* : Question regarding ports and process
From: prajakta chaudhari @ 2010-07-10 8:03 UTC (permalink / raw)
To: netdev
Dear All:
I am looking for unix system calls that will find the port used by a
process. I don't want to use the proc file. I want to know if this can be
done using unix system calls, or rtnetlink. I am not getting any clues to
start.
Any help will be highly appreciated.
Thank you,
Prajakta
^ permalink raw reply
* [PATCH 3/4 v3] ll_temac: fix DMA and memory leaks
From: Kulikov Vasiliy @ 2010-07-10 7:30 UTC (permalink / raw)
To: dkirjanov
Cc: Kernel Janitors, David S. Miller, John Linn, Grant Likely,
Jiri Pirko, Brian Hill, netdev
In-Reply-To: <AANLkTilm1b61ikLi28We3aLrF3Ld4c05oFZlh3K1pORe@mail.gmail.com>
temac_dma_bd_init() doesn't free DMA and memory on error. Also
temac_stop() must free them.
Signed-off-by: Denis Kirjanov <dkirjanov@kernel.org>
Signed-off-by: Kulikov Vasiliy <segooon@gmail.com>
---
drivers/net/ll_temac_main.c | 38 ++++++++++++++++++++++++++++++++++++++
1 files changed, 38 insertions(+), 0 deletions(-)
diff --git a/drivers/net/ll_temac_main.c b/drivers/net/ll_temac_main.c
index 5bca20b..9090e79 100644
--- a/drivers/net/ll_temac_main.c
+++ b/drivers/net/ll_temac_main.c
@@ -193,6 +193,41 @@ static int temac_dcr_setup(struct temac_local *lp, struct of_device *op,
#endif
/**
+ * * temac_dma_bd_release - Release buffer descriptor rings
+ */
+static void temac_dma_bd_release(struct net_device *ndev)
+{
+ struct temac_local *lp = netdev_priv(ndev);
+ int i;
+
+ if (lp->rx_skb) {
+ for (i = 0; i < RX_BD_NUM; i++) {
+ if (!lp->rx_skb[i])
+ break;
+ dma_unmap_single(ndev->dev.parent, lp->rx_bd_v[i].phys,
+ XTE_MAX_JUMBO_FRAME_SIZE, DMA_FROM_DEVICE);
+ dev_kfree_skb(lp->rx_skb[i]);
+ }
+ kfree(lp->rx_skb);
+ lp->rx_skb = NULL;
+ }
+
+ if (lp->rx_bd_v) {
+ dma_free_coherent(ndev->dev.parent,
+ sizeof(*lp->rx_bd_v) * RX_BD_NUM,
+ lp->rx_bd_v, lp->rx_bd_p);
+ lp->rx_bd_v = NULL;
+ }
+
+ if (lp->tx_bd_v) {
+ dma_free_coherent(ndev->dev.parent,
+ sizeof(*lp->tx_bd_v) * TX_BD_NUM,
+ lp->tx_bd_v, lp->tx_bd_p);
+ lp->tx_bd_v = NULL;
+ }
+}
+
+/**
* temac_dma_bd_init - Setup buffer descriptor rings
*/
static int temac_dma_bd_init(struct net_device *ndev)
@@ -275,6 +310,7 @@ static int temac_dma_bd_init(struct net_device *ndev)
return 0;
out:
+ temac_dma_bd_release(ndev);
return -ENOMEM;
}
@@ -858,6 +894,8 @@ static int temac_stop(struct net_device *ndev)
phy_disconnect(lp->phy_dev);
lp->phy_dev = NULL;
+ temac_dma_bd_release(ndev);
+
return 0;
}
--
1.7.0.4
^ permalink raw reply related
* [PATCH net-next-2.6] net/ipv4: EXPORT_SYMBOL cleanups
From: Eric Dumazet @ 2010-07-10 7:22 UTC (permalink / raw)
To: David Miller; +Cc: netdev
CodingStyle cleanups
EXPORT_SYMBOL should immediately follow the symbol declaration.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
---
net/ipv4/arp.c | 18 ++++++---------
net/ipv4/datagram.c | 2 -
net/ipv4/fib_frontend.c | 7 ++----
net/ipv4/icmp.c | 7 ++----
net/ipv4/igmp.c | 9 +++----
net/ipv4/inet_connection_sock.c | 19 ----------------
net/ipv4/inet_fragment.c | 1
net/ipv4/inet_hashtables.c | 4 ---
net/ipv4/ip_fragment.c | 3 --
net/ipv4/ip_output.c | 9 ++-----
net/ipv4/netfilter/ipt_REJECT.c | 2 -
net/ipv4/protocol.c | 3 --
net/ipv4/route.c | 7 +-----
net/ipv4/tcp.c | 35 ++++++++++--------------------
net/ipv4/tcp_input.c | 18 ++++++---------
net/ipv4/tcp_ipv4.c | 35 ++++++++++--------------------
net/ipv4/tcp_minisocks.c | 9 ++-----
net/ipv4/tcp_output.c | 12 ++++------
net/ipv4/tcp_timer.c | 1
net/ipv4/tunnel4.c | 2 -
net/ipv4/udplite.c | 3 --
net/ipv4/xfrm4_input.c | 1
22 files changed, 67 insertions(+), 140 deletions(-)
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 09ead1b..96c1955 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -116,6 +116,7 @@
#if defined(CONFIG_ATM_CLIP) || defined(CONFIG_ATM_CLIP_MODULE)
#include <net/atmclip.h>
struct neigh_table *clip_tbl_hook;
+EXPORT_SYMBOL(clip_tbl_hook);
#endif
#include <asm/system.h>
@@ -169,6 +170,7 @@ const struct neigh_ops arp_broken_ops = {
.hh_output = dev_queue_xmit,
.queue_xmit = dev_queue_xmit,
};
+EXPORT_SYMBOL(arp_broken_ops);
struct neigh_table arp_tbl = {
.family = AF_INET,
@@ -198,6 +200,7 @@ struct neigh_table arp_tbl = {
.gc_thresh2 = 512,
.gc_thresh3 = 1024,
};
+EXPORT_SYMBOL(arp_tbl);
int arp_mc_map(__be32 addr, u8 *haddr, struct net_device *dev, int dir)
{
@@ -499,6 +502,7 @@ int arp_find(unsigned char *haddr, struct sk_buff *skb)
kfree_skb(skb);
return 1;
}
+EXPORT_SYMBOL(arp_find);
/* END OF OBSOLETE FUNCTIONS */
@@ -700,6 +704,7 @@ out:
kfree_skb(skb);
return NULL;
}
+EXPORT_SYMBOL(arp_create);
/*
* Send an arp packet.
@@ -709,6 +714,7 @@ void arp_xmit(struct sk_buff *skb)
/* Send it off, maybe filter it using firewalling first. */
NF_HOOK(NFPROTO_ARP, NF_ARP_OUT, skb, NULL, skb->dev, dev_queue_xmit);
}
+EXPORT_SYMBOL(arp_xmit);
/*
* Create and send an arp packet.
@@ -735,6 +741,7 @@ void arp_send(int type, int ptype, __be32 dest_ip,
arp_xmit(skb);
}
+EXPORT_SYMBOL(arp_send);
/*
* Process an arp request.
@@ -1452,14 +1459,3 @@ static int __init arp_proc_init(void)
}
#endif /* CONFIG_PROC_FS */
-
-EXPORT_SYMBOL(arp_broken_ops);
-EXPORT_SYMBOL(arp_find);
-EXPORT_SYMBOL(arp_create);
-EXPORT_SYMBOL(arp_xmit);
-EXPORT_SYMBOL(arp_send);
-EXPORT_SYMBOL(arp_tbl);
-
-#if defined(CONFIG_ATM_CLIP) || defined(CONFIG_ATM_CLIP_MODULE)
-EXPORT_SYMBOL(clip_tbl_hook);
-#endif
diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index fe3daa7..f055094 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -72,6 +72,4 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
sk_dst_set(sk, &rt->dst);
return(0);
}
-
EXPORT_SYMBOL(ip4_datagram_connect);
-
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index e830f7a..a439689 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -175,6 +175,7 @@ out:
fib_res_put(&res);
return dev;
}
+EXPORT_SYMBOL(ip_dev_find);
/*
* Find address type as if only "dev" was present in the system. If
@@ -214,12 +215,14 @@ unsigned int inet_addr_type(struct net *net, __be32 addr)
{
return __inet_dev_addr_type(net, NULL, addr);
}
+EXPORT_SYMBOL(inet_addr_type);
unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev,
__be32 addr)
{
return __inet_dev_addr_type(net, dev, addr);
}
+EXPORT_SYMBOL(inet_dev_addr_type);
/* Given (packet source, input interface) and optional (dst, oif, tos):
- (main) check, that source is valid i.e. not broadcast or our local
@@ -1077,7 +1080,3 @@ void __init ip_fib_init(void)
fib_hash_init();
}
-
-EXPORT_SYMBOL(inet_addr_type);
-EXPORT_SYMBOL(inet_dev_addr_type);
-EXPORT_SYMBOL(ip_dev_find);
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 7569b21..a0d847c 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -181,6 +181,7 @@ const struct icmp_err icmp_err_convert[] = {
.fatal = 1,
},
};
+EXPORT_SYMBOL(icmp_err_convert);
/*
* ICMP control array. This specifies what to do with each ICMP.
@@ -267,6 +268,7 @@ int xrlim_allow(struct dst_entry *dst, int timeout)
dst->rate_tokens = token;
return rc;
}
+EXPORT_SYMBOL(xrlim_allow);
static inline int icmpv4_xrlim_allow(struct net *net, struct rtable *rt,
int type, int code)
@@ -647,6 +649,7 @@ out_unlock:
icmp_xmit_unlock(sk);
out:;
}
+EXPORT_SYMBOL(icmp_send);
/*
@@ -1214,7 +1217,3 @@ int __init icmp_init(void)
{
return register_pernet_subsys(&icmp_sk_ops);
}
-
-EXPORT_SYMBOL(icmp_err_convert);
-EXPORT_SYMBOL(icmp_send);
-EXPORT_SYMBOL(xrlim_allow);
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index b5580d4..a1ad0e7 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -1244,6 +1244,7 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr)
out:
return;
}
+EXPORT_SYMBOL(ip_mc_inc_group);
/*
* Resend IGMP JOIN report; used for bonding.
@@ -1266,6 +1267,7 @@ void ip_mc_rejoin_group(struct ip_mc_list *im)
igmp_ifc_event(in_dev);
#endif
}
+EXPORT_SYMBOL(ip_mc_rejoin_group);
/*
* A socket has left a multicast group on device dev
@@ -1296,6 +1298,7 @@ void ip_mc_dec_group(struct in_device *in_dev, __be32 addr)
}
}
}
+EXPORT_SYMBOL(ip_mc_dec_group);
/* Device changing type */
@@ -1804,6 +1807,7 @@ done:
rtnl_unlock();
return err;
}
+EXPORT_SYMBOL(ip_mc_join_group);
static void ip_sf_socklist_reclaim(struct rcu_head *rp)
{
@@ -2676,8 +2680,3 @@ int __init igmp_mc_proc_init(void)
return register_pernet_subsys(&igmp_net_ops);
}
#endif
-
-EXPORT_SYMBOL(ip_mc_dec_group);
-EXPORT_SYMBOL(ip_mc_inc_group);
-EXPORT_SYMBOL(ip_mc_join_group);
-EXPORT_SYMBOL(ip_mc_rejoin_group);
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 57c9e4d..7174370 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -84,7 +84,6 @@ int inet_csk_bind_conflict(const struct sock *sk,
}
return node != NULL;
}
-
EXPORT_SYMBOL_GPL(inet_csk_bind_conflict);
/* Obtain a reference to a local port for the given sock,
@@ -212,7 +211,6 @@ fail:
local_bh_enable();
return ret;
}
-
EXPORT_SYMBOL_GPL(inet_csk_get_port);
/*
@@ -305,7 +303,6 @@ out_err:
*err = error;
goto out;
}
-
EXPORT_SYMBOL(inet_csk_accept);
/*
@@ -327,7 +324,6 @@ void inet_csk_init_xmit_timers(struct sock *sk,
setup_timer(&sk->sk_timer, keepalive_handler, (unsigned long)sk);
icsk->icsk_pending = icsk->icsk_ack.pending = 0;
}
-
EXPORT_SYMBOL(inet_csk_init_xmit_timers);
void inet_csk_clear_xmit_timers(struct sock *sk)
@@ -340,21 +336,18 @@ void inet_csk_clear_xmit_timers(struct sock *sk)
sk_stop_timer(sk, &icsk->icsk_delack_timer);
sk_stop_timer(sk, &sk->sk_timer);
}
-
EXPORT_SYMBOL(inet_csk_clear_xmit_timers);
void inet_csk_delete_keepalive_timer(struct sock *sk)
{
sk_stop_timer(sk, &sk->sk_timer);
}
-
EXPORT_SYMBOL(inet_csk_delete_keepalive_timer);
void inet_csk_reset_keepalive_timer(struct sock *sk, unsigned long len)
{
sk_reset_timer(sk, &sk->sk_timer, jiffies + len);
}
-
EXPORT_SYMBOL(inet_csk_reset_keepalive_timer);
struct dst_entry *inet_csk_route_req(struct sock *sk,
@@ -391,7 +384,6 @@ no_route:
IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES);
return NULL;
}
-
EXPORT_SYMBOL_GPL(inet_csk_route_req);
static inline u32 inet_synq_hash(const __be32 raddr, const __be16 rport,
@@ -433,7 +425,6 @@ struct request_sock *inet_csk_search_req(const struct sock *sk,
return req;
}
-
EXPORT_SYMBOL_GPL(inet_csk_search_req);
void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req,
@@ -447,11 +438,11 @@ void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req,
reqsk_queue_hash_req(&icsk->icsk_accept_queue, h, req, timeout);
inet_csk_reqsk_queue_added(sk, timeout);
}
+EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_hash_add);
/* Only thing we need from tcp.h */
extern int sysctl_tcp_synack_retries;
-EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_hash_add);
/* Decide when to expire the request and when to resend SYN-ACK */
static inline void syn_ack_recalc(struct request_sock *req, const int thresh,
@@ -569,7 +560,6 @@ void inet_csk_reqsk_queue_prune(struct sock *parent,
if (lopt->qlen)
inet_csk_reset_keepalive_timer(parent, interval);
}
-
EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_prune);
struct sock *inet_csk_clone(struct sock *sk, const struct request_sock *req,
@@ -599,7 +589,6 @@ struct sock *inet_csk_clone(struct sock *sk, const struct request_sock *req,
}
return newsk;
}
-
EXPORT_SYMBOL_GPL(inet_csk_clone);
/*
@@ -630,7 +619,6 @@ void inet_csk_destroy_sock(struct sock *sk)
percpu_counter_dec(sk->sk_prot->orphan_count);
sock_put(sk);
}
-
EXPORT_SYMBOL(inet_csk_destroy_sock);
int inet_csk_listen_start(struct sock *sk, const int nr_table_entries)
@@ -665,7 +653,6 @@ int inet_csk_listen_start(struct sock *sk, const int nr_table_entries)
__reqsk_queue_destroy(&icsk->icsk_accept_queue);
return -EADDRINUSE;
}
-
EXPORT_SYMBOL_GPL(inet_csk_listen_start);
/*
@@ -720,7 +707,6 @@ void inet_csk_listen_stop(struct sock *sk)
}
WARN_ON(sk->sk_ack_backlog);
}
-
EXPORT_SYMBOL_GPL(inet_csk_listen_stop);
void inet_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr)
@@ -732,7 +718,6 @@ void inet_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr)
sin->sin_addr.s_addr = inet->inet_daddr;
sin->sin_port = inet->inet_dport;
}
-
EXPORT_SYMBOL_GPL(inet_csk_addr2sockaddr);
#ifdef CONFIG_COMPAT
@@ -747,7 +732,6 @@ int inet_csk_compat_getsockopt(struct sock *sk, int level, int optname,
return icsk->icsk_af_ops->getsockopt(sk, level, optname,
optval, optlen);
}
-
EXPORT_SYMBOL_GPL(inet_csk_compat_getsockopt);
int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname,
@@ -761,6 +745,5 @@ int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname,
return icsk->icsk_af_ops->setsockopt(sk, level, optname,
optval, optlen);
}
-
EXPORT_SYMBOL_GPL(inet_csk_compat_setsockopt);
#endif
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index a2ca6ae..5ff2a51 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -114,7 +114,6 @@ void inet_frag_kill(struct inet_frag_queue *fq, struct inet_frags *f)
fq->last_in |= INET_FRAG_COMPLETE;
}
}
-
EXPORT_SYMBOL(inet_frag_kill);
static inline void frag_kfree_skb(struct netns_frags *nf, struct inet_frags *f,
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index d3e160a..fb7ad5a 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -99,7 +99,6 @@ void inet_put_port(struct sock *sk)
__inet_put_port(sk);
local_bh_enable();
}
-
EXPORT_SYMBOL(inet_put_port);
void __inet_inherit_port(struct sock *sk, struct sock *child)
@@ -116,7 +115,6 @@ void __inet_inherit_port(struct sock *sk, struct sock *child)
inet_csk(child)->icsk_bind_hash = tb;
spin_unlock(&head->lock);
}
-
EXPORT_SYMBOL_GPL(__inet_inherit_port);
static inline int compute_score(struct sock *sk, struct net *net,
@@ -546,7 +544,6 @@ int inet_hash_connect(struct inet_timewait_death_row *death_row,
return __inet_hash_connect(death_row, sk, inet_sk_port_offset(sk),
__inet_check_established, __inet_hash_nolisten);
}
-
EXPORT_SYMBOL_GPL(inet_hash_connect);
void inet_hashinfo_init(struct inet_hashinfo *h)
@@ -560,5 +557,4 @@ void inet_hashinfo_init(struct inet_hashinfo *h)
i + LISTENING_NULLS_BASE);
}
}
-
EXPORT_SYMBOL_GPL(inet_hashinfo_init);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index dd0dbf0..b7c4165 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -632,6 +632,7 @@ int ip_defrag(struct sk_buff *skb, u32 user)
kfree_skb(skb);
return -ENOMEM;
}
+EXPORT_SYMBOL(ip_defrag);
#ifdef CONFIG_SYSCTL
static int zero;
@@ -785,5 +786,3 @@ void __init ipfrag_init(void)
ip4_frags.secret_interval = 10 * 60 * HZ;
inet_frags_init(&ip4_frags);
}
-
-EXPORT_SYMBOL(ip_defrag);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 663cb2a..6652bd9 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -89,6 +89,7 @@ __inline__ void ip_send_check(struct iphdr *iph)
iph->check = 0;
iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
}
+EXPORT_SYMBOL(ip_send_check);
int __ip_local_out(struct sk_buff *skb)
{
@@ -172,7 +173,6 @@ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk,
/* Send it out. */
return ip_local_out(skb);
}
-
EXPORT_SYMBOL_GPL(ip_build_and_send_pkt);
static inline int ip_finish_output2(struct sk_buff *skb)
@@ -403,6 +403,7 @@ no_route:
kfree_skb(skb);
return -EHOSTUNREACH;
}
+EXPORT_SYMBOL(ip_queue_xmit);
static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
@@ -696,7 +697,6 @@ fail:
IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
return err;
}
-
EXPORT_SYMBOL(ip_fragment);
int
@@ -715,6 +715,7 @@ ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk
}
return 0;
}
+EXPORT_SYMBOL(ip_generic_getfrag);
static inline __wsum
csum_page(struct page *page, int offset, int copy)
@@ -1447,7 +1448,3 @@ void __init ip_init(void)
igmp_mc_proc_init();
#endif
}
-
-EXPORT_SYMBOL(ip_generic_getfrag);
-EXPORT_SYMBOL(ip_queue_xmit);
-EXPORT_SYMBOL(ip_send_check);
diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c
index f5f4a88..bbbd273 100644
--- a/net/ipv4/netfilter/ipt_REJECT.c
+++ b/net/ipv4/netfilter/ipt_REJECT.c
@@ -109,7 +109,7 @@ static void send_reset(struct sk_buff *oldskb, int hook)
addr_type = RTN_LOCAL;
/* ip_route_me_harder expects skb->dst to be set */
- skb_dst_set(nskb, dst_clone(skb_dst(oldskb)));
+ skb_dst_set_noref(nskb, skb_dst(oldskb));
if (ip_route_me_harder(nskb, addr_type))
goto free_nskb;
diff --git a/net/ipv4/protocol.c b/net/ipv4/protocol.c
index 542f22f..f2d2973 100644
--- a/net/ipv4/protocol.c
+++ b/net/ipv4/protocol.c
@@ -52,6 +52,7 @@ int inet_add_protocol(const struct net_protocol *prot, unsigned char protocol)
return ret;
}
+EXPORT_SYMBOL(inet_add_protocol);
/*
* Remove a protocol from the hash tables.
@@ -76,6 +77,4 @@ int inet_del_protocol(const struct net_protocol *prot, unsigned char protocol)
return ret;
}
-
-EXPORT_SYMBOL(inet_add_protocol);
EXPORT_SYMBOL(inet_del_protocol);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 03430de..562ce92 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1324,6 +1324,7 @@ void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more)
ip_select_fb_ident(iph);
}
+EXPORT_SYMBOL(__ip_select_ident);
static void rt_del(unsigned hash, struct rtable *rt)
{
@@ -2735,7 +2736,6 @@ int __ip_route_output_key(struct net *net, struct rtable **rp,
slow_output:
return ip_route_output_slow(net, rp, flp);
}
-
EXPORT_SYMBOL_GPL(__ip_route_output_key);
static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu)
@@ -2819,13 +2819,13 @@ int ip_route_output_flow(struct net *net, struct rtable **rp, struct flowi *flp,
return 0;
}
-
EXPORT_SYMBOL_GPL(ip_route_output_flow);
int ip_route_output_key(struct net *net, struct rtable **rp, struct flowi *flp)
{
return ip_route_output_flow(net, rp, flp, NULL, 0);
}
+EXPORT_SYMBOL(ip_route_output_key);
static int rt_fill_info(struct net *net,
struct sk_buff *skb, u32 pid, u32 seq, int event,
@@ -3363,6 +3363,3 @@ void __init ip_static_sysctl_init(void)
register_sysctl_paths(ipv4_path, ipv4_skeleton);
}
#endif
-
-EXPORT_SYMBOL(__ip_select_ident);
-EXPORT_SYMBOL(ip_route_output_key);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 4e6ddfb..b8601b7 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -315,7 +315,6 @@ struct tcp_splice_state {
* is strict, actions are advisory and have some latency.
*/
int tcp_memory_pressure __read_mostly;
-
EXPORT_SYMBOL(tcp_memory_pressure);
void tcp_enter_memory_pressure(struct sock *sk)
@@ -325,7 +324,6 @@ void tcp_enter_memory_pressure(struct sock *sk)
tcp_memory_pressure = 1;
}
}
-
EXPORT_SYMBOL(tcp_enter_memory_pressure);
/* Convert seconds to retransmits based on initial and max timeout */
@@ -460,6 +458,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
}
return mask;
}
+EXPORT_SYMBOL(tcp_poll);
int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
{
@@ -508,6 +507,7 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
return put_user(answ, (int __user *)arg);
}
+EXPORT_SYMBOL(tcp_ioctl);
static inline void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb)
{
@@ -675,6 +675,7 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos,
return ret;
}
+EXPORT_SYMBOL(tcp_splice_read);
struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp)
{
@@ -873,6 +874,7 @@ ssize_t tcp_sendpage(struct socket *sock, struct page *page, int offset,
release_sock(sk);
return res;
}
+EXPORT_SYMBOL(tcp_sendpage);
#define TCP_PAGE(sk) (sk->sk_sndmsg_page)
#define TCP_OFF(sk) (sk->sk_sndmsg_off)
@@ -1121,6 +1123,7 @@ out_err:
release_sock(sk);
return err;
}
+EXPORT_SYMBOL(tcp_sendmsg);
/*
* Handle reading urgent data. BSD has very simple semantics for
@@ -1380,6 +1383,7 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
tcp_cleanup_rbuf(sk, copied);
return copied;
}
+EXPORT_SYMBOL(tcp_read_sock);
/*
* This routine copies from a sock struct into the user buffer.
