - - target = try_then_request_module(find_target(name, revision), - "ipt_%s", name); - if (IS_ERR(target) || !target) - return NULL; - return target; -} - -static int match_revfn(const char *name, u8 revision, int *bestp) -{ - struct ipt_match *m; - int have_rev = 0; - - list_for_each_entry(m, &ipt_match, list) { - if (strcmp(m->name, name) == 0) { - if (m->revision > *bestp) - *bestp = m->revision; - if (m->revision == revision) - have_rev = 1; - } - } - return have_rev; -} - -static int target_revfn(const char *name, u8 revision, int *bestp) -{ - struct ipt_target *t; - int have_rev = 0; - - list_for_each_entry(t, &ipt_target, list) { - if (strcmp(t->name, name) == 0) { - if (t->revision > *bestp) - *bestp = t->revision; - if (t->revision == revision) - have_rev = 1; - } - } - return have_rev; -} - -/* Returns true or false (if no such extension at all) */ -static inline int find_revision(const char *name, u8 revision, - int (*revfn)(const char *, u8, int *), - int *err) -{ - int have_rev, best = -1; - - if (down_interruptible(&ipt_mutex) != 0) { - *err = -EINTR; - return 1; - } - have_rev = revfn(name, revision, &best); - up(&ipt_mutex); - - /* Nothing at all? Return 0 to try loading module. */ - if (best == -1) { - *err = -ENOENT; - return 0; - } - - *err = best; - if (!have_rev) - *err = -EPROTONOSUPPORT; - return 1; -} - - /* All zeroes == unconditional rule. */ static inline int unconditional(const struct ipt_ip *ip) @@ -552,7 +363,7 @@ unconditional(const struct ipt_ip *ip) /* Figures out from what hook each rule can be called: returns 0 if there are loops. Puts hook bitmask in comefrom. */ static int -mark_source_chains(struct ipt_table_info *newinfo, +mark_source_chains(struct xt_table_info *newinfo, unsigned int valid_hooks, void *entry0) { unsigned int hook; @@ -698,7 +509,7 @@ check_match(struct ipt_entry_match *m, { struct ipt_match *match; - match = try_then_request_module(find_match(m->u.user.name, + match = try_then_request_module(xt_find_match(AF_INET, m->u.user.name, m->u.user.revision), "ipt_%s", m->u.user.name); if (IS_ERR(match) || !match) { @@ -743,7 +554,8 @@ check_entry(struct ipt_entry *e, const char *name, unsigned int size, goto cleanup_matches; t = ipt_get_target(e); - target = try_then_request_module(find_target(t->u.user.name, + target = try_then_request_module(xt_find_target(AF_INET, + t->u.user.name, t->u.user.revision), "ipt_%s", t->u.user.name); if (IS_ERR(target) || !target) { @@ -780,7 +592,7 @@ check_entry(struct ipt_entry *e, const char *name, unsigned int size, static inline int check_entry_size_and_hooks(struct ipt_entry *e, - struct ipt_table_info *newinfo, + struct xt_table_info *newinfo, unsigned char *base, unsigned char *limit, const unsigned int *hook_entries, @@ -814,7 +626,7 @@ check_entry_size_and_hooks(struct ipt_entry *e, < 0 (not IPT_RETURN). --RR */ /* Clear counters and comefrom */ - e->counters = ((struct ipt_counters) { 0, 0 }); + e->counters = ((struct xt_counters) { 0, 0 }); e->comefrom = 0; (*i)++; @@ -844,7 +656,7 @@ cleanup_entry(struct ipt_entry *e, unsigned int *i) static int translate_table(const char *name, unsigned int valid_hooks, - struct ipt_table_info *newinfo, + struct xt_table_info *newinfo, void *entry0, unsigned int size, unsigned int number, @@ -921,48 +733,10 @@ translate_table(const char *name, return ret; } -static struct ipt_table_info * -replace_table(struct ipt_table *table, - unsigned int num_counters, - struct ipt_table_info *newinfo, - int *error) -{ - struct ipt_table_info *oldinfo; - -#ifdef CONFIG_NETFILTER_DEBUG - { - int cpu; - - for_each_cpu(cpu) { - struct ipt_entry *table_base = newinfo->entries[cpu]; - if (table_base) - table_base->comefrom = 0xdead57ac; - } - } -#endif - - /* Do the substitution. */ - write_lock_bh(&table->lock); - /* Check inside lock: is the old number correct? */ - if (num_counters != table->private->number) { - duprintf("num_counters != table->private->number (%u/%u)\n", - num_counters, table->private->number); - write_unlock_bh(&table->lock); - *error = -EAGAIN; - return NULL; - } - oldinfo = table->private; - table->private = newinfo; - newinfo->initial_entries = oldinfo->initial_entries; - write_unlock_bh(&table->lock); - - return oldinfo; -} - /* Gets counters. */ static inline int add_entry_to_counter(const struct ipt_entry *e, - struct ipt_counters total[], + struct xt_counters total[], unsigned int *i) { ADD_COUNTER(total[*i], e->counters.bcnt, e->counters.pcnt); @@ -983,8 +757,8 @@ set_entry_to_counter(const struct ipt_entry *e, } static void -get_counters(const struct ipt_table_info *t, - struct ipt_counters counters[]) +get_counters(const struct xt_table_info *t, + struct xt_counters counters[]) { unsigned int cpu; unsigned int i; @@ -1023,14 +797,15 @@ copy_entries_to_user(unsigned int total_size, { unsigned int off, num, countersize; struct ipt_entry *e; - struct ipt_counters *counters; + struct xt_counters *counters; + struct xt_table_info *private = table->private; int ret = 0; void *loc_cpu_entry; /* We need atomic snapshot of counters: rest doesn't change (other than comefrom, which userspace doesn't care about). */ - countersize = sizeof(struct ipt_counters) * table->private->number; + countersize = sizeof(struct xt_counters) * private->number; counters = vmalloc_node(countersize, numa_node_id()); if (counters == NULL) @@ -1038,14 +813,14 @@ copy_entries_to_user(unsigned int total_size, /* First, sum counters... */ write_lock_bh(&table->lock); - get_counters(table->private, counters); + get_counters(private, counters); write_unlock_bh(&table->lock); /* choose the copy that is on our node/cpu, ... * This choice is lazy (because current thread is * allowed to migrate to another cpu) */ - loc_cpu_entry = table->private->entries[raw_smp_processor_id()]; + loc_cpu_entry = private->entries[raw_smp_processor_id()]; /* ... then copy entire thing ... */ if (copy_to_user(userptr, loc_cpu_entry, total_size) != 0) { ret = -EFAULT; @@ -1107,74 +882,36 @@ get_entries(const struct ipt_get_entries *entries, int ret; struct ipt_table *t; - t = find_table_lock(entries->name); + t = xt_find_table_lock(AF_INET, entries->name); if (t && !IS_ERR(t)) { + struct xt_table_info *private = t->private; duprintf("t->private->number = %u\n", - t->private->number); - if (entries->size == t->private->size) - ret = copy_entries_to_user(t->private->size, + private->number); + if (entries->size == private->size) + ret = copy_entries_to_user(private->size, t, uptr->entrytable); else { duprintf("get_entries: I've got %u not %u!\n", - t->private->size, + private->size, entries->size); ret = -EINVAL; } module_put(t->me); - up(&ipt_mutex); + xt_table_unlock(t); } else ret = t ? PTR_ERR(t) : -ENOENT; return ret; } -static void free_table_info(struct ipt_table_info *info) -{ - int cpu; - for_each_cpu(cpu) { - if (info->size <= PAGE_SIZE) - kfree(info->entries[cpu]); - else - vfree(info->entries[cpu]); - } - kfree(info); -} - -static struct ipt_table_info *alloc_table_info(unsigned int size) -{ - struct ipt_table_info *newinfo; - int cpu; - - newinfo = kzalloc(sizeof(struct ipt_table_info), GFP_KERNEL); - if (!newinfo) - return NULL; - - newinfo->size = size; - - for_each_cpu(cpu) { - if (size <= PAGE_SIZE) - newinfo->entries[cpu] = kmalloc_node(size, - GFP_KERNEL, - cpu_to_node(cpu)); - else - newinfo->entries[cpu] = vmalloc_node(size, cpu_to_node(cpu)); - if (newinfo->entries[cpu] == 0) { - free_table_info(newinfo); - return NULL; - } - } - - return newinfo; -} - static int do_replace(void __user *user, unsigned int len) { int ret; struct ipt_replace tmp; struct ipt_table *t; - struct ipt_table_info *newinfo, *oldinfo; - struct ipt_counters *counters; + struct xt_table_info *newinfo, *oldinfo; + struct xt_counters *counters; void *loc_cpu_entry, *loc_cpu_old_entry; if (copy_from_user(&tmp, user, sizeof(tmp)) != 0) @@ -1184,11 +921,7 @@ do_replace(void __user *user, unsigned int len) if (len != sizeof(tmp) + tmp.size) return -ENOPROTOOPT; - /* Pedantry: prevent them from hitting BUG() in vmalloc.c --RR */ - if ((SMP_ALIGN(tmp.size) >> PAGE_SHIFT) + 2 > num_physpages) - return -ENOMEM; - - newinfo = alloc_table_info(tmp.size); + newinfo = xt_alloc_table_info(tmp.size); if (!newinfo) return -ENOMEM; @@ -1200,7 +933,7 @@ do_replace(void __user *user, unsigned int len) goto free_newinfo; } - counters = vmalloc(tmp.num_counters * sizeof(struct ipt_counters)); + counters = vmalloc(tmp.num_counters * sizeof(struct xt_counters)); if (!counters) { ret = -ENOMEM; goto free_newinfo; @@ -1214,7 +947,7 @@ do_replace(void __user *user, unsigned int len) duprintf("ip_tables: Translated table\n"); - t = try_then_request_module(find_table_lock(tmp.name), + t = try_then_request_module(xt_find_table_lock(AF_INET, tmp.name), "iptable_%s", tmp.name); if (!t || IS_ERR(t)) { ret = t ? PTR_ERR(t) : -ENOENT; @@ -1229,7 +962,7 @@ do_replace(void __user *user, unsigned int len) goto put_module; } - oldinfo = replace_table(t, tmp.num_counters, newinfo, &ret); + oldinfo = xt_replace_table(t, tmp.num_counters, newinfo, &ret); if (!oldinfo) goto put_module; @@ -1248,23 +981,23 @@ do_replace(void __user *user, unsigned int len) /* Decrease module usage counts and free resource */ loc_cpu_old_entry = oldinfo->entries[raw_smp_processor_id()]; IPT_ENTRY_ITERATE(loc_cpu_old_entry, oldinfo->size, cleanup_entry,NULL); - free_table_info(oldinfo); + xt_free_table_info(oldinfo); if (copy_to_user(tmp.counters, counters, - sizeof(struct ipt_counters) * tmp.num_counters) != 0) + sizeof(struct xt_counters) * tmp.num_counters) != 0) ret = -EFAULT; vfree(counters); - up(&ipt_mutex); + xt_table_unlock(t); return ret; put_module: module_put(t->me); - up(&ipt_mutex); + xt_table_unlock(t); free_newinfo_counters_untrans: IPT_ENTRY_ITERATE(loc_cpu_entry, newinfo->size, cleanup_entry,NULL); free_newinfo_counters: vfree(counters); free_newinfo: - free_table_info(newinfo); + xt_free_table_info(newinfo); return ret; } @@ -1272,7 +1005,7 @@ do_replace(void __user *user, unsigned int len) * and everything is OK. */ static inline int add_counter_to_entry(struct ipt_entry *e, - const struct ipt_counters addme[], + const struct xt_counters addme[], unsigned int *i) { #if 0 @@ -1294,15 +1027,16 @@ static int do_add_counters(void __user *user, unsigned int len) { unsigned int i; - struct ipt_counters_info tmp, *paddc; + struct xt_counters_info tmp, *paddc; struct ipt_table *t; + struct xt_table_info *private; int ret = 0; void *loc_cpu_entry; if (copy_from_user(&tmp, user, sizeof(tmp)) != 0) return -EFAULT; - if (len != sizeof(tmp) + tmp.num_counters*sizeof(struct ipt_counters)) + if (len != sizeof(tmp) + tmp.num_counters*sizeof(struct xt_counters)) return -EINVAL; paddc = vmalloc_node(len, numa_node_id()); @@ -1314,29 +1048,30 @@ do_add_counters(void __user *user, unsigned int len) goto free; } - t = find_table_lock(tmp.name); + t = xt_find_table_lock(AF_INET, tmp.name); if (!t || IS_ERR(t)) { ret = t ? PTR_ERR(t) : -ENOENT; goto free; } write_lock_bh(&t->lock); - if (t->private->number != paddc->num_counters) { + private = t->private; + if (private->number != paddc->num_counters) { ret = -EINVAL; goto unlock_up_free; } i = 0; /* Choose the copy that is on our node */ - loc_cpu_entry = t->private->entries[raw_smp_processor_id()]; + loc_cpu_entry = private->entries[raw_smp_processor_id()]; IPT_ENTRY_ITERATE(loc_cpu_entry, - t->private->size, + private->size, add_counter_to_entry, paddc->counters, &i); unlock_up_free: write_unlock_bh(&t->lock); - up(&ipt_mutex); + xt_table_unlock(t); module_put(t->me); free: vfree(paddc); @@ -1395,25 +1130,26 @@ do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) } name[IPT_TABLE_MAXNAMELEN-1] = '\0'; - t = try_then_request_module(find_table_lock(name), + t = try_then_request_module(xt_find_table_lock(AF_INET, name), "iptable_%s", name); if (t && !IS_ERR(t)) { struct ipt_getinfo info; + struct xt_table_info *private = t->private; info.valid_hooks = t->valid_hooks; - memcpy(info.hook_entry, t->private->hook_entry, + memcpy(info.hook_entry, private->hook_entry, sizeof(info.hook_entry)); - memcpy(info.underflow, t->private->underflow, + memcpy(info.underflow, private->underflow, sizeof(info.underflow)); - info.num_entries = t->private->number; - info.size = t->private->size; + info.num_entries = private->number; + info.size = private->size; memcpy(info.name, name, sizeof(info.name)); if (copy_to_user(user, &info, *len) != 0) ret = -EFAULT; else ret = 0; - up(&ipt_mutex); + xt_table_unlock(t); module_put(t->me); } else ret = t ? PTR_ERR(t) : -ENOENT; @@ -1440,7 +1176,7 @@ do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) case IPT_SO_GET_REVISION_MATCH: case IPT_SO_GET_REVISION_TARGET: { struct ipt_get_revision rev; - int (*revfn)(const char *, u8, int *); + int target; if (*len != sizeof(rev)) { ret = -EINVAL; @@ -1452,12 +1188,13 @@ do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) } if (cmd == IPT_SO_GET_REVISION_TARGET) - revfn = target_revfn; + target = 1; else - revfn = match_revfn; + target = 0; - try_then_request_module(find_revision(rev.name, rev.revision, - revfn, &ret), + try_then_request_module(xt_find_revision(AF_INET, rev.name, + rev.revision, + target, &ret), "ipt_%s", rev.name); break; } @@ -1470,60 +1207,15 @@ do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) return ret; } -/* Registration hooks for targets. */ -int -ipt_register_target(struct ipt_target *target) +int ipt_register_table(struct xt_table *table, const struct ipt_replace *repl) { int ret; - - ret = down_interruptible(&ipt_mutex); - if (ret != 0) - return ret; - list_add(&target->list, &ipt_target); - up(&ipt_mutex); - return ret; -} - -void -ipt_unregister_target(struct ipt_target *target) -{ - down(&ipt_mutex); - LIST_DELETE(&ipt_target, target); - up(&ipt_mutex); -} - -int -ipt_register_match(struct ipt_match *match) -{ - int ret; - - ret = down_interruptible(&ipt_mutex); - if (ret != 0) - return ret; - - list_add(&match->list, &ipt_match); - up(&ipt_mutex); - - return ret; -} - -void -ipt_unregister_match(struct ipt_match *match) -{ - down(&ipt_mutex); - LIST_DELETE(&ipt_match, match); - up(&ipt_mutex); -} - -int ipt_register_table(struct ipt_table *table, const struct ipt_replace *repl) -{ - int ret; - struct ipt_table_info *newinfo; - static struct ipt_table_info bootstrap + struct xt_table_info *newinfo; + static struct xt_table_info bootstrap = { 0, 0, 0, { 0 }, { 0 }, { } }; void *loc_cpu_entry; - newinfo = alloc_table_info(repl->size); + newinfo = xt_alloc_table_info(repl->size); if (!newinfo) return -ENOMEM; @@ -1539,246 +1231,29 @@ int ipt_register_table(struct ipt_table *table, const struct ipt_replace *repl) repl->hook_entry, repl->underflow); if (ret != 0) { - free_table_info(newinfo); + xt_free_table_info(newinfo); return ret; } - ret = down_interruptible(&ipt_mutex); - if (ret != 0) { - free_table_info(newinfo); + if (xt_register_table(table, &bootstrap, newinfo) != 0) { + xt_free_table_info(newinfo); return ret; } - /* Don't autoload: we'd eat our tail... */ - if (list_named_find(&ipt_tables, table->name)) { - ret = -EEXIST; - goto free_unlock; - } - - /* Simplifies replace_table code. */ - table->private = &bootstrap; - if (!replace_table(table, 0, newinfo, &ret)) - goto free_unlock; - - duprintf("table->private->number = %u\n", - table->private->number); - - /* save number of initial entries */ - table->private->initial_entries = table->private->number; - - rwlock_init(&table->lock); - list_prepend(&ipt_tables, table); - - unlock: - up(&ipt_mutex); - return ret; - - free_unlock: - free_table_info(newinfo); - goto unlock; + return 0; } void ipt_unregister_table(struct ipt_table *table) { + struct xt_table_info *private; void *loc_cpu_entry; - down(&ipt_mutex); - LIST_DELETE(&ipt_tables, table); - up(&ipt_mutex); + private = xt_unregister_table(table); /* Decrease module usage counts and free resources */ - loc_cpu_entry = table->private->entries[raw_smp_processor_id()]; - IPT_ENTRY_ITERATE(loc_cpu_entry, table->private->size, - cleanup_entry, NULL); - free_table_info(table->private); -} - -/* Returns 1 if the port is matched by the range, 0 otherwise */ -static inline int -port_match(u_int16_t min, u_int16_t max, u_int16_t port, int invert) -{ - int ret; - - ret = (port >= min && port <= max) ^ invert; - return ret; -} - -static int -tcp_find_option(u_int8_t option, - const struct sk_buff *skb, - unsigned int optlen, - int invert, - int *hotdrop) -{ - /* tcp.doff is only 4 bits, ie. max 15 * 4 bytes */ - u_int8_t _opt[60 - sizeof(struct tcphdr)], *op; - unsigned int i; - - duprintf("tcp_match: finding option\n"); - - if (!optlen) - return invert; - - /* If we don't have the whole header, drop packet. */ - op = skb_header_pointer(skb, - skb->nh.iph->ihl*4 + sizeof(struct tcphdr), - optlen, _opt); - if (op == NULL) { - *hotdrop = 1; - return 0; - } - - for (i = 0; i < optlen; ) { - if (op[i] == option) return !invert; - if (op[i] < 2) i++; - else i += op[i+1]?:1; - } - - return invert; -} - -static int -tcp_match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - int *hotdrop) -{ - struct tcphdr _tcph, *th; - const struct ipt_tcp *tcpinfo = matchinfo; - - if (offset) { - /* To quote Alan: - - Don't allow a fragment of TCP 8 bytes in. Nobody normal - causes this. Its a cracker trying to break in by doing a - flag overwrite to pass the direction checks. - */ - if (offset == 1) { - duprintf("Dropping evil TCP offset=1 frag.\n"); - *hotdrop = 1; - } - /* Must not be a fragment. */ - return 0; - } - -#define FWINVTCP(bool,invflg) ((bool) ^ !!(tcpinfo->invflags & invflg)) - - th = skb_header_pointer(skb, skb->nh.iph->ihl*4, - sizeof(_tcph), &_tcph); - if (th == NULL) { - /* We've been asked to examine this packet, and we - can't. Hence, no choice but to drop. */ - duprintf("Dropping evil TCP offset=0 tinygram.\n"); - *hotdrop = 1; - return 0; - } - - if (!port_match(tcpinfo->spts[0], tcpinfo->spts[1], - ntohs(th->source), - !!(tcpinfo->invflags & IPT_TCP_INV_SRCPT))) - return 0; - if (!port_match(tcpinfo->dpts[0], tcpinfo->dpts[1], - ntohs(th->dest), - !!(tcpinfo->invflags & IPT_TCP_INV_DSTPT))) - return 0; - if (!FWINVTCP((((unsigned char *)th)[13] & tcpinfo->flg_mask) - == tcpinfo->flg_cmp, - IPT_TCP_INV_FLAGS)) - return 0; - if (tcpinfo->option) { - if (th->doff * 4 < sizeof(_tcph)) { - *hotdrop = 1; - return 0; - } - if (!tcp_find_option(tcpinfo->option, skb, - th->doff*4 - sizeof(_tcph), - tcpinfo->invflags & IPT_TCP_INV_OPTION, - hotdrop)) - return 0; - } - return 1; -} - -/* Called when user tries to insert an entry of this type. */ -static int -tcp_checkentry(const char *tablename, - const struct ipt_ip *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - const struct ipt_tcp *tcpinfo = matchinfo; - - /* Must specify proto == TCP, and no unknown invflags */ - return ip->proto == IPPROTO_TCP - && !(ip->invflags & IPT_INV_PROTO) - && matchsize == IPT_ALIGN(sizeof(struct ipt_tcp)) - && !(tcpinfo->invflags & ~IPT_TCP_INV_MASK); -} - -static int -udp_match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - int *hotdrop) -{ - struct udphdr _udph, *uh; - const struct ipt_udp *udpinfo = matchinfo; - - /* Must not be a fragment. */ - if (offset) - return 0; - - uh = skb_header_pointer(skb, skb->nh.iph->ihl*4, - sizeof(_udph), &_udph); - if (uh == NULL) { - /* We've been asked to examine this packet, and we - can't. Hence, no choice but to drop. */ - duprintf("Dropping evil UDP tinygram.\n"); - *hotdrop = 1; - return 0; - } - - return port_match(udpinfo->spts[0], udpinfo->spts[1], - ntohs(uh->source), - !!(udpinfo->invflags & IPT_UDP_INV_SRCPT)) - && port_match(udpinfo->dpts[0], udpinfo->dpts[1], - ntohs(uh->dest), - !!(udpinfo->invflags & IPT_UDP_INV_DSTPT)); -} - -/* Called when user tries to insert an entry of this type. */ -static int -udp_checkentry(const char *tablename, - const struct ipt_ip *ip, - void *matchinfo, - unsigned int matchinfosize, - unsigned int hook_mask) -{ - const struct ipt_udp *udpinfo = matchinfo; - - /* Must specify proto == UDP, and no unknown invflags */ - if (ip->proto != IPPROTO_UDP || (ip->invflags & IPT_INV_PROTO)) { - duprintf("ipt_udp: Protocol %u != %u\n", ip->proto, - IPPROTO_UDP); - return 0; - } - if (matchinfosize != IPT_ALIGN(sizeof(struct ipt_udp))) { - duprintf("ipt_udp: matchsize %u != %u\n", - matchinfosize, IPT_ALIGN(sizeof(struct ipt_udp))); - return 0; - } - if (udpinfo->invflags & ~IPT_UDP_INV_MASK) { - duprintf("ipt_udp: unknown flags %X\n", - udpinfo->invflags); - return 0; - } - - return 1; + loc_cpu_entry = private->entries[raw_smp_processor_id()]; + IPT_ENTRY_ITERATE(loc_cpu_entry, private->size, cleanup_entry, NULL); + xt_free_table_info(private); } /* Returns 1 if the type and code is matched by the range, 0 otherwise */ @@ -1797,6 +1272,7 @@ icmp_match(const struct sk_buff *skb, const struct net_device *out, const void *matchinfo, int offset, + unsigned int protoff, int *hotdrop) { struct icmphdr _icmph, *ic; @@ -1806,8 +1282,7 @@ icmp_match(const struct sk_buff *skb, if (offset) return 0; - ic = skb_header_pointer(skb, skb->nh.iph->ihl*4, - sizeof(_icmph), &_icmph); + ic = skb_header_pointer(skb, protoff, sizeof(_icmph), &_icmph); if (ic == NULL) { /* We've been asked to examine this packet, and we * can't. Hence, no choice but to drop. @@ -1827,11 +1302,12 @@ icmp_match(const struct sk_buff *skb, /* Called when user tries to insert an entry of this type. */ static int icmp_checkentry(const char *tablename, - const struct ipt_ip *ip, + const void *info, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { + const struct ipt_ip *ip = info; const struct ipt_icmp *icmpinfo = matchinfo; /* Must specify proto == ICMP, and no unknown invflags */ @@ -1861,123 +1337,22 @@ static struct nf_sockopt_ops ipt_sockopts = { .get = do_ipt_get_ctl, }; -static struct ipt_match tcp_matchstruct = { - .name = "tcp", - .match = &tcp_match, - .checkentry = &tcp_checkentry, -}; - -static struct ipt_match udp_matchstruct = { - .name = "udp", - .match = &udp_match, - .checkentry = &udp_checkentry, -}; - static struct ipt_match icmp_matchstruct = { .name = "icmp", .match = &icmp_match, .checkentry = &icmp_checkentry, }; -#ifdef CONFIG_PROC_FS -static inline int print_name(const char *i, - off_t start_offset, char *buffer, int length, - off_t *pos, unsigned int *count) -{ - if ((*count)++ >= start_offset) { - unsigned int namelen; - - namelen = sprintf(buffer + *pos, "%s\n", - i + sizeof(struct list_head)); - if (*pos + namelen > length) { - /* Stop iterating */ - return 1; - } - *pos += namelen; - } - return 0; -} - -static inline int print_target(const struct ipt_target *t, - off_t start_offset, char *buffer, int length, - off_t *pos, unsigned int *count) -{ - if (t == &ipt_standard_target || t == &ipt_error_target) - return 0; - return print_name((char *)t, start_offset, buffer, length, pos, count); -} - -static int ipt_get_tables(char *buffer, char **start, off_t offset, int length) -{ - off_t pos = 0; - unsigned int count = 0; - - if (down_interruptible(&ipt_mutex) != 0) - return 0; - - LIST_FIND(&ipt_tables, print_name, void *, - offset, buffer, length, &pos, &count); - - up(&ipt_mutex); - - /* `start' hack - see fs/proc/generic.c line ~105 */ - *start=(char *)((unsigned long)count-offset); - return pos; -} - -static int ipt_get_targets(char *buffer, char **start, off_t offset, int length) -{ - off_t pos = 0; - unsigned int count = 0; - - if (down_interruptible(&ipt_mutex) != 0) - return 0; - - LIST_FIND(&ipt_target, print_target, struct ipt_target *, - offset, buffer, length, &pos, &count); - - up(&ipt_mutex); - - *start = (char *)((unsigned long)count - offset); - return pos; -} - -static int ipt_get_matches(char *buffer, char **start, off_t offset, int length) -{ - off_t pos = 0; - unsigned int count = 0; - - if (down_interruptible(&ipt_mutex) != 0) - return 0; - - LIST_FIND(&ipt_match, print_name, void *, - offset, buffer, length, &pos, &count); - - up(&ipt_mutex); - - *start = (char *)((unsigned long)count - offset); - return pos; -} - -static const struct { char *name; get_info_t *get_info; } ipt_proc_entry[] = -{ { "ip_tables_names", ipt_get_tables }, - { "ip_tables_targets", ipt_get_targets }, - { "ip_tables_matches", ipt_get_matches }, - { NULL, NULL} }; -#endif /*CONFIG_PROC_FS*/ - static int __init init(void) { int ret; + xt_proto_init(AF_INET); + /* Noone else will be downing sem now, so we won't sleep */ - down(&ipt_mutex); - list_append(&ipt_target, &ipt_standard_target); - list_append(&ipt_target, &ipt_error_target); - list_append(&ipt_match, &tcp_matchstruct); - list_append(&ipt_match, &udp_matchstruct); - list_append(&ipt_match, &icmp_matchstruct); - up(&ipt_mutex); + xt_register_target(AF_INET, &ipt_standard_target); + xt_register_target(AF_INET, &ipt_error_target); + xt_register_match(AF_INET, &icmp_matchstruct); /* Register setsockopt */ ret = nf_register_sockopt(&ipt_sockopts); @@ -1986,49 +1361,23 @@ static int __init init(void) return ret; } -#ifdef CONFIG_PROC_FS - { - struct proc_dir_entry *proc; - int i; - - for (i = 0; ipt_proc_entry[i].name; i++) { - proc = proc_net_create(ipt_proc_entry[i].name, 0, - ipt_proc_entry[i].get_info); - if (!proc) { - while (--i >= 0) - proc_net_remove(ipt_proc_entry[i].name); - nf_unregister_sockopt(&ipt_sockopts); - return -ENOMEM; - } - proc->owner = THIS_MODULE; - } - } -#endif - - printk("ip_tables: (C) 2000-2002 Netfilter core team\n"); + printk("ip_tables: (C) 2000-2006 Netfilter Core Team\n"); return 0; } static void __exit fini(void) { nf_unregister_sockopt(&ipt_sockopts); -#ifdef CONFIG_PROC_FS - { - int i; - for (i = 0; ipt_proc_entry[i].name; i++) - proc_net_remove(ipt_proc_entry[i].name); - } -#endif + + xt_unregister_match(AF_INET, &icmp_matchstruct); + xt_unregister_target(AF_INET, &ipt_error_target); + xt_unregister_target(AF_INET, &ipt_standard_target); + + xt_proto_fini(AF_INET); } EXPORT_SYMBOL(ipt_register_table); EXPORT_SYMBOL(ipt_unregister_table); -EXPORT_SYMBOL(ipt_register_match); -EXPORT_SYMBOL(ipt_unregister_match); EXPORT_SYMBOL(ipt_do_table); -EXPORT_SYMBOL(ipt_register_target); -EXPORT_SYMBOL(ipt_unregister_target); -EXPORT_SYMBOL(ipt_find_target); - module_init(init); module_exit(fini); diff --git a/net/ipv4/netfilter/ipt_CLASSIFY.c b/net/ipv4/netfilter/ipt_CLASSIFY.c deleted file mode 100644 index dab78d8bd494..000000000000 --- a/net/ipv4/netfilter/ipt_CLASSIFY.c +++ /dev/null @@ -1,90 +0,0 @@ -/* - * This is a module which is used for setting the skb->priority field - * of an skb for qdisc classification. - */ - -/* (C) 2001-2002 Patrick McHardy <kaber@trash.net> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/module.h> -#include <linux/skbuff.h> -#include <linux/ip.h> -#include <net/checksum.h> - -#include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netfilter_ipv4/ipt_CLASSIFY.h> - -MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); -MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("iptables qdisc classification target module"); - -static unsigned int -target(struct sk_buff **pskb, - const struct net_device *in, - const struct net_device *out, - unsigned int hooknum, - const void *targinfo, - void *userinfo) -{ - const struct ipt_classify_target_info *clinfo = targinfo; - - if((*pskb)->priority != clinfo->priority) - (*pskb)->priority = clinfo->priority; - - return IPT_CONTINUE; -} - -static int -checkentry(const char *tablename, - const struct ipt_entry *e, - void *targinfo, - unsigned int targinfosize, - unsigned int hook_mask) -{ - if (targinfosize != IPT_ALIGN(sizeof(struct ipt_classify_target_info))){ - printk(KERN_ERR "CLASSIFY: invalid size (%u != %Zu).\n", - targinfosize, - IPT_ALIGN(sizeof(struct ipt_classify_target_info))); - return 0; - } - - if (hook_mask & ~((1 << NF_IP_LOCAL_OUT) | (1 << NF_IP_FORWARD) | - (1 << NF_IP_POST_ROUTING))) { - printk(KERN_ERR "CLASSIFY: only valid in LOCAL_OUT, FORWARD " - "and POST_ROUTING.\n"); - return 0; - } - - if (strcmp(tablename, "mangle") != 0) { - printk(KERN_ERR "CLASSIFY: can only be called from " - "\"mangle\" table, not \"%s\".\n", - tablename); - return 0; - } - - return 1; -} - -static struct ipt_target ipt_classify_reg = { - .name = "CLASSIFY", - .target = target, - .checkentry = checkentry, - .me = THIS_MODULE, -}; - -static int __init init(void) -{ - return ipt_register_target(&ipt_classify_reg); -} - -static void __exit fini(void) -{ - ipt_unregister_target(&ipt_classify_reg); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 45c52d8f4d99..d9bc971f03af 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -379,12 +379,13 @@ target(struct sk_buff **pskb, static int checkentry(const char *tablename, - const struct ipt_entry *e, + const void *e_void, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) { struct ipt_clusterip_tgt_info *cipinfo = targinfo; + const struct ipt_entry *e = e_void; struct clusterip_config *config; diff --git a/net/ipv4/netfilter/ipt_CONNMARK.c b/net/ipv4/netfilter/ipt_CONNMARK.c deleted file mode 100644 index 8acac5a40a92..000000000000 --- a/net/ipv4/netfilter/ipt_CONNMARK.c +++ /dev/null @@ -1,122 +0,0 @@ -/* This kernel module is used to modify the connection mark values, or - * to optionally restore the skb nfmark from the connection mark - * - * Copyright (C) 2002,2004 MARA Systems AB <http://www.marasystems.com> - * by Henrik Nordstrom <hno@marasystems.