From b71d1d426d263b0b6cb5760322efebbfc89d4463 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 22 Apr 2011 04:53:02 +0000 Subject: inet: constify ip headers and in6_addr Add const qualifiers to structs iphdr, ipv6hdr and in6_addr pointers where possible, to make code intention more obvious. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index f7e6c2c2d2bb..edf18bd74b87 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -279,7 +279,7 @@ EXPORT_SYMBOL(tcp_v4_connect); /* * This routine does path mtu discovery as defined in RFC1191. */ -static void do_pmtu_discovery(struct sock *sk, struct iphdr *iph, u32 mtu) +static void do_pmtu_discovery(struct sock *sk, const struct iphdr *iph, u32 mtu) { struct dst_entry *dst; struct inet_sock *inet = inet_sk(sk); @@ -341,7 +341,7 @@ static void do_pmtu_discovery(struct sock *sk, struct iphdr *iph, u32 mtu) void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) { - struct iphdr *iph = (struct iphdr *)icmp_skb->data; + const struct iphdr *iph = (const struct iphdr *)icmp_skb->data; struct tcphdr *th = (struct tcphdr *)(icmp_skb->data + (iph->ihl << 2)); struct inet_connection_sock *icsk; struct tcp_sock *tp; @@ -2527,7 +2527,7 @@ void tcp4_proc_exit(void) struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb) { - struct iphdr *iph = skb_gro_network_header(skb); + const struct iphdr *iph = skb_gro_network_header(skb); switch (skb->ip_summed) { case CHECKSUM_COMPLETE: @@ -2548,7 +2548,7 @@ struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb) int tcp4_gro_complete(struct sk_buff *skb) { - struct iphdr *iph = ip_hdr(skb); + const struct iphdr *iph = ip_hdr(skb); struct tcphdr *th = tcp_hdr(skb); th->check = ~tcp_v4_check(skb->len - skb_transport_offset(skb), -- cgit v1.2.3 From 2d7192d6cbab20e153c47fa1559ffd41ceef0e79 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 26 Apr 2011 13:28:44 -0700 Subject: ipv4: Sanitize and simplify ip_route_{connect,newports}() These functions are used together as a unit for route resolution during connect(). They address the chicken-and-egg problem that exists when ports need to be allocated during connect() processing, yet such port allocations require addressing information from the routing code. It's currently more heavy handed than it needs to be, and in particular we allocate and initialize a flow object twice. Let the callers provide the on-stack flow object. That way we only need to initialize it once in the ip_route_connect() call. Later, if ip_route_newports() needs to do anything, it re-uses that flow object as-is except for the ports which it updates before the route re-lookup. Also, describe why this set of facilities are needed and how it works in a big comment. Signed-off-by: David S. Miller Reviewed-by: Eric Dumazet --- net/ipv4/tcp_ipv4.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index edf18bd74b87..310454c2f4d1 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -146,12 +146,13 @@ EXPORT_SYMBOL_GPL(tcp_twsk_unique); /* This will initiate an outgoing connection. */ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { + struct sockaddr_in *usin = (struct sockaddr_in *)uaddr; struct inet_sock *inet = inet_sk(sk); struct tcp_sock *tp = tcp_sk(sk); - struct sockaddr_in *usin = (struct sockaddr_in *)uaddr; __be16 orig_sport, orig_dport; - struct rtable *rt; __be32 daddr, nexthop; + struct flowi4 fl4; + struct rtable *rt; int err; if (addr_len < sizeof(struct sockaddr_in)) @@ -169,7 +170,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) orig_sport = inet->inet_sport; orig_dport = usin->sin_port; - rt = ip_route_connect(nexthop, inet->inet_saddr, + rt = ip_route_connect(&fl4, nexthop, inet->inet_saddr, RT_CONN_FLAGS(sk), sk->sk_bound_dev_if, IPPROTO_TCP, orig_sport, orig_dport, sk, true); @@ -236,8 +237,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (err) goto