@@ -1774,6 +1778,7 @@ recv_urg:
err = tcp_recv_urg(sk, msg, len, flags);
goto out;
}
+EXPORT_SYMBOL(tcp_recvmsg);
void tcp_set_state(struct sock *sk, int state)
{
@@ -1866,6 +1871,7 @@ void tcp_shutdown(struct sock *sk, int how)
tcp_send_fin(sk);
}
}
+EXPORT_SYMBOL(tcp_shutdown);
void tcp_close(struct sock *sk, long timeout)
{
@@ -2029,6 +2035,7 @@ out:
local_bh_enable();
sock_put(sk);
}
+EXPORT_SYMBOL(tcp_close);
/* These states need RST on ABORT according to RFC793 */
@@ -2102,6 +2109,7 @@ int tcp_disconnect(struct sock *sk, int flags)
sk->sk_error_report(sk);
return err;
}
+EXPORT_SYMBOL(tcp_disconnect);
/*
* Socket option code for TCP.
@@ -2400,6 +2408,7 @@ int tcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval,
optval, optlen);
return do_tcp_setsockopt(sk, level, optname, optval, optlen);
}
+EXPORT_SYMBOL(tcp_setsockopt);
#ifdef CONFIG_COMPAT
int compat_tcp_setsockopt(struct sock *sk, int level, int optname,
@@ -2410,7 +2419,6 @@ int compat_tcp_setsockopt(struct sock *sk, int level, int optname,
optval, optlen);
return do_tcp_setsockopt(sk, level, optname, optval, optlen);
}
-
EXPORT_SYMBOL(compat_tcp_setsockopt);
#endif
@@ -2476,7 +2484,6 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
info->tcpi_total_retrans = tp->total_retrans;
}
-
EXPORT_SYMBOL_GPL(tcp_get_info);
static int do_tcp_getsockopt(struct sock *sk, int level,
@@ -2615,6 +2622,7 @@ int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval,
optval, optlen);
return do_tcp_getsockopt(sk, level, optname, optval, optlen);
}
+EXPORT_SYMBOL(tcp_getsockopt);
#ifdef CONFIG_COMPAT
int compat_tcp_getsockopt(struct sock *sk, int level, int optname,
@@ -2625,7 +2633,6 @@ int compat_tcp_getsockopt(struct sock *sk, int level, int optname,
optval, optlen);
return do_tcp_getsockopt(sk, level, optname, optval, optlen);
}
-
EXPORT_SYMBOL(compat_tcp_getsockopt);
#endif
@@ -2862,7 +2869,6 @@ void tcp_free_md5sig_pool(void)
if (pool)
__tcp_free_md5sig_pool(pool);
}
-
EXPORT_SYMBOL(tcp_free_md5sig_pool);
static struct tcp_md5sig_pool * __percpu *
@@ -2938,7 +2944,6 @@ retry:
}
return pool;
}
-
EXPORT_SYMBOL(tcp_alloc_md5sig_pool);
@@ -2990,7 +2995,6 @@ int tcp_md5_hash_header(struct tcp_md5sig_pool *hp,
th->check = old_checksum;
return err;
}
-
EXPORT_SYMBOL(tcp_md5_hash_header);
int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *hp,
@@ -3024,7 +3028,6 @@ int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *hp,
return 0;
}
-
EXPORT_SYMBOL(tcp_md5_hash_skb_data);
int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, struct tcp_md5sig_key *key)
@@ -3034,7 +3037,6 @@ int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, struct tcp_md5sig_key *key)
sg_init_one(&sg, key->key, key->keylen);
return crypto_hash_update(&hp->md5_desc, &sg, key->keylen);
}
-
EXPORT_SYMBOL(tcp_md5_hash_key);
#endif
@@ -3306,16 +3308,3 @@ void __init tcp_init(void)
tcp_secret_retiring = &tcp_secret_two;
tcp_secret_secondary = &tcp_secret_two;
}
-
-EXPORT_SYMBOL(tcp_close);
-EXPORT_SYMBOL(tcp_disconnect);
-EXPORT_SYMBOL(tcp_getsockopt);
-EXPORT_SYMBOL(tcp_ioctl);
-EXPORT_SYMBOL(tcp_poll);
-EXPORT_SYMBOL(tcp_read_sock);
-EXPORT_SYMBOL(tcp_recvmsg);
-EXPORT_SYMBOL(tcp_sendmsg);
-EXPORT_SYMBOL(tcp_splice_read);
-EXPORT_SYMBOL(tcp_sendpage);
-EXPORT_SYMBOL(tcp_setsockopt);
-EXPORT_SYMBOL(tcp_shutdown);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 0433466..3c426cb 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -78,10 +78,13 @@ int sysctl_tcp_window_scaling __read_mostly = 1;
int sysctl_tcp_sack __read_mostly = 1;
int sysctl_tcp_fack __read_mostly = 1;
int sysctl_tcp_reordering __read_mostly = TCP_FASTRETRANS_THRESH;
+EXPORT_SYMBOL(sysctl_tcp_reordering);
int sysctl_tcp_ecn __read_mostly = 2;
+EXPORT_SYMBOL(sysctl_tcp_ecn);
int sysctl_tcp_dsack __read_mostly = 1;
int sysctl_tcp_app_win __read_mostly = 31;
int sysctl_tcp_adv_win_scale __read_mostly = 2;
+EXPORT_SYMBOL(sysctl_tcp_adv_win_scale);
int sysctl_tcp_stdurg __read_mostly;
int sysctl_tcp_rfc1337 __read_mostly;
@@ -419,6 +422,7 @@ void tcp_initialize_rcv_mss(struct sock *sk)
inet_csk(sk)->icsk_ack.rcv_mss = hint;
}
+EXPORT_SYMBOL(tcp_initialize_rcv_mss);
/* Receiver "autotuning" code.
*
@@ -2938,6 +2942,7 @@ void tcp_simple_retransmit(struct sock *sk)
}
tcp_xmit_retransmit_queue(sk);
}
+EXPORT_SYMBOL(tcp_simple_retransmit);
/* Process an event, which can update packets-in-flight not trivially.
* Main goal of this function is to calculate new estimate for left_out,
@@ -3858,6 +3863,7 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx,
}
}
}
+EXPORT_SYMBOL(tcp_parse_options);
static int tcp_parse_aligned_timestamp(struct tcp_sock *tp, struct tcphdr *th)
{
@@ -3931,6 +3937,7 @@ u8 *tcp_parse_md5sig_option(struct tcphdr *th)
}
return NULL;
}
+EXPORT_SYMBOL(tcp_parse_md5sig_option);
#endif
static inline void tcp_store_ts_recent(struct tcp_sock *tp)
@@ -5432,6 +5439,7 @@ discard:
__kfree_skb(skb);
return 0;
}
+EXPORT_SYMBOL(tcp_rcv_established);
static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
struct tcphdr *th, unsigned len)
@@ -5931,14 +5939,4 @@ discard:
}
return 0;
}
-
-EXPORT_SYMBOL(sysctl_tcp_ecn);
-EXPORT_SYMBOL(sysctl_tcp_reordering);
-EXPORT_SYMBOL(sysctl_tcp_adv_win_scale);
-EXPORT_SYMBOL(tcp_parse_options);
-#ifdef CONFIG_TCP_MD5SIG
-EXPORT_SYMBOL(tcp_parse_md5sig_option);
-#endif
-EXPORT_SYMBOL(tcp_rcv_established);
EXPORT_SYMBOL(tcp_rcv_state_process);
-EXPORT_SYMBOL(tcp_initialize_rcv_mss);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 8fa32f5..44545e8 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -84,6 +84,7 @@
int sysctl_tcp_tw_reuse __read_mostly;
int sysctl_tcp_low_latency __read_mostly;
+EXPORT_SYMBOL(sysctl_tcp_low_latency);
#ifdef CONFIG_TCP_MD5SIG
@@ -100,6 +101,7 @@ struct tcp_md5sig_key *tcp_v4_md5_do_lookup(struct sock *sk, __be32 addr)
#endif
struct inet_hashinfo tcp_hashinfo;
+EXPORT_SYMBOL(tcp_hashinfo);
static inline __u32 tcp_v4_init_sequence(struct sk_buff *skb)
{
@@ -139,7 +141,6 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
return 0;
}
-
EXPORT_SYMBOL_GPL(tcp_twsk_unique);
/* This will initiate an outgoing connection. */
@@ -267,6 +268,7 @@ failure:
inet->inet_dport = 0;
return err;
}
+EXPORT_SYMBOL(tcp_v4_connect);
/*
* This routine does path mtu discovery as defined in RFC1191.
@@ -545,6 +547,7 @@ void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb)
__tcp_v4_send_check(skb, inet->inet_saddr, inet->inet_daddr);
}
+EXPORT_SYMBOL(tcp_v4_send_check);
int tcp_v4_gso_send_check(struct sk_buff *skb)
{
@@ -860,7 +863,6 @@ struct tcp_md5sig_key *tcp_v4_md5_lookup(struct sock *sk,
{
return tcp_v4_md5_do_lookup(sk, inet_sk(addr_sk)->inet_daddr);
}
-
EXPORT_SYMBOL(tcp_v4_md5_lookup);
static struct tcp_md5sig_key *tcp_v4_reqsk_md5_lookup(struct sock *sk,
@@ -927,7 +929,6 @@ int tcp_v4_md5_do_add(struct sock *sk, __be32 addr,
}
return 0;
}
-
EXPORT_SYMBOL(tcp_v4_md5_do_add);
static int tcp_v4_md5_add_func(struct sock *sk, struct sock *addr_sk,
@@ -965,7 +966,6 @@ int tcp_v4_md5_do_del(struct sock *sk, __be32 addr)
}
return -ENOENT;
}
-
EXPORT_SYMBOL(tcp_v4_md5_do_del);
static void tcp_v4_clear_md5_list(struct sock *sk)
@@ -1138,7 +1138,6 @@ clear_hash_noput:
memset(md5_hash, 0, 16);
return 1;
}
-
EXPORT_SYMBOL(tcp_v4_md5_hash_skb);
static int tcp_v4_inbound_md5_hash(struct sock *sk, struct sk_buff *skb)
@@ -1396,6 +1395,7 @@ drop_and_free:
drop:
return 0;
}
+EXPORT_SYMBOL(tcp_v4_conn_request);
/*
@@ -1481,6 +1481,7 @@ exit:
dst_release(dst);
return NULL;
}
+EXPORT_SYMBOL(tcp_v4_syn_recv_sock);
static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb)
{
@@ -1610,6 +1611,7 @@ csum_err:
TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_INERRS);
goto discard;
}
+EXPORT_SYMBOL(tcp_v4_do_rcv);
/*
* From tcp_input.c
@@ -1796,6 +1798,7 @@ int tcp_v4_remember_stamp(struct sock *sk)
return 0;
}
+EXPORT_SYMBOL(tcp_v4_remember_stamp);
int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw)
{
@@ -1835,6 +1838,7 @@ const struct inet_connection_sock_af_ops ipv4_specific = {
.compat_getsockopt = compat_ip_getsockopt,
#endif
};
+EXPORT_SYMBOL(ipv4_specific);
#ifdef CONFIG_TCP_MD5SIG
static const struct tcp_sock_af_ops tcp_sock_ipv4_specific = {
@@ -1963,7 +1967,6 @@ void tcp_v4_destroy_sock(struct sock *sk)
percpu_counter_dec(&tcp_sockets_allocated);
}
-
EXPORT_SYMBOL(tcp_v4_destroy_sock);
#ifdef CONFIG_PROC_FS
@@ -2367,11 +2370,13 @@ int tcp_proc_register(struct net *net, struct tcp_seq_afinfo *afinfo)
rc = -ENOMEM;
return rc;
}
+EXPORT_SYMBOL(tcp_proc_register);
void tcp_proc_unregister(struct net *net, struct tcp_seq_afinfo *afinfo)
{
proc_net_remove(net, afinfo->name);
}
+EXPORT_SYMBOL(tcp_proc_unregister);
static void get_openreq4(struct sock *sk, struct request_sock *req,
struct seq_file *f, int i, int uid, int *len)
@@ -2618,6 +2623,7 @@ struct proto tcp_prot = {
.compat_getsockopt = compat_tcp_getsockopt,
#endif
};
+EXPORT_SYMBOL(tcp_prot);
static int __net_init tcp_sk_init(struct net *net)
@@ -2648,20 +2654,3 @@ void __init tcp_v4_init(void)
if (register_pernet_subsys(&tcp_sk_ops))
panic("Failed to create the TCP control socket.\n");
}
-
-EXPORT_SYMBOL(ipv4_specific);
-EXPORT_SYMBOL(tcp_hashinfo);
-EXPORT_SYMBOL(tcp_prot);
-EXPORT_SYMBOL(tcp_v4_conn_request);
-EXPORT_SYMBOL(tcp_v4_connect);
-EXPORT_SYMBOL(tcp_v4_do_rcv);
-EXPORT_SYMBOL(tcp_v4_remember_stamp);
-EXPORT_SYMBOL(tcp_v4_send_check);
-EXPORT_SYMBOL(tcp_v4_syn_recv_sock);
-
-#ifdef CONFIG_PROC_FS
-EXPORT_SYMBOL(tcp_proc_register);
-EXPORT_SYMBOL(tcp_proc_unregister);
-#endif
-EXPORT_SYMBOL(sysctl_tcp_low_latency);
-
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 794c2e1..f25b56c 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -47,7 +47,6 @@ struct inet_timewait_death_row tcp_death_row = {
.twcal_timer = TIMER_INITIALIZER(inet_twdr_twcal_tick, 0,
(unsigned long)&tcp_death_row),
};
-
EXPORT_SYMBOL_GPL(tcp_death_row);
static __inline__ int tcp_in_window(u32 seq, u32 end_seq, u32 s_win, u32 e_win)
@@ -262,6 +261,7 @@ kill:
inet_twsk_put(tw);
return TCP_TW_SUCCESS;
}
+EXPORT_SYMBOL(tcp_timewait_state_process);
/*
* Move a socket to time-wait or dead fin-wait-2 state.
@@ -362,7 +362,6 @@ void tcp_twsk_destructor(struct sock *sk)
tcp_free_md5sig_pool();
#endif
}
-
EXPORT_SYMBOL_GPL(tcp_twsk_destructor);
static inline void TCP_ECN_openreq_child(struct tcp_sock *tp,
@@ -510,6 +509,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
}
return newsk;
}
+EXPORT_SYMBOL(tcp_create_openreq_child);
/*
* Process an incoming packet for SYN_RECV sockets represented
@@ -706,6 +706,7 @@ embryonic_reset:
inet_csk_reqsk_queue_drop(sk, req, prev);
return NULL;
}
+EXPORT_SYMBOL(tcp_check_req);
/*
* Queue segment on the new socket if the new socket is active,
@@ -737,8 +738,4 @@ int tcp_child_process(struct sock *parent, struct sock *child,
sock_put(child);
return ret;
}
-
-EXPORT_SYMBOL(tcp_check_req);
EXPORT_SYMBOL(tcp_child_process);
-EXPORT_SYMBOL(tcp_create_openreq_child);
-EXPORT_SYMBOL(tcp_timewait_state_process);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 25ff62e..b3f6f09 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -247,6 +247,7 @@ void tcp_select_initial_window(int __space, __u32 mss,
/* Set the clamp no higher than max representable value */
(*window_clamp) = min(65535U << (*rcv_wscale), *window_clamp);
}
+EXPORT_SYMBOL(tcp_select_initial_window);
/* Chose a new window to advertise, update state in tcp_sock for the
* socket, and return result with RFC1323 scaling applied. The return
@@ -1189,6 +1190,7 @@ void tcp_mtup_init(struct sock *sk)
icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, sysctl_tcp_base_mss);
icsk->icsk_mtup.probe_size = 0;
}
+EXPORT_SYMBOL(tcp_mtup_init);
/* This function synchronize snd mss to current pmtu/exthdr set.
@@ -1232,6 +1234,7 @@ unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu)
return mss_now;
}
+EXPORT_SYMBOL(tcp_sync_mss);
/* Compute the current effective MSS, taking SACKs and IP options,
* and even PMTU discovery events into account.
@@ -2514,6 +2517,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
return skb;
}
+EXPORT_SYMBOL(tcp_make_synack);
/* Do all connect socket setups that can be done AF independent. */
static void tcp_connect_init(struct sock *sk)
@@ -2616,6 +2620,7 @@ int tcp_connect(struct sock *sk)
inet_csk(sk)->icsk_rto, TCP_RTO_MAX);
return 0;
}
+EXPORT_SYMBOL(tcp_connect);
/* Send out a delayed ack, the caller does the policy checking
* to see if we should even be here. See tcp_input.c:tcp_ack_snd_check()
@@ -2820,10 +2825,3 @@ void tcp_send_probe0(struct sock *sk)
TCP_RTO_MAX);
}
}
-
-EXPORT_SYMBOL(tcp_select_initial_window);
-EXPORT_SYMBOL(tcp_connect);
-EXPORT_SYMBOL(tcp_make_synack);
-EXPORT_SYMBOL(tcp_simple_retransmit);
-EXPORT_SYMBOL(tcp_sync_mss);
-EXPORT_SYMBOL(tcp_mtup_init);
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 440a5c6..808bb92 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -41,7 +41,6 @@ void tcp_init_xmit_timers(struct sock *sk)
inet_csk_init_xmit_timers(sk, &tcp_write_timer, &tcp_delack_timer,
&tcp_keepalive_timer);
}
-
EXPORT_SYMBOL(tcp_init_xmit_timers);
static void tcp_write_err(struct sock *sk)
diff --git a/net/ipv4/tunnel4.c b/net/ipv4/tunnel4.c
index 3b3813c..59186ca 100644
--- a/net/ipv4/tunnel4.c
+++ b/net/ipv4/tunnel4.c
@@ -48,7 +48,6 @@ err:
return ret;
}
-
EXPORT_SYMBOL(xfrm4_tunnel_register);
int xfrm4_tunnel_deregister(struct xfrm_tunnel *handler, unsigned short family)
@@ -72,7 +71,6 @@ int xfrm4_tunnel_deregister(struct xfrm_tunnel *handler, unsigned short family)
return ret;
}
-
EXPORT_SYMBOL(xfrm4_tunnel_deregister);
static int tunnel4_rcv(struct sk_buff *skb)
diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c
index 6610bf7..ab76aa9 100644
--- a/net/ipv4/udplite.c
+++ b/net/ipv4/udplite.c
@@ -58,6 +58,7 @@ struct proto udplite_prot = {
.compat_getsockopt = compat_udp_getsockopt,
#endif
};
+EXPORT_SYMBOL(udplite_prot);
static struct inet_protosw udplite4_protosw = {
.type = SOCK_DGRAM,
@@ -127,5 +128,3 @@ out_unregister_proto:
out_register_err:
printk(KERN_CRIT "%s: Cannot add UDP-Lite protocol.\n", __func__);
}
-
-EXPORT_SYMBOL(udplite_prot);
diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c
index ad8fbb8..06814b6 100644
--- a/net/ipv4/xfrm4_input.c
+++ b/net/ipv4/xfrm4_input.c
@@ -163,5 +163,4 @@ int xfrm4_rcv(struct sk_buff *skb)
{
return xfrm4_rcv_spi(skb, ip_hdr(skb)->protocol, 0);
}
-
EXPORT_SYMBOL(xfrm4_rcv);
^ permalink raw reply related
* [PATCH net-next-2.6] net/core: EXPORT_SYMBOL cleanups
From: Eric Dumazet @ 2010-07-10 7:22 UTC (permalink / raw)
To: David Miller; +Cc: netdev
CodingStyle cleanups
EXPORT_SYMBOL should immediately follow the symbol declaration.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
---
net/core/datagram.c | 8 +++-----
net/core/flow.c | 5 ++---
net/core/gen_stats.c | 14 ++++++--------
net/core/iovec.c | 9 ++++-----
net/core/link_watch.c | 1 -
net/core/net-sysfs.c | 3 +--
net/core/netevent.c | 5 ++---
net/core/netpoll.c | 19 +++++++++----------
net/core/rtnetlink.c | 2 +-
net/core/scm.c | 9 ++++-----
net/core/skbuff.c | 1 -
net/core/stream.c | 6 ------
net/core/utils.c | 3 ---
13 files changed, 32 insertions(+), 53 deletions(-)
diff --git a/net/core/datagram.c b/net/core/datagram.c
index f5b6f43..251997a 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -219,6 +219,7 @@ struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags,
return __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0),
&peeked, err);
}
+EXPORT_SYMBOL(skb_recv_datagram);
void skb_free_datagram(struct sock *sk, struct sk_buff *skb)
{
@@ -288,7 +289,6 @@ int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags)
return err;
}
-
EXPORT_SYMBOL(skb_kill_datagram);
/**
@@ -373,6 +373,7 @@ int skb_copy_datagram_iovec(const struct sk_buff *skb, int offset,
fault:
return -EFAULT;
}
+EXPORT_SYMBOL(skb_copy_datagram_iovec);
/**
* skb_copy_datagram_const_iovec - Copy a datagram to an iovec.
@@ -716,6 +717,7 @@ csum_error:
fault:
return -EFAULT;
}
+EXPORT_SYMBOL(skb_copy_and_csum_datagram_iovec);
/**
* datagram_poll - generic datagram poll
@@ -770,8 +772,4 @@ unsigned int datagram_poll(struct file *file, struct socket *sock,
return mask;
}
-
EXPORT_SYMBOL(datagram_poll);
-EXPORT_SYMBOL(skb_copy_and_csum_datagram_iovec);
-EXPORT_SYMBOL(skb_copy_datagram_iovec);
-EXPORT_SYMBOL(skb_recv_datagram);
diff --git a/net/core/flow.c b/net/core/flow.c
index 8c7c91a..f67dcbf 100644
--- a/net/core/flow.c
+++ b/net/core/flow.c
@@ -62,6 +62,7 @@ struct flow_cache {
};
atomic_t flow_cache_genid = ATOMIC_INIT(0);
+EXPORT_SYMBOL(flow_cache_genid);
static struct flow_cache flow_cache_global;
static struct kmem_cache *flow_cachep;
@@ -291,6 +292,7 @@ ret_object:
local_bh_enable();
return flo;
}
+EXPORT_SYMBOL(flow_cache_lookup);
static void flow_cache_flush_tasklet(unsigned long data)
{
@@ -424,6 +426,3 @@ static int __init flow_cache_init_global(void)
}
module_init(flow_cache_init_global);
-
-EXPORT_SYMBOL(flow_cache_genid);
-EXPORT_SYMBOL(flow_cache_lookup);
diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c
index 393b1d8..0452eb2 100644
--- a/net/core/gen_stats.c
+++ b/net/core/gen_stats.c
@@ -73,6 +73,7 @@ gnet_stats_start_copy_compat(struct sk_buff *skb, int type, int tc_stats_type,
return 0;
}
+EXPORT_SYMBOL(gnet_stats_start_copy_compat);
/**
* gnet_stats_start_copy_compat - start dumping procedure in compatibility mode
@@ -93,6 +94,7 @@ gnet_stats_start_copy(struct sk_buff *skb, int type, spinlock_t *lock,
{
return gnet_stats_start_copy_compat(skb, type, 0, 0, lock, d);
}
+EXPORT_SYMBOL(gnet_stats_start_copy);
/**
* gnet_stats_copy_basic - copy basic statistics into statistic TLV
@@ -123,6 +125,7 @@ gnet_stats_copy_basic(struct gnet_dump *d, struct gnet_stats_basic_packed *b)
}
return 0;
}
+EXPORT_SYMBOL(gnet_stats_copy_basic);
/**
* gnet_stats_copy_rate_est - copy rate estimator statistics into statistics TLV
@@ -154,6 +157,7 @@ gnet_stats_copy_rate_est(struct gnet_dump *d,
return 0;
}
+EXPORT_SYMBOL(gnet_stats_copy_rate_est);
/**
* gnet_stats_copy_queue - copy queue statistics into statistics TLV
@@ -181,6 +185,7 @@ gnet_stats_copy_queue(struct gnet_dump *d, struct gnet_stats_queue *q)
return 0;
}
+EXPORT_SYMBOL(gnet_stats_copy_queue);
/**
* gnet_stats_copy_app - copy application specific statistics into statistics TLV
@@ -208,6 +213,7 @@ gnet_stats_copy_app(struct gnet_dump *d, void *st, int len)
return 0;
}
+EXPORT_SYMBOL(gnet_stats_copy_app);
/**
* gnet_stats_finish_copy - finish dumping procedure
@@ -241,12 +247,4 @@ gnet_stats_finish_copy(struct gnet_dump *d)
spin_unlock_bh(d->lock);
return 0;
}
-
-
-EXPORT_SYMBOL(gnet_stats_start_copy);
-EXPORT_SYMBOL(gnet_stats_start_copy_compat);
-EXPORT_SYMBOL(gnet_stats_copy_basic);
-EXPORT_SYMBOL(gnet_stats_copy_rate_est);
-EXPORT_SYMBOL(gnet_stats_copy_queue);
-EXPORT_SYMBOL(gnet_stats_copy_app);
EXPORT_SYMBOL(gnet_stats_finish_copy);
diff --git a/net/core/iovec.c b/net/core/iovec.c
index 1e7f4e9..1cd98df 100644
--- a/net/core/iovec.c
+++ b/net/core/iovec.c
@@ -95,6 +95,7 @@ int memcpy_toiovec(struct iovec *iov, unsigned char *kdata, int len)
return 0;
}
+EXPORT_SYMBOL(memcpy_toiovec);
/*
* Copy kernel to iovec. Returns -EFAULT on error.