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ -#include <linux/module.h> -#include <linux/skbuff.h> -#include <linux/ip.h> -#include <net/checksum.h> - -MODULE_AUTHOR("Henrik Nordstrom <hno@marasytems.com>"); -MODULE_DESCRIPTION("IP tables CONNMARK matching module"); -MODULE_LICENSE("GPL"); - -#include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netfilter_ipv4/ipt_CONNMARK.h> -#include <net/netfilter/nf_conntrack_compat.h> - -static unsigned int -target(struct sk_buff **pskb, - const struct net_device *in, - const struct net_device *out, - unsigned int hooknum, - const void *targinfo, - void *userinfo) -{ - const struct ipt_connmark_target_info *markinfo = targinfo; - u_int32_t diff; - u_int32_t nfmark; - u_int32_t newmark; - u_int32_t ctinfo; - u_int32_t *ctmark = nf_ct_get_mark(*pskb, &ctinfo); - - if (ctmark) { - switch(markinfo->mode) { - case IPT_CONNMARK_SET: - newmark = (*ctmark & ~markinfo->mask) | markinfo->mark; - if (newmark != *ctmark) - *ctmark = newmark; - break; - case IPT_CONNMARK_SAVE: - newmark = (*ctmark & ~markinfo->mask) | ((*pskb)->nfmark & markinfo->mask); - if (*ctmark != newmark) - *ctmark = newmark; - break; - case IPT_CONNMARK_RESTORE: - nfmark = (*pskb)->nfmark; - diff = (*ctmark ^ nfmark) & markinfo->mask; - if (diff != 0) - (*pskb)->nfmark = nfmark ^ diff; - break; - } - } - - return IPT_CONTINUE; -} - -static int -checkentry(const char *tablename, - const struct ipt_entry *e, - void *targinfo, - unsigned int targinfosize, - unsigned int hook_mask) -{ - struct ipt_connmark_target_info *matchinfo = targinfo; - if (targinfosize != IPT_ALIGN(sizeof(struct ipt_connmark_target_info))) { - printk(KERN_WARNING "CONNMARK: targinfosize %u != %Zu\n", - targinfosize, - IPT_ALIGN(sizeof(struct ipt_connmark_target_info))); - return 0; - } - - if (matchinfo->mode == IPT_CONNMARK_RESTORE) { - if (strcmp(tablename, "mangle") != 0) { - printk(KERN_WARNING "CONNMARK: restore can only be called from \"mangle\" table, not \"%s\"\n", tablename); - return 0; - } - } - - if (matchinfo->mark > 0xffffffff || matchinfo->mask > 0xffffffff) { - printk(KERN_WARNING "CONNMARK: Only supports 32bit mark\n"); - return 0; - } - - return 1; -} - -static struct ipt_target ipt_connmark_reg = { - .name = "CONNMARK", - .target = &target, - .checkentry = &checkentry, - .me = THIS_MODULE -}; - -static int __init init(void) -{ - need_ip_conntrack(); - return ipt_register_target(&ipt_connmark_reg); -} - -static void __exit fini(void) -{ - ipt_unregister_target(&ipt_connmark_reg); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv4/netfilter/ipt_DSCP.c b/net/ipv4/netfilter/ipt_DSCP.c index 6e319570a28c..898cdf79ce18 100644 --- a/net/ipv4/netfilter/ipt_DSCP.c +++ b/net/ipv4/netfilter/ipt_DSCP.c @@ -57,7 +57,7 @@ target(struct sk_buff **pskb, static int checkentry(const char *tablename, - const struct ipt_entry *e, + const void *e_void, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) diff --git a/net/ipv4/netfilter/ipt_ECN.c b/net/ipv4/netfilter/ipt_ECN.c index a1319693f648..706445426a6d 100644 --- a/net/ipv4/netfilter/ipt_ECN.c +++ b/net/ipv4/netfilter/ipt_ECN.c @@ -113,12 +113,13 @@ target(struct sk_buff **pskb, static int checkentry(const char *tablename, - const struct ipt_entry *e, + const void *e_void, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) { const struct ipt_ECN_info *einfo = (struct ipt_ECN_info *)targinfo; + const struct ipt_entry *e = e_void; if (targinfosize != IPT_ALIGN(sizeof(struct ipt_ECN_info))) { printk(KERN_WARNING "ECN: targinfosize %u != %Zu\n", diff --git a/net/ipv4/netfilter/ipt_LOG.c b/net/ipv4/netfilter/ipt_LOG.c index 30be0f1dae37..6606ddb66a29 100644 --- a/net/ipv4/netfilter/ipt_LOG.c +++ b/net/ipv4/netfilter/ipt_LOG.c @@ -431,7 +431,7 @@ ipt_log_target(struct sk_buff **pskb, } static int ipt_log_checkentry(const char *tablename, - const struct ipt_entry *e, + const void *e, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) diff --git a/net/ipv4/netfilter/ipt_MARK.c b/net/ipv4/netfilter/ipt_MARK.c deleted file mode 100644 index 52b4f2c296bf..000000000000 --- a/net/ipv4/netfilter/ipt_MARK.c +++ /dev/null @@ -1,172 +0,0 @@ -/* This is a module which is used for setting the NFMARK field of an skb. */ - -/* (C) 1999-2001 Marc Boucher <marc@mbsi.ca> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/module.h> -#include <linux/skbuff.h> -#include <linux/ip.h> -#include <net/checksum.h> - -#include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netfilter_ipv4/ipt_MARK.h> - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Marc Boucher <marc@mbsi.ca>"); -MODULE_DESCRIPTION("iptables MARK modification module"); - -static unsigned int -target_v0(struct sk_buff **pskb, - const struct net_device *in, - const struct net_device *out, - unsigned int hooknum, - const void *targinfo, - void *userinfo) -{ - const struct ipt_mark_target_info *markinfo = targinfo; - - if((*pskb)->nfmark != markinfo->mark) - (*pskb)->nfmark = markinfo->mark; - - return IPT_CONTINUE; -} - -static unsigned int -target_v1(struct sk_buff **pskb, - const struct net_device *in, - const struct net_device *out, - unsigned int hooknum, - const void *targinfo, - void *userinfo) -{ - const struct ipt_mark_target_info_v1 *markinfo = targinfo; - int mark = 0; - - switch (markinfo->mode) { - case IPT_MARK_SET: - mark = markinfo->mark; - break; - - case IPT_MARK_AND: - mark = (*pskb)->nfmark & markinfo->mark; - break; - - case IPT_MARK_OR: - mark = (*pskb)->nfmark | markinfo->mark; - break; - } - - if((*pskb)->nfmark != mark) - (*pskb)->nfmark = mark; - - return IPT_CONTINUE; -} - - -static int -checkentry_v0(const char *tablename, - const struct ipt_entry *e, - void *targinfo, - unsigned int targinfosize, - unsigned int hook_mask) -{ - struct ipt_mark_target_info *markinfo = targinfo; - - if (targinfosize != IPT_ALIGN(sizeof(struct ipt_mark_target_info))) { - printk(KERN_WARNING "MARK: targinfosize %u != %Zu\n", - targinfosize, - IPT_ALIGN(sizeof(struct ipt_mark_target_info))); - return 0; - } - - if (strcmp(tablename, "mangle") != 0) { - printk(KERN_WARNING "MARK: can only be called from \"mangle\" table, not \"%s\"\n", tablename); - return 0; - } - - if (markinfo->mark > 0xffffffff) { - printk(KERN_WARNING "MARK: Only supports 32bit wide mark\n"); - return 0; - } - - return 1; -} - -static int -checkentry_v1(const char *tablename, - const struct ipt_entry *e, - void *targinfo, - unsigned int targinfosize, - unsigned int hook_mask) -{ - struct ipt_mark_target_info_v1 *markinfo = targinfo; - - if (targinfosize != IPT_ALIGN(sizeof(struct ipt_mark_target_info_v1))){ - printk(KERN_WARNING "MARK: targinfosize %u != %Zu\n", - targinfosize, - IPT_ALIGN(sizeof(struct ipt_mark_target_info_v1))); - return 0; - } - - if (strcmp(tablename, "mangle") != 0) { - printk(KERN_WARNING "MARK: can only be called from \"mangle\" table, not \"%s\"\n", tablename); - return 0; - } - - if (markinfo->mode != IPT_MARK_SET - && markinfo->mode != IPT_MARK_AND - && markinfo->mode != IPT_MARK_OR) { - printk(KERN_WARNING "MARK: unknown mode %u\n", - markinfo->mode); - return 0; - } - - if (markinfo->mark > 0xffffffff) { - printk(KERN_WARNING "MARK: Only supports 32bit wide mark\n"); - return 0; - } - - return 1; -} - -static struct ipt_target ipt_mark_reg_v0 = { - .name = "MARK", - .target = target_v0, - .checkentry = checkentry_v0, - .me = THIS_MODULE, - .revision = 0, -}; - -static struct ipt_target ipt_mark_reg_v1 = { - .name = "MARK", - .target = target_v1, - .checkentry = checkentry_v1, - .me = THIS_MODULE, - .revision = 1, -}; - -static int __init init(void) -{ - int err; - - err = ipt_register_target(&ipt_mark_reg_v0); - if (!err) { - err = ipt_register_target(&ipt_mark_reg_v1); - if (err) - ipt_unregister_target(&ipt_mark_reg_v0); - } - return err; -} - -static void __exit fini(void) -{ - ipt_unregister_target(&ipt_mark_reg_v0); - ipt_unregister_target(&ipt_mark_reg_v1); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c index 27860510ca6d..12c56d3343ca 100644 --- a/net/ipv4/netfilter/ipt_MASQUERADE.c +++ b/net/ipv4/netfilter/ipt_MASQUERADE.c @@ -40,7 +40,7 @@ static DEFINE_RWLOCK(masq_lock); /* FIXME: Multiple targets. --RR */ static int masquerade_check(const char *tablename, - const struct ipt_entry *e, + const void *e, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) diff --git a/net/ipv4/netfilter/ipt_NETMAP.c b/net/ipv4/netfilter/ipt_NETMAP.c index e6e7b6095363..b074467fe67b 100644 --- a/net/ipv4/netfilter/ipt_NETMAP.c +++ b/net/ipv4/netfilter/ipt_NETMAP.c @@ -31,7 +31,7 @@ MODULE_DESCRIPTION("iptables 1:1 NAT mapping of IP networks target"); static int check(const char *tablename, - const struct ipt_entry *e, + const void *e, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) diff --git a/net/ipv4/netfilter/ipt_NFQUEUE.c b/net/ipv4/netfilter/ipt_NFQUEUE.c deleted file mode 100644 index 3cedc9be8807..000000000000 --- a/net/ipv4/netfilter/ipt_NFQUEUE.c +++ /dev/null @@ -1,70 +0,0 @@ -/* iptables module for using new netfilter netlink queue - * - * (C) 2005 by Harald Welte <laforge@netfilter.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - */ - -#include <linux/module.h> -#include <linux/skbuff.h> - -#include <linux/netfilter.h> -#include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netfilter_ipv4/ipt_NFQUEUE.h> - -MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); -MODULE_DESCRIPTION("iptables NFQUEUE target"); -MODULE_LICENSE("GPL"); - -static unsigned int -target(struct sk_buff **pskb, - const struct net_device *in, - const struct net_device *out, - unsigned int hooknum, - const void *targinfo, - void *userinfo) -{ - const struct ipt_NFQ_info *tinfo = targinfo; - - return NF_QUEUE_NR(tinfo->queuenum); -} - -static int -checkentry(const char *tablename, - const struct ipt_entry *e, - void *targinfo, - unsigned int targinfosize, - unsigned int hook_mask) -{ - if (targinfosize != IPT_ALIGN(sizeof(struct ipt_NFQ_info))) { - printk(KERN_WARNING "NFQUEUE: targinfosize %u != %Zu\n", - targinfosize, - IPT_ALIGN(sizeof(struct ipt_NFQ_info))); - return 0; - } - - return 1; -} - -static struct ipt_target ipt_NFQ_reg = { - .name = "NFQUEUE", - .target = target, - .checkentry = checkentry, - .me = THIS_MODULE, -}; - -static int __init init(void) -{ - return ipt_register_target(&ipt_NFQ_reg); -} - -static void __exit fini(void) -{ - ipt_unregister_target(&ipt_NFQ_reg); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv4/netfilter/ipt_NOTRACK.c b/net/ipv4/netfilter/ipt_NOTRACK.c deleted file mode 100644 index e3c69d072c6e..000000000000 --- a/net/ipv4/netfilter/ipt_NOTRACK.c +++ /dev/null @@ -1,76 +0,0 @@ -/* This is a module which is used for setting up fake conntracks - * on packets so that they are not seen by the conntrack/NAT code. - */ -#include <linux/module.h> -#include <linux/skbuff.h> - -#include <linux/netfilter_ipv4/ip_tables.h> -#include <net/netfilter/nf_conntrack_compat.h> - -static unsigned int -target(struct sk_buff **pskb, - const struct net_device *in, - const struct net_device *out, - unsigned int hooknum, - const void *targinfo, - void *userinfo) -{ - /* Previously seen (loopback)? Ignore. */ - if ((*pskb)->nfct != NULL) - return IPT_CONTINUE; - - /* Attach fake conntrack entry. - If there is a real ct entry correspondig to this packet, - it'll hang aroun till timing out. We don't deal with it - for performance reasons. JK */ - nf_ct_untrack(*pskb); - (*pskb)->nfctinfo = IP_CT_NEW; - nf_conntrack_get((*pskb)->nfct); - - return IPT_CONTINUE; -} - -static int -checkentry(const char *tablename, - const struct ipt_entry *e, - void *targinfo, - unsigned int targinfosize, - unsigned int hook_mask) -{ - if (targinfosize != 0) { - printk(KERN_WARNING "NOTRACK: targinfosize %u != 0\n", - targinfosize); - return 0; - } - - if (strcmp(tablename, "raw") != 0) { - printk(KERN_WARNING "NOTRACK: can only be called from \"raw\" table, not \"%s\"\n", tablename); - return 0; - } - - return 1; -} - -static struct ipt_target ipt_notrack_reg = { - .name = "NOTRACK", - .target = target, - .checkentry = checkentry, - .me = THIS_MODULE -}; - -static int __init init(void) -{ - if (ipt_register_target(&ipt_notrack_reg)) - return -EINVAL; - - return 0; -} - -static void __exit fini(void) -{ - ipt_unregister_target(&ipt_notrack_reg); -} - -module_init(init); -module_exit(fini); -MODULE_LICENSE("GPL"); diff --git a/net/ipv4/netfilter/ipt_REDIRECT.c b/net/ipv4/netfilter/ipt_REDIRECT.c index 5245bfd33d52..140be51f2f01 100644 --- a/net/ipv4/netfilter/ipt_REDIRECT.c +++ b/net/ipv4/netfilter/ipt_REDIRECT.c @@ -33,7 +33,7 @@ MODULE_DESCRIPTION("iptables REDIRECT target module"); /* FIXME: Take multiple ranges --RR */ static int redirect_check(const char *tablename, - const struct ipt_entry *e, + const void *e, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c index 6693526ae128..3eb47aae78c5 100644 --- a/net/ipv4/netfilter/ipt_REJECT.c +++ b/net/ipv4/netfilter/ipt_REJECT.c @@ -282,12 +282,13 @@ static unsigned int reject(struct sk_buff **pskb, } static int check(const char *tablename, - const struct ipt_entry *e, + const void *e_void, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) { const struct ipt_reject_info *rejinfo = targinfo; + const struct ipt_entry *e = e_void; if (targinfosize != IPT_ALIGN(sizeof(struct ipt_reject_info))) { DEBUGP("REJECT: targinfosize %u != 0\n", targinfosize); diff --git a/net/ipv4/netfilter/ipt_SAME.c b/net/ipv4/netfilter/ipt_SAME.c index 7a0536d864ac..a22de59bba0e 100644 --- a/net/ipv4/netfilter/ipt_SAME.c +++ b/net/ipv4/netfilter/ipt_SAME.c @@ -49,7 +49,7 @@ MODULE_DESCRIPTION("iptables special SNAT module for consistent sourceip"); static int same_check(const char *tablename, - const struct ipt_entry *e, + const void *e, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) diff --git a/net/ipv4/netfilter/ipt_TCPMSS.c b/net/ipv4/netfilter/ipt_TCPMSS.c index 8db70d6908c3..c122841e182c 100644 --- a/net/ipv4/netfilter/ipt_TCPMSS.c +++ b/net/ipv4/netfilter/ipt_TCPMSS.c @@ -210,12 +210,13 @@ static inline int find_syn_match(const struct ipt_entry_match *m) /* Must specify -p tcp --syn/--tcp-flags SYN */ static int ipt_tcpmss_checkentry(const char *tablename, - const struct ipt_entry *e, + const void *e_void, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) { const struct ipt_tcpmss_info *tcpmssinfo = targinfo; + const struct ipt_entry *e = e_void; if (targinfosize != IPT_ALIGN(sizeof(struct ipt_tcpmss_info))) { DEBUGP("ipt_tcpmss_checkentry: targinfosize %u != %u\n", diff --git a/net/ipv4/netfilter/ipt_TOS.c b/net/ipv4/netfilter/ipt_TOS.c index deadb36d4428..3a44a56db239 100644 --- a/net/ipv4/netfilter/ipt_TOS.c +++ b/net/ipv4/netfilter/ipt_TOS.c @@ -52,7 +52,7 @@ target(struct sk_buff **pskb, static int checkentry(const char *tablename, - const struct ipt_entry *e, + const void *e_void, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) diff --git a/net/ipv4/netfilter/ipt_TTL.c b/net/ipv4/netfilter/ipt_TTL.c index b9ae6a9382f3..b769eb231970 100644 --- a/net/ipv4/netfilter/ipt_TTL.c +++ b/net/ipv4/netfilter/ipt_TTL.c @@ -66,7 +66,7 @@ ipt_ttl_target(struct sk_buff **pskb, const struct net_device *in, } static int ipt_ttl_checkentry(const char *tablename, - const struct ipt_entry *e, + const void *e, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c index 38641cd06123..641dbc477650 100644 --- a/net/ipv4/netfilter/ipt_ULOG.c +++ b/net/ipv4/netfilter/ipt_ULOG.c @@ -330,7 +330,7 @@ static void ipt_logfn(unsigned int pf, } static int ipt_ulog_checkentry(const char *tablename, - const struct ipt_entry *e, + const void *e, void *targinfo, unsigned int targinfosize, unsigned int hookmask) diff --git a/net/ipv4/netfilter/ipt_addrtype.c b/net/ipv4/netfilter/ipt_addrtype.c index e19c2a52d00c..d6b83a976518 100644 --- a/net/ipv4/netfilter/ipt_addrtype.c +++ b/net/ipv4/netfilter/ipt_addrtype.c @@ -29,7 +29,7 @@ static inline int match_type(u_int32_t addr, u_int16_t mask) static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, const void *matchinfo, - int offset, int *hotdrop) + int offset, unsigned int protoff, int *hotdrop) { const struct ipt_addrtype_info *info = matchinfo; const struct iphdr *iph = skb->nh.iph; @@ -43,7 +43,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, return ret; } -static int checkentry(const char *tablename, const struct ipt_ip *ip, +static int checkentry(const char *tablename, const void *ip, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { diff --git a/net/ipv4/netfilter/ipt_ah.c b/net/ipv4/netfilter/ipt_ah.c index a0fea847cb72..144adfec13cc 100644 --- a/net/ipv4/netfilter/ipt_ah.c +++ b/net/ipv4/netfilter/ipt_ah.c @@ -41,6 +41,7 @@ match(const struct sk_buff *skb, const struct net_device *out, const void *matchinfo, int offset, + unsigned int protoff, int *hotdrop) { struct ip_auth_hdr _ahdr, *ah; @@ -50,7 +51,7 @@ match(const struct sk_buff *skb, if (offset) return 0; - ah = skb_header_pointer(skb, skb->nh.iph->ihl * 4, + ah = skb_header_pointer(skb, protoff, sizeof(_ahdr), &_ahdr); if (ah == NULL) { /* We've been asked to examine this packet, and we @@ -69,12 +70,13 @@ match(const struct sk_buff *skb, /* Called when user tries to insert an entry of this type. */ static int checkentry(const char *tablename, - const struct ipt_ip *ip, + const void *ip_void, void *matchinfo, unsigned int matchinfosize, unsigned int hook_mask) { const struct ipt_ah *ahinfo = matchinfo; + const struct ipt_ip *ip = ip_void; /* Must specify proto == AH, and no unknown invflags */ if (ip->proto != IPPROTO_AH || (ip->invflags & IPT_INV_PROTO)) { diff --git a/net/ipv4/netfilter/ipt_comment.c b/net/ipv4/netfilter/ipt_comment.c deleted file mode 100644 index 6b76a1ea5245..000000000000 --- a/net/ipv4/netfilter/ipt_comment.c +++ /dev/null @@ -1,59 +0,0 @@ -/* - * Implements a dummy match to allow attaching comments to rules - * - * 2003-05-13 Brad Fisher (brad@info-link.net) - */ - -#include <linux/module.h> -#include <linux/skbuff.h> -#include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netfilter_ipv4/ipt_comment.h> - -MODULE_AUTHOR("Brad Fisher <brad@info-link.net>"); -MODULE_DESCRIPTION("iptables comment match module"); -MODULE_LICENSE("GPL"); - -static int -match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - int *hotdrop) -{ - /* We always match */ - return 1; -} - -static int -checkentry(const char *tablename, - const struct ipt_ip *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - /* Check the size */ - if (matchsize != IPT_ALIGN(sizeof(struct ipt_comment_info))) - return 0; - return 1; -} - -static struct ipt_match comment_match = { - .name = "comment", - .match = match, - .checkentry = checkentry, - .me = THIS_MODULE -}; - -static int __init init(void) -{ - return ipt_register_match(&comment_match); -} - -static void __exit fini(void) -{ - ipt_unregister_match(&comment_match); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv4/netfilter/ipt_connbytes.c b/net/ipv4/netfilter/ipt_connbytes.c deleted file mode 100644 index d68a048b7176..000000000000 --- a/net/ipv4/netfilter/ipt_connbytes.c +++ /dev/null @@ -1,161 +0,0 @@ -/* Kernel module to match connection tracking byte counter. - * GPL (C) 2002 Martin Devera (devik@cdi.cz). - * - * 2004-07-20 Harald Welte <laforge@netfilter.org> - * - reimplemented to use per-connection accounting counters - * - add functionality to match number of packets - * - add functionality to match average packet size - * - add support to match directions seperately - * - */ -#include <linux/module.h> -#include <linux/skbuff.h> -#include <net/netfilter/nf_conntrack_compat.h> -#include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netfilter_ipv4/ipt_connbytes.h> - -#include <asm/div64.h> -#include <asm/bitops.h> - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); -MODULE_DESCRIPTION("iptables match for matching number of pkts/bytes per connection"); - -/* 64bit divisor, dividend and result. dynamic precision */ -static u_int64_t div64_64(u_int64_t dividend, u_int64_t divisor) -{ - u_int32_t d = divisor; - - if (divisor > 0xffffffffULL) { - unsigned int shift = fls(divisor >> 32); - - d = divisor >> shift; - dividend >>= shift; - } - - do_div(dividend, d); - return dividend; -} - -static int -match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - int *hotdrop) -{ - const struct ipt_connbytes_info *sinfo = matchinfo; - u_int64_t what = 0; /* initialize to make gcc happy */ - const struct ip_conntrack_counter *counters; - - if (!(counters = nf_ct_get_counters(skb))) - return 0; /* no match */ - - switch (sinfo->what) { - case IPT_CONNBYTES_PKTS: - switch (sinfo->direction) { - case IPT_CONNBYTES_DIR_ORIGINAL: - what = counters[IP_CT_DIR_ORIGINAL].packets; - break; - case IPT_CONNBYTES_DIR_REPLY: - what = counters[IP_CT_DIR_REPLY].packets; - break; - case IPT_CONNBYTES_DIR_BOTH: - what = counters[IP_CT_DIR_ORIGINAL].packets; - what += counters[IP_CT_DIR_REPLY].packets; - break; - } - break; - case IPT_CONNBYTES_BYTES: - switch (sinfo->direction) { - case IPT_CONNBYTES_DIR_ORIGINAL: - what = counters[IP_CT_DIR_ORIGINAL].bytes; - break; - case IPT_CONNBYTES_DIR_REPLY: - what = counters[IP_CT_DIR_REPLY].bytes; - break; - case IPT_CONNBYTES_DIR_BOTH: - what = counters[IP_CT_DIR_ORIGINAL].bytes; - what += counters[IP_CT_DIR_REPLY].bytes; - break; - } - break; - case IPT_CONNBYTES_AVGPKT: - switch (sinfo->direction) { - case IPT_CONNBYTES_DIR_ORIGINAL: - what = div64_64(counters[IP_CT_DIR_ORIGINAL].bytes, - counters[IP_CT_DIR_ORIGINAL].packets); - break; - case IPT_CONNBYTES_DIR_REPLY: - what = div64_64(counters[IP_CT_DIR_REPLY].bytes, - counters[IP_CT_DIR_REPLY].packets); - break; - case IPT_CONNBYTES_DIR_BOTH: - { - u_int64_t bytes; - u_int64_t pkts; - bytes = counters[IP_CT_DIR_ORIGINAL].bytes + - counters[IP_CT_DIR_REPLY].bytes; - pkts = counters[IP_CT_DIR_ORIGINAL].packets+ - counters[IP_CT_DIR_REPLY].packets; - - /* FIXME_THEORETICAL: what to do if sum - * overflows ? */ - - what = div64_64(bytes, pkts); - } - break; - } - break; - } - - if (sinfo->count.to) - return (what <= sinfo->count.to && what >= sinfo->count.from); - else - return (what >= sinfo->count.from); -} - -static int check(const char *tablename, - const struct ipt_ip *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - const struct ipt_connbytes_info *sinfo = matchinfo; - - if (matchsize != IPT_ALIGN(sizeof(struct ipt_connbytes_info))) - return 0; - - if (sinfo->what != IPT_CONNBYTES_PKTS && - sinfo->what != IPT_CONNBYTES_BYTES && - sinfo->what != IPT_CONNBYTES_AVGPKT) - return 0; - - if (sinfo->direction != IPT_CONNBYTES_DIR_ORIGINAL && - sinfo->direction != IPT_CONNBYTES_DIR_REPLY && - sinfo->direction != IPT_CONNBYTES_DIR_BOTH) - return 0; - - return 1; -} - -static struct ipt_match state_match = { - .name = "connbytes", - .match = &match, - .checkentry = &check, - .me = THIS_MODULE -}; - -static int __init init(void) -{ - return ipt_register_match(&state_match); -} - -static void __exit fini(void) -{ - ipt_unregister_match(&state_match); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv4/netfilter/ipt_connmark.c b/net/ipv4/netfilter/ipt_connmark.c deleted file mode 100644 index 5306ef293b92..000000000000 --- a/net/ipv4/netfilter/ipt_connmark.c +++ /dev/null @@ -1,88 +0,0 @@ -/* This kernel module matches connection mark values set by the - * CONNMARK target - * - * Copyright (C) 2002,2004 MARA Systems AB <http://www.marasystems.com> - * by Henrik Nordstrom <hno@marasystems.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#include <linux/module.h> -#include <linux/skbuff.h> - -MODULE_AUTHOR("Henrik Nordstrom <hno@marasytems.com>"); -MODULE_DESCRIPTION("IP tables connmark match module"); -MODULE_LICENSE("GPL"); - -#include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netfilter_ipv4/ipt_connmark.h> -#include <net/netfilter/nf_conntrack_compat.h> - -static int -match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - int *hotdrop) -{ - const struct ipt_connmark_info *info = matchinfo; - u_int32_t ctinfo; - const u_int32_t *ctmark = nf_ct_get_mark(skb, &ctinfo); - if (!ctmark) - return 0; - - return (((*ctmark) & info->mask) == info->mark) ^ info->invert; -} - -static int -checkentry(const char *tablename, - const struct ipt_ip *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - struct ipt_connmark_info *cm = - (struct ipt_connmark_info *)matchinfo; - if (matchsize != IPT_ALIGN(sizeof(struct ipt_connmark_info))) - return 0; - - if (cm->mark > 0xffffffff || cm->mask > 0xffffffff) { - printk(KERN_WARNING "connmark: only support 32bit mark\n"); - return 0; - } - - return 1; -} - -static struct ipt_match connmark_match = { - .name = "connmark", - .match = &match, - .checkentry = &checkentry, - .me = THIS_MODULE -}; - -static int __init init(void) -{ - return ipt_register_match(&connmark_match); -} - -static void __exit fini(void) -{ - ipt_unregister_match(&connmark_match); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv4/netfilter/ipt_conntrack.c b/net/ipv4/netfilter/ipt_conntrack.c deleted file mode 100644 index c8d18705469b..000000000000 --- a/net/ipv4/netfilter/ipt_conntrack.c +++ /dev/null @@ -1,232 +0,0 @@ -/* Kernel module to match connection tracking information. - * Superset of Rusty's minimalistic state match. - * - * (C) 2001 Marc Boucher (marc@mbsi.ca). - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/module.h> -#include <linux/skbuff.h> - -#if defined(CONFIG_IP_NF_CONNTRACK) || defined(CONFIG_IP_NF_CONNTRACK_MODULE) -#include <linux/netfilter_ipv4/ip_conntrack.h> -#include <linux/netfilter_ipv4/ip_conntrack_tuple.h> -#else -#include <net/netfilter/nf_conntrack.h> -#endif - -#include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netfilter_ipv4/ipt_conntrack.h> - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Marc Boucher <marc@mbsi.ca>"); -MODULE_DESCRIPTION("iptables connection tracking match module"); - -#if defined(CONFIG_IP_NF_CONNTRACK) || defined(CONFIG_IP_NF_CONNTRACK_MODULE) - -static int -match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - int *hotdrop) -{ - const struct ipt_conntrack_info *sinfo = matchinfo; - struct ip_conntrack *ct; - enum ip_conntrack_info ctinfo; - unsigned int statebit; - - ct = ip_conntrack_get((struct sk_buff *)skb, &ctinfo); - -#define FWINV(bool,invflg) ((bool) ^ !!(sinfo->invflags & invflg)) - - if (ct == &ip_conntrack_untracked) - statebit = IPT_CONNTRACK_STATE_UNTRACKED; - else if (ct) - statebit = IPT_CONNTRACK_STATE_BIT(ctinfo); - else - statebit = IPT_CONNTRACK_STATE_INVALID; - - if(sinfo->flags & IPT_CONNTRACK_STATE) { - if (ct) { - if(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.ip != - ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.ip) - statebit |= IPT_CONNTRACK_STATE_SNAT; - - if(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.ip != - ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.ip) - statebit |= IPT_CONNTRACK_STATE_DNAT; - } - - if (FWINV((statebit & sinfo->statemask) == 0, IPT_CONNTRACK_STATE)) - return 0; - } - - if(sinfo->flags & IPT_CONNTRACK_PROTO) { - if (!ct || FWINV(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum != sinfo->tuple[IP_CT_DIR_ORIGINAL].dst.protonum, IPT_CONNTRACK_PROTO)) - return 0; - } - - if(sinfo->flags & IPT_CONNTRACK_ORIGSRC) { - if (!ct || FWINV((ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.ip&sinfo->sipmsk[IP_CT_DIR_ORIGINAL].s_addr) != sinfo->tuple[IP_CT_DIR_ORIGINAL].src.ip, IPT_CONNTRACK_ORIGSRC)) - return 0; - } - - if(sinfo->flags & IPT_CONNTRACK_ORIGDST) { - if (!ct || FWINV((ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.ip&sinfo->dipmsk[IP_CT_DIR_ORIGINAL].s_addr) != sinfo->tuple[IP_CT_DIR_ORIGINAL].dst.ip, IPT_CONNTRACK_ORIGDST)) - return 0; - } - - if(sinfo->flags & IPT_CONNTRACK_REPLSRC) { - if (!ct || FWINV((ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.ip&sinfo->sipmsk[IP_CT_DIR_REPLY].s_addr) != sinfo->tuple[IP_CT_DIR_REPLY].src.ip, IPT_CONNTRACK_REPLSRC)) - return 0; - } - - if(sinfo->flags & IPT_CONNTRACK_REPLDST) { - if (!ct || FWINV((ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.ip&sinfo->dipmsk[IP_CT_DIR_REPLY].s_addr) != sinfo->tuple[IP_CT_DIR_REPLY].dst.ip, IPT_CONNTRACK_REPLDST)) - return 0; - } - - if(sinfo->flags & IPT_CONNTRACK_STATUS) { - if (!ct || FWINV((ct->status & sinfo->statusmask) == 0, IPT_CONNTRACK_STATUS)) - return 0; - } - - if(sinfo->flags & IPT_CONNTRACK_EXPIRES) { - unsigned long expires; - - if(!ct) - return 0; - - expires = timer_pending(&ct->timeout) ? (ct->timeout.expires - jiffies)/HZ : 0; - - if (FWINV(!(expires >= sinfo->expires_min && expires <= sinfo->expires_max), IPT_CONNTRACK_EXPIRES)) - return 0; - } - - return 1; -} - -#else /* CONFIG_IP_NF_CONNTRACK */ -static int -match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - int *hotdrop) -{ - const struct ipt_conntrack_info *sinfo = matchinfo; - struct nf_conn *ct; - enum ip_conntrack_info ctinfo; - unsigned int statebit; - - ct = nf_ct_get((struct sk_buff *)skb, &ctinfo); - -#define FWINV(bool,invflg) ((bool) ^ !!(sinfo->invflags & invflg)) - - if (ct == &nf_conntrack_untracked) - statebit = IPT_CONNTRACK_STATE_UNTRACKED; - else if (ct) - statebit = IPT_CONNTRACK_STATE_BIT(ctinfo); - else - statebit = IPT_CONNTRACK_STATE_INVALID; - - if(sinfo->flags & IPT_CONNTRACK_STATE) { - if (ct) { - if(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip != - ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip) - statebit |= IPT_CONNTRACK_STATE_SNAT; - - if(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.ip != - ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip) - statebit |= IPT_CONNTRACK_STATE_DNAT; - } - - if (FWINV((statebit & sinfo->statemask) == 0, IPT_CONNTRACK_STATE)) - return 0; - } - - if(sinfo->flags & IPT_CONNTRACK_PROTO) { - if (!ct || FWINV(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum != sinfo->tuple[IP_CT_DIR_ORIGINAL].dst.protonum, IPT_CONNTRACK_PROTO)) - return 0; - } - - if(sinfo->flags & IPT_CONNTRACK_ORIGSRC) { - if (!ct || FWINV((ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip&sinfo->sipmsk[IP_CT_DIR_ORIGINAL].s_addr) != sinfo->tuple[IP_CT_DIR_ORIGINAL].src.ip, IPT_CONNTRACK_ORIGSRC)) - return 0; - } - - if(sinfo->flags & IPT_CONNTRACK_ORIGDST) { - if (!ct || FWINV((ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.ip&sinfo->dipmsk[IP_CT_DIR_ORIGINAL].s_addr) != sinfo->tuple[IP_CT_DIR_ORIGINAL].dst.ip, IPT_CONNTRACK_ORIGDST)) - return 0; - } - - if(sinfo->flags & IPT_CONNTRACK_REPLSRC) { - if (!ct || FWINV((ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip&sinfo->sipmsk[IP_CT_DIR_REPLY].s_addr) != sinfo->tuple[IP_CT_DIR_REPLY].src.ip, IPT_CONNTRACK_REPLSRC)) - return 0; - } - - if(sinfo->flags & IPT_CONNTRACK_REPLDST) { - if (!ct || FWINV((ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip&sinfo->dipmsk[IP_CT_DIR_REPLY].s_addr) != sinfo->tuple[IP_CT_DIR_REPLY].dst.ip, IPT_CONNTRACK_REPLDST)) - return 0; - } - - if(sinfo->flags & IPT_CONNTRACK_STATUS) { - if (!ct || FWINV((ct->status & sinfo->statusmask) == 0, IPT_CONNTRACK_STATUS)) - return 0; - } - - if(sinfo->flags & IPT_CONNTRACK_EXPIRES) { - unsigned long expires; - - if(!ct) - return 0; - - expires = timer_pending(&ct->timeout) ? (ct->timeout.expires - jiffies)/HZ : 0; - - if (FWINV(!