failure; - rt = ip_route_newports(rt, IPPROTO_TCP, - orig_sport, orig_dport, + rt = ip_route_newports(&fl4, rt, orig_sport, orig_dport, inet->inet_sport, inet->inet_dport, sk); if (IS_ERR(rt)) { err = PTR_ERR(rt); -- cgit v1.2.3 From f6d8bd051c391c1c0458a30b2a7abcd939329259 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 21 Apr 2011 09:45:37 +0000 Subject: inet: add RCU protection to inet->opt We lack proper synchronization to manipulate inet->opt ip_options Problem is ip_make_skb() calls ip_setup_cork() and ip_setup_cork() possibly makes a copy of ipc->opt (struct ip_options), without any protection against another thread manipulating inet->opt. Another thread can change inet->opt pointer and free old one under us. Use RCU to protect inet->opt (changed to inet->inet_opt). Instead of handling atomic refcounts, just copy ip_options when necessary, to avoid cache line dirtying. We cant insert an rcu_head in struct ip_options since its included in skb->cb[], so this patch is large because I had to introduce a new ip_options_rcu structure. Signed-off-by: Eric Dumazet Cc: Herbert Xu Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 34 ++++++++++++++++++++-------------- 1 file changed, 20 insertions(+), 14 deletions(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 310454c2f4d1..d60732fe5f21 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -154,6 +154,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) struct flowi4 fl4; struct rtable *rt; int err; + struct ip_options_rcu *inet_opt; if (addr_len < sizeof(struct sockaddr_in)) return -EINVAL; @@ -162,10 +163,12 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) return -EAFNOSUPPORT; nexthop = daddr = usin->sin_addr.s_addr; - if (inet->opt && inet->opt->srr) { + inet_opt = rcu_dereference_protected(inet->inet_opt, + sock_owned_by_user(sk)); + if (inet_opt && inet_opt->opt.srr) { if (!daddr) return -EINVAL; - nexthop = inet->opt->faddr; + nexthop = inet_opt->opt.faddr; } orig_sport = inet->inet_sport; @@ -186,7 +189,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) return -ENETUNREACH; } - if (!inet->opt || !inet->opt->srr) + if (!inet_opt || !inet_opt->opt.srr) daddr = rt->rt_dst; if (!inet->inet_saddr) @@ -222,8 +225,8 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_daddr = daddr; inet_csk(sk)->icsk_ext_hdr_len = 0; - if (inet->opt) - inet_csk(sk)->icsk_ext_hdr_len = inet->opt->optlen; + if (inet_opt) + inet_csk(sk)->icsk_ext_hdr_len = inet_opt->opt.optlen; tp->rx_opt.mss_clamp = TCP_MSS_DEFAULT; @@ -820,17 +823,18 @@ static void syn_flood_warning(const struct sk_buff *skb) /* * Save and compile IPv4 options into the request_sock if needed. */ -static struct ip_options *tcp_v4_save_options(struct sock *sk, - struct sk_buff *skb) +static struct ip_options_rcu *tcp_v4_save_options(struct sock *sk, + struct sk_buff *skb) { - struct ip_options *opt = &(IPCB(skb)->opt); - struct ip_options *dopt = NULL; + const struct ip_options *opt = &(IPCB(skb)->opt); + struct ip_options_rcu *dopt = NULL; if (opt && opt->optlen) { - int opt_size = optlength(opt); + int opt_size = sizeof(*dopt) + opt->optlen; + dopt = kmalloc(opt_size, GFP_ATOMIC); if (dopt) { - if (ip_options_echo(dopt, skb)) { + if (ip_options_echo(&dopt->opt, skb)) { kfree(dopt); dopt = NULL; } @@ -1411,6 +1415,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *key; #endif + struct ip_options_rcu *inet_opt; if (sk_acceptq_is_full(sk)) goto exit_overflow; @@ -1431,13 +1436,14 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newinet->inet_daddr = ireq->rmt_addr; newinet->inet_rcv_saddr = ireq->loc_addr; newinet->inet_saddr = ireq->loc_addr; - newinet->opt = ireq->opt; + inet_opt = ireq->opt; + rcu_assign_pointer(newinet->inet_opt, inet_opt); ireq->opt = NULL; newinet->mc_index = inet_iif(skb); newinet->mc_ttl = ip_hdr(skb)->ttl; inet_csk(newsk)->icsk_ext_hdr_len = 0; - if (newinet->opt) - inet_csk(newsk)->icsk_ext_hdr_len = newinet->opt->optlen; + if (inet_opt) + inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen; newinet->inet_id = newtp->write_seq ^ jiffies; tcp_mtup_init(newsk); -- cgit v1.2.3 From 4071cfff84c5b084762fe288781cd7faab14cb4b Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Thu, 28 Apr 2011 23:17:31 -0700 Subject: ipv4: Fetch route saddr from flow key in tcp_v4_connect(). Now that output route lookups update the flow with source address selection, we can fetch it from fl4->saddr instead of rt->rt_src Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index d60732fe5f21..3be00afc8900 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -193,7 +193,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) daddr = rt->rt_dst; if (!inet->inet_saddr) - inet->inet_saddr = rt->rt_src; + inet->inet_saddr = fl4.saddr; inet->inet_rcv_saddr = inet->inet_saddr; if (tp->rx_opt.ts_recent_stamp && inet->inet_daddr != daddr) { -- cgit v1.2.3 From d4fb3d74d7a17833de2ba8cbd4f029b30feb4825 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Thu, 28 Apr 2011 23:50:32 -0700 Subject: ipv4: Get route daddr from flow key in tcp_v4_connect(). Now that output route lookups update the flow with destination address selection, we can fetch it from fl4->daddr instead of rt->rt_dst Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 3be00afc8900..f3d16d8918c7 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -190,7 +190,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) } if (!inet_opt || !inet_opt->opt.srr) - daddr = rt->rt_dst; + daddr = fl4.daddr; if (!inet->inet_saddr) inet->inet_saddr = fl4.saddr; @@ -204,7 +204,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) } if (tcp_death_row.sysctl_tw_recycle && - !tp->rx_opt.ts_recent_stamp && rt->rt_dst == daddr) { + !tp->rx_opt.ts_recent_stamp && fl4.daddr == daddr) { struct inet_peer *peer = rt_get_peer(rt); /* * VJ's idea. We save last timestamp seen from -- cgit v1.2.3 From da905bd1d5a6480d206f4b3dc61243f95adfae2c Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 6 May 2011 16:11:19 -0700 Subject: tcp: Use cork flow in tcp_v4_connect() Since this is invoked from inet_stream_connect() the socket is locked and therefore this usage is safe. Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index f3d16d8918c7..a71217156856 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -151,7 +151,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) struct tcp_sock *tp = tcp_sk(sk); __be16 orig_sport, orig_dport; __be32 daddr, nexthop; - struct flowi4 fl4; + struct flowi4 *fl4; struct rtable *rt; int err; struct ip_options_rcu *inet_opt; @@ -173,7 +173,8 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) orig_sport = inet->inet_sport; orig_dport = usin->sin_port; - rt = ip_route_connect(&fl4, nexthop, inet->inet_saddr, + fl4 = &inet->cork.fl.u.ip4; + rt = ip_route_connect(fl4, nexthop, inet->inet_saddr, RT_CONN_FLAGS(sk), sk->sk_bound_dev_if, IPPROTO_TCP, orig_sport, orig_dport, sk, true); @@ -190,10 +191,10 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) } if (!inet_opt || !inet_opt->opt.srr) - daddr = fl4.daddr; + daddr = fl4->daddr; if (!inet->inet_saddr) - inet->inet_saddr = fl4.saddr; + inet->inet_saddr = fl4->saddr; inet->inet_rcv_saddr = inet->inet_saddr; if (tp->rx_opt.ts_recent_stamp && inet->inet_daddr != daddr) { @@ -204,7 +205,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) } if (tcp_death_row.sysctl_tw_recycle && - !tp->rx_opt.ts_recent_stamp && fl4.daddr == daddr) { + !tp->rx_opt.ts_recent_stamp && fl4->daddr == daddr) { struct inet_peer *peer = rt_get_peer(rt); /* * VJ's idea. We save last timestamp seen from @@ -240,7 +241,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (err) goto failure; - rt = ip_route_newports(&fl4, rt, orig_sport, orig_dport, + rt = ip_route_newports(fl4, rt, orig_sport, orig_dport, inet->inet_sport, inet->inet_dport, sk); if (IS_ERR(rt)) { err = PTR_ERR(rt); -- cgit v1.2.3 From 0e734419923bd8e599858f8fc196c7804bb85564 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Sun, 8 May 2011 15:28:03 -0700 Subject: ipv4: Use inet_csk_route_child_sock() in DCCP and TCP. Operation order is now transposed, we first create the child socket then we try to hook up the route. Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a71217156856..374de3c98d5e 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1421,15 +1421,11 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, if (sk_acceptq_is_full(sk)) goto exit_overflow; - if (!dst && (dst = inet_csk_route_req(sk, req)) == NULL) - goto exit; - newsk = tcp_create_openreq_child(sk, req, skb); if (!newsk) goto exit_nonewsk; newsk->sk_gso_type = SKB_GSO_TCPV4; - sk_setup_caps(newsk, dst); newtp = tcp_sk(newsk); newinet = inet_sk(newsk); @@ -1447,6 +1443,11 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen; newinet->inet_id = newtp->write_seq ^ jiffies; + if (!dst && (dst = inet_csk_route_child_sock(sk, newsk, req)) == NULL) + goto put_and_exit; + + sk_setup_caps(newsk, dst); + tcp_mtup_init(newsk); tcp_sync_mss(newsk, dst_mtu(dst)); newtp->advmss = dst_metric_advmss(dst); @@ -1474,10 +1475,8 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, } #endif - if (__inet_inherit_port(sk, newsk) < 0) { - sock_put(newsk); - goto exit; - } + if (__inet_inherit_port(sk, newsk) < 0) + goto put_and_exit; __inet_hash_nolisten(newsk, NULL); return newsk; @@ -1489,6 +1488,9 @@ exit_nonewsk: exit: NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); return NULL; +put_and_exit: + sock_put(newsk); + goto exit; } EXPORT_SYMBOL(tcp_v4_syn_recv_sock); -- cgit v1.2.3 From c5216cc70fa769e5a51837f2cf07c4a0aa734fcf Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 6 May 2011 22:36:30 -0700 Subject: tcp: Use cork flow info instead of rt->rt_dst in tcp_v4_get_peer() Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 374de3c98d5e..2b655031b392 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1773,7 +1773,8 @@ struct inet_peer *tcp_v4_get_peer(struct sock *sk, bool *release_it) struct inet_sock *inet = inet_sk(sk); struct inet_peer *peer; - if (!rt || rt->rt_dst != inet->inet_daddr) { + if (!rt || + inet->cork.fl.u.ip4.daddr != inet->inet_daddr) { peer = inet_getpeer_v4(inet->inet_daddr, 1); *release_it = true; } else { -- cgit v1.2.3 From 0a5ebb8000c5362be368df9d197943deb06b6916 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 9 May 2011 13:22:43 -0700 Subject: ipv4: Pass explicit daddr arg to ip_send_reply(). This eliminates an access to rt->rt_src. Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 2b655031b392..f67fb34e16e5 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -651,7 +651,7 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) arg.flags = (sk && inet_sk(sk)->transparent) ? IP_REPLY_ARG_NOSRCCHECK : 0; net = dev_net(skb_dst(skb)->dev); - ip_send_reply(net->ipv4.tcp_sock, skb, + ip_send_reply(net->ipv4.tcp_sock, skb, ip_hdr(skb)->saddr, &arg, arg.iov[0].iov_len); TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); @@ -726,7 +726,7 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, if (oif) arg.bound_dev_if = oif; - ip_send_reply(net->ipv4.tcp_sock, skb, + ip_send_reply(net->ipv4.tcp_sock, skb, ip_hdr(skb)->saddr, &arg, arg.iov[0].iov_len); TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); -- cgit v1.2.3 From 6bd023f3dddfc7c5f660089598c10e1f4167083b Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Wed, 18 May 2011 18:32:03 -0400 Subject: ipv4: Make caller provide flowi4 key to inet_csk_route_req(). This way the caller can get at the fully resolved fl4->{daddr,saddr} etc. Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index f67fb34e16e5..7e0bc604ebd2 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -769,11 +769,12 @@ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, struct request_values *rvp) { const struct inet_request_sock *ireq = inet_rsk(req); + struct flowi4 fl4; int err = -1; struct sk_buff * skb; /* First, grab a route. */ - if (!dst && (dst = inet_csk_route_req(sk, req)) == NULL) + if (!dst && (dst = inet_csk_route_req(sk, &fl4, req)) == NULL) return -1; skb = tcp_make_synack(sk, dst, req, rvp); @@ -1338,6 +1339,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) req->cookie_ts = tmp_opt.tstamp_ok; } else if (!isn) { struct inet_peer *peer = NULL; + struct flowi4 fl4; /* VJ's idea. We save last timestamp seen * from the destination in peer table, when entering @@ -1350,7 +1352,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) */ if (tmp_opt.saw_tstamp && tcp_death_row.sysctl_tw_recycle && - (dst = inet_csk_route_req(sk, req)) != NULL && + (dst = inet_csk_route_req(sk, &fl4, req)) != NULL && (peer = rt_get_peer((struct rtable *)dst)) != NULL && peer->daddr.addr.a4 == saddr) { inet_peer_refcheck(peer); -- cgit v1.2.3 From ed2361e66eec60645f8e4715fe39a42235ef43ae Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Wed, 18 May 2011 18:38:54 -0400 Subject: ipv4: Pass explicit destination address to rt_get_peer(). This will next trickle down to rt_bind_peer(). Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 7e0bc604ebd2..1d290acdcb27 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -206,7 +206,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (tcp_death_row.sysctl_tw_recycle && !tp->rx_opt.ts_recent_stamp && fl4->daddr == daddr) { - struct inet_peer *peer = rt_get_peer(rt); + struct inet_peer *peer = rt_get_peer(rt, fl4->daddr); /* * VJ's idea. We save last timestamp seen from * the destination in peer table, when entering state @@ -1353,8 +1353,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) if (tmp_opt.saw_tstamp && tcp_death_row.sysctl_tw_recycle && (dst = inet_csk_route_req(sk, &fl4, req)) != NULL && - (peer = rt_get_peer((struct rtable *)dst)) != NULL && - peer->daddr.addr.a4 == saddr) { + fl4.daddr == saddr && + (peer = rt_get_peer((struct rtable *)dst, fl4.daddr)) != NULL) { inet_peer_refcheck(peer); if ((u32)get_seconds() - peer->tcp_ts_stamp < TCP_PAWS_MSL && (s32)(peer->tcp_ts - req->ts_recent) > -- cgit v1.2.3 From a48eff128865aa20520fa6e0e0c5fbd2ac50d712 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Wed, 18 May 2011 18:42:43 -0400 Subject: ipv4: Pass explicit destination address to rt_bind_peer(). Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 1d290acdcb27..3c8d9b6f1ea4 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1781,7 +1781,7 @@ struct inet_peer *tcp_v4_get_peer(struct sock *sk, bool *release_it) *release_it = true; } else { if (!rt->peer) - rt_bind_peer(rt, 1); + rt_bind_peer(rt, inet->inet_daddr, 1); peer = rt->peer; *release_it = false; } -- cgit v1.2.3 From 71338aa7d050c86d8765cd36e46be514fb0ebbce Mon Sep 17 00:00:00 2001 From: Dan Rosenberg Date: Mon, 23 May 2011 12:17:35 +0000 Subject: net: convert %p usage to %pK The %pK format specifier is designed to hide exposed kernel pointers, specifically via /proc interfaces. Exposing these pointers provides an easy target for kernel write vulnerabilities, since they reveal the locations of writable structures containing easily triggerable function pointers. The behavior of %pK depends on the kptr_restrict sysctl. If kptr_restrict is set to 0, no deviation from the standard %p behavior occurs. If kptr_restrict is set to 1, the default, if the current user (intended to be a reader via seq_printf(), etc.) does not have CAP_SYSLOG (currently in the LSM