@@ -120,6 +121,7 @@ int memcpy_toiovecend(const struct iovec *iov, unsigned char *kdata,
return 0;
}
+EXPORT_SYMBOL(memcpy_toiovecend);
/*
* Copy iovec to kernel. Returns -EFAULT on error.
@@ -144,6 +146,7 @@ int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len)
return 0;
}
+EXPORT_SYMBOL(memcpy_fromiovec);
/*
* Copy iovec from kernel. Returns -EFAULT on error.
@@ -172,6 +175,7 @@ int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov,
return 0;
}
+EXPORT_SYMBOL(memcpy_fromiovecend);
/*
* And now for the all-in-one: copy and checksum from a user iovec
@@ -256,9 +260,4 @@ out_fault:
err = -EFAULT;
goto out;
}
-
EXPORT_SYMBOL(csum_partial_copy_fromiovecend);
-EXPORT_SYMBOL(memcpy_fromiovec);
-EXPORT_SYMBOL(memcpy_fromiovecend);
-EXPORT_SYMBOL(memcpy_toiovec);
-EXPORT_SYMBOL(memcpy_toiovecend);
diff --git a/net/core/link_watch.c b/net/core/link_watch.c
index bdbce2f..01a1101 100644
--- a/net/core/link_watch.c
+++ b/net/core/link_watch.c
@@ -243,5 +243,4 @@ void linkwatch_fire_event(struct net_device *dev)
linkwatch_schedule_work(urgent);
}
-
EXPORT_SYMBOL(linkwatch_fire_event);
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 914f42b..d2b5965 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -924,13 +924,12 @@ int netdev_class_create_file(struct class_attribute *class_attr)
{
return class_create_file(&net_class, class_attr);
}
+EXPORT_SYMBOL(netdev_class_create_file);
void netdev_class_remove_file(struct class_attribute *class_attr)
{
class_remove_file(&net_class, class_attr);
}
-
-EXPORT_SYMBOL(netdev_class_create_file);
EXPORT_SYMBOL(netdev_class_remove_file);
int netdev_kobject_init(void)
diff --git a/net/core/netevent.c b/net/core/netevent.c
index 95f81de..865f0ce 100644
--- a/net/core/netevent.c
+++ b/net/core/netevent.c
@@ -35,6 +35,7 @@ int register_netevent_notifier(struct notifier_block *nb)
err = atomic_notifier_chain_register(&netevent_notif_chain, nb);
return err;
}
+EXPORT_SYMBOL_GPL(register_netevent_notifier);
/**
* netevent_unregister_notifier - unregister a netevent notifier block
@@ -50,6 +51,7 @@ int unregister_netevent_notifier(struct notifier_block *nb)
{
return atomic_notifier_chain_unregister(&netevent_notif_chain, nb);
}
+EXPORT_SYMBOL_GPL(unregister_netevent_notifier);
/**
* call_netevent_notifiers - call all netevent notifier blocks
@@ -64,7 +66,4 @@ int call_netevent_notifiers(unsigned long val, void *v)
{
return atomic_notifier_call_chain(&netevent_notif_chain, val, v);
}
-
-EXPORT_SYMBOL_GPL(register_netevent_notifier);
-EXPORT_SYMBOL_GPL(unregister_netevent_notifier);
EXPORT_SYMBOL_GPL(call_netevent_notifiers);
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index ca6dc31..c2b7a8b 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -197,11 +197,13 @@ void netpoll_poll_dev(struct net_device *dev)
service_arp_queue(dev->npinfo);
}
+EXPORT_SYMBOL(netpoll_poll_dev);
void netpoll_poll(struct netpoll *np)
{
netpoll_poll_dev(np->dev);
}
+EXPORT_SYMBOL(netpoll_poll);
static void refill_skbs(void)
{
@@ -313,6 +315,7 @@ void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb)
schedule_delayed_work(&npinfo->tx_work,0);
}
}
+EXPORT_SYMBOL(netpoll_send_skb);
void netpoll_send_udp(struct netpoll *np, const char *msg, int len)
{
@@ -374,6 +377,7 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len)
netpoll_send_skb(np, skb);
}
+EXPORT_SYMBOL(netpoll_send_udp);
static void arp_reply(struct sk_buff *skb)
{
@@ -600,6 +604,7 @@ void netpoll_print_options(struct netpoll *np)
printk(KERN_INFO "%s: remote ethernet address %pM\n",
np->name, np->remote_mac);
}
+EXPORT_SYMBOL(netpoll_print_options);
int netpoll_parse_options(struct netpoll *np, char *opt)
{
@@ -692,6 +697,7 @@ int netpoll_parse_options(struct netpoll *np, char *opt)
np->name, cur);
return -1;
}
+EXPORT_SYMBOL(netpoll_parse_options);
int __netpoll_setup(struct netpoll *np)
{
@@ -848,6 +854,7 @@ put:
dev_put(ndev);
return err;
}
+EXPORT_SYMBOL(netpoll_setup);
static int __init netpoll_init(void)
{
@@ -908,11 +915,13 @@ void netpoll_cleanup(struct netpoll *np)
dev_put(np->dev);
np->dev = NULL;
}
+EXPORT_SYMBOL(netpoll_cleanup);
int netpoll_trap(void)
{
return atomic_read(&trapped);
}
+EXPORT_SYMBOL(netpoll_trap);
void netpoll_set_trap(int trap)
{
@@ -921,14 +930,4 @@ void netpoll_set_trap(int trap)
else
atomic_dec(&trapped);
}
-
-EXPORT_SYMBOL(netpoll_send_skb);
EXPORT_SYMBOL(netpoll_set_trap);
-EXPORT_SYMBOL(netpoll_trap);
-EXPORT_SYMBOL(netpoll_print_options);
-EXPORT_SYMBOL(netpoll_parse_options);
-EXPORT_SYMBOL(netpoll_setup);
-EXPORT_SYMBOL(netpoll_cleanup);
-EXPORT_SYMBOL(netpoll_send_udp);
-EXPORT_SYMBOL(netpoll_poll_dev);
-EXPORT_SYMBOL(netpoll_poll);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 5e773ea..f78d821 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -686,7 +686,7 @@ static size_t rtnl_port_size(const struct net_device *dev)
return port_self_size;
}
-static inline size_t if_nlmsg_size(const struct net_device *dev)
+static noinline size_t if_nlmsg_size(const struct net_device *dev)
{
return NLMSG_ALIGN(sizeof(struct ifinfomsg))
+ nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */
diff --git a/net/core/scm.c b/net/core/scm.c
index 681c976..413cab8 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -130,6 +130,7 @@ void __scm_destroy(struct scm_cookie *scm)
}
}
}
+EXPORT_SYMBOL(__scm_destroy);
int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p)
{
@@ -211,6 +212,7 @@ error:
scm_destroy(p);
return err;
}
+EXPORT_SYMBOL(__scm_send);
int put_cmsg(struct msghdr * msg, int level, int type, int len, void *data)
{
@@ -249,6 +251,7 @@ int put_cmsg(struct msghdr * msg, int level, int type, int len, void *data)
out:
return err;
}
+EXPORT_SYMBOL(put_cmsg);
void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm)
{
@@ -318,6 +321,7 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm)
*/
__scm_destroy(scm);
}
+EXPORT_SYMBOL(scm_detach_fds);
struct scm_fp_list *scm_fp_dup(struct scm_fp_list *fpl)
{
@@ -335,9 +339,4 @@ struct scm_fp_list *scm_fp_dup(struct scm_fp_list *fpl)
}
return new_fpl;
}
-
-EXPORT_SYMBOL(__scm_destroy);
-EXPORT_SYMBOL(__scm_send);
-EXPORT_SYMBOL(put_cmsg);
-EXPORT_SYMBOL(scm_detach_fds);
EXPORT_SYMBOL(scm_fp_dup);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 34432b4..76d33ca 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2483,7 +2483,6 @@ unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len)
skb_postpull_rcsum(skb, skb->data, len);
return skb->data += len;
}
-
EXPORT_SYMBOL_GPL(skb_pull_rcsum);
/**
diff --git a/net/core/stream.c b/net/core/stream.c
index cc196f4..d959e0f 100644
--- a/net/core/stream.c
+++ b/net/core/stream.c
@@ -43,7 +43,6 @@ void sk_stream_write_space(struct sock *sk)
rcu_read_unlock();
}
}
-
EXPORT_SYMBOL(sk_stream_write_space);
/**
@@ -81,7 +80,6 @@ int sk_stream_wait_connect(struct sock *sk, long *timeo_p)
} while (!done);
return 0;
}
-
EXPORT_SYMBOL(sk_stream_wait_connect);
/**
@@ -109,7 +107,6 @@ void sk_stream_wait_close(struct sock *sk, long timeout)
finish_wait(sk_sleep(sk), &wait);
}
}
-
EXPORT_SYMBOL(sk_stream_wait_close);
/**
@@ -174,7 +171,6 @@ do_interrupted:
err = sock_intr_errno(*timeo_p);
goto out;
}
-
EXPORT_SYMBOL(sk_stream_wait_memory);
int sk_stream_error(struct sock *sk, int flags, int err)
@@ -185,7 +181,6 @@ int sk_stream_error(struct sock *sk, int flags, int err)
send_sig(SIGPIPE, current, 0);
return err;
}
-
EXPORT_SYMBOL(sk_stream_error);
void sk_stream_kill_queues(struct sock *sk)
@@ -210,5 +205,4 @@ void sk_stream_kill_queues(struct sock *sk)
* have gone away, only the net layer knows can touch it.
*/
}
-
EXPORT_SYMBOL(sk_stream_kill_queues);
diff --git a/net/core/utils.c b/net/core/utils.c
index 8382502..f418544 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -77,7 +77,6 @@ __be32 in_aton(const char *str)
}
return(htonl(l));
}
-
EXPORT_SYMBOL(in_aton);
#define IN6PTON_XDIGIT 0x00010000
@@ -162,7 +161,6 @@ out:
*end = s;
return ret;
}
-
EXPORT_SYMBOL(in4_pton);
int in6_pton(const char *src, int srclen,
@@ -280,7 +278,6 @@ out:
*end = s;
return ret;
}
-
EXPORT_SYMBOL(in6_pton);
void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb,
^ permalink raw reply related
* Re: net/sched/act_nat.c BUG
From: Eric Dumazet @ 2010-07-10 6:27 UTC (permalink / raw)
To: Herbert Xu
Cc: Rodrigo Partearroyo González, Linux Kernel Mailing List,
Iratxo Pichel Ortiz, Noelia Morón, netdev
In-Reply-To: <20100709232359.GA2501@gondor.apana.org.au>
Le samedi 10 juillet 2010 à 07:23 +0800, Herbert Xu a écrit :
> No we do need the second IP header, think about it...
>
> However, we should only drop it only if it's long enough and
> pskb_may_pull fails.
Indeed right you are !
As Changli suggested, we need another pskb_may_pull() call.
Thanks
^ permalink raw reply
* Re: [PATCH] act_nat: not all of the ICMP packets need an IP header payload
From: Herbert Xu @ 2010-07-10 6:26 UTC (permalink / raw)
To: Changli Gao
Cc: David S. Miller, Jamal Hadi Salim,
Rodrigo Partearroyo González, Eric Dumazet,
Iratxo Pichel Ortiz, Noelia Morón, netdev
In-Reply-To: <1278725605-28598-1-git-send-email-xiaosuo@gmail.com>
On Sat, Jul 10, 2010 at 09:33:25AM +0800, Changli Gao wrote:
> act_nat: not all of the ICMP packets need an IP header payload
>
> not all of the ICMP packets need an IP header payload, so we check the length
> of the skbs only when the packets should have an IP header payload.
>
> Signed-off-by: Changli Gao <xiaosuo@gmail.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Thanks!
--
Email: Herbert Xu <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
^ permalink raw reply
* Re: [PATCH] act_nat: not all of the ICMP packets need an IP header payload
From: Eric Dumazet @ 2010-07-10 6:22 UTC (permalink / raw)
To: Changli Gao
Cc: David S. Miller, Jamal Hadi Salim,
Rodrigo Partearroyo González, Herbert Xu,
Iratxo Pichel Ortiz, Noelia Morón, netdev
In-Reply-To: <1278725605-28598-1-git-send-email-xiaosuo@gmail.com>
Le samedi 10 juillet 2010 à 09:33 +0800, Changli Gao a écrit :
> act_nat: not all of the ICMP packets need an IP header payload
>
> not all of the ICMP packets need an IP header payload, so we check the length
> of the skbs only when the packets should have an IP header payload.
>
> Signed-off-by: Changli Gao <xiaosuo@gmail.com>
> ----
> net/sched/act_nat.c | 5 ++++-
> 1 file changed, 4 insertions(+), 1 deletion(-)
> diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
> index 0be49a4..24e614c 100644
> --- a/net/sched/act_nat.c
> +++ b/net/sched/act_nat.c
> @@ -205,7 +205,7 @@ static int tcf_nat(struct sk_buff *skb, struct tc_action *a,
> {
> struct icmphdr *icmph;
>
> - if (!pskb_may_pull(skb, ihl + sizeof(*icmph) + sizeof(*iph)))
> + if (!pskb_may_pull(skb, ihl + sizeof(*icmph)))
> goto drop;
>
> icmph = (void *)(skb_network_header(skb) + ihl);
> @@ -215,6 +215,9 @@ static int tcf_nat(struct sk_buff *skb, struct tc_action *a,
> (icmph->type != ICMP_PARAMETERPROB))
> break;
>
> + if (!pskb_may_pull(skb, ihl + sizeof(*icmph) + sizeof(*iph)))
> + goto drop;
> +
> iph = (void *)(icmph + 1);
> if (egress)
> addr = iph->daddr;
Changli, this patch has no attribution.
Rodrigo spent lot of time to find the problem and is willing to fix it.
Could you please give a chance to Rodrigo to complete its first kernel
patch ?
Thanks
^ permalink raw reply
* Re: [PATCH] tproxy: nf_tproxy_assign_sock() can handle tw sockets
From: Eric Dumazet @ 2010-07-10 6:17 UTC (permalink / raw)
To: Felipe W Damasio; +Cc: David Miller, Patrick McHardy, linux-kernel, netdev
In-Reply-To: <AANLkTil39xHOhcdAo4h_jWtx_UuYdFHGdQVAdwPMd7QJ@mail.gmail.com>
Le samedi 10 juillet 2010 à 00:18 -0300, Felipe W Damasio a écrit :
> Hi Mr. Dumazet,
>
> 2010/7/9 Eric Dumazet <eric.dumazet@gmail.com>:
> > Reviewing tproxy stuff I spotted a problem in nf_tproxy_assign_sock()
> > but I could not see how it could explain your crash.
> >
> > We can read uninitialized memory and trigger a fault in
> > nf_tproxy_assign_sock(), not later in tcp_recvmsg()...
> >
> > David, Patrick, what do you think ?
>
> But do you think that the bug that squid triggered was caused by the
> TProxy code?
>
I dont think so, but I was asking David or Patrick another point of
view.
Strange thing with your crash report is CR2 value, with unexpected value
of 000000000b388000 while RAX value is dce8dce85d415d41
Faulting instruction is :
48 83 b8 b0 00 00 00 00 cmpq $0x0,0xb0(%rax)
So I would have expected CR2 being RAX+0xb0, but its not.
> Or is related to the network-stack in some other point.
>
> I don't know if this helps, but I'm using ebtables to remove the
> packets from the bridge, and iptables to redirect the traffic to
> squid.
>
> ebtables rules are:
>
> -p IPv4 -i eth0 --ip-proto tcp --ip-dport 80 -j redirect --redirect-target DROP
> -p IPv4 -i eth1 --ip-proto tcp --ip-sport 80 -j redirect --redirect-target DROP
>
>
> iptables -t mangle -L -n is:
>
> iptables -t mangle -L -n
> Chain PREROUTING (policy ACCEPT)
> target prot opt source destination
> DIVERT tcp -- 0.0.0.0/0 0.0.0.0/0 socket
> extrachain tcp -- 0.0.0.0/0 0.0.0.0/0 tcp
> dpt:80 ctstate NEW
> TPROXY tcp -- 0.0.0.0/0 !201.40.162.5 tcp
> dpt:80 connmark match 0x0 TPROXY redirect 127.0.0.1:3127 mark 0x1/0x1
> TPROXY tcp -- 0.0.0.0/0 !201.40.162.5 tcp
> dpt:80 connmark match 0x1 TPROXY redirect 127.0.0.1:3128 mark 0x1/0x1
> TPROXY tcp -- 0.0.0.0/0 !201.40.162.5 tcp
> dpt:80 connmark match 0x2 TPROXY redirect 127.0.0.1:3129 mark 0x1/0x1
>
> Chain DIVERT (1 references)
> target prot opt source destination
> MARK all -- 0.0.0.0/0 0.0.0.0/0 MARK xset
> 0x1/0xffffffff
> ACCEPT all -- 0.0.0.0/0 0.0.0.0/0
>
> Chain extrachain (1 references)
> target prot opt source destination
> CONNMARK all -- 0.0.0.0/0 0.0.0.0/0 statistic
> mode nth every 35 CONNMARK and 0x0
> CONNMARK all -- 0.0.0.0/0 0.0.0.0/0 statistic
> mode nth every 35 packet 1 CONNMARK xset 0x1/0xffffffff
> CONNMARK all -- 0.0.0.0/0 0.0.0.0/0 statistic
> mode nth every 35 packet 2 CONNMARK xset 0x2/0xffffffff
>
> Don't know if the code on these can be traced back to tcp_recvmsg()
> accessing some wrong memory address...
>
> Cheers,
>
> Felipe Damasio
^ permalink raw reply
* Re: [PATCH] tproxy: nf_tproxy_assign_sock() can handle tw sockets
From: Felipe W Damasio @ 2010-07-10 3:18 UTC (permalink / raw)
To: Eric Dumazet; +Cc: David Miller, Patrick McHardy, linux-kernel, netdev
In-Reply-To: <1278695580.2696.55.camel@edumazet-laptop>
Hi Mr. Dumazet,
2010/7/9 Eric Dumazet <eric.dumazet@gmail.com>:
> Reviewing tproxy stuff I spotted a problem in nf_tproxy_assign_sock()
> but I could not see how it could explain your crash.
>
> We can read uninitialized memory and trigger a fault in
> nf_tproxy_assign_sock(), not later in tcp_recvmsg()...
>
> David, Patrick, what do you think ?
But do you think that the bug that squid triggered was caused by the
TProxy code?
Or is related to the network-stack in some other point.
I don't know if this helps, but I'm using ebtables to remove the
packets from the bridge, and iptables to redirect the traffic to
squid.
ebtables rules are:
-p IPv4 -i eth0 --ip-proto tcp --ip-dport 80 -j redirect --redirect-target DROP
-p IPv4 -i eth1 --ip-proto tcp --ip-sport 80 -j redirect --redirect-target DROP
iptables -t mangle -L -n is:
iptables -t mangle -L -n
Chain PREROUTING (policy ACCEPT)
target prot opt source destination
DIVERT tcp -- 0.0.0.0/0 0.0.0.0/0 socket
extrachain tcp -- 0.0.0.0/0 0.0.0.0/0 tcp
dpt:80 ctstate NEW
TPROXY tcp -- 0.0.0.0/0 !201.40.162.5 tcp
dpt:80 connmark match 0x0 TPROXY redirect 127.0.0.1:3127 mark 0x1/0x1
TPROXY tcp -- 0.0.0.0/0 !201.40.162.5 tcp
dpt:80 connmark match 0x1 TPROXY redirect 127.0.0.1:3128 mark 0x1/0x1
TPROXY tcp -- 0.0.0.0/0 !201.40.162.5 tcp
dpt:80 connmark match 0x2 TPROXY redirect 127.0.0.1:3129 mark 0x1/0x1
Chain DIVERT (1 references)
target prot opt source destination
MARK all -- 0.0.0.0/0 0.0.0.0/0 MARK xset
0x1/0xffffffff
ACCEPT all -- 0.0.0.0/0 0.0.0.0/0
Chain extrachain (1 references)
target prot opt source destination
CONNMARK all -- 0.0.0.0/0 0.0.0.0/0 statistic
mode nth every 35 CONNMARK and 0x0
CONNMARK all -- 0.0.0.0/0 0.0.0.0/0 statistic
mode nth every 35 packet 1 CONNMARK xset 0x1/0xffffffff
CONNMARK all -- 0.0.0.0/0 0.0.0.0/0 statistic
mode nth every 35 packet 2 CONNMARK xset 0x2/0xffffffff
Don't know if the code on these can be traced back to tcp_recvmsg()
accessing some wrong memory address...
Cheers,
Felipe Damasio
^ permalink raw reply
* [patch] netfilter: default to NF_DROP in sip_help_tcp()
From: Simon Horman @ 2010-07-10 3:16 UTC (permalink / raw)
To: netfilter-devel, netdev; +Cc: Patrick McHardy
I initially noticed this because of the compiler warning below, but it does
seem to be a valid concern in the case where ct_sip_get_header() returns 0
in the first iteration of the while loop.
net/netfilter/nf_conntrack_sip.c: In function 'sip_help_tcp':
net/netfilter/nf_conntrack_sip.c:1379: warning: 'ret' may be used uninitialized in this function
Signed-off-by: Simon Horman <horms@verge.net.au>
Index: nf-next-2.6/net/netfilter/nf_conntrack_sip.c
===================================================================
--- nf-next-2.6.orig/net/netfilter/nf_conntrack_sip.c 2010-07-10 12:11:52.000000000 +0900
+++ nf-next-2.6/net/netfilter/nf_conntrack_sip.c 2010-07-10 12:11:57.000000000 +0900
@@ -1376,7 +1376,7 @@ static int sip_help_tcp(struct sk_buff *
unsigned int msglen, origlen;
const char *dptr, *end;
s16 diff, tdiff = 0;
- int ret;
+ int ret = NF_DROP;
typeof(nf_nat_sip_seq_adjust_hook) nf_nat_sip_seq_adjust;
if (ctinfo != IP_CT_ESTABLISHED &&
^ permalink raw reply
* [patch v2.5 4/4] libxt_ipvs: user-space lib for netfilter matcher xt_ipvs
From: Simon Horman, Simon Horman @ 2010-07-10 3:01 UTC (permalink / raw)
To: lvs-devel, netdev, linux-kernel, netfilter, netfilter-devel
Cc: Malcolm Turnbull, Wensong Zhang, Julius Volz, Patrick McHardy,
David S. Miller, Hannes Eder
In-Reply-To: <20100710030057.731118760@vergenet.net>
[-- Attachment #1: libxt_ipvs-user-space-lib-for-netfilter-matcher-xt_ipvs.patch --]
[-- Type: text/plain, Size: 13930 bytes --]
From: Hannes Eder <heder@google.com>
The user-space library for the netfilter matcher xt_ipvs.
[ trivial up-port by Simon Horman <horms@verge.net.au> ]
Signed-off-by: Hannes Eder <heder@google.com>
Acked-by: Simon Horman <horms@verge.net.au>
configure.ac | 10 -
extensions/libxt_ipvs.c | 365 +++++++++++++++++++++++++++++++++++++
extensions/libxt_ipvs.man | 24 ++
include/linux/netfilter/xt_ipvs.h | 25 +++
4 files changed, 422 insertions(+), 2 deletions(-)
create mode 100644 extensions/libxt_ipvs.c
create mode 100644 extensions/libxt_ipvs.man
create mode 100644 include/linux/netfilter/xt_ipvs.h
v2.1, v2.3
Trivial up-port
v2.2
No change
Index: iptables/configure.ac
===================================================================
--- iptables.orig/configure.ac 2010-07-04 20:21:07.000000000 +0900
+++ iptables/configure.ac 2010-07-04 20:23:30.000000000 +0900
@@ -52,12 +52,18 @@ AC_ARG_WITH([pkgconfigdir], AS_HELP_STRI
[Path to the pkgconfig directory [[LIBDIR/pkgconfig]]]),
[pkgconfigdir="$withval"], [pkgconfigdir='${libdir}/pkgconfig'])
-AC_CHECK_HEADER([linux/dccp.h])
-
blacklist_modules="";
+
+AC_CHECK_HEADER([linux/dccp.h])
if test "$ac_cv_header_linux_dccp_h" != "yes"; then
blacklist_modules="$blacklist_modules dccp";
fi;
+
+AC_CHECK_HEADER([linux/ip_vs.h])
+if test "$ac_cv_header_linux_ip_vs_h" != "yes"; then
+ blacklist_modules="$blacklist_modules ipvs";
+fi;
+
AC_SUBST([blacklist_modules])
AM_CONDITIONAL([ENABLE_STATIC], [test "$enable_static" = "yes"])
Index: iptables/extensions/libxt_ipvs.c
===================================================================
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ iptables/extensions/libxt_ipvs.c 2010-07-04 20:24:01.000000000 +0900
@@ -0,0 +1,365 @@
+/*
+ * Shared library add-on to iptables to add IPVS matching.