(expires >= sinfo->expires_min && expires <= sinfo->expires_max), IPT_CONNTRACK_EXPIRES)) - return 0; - } - - return 1; -} - -#endif /* CONFIG_NF_IP_CONNTRACK */ - -static int check(const char *tablename, - const struct ipt_ip *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - if (matchsize != IPT_ALIGN(sizeof(struct ipt_conntrack_info))) - return 0; - - return 1; -} - -static struct ipt_match conntrack_match = { - .name = "conntrack", - .match = &match, - .checkentry = &check, - .me = THIS_MODULE, -}; - -static int __init init(void) -{ - need_ip_conntrack(); - return ipt_register_match(&conntrack_match); -} - -static void __exit fini(void) -{ - ipt_unregister_match(&conntrack_match); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv4/netfilter/ipt_dccp.c b/net/ipv4/netfilter/ipt_dccp.c deleted file mode 100644 index ad3278bba6c1..000000000000 --- a/net/ipv4/netfilter/ipt_dccp.c +++ /dev/null @@ -1,176 +0,0 @@ -/* - * iptables module for DCCP protocol header matching - * - * (C) 2005 by Harald Welte <laforge@netfilter.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/module.h> -#include <linux/skbuff.h> -#include <linux/spinlock.h> -#include <net/ip.h> -#include <linux/dccp.h> - -#include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netfilter_ipv4/ipt_dccp.h> - -#define DCCHECK(cond, option, flag, invflag) (!((flag) & (option)) \ - || (!!((invflag) & (option)) ^ (cond))) - -static unsigned char *dccp_optbuf; -static DEFINE_SPINLOCK(dccp_buflock); - -static inline int -dccp_find_option(u_int8_t option, - const struct sk_buff *skb, - const struct dccp_hdr *dh, - int *hotdrop) -{ - /* tcp.doff is only 4 bits, ie. max 15 * 4 bytes */ - unsigned char *op; - unsigned int optoff = __dccp_hdr_len(dh); - unsigned int optlen = dh->dccph_doff*4 - __dccp_hdr_len(dh); - unsigned int i; - - if (dh->dccph_doff * 4 < __dccp_hdr_len(dh)) { - *hotdrop = 1; - return 0; - } - - if (!optlen) - return 0; - - spin_lock_bh(&dccp_buflock); - op = skb_header_pointer(skb, - skb->nh.iph->ihl*4 + optoff, - optlen, dccp_optbuf); - if (op == NULL) { - /* If we don't have the whole header, drop packet. */ - spin_unlock_bh(&dccp_buflock); - *hotdrop = 1; - return 0; - } - - for (i = 0; i < optlen; ) { - if (op[i] == option) { - spin_unlock_bh(&dccp_buflock); - return 1; - } - - if (op[i] < 2) - i++; - else - i += op[i+1]?:1; - } - - spin_unlock_bh(&dccp_buflock); - return 0; -} - - -static inline int -match_types(const struct dccp_hdr *dh, u_int16_t typemask) -{ - return (typemask & (1 << dh->dccph_type)); -} - -static inline int -match_option(u_int8_t option, const struct sk_buff *skb, - const struct dccp_hdr *dh, int *hotdrop) -{ - return dccp_find_option(option, skb, dh, hotdrop); -} - -static int -match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - int *hotdrop) -{ - const struct ipt_dccp_info *info = - (const struct ipt_dccp_info *)matchinfo; - struct dccp_hdr _dh, *dh; - - if (offset) - return 0; - - dh = skb_header_pointer(skb, skb->nh.iph->ihl*4, sizeof(_dh), &_dh); - if (dh == NULL) { - *hotdrop = 1; - return 0; - } - - return DCCHECK(((ntohs(dh->dccph_sport) >= info->spts[0]) - && (ntohs(dh->dccph_sport) <= info->spts[1])), - IPT_DCCP_SRC_PORTS, info->flags, info->invflags) - && DCCHECK(((ntohs(dh->dccph_dport) >= info->dpts[0]) - && (ntohs(dh->dccph_dport) <= info->dpts[1])), - IPT_DCCP_DEST_PORTS, info->flags, info->invflags) - && DCCHECK(match_types(dh, info->typemask), - IPT_DCCP_TYPE, info->flags, info->invflags) - && DCCHECK(match_option(info->option, skb, dh, hotdrop), - IPT_DCCP_OPTION, info->flags, info->invflags); -} - -static int -checkentry(const char *tablename, - const struct ipt_ip *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - const struct ipt_dccp_info *info; - - info = (const struct ipt_dccp_info *)matchinfo; - - return ip->proto == IPPROTO_DCCP - && !(ip->invflags & IPT_INV_PROTO) - && matchsize == IPT_ALIGN(sizeof(struct ipt_dccp_info)) - && !(info->flags & ~IPT_DCCP_VALID_FLAGS) - && !(info->invflags & ~IPT_DCCP_VALID_FLAGS) - && !(info->invflags & ~info->flags); -} - -static struct ipt_match dccp_match = -{ - .name = "dccp", - .match = &match, - .checkentry = &checkentry, - .me = THIS_MODULE, -}; - -static int __init init(void) -{ - int ret; - - /* doff is 8 bits, so the maximum option size is (4*256). Don't put - * this in BSS since DaveM is worried about locked TLB's for kernel - * BSS. */ - dccp_optbuf = kmalloc(256 * 4, GFP_KERNEL); - if (!dccp_optbuf) - return -ENOMEM; - ret = ipt_register_match(&dccp_match); - if (ret) - kfree(dccp_optbuf); - - return ret; -} - -static void __exit fini(void) -{ - ipt_unregister_match(&dccp_match); - kfree(dccp_optbuf); -} - -module_init(init); -module_exit(fini); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); -MODULE_DESCRIPTION("Match for DCCP protocol packets"); - diff --git a/net/ipv4/netfilter/ipt_dscp.c b/net/ipv4/netfilter/ipt_dscp.c index 5df52a64a5d4..92063b4f8602 100644 --- a/net/ipv4/netfilter/ipt_dscp.c +++ b/net/ipv4/netfilter/ipt_dscp.c @@ -21,7 +21,7 @@ MODULE_LICENSE("GPL"); static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, const void *matchinfo, - int offset, int *hotdrop) + int offset, unsigned int protoff, int *hotdrop) { const struct ipt_dscp_info *info = matchinfo; const struct iphdr *iph = skb->nh.iph; @@ -31,7 +31,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, return ((iph->tos&IPT_DSCP_MASK) == sh_dscp) ^ info->invert; } -static int checkentry(const char *tablename, const struct ipt_ip *ip, +static int checkentry(const char *tablename, const void *ip, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { diff --git a/net/ipv4/netfilter/ipt_ecn.c b/net/ipv4/netfilter/ipt_ecn.c index b6f7181e89cc..e68b0c7981f0 100644 --- a/net/ipv4/netfilter/ipt_ecn.c +++ b/net/ipv4/netfilter/ipt_ecn.c @@ -67,7 +67,7 @@ static inline int match_tcp(const struct sk_buff *skb, static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, const void *matchinfo, - int offset, int *hotdrop) + int offset, unsigned int protoff, int *hotdrop) { const struct ipt_ecn_info *info = matchinfo; @@ -85,11 +85,12 @@ static int match(const struct sk_buff *skb, const struct net_device *in, return 1; } -static int checkentry(const char *tablename, const struct ipt_ip *ip, +static int checkentry(const char *tablename, const void *ip_void, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { const struct ipt_ecn_info *info = matchinfo; + const struct ipt_ip *ip = ip_void; if (matchsize != IPT_ALIGN(sizeof(struct ipt_ecn_info))) return 0; diff --git a/net/ipv4/netfilter/ipt_esp.c b/net/ipv4/netfilter/ipt_esp.c index e1d0dd31e117..9de191a8162d 100644 --- a/net/ipv4/netfilter/ipt_esp.c +++ b/net/ipv4/netfilter/ipt_esp.c @@ -42,6 +42,7 @@ match(const struct sk_buff *skb, const struct net_device *out, const void *matchinfo, int offset, + unsigned int protoff, int *hotdrop) { struct ip_esp_hdr _esp, *eh; @@ -51,7 +52,7 @@ match(const struct sk_buff *skb, if (offset) return 0; - eh = skb_header_pointer(skb, skb->nh.iph->ihl * 4, + eh = skb_header_pointer(skb, protoff, sizeof(_esp), &_esp); if (eh == NULL) { /* We've been asked to examine this packet, and we @@ -70,12 +71,13 @@ match(const struct sk_buff *skb, /* Called when user tries to insert an entry of this type. */ static int checkentry(const char *tablename, - const struct ipt_ip *ip, + const void *ip_void, void *matchinfo, unsigned int matchinfosize, unsigned int hook_mask) { const struct ipt_esp *espinfo = matchinfo; + const struct ipt_ip *ip = ip_void; /* Must specify proto == ESP, and no unknown invflags */ if (ip->proto != IPPROTO_ESP || (ip->invflags & IPT_INV_PROTO)) { diff --git a/net/ipv4/netfilter/ipt_hashlimit.c b/net/ipv4/netfilter/ipt_hashlimit.c index 2dd1cccbdab9..4fe48c1bd5f3 100644 --- a/net/ipv4/netfilter/ipt_hashlimit.c +++ b/net/ipv4/netfilter/ipt_hashlimit.c @@ -429,6 +429,7 @@ hashlimit_match(const struct sk_buff *skb, const struct net_device *out, const void *matchinfo, int offset, + unsigned int protoff, int *hotdrop) { struct ipt_hashlimit_info *r = @@ -504,7 +505,7 @@ hashlimit_match(const struct sk_buff *skb, static int hashlimit_checkentry(const char *tablename, - const struct ipt_ip *ip, + const void *inf, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) diff --git a/net/ipv4/netfilter/ipt_helper.c b/net/ipv4/netfilter/ipt_helper.c deleted file mode 100644 index aef649e393af..000000000000 --- a/net/ipv4/netfilter/ipt_helper.c +++ /dev/null @@ -1,168 +0,0 @@ -/* iptables module to match on related connections */ -/* - * (C) 2001 Martin Josefsson <gandalf@wlug.westbo.se> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * 19 Mar 2002 Harald Welte <laforge@gnumonks.org>: - * - Port to newnat infrastructure - */ - -#include <linux/module.h> -#include <linux/skbuff.h> -#include <linux/netfilter.h> -#include <linux/interrupt.h> -#if defined(CONFIG_IP_NF_CONNTRACK) || defined(CONFIG_IP_NF_CONNTRACK_MODULE) -#include <linux/netfilter_ipv4/ip_conntrack.h> -#include <linux/netfilter_ipv4/ip_conntrack_core.h> -#include <linux/netfilter_ipv4/ip_conntrack_helper.h> -#else -#include <net/netfilter/nf_conntrack.h> -#include <net/netfilter/nf_conntrack_core.h> -#include <net/netfilter/nf_conntrack_helper.h> -#endif -#include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netfilter_ipv4/ipt_helper.h> - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Martin Josefsson <gandalf@netfilter.org>"); -MODULE_DESCRIPTION("iptables helper match module"); - -#if 0 -#define DEBUGP printk -#else -#define DEBUGP(format, args...) -#endif - -#if defined(CONFIG_IP_NF_CONNTRACK) || defined(CONFIG_IP_NF_CONNTRACK_MODULE) -static int -match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - int *hotdrop) -{ - const struct ipt_helper_info *info = matchinfo; - struct ip_conntrack *ct; - enum ip_conntrack_info ctinfo; - int ret = info->invert; - - ct = ip_conntrack_get((struct sk_buff *)skb, &ctinfo); - if (!ct) { - DEBUGP("ipt_helper: Eek! invalid conntrack?\n"); - return ret; - } - - if (!ct->master) { - DEBUGP("ipt_helper: conntrack %p has no master\n", ct); - return ret; - } - - read_lock_bh(&ip_conntrack_lock); - if (!ct->master->helper) { - DEBUGP("ipt_helper: master ct %p has no helper\n", - exp->expectant); - goto out_unlock; - } - - DEBUGP("master's name = %s , info->name = %s\n", - ct->master->helper->name, info->name); - - if (info->name[0] == '\0') - ret ^= 1; - else - ret ^= !strncmp(ct->master->helper->name, info->name, - strlen(ct->master->helper->name)); -out_unlock: - read_unlock_bh(&ip_conntrack_lock); - return ret; -} - -#else /* CONFIG_IP_NF_CONNTRACK */ - -static int -match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - int *hotdrop) -{ - const struct ipt_helper_info *info = matchinfo; - struct nf_conn *ct; - enum ip_conntrack_info ctinfo; - int ret = info->invert; - - ct = nf_ct_get((struct sk_buff *)skb, &ctinfo); - if (!ct) { - DEBUGP("ipt_helper: Eek! invalid conntrack?\n"); - return ret; - } - - if (!ct->master) { - DEBUGP("ipt_helper: conntrack %p has no master\n", ct); - return ret; - } - - read_lock_bh(&nf_conntrack_lock); - if (!ct->master->helper) { - DEBUGP("ipt_helper: master ct %p has no helper\n", - exp->expectant); - goto out_unlock; - } - - DEBUGP("master's name = %s , info->name = %s\n", - ct->master->helper->name, info->name); - - if (info->name[0] == '\0') - ret ^= 1; - else - ret ^= !strncmp(ct->master->helper->name, info->name, - strlen(ct->master->helper->name)); -out_unlock: - read_unlock_bh(&nf_conntrack_lock); - return ret; -} -#endif - -static int check(const char *tablename, - const struct ipt_ip *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - struct ipt_helper_info *info = matchinfo; - - info->name[29] = '\0'; - - /* verify size */ - if (matchsize != IPT_ALIGN(sizeof(struct ipt_helper_info))) - return 0; - - return 1; -} - -static struct ipt_match helper_match = { - .name = "helper", - .match = &match, - .checkentry = &check, - .me = THIS_MODULE, -}; - -static int __init init(void) -{ - need_ip_conntrack(); - return ipt_register_match(&helper_match); -} - -static void __exit fini(void) -{ - ipt_unregister_match(&helper_match); -} - -module_init(init); -module_exit(fini); - diff --git a/net/ipv4/netfilter/ipt_iprange.c b/net/ipv4/netfilter/ipt_iprange.c index b835b7b2e560..13fb16fb7892 100644 --- a/net/ipv4/netfilter/ipt_iprange.c +++ b/net/ipv4/netfilter/ipt_iprange.c @@ -28,7 +28,7 @@ match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, const void *matchinfo, - int offset, int *hotdrop) + int offset, unsigned int protoff, int *hotdrop) { const struct ipt_iprange_info *info = matchinfo; const struct iphdr *iph = skb->nh.iph; @@ -63,7 +63,7 @@ match(const struct sk_buff *skb, } static int check(const char *tablename, - const struct ipt_ip *ip, + const void *inf, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) diff --git a/net/ipv4/netfilter/ipt_length.c b/net/ipv4/netfilter/ipt_length.c deleted file mode 100644 index 4eabcfbda9d1..000000000000 --- a/net/ipv4/netfilter/ipt_length.c +++ /dev/null @@ -1,64 +0,0 @@ -/* Kernel module to match packet length. */ -/* (C) 1999-2001 James Morris <jmorros@intercode.com.au> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/module.h> -#include <linux/skbuff.h> - -#include <linux/netfilter_ipv4/ipt_length.h> -#include <linux/netfilter_ipv4/ip_tables.h> - -MODULE_AUTHOR("James Morris <jmorris@intercode.com.au>"); -MODULE_DESCRIPTION("IP tables packet length matching module"); -MODULE_LICENSE("GPL"); - -static int -match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - int *hotdrop) -{ - const struct ipt_length_info *info = matchinfo; - u_int16_t pktlen = ntohs(skb->nh.iph->tot_len); - - return (pktlen >= info->min && pktlen <= info->max) ^ info->invert; -} - -static int -checkentry(const char *tablename, - const struct ipt_ip *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - if (matchsize != IPT_ALIGN(sizeof(struct ipt_length_info))) - return 0; - - return 1; -} - -static struct ipt_match length_match = { - .name = "length", - .match = &match, - .checkentry = &checkentry, - .me = THIS_MODULE, -}; - -static int __init init(void) -{ - return ipt_register_match(&length_match); -} - -static void __exit fini(void) -{ - ipt_unregister_match(&length_match); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv4/netfilter/ipt_limit.c b/net/ipv4/netfilter/ipt_limit.c deleted file mode 100644 index 0c24dcc703a5..000000000000 --- a/net/ipv4/netfilter/ipt_limit.c +++ /dev/null @@ -1,157 +0,0 @@ -/* Kernel module to control the rate - * - * 2 September 1999: Changed from the target RATE to the match - * `limit', removed logging. Did I mention that - * Alexey is a fucking genius? - * Rusty Russell (rusty@rustcorp.com.au). */ - -/* (C) 1999 Jérôme de Vivie <devivie@info.enserb.u-bordeaux.fr> - * (C) 1999 Hervé Eychenne <eychenne@info.enserb.u-bordeaux.fr> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/module.h> -#include <linux/skbuff.h> -#include <linux/spinlock.h> -#include <linux/interrupt.h> - -#include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netfilter_ipv4/ipt_limit.h> - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Herve Eychenne <rv@wallfire.org>"); -MODULE_DESCRIPTION("iptables rate limit match"); - -/* The algorithm used is the Simple Token Bucket Filter (TBF) - * see net/sched/sch_tbf.c in the linux source tree - */ - -static DEFINE_SPINLOCK(limit_lock); - -/* Rusty: This is my (non-mathematically-inclined) understanding of - this algorithm. The `average rate' in jiffies becomes your initial - amount of credit `credit' and the most credit you can ever have - `credit_cap'. The `peak rate' becomes the cost of passing the - test, `cost'. - - `prev' tracks the last packet hit: you gain one credit per jiffy. - If you get credit balance more than this, the extra credit is - discarded. Every time the match passes, you lose `cost' credits; - if you don't have that many, the test fails. - - See Alexey's formal explanation in net/sched/sch_tbf.c. - - To get the maxmum range, we multiply by this factor (ie. you get N - credits per jiffy). We want to allow a rate as low as 1 per day - (slowest userspace tool allows), which means - CREDITS_PER_JIFFY*HZ*60*60*24 < 2^32. ie. */ -#define MAX_CPJ (0xFFFFFFFF / (HZ*60*60*24)) - -/* Repeated shift and or gives us all 1s, final shift and add 1 gives - * us the power of 2 below the theoretical max, so GCC simply does a - * shift. */ -#define _POW2_BELOW2(x) ((x)|((x)>>1)) -#define _POW2_BELOW4(x) (_POW2_BELOW2(x)|_POW2_BELOW2((x)>>2)) -#define _POW2_BELOW8(x) (_POW2_BELOW4(x)|_POW2_BELOW4((x)>>4)) -#define _POW2_BELOW16(x) (_POW2_BELOW8(x)|_POW2_BELOW8((x)>>8)) -#define _POW2_BELOW32(x) (_POW2_BELOW16(x)|_POW2_BELOW16((x)>>16)) -#define POW2_BELOW32(x) ((_POW2_BELOW32(x)>>1) + 1) - -#define CREDITS_PER_JIFFY POW2_BELOW32(MAX_CPJ) - -static int -ipt_limit_match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - int *hotdrop) -{ - struct ipt_rateinfo *r = ((struct ipt_rateinfo *)matchinfo)->master; - unsigned long now = jiffies; - - spin_lock_bh(&limit_lock); - r->credit += (now - xchg(&r->prev, now)) * CREDITS_PER_JIFFY; - if (r->credit > r->credit_cap) - r->credit = r->credit_cap; - - if (r->credit >= r->cost) { - /* We're not limited. */ - r->credit -= r->cost; - spin_unlock_bh(&limit_lock); - return 1; - } - - spin_unlock_bh(&limit_lock); - return 0; -} - -/* Precision saver. */ -static u_int32_t -user2credits(u_int32_t user) -{ - /* If multiplying would overflow... */ - if (user > 0xFFFFFFFF / (HZ*CREDITS_PER_JIFFY)) - /* Divide first. */ - return (user / IPT_LIMIT_SCALE) * HZ * CREDITS_PER_JIFFY; - - return (user * HZ * CREDITS_PER_JIFFY) / IPT_LIMIT_SCALE; -} - -static int -ipt_limit_checkentry(const char *tablename, - const struct ipt_ip *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - struct ipt_rateinfo *r = matchinfo; - - if (matchsize != IPT_ALIGN(sizeof(struct ipt_rateinfo))) - return 0; - - /* Check for overflow. */ - if (r->burst == 0 - || user2credits(r->avg * r->burst) < user2credits(r->avg)) { - printk("Overflow in ipt_limit, try lower: %u/%u\n", - r->avg, r->burst); - return 0; - } - - /* User avg in seconds * IPT_LIMIT_SCALE: convert to jiffies * - 128. */ - r->prev = jiffies; - r->credit = user2credits(r->avg * r->burst); /* Credits full. */ - r->credit_cap = user2credits(r->avg * r->burst); /* Credits full. */ - r->cost = user2credits(r->avg); - - /* For SMP, we only want to use one set of counters. */ - r->master = r; - - return 1; -} - -static struct ipt_match ipt_limit_reg = { - .name = "limit", - .match = ipt_limit_match, - .checkentry = ipt_limit_checkentry, - .me = THIS_MODULE, -}; - -static int __init init(void) -{ - if (ipt_register_match(&ipt_limit_reg)) - return -EINVAL; - return 0; -} - -static void __exit fini(void) -{ - ipt_unregister_match(&ipt_limit_reg); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv4/netfilter/ipt_mac.c b/net/ipv4/netfilter/ipt_mac.c deleted file mode 100644 index 11a459e33f25..000000000000 --- a/net/ipv4/netfilter/ipt_mac.c +++ /dev/null @@ -1,79 +0,0 @@ -/* Kernel module to match MAC address parameters. */ - -/* (C) 1999-2001 Paul `Rusty' Russell - * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/module.h> -#include <linux/skbuff.h> -#include <linux/if_ether.h> - -#include <linux/netfilter_ipv4/ipt_mac.h> -#include <linux/netfilter_ipv4/ip_tables.h> - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); -MODULE_DESCRIPTION("iptables mac matching module"); - -static int -match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - int *hotdrop) -{ - const struct ipt_mac_info *info = matchinfo; - - /* Is mac pointer valid? */ - return (skb->mac.raw >= skb->head - && (skb->mac.raw + ETH_HLEN) <= skb->data - /* If so, compare... */ - && ((memcmp(eth_hdr(skb)->h_source, info->srcaddr, ETH_ALEN) - == 0) ^ info->invert)); -} - -static int -ipt_mac_checkentry(const char *tablename, - const struct ipt_ip *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - /* FORWARD isn't always valid, but it's nice to be able to do --RR */ - if (hook_mask - & ~((1 << NF_IP_PRE_ROUTING) | (1 << NF_IP_LOCAL_IN) - | (1 << NF_IP_FORWARD))) { - printk("ipt_mac: only valid for PRE_ROUTING, LOCAL_IN or FORWARD.\n"); - return 0; - } - - if (matchsize != IPT_ALIGN(sizeof(struct ipt_mac_info))) - return 0; - - return 1; -} - -static struct ipt_match mac_match = { - .name = "mac", - .match = &match, - .checkentry = &ipt_mac_checkentry, - .me = THIS_MODULE, -}; - -static int __init init(void) -{ - return ipt_register_match(&mac_match); -} - -static void __exit fini(void) -{ - ipt_unregister_match(&mac_match); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv4/netfilter/ipt_mark.c b/net/ipv4/netfilter/ipt_mark.c deleted file mode 100644 index 00bef6cdd3f8..000000000000 --- a/net/ipv4/netfilter/ipt_mark.c +++ /dev/null @@ -1,71 +0,0 @@ -/* Kernel module to match NFMARK values. */ - -/* (C) 1999-2001 Marc Boucher <marc@mbsi.ca> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/module.h> -#include <linux/skbuff.h> - -#include <linux/netfilter_ipv4/ipt_mark.h> -#include <linux/netfilter_ipv4/ip_tables.h> - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Marc Boucher <marc@mbsi.ca>"); -MODULE_DESCRIPTION("iptables mark matching module"); - -static int -match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - int *hotdrop) -{ - const struct ipt_mark_info *info = matchinfo; - - return ((skb->nfmark & info->mask) == info->mark) ^ info->invert; -} - -static int -checkentry(const char *tablename, - const struct ipt_ip *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - struct ipt_mark_info *minfo = (struct ipt_mark_info *) matchinfo; - - if (matchsize != IPT_ALIGN(sizeof(struct ipt_mark_info))) - return 0; - - if (minfo->mark > 0xffffffff || minfo->mask > 0xffffffff) { - printk(KERN_WARNING "mark: only supports 32bit mark\n"); - return 0; - } - - return 1; -} - -static struct ipt_match mark_match = { - .name = "mark", - .match = &match, - .checkentry = &checkentry, - .me = THIS_MODULE, -}; - -static int __init init(void) -{ - return ipt_register_match(&mark_match); -} - -static void __exit fini(void) -{ - ipt_unregister_match(&mark_match); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv4/netfilter/ipt_multiport.c b/net/ipv4/netfilter/ipt_multiport.c index 99e8188162e2..2d52326553f1 100644 --- a/net/ipv4/netfilter/ipt_multiport.c +++ b/net/ipv4/netfilter/ipt_multiport.c @@ -97,6 +97,7 @@ match(const struct sk_buff *skb, const struct net_device *out, const void *matchinfo, int offset, + unsigned int protoff, int *hotdrop) { u16 _ports[2], *pptr; @@ -105,7 +106,7 @@ match(const struct sk_buff *skb, if (offset) return 0; - pptr = skb_header_pointer(skb, skb->nh.iph->ihl * 4, + pptr = skb_header_pointer(skb, protoff, sizeof(_ports), _ports); if (pptr == NULL) { /* We've been asked to examine this packet, and we @@ -128,6 +129,7 @@ match_v1(const struct sk_buff *skb, const struct net_device *out, const void *matchinfo, int offset, + unsigned int protoff, int *hotdrop) { u16 _ports[2], *pptr; @@ -136,7 +138,7 @@ match_v1(const struct sk_buff *skb, if (offset) return 0; - pptr = skb_header_pointer(skb, skb->nh.iph->ihl * 4, + pptr = skb_header_pointer(skb, protoff, sizeof(_ports), _ports); if (pptr == NULL) { /* We've been asked to examine this packet, and we @@ -154,7 +156,7 @@ match_v1(const struct sk_buff *skb, /* Called when user tries to insert an entry of this type. */ static int checkentry(const char *tablename, - const struct ipt_ip *ip, + const void *ip, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) @@ -164,7 +166,7 @@ checkentry(const char *tablename, static int checkentry_v1(const char *tablename, - const struct ipt_ip *ip, + const void *ip, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) diff --git a/net/ipv4/netfilter/ipt_owner.c b/net/ipv4/netfilter/ipt_owner.c index 0cee2862ed85..4843d0c9734f 100644 --- a/net/ipv4/netfilter/ipt_owner.c +++ b/net/ipv4/netfilter/ipt_owner.c @@ -27,6 +27,7 @@ match(const struct sk_buff *skb, const struct net_device *out, const void *matchinfo, int offset, + unsigned int protoff, int *hotdrop) { const struct ipt_owner_info *info = matchinfo; @@ -51,7 +52,7 @@ match(const struct sk_buff *skb, static int checkentry(const char *tablename, - const struct ipt_ip *ip, + const void *ip, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) diff --git a/net/ipv4/netfilter/ipt_physdev.c b/net/ipv4/netfilter/ipt_physdev.c deleted file mode 100644 index 03f554857a4d..000000000000 --- a/net/ipv4/netfilter/ipt_physdev.c +++ /dev/null @@ -1,135 +0,0 @@ -/* Kernel module to match the bridge port in and - * out device for IP packets coming into contact with a bridge. */ - -/* (C) 2001-2003 Bart De Schuymer <bdschuym@pandora.be> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/module.h> -#include <linux/netdevice.h> -#include <linux/skbuff.h> -#include <linux/netfilter_ipv4/ipt_physdev.h> -#include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netfilter_bridge.h> -#define MATCH 1 -#define NOMATCH 0 - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Bart De Schuymer <bdschuym@pandora.be>"); -MODULE_DESCRIPTION("iptables bridge physical device match module"); - -static int -match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - int *hotdrop) -{ - int i; - static const char nulldevname[IFNAMSIZ]; - const struct ipt_physdev_info *info = matchinfo; - unsigned int ret; - const char *indev, *outdev; - struct nf_bridge_info *nf_bridge; - - /* Not a bridged IP packet or no info available yet: - * LOCAL_OUT/mangle and LOCAL_OUT/nat don't know if - * the destination device will be a bridge. */ - if (!(nf_bridge = skb->nf_bridge)) { - /* Return MATCH if the invert flags of the used options are on */ - if ((info->bitmask & IPT_PHYSDEV_OP_BRIDGED) && - !(info->invert & IPT_PHYSDEV_OP_BRIDGED)) - return NOMATCH; - if ((info->bitmask & IPT_PHYSDEV_OP_ISIN) && - !(info->invert & IPT_PHYSDEV_OP_ISIN)) - return NOMATCH; - if ((info->bitmask & IPT_PHYSDEV_OP_ISOUT) && - !(info->invert & IPT_PHYSDEV_OP_ISOUT)) - return NOMATCH; - if ((info->bitmask & IPT_PHYSDEV_OP_IN) && - !(info->invert & IPT_PHYSDEV_OP_IN)) - return NOMATCH; - if ((info->bitmask & IPT_PHYSDEV_OP_OUT) && - !(info->invert & IPT_PHYSDEV_OP_OUT)) - return NOMATCH; - return MATCH; - } - - /* This only makes sense in the FORWARD and POSTROUTING chains */ - if ((info->bitmask & IPT_PHYSDEV_OP_BRIDGED) && - (!!(nf_bridge->mask & BRNF_BRIDGED) ^ - !(info->invert & IPT_PHYSDEV_OP_BRIDGED))) - return NOMATCH; - - if ((info->bitmask & IPT_PHYSDEV_OP_ISIN && - (!nf_bridge->physindev ^ !!(info->invert & IPT_PHYSDEV_OP_ISIN))) || - (info->bitmask & IPT_PHYSDEV_OP_ISOUT && - (!nf_bridge->physoutdev ^ !!(info->invert & IPT_PHYSDEV_OP_ISOUT)))) - return NOMATCH; - - if (!(info->bitmask & IPT_PHYSDEV_OP_IN)) - goto match_outdev; - indev = nf_bridge->physindev ? nf_bridge->physindev->name : nulldevname; - for (i = 0, ret = 0; i < IFNAMSIZ/sizeof(unsigned int); i++) { - ret |= (((const unsigned int *)indev)[i] - ^ ((const unsigned int *)info->physindev)[i]) - & ((const unsigned int *)info->in_mask)[i]; - } - - if ((ret == 0) ^ !(info->invert & IPT_PHYSDEV_OP_IN)) - return NOMATCH; - -match_outdev: - if (!(info->bitmask & IPT_PHYSDEV_OP_OUT)) - return MATCH; - outdev = nf_bridge->physoutdev ? - nf_bridge->physoutdev->name : nulldevname; - for (i = 0, ret = 0; i < IFNAMSIZ/sizeof(unsigned int); i++) { - ret |= (((const unsigned int *)outdev)[i] - ^ ((const unsigned int *)info->physoutdev)[i]) - & ((const unsigned int *)info->out_mask)[i]; - } - - return (ret != 0) ^ !(info->invert & IPT_PHYSDEV_OP_OUT); -} - -static int -checkentry(const char *tablename, - const struct ipt_ip *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - const struct ipt_physdev_info *info = matchinfo; - - if (matchsize != IPT_ALIGN(sizeof(struct ipt_physdev_info))) - return 0; - if (!(info->bitmask & IPT_PHYSDEV_OP_MASK) || - info->bitmask & ~IPT_PHYSDEV_OP_MASK) - return 0; - return 1; -} - -static struct ipt_match physdev_match = { - .name = "physdev", - .match = &match, - .checkentry = &checkentry, - .me = THIS_MODULE, -}; - -static int __init init(void) -{ - return ipt_register_match(&physdev_match); -} - -static void __exit fini(void) -{ - ipt_unregister_match(&physdev_match); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv4/netfilter/ipt_pkttype.c b/net/ipv4/netfilter/ipt_pkttype.c deleted file mode 100644 index 8ddb1dc5e5ae..000000000000 --- a/net/ipv4/netfilter/ipt_pkttype.c +++ /dev/null @@ -1,70 +0,0 @@ -/* (C) 1999-2001 Michal Ludvig <michal@logix.cz> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/module.h> -#include <linux/skbuff.h> -#include <linux/if_ether.h> -#include <linux/if_packet.h> - -#include <linux/netfilter_ipv4/ipt_pkttype.h> -#include <linux/netfilter_ipv4/ip_tables.h> - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Michal Ludvig <michal@logix.cz>"); -MODULE_DESCRIPTION("IP tables match to match on linklayer packet type"); - -static int match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - int *hotdrop) -{ - const struct ipt_pkttype_info *info = matchinfo; - - return (skb->pkt_type == info->pkttype) ^ info->invert; -} - -static int checkentry(const char *tablename, - const struct ipt_ip *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ -/* - if (hook_mask - & ~((1 << NF_IP_PRE_ROUTING) | (1 << NF_IP_LOCAL_IN) - | (1 << NF_IP_FORWARD))) { - printk("ipt_pkttype: only valid for PRE_ROUTING, LOCAL_IN or FORWARD.