tree), kernel pointers using %pK are printed as 0's. If kptr_restrict is set to 2, kernel pointers using %pK are printed as 0's regardless of privileges. Replacing with 0's was chosen over the default "(null)", which cannot be parsed by userland %p, which expects "(nil)". The supporting code for kptr_restrict and %pK are currently in the -mm tree. This patch converts users of %p in net/ to %pK. Cases of printing pointers to the syslog are not covered, since this would eliminate useful information for postmortem debugging and the reading of the syslog is already optionally protected by the dmesg_restrict sysctl. Signed-off-by: Dan Rosenberg Cc: James Morris Cc: Eric Dumazet Cc: Thomas Graf Cc: Eugene Teo Cc: Kees Cook Cc: Ingo Molnar Cc: David S. Miller Cc: Peter Zijlstra Cc: Eric Paris Signed-off-by: Andrew Morton Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 3c8d9b6f1ea4..a7d6671e33b8 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2371,7 +2371,7 @@ static void get_openreq4(struct sock *sk, struct request_sock *req, int ttd = req->expires - jiffies; seq_printf(f, "%4d: %08X:%04X %08X:%04X" - " %02X %08X:%08X %02X:%08lX %08X %5d %8d %u %d %p%n", + " %02X %08X:%08X %02X:%08lX %08X %5d %8d %u %d %pK%n", i, ireq->loc_addr, ntohs(inet_sk(sk)->inet_sport), @@ -2426,7 +2426,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i, int *len) rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0); seq_printf(f, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX " - "%08X %5d %8d %lu %d %p %lu %lu %u %u %d%n", + "%08X %5d %8d %lu %d %pK %lu %lu %u %u %d%n", i, src, srcp, dest, destp, sk->sk_state, tp->write_seq - tp->snd_una, rx_queue, @@ -2461,7 +2461,7 @@ static void get_timewait4_sock(struct inet_timewait_sock *tw, srcp = ntohs(tw->tw_sport); seq_printf(f, "%4d: %08X:%04X %08X:%04X" - " %02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %p%n", + " %02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK%n", i, src, srcp, dest, destp, tw->tw_substate, 0, 0, 3, jiffies_to_clock_t(ttd), 0, 0, 0, 0, atomic_read(&tw->tw_refcnt), tw, len); -- cgit v1.2.3 From 1eddceadb0d6441cd39b2c38705a8f5fec86e770 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 17 Jun 2011 03:45:15 +0000 Subject: net: rfs: enable RFS before first data packet is received MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Le jeudi 16 juin 2011 à 23:38 -0400, David Miller a écrit : > From: Ben Hutchings > Date: Fri, 17 Jun 2011 00:50:46 +0100 > > > On Wed, 2011-06-15 at 04:15 +0200, Eric Dumazet wrote: > >> @@ -1594,6 +1594,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) > >> goto discard; > >> > >> if (nsk != sk) { > >> + sock_rps_save_rxhash(nsk, skb->rxhash); > >> if (tcp_child_process(sk, nsk, skb)) { > >> rsk = nsk; > >> goto reset; > >> > > > > I haven't tried this, but it looks reasonable to me. > > > > What about IPv6? The logic in tcp_v6_do_rcv() looks very similar. > > Indeed ipv6 side needs the same fix. > > Eric please add that part and resubmit. And in fact I might stick > this into net-2.6 instead of net-next-2.6 > OK, here is the net-2.6 based one then, thanks ! [PATCH v2] net: rfs: enable RFS before first data packet is received First packet received on a passive tcp flow is not correctly RFS steered. One sock_rps_record_flow() call is missing in inet_accept() But before that, we also must record rxhash when child socket is setup. Signed-off-by: Eric Dumazet CC: Tom Herbert CC: Ben Hutchings CC: Jamal Hadi Salim Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a7d6671e33b8..708dc203b034 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1589,6 +1589,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) goto discard; if (nsk != sk) { + sock_rps_save_rxhash(nsk, skb->rxhash); if (tcp_child_process(sk, nsk, skb)) { rsk = nsk; goto reset; -- cgit v1.2.3