+ *
+ * Detailed doc is in the kernel module source net/netfilter/xt_ipvs.c
+ *
+ * Author: Hannes Eder <heder@google.com>
+ */
+#include <sys/types.h>
+#include <assert.h>
+#include <ctype.h>
+#include <errno.h>
+#include <getopt.h>
+#include <netdb.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <xtables.h>
+#include <linux/ip_vs.h>
+#include <linux/netfilter/xt_ipvs.h>
+
+static const struct option ipvs_mt_opts[] = {
+ { .name = "ipvs", .has_arg = false, .val = '0' },
+ { .name = "vproto", .has_arg = true, .val = '1' },
+ { .name = "vaddr", .has_arg = true, .val = '2' },
+ { .name = "vport", .has_arg = true, .val = '3' },
+ { .name = "vdir", .has_arg = true, .val = '4' },
+ { .name = "vmethod", .has_arg = true, .val = '5' },
+ { .name = "vportctl", .has_arg = true, .val = '6' },
+ { .name = NULL }
+};
+
+static void ipvs_mt_help(void)
+{
+ printf(
+"IPVS match options:\n"
+"[!] --ipvs packet belongs to an IPVS connection\n"
+"\n"
+"Any of the following options implies --ipvs (even negated)\n"
+"[!] --vproto protocol VIP protocol to match; by number or name,\n"
+" e.g. \"tcp\"\n"
+"[!] --vaddr address[/mask] VIP address to match\n"
+"[!] --vport port VIP port to match; by number or name,\n"
+" e.g. \"http\"\n"
+" --vdir {ORIGINAL|REPLY} flow direction of packet\n"
+"[!] --vmethod {GATE|IPIP|MASQ} IPVS forwarding method used\n"
+"[!] --vportctl port VIP port of the controlling connection to\n"
+" match, e.g. 21 for FTP\n"
+ );
+}
+
+static void ipvs_mt_parse_addr_and_mask(const char *arg,
+ union nf_inet_addr *address,
+ union nf_inet_addr *mask,
+ unsigned int family)
+{
+ struct in_addr *addr = NULL;
+ struct in6_addr *addr6 = NULL;
+ unsigned int naddrs = 0;
+
+ if (family == NFPROTO_IPV4) {
+ xtables_ipparse_any(arg, &addr, &mask->in, &naddrs);
+ if (naddrs > 1)
+ xtables_error(PARAMETER_PROBLEM,
+ "multiple IP addresses not allowed");
+ if (naddrs == 1)
+ memcpy(&address->in, addr, sizeof(*addr));
+ } else if (family == NFPROTO_IPV6) {
+ xtables_ip6parse_any(arg, &addr6, &mask->in6, &naddrs);
+ if (naddrs > 1)
+ xtables_error(PARAMETER_PROBLEM,
+ "multiple IP addresses not allowed");
+ if (naddrs == 1)
+ memcpy(&address->in6, addr6, sizeof(*addr6));
+ } else {
+ /* Hu? */
+ assert(false);
+ }
+}
+
+/* Function which parses command options; returns true if it ate an option */
+static int ipvs_mt_parse(int c, char **argv, int invert, unsigned int *flags,
+ const void *entry, struct xt_entry_match **match,
+ unsigned int family)
+{
+ struct xt_ipvs_mtinfo *data = (void *)(*match)->data;
+ char *p = NULL;
+ u_int8_t op = 0;
+
+ if ('0' <= c && c <= '6') {
+ static const int ops[] = {
+ XT_IPVS_IPVS_PROPERTY,
+ XT_IPVS_PROTO,
+ XT_IPVS_VADDR,
+ XT_IPVS_VPORT,
+ XT_IPVS_DIR,
+ XT_IPVS_METHOD,
+ XT_IPVS_VPORTCTL
+ };
+ op = ops[c - '0'];
+ } else
+ return 0;
+
+ if (*flags & op & XT_IPVS_ONCE_MASK)
+ goto multiple_use;
+
+ switch (c) {
+ case '0': /* --ipvs */
+ /* Nothing to do here. */
+ break;
+
+ case '1': /* --vproto */
+ /* Canonicalize into lower case */
+ for (p = optarg; *p != '\0'; ++p)
+ *p = tolower(*p);
+
+ data->l4proto = xtables_parse_protocol(optarg);
+ break;
+
+ case '2': /* --vaddr */
+ ipvs_mt_parse_addr_and_mask(optarg, &data->vaddr,
+ &data->vmask, family);
+ break;
+
+ case '3': /* --vport */
+ data->vport = htons(xtables_parse_port(optarg, "tcp"));
+ break;
+
+ case '4': /* --vdir */
+ xtables_param_act(XTF_NO_INVERT, "ipvs", "--vdir", invert);
+ if (strcasecmp(optarg, "ORIGINAL") == 0) {
+ data->bitmask |= XT_IPVS_DIR;
+ data->invert &= ~XT_IPVS_DIR;
+ } else if (strcasecmp(optarg, "REPLY") == 0) {
+ data->bitmask |= XT_IPVS_DIR;
+ data->invert |= XT_IPVS_DIR;
+ } else {
+ xtables_param_act(XTF_BAD_VALUE,
+ "ipvs", "--vdir", optarg);
+ }
+ break;
+
+ case '5': /* --vmethod */
+ if (strcasecmp(optarg, "GATE") == 0)
+ data->fwd_method = IP_VS_CONN_F_DROUTE;
+ else if (strcasecmp(optarg, "IPIP") == 0)
+ data->fwd_method = IP_VS_CONN_F_TUNNEL;
+ else if (strcasecmp(optarg, "MASQ") == 0)
+ data->fwd_method = IP_VS_CONN_F_MASQ;
+ else
+ xtables_param_act(XTF_BAD_VALUE,
+ "ipvs", "--vmethod", optarg);
+ break;
+
+ case '6': /* --vportctl */
+ data->vportctl = htons(xtables_parse_port(optarg, "tcp"));
+ break;
+
+ default:
+ /* Hu? How did we come here? */
+ assert(false);
+ return 0;
+ }
+
+ if (op & XT_IPVS_ONCE_MASK) {
+ if (data->invert & XT_IPVS_IPVS_PROPERTY)
+ xtables_error(PARAMETER_PROBLEM,
+ "! --ipvs cannot be together with"
+ " other options");
+ data->bitmask |= XT_IPVS_IPVS_PROPERTY;
+ }
+
+ data->bitmask |= op;
+ if (invert)
+ data->invert |= op;
+ *flags |= op;
+ return 1;
+
+multiple_use:
+ xtables_error(PARAMETER_PROBLEM,
+ "multiple use of the same IPVS option is not allowed");
+}
+
+static int ipvs_mt4_parse(int c, char **argv, int invert, unsigned int *flags,
+ const void *entry, struct xt_entry_match **match)
+{
+ return ipvs_mt_parse(c, argv, invert, flags, entry, match,
+ NFPROTO_IPV4);
+}
+
+static int ipvs_mt6_parse(int c, char **argv, int invert, unsigned int *flags,
+ const void *entry, struct xt_entry_match **match)
+{
+ return ipvs_mt_parse(c, argv, invert, flags, entry, match,
+ NFPROTO_IPV6);
+}
+
+static void ipvs_mt_check(unsigned int flags)
+{
+ if (flags == 0)
+ xtables_error(PARAMETER_PROBLEM,
+ "IPVS: At least one option is required");
+}
+
+/* Shamelessly copied from libxt_conntrack.c */
+static void ipvs_mt_dump_addr(const union nf_inet_addr *addr,
+ const union nf_inet_addr *mask,
+ unsigned int family, bool numeric)
+{
+ char buf[BUFSIZ];
+
+ if (family == NFPROTO_IPV4) {
+ if (!numeric && addr->ip == 0) {
+ printf("anywhere ");
+ return;
+ }
+ if (numeric)
+ strcpy(buf, xtables_ipaddr_to_numeric(&addr->in));
+ else
+ strcpy(buf, xtables_ipaddr_to_anyname(&addr->in));
+ strcat(buf, xtables_ipmask_to_numeric(&mask->in));
+ printf("%s ", buf);
+ } else if (family == NFPROTO_IPV6) {
+ if (!numeric && addr->ip6[0] == 0 && addr->ip6[1] == 0 &&
+ addr->ip6[2] == 0 && addr->ip6[3] == 0) {
+ printf("anywhere ");
+ return;
+ }
+ if (numeric)
+ strcpy(buf, xtables_ip6addr_to_numeric(&addr->in6));
+ else
+ strcpy(buf, xtables_ip6addr_to_anyname(&addr->in6));
+ strcat(buf, xtables_ip6mask_to_numeric(&mask->in6));
+ printf("%s ", buf);
+ }
+}
+
+static void ipvs_mt_dump(const void *ip, const struct xt_ipvs_mtinfo *data,
+ unsigned int family, bool numeric, const char *prefix)
+{
+ if (data->bitmask == XT_IPVS_IPVS_PROPERTY) {
+ if (data->invert & XT_IPVS_IPVS_PROPERTY)
+ printf("! ");
+ printf("%sipvs ", prefix);
+ }
+
+ if (data->bitmask & XT_IPVS_PROTO) {
+ if (data->invert & XT_IPVS_PROTO)
+ printf("! ");
+ printf("%sproto %u ", prefix, data->l4proto);
+ }
+
+ if (data->bitmask & XT_IPVS_VADDR) {
+ if (data->invert & XT_IPVS_VADDR)
+ printf("! ");
+
+ printf("%svaddr ", prefix);
+ ipvs_mt_dump_addr(&data->vaddr, &data->vmask, family, numeric);
+ }
+
+ if (data->bitmask & XT_IPVS_VPORT) {
+ if (data->invert & XT_IPVS_VPORT)
+ printf("! ");
+
+ printf("%svport %u ", prefix, ntohs(data->vport));
+ }
+
+ if (data->bitmask & XT_IPVS_DIR) {
+ if (data->invert & XT_IPVS_DIR)
+ printf("%svdir REPLY ", prefix);
+ else
+ printf("%svdir ORIGINAL ", prefix);
+ }
+
+ if (data->bitmask & XT_IPVS_METHOD) {
+ if (data->invert & XT_IPVS_METHOD)
+ printf("! ");
+
+ printf("%svmethod ", prefix);
+ switch (data->fwd_method) {
+ case IP_VS_CONN_F_DROUTE:
+ printf("GATE ");
+ break;
+ case IP_VS_CONN_F_TUNNEL:
+ printf("IPIP ");
+ break;
+ case IP_VS_CONN_F_MASQ:
+ printf("MASQ ");
+ break;
+ default:
+ /* Hu? */
+ printf("UNKNOWN ");
+ break;
+ }
+ }
+
+ if (data->bitmask & XT_IPVS_VPORTCTL) {
+ if (data->invert & XT_IPVS_VPORTCTL)
+ printf("! ");
+
+ printf("%svportctl %u ", prefix, ntohs(data->vportctl));
+ }
+}
+
+static void ipvs_mt4_print(const void *ip, const struct xt_entry_match *match,
+ int numeric)
+{
+ const struct xt_ipvs_mtinfo *data = (const void *)match->data;
+ ipvs_mt_dump(ip, data, NFPROTO_IPV4, numeric, "");
+}
+
+static void ipvs_mt6_print(const void *ip, const struct xt_entry_match *match,
+ int numeric)
+{
+ const struct xt_ipvs_mtinfo *data = (const void *)match->data;
+ ipvs_mt_dump(ip, data, NFPROTO_IPV6, numeric, "");
+}
+
+static void ipvs_mt4_save(const void *ip, const struct xt_entry_match *match)
+{
+ const struct xt_ipvs_mtinfo *data = (const void *)match->data;
+ ipvs_mt_dump(ip, data, NFPROTO_IPV4, true, "--");
+}
+
+static void ipvs_mt6_save(const void *ip, const struct xt_entry_match *match)
+{
+ const struct xt_ipvs_mtinfo *data = (const void *)match->data;
+ ipvs_mt_dump(ip, data, NFPROTO_IPV6, true, "--");
+}
+
+static struct xtables_match ipvs_matches_reg[] = {
+ {
+ .version = XTABLES_VERSION,
+ .name = "ipvs",
+ .revision = 0,
+ .family = NFPROTO_IPV4,
+ .size = XT_ALIGN(sizeof(struct xt_ipvs_mtinfo)),
+ .userspacesize = XT_ALIGN(sizeof(struct xt_ipvs_mtinfo)),
+ .help = ipvs_mt_help,
+ .parse = ipvs_mt4_parse,
+ .final_check = ipvs_mt_check,
+ .print = ipvs_mt4_print,
+ .save = ipvs_mt4_save,
+ .extra_opts = ipvs_mt_opts,
+ },
+ {
+ .version = XTABLES_VERSION,
+ .name = "ipvs",
+ .revision = 0,
+ .family = NFPROTO_IPV6,
+ .size = XT_ALIGN(sizeof(struct xt_ipvs_mtinfo)),
+ .userspacesize = XT_ALIGN(sizeof(struct xt_ipvs_mtinfo)),
+ .help = ipvs_mt_help,
+ .parse = ipvs_mt6_parse,
+ .final_check = ipvs_mt_check,
+ .print = ipvs_mt6_print,
+ .save = ipvs_mt6_save,
+ .extra_opts = ipvs_mt_opts,
+ },
+};
+
+void _init(void)
+{
+ xtables_register_matches(ipvs_matches_reg,
+ ARRAY_SIZE(ipvs_matches_reg));
+}
Index: iptables/extensions/libxt_ipvs.man
===================================================================
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ iptables/extensions/libxt_ipvs.man 2010-07-04 20:23:30.000000000 +0900
@@ -0,0 +1,24 @@
+Match IPVS connection properties.
+.TP
+[\fB!\fR] \fB\-\-ipvs\fP
+packet belongs to an IPVS connection
+.TP
+Any of the following options implies \-\-ipvs (even negated)
+.TP
+[\fB!\fR] \fB\-\-vproto\fP \fIprotocol\fP
+VIP protocol to match; by number or name, e.g. "tcp"
+.TP
+[\fB!\fR] \fB\-\-vaddr\fP \fIaddress\fP[\fB/\fP\fImask\fP]
+VIP address to match
+.TP
+[\fB!\fR] \fB\-\-vport\fP \fIport\fP
+VIP port to match; by number or name, e.g. "http"
+.TP
+\fB\-\-vdir\fP {\fBORIGINAL\fP|\fBREPLY\fP}
+flow direction of packet
+.TP
+[\fB!\fR] \fB\-\-vmethod\fP {\fBGATE\fP|\fBIPIP\fP|\fBMASQ\fP}
+IPVS forwarding method used
+.TP
+[\fB!\fR] \fB\-\-vportctl\fP \fIport\fP
+VIP port of the controlling connection to match, e.g. 21 for FTP
Index: iptables/include/linux/netfilter/xt_ipvs.h
===================================================================
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ iptables/include/linux/netfilter/xt_ipvs.h 2010-07-04 20:23:30.000000000 +0900
@@ -0,0 +1,25 @@
+#ifndef _XT_IPVS_H
+#define _XT_IPVS_H 1
+
+#define XT_IPVS_IPVS_PROPERTY (1 << 0) /* all other options imply this one */
+#define XT_IPVS_PROTO (1 << 1)
+#define XT_IPVS_VADDR (1 << 2)
+#define XT_IPVS_VPORT (1 << 3)
+#define XT_IPVS_DIR (1 << 4)
+#define XT_IPVS_METHOD (1 << 5)
+#define XT_IPVS_VPORTCTL (1 << 6)
+#define XT_IPVS_MASK ((1 << 7) - 1)
+#define XT_IPVS_ONCE_MASK (XT_IPVS_MASK & ~XT_IPVS_IPVS_PROPERTY)
+
+struct xt_ipvs_mtinfo {
+ union nf_inet_addr vaddr, vmask;
+ __be16 vport;
+ __u16 l4proto;
+ __u16 fwd_method;
+ __be16 vportctl;
+
+ __u8 invert;
+ __u8 bitmask;
+};
+
+#endif /* _XT_IPVS_H */
^ permalink raw reply
* [patch v2.5 3/4] IPVS: make FTP work with full NAT support
From: Simon Horman, Simon Horman @ 2010-07-10 3:01 UTC (permalink / raw)
To: lvs-devel, netdev, linux-kernel, netfilter, netfilter-devel
Cc: Malcolm Turnbull, Wensong Zhang, Julius Volz, Patrick McHardy,
David S. Miller, Hannes Eder
In-Reply-To: <20100710030057.731118760@vergenet.net>
[-- Attachment #1: IPVS-make-FTP-work-with-full-NAT-support.patch --]
[-- Type: text/plain, Size: 12591 bytes --]
From: Hannes Eder <heder@google.com>
Use nf_conntrack/nf_nat code to do the packet mangling and the TCP
sequence adjusting. The function 'ip_vs_skb_replace' is now dead
code, so it is removed.
To SNAT FTP, use something like:
% iptables -t nat -A POSTROUTING -m ipvs --vaddr 192.168.100.30/32 \
> --vport 21 -j SNAT --to-source 192.168.10.10
and for the data connections in passive mode:
% iptables -t nat -A POSTROUTING -m ipvs --vaddr 192.168.100.30/32 \
> --vportctl 21 -j SNAT --to-source 192.168.10.10
using '-m state --state RELATED' would also works.
Make sure the kernel modules ip_vs_ftp, nf_conntrack_ftp, and
nf_nat_ftp are loaded.
[ up-port and minor fixes by Simon Horman <horms@verge.net.au> ]
Signed-off-by: Hannes Eder <heder@google.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
include/net/ip_vs.h | 2
net/netfilter/ipvs/Kconfig | 2
net/netfilter/ipvs/ip_vs_app.c | 43 ---------
net/netfilter/ipvs/ip_vs_core.c | 1
net/netfilter/ipvs/ip_vs_ftp.c | 174 ++++++++++++++++++++++++++++++++++++---
5 files changed, 164 insertions(+), 58 deletions(-)
v2.5
* Use nf_ct_is_untracked(ct) instead of nf_ct_is_untracked(),
the latter is blatantly incorrect
* Return 0 (and thus drop the packet) if mangling wasn't attempted
v2.4
As suggested by Patrick McHardy
* Use nf_conntrack_untracked() instead of &nf_conntrack_untracked
* Fix ip_vs_ftp_out logic
- Don't call nf_nat_mangle_tcp_packet() unless ct is valid and tracked
- Only call ip_vs_expect_relatedi() if nf_nat_mangle_tcp_packet()
succeeds
- Note that packets are dropped if mangling fails
Other
* Drop unrelated cosmetic change to sizing of buf in ip_vs_ftp_out()
v2.3
* Up-port
* Drop buf_len = snprintf() change - its a separate, cosmetic, fix
As suggested by Patrick McHardy
* Use %pI4 instead of NIPQUAD
v2.2
* No change
v2.1
* Up-port
Index: nf-next-2.6/include/net/ip_vs.h
===================================================================
--- nf-next-2.6.orig/include/net/ip_vs.h 2010-07-10 11:48:53.000000000 +0900
+++ nf-next-2.6/include/net/ip_vs.h 2010-07-10 11:56:12.000000000 +0900
@@ -736,8 +736,6 @@ extern void ip_vs_app_inc_put(struct ip_
extern int ip_vs_app_pkt_out(struct ip_vs_conn *, struct sk_buff *skb);
extern int ip_vs_app_pkt_in(struct ip_vs_conn *, struct sk_buff *skb);
-extern int ip_vs_skb_replace(struct sk_buff *skb, gfp_t pri,
- char *o_buf, int o_len, char *n_buf, int n_len);
extern int ip_vs_app_init(void);
extern void ip_vs_app_cleanup(void);
Index: nf-next-2.6/net/netfilter/ipvs/Kconfig
===================================================================
--- nf-next-2.6.orig/net/netfilter/ipvs/Kconfig 2010-07-10 11:56:01.000000000 +0900
+++ nf-next-2.6/net/netfilter/ipvs/Kconfig 2010-07-10 11:56:12.000000000 +0900
@@ -235,7 +235,7 @@ comment 'IPVS application helper'
config IP_VS_FTP
tristate "FTP protocol helper"
- depends on IP_VS_PROTO_TCP
+ depends on IP_VS_PROTO_TCP && NF_NAT
---help---
FTP is a protocol that transfers IP address and/or port number in
the payload. In the virtual server via Network Address Translation,
Index: nf-next-2.6/net/netfilter/ipvs/ip_vs_app.c
===================================================================
--- nf-next-2.6.orig/net/netfilter/ipvs/ip_vs_app.c 2010-07-10 11:48:53.000000000 +0900
+++ nf-next-2.6/net/netfilter/ipvs/ip_vs_app.c 2010-07-10 11:56:12.000000000 +0900
@@ -569,49 +569,6 @@ static const struct file_operations ip_v
};
#endif
-
-/*
- * Replace a segment of data with a new segment
- */
-int ip_vs_skb_replace(struct sk_buff *skb, gfp_t pri,
- char *o_buf, int o_len, char *n_buf, int n_len)
-{
- int diff;
- int o_offset;
- int o_left;
-
- EnterFunction(9);
-
- diff = n_len - o_len;
- o_offset = o_buf - (char *)skb->data;
- /* The length of left data after o_buf+o_len in the skb data */
- o_left = skb->len - (o_offset + o_len);
-
- if (diff <= 0) {
- memmove(o_buf + n_len, o_buf + o_len, o_left);
- memcpy(o_buf, n_buf, n_len);
- skb_trim(skb, skb->len + diff);
- } else if (diff <= skb_tailroom(skb)) {
- skb_put(skb, diff);
- memmove(o_buf + n_len, o_buf + o_len, o_left);
- memcpy(o_buf, n_buf, n_len);
- } else {
- if (pskb_expand_head(skb, skb_headroom(skb), diff, pri))
- return -ENOMEM;
- skb_put(skb, diff);
- memmove(skb->data + o_offset + n_len,
- skb->data + o_offset + o_len, o_left);
- skb_copy_to_linear_data_offset(skb, o_offset, n_buf, n_len);
- }
-
- /* must update the iph total length here */
- ip_hdr(skb)->tot_len = htons(skb->len);
-
- LeaveFunction(9);
- return 0;
-}
-
-
int __init ip_vs_app_init(void)
{
/* we will replace it with proc_net_ipvs_create() soon */
Index: nf-next-2.6/net/netfilter/ipvs/ip_vs_core.c
===================================================================
--- nf-next-2.6.orig/net/netfilter/ipvs/ip_vs_core.c 2010-07-10 11:56:01.000000000 +0900
+++ nf-next-2.6/net/netfilter/ipvs/ip_vs_core.c 2010-07-10 11:56:12.000000000 +0900
@@ -54,7 +54,6 @@
EXPORT_SYMBOL(register_ip_vs_scheduler);
EXPORT_SYMBOL(unregister_ip_vs_scheduler);
-EXPORT_SYMBOL(ip_vs_skb_replace);
EXPORT_SYMBOL(ip_vs_proto_name);
EXPORT_SYMBOL(ip_vs_conn_new);
EXPORT_SYMBOL(ip_vs_conn_in_get);
Index: nf-next-2.6/net/netfilter/ipvs/ip_vs_ftp.c
===================================================================
--- nf-next-2.6.orig/net/netfilter/ipvs/ip_vs_ftp.c 2010-07-10 11:48:54.000000000 +0900
+++ nf-next-2.6/net/netfilter/ipvs/ip_vs_ftp.c 2010-07-10 11:59:19.000000000 +0900
@@ -20,6 +20,17 @@
*
* Author: Wouter Gadeyne
*
+ *
+ * Code for ip_vs_expect_related and ip_vs_expect_callback is taken from
+ * http://www.ssi.bg/~ja/nfct/:
+ *
+ * ip_vs_nfct.c: Netfilter connection tracking support for IPVS
+ *
+ * Portions Copyright (C) 2001-2002
+ * Antefacto Ltd, 181 Parnell St, Dublin 1, Ireland.