\n"); - return 0; - } -*/ - if (matchsize != IPT_ALIGN(sizeof(struct ipt_pkttype_info))) - return 0; - - return 1; -} - -static struct ipt_match pkttype_match = { - .name = "pkttype", - .match = &match, - .checkentry = &checkentry, - .me = THIS_MODULE, -}; - -static int __init init(void) -{ - return ipt_register_match(&pkttype_match); -} - -static void __exit fini(void) -{ - ipt_unregister_match(&pkttype_match); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv4/netfilter/ipt_policy.c b/net/ipv4/netfilter/ipt_policy.c new file mode 100644 index 000000000000..18ca8258a1c5 --- /dev/null +++ b/net/ipv4/netfilter/ipt_policy.c @@ -0,0 +1,173 @@ +/* IP tables module for matching IPsec policy + * + * Copyright (c) 2004,2005 Patrick McHardy, <kaber@trash.net> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/kernel.h> +#include <linux/config.h> +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/init.h> +#include <net/xfrm.h> + +#include <linux/netfilter_ipv4.h> +#include <linux/netfilter_ipv4/ip_tables.h> +#include <linux/netfilter_ipv4/ipt_policy.h> + +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_DESCRIPTION("IPtables IPsec policy matching module"); +MODULE_LICENSE("GPL"); + + +static inline int +match_xfrm_state(struct xfrm_state *x, const struct ipt_policy_elem *e) +{ +#define MATCH(x,y) (!e->match.x || ((e->x == (y)) ^ e->invert.x)) + + return MATCH(saddr, x->props.saddr.a4 & e->smask) && + MATCH(daddr, x->id.daddr.a4 & e->dmask) && + MATCH(proto, x->id.proto) && + MATCH(mode, x->props.mode) && + MATCH(spi, x->id.spi) && + MATCH(reqid, x->props.reqid); +} + +static int +match_policy_in(const struct sk_buff *skb, const struct ipt_policy_info *info) +{ + const struct ipt_policy_elem *e; + struct sec_path *sp = skb->sp; + int strict = info->flags & IPT_POLICY_MATCH_STRICT; + int i, pos; + + if (sp == NULL) + return -1; + if (strict && info->len != sp->len) + return 0; + + for (i = sp->len - 1; i >= 0; i--) { + pos = strict ? i - sp->len + 1 : 0; + if (pos >= info->len) + return 0; + e = &info->pol[pos]; + + if (match_xfrm_state(sp->x[i].xvec, e)) { + if (!strict) + return 1; + } else if (strict) + return 0; + } + + return strict ? 1 : 0; +} + +static int +match_policy_out(const struct sk_buff *skb, const struct ipt_policy_info *info) +{ + const struct ipt_policy_elem *e; + struct dst_entry *dst = skb->dst; + int strict = info->flags & IPT_POLICY_MATCH_STRICT; + int i, pos; + + if (dst->xfrm == NULL) + return -1; + + for (i = 0; dst && dst->xfrm; dst = dst->child, i++) { + pos = strict ? i : 0; + if (pos >= info->len) + return 0; + e = &info->pol[pos]; + + if (match_xfrm_state(dst->xfrm, e)) { + if (!strict) + return 1; + } else if (strict) + return 0; + } + + return strict ? 1 : 0; +} + +static int match(const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const void *matchinfo, + int offset, + unsigned int protoff, + int *hotdrop) +{ + const struct ipt_policy_info *info = matchinfo; + int ret; + + if (info->flags & IPT_POLICY_MATCH_IN) + ret = match_policy_in(skb, info); + else + ret = match_policy_out(skb, info); + + if (ret < 0) + ret = info->flags & IPT_POLICY_MATCH_NONE ? 1 : 0; + else if (info->flags & IPT_POLICY_MATCH_NONE) + ret = 0; + + return ret; +} + +static int checkentry(const char *tablename, const void *ip_void, + void *matchinfo, unsigned int matchsize, + unsigned int hook_mask) +{ + struct ipt_policy_info *info = matchinfo; + + if (matchsize != IPT_ALIGN(sizeof(*info))) { + printk(KERN_ERR "ipt_policy: matchsize %u != %zu\n", + matchsize, IPT_ALIGN(sizeof(*info))); + return 0; + } + if (!(info->flags & (IPT_POLICY_MATCH_IN|IPT_POLICY_MATCH_OUT))) { + printk(KERN_ERR "ipt_policy: neither incoming nor " + "outgoing policy selected\n"); + return 0; + } + if (hook_mask & (1 << NF_IP_PRE_ROUTING | 1 << NF_IP_LOCAL_IN) + && info->flags & IPT_POLICY_MATCH_OUT) { + printk(KERN_ERR "ipt_policy: output policy not valid in " + "PRE_ROUTING and INPUT\n"); + return 0; + } + if (hook_mask & (1 << NF_IP_POST_ROUTING | 1 << NF_IP_LOCAL_OUT) + && info->flags & IPT_POLICY_MATCH_IN) { + printk(KERN_ERR "ipt_policy: input policy not valid in " + "POST_ROUTING and OUTPUT\n"); + return 0; + } + if (info->len > IPT_POLICY_MAX_ELEM) { + printk(KERN_ERR "ipt_policy: too many policy elements\n"); + return 0; + } + + return 1; +} + +static struct ipt_match policy_match = { + .name = "policy", + .match = match, + .checkentry = checkentry, + .me = THIS_MODULE, +}; + +static int __init init(void) +{ + return ipt_register_match(&policy_match); +} + +static void __exit fini(void) +{ + ipt_unregister_match(&policy_match); +} + +module_init(init); +module_exit(fini); diff --git a/net/ipv4/netfilter/ipt_realm.c b/net/ipv4/netfilter/ipt_realm.c deleted file mode 100644 index 54a6897ebaa6..000000000000 --- a/net/ipv4/netfilter/ipt_realm.c +++ /dev/null @@ -1,76 +0,0 @@ -/* IP tables module for matching the routing realm - * - * $Id: ipt_realm.c,v 1.3 2004/03/05 13:25:40 laforge Exp $ - * - * (C) 2003 by Sampsa Ranta <sampsa@netsonic.fi> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/module.h> -#include <linux/skbuff.h> -#include <linux/netdevice.h> -#include <net/route.h> - -#include <linux/netfilter_ipv4/ipt_realm.h> -#include <linux/netfilter_ipv4/ip_tables.h> - -MODULE_AUTHOR("Sampsa Ranta <sampsa@netsonic.fi>"); -MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("iptables realm match"); - -static int -match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - int *hotdrop) -{ - const struct ipt_realm_info *info = matchinfo; - struct dst_entry *dst = skb->dst; - - return (info->id == (dst->tclassid & info->mask)) ^ info->invert; -} - -static int check(const char *tablename, - const struct ipt_ip *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - if (hook_mask - & ~((1 << NF_IP_POST_ROUTING) | (1 << NF_IP_FORWARD) | - (1 << NF_IP_LOCAL_OUT) | (1 << NF_IP_LOCAL_IN))) { - printk("ipt_realm: only valid for POST_ROUTING, LOCAL_OUT, " - "LOCAL_IN or FORWARD.\n"); - return 0; - } - if (matchsize != IPT_ALIGN(sizeof(struct ipt_realm_info))) { - printk("ipt_realm: invalid matchsize.\n"); - return 0; - } - return 1; -} - -static struct ipt_match realm_match = { - .name = "realm", - .match = match, - .checkentry = check, - .me = THIS_MODULE -}; - -static int __init init(void) -{ - return ipt_register_match(&realm_match); -} - -static void __exit fini(void) -{ - ipt_unregister_match(&realm_match); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv4/netfilter/ipt_recent.c b/net/ipv4/netfilter/ipt_recent.c index 5ddccb18c65e..44611d6d14f5 100644 --- a/net/ipv4/netfilter/ipt_recent.c +++ b/net/ipv4/netfilter/ipt_recent.c @@ -104,6 +104,7 @@ match(const struct sk_buff *skb, const struct net_device *out, const void *matchinfo, int offset, + unsigned int protoff, int *hotdrop); /* Function to hash a given address into the hash table of table_size size */ @@ -317,7 +318,7 @@ static int ip_recent_ctrl(struct file *file, const char __user *input, unsigned skb->nh.iph->daddr = 0; /* Clear ttl since we have no way of knowing it */ skb->nh.iph->ttl = 0; - match(skb,NULL,NULL,info,0,NULL); + match(skb,NULL,NULL,info,0,0,NULL); kfree(skb->nh.iph); out_free_skb: @@ -357,6 +358,7 @@ match(const struct sk_buff *skb, const struct net_device *out, const void *matchinfo, int offset, + unsigned int protoff, int *hotdrop) { int pkt_count, hits_found, ans; @@ -654,7 +656,7 @@ match(const struct sk_buff *skb, */ static int checkentry(const char *tablename, - const struct ipt_ip *ip, + const void *ip, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) diff --git a/net/ipv4/netfilter/ipt_sctp.c b/net/ipv4/netfilter/ipt_sctp.c deleted file mode 100644 index fe2b327bcaa4..000000000000 --- a/net/ipv4/netfilter/ipt_sctp.c +++ /dev/null @@ -1,203 +0,0 @@ -#include <linux/module.h> -#include <linux/skbuff.h> -#include <net/ip.h> -#include <linux/sctp.h> - -#include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netfilter_ipv4/ipt_sctp.h> - -#ifdef DEBUG_SCTP -#define duprintf(format, args...) printk(format , ## args) -#else -#define duprintf(format, args...) -#endif - -#define SCCHECK(cond, option, flag, invflag) (!((flag) & (option)) \ - || (!!((invflag) & (option)) ^ (cond))) - -static int -match_flags(const struct ipt_sctp_flag_info *flag_info, - const int flag_count, - u_int8_t chunktype, - u_int8_t chunkflags) -{ - int i; - - for (i = 0; i < flag_count; i++) { - if (flag_info[i].chunktype == chunktype) { - return (chunkflags & flag_info[i].flag_mask) == flag_info[i].flag; - } - } - - return 1; -} - -static int -match_packet(const struct sk_buff *skb, - const u_int32_t *chunkmap, - int chunk_match_type, - const struct ipt_sctp_flag_info *flag_info, - const int flag_count, - int *hotdrop) -{ - int offset; - u_int32_t chunkmapcopy[256 / sizeof (u_int32_t)]; - sctp_chunkhdr_t _sch, *sch; - -#ifdef DEBUG_SCTP - int i = 0; -#endif - - if (chunk_match_type == SCTP_CHUNK_MATCH_ALL) { - SCTP_CHUNKMAP_COPY(chunkmapcopy, chunkmap); - } - - offset = skb->nh.iph->ihl * 4 + sizeof (sctp_sctphdr_t); - do { - sch = skb_header_pointer(skb, offset, sizeof(_sch), &_sch); - if (sch == NULL) { - duprintf("Dropping invalid SCTP packet.\n"); - *hotdrop = 1; - return 0; - } - - duprintf("Chunk num: %d\toffset: %d\ttype: %d\tlength: %d\tflags: %x\n", - ++i, offset, sch->type, htons(sch->length), sch->flags); - - offset += (htons(sch->length) + 3) & ~3; - - duprintf("skb->len: %d\toffset: %d\n", skb->len, offset); - - if (SCTP_CHUNKMAP_IS_SET(chunkmap, sch->type)) { - switch (chunk_match_type) { - case SCTP_CHUNK_MATCH_ANY: - if (match_flags(flag_info, flag_count, - sch->type, sch->flags)) { - return 1; - } - break; - - case SCTP_CHUNK_MATCH_ALL: - if (match_flags(flag_info, flag_count, - sch->type, sch->flags)) { - SCTP_CHUNKMAP_CLEAR(chunkmapcopy, sch->type); - } - break; - - case SCTP_CHUNK_MATCH_ONLY: - if (!match_flags(flag_info, flag_count, - sch->type, sch->flags)) { - return 0; - } - break; - } - } else { - switch (chunk_match_type) { - case SCTP_CHUNK_MATCH_ONLY: - return 0; - } - } - } while (offset < skb->len); - - switch (chunk_match_type) { - case SCTP_CHUNK_MATCH_ALL: - return SCTP_CHUNKMAP_IS_CLEAR(chunkmap); - case SCTP_CHUNK_MATCH_ANY: - return 0; - case SCTP_CHUNK_MATCH_ONLY: - return 1; - } - - /* This will never be reached, but required to stop compiler whine */ - return 0; -} - -static int -match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - int *hotdrop) -{ - const struct ipt_sctp_info *info; - sctp_sctphdr_t _sh, *sh; - - info = (const struct ipt_sctp_info *)matchinfo; - - if (offset) { - duprintf("Dropping non-first fragment.. FIXME\n"); - return 0; - } - - sh = skb_header_pointer(skb, skb->nh.iph->ihl*4, sizeof(_sh), &_sh); - if (sh == NULL) { - duprintf("Dropping evil TCP offset=0 tinygram.\n"); - *hotdrop = 1; - return 0; - } - duprintf("spt: %d\tdpt: %d\n", ntohs(sh->source), ntohs(sh->dest)); - - return SCCHECK(((ntohs(sh->source) >= info->spts[0]) - && (ntohs(sh->source) <= info->spts[1])), - IPT_SCTP_SRC_PORTS, info->flags, info->invflags) - && SCCHECK(((ntohs(sh->dest) >= info->dpts[0]) - && (ntohs(sh->dest) <= info->dpts[1])), - IPT_SCTP_DEST_PORTS, info->flags, info->invflags) - && SCCHECK(match_packet(skb, info->chunkmap, info->chunk_match_type, - info->flag_info, info->flag_count, - hotdrop), - IPT_SCTP_CHUNK_TYPES, info->flags, info->invflags); -} - -static int -checkentry(const char *tablename, - const struct ipt_ip *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - const struct ipt_sctp_info *info; - - info = (const struct ipt_sctp_info *)matchinfo; - - return ip->proto == IPPROTO_SCTP - && !(ip->invflags & IPT_INV_PROTO) - && matchsize == IPT_ALIGN(sizeof(struct ipt_sctp_info)) - && !(info->flags & ~IPT_SCTP_VALID_FLAGS) - && !(info->invflags & ~IPT_SCTP_VALID_FLAGS) - && !(info->invflags & ~info->flags) - && ((!(info->flags & IPT_SCTP_CHUNK_TYPES)) || - (info->chunk_match_type & - (SCTP_CHUNK_MATCH_ALL - | SCTP_CHUNK_MATCH_ANY - | SCTP_CHUNK_MATCH_ONLY))); -} - -static struct ipt_match sctp_match = -{ - .list = { NULL, NULL}, - .name = "sctp", - .match = &match, - .checkentry = &checkentry, - .destroy = NULL, - .me = THIS_MODULE -}; - -static int __init init(void) -{ - return ipt_register_match(&sctp_match); -} - -static void __exit fini(void) -{ - ipt_unregister_match(&sctp_match); -} - -module_init(init); -module_exit(fini); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Kiran Kumar Immidi"); -MODULE_DESCRIPTION("Match for SCTP protocol packets"); - diff --git a/net/ipv4/netfilter/ipt_state.c b/net/ipv4/netfilter/ipt_state.c deleted file mode 100644 index 4d7f16b70cec..000000000000 --- a/net/ipv4/netfilter/ipt_state.c +++ /dev/null @@ -1,74 +0,0 @@ -/* Kernel module to match connection tracking information. */ - -/* (C) 1999-2001 Paul `Rusty' Russell - * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/module.h> -#include <linux/skbuff.h> -#include <net/netfilter/nf_conntrack_compat.h> -#include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netfilter_ipv4/ipt_state.h> - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Rusty Russell <rusty@rustcorp.com.au>"); -MODULE_DESCRIPTION("iptables connection tracking state match module"); - -static int -match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - int *hotdrop) -{ - const struct ipt_state_info *sinfo = matchinfo; - enum ip_conntrack_info ctinfo; - unsigned int statebit; - - if (nf_ct_is_untracked(skb)) - statebit = IPT_STATE_UNTRACKED; - else if (!nf_ct_get_ctinfo(skb, &ctinfo)) - statebit = IPT_STATE_INVALID; - else - statebit = IPT_STATE_BIT(ctinfo); - - return (sinfo->statemask & statebit); -} - -static int check(const char *tablename, - const struct ipt_ip *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - if (matchsize != IPT_ALIGN(sizeof(struct ipt_state_info))) - return 0; - - return 1; -} - -static struct ipt_match state_match = { - .name = "state", - .match = &match, - .checkentry = &check, - .me = THIS_MODULE, -}; - -static int __init init(void) -{ - need_ip_conntrack(); - return ipt_register_match(&state_match); -} - -static void __exit fini(void) -{ - ipt_unregister_match(&state_match); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv4/netfilter/ipt_string.c b/net/ipv4/netfilter/ipt_string.c deleted file mode 100644 index b5def204d798..000000000000 --- a/net/ipv4/netfilter/ipt_string.c +++ /dev/null @@ -1,91 +0,0 @@ -/* String matching match for iptables - * - * (C) 2005 Pablo Neira Ayuso <pablo@eurodev.net> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/init.h> -#include <linux/module.h> -#include <linux/kernel.h> -#include <linux/skbuff.h> -#include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netfilter_ipv4/ipt_string.h> -#include <linux/textsearch.h> - -MODULE_AUTHOR("Pablo Neira Ayuso <pablo@eurodev.net>"); -MODULE_DESCRIPTION("IP tables string match module"); -MODULE_LICENSE("GPL"); - -static int match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - int *hotdrop) -{ - struct ts_state state; - struct ipt_string_info *conf = (struct ipt_string_info *) matchinfo; - - memset(&state, 0, sizeof(struct ts_state)); - - return (skb_find_text((struct sk_buff *)skb, conf->from_offset, - conf->to_offset, conf->config, &state) - != UINT_MAX) && !conf->invert; -} - -#define