+ *
+ * Portions Copyright (C) 2003-2008
+ * Julian Anastasov
*/
#define KMSG_COMPONENT "IPVS"
@@ -32,6 +43,9 @@
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/netfilter.h>
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_expect.h>
+#include <net/netfilter/nf_nat_helper.h>
#include <linux/gfp.h>
#include <net/protocol.h>
#include <net/tcp.h>
@@ -43,6 +57,16 @@
#define SERVER_STRING "227 Entering Passive Mode ("
#define CLIENT_STRING "PORT "
+#define FMT_TUPLE "%pI4:%u->%pI4:%u/%u"
+#define ARG_TUPLE(T) (T)->src.u3.ip, ntohs((T)->src.u.all), \
+ (T)->dst.u3.ip, ntohs((T)->dst.u.all), \
+ (T)->dst.protonum
+
+#define FMT_CONN "%pI4:%u->%pI4:%u->%pI4:%u/%u:%u"
+#define ARG_CONN(C) (C)->caddr, ntohs((C)->cport), \
+ (C)->vaddr, ntohs((C)->vport), \
+ (C)->daddr, ntohs((C)->dport), \
+ (C)->protocol, (C)->state
/*
* List of ports (up to IP_VS_APP_MAX_PORTS) to be handled by helper
@@ -123,6 +147,119 @@ static int ip_vs_ftp_get_addrport(char *
return 1;
}
+/*
+ * Called from init_conntrack() as expectfn handler.
+ */
+static void
+ip_vs_expect_callback(struct nf_conn *ct,
+ struct nf_conntrack_expect *exp)
+{
+ struct nf_conntrack_tuple *orig, new_reply;
+ struct ip_vs_conn *cp;
+
+ if (exp->tuple.src.l3num != PF_INET)
+ return;
+
+ /*
+ * We assume that no NF locks are held before this callback.
+ * ip_vs_conn_out_get and ip_vs_conn_in_get should match their
+ * expectations even if they use wildcard values, now we provide the
+ * actual values from the newly created original conntrack direction.
+ * The conntrack is confirmed when packet reaches IPVS hooks.
+ */
+
+ /* RS->CLIENT */
+ orig = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple;
+ cp = ip_vs_conn_out_get(exp->tuple.src.l3num, orig->dst.protonum,
+ &orig->src.u3, orig->src.u.tcp.port,
+ &orig->dst.u3, orig->dst.u.tcp.port);
+ if (cp) {
+ /* Change reply CLIENT->RS to CLIENT->VS */
+ new_reply = ct->tuplehash[IP_CT_DIR_REPLY].tuple;
+ IP_VS_DBG(7, "%s(): ct=%p, status=0x%lX, tuples=" FMT_TUPLE ", "
+ FMT_TUPLE ", found inout cp=" FMT_CONN "\n",
+ __func__, ct, ct->status,
+ ARG_TUPLE(orig), ARG_TUPLE(&new_reply),
+ ARG_CONN(cp));
+ new_reply.dst.u3 = cp->vaddr;
+ new_reply.dst.u.tcp.port = cp->vport;
+ IP_VS_DBG(7, "%s(): ct=%p, new tuples=" FMT_TUPLE ", " FMT_TUPLE
+ ", inout cp=" FMT_CONN "\n",
+ __func__, ct,
+ ARG_TUPLE(orig), ARG_TUPLE(&new_reply),
+ ARG_CONN(cp));
+ goto alter;
+ }
+
+ /* CLIENT->VS */
+ cp = ip_vs_conn_in_get(exp->tuple.src.l3num, orig->dst.protonum,
+ &orig->src.u3, orig->src.u.tcp.port,
+ &orig->dst.u3, orig->dst.u.tcp.port);
+ if (cp) {
+ /* Change reply VS->CLIENT to RS->CLIENT */
+ new_reply = ct->tuplehash[IP_CT_DIR_REPLY].tuple;
+ IP_VS_DBG(7, "%s(): ct=%p, status=0x%lX, tuples=" FMT_TUPLE ", "
+ FMT_TUPLE ", found outin cp=" FMT_CONN "\n",
+ __func__, ct, ct->status,
+ ARG_TUPLE(orig), ARG_TUPLE(&new_reply),
+ ARG_CONN(cp));
+ new_reply.src.u3 = cp->daddr;
+ new_reply.src.u.tcp.port = cp->dport;
+ IP_VS_DBG(7, "%s(): ct=%p, new tuples=" FMT_TUPLE ", "
+ FMT_TUPLE ", outin cp=" FMT_CONN "\n",
+ __func__, ct,
+ ARG_TUPLE(orig), ARG_TUPLE(&new_reply),
+ ARG_CONN(cp));
+ goto alter;
+ }
+
+ IP_VS_DBG(7, "%s(): ct=%p, status=0x%lX, tuple=" FMT_TUPLE
+ " - unknown expect\n",
+ __func__, ct, ct->status, ARG_TUPLE(orig));
+ return;
+
+alter:
+ /* Never alter conntrack for non-NAT conns */
+ if (IP_VS_FWD_METHOD(cp) == IP_VS_CONN_F_MASQ)
+ nf_conntrack_alter_reply(ct, &new_reply);
+ ip_vs_conn_put(cp);
+ return;
+}
+
+/*
+ * Create NF conntrack expectation with wildcard (optional) source port.
+ * Then the default callback function will alter the reply and will confirm
+ * the conntrack entry when the first packet comes.
+ */
+static void
+ip_vs_expect_related(struct sk_buff *skb, struct nf_conn *ct,
+ struct ip_vs_conn *cp, u_int8_t proto,
+ const __be16 *port, int from_rs)
+{
+ struct nf_conntrack_expect *exp;
+
+ BUG_ON(!ct || ct == &nf_conntrack_untracked);
+
+ exp = nf_ct_expect_alloc(ct);
+ if (!exp)
+ return;
+
+ if (from_rs)
+ nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT,
+ nf_ct_l3num(ct), &cp->daddr, &cp->caddr,
+ proto, port, &cp->cport);
+ else
+ nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT,
+ nf_ct_l3num(ct), &cp->caddr, &cp->vaddr,
+ proto, port, &cp->vport);
+
+ exp->expectfn = ip_vs_expect_callback;
+
+ IP_VS_DBG(7, "%s(): ct=%p, expect tuple=" FMT_TUPLE "\n",
+ __func__, ct, ARG_TUPLE(&exp->tuple));
+ nf_ct_expect_related(exp);
+ nf_ct_expect_put(exp);
+}
/*
* Look at outgoing ftp packets to catch the response to a PASV command
@@ -149,7 +286,9 @@ static int ip_vs_ftp_out(struct ip_vs_ap
struct ip_vs_conn *n_cp;
char buf[24]; /* xxx.xxx.xxx.xxx,ppp,ppp\000 */
unsigned buf_len;
- int ret;
+ int ret = 0;
+ enum ip_conntrack_info ctinfo;
+ struct nf_conn *ct;
#ifdef CONFIG_IP_VS_IPV6
/* This application helper doesn't work with IPv6 yet,
@@ -219,19 +358,26 @@ static int ip_vs_ftp_out(struct ip_vs_ap
buf_len = strlen(buf);
+ ct = nf_ct_get(skb, &ctinfo);
+ if (ct && !nf_ct_is_untracked(ct)) {
+ /* If mangling fails this function will return 0
+ * which will cause the packet to be dropped.
+ * Mangling can only fail under memory pressure,
+ * hopefully it will succeed on the retransmitted
+ * packet.
+ */
+ ret = nf_nat_mangle_tcp_packet(skb, ct, ctinfo,
+ start-data, end-start,
+ buf, buf_len);
+ if (ret)
+ ip_vs_expect_related(skb, ct, n_cp,
+ IPPROTO_TCP, NULL, 0);
+ }
+
/*
- * Calculate required delta-offset to keep TCP happy
+ * Not setting 'diff' is intentional, otherwise the sequence
+ * would be adjusted twice.
*/
- *diff = buf_len - (end-start);
-
- if (*diff == 0) {
- /* simply replace it with new passive address */
- memcpy(start, buf, buf_len);
- ret = 1;
- } else {
- ret = !ip_vs_skb_replace(skb, GFP_ATOMIC, start,
- end-start, buf, buf_len);
- }
cp->app_data = NULL;
ip_vs_tcp_conn_listen(n_cp);
@@ -263,6 +409,7 @@ static int ip_vs_ftp_in(struct ip_vs_app
union nf_inet_addr to;
__be16 port;
struct ip_vs_conn *n_cp;
+ struct nf_conn *ct;
#ifdef CONFIG_IP_VS_IPV6
/* This application helper doesn't work with IPv6 yet,
@@ -349,6 +496,11 @@ static int ip_vs_ftp_in(struct ip_vs_app
ip_vs_control_add(n_cp, cp);
}
+ ct = (struct nf_conn *)skb->nfct;
+ if (ct && ct != &nf_conntrack_untracked)
+ ip_vs_expect_related(skb, ct, n_cp,
+ IPPROTO_TCP, &n_cp->dport, 1);
+
/*
* Move tunnel to listen state
*/
^ permalink raw reply
* [patch v2.5 2/4] IPVS: make friends with nf_conntrack
From: Simon Horman, Simon Horman @ 2010-07-10 3:00 UTC (permalink / raw)
To: lvs-devel, netdev, linux-kernel, netfilter, netfilter-devel
Cc: Malcolm Turnbull, Wensong Zhang, Julius Volz, Patrick McHardy,
David S. Miller, Hannes Eder
In-Reply-To: <20100710030057.731118760@vergenet.net>
[-- Attachment #1: IPVS-make-friends-with-nf_conntrack.patch --]
[-- Type: text/plain, Size: 5649 bytes --]
From: Hannes Eder <heder@google.com>
Update the nf_conntrack tuple in reply direction, as we will see
traffic from the real server (RIP) to the client (CIP). Once this is
done we can use netfilters SNAT in POSTROUTING, especially with
xt_ipvs, to do source NAT, e.g.:
% iptables -t nat -A POSTROUTING -m ipvs --vaddr 192.168.100.30/32 --vport 80 \
> -j SNAT --to-source 192.168.10.10
[ minor fixes by Simon Horman <horms@verge.net.au> ]
Signed-off-by: Hannes Eder <heder@google.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
net/netfilter/ipvs/Kconfig | 2 +-
net/netfilter/ipvs/ip_vs_core.c | 36 ------------------------------------
net/netfilter/ipvs/ip_vs_xmit.c | 29 +++++++++++++++++++++++++++++
3 files changed, 30 insertions(+), 37 deletions(-)
v2.4
As per advice from Patrick McHardy
* Use nf_conntrack_untracked() instead of &nf_conntrack_untracked
v2.1, v2.2, v2.3
No change
Index: nf-next-2.6/net/netfilter/ipvs/Kconfig
===================================================================
--- nf-next-2.6.orig/net/netfilter/ipvs/Kconfig 2010-07-07 13:24:31.000000000 +0900
+++ nf-next-2.6/net/netfilter/ipvs/Kconfig 2010-07-07 13:38:23.000000000 +0900
@@ -3,7 +3,7 @@
#
menuconfig IP_VS
tristate "IP virtual server support"
- depends on NET && INET && NETFILTER
+ depends on NET && INET && NETFILTER && NF_CONNTRACK
---help---
IP Virtual Server support will let you build a high-performance
virtual server based on cluster of two or more real servers. This
Index: nf-next-2.6/net/netfilter/ipvs/ip_vs_core.c
===================================================================
--- nf-next-2.6.orig/net/netfilter/ipvs/ip_vs_core.c 2010-07-07 13:23:37.000000000 +0900
+++ nf-next-2.6/net/netfilter/ipvs/ip_vs_core.c 2010-07-07 13:38:23.000000000 +0900
@@ -536,26 +536,6 @@ int ip_vs_leave(struct ip_vs_service *sv
return NF_DROP;
}
-
-/*
- * It is hooked before NF_IP_PRI_NAT_SRC at the NF_INET_POST_ROUTING
- * chain, and is used for VS/NAT.
- * It detects packets for VS/NAT connections and sends the packets
- * immediately. This can avoid that iptable_nat mangles the packets
- * for VS/NAT.
- */
-static unsigned int ip_vs_post_routing(unsigned int hooknum,
- struct sk_buff *skb,
- const struct net_device *in,
- const struct net_device *out,
- int (*okfn)(struct sk_buff *))
-{
- if (!skb->ipvs_property)
- return NF_ACCEPT;
- /* The packet was sent from IPVS, exit this chain */
- return NF_STOP;
-}
-
__sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset)
{
return csum_fold(skb_checksum(skb, offset, skb->len - offset, 0));
@@ -1499,14 +1479,6 @@ static struct nf_hook_ops ip_vs_ops[] __
.hooknum = NF_INET_FORWARD,
.priority = 99,
},
- /* Before the netfilter connection tracking, exit from POST_ROUTING */
- {
- .hook = ip_vs_post_routing,
- .owner = THIS_MODULE,
- .pf = PF_INET,
- .hooknum = NF_INET_POST_ROUTING,
- .priority = NF_IP_PRI_NAT_SRC-1,
- },
#ifdef CONFIG_IP_VS_IPV6
/* After packet filtering, forward packet through VS/DR, VS/TUN,
* or VS/NAT(change destination), so that filtering rules can be
@@ -1535,14 +1507,6 @@ static struct nf_hook_ops ip_vs_ops[] __
.hooknum = NF_INET_FORWARD,
.priority = 99,
},
- /* Before the netfilter connection tracking, exit from POST_ROUTING */
- {
- .hook = ip_vs_post_routing,
- .owner = THIS_MODULE,
- .pf = PF_INET6,
- .hooknum = NF_INET_POST_ROUTING,
- .priority = NF_IP6_PRI_NAT_SRC-1,
- },
#endif
};
Index: nf-next-2.6/net/netfilter/ipvs/ip_vs_xmit.c
===================================================================
--- nf-next-2.6.orig/net/netfilter/ipvs/ip_vs_xmit.c 2010-07-07 13:23:37.000000000 +0900
+++ nf-next-2.6/net/netfilter/ipvs/ip_vs_xmit.c 2010-07-07 13:42:22.000000000 +0900
@@ -28,6 +28,7 @@
#include <net/ip6_route.h>
#include <linux/icmpv6.h>
#include <linux/netfilter.h>
+#include <net/netfilter/nf_conntrack.h>
#include <linux/netfilter_ipv4.h>
#include <net/ip_vs.h>
@@ -348,6 +349,30 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb
}
#endif
+static void
+ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp)
+{
+ struct nf_conn *ct = (struct nf_conn *)skb->nfct;
+ struct nf_conntrack_tuple new_tuple;
+
+ if (ct == NULL || nf_ct_is_untracked(ct) || nf_ct_is_confirmed(ct))
+ return;
+
+ /*
+ * The connection is not yet in the hashtable, so we update it.
+ * CIP->VIP will remain the same, so leave the tuple in
+ * IP_CT_DIR_ORIGINAL untouched. When the reply comes back from the
+ * real-server we will see RIP->DIP.
+ */
+ new_tuple = ct->tuplehash[IP_CT_DIR_REPLY].tuple;
+ new_tuple.src.u3 = cp->daddr;
+ /*
+ * This will also take care of UDP and other protocols.
+ */
+ new_tuple.src.u.tcp.port = cp->dport;
+ nf_conntrack_alter_reply(ct, &new_tuple);
+}
+
/*
* NAT transmitter (only for outside-to-inside nat forwarding)
* Not used for related ICMP
@@ -403,6 +428,8 @@ ip_vs_nat_xmit(struct sk_buff *skb, stru
IP_VS_DBG_PKT(10, pp, skb, 0, "After DNAT");
+ ip_vs_update_conntrack(skb, cp);
+
/* FIXME: when application helper enlarges the packet and the length
is larger than the MTU of outgoing device, there will be still
MTU problem. */
@@ -479,6 +506,8 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, s
IP_VS_DBG_PKT(10, pp, skb, 0, "After DNAT");
+ ip_vs_update_conntrack(skb, cp);
+
/* FIXME: when application helper enlarges the packet and the length
is larger than the MTU of outgoing device, there will be still
MTU problem. */
^ permalink raw reply
* [patch v2.5 1/4] netfilter: xt_ipvs (netfilter matcher for IPVS)
From: Simon Horman, Simon Horman @ 2010-07-10 3:00 UTC (permalink / raw)
To: lvs-devel, netdev, linux-kernel, netfilter, netfilter-devel
Cc: Malcolm Turnbull, Wensong Zhang, Julius Volz, Patrick McHardy,
David S. Miller, Hannes Eder
In-Reply-To: <20100710030057.731118760@vergenet.net>
[-- Attachment #1: netfilter-xt_ipvs-netfilter-matcher-for-IPVS.patch --]
[-- Type: text/plain, Size: 8874 bytes --]
From: Hannes Eder <heder@google.com>
This implements the kernel-space side of the netfilter matcher xt_ipvs.
[ minor fixes by Simon Horman <horms@verge.net.au> ]
Signed-off-by: Hannes Eder <heder@google.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
include/linux/netfilter/xt_ipvs.h | 25 ++++
net/netfilter/Kconfig | 10 +
net/netfilter/Makefile | 1
net/netfilter/ipvs/ip_vs_proto.c | 1
net/netfilter/xt_ipvs.c | 189 +++++++++++++++++++++++++++++++++++++
5 files changed, 226 insertions(+), 0 deletions(-)
create mode 100644 include/linux/netfilter/xt_ipvs.h
create mode 100644 net/netfilter/xt_ipvs.c
v2.5
* Use nf_ct_is_untracked(ct) instead of ct == nf_ct_is_untracked(ct),
the later is blatantly incorrect.
v2.4
As per advice from Patrick McHardy
* Reduce size of l4proto and fwd_method members of struct xt_ipvs_mtinf
from __u16 to __u8
* Use nf_conntrack_untracked() instead of &nf_conntrack_untracked
v2.3
As per advice from Patrick McHardy
* Don't define a value for _XT_IPVS_H in xt_ipvs.h
* Depend on NF_CONNTRACK
* Update to new API
- ipvs_mt_check() should return an int rather than a bool
- Change type of ipvs_mt()'s par parameter from
struct xt_action_param to struct xt_match_param
- Make ipvs_mt()'s par parameter non-const
v2.1, v2.2
No Change
Index: nf-next-2.6/include/linux/netfilter/xt_ipvs.h
===================================================================
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ nf-next-2.6/include/linux/netfilter/xt_ipvs.h 2010-07-10 11:49:23.000000000 +0900
@@ -0,0 +1,25 @@
+#ifndef _XT_IPVS_H
+#define _XT_IPVS_H
+
+#define XT_IPVS_IPVS_PROPERTY (1 << 0) /* all other options imply this one */
+#define XT_IPVS_PROTO (1 << 1)
+#define XT_IPVS_VADDR (1 << 2)
+#define XT_IPVS_VPORT (1 << 3)
+#define XT_IPVS_DIR (1 << 4)
+#define XT_IPVS_METHOD (1 << 5)
+#define XT_IPVS_VPORTCTL (1 << 6)
+#define XT_IPVS_MASK ((1 << 7) - 1)
+#define XT_IPVS_ONCE_MASK (XT_IPVS_MASK & ~XT_IPVS_IPVS_PROPERTY)
+
+struct xt_ipvs_mtinfo {
+ union nf_inet_addr vaddr, vmask;
+ __be16 vport;
+ __u8 l4proto;
+ __u8 fwd_method;
+ __be16 vportctl;
+
+ __u8 invert;
+ __u8 bitmask;
+};
+
+#endif /* _XT_IPVS_H */
Index: nf-next-2.6/net/netfilter/Kconfig
===================================================================
--- nf-next-2.6.orig/net/netfilter/Kconfig 2010-07-10 11:48:54.000000000 +0900
+++ nf-next-2.6/net/netfilter/Kconfig 2010-07-10 11:49:23.000000000 +0900
@@ -726,6 +726,16 @@ config NETFILTER_XT_MATCH_IPRANGE
If unsure, say M.
+config NETFILTER_XT_MATCH_IPVS
+ tristate '"ipvs" match support'
+ depends on IP_VS
+ depends on NETFILTER_ADVANCED
+ depends on NF_CONNTRACK
+ help
+ This option allows you to match against IPVS properties of a packet.
+
+ If unsure, say N.
+
config NETFILTER_XT_MATCH_LENGTH
tristate '"length" match support'
depends on NETFILTER_ADVANCED
Index: nf-next-2.6/net/netfilter/Makefile
===================================================================
--- nf-next-2.6.orig/net/netfilter/Makefile 2010-07-10 11:48:54.000000000 +0900
+++ nf-next-2.6/net/netfilter/Makefile 2010-07-10 11:49:23.000000000 +0900
@@ -76,6 +76,7 @@ obj-$(CONFIG_NETFILTER_XT_MATCH_HASHLIMI
obj-$(CONFIG_NETFILTER_XT_MATCH_HELPER) += xt_helper.o
obj-$(CONFIG_NETFILTER_XT_MATCH_HL) += xt_hl.o
obj-$(CONFIG_NETFILTER_XT_MATCH_IPRANGE) += xt_iprange.o
+obj-$(CONFIG_NETFILTER_XT_MATCH_IPVS) += xt_ipvs.o
obj-$(CONFIG_NETFILTER_XT_MATCH_LENGTH) += xt_length.o
obj-$(CONFIG_NETFILTER_XT_MATCH_LIMIT) += xt_limit.o
obj-$(CONFIG_NETFILTER_XT_MATCH_MAC) += xt_mac.o
Index: nf-next-2.6/net/netfilter/ipvs/ip_vs_proto.c
===================================================================
--- nf-next-2.6.orig/net/netfilter/ipvs/ip_vs_proto.c 2010-07-10 11:48:54.000000000 +0900
+++ nf-next-2.6/net/netfilter/ipvs/ip_vs_proto.c 2010-07-10 11:49:23.000000000 +0900
@@ -98,6 +98,7 @@ struct ip_vs_protocol * ip_vs_proto_get(
return NULL;
}
+EXPORT_SYMBOL(ip_vs_proto_get);
/*
Index: nf-next-2.6/net/netfilter/xt_ipvs.c
===================================================================
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ nf-next-2.6/net/netfilter/xt_ipvs.c 2010-07-10 11:54:50.000000000 +0900
@@ -0,0 +1,189 @@
+/*
+ * xt_ipvs - kernel module to match IPVS connection properties
+ *
+ * Author: Hannes Eder <heder@google.com>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/spinlock.h>
+#include <linux/skbuff.h>
+#ifdef CONFIG_IP_VS_IPV6
+#include <net/ipv6.h>
+#endif
+#include <linux/ip_vs.h>
+#include <linux/types.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter/xt_ipvs.h>
+#include <net/netfilter/nf_conntrack.h>
+
+#include <net/ip_vs.h>
+
+MODULE_AUTHOR("Hannes Eder <heder@google.com>");
+MODULE_DESCRIPTION("Xtables: match IPVS connection properties");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("ipt_ipvs");
+MODULE_ALIAS("ip6t_ipvs");
+
+/* borrowed from xt_conntrack */
+static bool ipvs_mt_addrcmp(const union nf_inet_addr *kaddr,
+ const union nf_inet_addr *uaddr,
+ const union nf_inet_addr *umask,
+ unsigned int l3proto)
+{
+ if (l3proto == NFPROTO_IPV4)
+ return ((kaddr->ip ^ uaddr->ip) & umask->ip) == 0;
+#ifdef CONFIG_IP_VS_IPV6
+ else if (l3proto == NFPROTO_IPV6)
+ return ipv6_masked_addr_cmp(&kaddr->in6, &umask->in6,
+ &uaddr->in6) == 0;
+#endif
+ else
+ return false;
+}
+
+static bool
+ipvs_mt(const struct sk_buff *skb, struct xt_action_param *par)
+{
+ const struct xt_ipvs_mtinfo *data = par->matchinfo;
+ /* ipvs_mt_check ensures that family is only NFPROTO_IPV[46]. */
+ const u_int8_t family = par->family;
+ struct ip_vs_iphdr iph;
+ struct ip_vs_protocol *pp;
+ struct ip_vs_conn *cp;
+ bool match = true;
+
+ if (data->bitmask == XT_IPVS_IPVS_PROPERTY) {
+ match = skb->ipvs_property ^
+ !!(data->invert & XT_IPVS_IPVS_PROPERTY);
+ goto out;
+ }
+
+ /* other flags than XT_IPVS_IPVS_PROPERTY are set */
+ if (!skb->ipvs_property) {
+ match = false;
+ goto out;
+ }
+
+ ip_vs_fill_iphdr(family, skb_network_header(skb), &iph);
+
+ if (data->bitmask & XT_IPVS_PROTO)
+ if ((iph.protocol == data->l4proto) ^
+ !(data->invert & XT_IPVS_PROTO)) {
+ match = false;
+ goto out;
+ }
+
+ pp = ip_vs_proto_get(iph.protocol);
+ if (unlikely(!pp)) {
+ match = false;
+ goto out;
+ }
+
+ /*
+ * Check if the packet belongs to an existing entry
+ */
+ cp = pp->conn_out_get(family, skb, pp, &iph, iph.len, 1 /* inverse */);
+ if (unlikely(cp == NULL)) {
+ match = false;
+ goto out;
+ }
+
+ /*
+ * We found a connection, i.e. ct != 0, make sure to call
+ * __ip_vs_conn_put before returning. In our case jump to out_put_con.
+ */
+
+ if (data->bitmask & XT_IPVS_VPORT)
+ if ((cp->vport == data->vport) ^
+ !(data->invert & XT_IPVS_VPORT)) {
+ match = false;
+ goto out_put_cp;
+ }
+
+ if (data->bitmask & XT_IPVS_VPORTCTL)
+ if ((cp->control != NULL &&
+ cp->control->vport == data->vportctl) ^
+ !(data->invert & XT_IPVS_VPORTCTL)) {
+ match = false;
+ goto out_put_cp;
+ }
+
+ if (data->bitmask & XT_IPVS_DIR) {
+ enum ip_conntrack_info ctinfo;
+ struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
+
+ if (ct == NULL || nf_ct_is_untracked(ct)) {
+ match = false;
+ goto out_put_cp;
+ }
+
+ if ((ctinfo >= IP_CT_IS_REPLY) ^
+ !!(data->invert & XT_IPVS_DIR)) {
+ match = false;
+ goto out_put_cp;
+ }
+ }
+
+ if (data->bitmask & XT_IPVS_METHOD)
+ if (((cp->flags & IP_VS_CONN_F_FWD_MASK) == data->fwd_method) ^
+ !(data->invert & XT_IPVS_METHOD)) {
+ match = false;
+ goto out_put_cp;
+ }
+
+ if (data->bitmask & XT_IPVS_VADDR) {
+ if (ipvs_mt_addrcmp(&cp->vaddr, &data->vaddr,
+ &data->vmask, family) ^
+ !(data->invert & XT_IPVS_VADDR)) {
+ match = false;
+ goto out_put_cp;
+ }
+ }
+
+out_put_cp:
+ __ip_vs_conn_put(cp);
+out:
+ pr_debug("match=%d\n", match);
+ return match;
+}
+
+static int ipvs_mt_check(const struct xt_mtchk_param *par)
+{
+ if (par->family != NFPROTO_IPV4
+#ifdef CONFIG_IP_VS_IPV6
+ && par->family != NFPROTO_IPV6
+#endif
+ ) {
+ pr_info("protocol family %u not supported\n", par->family);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static struct xt_match xt_ipvs_mt_reg __read_mostly = {
+ .name = "ipvs",
+ .revision = 0,
+ .family = NFPROTO_UNSPEC,
+ .match = ipvs_mt,
+ .checkentry = ipvs_mt_check,
+ .matchsize = XT_ALIGN(sizeof(struct xt_ipvs_mtinfo)),
+ .me = THIS_MODULE,
+};
+
+static int __init ipvs_mt_init(void)
+{
+ return xt_register_match(&xt_ipvs_mt_reg);
+}
+
+static void __exit ipvs_mt_exit(void)
+{
+ xt_unregister_match(&xt_ipvs_mt_reg);
+}
+
+module_init(ipvs_mt_init);
+module_exit(ipvs_mt_exit);
^ permalink raw reply
* [patch v2.5 0/4] [patch v2.4 0/4] IPVS full NAT support + netfilter 'ipvs' match support
From: Simon Horman, Simon Horman @ 2010-07-10 3:00 UTC (permalink / raw)
To: lvs-devel, netdev, linux-kernel, netfilter, netfilter-devel
Cc: Malcolm Turnbull, Wensong Zhang, Julius Volz, Patrick McHardy,
David S. Miller, Hannes Eder
This is a repost of a patch-series posted by Hannes Eder last September.
This is v2 of the patch series and I don't see any outstanding objections to
it in the mailing list archives.
Series v2.5 fixes some problems introduced in v2.4.
Series v2.4 addresses all of the concerns that Patrick McHardy raised
witht the v2.3 series.
Malcolm Turnbull has offered to test this code so I'd like to get
a Reviewed-by from him before the code gets merged. In other words,
at this stage these patches are for review not merging.
The original cover-email from Hannes follows.
The diffstat output has been updated to reflect minor up-porting by me.
From: Hannes Eder <heder@google.com>
The following series implements full NAT support for IPVS. The
approach is via a minimal change to IPVS (make friends with
nf_conntrack) and adding a netfilter matcher, kernel- and user-space
part, i.e. xt_ipvs and libxt_ipvs.
Example usage:
% ipvsadm -A -t 192.168.100.30:80 -s rr
% ipvsadm -a -t 192.168.100.30:80 -r 192.168.10.20:80 -m
# ...
# Source NAT for VIP 192.168.100.30:80
% iptables -t nat -A POSTROUTING -m ipvs --vaddr 192.168.100.30/32 \
> --vport 80 -j SNAT --to-source 192.168.10.10
or SNAT-ing only a specific real server:
% iptables -t nat -A POSTROUTING --dst 192.168.11.20 \
> -m ipvs --vaddr 192.168.100.30/32 -j SNAT --to-source 192.168.10.10
First of all, thanks for all the feedback. This is the changelog for v2:
- Make ip_vs_ftp work again. Setup nf_conntrack expectations for
related data connections (based on Julian's patch see
http://www.ssi.bg/~ja/nfct/) and let nf_conntrack/nf_nat do the
packet mangling and the TCP sequence adjusting.
This change rises the question how to deal with ip_vs_sync? Does it
work together with conntrackd? Wild idea: what about getting rid of
ip_vs_sync and piggy packing all on nf_conntrack and use conntrackd?
Any comments on this?
- xt_ipvs: add new rule '--vportctl port' to match the VIP port of the
controlling connection, e.g. port 21 for FTP. Can be used to match
a related data connection for FTP:
# SNAT FTP control connection
% iptables -t nat -A POSTROUTING -m ipvs --vaddr 192.168.100.30/32 \
> --vport 21 -j SNAT --to-source 192.168.10.10
# SNAT FTP passive data connection
% iptables -t nat -A POSTROUTING -m ipvs --vaddr 192.168.100.30/32 \
> --vportctl 21 -j SNAT --to-source 192.168.10.10
- xt_ipvs: use 'par->family' instead of 'skb->protocol'
- xt_ipvs: add ipvs_mt_check and restrict to NFPROTO_IPV4 and NFPROTO_IPV6
- Call nf_conntrack_alter_reply(), so helper lookup is performed based
on the changed tuple.
Changes to the linux kernel
(nf-next-2.6, "bridge: add per bridge device controls for invoking iptables")
Hannes Eder (3):
netfilter: xt_ipvs (netfilter matcher for IPVS)
IPVS: make friends with nf_conntrack
IPVS: make FTP work with full NAT support
include/linux/netfilter/xt_ipvs.h | 25 +++++
include/net/ip_vs.h | 2
net/netfilter/Kconfig | 10 ++
net/netfilter/Makefile | 1
net/netfilter/ipvs/Kconfig | 4
net/netfilter/ipvs/ip_vs_app.c | 43 ---------
net/netfilter/ipvs/ip_vs_core.c | 37 --------
net/netfilter/ipvs/ip_vs_ftp.c | 174 +++++++++++++++++++++++++++++++++++---
net/netfilter/ipvs/ip_vs_proto.c | 1
net/netfilter/ipvs/ip_vs_xmit.c | 29 ++++++
net/netfilter/xt_ipvs.c | 189 +++++++++++++++++++++++++++++++++++++
11 files changed, 420 insertions(+), 95 deletions(-)
create mode 100644 include/linux/netfilter/xt_ipvs.h
create mode 100644 net/netfilter/xt_ipvs.c
Changes to iptables
(iptables.git, "xt_quota: also document negation")
Hannes Eder (1):
libxt_ipvs: user-space lib for netfilter matcher xt_ipvs
configure.ac | 10 1
extensions/libxt_ipvs.c | 365 +++++++++++++++++++++++++++++++++++++
extensions/libxt_ipvs.man | 24 ++
include/linux/netfilter/xt_ipvs.h | 25 +++
4 files changed, 422 insertions(+), 2 deletions(-)
create mode 100644 extensions/libxt_ipvs.c
create mode 100644 extensions/libxt_ipvs.man
create mode 100644 include/linux/netfilter/xt_ipvs.h
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
--
To unsubscribe from this list: send the line "unsubscribe netfilter-devel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [patch v2.4 0/4] IPVS full NAT support + netfilter 'ipvs' match support
From: Simon Horman @ 2010-07-10 2:54 UTC (permalink / raw)
To: lvs-devel, netdev, linux-kernel, netfilter, netfilter-devel
Cc: Malcolm Turnbull, Wensong Zhang, Julius Volz, Patrick McHardy,
David S. Miller, Hannes Eder
In-Reply-To: <20100710020351.168273435@vergenet.net>
Sorry, there are several errors in this patch series.
I will repost v2.5 ASAP.
^ permalink raw reply
* [patch v2.4 4/4] libxt_ipvs: user-space lib for netfilter matcher xt_ipvs
From: Simon Horman, Simon Horman @ 2010-07-10 2:03 UTC (permalink / raw)
To: lvs-devel, netdev, linux-kernel, netfilter, netfilter-devel
Cc: Malcolm Turnbull, Wensong Zhang, Julius Volz, Patrick McHardy,
David S. Miller, Hannes Eder
In-Reply-To: <20100710020351.168273435@vergenet.net>
[-- Attachment #1: libxt_ipvs-user-space-lib-for-netfilter-matcher-xt_ipvs.patch --]
[-- Type: text/plain, Size: 13930 bytes --]
From: Hannes Eder <heder@google.com>
The user-space library for the netfilter matcher xt_ipvs.
[ trivial up-port by Simon Horman <horms@verge.net.au> ]
Signed-off-by: Hannes Eder <heder@google.com>
Acked-by: Simon Horman <horms@verge.net.au>
configure.ac | 10 -
extensions/libxt_ipvs.c | 365 +++++++++++++++++++++++++++++++++++++
extensions/libxt_ipvs.man | 24 ++
include/linux/netfilter/xt_ipvs.h | 25 +++
4 files changed, 422 insertions(+), 2 deletions(-)
create mode 100644 extensions/libxt_ipvs.c
create mode 100644 extensions/libxt_ipvs.man
create mode 100644 include/linux/netfilter/xt_ipvs.h
v2.1, v2.3
Trivial up-port
v2.2
No change
Index: iptables/configure.ac
===================================================================
--- iptables.orig/configure.ac 2010-07-04 20:21:07.000000000 +0900
+++ iptables/configure.ac 2010-07-04 20:23:30.000000000 +0900
@@ -52,12 +52,18 @@ AC_ARG_WITH([pkgconfigdir], AS_HELP_STRI
[Path to the pkgconfig directory [[LIBDIR/pkgconfig]]]),
[pkgconfigdir="$withval"], [pkgconfigdir='${libdir}/pkgconfig'])
-AC_CHECK_HEADER([linux/dccp.h])
-
blacklist_modules="";
+
+AC_CHECK_HEADER([linux/dccp.h])
if test "$ac_cv_header_linux_dccp_h" != "yes"; then
blacklist_modules="$blacklist_modules dccp";
fi;
+
+AC_CHECK_HEADER([linux/ip_vs.h])
+if test "$ac_cv_header_linux_ip_vs_h" != "yes"; then
+ blacklist_modules="$blacklist_modules ipvs";
+fi;
+
AC_SUBST([blacklist_modules])
AM_CONDITIONAL([ENABLE_STATIC], [test "$enable_static" = "yes"])
Index: iptables/extensions/libxt_ipvs.c
===================================================================
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ iptables/extensions/libxt_ipvs.c 2010-07-04 20:24:01.000000000 +0900
@@ -0,0 +1,365 @@
+/*
+ * Shared library add-on to iptables to add IPVS matching.
+ *
+ * Detailed doc is in the kernel module source net/netfilter/xt_ipvs.c
+ *
+ * Author: Hannes Eder <heder@google.com>
+ */
+#include <sys/types.h>
+#include <assert.h>
+#include <ctype.h>
+#include <errno.h>
+#include <getopt.h>
+#include <netdb.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <xtables.h>
+#include <linux/ip_vs.h>
+#include <linux/netfilter/xt_ipvs.h>
+
+static const struct option ipvs_mt_opts[] = {
+ { .name = "ipvs", .has_arg = false, .val = '0' },
+ { .name = "vproto", .has_arg = true, .val = '1' },
+ { .name = "vaddr", .has_arg = true, .val = '2' },
+ { .name = "vport", .has_arg = true, .val = '3' },
+ { .name = "vdir", .has_arg = true, .val = '4' },
+ { .name = "vmethod", .has_arg = true, .val = '5' },
+ { .name = "vportctl", .has_arg = true, .val = '6' },
+ { .name = NULL }
+};
+
+static void ipvs_mt_help(void)
+{
+ printf(
+"IPVS match options:\n"
+"[!] --ipvs packet belongs to an IPVS connection\n"
+"\n"
+"Any of the following options implies --ipvs (even negated)\n"
+"[!] --vproto protocol VIP protocol to match; by number or name,\n"
+" e.g. \"tcp\"\n"
+"[!] --vaddr address[/mask] VIP address to match\n"
+"[!] --vport port VIP port to match; by number or name,\n"
+" e.g. \"http\"\n"
+" --vdir {ORIGINAL|REPLY} flow direction of packet\n"
+"[!] --vmethod {GATE|IPIP|MASQ} IPVS forwarding method used\n"
+"[!] --vportctl port VIP port of the controlling connection to\n"
+" match, e.g. 21 for FTP\n"
+ );
+}
+
+static void ipvs_mt_parse_addr_and_mask(const char *arg,
+ union nf_inet_addr *address,
+ union nf_inet_addr *mask,
+ unsigned int family)
+{
+ struct in_addr *addr = NULL;
+ struct in6_addr *addr6 = NULL;
+ unsigned int naddrs = 0;
+
+ if (family == NFPROTO_IPV4) {
+ xtables_ipparse_any(arg, &addr, &mask->in, &naddrs);
+ if (naddrs > 1)
+ xtables_error(PARAMETER_PROBLEM,
+ "multiple IP addresses not allowed");
+ if (naddrs == 1)
+ memcpy(&address->in, addr, sizeof(*addr));
+ } else if (family == NFPROTO_IPV6) {
+ xtables_ip6parse_any(arg, &addr6, &mask->in6, &naddrs);
+ if (naddrs > 1)
+ xtables_error(PARAMETER_PROBLEM,
+ "multiple IP addresses not allowed");
+ if (naddrs == 1)
+ memcpy(&address->in6, addr6, sizeof(*addr6));
+ } else {
+ /* Hu? */
+ assert(false);
+ }
+}
+
+/* Function which parses command options; returns true if it ate an option */
+static int ipvs_mt_parse(int c, char **argv, int invert, unsigned int *flags,
+ const void *entry, struct xt_entry_match **match,
+ unsigned int family)
+{
+ struct xt_ipvs_mtinfo *data = (void *)(*match)->data;
+ char *p = NULL;
+ u_int8_t op = 0;
+
+ if ('0' <= c && c <= '6') {
+ static const int ops[] = {
+ XT_IPVS_IPVS_PROPERTY,
+ XT_IPVS_PROTO,
+ XT_IPVS_VADDR,
+ XT_IPVS_VPORT,
+ XT_IPVS_DIR,
+ XT_IPVS_METHOD,
+ XT_IPVS_VPORTCTL
+ };
+ op = ops[c - '0'];
+ } else
+ return 0;
+
+ if (*flags & op & XT_IPVS_ONCE_MASK)
+ goto multiple_use;
+
+ switch (c) {
+ case '0': /* --ipvs */
+ /* Nothing to do here. */
+ break;
+
+ case '1': /* --vproto */
+ /* Canonicalize into lower case */
+ for (p = optarg; *p != '\0'; ++p)
+ *p = tolower(*p);
+
+ data->l4proto = xtables_parse_protocol(optarg);
+ break;
+
+ case '2': /* --vaddr */
+ ipvs_mt_parse_addr_and_mask(optarg, &data->vaddr,
+ &data->vmask, family);
+ break;
+
+ case '3': /* --vport */
+ data->vport = htons(xtables_parse_port(optarg, "tcp"));
+ break;
+
+ case '4': /* --vdir */
+ xtables_param_act(XTF_NO_INVERT, "ipvs", "--vdir", invert);
+ if (strcasecmp(optarg, "ORIGINAL") == 0) {
+ data->bitmask |= XT_IPVS_DIR;
+ data->invert &= ~XT_IPVS_DIR;
+ } else if (strcasecmp(optarg, "REPLY") == 0) {
+ data->bitmask |= XT_IPVS_DIR;
+ data->invert |= XT_IPVS_DIR;
+ } else {
+ xtables_param_act(XTF_BAD_VALUE,
+ "ipvs", "--vdir", optarg);
+ }
+ break;
+
+ case '5': /* --vmethod */
+ if (strcasecmp(optarg, "GATE") == 0)
+ data->fwd_method = IP_VS_CONN_F_DROUTE;
+ else if (strcasecmp(optarg, "IPIP") == 0)
+ data->fwd_method = IP_VS_CONN_F_TUNNEL;
+ else if (strcasecmp(optarg, "MASQ") == 0)
+ data->fwd_method = IP_VS_CONN_F_MASQ;
+ else
+ xtables_param_act(XTF_BAD_VALUE,
+ "ipvs", "--vmethod", optarg);
+ break;
+
+ case '6': /* --vportctl */
+ data->vportctl = htons(xtables_parse_port(optarg, "tcp"));
+ break;
+
+ default:
+ /* Hu? How did we come here? */
+ assert(false);
+ return 0;
+ }
+
+ if (op & XT_IPVS_ONCE_MASK) {
+ if (data->invert & XT_IPVS_IPVS_PROPERTY)
+ xtables_error(PARAMETER_PROBLEM,
+ "! --ipvs cannot be together with"
+ " other options");
+ data->bitmask |= XT_IPVS_IPVS_PROPERTY;
+ }
+
+ data->bitmask |= op;
+ if (invert)
+ data->invert |= op;
+ *flags |= op;
+ return 1;
+
+multiple_use:
+ xtables_error(PARAMETER_PROBLEM,
+ "multiple use of the same IPVS option is not allowed");
+}
+
+static int ipvs_mt4_parse(int c, char **argv, int invert, unsigned int *flags,
+ const void *entry, struct xt_entry_match **match)
+{
+ return ipvs_mt_parse(c, argv, invert, flags, entry, match,
+ NFPROTO_IPV4);
+}
+
+static int ipvs_mt6_parse(int c, char **argv, int invert, unsigned int *flags,
+ const void *entry, struct xt_entry_match **match)
+{
+ return ipvs_mt_parse(c, argv, invert, flags, entry, match,
+ NFPROTO_IPV6);
+}
+
+static void ipvs_mt_check(unsigned int flags)
+{
+ if (flags == 0)
+ xtables_error(PARAMETER_PROBLEM,
+ "IPVS: At least one option is required");
+}
+
+/* Shamelessly copied from libxt_conntrack.c */
+static void ipvs_mt_dump_addr(const union nf_inet_addr *addr,
+ const union nf_inet_addr *mask,
+ unsigned int family, bool numeric)
+{
+ char buf[BUFSIZ];
+
+ if (family == NFPROTO_IPV4) {
+ if (!numeric && addr->ip == 0) {
+ printf("anywhere ");
+ return;
+ }
+ if (numeric)
+ strcpy(buf, xtables_ipaddr_to_numeric(&addr->in));
+ else
+ strcpy(buf, xtables_ipaddr_to_anyname(&addr->in));
+ strcat(buf, xtables_ipmask_to_numeric(&mask->in));
+ printf("%s ", buf);
+ } else if (family == NFPROTO_IPV6) {
+ if (!numeric && addr->ip6[0] == 0 && addr->ip6[1] == 0 &&
+ addr->ip6[2] == 0 && addr->ip6[3] == 0) {
+ printf("anywhere ");
+ return;
+ }
+ if (numeric)
+ strcpy(buf, xtables_ip6addr_to_numeric(&addr->in6));
+ else
+ strcpy(buf, xtables_ip6addr_to_anyname(&addr->in6));
+ strcat(buf, xtables_ip6mask_to_numeric(&mask->in6));
+ printf("%s ", buf);
+ }
+}
+
+static void ipvs_mt_dump(const void *ip, const struct xt_ipvs_mtinfo *data,
+ unsigned int family, bool numeric, const char *prefix)
+{
+ if (data->bitmask == XT_IPVS_IPVS_PROPERTY) {
+ if (data->invert & XT_IPVS_IPVS_PROPERTY)
+ printf("! ");
+ printf("%sipvs ", prefix);
+ }
+
+ if (data->bitmask & XT_IPVS_PROTO) {
+ if (data->invert & XT_IPVS_PROTO)
+ printf("! ");
+ printf("%sproto %u ", prefix, data->l4proto);
+ }
+
+ if (data->bitmask & XT_IPVS_VADDR) {
+ if (data->invert & XT_IPVS_VADDR)
+ printf("! ");
+
+ printf("%svaddr ", prefix);
+ ipvs_mt_dump_addr(&data->vaddr, &data->vmask, family, numeric);
+ }
+
+ if (data->bitmask & XT_IPVS_VPORT) {
+ if (data->invert & XT_IPVS_VPORT)
+ printf("! ");
+
+ printf("%svport %u ", prefix, ntohs(data->vport));
+ }
+
+ if (data->bitmask & XT_IPVS_DIR) {
+ if (data->invert & XT_IPVS_DIR)
+ printf("%svdir REPLY ", prefix);
+ else
+ printf("%svdir ORIGINAL ", prefix);
+ }
+
+ if (data->bitmask & XT_IPVS_METHOD) {
+ if (data->invert & XT_IPVS_METHOD)
+ printf("! ");
+
+ printf("%svmethod ", prefix);
+ switch (data->fwd_method) {
+ case IP_VS_CONN_F_DROUTE:
+ printf("GATE ");
+ break;
+ case IP_VS_CONN_F_TUNNEL:
+ printf("IPIP ");
+ break;
+ case IP_VS_CONN_F_MASQ:
+ printf("MASQ ");
+ break;
+ default:
+ /* Hu? */
+ printf("UNKNOWN ");
+ break;
+ }
+ }
+
+ if (data->bitmask & XT_IPVS_VPORTCTL) {
+ if (data->invert & XT_IPVS_VPORTCTL)
+ printf("! ");
+
+ printf("%svportctl %u ", prefix, ntohs(data->vportctl));
+ }
+}
+
+static void ipvs_mt4_print(const void *ip, const struct xt_entry_match *match,
+ int numeric)
+{
+ const struct xt_ipvs_mtinfo *data = (const void *)match->data;
+ ipvs_mt_dump(ip, data, NFPROTO_IPV4, numeric, "");
+}
+
+static void ipvs_mt6_print(const void *ip, const struct xt_entry_match *match,
+ int numeric)
+{
+ const struct xt_ipvs_mtinfo *data = (const void *)match->data;
+ ipvs_mt_dump(ip, data, NFPROTO_IPV6, numeric, "");
+}
+
+static void ipvs_mt4_save(const void *ip, const struct xt_entry_match *match)
+{
+ const struct xt_ipvs_mtinfo *data = (const void *)match->data;
+ ipvs_mt_dump(ip, data, NFPROTO_IPV4, true, "--");
+}
+
+static void ipvs_mt6_save(const void *ip, const struct xt_entry_match *match)
+{
+ const struct xt_ipvs_mtinfo *data = (const void *)match->data;
+ ipvs_mt_dump(ip, data, NFPROTO_IPV6, true, "--");
+}
+
+static struct xtables_match ipvs_matches_reg[] = {
+ {
+ .version = XTABLES_VERSION,
+ .name = "ipvs",
+ .revision = 0,
+ .family = NFPROTO_IPV4,
+ .size = XT_ALIGN(sizeof(struct xt_ipvs_mtinfo)),
+ .userspacesize = XT_ALIGN(sizeof(struct xt_ipvs_mtinfo)),
+ .help = ipvs_mt_help,
+ .parse = ipvs_mt4_parse,
+ .final_check = ipvs_mt_check,
+ .print = ipvs_mt4_print,
+ .save = ipvs_mt4_save,
+ .extra_opts = ipvs_mt_opts,
+ },
+ {
+ .version = XTABLES_VERSION,
+ .name = "ipvs",
+ .revision = 0,
+ .family = NFPROTO_IPV6,
+ .size = XT_ALIGN(sizeof(struct xt_ipvs_mtinfo)),
+ .userspacesize = XT_ALIGN(sizeof(struct xt_ipvs_mtinfo)),
+ .help = ipvs_mt_help,
+ .parse = ipvs_mt6_parse,
+ .final_check = ipvs_mt_check,
+ .print = ipvs_mt6_print,
+ .save = ipvs_mt6_save,
+ .extra_opts = ipvs_mt_opts,
+ },
+};
+
+void _init(void)
+{
+ xtables_register_matches(ipvs_matches_reg,
+ ARRAY_SIZE(ipvs_matches_reg));
+}
Index: iptables/extensions/libxt_ipvs.man
===================================================================
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ iptables/extensions/libxt_ipvs.man 2010-07-04 20:23:30.000000000 +0900
@@ -0,0 +1,24 @@
+Match IPVS connection properties.