STRING_TEXT_PRIV(m) ((struct ipt_string_info *) m) - -static int checkentry(const char *tablename, - const struct ipt_ip *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - struct ipt_string_info *conf = matchinfo; - struct ts_config *ts_conf; - - if (matchsize != IPT_ALIGN(sizeof(struct ipt_string_info))) - return 0; - - /* Damn, can't handle this case properly with iptables... */ - if (conf->from_offset > conf->to_offset) - return 0; - - ts_conf = textsearch_prepare(conf->algo, conf->pattern, conf->patlen, - GFP_KERNEL, TS_AUTOLOAD); - if (IS_ERR(ts_conf)) - return 0; - - conf->config = ts_conf; - - return 1; -} - -static void destroy(void *matchinfo, unsigned int matchsize) -{ - textsearch_destroy(STRING_TEXT_PRIV(matchinfo)->config); -} - -static struct ipt_match string_match = { - .name = "string", - .match = match, - .checkentry = checkentry, - .destroy = destroy, - .me = THIS_MODULE -}; - -static int __init init(void) -{ - return ipt_register_match(&string_match); -} - -static void __exit fini(void) -{ - ipt_unregister_match(&string_match); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv4/netfilter/ipt_tcpmss.c b/net/ipv4/netfilter/ipt_tcpmss.c deleted file mode 100644 index 4dc9b16ab4a3..000000000000 --- a/net/ipv4/netfilter/ipt_tcpmss.c +++ /dev/null @@ -1,127 +0,0 @@ -/* Kernel module to match TCP MSS values. */ - -/* Copyright (C) 2000 Marc Boucher <marc@mbsi.ca> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/module.h> -#include <linux/skbuff.h> -#include <net/tcp.h> - -#include <linux/netfilter_ipv4/ipt_tcpmss.h> -#include <linux/netfilter_ipv4/ip_tables.h> - -#define TH_SYN 0x02 - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Marc Boucher <marc@mbsi.ca>"); -MODULE_DESCRIPTION("iptables TCP MSS match module"); - -/* Returns 1 if the mss option is set and matched by the range, 0 otherwise */ -static inline int -mssoption_match(u_int16_t min, u_int16_t max, - const struct sk_buff *skb, - int invert, - int *hotdrop) -{ - struct tcphdr _tcph, *th; - /* tcp.doff is only 4 bits, ie. max 15 * 4 bytes */ - u8 _opt[15 * 4 - sizeof(_tcph)], *op; - unsigned int i, optlen; - - /* If we don't have the whole header, drop packet. */ - th = skb_header_pointer(skb, skb->nh.iph->ihl * 4, - sizeof(_tcph), &_tcph); - if (th == NULL) - goto dropit; - - /* Malformed. */ - if (th->doff*4 < sizeof(*th)) - goto dropit; - - optlen = th->doff*4 - sizeof(*th); - if (!optlen) - goto out; - - /* Truncated options. */ - op = skb_header_pointer(skb, skb->nh.iph->ihl * 4 + sizeof(*th), - optlen, _opt); - if (op == NULL) - goto dropit; - - for (i = 0; i < optlen; ) { - if (op[i] == TCPOPT_MSS - && (optlen - i) >= TCPOLEN_MSS - && op[i+1] == TCPOLEN_MSS) { - u_int16_t mssval; - - mssval = (op[i+2] << 8) | op[i+3]; - - return (mssval >= min && mssval <= max) ^ invert; - } - if (op[i] < 2) i++; - else i += op[i+1]?:1; - } -out: - return invert; - - dropit: - *hotdrop = 1; - return 0; -} - -static int -match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - int *hotdrop) -{ - const struct ipt_tcpmss_match_info *info = matchinfo; - - return mssoption_match(info->mss_min, info->mss_max, skb, - info->invert, hotdrop); -} - -static int -checkentry(const char *tablename, - const struct ipt_ip *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - if (matchsize != IPT_ALIGN(sizeof(struct ipt_tcpmss_match_info))) - return 0; - - /* Must specify -p tcp */ - if (ip->proto != IPPROTO_TCP || (ip->invflags & IPT_INV_PROTO)) { - printk("tcpmss: Only works on TCP packets\n"); - return 0; - } - - return 1; -} - -static struct ipt_match tcpmss_match = { - .name = "tcpmss", - .match = &match, - .checkentry = &checkentry, - .me = THIS_MODULE, -}; - -static int __init init(void) -{ - return ipt_register_match(&tcpmss_match); -} - -static void __exit fini(void) -{ - ipt_unregister_match(&tcpmss_match); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv4/netfilter/ipt_tos.c b/net/ipv4/netfilter/ipt_tos.c index 086a1bb61e3e..9ab765e126f2 100644 --- a/net/ipv4/netfilter/ipt_tos.c +++ b/net/ipv4/netfilter/ipt_tos.c @@ -23,6 +23,7 @@ match(const struct sk_buff *skb, const struct net_device *out, const void *matchinfo, int offset, + unsigned int protoff, int *hotdrop) { const struct ipt_tos_info *info = matchinfo; @@ -32,7 +33,7 @@ match(const struct sk_buff *skb, static int checkentry(const char *tablename, - const struct ipt_ip *ip, + const void *ip, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) diff --git a/net/ipv4/netfilter/ipt_ttl.c b/net/ipv4/netfilter/ipt_ttl.c index 219aa9de88cc..82da53f430ab 100644 --- a/net/ipv4/netfilter/ipt_ttl.c +++ b/net/ipv4/netfilter/ipt_ttl.c @@ -21,7 +21,7 @@ MODULE_LICENSE("GPL"); static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, const void *matchinfo, - int offset, int *hotdrop) + int offset, unsigned int protoff, int *hotdrop) { const struct ipt_ttl_info *info = matchinfo; @@ -47,7 +47,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, return 0; } -static int checkentry(const char *tablename, const struct ipt_ip *ip, +static int checkentry(const char *tablename, const void *ip, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index 260a4f0a2a90..212a3079085b 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -78,7 +78,8 @@ static struct ipt_table packet_filter = { .name = "filter", .valid_hooks = FILTER_VALID_HOOKS, .lock = RW_LOCK_UNLOCKED, - .me = THIS_MODULE + .me = THIS_MODULE, + .af = AF_INET, }; /* The work comes in here from netfilter.c. */ diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index 160eb11b6e2f..3212a5cc4b6b 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -109,6 +109,7 @@ static struct ipt_table packet_mangler = { .valid_hooks = MANGLE_VALID_HOOKS, .lock = RW_LOCK_UNLOCKED, .me = THIS_MODULE, + .af = AF_INET, }; /* The work comes in here from netfilter.c. */ diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c index 47449ba83eb9..fdb9e9c81e81 100644 --- a/net/ipv4/netfilter/iptable_raw.c +++ b/net/ipv4/netfilter/iptable_raw.c @@ -83,7 +83,8 @@ static struct ipt_table packet_raw = { .name = "raw", .valid_hooks = RAW_VALID_HOOKS, .lock = RW_LOCK_UNLOCKED, - .me = THIS_MODULE + .me = THIS_MODULE, + .af = AF_INET, }; /* The work comes in here from netfilter.c. */ diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index 9bdbb7793971..167619f638c6 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -277,7 +277,7 @@ static struct nf_hook_ops ipv4_conntrack_local_in_ops = { #ifdef CONFIG_SYSCTL /* From nf_conntrack_proto_icmp.c */ -extern unsigned long nf_ct_icmp_timeout; +extern unsigned int nf_ct_icmp_timeout; static struct ctl_table_header *nf_ct_ipv4_sysctl_header; static ctl_table nf_ct_sysctl_table[] = { @@ -575,7 +575,7 @@ MODULE_LICENSE("GPL"); static int __init init(void) { - need_nf_conntrack(); + need_conntrack(); return init_or_cleanup(1); } @@ -587,9 +587,4 @@ static void __exit fini(void) module_init(init); module_exit(fini); -void need_ip_conntrack(void) -{ -} - -EXPORT_SYMBOL(need_ip_conntrack); EXPORT_SYMBOL(nf_ct_ipv4_gather_frags); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 4b0d7e4d6269..f29a12da5109 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -40,12 +40,12 @@ */ #include <linux/config.h> +#include <linux/types.h> #include <asm/atomic.h> #include <asm/byteorder.h> #include <asm/current.h> #include <asm/uaccess.h> #include <asm/ioctls.h> -#include <linux/types.h> #include <linux/stddef.h> #include <linux/slab.h> #include <linux/errno.h> @@ -255,6 +255,7 @@ int raw_rcv(struct sock *sk, struct sk_buff *skb) kfree_skb(skb); return NET_RX_DROP; } + nf_reset(skb); skb_push(skb, skb->data - skb->nh.raw); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index f701a136a6ae..d82c242ea704 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -240,9 +240,9 @@ static unsigned rt_hash_mask; static int rt_hash_log; static unsigned int rt_hash_rnd; -static struct rt_cache_stat *rt_cache_stat; -#define RT_CACHE_STAT_INC(field) \ - (per_cpu_ptr(rt_cache_stat, raw_smp_processor_id())->field++) +static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat); +#define RT_CACHE_STAT_INC(field) \ + (per_cpu(rt_cache_stat, raw_smp_processor_id()).field++) static int rt_intern_hash(unsigned hash, struct rtable *rth, struct rtable **res); @@ -401,7 +401,7 @@ static void *rt_cpu_seq_start(struct seq_file *seq, loff_t *pos) if (!cpu_possible(cpu)) continue; *pos = cpu+1; - return per_cpu_ptr(rt_cache_stat, cpu); + return &per_cpu(rt_cache_stat, cpu); } return NULL; } @@ -414,7 +414,7 @@ static void *rt_cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos) if (!cpu_possible(cpu)) continue; *pos = cpu+1; - return per_cpu_ptr(rt_cache_stat, cpu); + return &per_cpu(rt_cache_stat, cpu); } return NULL; @@ -3160,10 +3160,6 @@ int __init ip_rt_init(void) ipv4_dst_ops.gc_thresh = (rt_hash_mask + 1); ip_rt_max_size = (rt_hash_mask + 1) * 16; - rt_cache_stat = alloc_percpu(struct rt_cache_stat); - if (!rt_cache_stat) - return -ENOMEM; - devinet_init(); ip_fib_init(); @@ -3191,7 +3187,6 @@ int __init ip_rt_init(void) if (!proc_net_fops_create("rt_cache", S_IRUGO, &rt_cache_seq_fops) || !(rtstat_pde = create_proc_entry("rt_cache", S_IRUGO, proc_net_stat))) { - free_percpu(rt_cache_stat); return -ENOMEM; } rtstat_pde->proc_fops = &rt_cpu_seq_fops; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 0a461232329f..a97ed5416c28 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3347,7 +3347,7 @@ tcp_collapse(struct sock *sk, struct sk_buff_head *list, int offset = start - TCP_SKB_CB(skb)->seq; int size = TCP_SKB_CB(skb)->end_seq - start; - if (offset < 0) BUG(); + BUG_ON(offset < 0); if (size > 0) { size = min(copy, size); if (skb_copy_bits(skb, offset, skb_put(nskb, size), size)) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index e9f83e5b28ce..6ea353907af5 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1080,6 +1080,7 @@ process: if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_and_relse; + nf_reset(skb); if (sk_filter(sk, skb, 0)) goto discard_and_relse; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 223abaa72bc5..00840474a449 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -989,6 +989,7 @@ static int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) kfree_skb(skb); return -1; } + nf_reset(skb); if (up->encap_type) { /* @@ -1149,6 +1150,7 @@ int udp_rcv(struct sk_buff *skb) if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto drop; + nf_reset(skb); /* No socket. Drop packet silently, if checksum is wrong */ if (udp_checksum_complete(skb)) diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index 2d3849c38a0f..850d919591d1 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -11,6 +11,8 @@ #include <linux/module.h> #include <linux/string.h> +#include <linux/netfilter.h> +#include <linux/netfilter_ipv4.h> #include <net/inet_ecn.h> #include <net/ip.h> #include <net/xfrm.h> @@ -45,6 +47,23 @@ static int xfrm4_parse_spi(struct sk_buff *skb, u8 nexthdr, u32 *spi, u32 *seq) return xfrm_parse_spi(skb, nexthdr, spi, seq); } +#ifdef CONFIG_NETFILTER +static inline int xfrm4_rcv_encap_finish(struct sk_buff *skb) +{ + struct iphdr *iph = skb->nh.iph; + + if (skb->dst == NULL) { + if (ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, + skb->dev)) + goto drop; + } + return dst_input(skb); +drop: + kfree_skb(skb); + return NET_RX_DROP; +} +#endif + int xfrm4_rcv_encap(struct sk_buff *skb, __u16 encap_type) { int err; @@ -137,6 +156,8 @@ int xfrm4_rcv_encap(struct sk_buff *skb, __u16 encap_type) memcpy(skb->sp->x+skb->sp->len, xfrm_vec, xfrm_nr*sizeof(struct sec_decap_state)); skb->sp->len += xfrm_nr; + nf_reset(skb); + if (decaps) { if (!(skb->dev->flags&IFF_LOOPBACK)) { dst_release(skb->dst); @@ -145,7 +166,17 @@ int xfrm4_rcv_encap(struct sk_buff *skb, __u16 encap_type) netif_rx(skb); return 0; } else { +#ifdef CONFIG_NETFILTER + __skb_push(skb, skb->data - skb->nh.raw); + skb->nh.iph->tot_len = htons(skb->len); + ip_send_check(skb->nh.iph); + + NF_HOOK(PF_INET, NF_IP_PRE_ROUTING, skb, skb->dev, NULL, + xfrm4_rcv_encap_finish); + return 0; +#else return -skb->nh.iph->protocol; +#endif } drop_unlock: diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index 66620a95942a..d4df0ddd424b 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -8,8 +8,10 @@ * 2 of the License, or (at your option) any later version. */ +#include <linux/compiler.h> #include <linux/skbuff.h> #include <linux/spinlock.h> +#include <linux/netfilter_ipv4.h> #include <net/inet_ecn.h> #include <net/ip.h> #include <net/xfrm.h> @@ -95,7 +97,7 @@ out: return ret; } -int xfrm4_output(struct sk_buff *skb) +static int xfrm4_output_one(struct sk_buff *skb) { struct dst_entry *dst = skb->dst; struct xfrm_state *x = dst->xfrm; @@ -113,27 +115,33 @@ int xfrm4_output(struct sk_buff *skb) goto error_nolock; } - spin_lock_bh(&x->lock); - err = xfrm_state_check(x, skb); - if (err) - goto error; + do { + spin_lock_bh(&x->lock); + err = xfrm_state_check(x, skb); + if (err) + goto error; - xfrm4_encap(skb); + xfrm4_encap(skb); - err = x->type->output(x, skb); - if (err) - goto error; + err = x->type->output(x, skb); + if (err) + goto error; - x->curlft.bytes += skb->len; - x->curlft.packets++; + x->curlft.bytes += skb->len; + x->curlft.packets++; - spin_unlock_bh(&x->lock); + spin_unlock_bh(&x->lock); - if (!(skb->dst = dst_pop(dst))) { - err = -EHOSTUNREACH; - goto error_nolock; - } - err = NET_XMIT_BYPASS; + if (!(skb->dst = dst_pop(dst))) { + err = -EHOSTUNREACH; + goto error_nolock; + } + dst = skb->dst; + x = dst->xfrm; + } while (x && !x->props.mode); + + IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED; + err = 0; out_exit: return err; @@ -143,3 +151,33 @@ error_nolock: kfree_skb(skb); goto out_exit; } + +int xfrm4_output_finish(struct sk_buff *skb) +{ + int err; + + while (likely((err = xfrm4_output_one(skb)) == 0)) { + nf_reset(skb); + + err = nf_hook(PF_INET, NF_IP_LOCAL_OUT, &skb, NULL, + skb->dst->dev, dst_output); + if (unlikely(err != 1)) + break; + + if (!skb->dst->xfrm) + return dst_output(skb); + + err = nf_hook(PF_INET, NF_IP_POST_ROUTING, &skb, NULL, + skb->dst->dev, xfrm4_output_finish); + if (unlikely(err != 1)) + break; + } + + return err; +} + +int xfrm4_output(struct sk_buff *skb) +{ + return NF_HOOK(PF_INET, NF_IP_POST_ROUTING, skb, NULL, skb->dst->dev, + xfrm4_output_finish); +} diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c index d23e07fc81fa..dbabf81a9b7b 100644 --- a/net/ipv4/xfrm4_state.c +++ b/net/ipv4/xfrm4_state.c @@ -42,6 +42,21 @@ __xfrm4_init_tempsel(struct xfrm_state *x, struct flowi *fl, x->props.saddr = tmpl->saddr; if (x->props.saddr.a4 == 0) x->props.saddr.a4 = saddr->a4; + if (tmpl->mode && x->props.saddr.a4 == 0) { + struct rtable *rt; + struct flowi fl_tunnel = { + .nl_u = { + .ip4_u = { + .daddr = x->id.daddr.a4, + } + } + }; + if (!xfrm_dst_lookup((struct xfrm_dst **)&rt, + &fl_tunnel, AF_INET)) { + x->props.saddr.a4 = rt->rt_src; + dst_release(&rt->u.dst); + } + } x->props.mode = tmpl->mode; x->props.reqid = tmpl->reqid; x->props.family = AF_INET; |