+.TP
+[\fB!\fR] \fB\-\-ipvs\fP
+packet belongs to an IPVS connection
+.TP
+Any of the following options implies \-\-ipvs (even negated)
+.TP
+[\fB!\fR] \fB\-\-vproto\fP \fIprotocol\fP
+VIP protocol to match; by number or name, e.g. "tcp"
+.TP
+[\fB!\fR] \fB\-\-vaddr\fP \fIaddress\fP[\fB/\fP\fImask\fP]
+VIP address to match
+.TP
+[\fB!\fR] \fB\-\-vport\fP \fIport\fP
+VIP port to match; by number or name, e.g. "http"
+.TP
+\fB\-\-vdir\fP {\fBORIGINAL\fP|\fBREPLY\fP}
+flow direction of packet
+.TP
+[\fB!\fR] \fB\-\-vmethod\fP {\fBGATE\fP|\fBIPIP\fP|\fBMASQ\fP}
+IPVS forwarding method used
+.TP
+[\fB!\fR] \fB\-\-vportctl\fP \fIport\fP
+VIP port of the controlling connection to match, e.g. 21 for FTP
Index: iptables/include/linux/netfilter/xt_ipvs.h
===================================================================
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ iptables/include/linux/netfilter/xt_ipvs.h 2010-07-04 20:23:30.000000000 +0900
@@ -0,0 +1,25 @@
+#ifndef _XT_IPVS_H
+#define _XT_IPVS_H 1
+
+#define XT_IPVS_IPVS_PROPERTY (1 << 0) /* all other options imply this one */
+#define XT_IPVS_PROTO (1 << 1)
+#define XT_IPVS_VADDR (1 << 2)
+#define XT_IPVS_VPORT (1 << 3)
+#define XT_IPVS_DIR (1 << 4)
+#define XT_IPVS_METHOD (1 << 5)
+#define XT_IPVS_VPORTCTL (1 << 6)
+#define XT_IPVS_MASK ((1 << 7) - 1)
+#define XT_IPVS_ONCE_MASK (XT_IPVS_MASK & ~XT_IPVS_IPVS_PROPERTY)
+
+struct xt_ipvs_mtinfo {
+ union nf_inet_addr vaddr, vmask;
+ __be16 vport;
+ __u16 l4proto;
+ __u16 fwd_method;
+ __be16 vportctl;
+
+ __u8 invert;
+ __u8 bitmask;
+};
+
+#endif /* _XT_IPVS_H */
^ permalink raw reply
* [patch v2.4 3/4] IPVS: make FTP work with full NAT support
From: Simon Horman, Simon Horman @ 2010-07-10 2:03 UTC (permalink / raw)
To: lvs-devel, netdev, linux-kernel, netfilter, netfilter-devel
Cc: Malcolm Turnbull, Wensong Zhang, Julius Volz, Patrick McHardy,
David S. Miller, Hannes Eder
In-Reply-To: <20100710020351.168273435@vergenet.net>
[-- Attachment #1: IPVS-make-FTP-work-with-full-NAT-support.patch --]
[-- Type: text/plain, Size: 12301 bytes --]
From: Hannes Eder <heder@google.com>
Use nf_conntrack/nf_nat code to do the packet mangling and the TCP
sequence adjusting. The function 'ip_vs_skb_replace' is now dead
code, so it is removed.
To SNAT FTP, use something like:
% iptables -t nat -A POSTROUTING -m ipvs --vaddr 192.168.100.30/32 \
> --vport 21 -j SNAT --to-source 192.168.10.10
and for the data connections in passive mode:
% iptables -t nat -A POSTROUTING -m ipvs --vaddr 192.168.100.30/32 \
> --vportctl 21 -j SNAT --to-source 192.168.10.10
using '-m state --state RELATED' would also works.
Make sure the kernel modules ip_vs_ftp, nf_conntrack_ftp, and
nf_nat_ftp are loaded.
[ up-port and minor fixes by Simon Horman <horms@verge.net.au> ]
Signed-off-by: Hannes Eder <heder@google.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
include/net/ip_vs.h | 2
net/netfilter/ipvs/Kconfig | 2
net/netfilter/ipvs/ip_vs_app.c | 43 ----------
net/netfilter/ipvs/ip_vs_core.c | 1
net/netfilter/ipvs/ip_vs_ftp.c | 164 ++++++++++++++++++++++++++++++++++++---
5 files changed, 153 insertions(+), 59 deletions(-)
v2.4
As suggested by Patrick McHardy
* Use nf_conntrack_untracked() instead of &nf_conntrack_untracked
* Fix ip_vs_ftp_out logic
- Don't call nf_nat_mangle_tcp_packet() unless ct is valid and tracked
- Only call ip_vs_expect_relatedi() if nf_nat_mangle_tcp_packet()
succeeds
- Note that packets are dropped if mangling fails
v2.3
* Up-port
* Drop buf_len = snprintf() change - its a separate, cosmetic, fix
As suggested by Patrick McHardy
* Use %pI4 instead of NIPQUAD
v2.2
* No change
v2.1
* Up-port
Index: nf-next-2.6/include/net/ip_vs.h
===================================================================
--- nf-next-2.6.orig/include/net/ip_vs.h 2010-07-10 10:54:11.000000000 +0900
+++ nf-next-2.6/include/net/ip_vs.h 2010-07-10 10:54:12.000000000 +0900
@@ -736,8 +736,6 @@ extern void ip_vs_app_inc_put(struct ip_
extern int ip_vs_app_pkt_out(struct ip_vs_conn *, struct sk_buff *skb);
extern int ip_vs_app_pkt_in(struct ip_vs_conn *, struct sk_buff *skb);
-extern int ip_vs_skb_replace(struct sk_buff *skb, gfp_t pri,
- char *o_buf, int o_len, char *n_buf, int n_len);
extern int ip_vs_app_init(void);
extern void ip_vs_app_cleanup(void);
Index: nf-next-2.6/net/netfilter/ipvs/Kconfig
===================================================================
--- nf-next-2.6.orig/net/netfilter/ipvs/Kconfig 2010-07-10 10:54:11.000000000 +0900
+++ nf-next-2.6/net/netfilter/ipvs/Kconfig 2010-07-10 10:54:13.000000000 +0900
@@ -235,7 +235,7 @@ comment 'IPVS application helper'
config IP_VS_FTP
tristate "FTP protocol helper"
- depends on IP_VS_PROTO_TCP
+ depends on IP_VS_PROTO_TCP && NF_NAT
---help---
FTP is a protocol that transfers IP address and/or port number in
the payload. In the virtual server via Network Address Translation,
Index: nf-next-2.6/net/netfilter/ipvs/ip_vs_app.c
===================================================================
--- nf-next-2.6.orig/net/netfilter/ipvs/ip_vs_app.c 2010-07-10 10:54:11.000000000 +0900
+++ nf-next-2.6/net/netfilter/ipvs/ip_vs_app.c 2010-07-10 10:54:13.000000000 +0900
@@ -569,49 +569,6 @@ static const struct file_operations ip_v
};
#endif
-
-/*
- * Replace a segment of data with a new segment
- */
-int ip_vs_skb_replace(struct sk_buff *skb, gfp_t pri,
- char *o_buf, int o_len, char *n_buf, int n_len)
-{
- int diff;
- int o_offset;
- int o_left;
-
- EnterFunction(9);
-
- diff = n_len - o_len;
- o_offset = o_buf - (char *)skb->data;
- /* The length of left data after o_buf+o_len in the skb data */
- o_left = skb->len - (o_offset + o_len);
-
- if (diff <= 0) {
- memmove(o_buf + n_len, o_buf + o_len, o_left);
- memcpy(o_buf, n_buf, n_len);
- skb_trim(skb, skb->len + diff);
- } else if (diff <= skb_tailroom(skb)) {
- skb_put(skb, diff);
- memmove(o_buf + n_len, o_buf + o_len, o_left);
- memcpy(o_buf, n_buf, n_len);
- } else {
- if (pskb_expand_head(skb, skb_headroom(skb), diff, pri))
- return -ENOMEM;
- skb_put(skb, diff);
- memmove(skb->data + o_offset + n_len,
- skb->data + o_offset + o_len, o_left);
- skb_copy_to_linear_data_offset(skb, o_offset, n_buf, n_len);
- }
-
- /* must update the iph total length here */
- ip_hdr(skb)->tot_len = htons(skb->len);
-
- LeaveFunction(9);
- return 0;
-}
-
-
int __init ip_vs_app_init(void)
{
/* we will replace it with proc_net_ipvs_create() soon */
Index: nf-next-2.6/net/netfilter/ipvs/ip_vs_core.c
===================================================================
--- nf-next-2.6.orig/net/netfilter/ipvs/ip_vs_core.c 2010-07-10 10:54:11.000000000 +0900
+++ nf-next-2.6/net/netfilter/ipvs/ip_vs_core.c 2010-07-10 10:54:13.000000000 +0900
@@ -54,7 +54,6 @@
EXPORT_SYMBOL(register_ip_vs_scheduler);
EXPORT_SYMBOL(unregister_ip_vs_scheduler);
-EXPORT_SYMBOL(ip_vs_skb_replace);
EXPORT_SYMBOL(ip_vs_proto_name);
EXPORT_SYMBOL(ip_vs_conn_new);
EXPORT_SYMBOL(ip_vs_conn_in_get);
Index: nf-next-2.6/net/netfilter/ipvs/ip_vs_ftp.c
===================================================================
--- nf-next-2.6.orig/net/netfilter/ipvs/ip_vs_ftp.c 2010-07-10 10:54:11.000000000 +0900
+++ nf-next-2.6/net/netfilter/ipvs/ip_vs_ftp.c 2010-07-10 11:01:14.000000000 +0900
@@ -20,6 +20,17 @@
*
* Author: Wouter Gadeyne
*
+ *
+ * Code for ip_vs_expect_related and ip_vs_expect_callback is taken from
+ * http://www.ssi.bg/~ja/nfct/:
+ *
+ * ip_vs_nfct.c: Netfilter connection tracking support for IPVS
+ *
+ * Portions Copyright (C) 2001-2002
+ * Antefacto Ltd, 181 Parnell St, Dublin 1, Ireland.
+ *
+ * Portions Copyright (C) 2003-2008
+ * Julian Anastasov
*/
#define KMSG_COMPONENT "IPVS"
@@ -32,6 +43,9 @@
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/netfilter.h>
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_expect.h>
+#include <net/netfilter/nf_nat_helper.h>
#include <linux/gfp.h>
#include <net/protocol.h>
#include <net/tcp.h>
@@ -43,6 +57,16 @@
#define SERVER_STRING "227 Entering Passive Mode ("
#define CLIENT_STRING "PORT "
+#define FMT_TUPLE "%pI4:%u->%pI4:%u/%u"
+#define ARG_TUPLE(T) (T)->src.u3.ip, ntohs((T)->src.u.all), \
+ (T)->dst.u3.ip, ntohs((T)->dst.u.all), \
+ (T)->dst.protonum
+
+#define FMT_CONN "%pI4:%u->%pI4:%u->%pI4:%u/%u:%u"
+#define ARG_CONN(C) (C)->caddr, ntohs((C)->cport), \
+ (C)->vaddr, ntohs((C)->vport), \
+ (C)->daddr, ntohs((C)->dport), \
+ (C)->protocol, (C)->state
/*
* List of ports (up to IP_VS_APP_MAX_PORTS) to be handled by helper
@@ -123,6 +147,119 @@ static int ip_vs_ftp_get_addrport(char *
return 1;
}
+/*
+ * Called from init_conntrack() as expectfn handler.
+ */
+static void
+ip_vs_expect_callback(struct nf_conn *ct,
+ struct nf_conntrack_expect *exp)
+{
+ struct nf_conntrack_tuple *orig, new_reply;
+ struct ip_vs_conn *cp;
+
+ if (exp->tuple.src.l3num != PF_INET)
+ return;
+
+ /*
+ * We assume that no NF locks are held before this callback.
+ * ip_vs_conn_out_get and ip_vs_conn_in_get should match their
+ * expectations even if they use wildcard values, now we provide the
+ * actual values from the newly created original conntrack direction.
+ * The conntrack is confirmed when packet reaches IPVS hooks.
+ */
+
+ /* RS->CLIENT */
+ orig = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple;
+ cp = ip_vs_conn_out_get(exp->tuple.src.l3num, orig->dst.protonum,
+ &orig->src.u3, orig->src.u.tcp.port,
+ &orig->dst.u3, orig->dst.u.tcp.port);
+ if (cp) {
+ /* Change reply CLIENT->RS to CLIENT->VS */
+ new_reply = ct->tuplehash[IP_CT_DIR_REPLY].tuple;
+ IP_VS_DBG(7, "%s(): ct=%p, status=0x%lX, tuples=" FMT_TUPLE ", "
+ FMT_TUPLE ", found inout cp=" FMT_CONN "\n",
+ __func__, ct, ct->status,
+ ARG_TUPLE(orig), ARG_TUPLE(&new_reply),
+ ARG_CONN(cp));
+ new_reply.dst.u3 = cp->vaddr;
+ new_reply.dst.u.tcp.port = cp->vport;
+ IP_VS_DBG(7, "%s(): ct=%p, new tuples=" FMT_TUPLE ", " FMT_TUPLE
+ ", inout cp=" FMT_CONN "\n",
+ __func__, ct,
+ ARG_TUPLE(orig), ARG_TUPLE(&new_reply),
+ ARG_CONN(cp));
+ goto alter;
+ }
+
+ /* CLIENT->VS */
+ cp = ip_vs_conn_in_get(exp->tuple.src.l3num, orig->dst.protonum,
+ &orig->src.u3, orig->src.u.tcp.port,
+ &orig->dst.u3, orig->dst.u.tcp.port);
+ if (cp) {
+ /* Change reply VS->CLIENT to RS->CLIENT */
+ new_reply = ct->tuplehash[IP_CT_DIR_REPLY].tuple;
+ IP_VS_DBG(7, "%s(): ct=%p, status=0x%lX, tuples=" FMT_TUPLE ", "
+ FMT_TUPLE ", found outin cp=" FMT_CONN "\n",
+ __func__, ct, ct->status,
+ ARG_TUPLE(orig), ARG_TUPLE(&new_reply),
+ ARG_CONN(cp));
+ new_reply.src.u3 = cp->daddr;
+ new_reply.src.u.tcp.port = cp->dport;
+ IP_VS_DBG(7, "%s(): ct=%p, new tuples=" FMT_TUPLE ", "
+ FMT_TUPLE ", outin cp=" FMT_CONN "\n",
+ __func__, ct,
+ ARG_TUPLE(orig), ARG_TUPLE(&new_reply),
+ ARG_CONN(cp));
+ goto alter;
+ }
+
+ IP_VS_DBG(7, "%s(): ct=%p, status=0x%lX, tuple=" FMT_TUPLE
+ " - unknown expect\n",
+ __func__, ct, ct->status, ARG_TUPLE(orig));
+ return;
+
+alter:
+ /* Never alter conntrack for non-NAT conns */
+ if (IP_VS_FWD_METHOD(cp) == IP_VS_CONN_F_MASQ)
+ nf_conntrack_alter_reply(ct, &new_reply);
+ ip_vs_conn_put(cp);
+ return;
+}
+
+/*
+ * Create NF conntrack expectation with wildcard (optional) source port.
+ * Then the default callback function will alter the reply and will confirm
+ * the conntrack entry when the first packet comes.
+ */
+static void
+ip_vs_expect_related(struct sk_buff *skb, struct nf_conn *ct,
+ struct ip_vs_conn *cp, u_int8_t proto,
+ const __be16 *port, int from_rs)
+{
+ struct nf_conntrack_expect *exp;
+
+ BUG_ON(!ct || ct == &nf_conntrack_untracked);
+
+ exp = nf_ct_expect_alloc(ct);
+ if (!exp)
+ return;
+
+ if (from_rs)
+ nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT,
+ nf_ct_l3num(ct), &cp->daddr, &cp->caddr,
+ proto, port, &cp->cport);
+ else
+ nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT,
+ nf_ct_l3num(ct), &cp->caddr, &cp->vaddr,
+ proto, port, &cp->vport);
+
+ exp->expectfn = ip_vs_expect_callback;
+
+ IP_VS_DBG(7, "%s(): ct=%p, expect tuple=" FMT_TUPLE "\n",
+ __func__, ct, ARG_TUPLE(&exp->tuple));
+ nf_ct_expect_related(exp);
+ nf_ct_expect_put(exp);
+}
/*
* Look at outgoing ftp packets to catch the response to a PASV command
@@ -150,6 +287,8 @@ static int ip_vs_ftp_out(struct ip_vs_ap
char buf[24]; /* xxx.xxx.xxx.xxx,ppp,ppp\000 */
unsigned buf_len;
int ret;
+ enum ip_conntrack_info ctinfo;
+ struct nf_conn *ct;
#ifdef CONFIG_IP_VS_IPV6
/* This application helper doesn't work with IPv6 yet,
@@ -219,19 +358,26 @@ static int ip_vs_ftp_out(struct ip_vs_ap
buf_len = strlen(buf);
+ ct = nf_ct_get(skb, &ctinfo);
+ if (ct && !nf_ct_is_untracked()) {
+ /* If mangling fails this function will return 0
+ * which will cause the packet to be dropped.
+ * Mangling can only fail under memory pressure,
+ * hopefully it will succeed on the retransmitted
+ * packet.
+ */
+ ret = nf_nat_mangle_tcp_packet(skb, ct, ctinfo,
+ start-data, end-start,
+ buf, buf_len);
+ if (ret)
+ ip_vs_expect_related(skb, ct, n_cp,
+ IPPROTO_TCP, NULL, 0);
+ }
+
/*
- * Calculate required delta-offset to keep TCP happy
+ * Not setting 'diff' is intentional, otherwise the sequence
+ * would be adjusted twice.
*/
- *diff = buf_len - (end-start);
-
- if (*diff == 0) {
- /* simply replace it with new passive address */
- memcpy(start, buf, buf_len);
- ret = 1;
- } else {
- ret = !ip_vs_skb_replace(skb, GFP_ATOMIC, start,
- end-start, buf, buf_len);
- }
cp->app_data = NULL;
ip_vs_tcp_conn_listen(n_cp);
@@ -263,6 +409,7 @@ static int ip_vs_ftp_in(struct ip_vs_app
union nf_inet_addr to;
__be16 port;
struct ip_vs_conn *n_cp;
+ struct nf_conn *ct;
#ifdef CONFIG_IP_VS_IPV6
/* This application helper doesn't work with IPv6 yet,
@@ -349,6 +496,11 @@ static int ip_vs_ftp_in(struct ip_vs_app
ip_vs_control_add(n_cp, cp);
}
+ ct = (struct nf_conn *)skb->nfct;
+ if (ct && ct != &nf_conntrack_untracked)
+ ip_vs_expect_related(skb, ct, n_cp,
+ IPPROTO_TCP, &n_cp->dport, 1);
+
/*
* Move tunnel to listen state
*/
^ permalink raw reply
* [patch v2.4 2/4] IPVS: make friends with nf_conntrack
From: Simon Horman, Simon Horman @ 2010-07-10 2:03 UTC (permalink / raw)
To: lvs-devel, netdev, linux-kernel, netfilter, netfilter-devel
Cc: Malcolm Turnbull, Wensong Zhang, Julius Volz, Patrick McHardy,
David S. Miller, Hannes Eder
In-Reply-To: <20100710020351.168273435@vergenet.net>
[-- Attachment #1: IPVS-make-friends-with-nf_conntrack.patch --]
[-- Type: text/plain, Size: 5651 bytes --]
From: Hannes Eder <heder@google.com>
Update the nf_conntrack tuple in reply direction, as we will see
traffic from the real server (RIP) to the client (CIP). Once this is
done we can use netfilters SNAT in POSTROUTING, especially with
xt_ipvs, to do source NAT, e.g.:
% iptables -t nat -A POSTROUTING -m ipvs --vaddr 192.168.100.30/32 --vport 80 \
> -j SNAT --to-source 192.168.10.10
[ minor fixes by Simon Horman <horms@verge.net.au> ]
Signed-off-by: Hannes Eder <heder@google.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
net/netfilter/ipvs/Kconfig | 2 +-
net/netfilter/ipvs/ip_vs_core.c | 36 ------------------------------------
net/netfilter/ipvs/ip_vs_xmit.c | 30 ++++++++++++++++++++++++++++++
3 files changed, 31 insertions(+), 37 deletions(-)
v2.4
As per advice from Patrick McHardy
* Use nf_conntrack_untracked() instead of &nf_conntrack_untracked
v2.1, v2.2, v2.3
No change
Index: nf-next-2.6/net/netfilter/ipvs/Kconfig
===================================================================
--- nf-next-2.6.orig/net/netfilter/ipvs/Kconfig 2010-07-07 13:24:31.000000000 +0900
+++ nf-next-2.6/net/netfilter/ipvs/Kconfig 2010-07-07 13:38:23.000000000 +0900
@@ -3,7 +3,7 @@
#
menuconfig IP_VS
tristate "IP virtual server support"
- depends on NET && INET && NETFILTER
+ depends on NET && INET && NETFILTER && NF_CONNTRACK
---help---
IP Virtual Server support will let you build a high-performance
virtual server based on cluster of two or more real servers. This
Index: nf-next-2.6/net/netfilter/ipvs/ip_vs_core.c
===================================================================
--- nf-next-2.6.orig/net/netfilter/ipvs/ip_vs_core.c 2010-07-07 13:23:37.000000000 +0900
+++ nf-next-2.6/net/netfilter/ipvs/ip_vs_core.c 2010-07-07 13:38:23.000000000 +0900
@@ -536,26 +536,6 @@ int ip_vs_leave(struct ip_vs_service *sv
return NF_DROP;
}
-
-/*
- * It is hooked before NF_IP_PRI_NAT_SRC at the NF_INET_POST_ROUTING
- * chain, and is used for VS/NAT.
- * It detects packets for VS/NAT connections and sends the packets
- * immediately. This can avoid that iptable_nat mangles the packets
- * for VS/NAT.
- */
-static unsigned int ip_vs_post_routing(unsigned int hooknum,
- struct sk_buff *skb,
- const struct net_device *in,
- const struct net_device *out,
- int (*okfn)(struct sk_buff *))
-{
- if (!skb->ipvs_property)
- return NF_ACCEPT;
- /* The packet was sent from IPVS, exit this chain */
- return NF_STOP;
-}
-
__sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset)
{
return csum_fold(skb_checksum(skb, offset, skb->len - offset, 0));
@@ -1499,14 +1479,6 @@ static struct nf_hook_ops ip_vs_ops[] __
.hooknum = NF_INET_FORWARD,
.priority = 99,
},
- /* Before the netfilter connection tracking, exit from POST_ROUTING */
- {
- .hook = ip_vs_post_routing,
- .owner = THIS_MODULE,
- .pf = PF_INET,
- .hooknum = NF_INET_POST_ROUTING,
- .priority = NF_IP_PRI_NAT_SRC-1,
- },
#ifdef CONFIG_IP_VS_IPV6
/* After packet filtering, forward packet through VS/DR, VS/TUN,
* or VS/NAT(change destination), so that filtering rules can be
@@ -1535,14 +1507,6 @@ static struct nf_hook_ops ip_vs_ops[] __
.hooknum = NF_INET_FORWARD,
.priority = 99,
},
- /* Before the netfilter connection tracking, exit from POST_ROUTING */
- {
- .hook = ip_vs_post_routing,
- .owner = THIS_MODULE,
- .pf = PF_INET6,
- .hooknum = NF_INET_POST_ROUTING,
- .priority = NF_IP6_PRI_NAT_SRC-1,
- },
#endif
};
Index: nf-next-2.6/net/netfilter/ipvs/ip_vs_xmit.c
===================================================================
--- nf-next-2.6.orig/net/netfilter/ipvs/ip_vs_xmit.c 2010-07-07 13:23:37.000000000 +0900
+++ nf-next-2.6/net/netfilter/ipvs/ip_vs_xmit.c 2010-07-07 13:42:22.000000000 +0900
@@ -28,6 +28,7 @@
#include <net/ip6_route.h>
#include <linux/icmpv6.h>
#include <linux/netfilter.h>
+#include <net/netfilter/nf_conntrack.h>
#include <linux/netfilter_ipv4.h>
#include <net/ip_vs.h>
@@ -348,6 +349,30 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb
}
#endif
+static void
+ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp)
+{
+ struct nf_conn *ct = (struct nf_conn *)skb->nfct;
+ struct nf_conntrack_tuple new_tuple;
+
+ if (ct == NULL || nf_ct_is_untracked(ct) || nf_ct_is_confirmed(ct))
+ return;
+
+ /*
+ * The connection is not yet in the hashtable, so we update it.
+ * CIP->VIP will remain the same, so leave the tuple in
+ * IP_CT_DIR_ORIGINAL untouched. When the reply comes back from the
+ * real-server we will see RIP->DIP.
+ */
+ new_tuple = ct->tuplehash[IP_CT_DIR_REPLY].tuple;
+ new_tuple.src.u3 = cp->daddr;
+ /*
+ * This will also take care of UDP and other protocols.
+ */
+ new_tuple.src.u.tcp.port = cp->dport;
+ nf_conntrack_alter_reply(ct, &new_tuple);
+}
+
/*
* NAT transmitter (only for outside-to-inside nat forwarding)
* Not used for related ICMP
@@ -403,6 +428,8 @@ ip_vs_nat_xmit(struct sk_buff *skb, stru
IP_VS_DBG_PKT(10, pp, skb, 0, "After DNAT");
+ ip_vs_update_conntrack(skb, cp);
+
/* FIXME: when application helper enlarges the packet and the length
is larger than the MTU of outgoing device, there will be still
MTU problem. */
@@ -479,6 +506,8 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, s
IP_VS_DBG_PKT(10, pp, skb, 0, "After DNAT");
+ ip_vs_update_conntrack(skb, cp);
+
/* FIXME: when application helper enlarges the packet and the length
is larger than the MTU of outgoing device, there will be still
MTU problem. */
^ permalink raw reply
* [patch v2.4 1/4] netfilter: xt_ipvs (netfilter matcher for IPVS)
From: Simon Horman, Simon Horman @ 2010-07-10 2:03 UTC (permalink / raw)
To: lvs-devel, netdev, linux-kernel, netfilter, netfilter-devel
Cc: Malcolm Turnbull, Wensong Zhang, Julius Volz, Patrick McHardy,
David S. Miller, Hannes Eder
In-Reply-To: <20100710020351.168273435@vergenet.net>
[-- Attachment #1: netfilter-xt_ipvs-netfilter-matcher-for-IPVS.patch --]
[-- Type: text/plain, Size: 8768 bytes --]
From: Hannes Eder <heder@google.com>
This implements the kernel-space side of the netfilter matcher xt_ipvs.
[ minor fixes by Simon Horman <horms@verge.net.au> ]
Signed-off-by: Hannes Eder <heder@google.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
include/linux/netfilter/xt_ipvs.h | 25 ++++
net/netfilter/Kconfig | 10 +
net/netfilter/Makefile | 1
net/netfilter/ipvs/ip_vs_proto.c | 1
net/netfilter/xt_ipvs.c | 187 +++++++++++++++++++++++++++++++++++++
5 files changed, 224 insertions(+), 0 deletions(-)
create mode 100644 include/linux/netfilter/xt_ipvs.h
create mode 100644 net/netfilter/xt_ipvs.c
v2.4
As per advice from Patrick McHardy
* Reduce size of l4proto and fwd_method members of struct xt_ipvs_mtinf
from __u16 to __u8
* Use nf_conntrack_untracked() instead of &nf_conntrack_untracked
v2.3
As per advice from Patrick McHardy
* Don't define a value for _XT_IPVS_H in xt_ipvs.h
* Depend on NF_CONNTRACK
* Update to new API
- ipvs_mt_check() should return an int rather than a bool
- Change type of ipvs_mt()'s par parameter from
struct xt_action_param to struct xt_match_param
- Make ipvs_mt()'s par parameter non-const
v2.1, v2.2
No Change
Index: nf-next-2.6/include/linux/netfilter/xt_ipvs.h
===================================================================
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ nf-next-2.6/include/linux/netfilter/xt_ipvs.h 2010-07-07 13:33:32.000000000 +0900
@@ -0,0 +1,25 @@
+#ifndef _XT_IPVS_H
+#define _XT_IPVS_H
+
+#define XT_IPVS_IPVS_PROPERTY (1 << 0) /* all other options imply this one */
+#define XT_IPVS_PROTO (1 << 1)
+#define XT_IPVS_VADDR (1 << 2)
+#define XT_IPVS_VPORT (1 << 3)
+#define XT_IPVS_DIR (1 << 4)
+#define XT_IPVS_METHOD (1 << 5)
+#define XT_IPVS_VPORTCTL (1 << 6)
+#define XT_IPVS_MASK ((1 << 7) - 1)
+#define XT_IPVS_ONCE_MASK (XT_IPVS_MASK & ~XT_IPVS_IPVS_PROPERTY)
+
+struct xt_ipvs_mtinfo {
+ union nf_inet_addr vaddr, vmask;
+ __be16 vport;
+ __u8 l4proto;
+ __u8 fwd_method;
+ __be16 vportctl;
+
+ __u8 invert;
+ __u8 bitmask;
+};
+
+#endif /* _XT_IPVS_H */
Index: nf-next-2.6/net/netfilter/Kconfig
===================================================================
--- nf-next-2.6.orig/net/netfilter/Kconfig 2010-07-07 13:23:37.000000000 +0900
+++ nf-next-2.6/net/netfilter/Kconfig 2010-07-07 13:26:35.000000000 +0900
@@ -726,6 +726,16 @@ config NETFILTER_XT_MATCH_IPRANGE
If unsure, say M.
+config NETFILTER_XT_MATCH_IPVS
+ tristate '"ipvs" match support'
+ depends on IP_VS
+ depends on NETFILTER_ADVANCED
+ depends on NF_CONNTRACK
+ help
+ This option allows you to match against IPVS properties of a packet.
+
+ If unsure, say N.
+
config NETFILTER_XT_MATCH_LENGTH
tristate '"length" match support'
depends on NETFILTER_ADVANCED
Index: nf-next-2.6/net/netfilter/Makefile
===================================================================
--- nf-next-2.6.orig/net/netfilter/Makefile 2010-07-07 13:23:37.000000000 +0900
+++ nf-next-2.6/net/netfilter/Makefile 2010-07-07 13:26:35.000000000 +0900
@@ -76,6 +76,7 @@ obj-$(CONFIG_NETFILTER_XT_MATCH_HASHLIMI
obj-$(CONFIG_NETFILTER_XT_MATCH_HELPER) += xt_helper.o
obj-$(CONFIG_NETFILTER_XT_MATCH_HL) += xt_hl.o
obj-$(CONFIG_NETFILTER_XT_MATCH_IPRANGE) += xt_iprange.o
+obj-$(CONFIG_NETFILTER_XT_MATCH_IPVS) += xt_ipvs.o
obj-$(CONFIG_NETFILTER_XT_MATCH_LENGTH) += xt_length.o
obj-$(CONFIG_NETFILTER_XT_MATCH_LIMIT) += xt_limit.o
obj-$(CONFIG_NETFILTER_XT_MATCH_MAC) += xt_mac.o
Index: nf-next-2.6/net/netfilter/ipvs/ip_vs_proto.c
===================================================================
--- nf-next-2.6.orig/net/netfilter/ipvs/ip_vs_proto.c 2010-07-07 13:23:37.000000000 +0900
+++ nf-next-2.6/net/netfilter/ipvs/ip_vs_proto.c 2010-07-07 13:26:35.000000000 +0900
@@ -98,6 +98,7 @@ struct ip_vs_protocol * ip_vs_proto_get(
return NULL;
}
+EXPORT_SYMBOL(ip_vs_proto_get);
/*
Index: nf-next-2.6/net/netfilter/xt_ipvs.c
===================================================================
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ nf-next-2.6/net/netfilter/xt_ipvs.c 2010-07-07 13:36:47.000000000 +0900
@@ -0,0 +1,189 @@
+/*
+ * xt_ipvs - kernel module to match IPVS connection properties
+ *
+ * Author: Hannes Eder <heder@google.com>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/spinlock.h>
+#include <linux/skbuff.h>
+#ifdef CONFIG_IP_VS_IPV6
+#include <net/ipv6.h>
+#endif
+#include <linux/ip_vs.h>
+#include <linux/types.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter/xt_ipvs.h>
+#include <net/netfilter/nf_conntrack.h>
+
+#include <net/ip_vs.h>
+
+MODULE_AUTHOR("Hannes Eder <heder@google.com>");
+MODULE_DESCRIPTION("Xtables: match IPVS connection properties");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("ipt_ipvs");
+MODULE_ALIAS("ip6t_ipvs");
+
+/* borrowed from xt_conntrack */
+static bool ipvs_mt_addrcmp(const union nf_inet_addr *kaddr,
+ const union nf_inet_addr *uaddr,
+ const union nf_inet_addr *umask,
+ unsigned int l3proto)
+{
+ if (l3proto == NFPROTO_IPV4)
+ return ((kaddr->ip ^ uaddr->ip) & umask->ip) == 0;
+#ifdef CONFIG_IP_VS_IPV6
+ else if (l3proto == NFPROTO_IPV6)
+ return ipv6_masked_addr_cmp(&kaddr->in6, &umask->in6,
+ &uaddr->in6) == 0;
+#endif
+ else
+ return false;
+}
+
+static bool
+ipvs_mt(const struct sk_buff *skb, struct xt_action_param *par)
+{
+ const struct xt_ipvs_mtinfo *data = par->matchinfo;
+ /* ipvs_mt_check ensures that family is only NFPROTO_IPV[46]. */
+ const u_int8_t family = par->family;
+ struct ip_vs_iphdr iph;
+ struct ip_vs_protocol *pp;
+ struct ip_vs_conn *cp;
+ bool match = true;
+
+ if (data->bitmask == XT_IPVS_IPVS_PROPERTY) {
+ match = skb->ipvs_property ^
+ !!(data->invert & XT_IPVS_IPVS_PROPERTY);
+ goto out;
+ }
+
+ /* other flags than XT_IPVS_IPVS_PROPERTY are set */
+ if (!skb->ipvs_property) {
+ match = false;
+ goto out;
+ }
+
+ ip_vs_fill_iphdr(family, skb_network_header(skb), &iph);
+
+ if (data->bitmask & XT_IPVS_PROTO)
+ if ((iph.protocol == data->l4proto) ^
+ !(data->invert & XT_IPVS_PROTO)) {
+ match = false;
+ goto out;
+ }
+
+ pp = ip_vs_proto_get(iph.protocol);
+ if (unlikely(!pp)) {
+ match = false;
+ goto out;
+ }
+
+ /*
+ * Check if the packet belongs to an existing entry
+ */
+ cp = pp->conn_out_get(family, skb, pp, &iph, iph.len, 1 /* inverse */);
+ if (unlikely(cp == NULL)) {
+ match = false;
+ goto out;
+ }
+
+ /*
+ * We found a connection, i.e. ct != 0, make sure to call
+ * __ip_vs_conn_put before returning. In our case jump to out_put_con.
+ */
+
+ if (data->bitmask & XT_IPVS_VPORT)
+ if ((cp->vport == data->vport) ^
+ !(data->invert & XT_IPVS_VPORT)) {
+ match = false;
+ goto out_put_cp;
+ }
+
+ if (data->bitmask & XT_IPVS_VPORTCTL)
+ if ((cp->control != NULL &&
+ cp->control->vport == data->vportctl) ^
+ !(data->invert & XT_IPVS_VPORTCTL)) {
+ match = false;
+ goto out_put_cp;
+ }
+
+ if (data->bitmask & XT_IPVS_DIR) {
+ enum ip_conntrack_info ctinfo;
+ struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
+
+ if (ct == NULL || ct == nf_ct_is_untracked(ct)) {
+ match = false;
+ goto out_put_cp;
+ }
+
+ if ((ctinfo >= IP_CT_IS_REPLY) ^
+ !!(data->invert & XT_IPVS_DIR)) {
+ match = false;
+ goto out_put_cp;
+ }
+ }
+
+ if (data->bitmask & XT_IPVS_METHOD)
+ if (((cp->flags & IP_VS_CONN_F_FWD_MASK) == data->fwd_method) ^
+ !(data->invert & XT_IPVS_METHOD)) {
+ match = false;
+ goto out_put_cp;
+ }
+
+ if (data->bitmask & XT_IPVS_VADDR) {
+ if (ipvs_mt_addrcmp(&cp->vaddr, &data->vaddr,
+ &data->vmask, family) ^
+ !(data->invert & XT_IPVS_VADDR)) {
+ match = false;
+ goto out_put_cp;
+ }
+ }
+
+out_put_cp:
+ __ip_vs_conn_put(cp);
+out:
+ pr_debug("match=%d\n", match);
+ return match;
+}
+
+static int ipvs_mt_check(const struct xt_mtchk_param *par)
+{
+ if (par->family != NFPROTO_IPV4
+#ifdef CONFIG_IP_VS_IPV6
+ && par->family != NFPROTO_IPV6
+#endif
+ ) {
+ pr_info("protocol family %u not supported\n", par->family);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static struct xt_match xt_ipvs_mt_reg __read_mostly = {
+ .name = "ipvs",
+ .revision = 0,
+ .family = NFPROTO_UNSPEC,
+ .match = ipvs_mt,
+ .checkentry = ipvs_mt_check,
+ .matchsize = XT_ALIGN(sizeof(struct xt_ipvs_mtinfo)),
+ .me = THIS_MODULE,
+};
+
+static int __init ipvs_mt_init(void)
+{
+ return xt_register_match(&xt_ipvs_mt_reg);
+}
+
+static void __exit ipvs_mt_exit(void)
+{
+ xt_unregister_match(&xt_ipvs_mt_reg);
+}
+
+module_init(ipvs_mt_init);
+module_exit(ipvs_mt_exit);
^ permalink raw reply
* [patch v2.4 0/4] IPVS full NAT support + netfilter 'ipvs' match support
From: Simon Horman, Simon Horman @ 2010-07-10 2:03 UTC (permalink / raw)
To: lvs-devel, netdev, linux-kernel, netfilter, netfilter-devel
Cc: Malcolm Turnbull, Wensong Zhang, Julius Volz, Patrick McHardy,
David S. Miller, Hannes Eder
This is a repost of a patch-series posted by Hannes Eder last September.
This is v2 of the patch series and I don't see any outstanding objections to
it in the mailing list archives.
This addresses all of the concerns that Patrick McHardy raised
witht the v2.3 series.
Malcolm Turnbull has offered to test this code so I'd like to get
a Reviewed-by from him before the code gets merged. In other words,
at this stage these patches are for review not merging.
The original cover-email from Hannes follows.
The diffstat output has been updated to reflect minor up-porting by me.
From: Hannes Eder <heder@google.com>
The following series implements full NAT support for IPVS. The
approach is via a minimal change to IPVS (make friends with
nf_conntrack) and adding a netfilter matcher, kernel- and user-space
part, i.e. xt_ipvs and libxt_ipvs.
Example usage:
% ipvsadm -A -t 192.168.100.30:80 -s rr
% ipvsadm -a -t 192.168.100.30:80 -r 192.168.10.20:80 -m
# ...
# Source NAT for VIP 192.168.100.30:80
% iptables -t nat -A POSTROUTING -m ipvs --vaddr 192.168.100.30/32 \
> --vport 80 -j SNAT --to-source 192.168.10.10
or SNAT-ing only a specific real server:
% iptables -t nat -A POSTROUTING --dst 192.168.11.20 \
> -m ipvs --vaddr 192.168.100.30/32 -j SNAT --to-source 192.168.10.10
First of all, thanks for all the feedback. This is the changelog for v2:
- Make ip_vs_ftp work again. Setup nf_conntrack expectations for
related data connections (based on Julian's patch see
http://www.ssi.bg/~ja/nfct/) and let nf_conntrack/nf_nat do the
packet mangling and the TCP sequence adjusting.
This change rises the question how to deal with ip_vs_sync? Does it
work together with conntrackd? Wild idea: what about getting rid of
ip_vs_sync and piggy packing all on nf_conntrack and use conntrackd?
Any comments on this?
- xt_ipvs: add new rule '--vportctl port' to match the VIP port of the
controlling connection, e.g. port 21 for FTP. Can be used to match
a related data connection for FTP:
# SNAT FTP control connection
% iptables -t nat -A POSTROUTING -m ipvs --vaddr 192.168.100.30/32 \
> --vport 21 -j SNAT --to-source 192.168.10.10
# SNAT FTP passive data connection
% iptables -t nat -A POSTROUTING -m ipvs --vaddr 192.168.100.30/32 \
> --vportctl 21 -j SNAT --to-source 192.168.10.10
- xt_ipvs: use 'par->family' instead of 'skb->protocol'
- xt_ipvs: add ipvs_mt_check and restrict to NFPROTO_IPV4 and NFPROTO_IPV6
- Call nf_conntrack_alter_reply(), so helper lookup is performed based
on the changed tuple.
Changes to the linux kernel
(nf-next-2.6, "bridge: add per bridge device controls for invoking iptables")
Hannes Eder (3):
netfilter: xt_ipvs (netfilter matcher for IPVS)
IPVS: make friends with nf_conntrack
IPVS: make FTP work with full NAT support
include/linux/netfilter/xt_ipvs.h | 25 +++++
include/net/ip_vs.h | 2
net/netfilter/Kconfig | 10 ++
net/netfilter/Makefile | 1
net/netfilter/ipvs/Kconfig | 4
net/netfilter/ipvs/ip_vs_app.c | 43 ---------
net/netfilter/ipvs/ip_vs_core.c | 37 --------
net/netfilter/ipvs/ip_vs_ftp.c | 174 +++++++++++++++++++++++++++++++++++---
net/netfilter/ipvs/ip_vs_proto.c | 1
net/netfilter/ipvs/ip_vs_xmit.c | 29 ++++++
net/netfilter/xt_ipvs.c | 189 +++++++++++++++++++++++++++++++++++++
11 files changed, 420 insertions(+), 95 deletions(-)
create mode 100644 include/linux/netfilter/xt_ipvs.h
create mode 100644 net/netfilter/xt_ipvs.c
Changes to iptables
(iptables.git, "xt_quota: also document negation")
Hannes Eder (1):
libxt_ipvs: user-space lib for netfilter matcher xt_ipvs
configure.ac | 10 1
extensions/libxt_ipvs.c | 365 +++++++++++++++++++++++++++++++++++++
extensions/libxt_ipvs.man | 24 ++
include/linux/netfilter/xt_ipvs.h | 25 +++
4 files changed, 422 insertions(+), 2 deletions(-)
create mode 100644 extensions/libxt_ipvs.c
create mode 100644 extensions/libxt_ipvs.man
create mode 100644 include/linux/netfilter/xt_ipvs.h
^ permalink raw reply
* Re: [patch v2.3 3/4] IPVS: make FTP work with full NAT support
From: Simon Horman @ 2010-07-10 1:54 UTC (permalink / raw)
To: Patrick McHardy
Cc: lvs-devel, netdev, linux-kernel, netfilter, netfilter-devel,
Malcolm Turnbull, Wensong Zhang, Julius Volz, David S. Miller,
Hannes Eder
In-Reply-To: <4C373F48.8080504@trash.net>
On Fri, Jul 09, 2010 at 05:24:56PM +0200, Patrick McHardy wrote:
> Am 07.07.2010 08:53, schrieb Simon Horman:
> > On Tue, Jul 06, 2010 at 01:43:44PM +0200, Patrick McHardy wrote:
> >> Simon Horman wrote:
> >>> @@ -219,19 +358,23 @@ static int ip_vs_ftp_out(struct ip_vs_ap
> >>> buf_len = strlen(buf);
> >>> + ct = nf_ct_get(skb, &ctinfo);
> >>> + ret = nf_nat_mangle_tcp_packet(skb,
> >>> + ct,
> >>> + ctinfo,
> >>> + start-data,
> >>> + end-start,
> >>> + buf,
> >>> + buf_len);
> >>> +
> >>> + if (ct && ct != &nf_conntrack_untracked)
> >> This does not make sense, you're already using the conntrack above
> >> in the call to nf_nat_mangle_tcp_packet(), so the check should
> >> probably happen before that. You also should be checking the
> >> return value of nf_nat_mangle_tcp_packet() before setting up the
> >> expectation.
> >>
> >>> + ip_vs_expect_related(skb, ct, n_cp,
> >>> + IPPROTO_TCP, NULL, 0);
> >
> > Good point. Is this better?
> >
> > ct = nf_ct_get(skb, &ctinfo);
> > if (ct && !nf_ct_is_untracked()) {
> > ret = nf_nat_mangle_tcp_packet(skb, ct, ctinfo,
> > start-data, end-start,
> > buf, buf_len);
> > if (ret)
> > ip_vs_expect_related(skb, ct, n_cp,
> > IPPROTO_TCP, NULL, 0);
>
> Yes, that's better, although we're usually dropping packets
> when mangling fails. This can only happen under memory pressure,
> the assumption is that we might be able to properly mangle
> the packet when it is retransmitted.
I didn't notice this either, but ret will be end up being the return value
of ip_vs_ftp_out(), and if that is zero the packet will be dropped.
^ permalink raw reply
* [PATCH] act_nat: not all of the ICMP packets need an IP header payload
From: Changli Gao @ 2010-07-10 1:33 UTC (permalink / raw)
To: David S. Miller
Cc: Jamal Hadi Salim, Rodrigo Partearroyo González, Herbert Xu,
Eric Dumazet, Iratxo Pichel Ortiz, Noelia Morón, netdev,
Changli Gao
act_nat: not all of the ICMP packets need an IP header payload
not all of the ICMP packets need an IP header payload, so we check the length
of the skbs only when the packets should have an IP header payload.
Signed-off-by: Changli Gao <xiaosuo@gmail.com>
----
net/sched/act_nat.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index 0be49a4..24e614c 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -205,7 +205,7 @@ static int tcf_nat(struct sk_buff *skb, struct tc_action *a,
{
struct icmphdr *icmph;
- if (!pskb_may_pull(skb, ihl + sizeof(*icmph) + sizeof(*iph)))
+ if (!pskb_may_pull(skb, ihl + sizeof(*icmph)))
goto drop;
icmph = (void *)(skb_network_header(skb) + ihl);
@@ -215,6 +215,9 @@ static int tcf_nat(struct sk_buff *skb, struct tc_action *a,
(icmph->type != ICMP_PARAMETERPROB))
break;
+ if (!pskb_may_pull(skb, ihl + sizeof(*icmph) + sizeof(*iph)))
+ goto drop;
+
iph = (void *)(icmph + 1);
if (egress)
addr = iph->daddr;
^ permalink raw reply related
* Re: [PATCH net-next-2.6 2/2] qlcnic: Disable admin tools interface for VF driver mode
From: David Miller @ 2010-07-10 1:02 UTC (permalink / raw)
To: anirban.chakraborty; +Cc: netdev, Dept_NX_Linux_NIC_Driver
In-Reply-To: <alpine.OSX.2.00.1007091611371.44317@macintosh-2.qlogic.org>
From: Anirban Chakraborty <anirban.chakraborty@qlogic.com>
Date: Fri, 9 Jul 2010 16:15:05 -0700
>
> Non privileged (VF) driver will not be able to carry out any of the FW update,
> etc. operations. Disable the tools interface by not creating the sysfs nodes.
>
> Signed-off-by: Anirban Chakraborty <anirban.chakraborty@qlogic.com>
Applied.
^ permalink raw reply
* Re: [PATCH net-next-2.6 1/2] qlcnic: Check FW capability for TSO
From: David Miller @ 2010-07-10 1:02 UTC (permalink / raw)
To: anirban.chakraborty; +Cc: netdev, Dept_NX_Linux_NIC_Driver
In-Reply-To: <alpine.OSX.2.00.1007091544370.44317@macintosh-2.qlogic.org>
From: Anirban Chakraborty <anirban.chakraborty@qlogic.com>
Date: Fri, 9 Jul 2010 16:14:58 -0700
>
> Driver checks TSO capability from FW before enabling it.
>
> Signed-off-by: Anirban Chakraborty <anirban.chakraborty@qlogic.com>
Applied.
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox