From 628e341f319f1a64a4639088faba952e4ec8f0a8 Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Wed, 14 Aug 2013 13:05:23 +0200 Subject: xfrm: make local error reporting more robust In xfrm4 and xfrm6 we need to take care about sockets of the other address family. This could happen because a 6in4 or 4in6 tunnel could get protected by ipsec. Because we don't want to have a run-time dependency on ipv6 when only using ipv4 xfrm we have to embed a pointer to the correct local_error function in xfrm_state_afinet and look it up when returning an error depending on the socket address family. Thanks to vi0ss for the great bug report: v2: a) fix two more unsafe interpretations of skb->sk as ipv6 socket (xfrm6_local_dontfrag and __xfrm6_output) v3: a) add an EXPORT_SYMBOL_GPL(xfrm_local_error) to fix a link error when building ipv6 as a module (thanks to Steffen Klassert) Reported-by: Cc: Steffen Klassert Signed-off-by: Hannes Frederic Sowa Signed-off-by: Steffen Klassert --- net/ipv4/xfrm4_output.c | 12 ++++++++++-- net/ipv4/xfrm4_state.c | 1 + 2 files changed, 11 insertions(+), 2 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index 327a617d594..7a5491ffa4d 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -33,8 +33,7 @@ static int xfrm4_tunnel_check_size(struct sk_buff *skb) mtu = dst_mtu(dst); if (skb->len > mtu) { if (skb->sk) - ip_local_error(skb->sk, EMSGSIZE, ip_hdr(skb)->daddr, - inet_sk(skb->sk)->inet_dport, mtu); + xfrm_local_error(skb, mtu); else icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); @@ -99,3 +98,12 @@ int xfrm4_output(struct sk_buff *skb) x->outer_mode->afinfo->output_finish, !(IPCB(skb)->flags & IPSKB_REROUTED)); } + +void xfrm4_local_error(struct sk_buff *skb, u32 mtu) +{ + struct iphdr *hdr; + + hdr = skb->encapsulation ? inner_ip_hdr(skb) : ip_hdr(skb); + ip_local_error(skb->sk, EMSGSIZE, hdr->daddr, + inet_sk(skb->sk)->inet_dport, mtu); +} diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c index 9258e751bab..0b2a0641526 100644 --- a/net/ipv4/xfrm4_state.c +++ b/net/ipv4/xfrm4_state.c @@ -83,6 +83,7 @@ static struct xfrm_state_afinfo xfrm4_state_afinfo = { .extract_input = xfrm4_extract_input, .extract_output = xfrm4_extract_output, .transport_finish = xfrm4_transport_finish, + .local_error = xfrm4_local_error, }; void __init xfrm4_state_init(void) -- cgit v1.2.3-70-g09d2 From 0ea9d5e3e0e03a63b11392f5613378977dae7eca Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Tue, 13 Aug 2013 04:35:58 +0200 Subject: xfrm: introduce helper for safe determination of mtu skb->sk socket can be of AF_INET or AF_INET6 address family. Thus we always have to make sure we a referring to the correct interpretation of skb->sk. We only depend on header defines to query the mtu, so we don't introduce a new dependency to ipv6 by this change. Cc: Steffen Klassert Signed-off-by: Hannes Frederic Sowa Signed-off-by: Steffen Klassert --- include/net/route.h | 8 ++++++++ include/net/xfrm.h | 12 ++++++++++++ net/ipv4/ip_output.c | 8 -------- net/ipv4/xfrm4_output.c | 4 +--- net/ipv6/xfrm6_output.c | 5 ++++- 5 files changed, 25 insertions(+), 12 deletions(-) (limited to 'net/ipv4') diff --git a/include/net/route.h b/include/net/route.h index 2ea40c1b5e0..afdeeb5bec2 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -317,4 +317,12 @@ static inline int ip4_dst_hoplimit(const struct dst_entry *dst) return hoplimit; } +static inline int ip_skb_dst_mtu(struct sk_buff *skb) +{ + struct inet_sock *inet = skb->sk ? inet_sk(skb->sk) : NULL; + + return (inet && inet->pmtudisc == IP_PMTUDISC_PROBE) ? + skb_dst(skb)->dev->mtu : dst_mtu(skb_dst(skb)); +} + #endif /* _ROUTE_H */ diff --git a/include/net/xfrm.h b/include/net/xfrm.h index e823786e7c6..b41d2d10ff0 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -20,6 +20,7 @@ #include #include #include +#include #include #include @@ -1723,4 +1724,15 @@ static inline int xfrm_mark_put(struct sk_buff *skb, const struct xfrm_mark *m) return ret; } +static inline int xfrm_skb_dst_mtu(struct sk_buff *skb) +{ + struct sock *sk = skb->sk; + + if (sk && sk->sk_family == AF_INET6) + return ip6_skb_dst_mtu(skb); + else if (sk && sk->sk_family == AF_INET) + return ip_skb_dst_mtu(skb); + return dst_mtu(skb_dst(skb)); +} + #endif /* _NET_XFRM_H */ diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 4bcabf3ab4c..9ee17e3d11c 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -211,14 +211,6 @@ static inline int ip_finish_output2(struct sk_buff *skb) return -EINVAL; } -static inline int ip_skb_dst_mtu(struct sk_buff *skb) -{ - struct inet_sock *inet = skb->sk ? inet_sk(skb->sk) : NULL; - - return (inet && inet->pmtudisc == IP_PMTUDISC_PROBE) ? - skb_dst(skb)->dev->mtu : dst_mtu(skb_dst(skb)); -} - static int ip_finish_output(struct sk_buff *skb) { #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM) diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index 7a5491ffa4d..80baf4a3b1b 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -21,7 +21,6 @@ static int xfrm4_tunnel_check_size(struct sk_buff *skb) { int mtu, ret = 0; - struct dst_entry *dst; if (IPCB(skb)->flags & IPSKB_XFRM_TUNNEL_SIZE) goto out; @@ -29,8 +28,7 @@ static int xfrm4_tunnel_check_size(struct sk_buff *skb) if (!(ip_hdr(skb)->frag_off & htons(IP_DF)) || skb->local_df) goto out; - dst = skb_dst(skb); - mtu = dst_mtu(dst); + mtu = xfrm_skb_dst_mtu(skb); if (skb->len > mtu) { if (skb->sk) xfrm_local_error(skb, mtu); diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index b64fff30eb0..3ac5ab264fe 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -138,7 +138,10 @@ static int __xfrm6_output(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct xfrm_state *x = dst->xfrm; - int mtu = ip6_skb_dst_mtu(skb); + int mtu = xfrm_skb_dst_mtu(skb); + + if (mtu < IPV6_MIN_MTU) + mtu = IPV6_MIN_MTU; if (skb->len > mtu && xfrm6_local_dontfrag(skb)) { xfrm6_local_rxpmtu(skb, mtu); -- cgit v1.2.3-70-g09d2 From 5a25cf1e310888eb333f9e034be84a8117111d30 Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Mon, 26 Aug 2013 12:31:19 +0200 Subject: xfrm: revert ipv4 mtu determination to dst_mtu In commit 0ea9d5e3e0e03a63b11392f5613378977dae7eca ("xfrm: introduce helper for safe determination of mtu") I switched the determination of ipv4 mtus from dst_mtu to ip_skb_dst_mtu. This was an error because in case of IP_PMTUDISC_PROBE we fall back to the interface mtu, which is never correct for ipv4 ipsec. This patch partly reverts 0ea9d5e3e0e03a63b11392f5613378977dae7eca ("xfrm: introduce helper for safe determination of mtu"). Cc: Steffen Klassert Signed-off-by: Hannes Frederic Sowa Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 12 ------------ net/ipv4/xfrm4_output.c | 2 +- net/ipv6/xfrm6_output.c | 8 +++++--- 3 files changed, 6 insertions(+), 16 deletions(-) (limited to 'net/ipv4') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index ac5b0251535..e823786e7c6 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -20,7 +20,6 @@ #include #include #include -#include #include #include @@ -1724,15 +1723,4 @@ static inline int xfrm_mark_put(struct sk_buff *skb, const struct xfrm_mark *m) return ret; } -static inline int xfrm_skb_dst_mtu(struct sk_buff *skb) -{ - struct sock *sk = skb->sk; - - if (sk && skb->protocol == htons(ETH_P_IPV6)) - return ip6_skb_dst_mtu(skb); - else if (sk && skb->protocol == htons(ETH_P_IP)) - return ip_skb_dst_mtu(skb); - return dst_mtu(skb_dst(skb)); -} - #endif /* _NET_XFRM_H */ diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index 80baf4a3b1b..baa0f63731f 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -28,7 +28,7 @@ static int xfrm4_tunnel_check_size(struct sk_buff *skb) if (!(ip_hdr(skb)->frag_off & htons(IP_DF)) || skb->local_df) goto out; - mtu = xfrm_skb_dst_mtu(skb); + mtu = dst_mtu(skb_dst(skb)); if (skb->len > mtu) { if (skb->sk) xfrm_local_error(skb, mtu); diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index e092e306882..6cd625e3770 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -140,10 +140,12 @@ static int __xfrm6_output(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct xfrm_state *x = dst->xfrm; - int mtu = xfrm_skb_dst_mtu(skb); + int mtu; - if (mtu < IPV6_MIN_MTU) - mtu = IPV6_MIN_MTU; + if (skb->protocol == htons(ETH_P_IPV6)) + mtu = ip6_skb_dst_mtu(skb); + else + mtu = dst_mtu(skb_dst(skb)); if (skb->len > mtu && xfrm6_local_dontfrag(skb)) { xfrm6_local_rxpmtu(skb, mtu); -- cgit v1.2.3-70-g09d2 From c7781a6e3c4a9a17e144ec2db00ebfea327bd627 Mon Sep 17 00:00:00 2001 From: Andrew Vagin Date: Tue, 27 Aug 2013 12:20:40 +0400 Subject: tcp: initialize rcv_tstamp for restored sockets u32 rcv_tstamp; /* timestamp of last received ACK */ Its value used in tcp_retransmit_timer, which closes socket if the last ack was received more then TCP_RTO_MAX ago. Currently rcv_tstamp is initialized to zero and if tcp_retransmit_timer is called before receiving a first ack, the connection is closed. This patch initializes rcv_tstamp to a timestamp, when a socket was restored. Cc: Pavel Emelyanov Cc: Eric Dumazet Cc: "David S. Miller" Cc: Alexey Kuznetsov Cc: James Morris Cc: Hideaki YOSHIFUJI Cc: Patrick McHardy Reported-by: Cyrill Gorcunov Signed-off-by: Andrey Vagin Signed-off-by: David S. Miller --- net/ipv4/tcp_output.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 92fde8d1aa8..e2972993c67 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2814,6 +2814,8 @@ void tcp_connect_init(struct sock *sk) if (likely(!tp->repair)) tp->rcv_nxt = 0; + else + tp->rcv_tstamp = tcp_time_stamp; tp->rcv_wup = tp->rcv_nxt; tp->copied_seq = tp->rcv_nxt; -- cgit v1.2.3-70-g09d2 From e3e12028315749b7fa2edbc37328e5847be9ede9 Mon Sep 17 00:00:00 2001 From: Andrew Vagin Date: Tue, 27 Aug 2013 12:21:55 +0400 Subject: tcp: don't apply tsoffset if rcv_tsecr is zero The zero value means that tsecr is not valid, so it's a special case. tsoffset is used to customize tcp_time_stamp for one socket. tsoffset is usually zero, it's used when a socket was moved from one host to another host. Currently this issue affects logic of tcp_rcv_rtt_measure_ts. Due to incorrect value of rcv_tsecr, tcp_rcv_rtt_measure_ts sets rto to TCP_RTO_MAX. Cc: Pavel Emelyanov Cc: Eric Dumazet Cc: "David S. Miller" Cc: Alexey Kuznetsov Cc: James Morris Cc: Hideaki YOSHIFUJI Cc: Patrick McHardy Reported-by: Cyrill Gorcunov Signed-off-by: Andrey Vagin Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 28af45abe06..3ca2139a130 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3535,7 +3535,10 @@ static bool tcp_parse_aligned_timestamp(struct tcp_sock *tp, const struct tcphdr ++ptr; tp->rx_opt.rcv_tsval = ntohl(*ptr); ++ptr; - tp->rx_opt.rcv_tsecr = ntohl(*ptr) - tp->tsoffset; + if (*ptr) + tp->rx_opt.rcv_tsecr = ntohl(*ptr) - tp->tsoffset; + else + tp->rx_opt.rcv_tsecr = 0; return true; } return false; @@ -3560,7 +3563,7 @@ static bool tcp_fast_parse_options(const struct sk_buff *skb, } tcp_parse_options(skb, &tp->rx_opt, 1, NULL); - if (tp->rx_opt.saw_tstamp) + if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr) tp->rx_opt.rcv_tsecr -= tp->tsoffset; return true; @@ -5316,7 +5319,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, int saved_clamp = tp->rx_opt.mss_clamp; tcp_parse_options(skb, &tp->rx_opt, 0, &foc); - if (tp->rx_opt.saw_tstamp) + if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr) tp->rx_opt.rcv_tsecr -= tp->tsoffset; if (th->ack) { -- cgit v1.2.3-70-g09d2 From c27c9322d015dc1d9dfdf31724fca71c0476c4d1 Mon Sep 17 00:00:00 2001 From: Chris Clark Date: Tue, 27 Aug 2013 12:02:15 -0600 Subject: ipv4: sendto/hdrincl: don't use destination address found in header ipv4: raw_sendmsg: don't use header's destination address A sendto() regression was bisected and found to start with commit f8126f1d5136be1 (ipv4: Adjust semantics of rt->rt_gateway.) The problem is that it tries to ARP-lookup the constructed packet's destination address rather than the explicitly provided address. Fix this using FLOWI_FLAG_KNOWN_NH so that given nexthop is used. cf. commit 2ad5b9e4bd314fc685086b99e90e5de3bc59e26b Reported-by: Chris Clark Bisected-by: Chris Clark Tested-by: Chris Clark Suggested-by: Julian Anastasov Signed-off-by: Chris Clark Signed-off-by: David S. Miller --- net/ipv4/raw.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net/ipv4') diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index dd44e0ab600..61e60d67adc 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -571,7 +571,8 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol, - inet_sk_flowi_flags(sk) | FLOWI_FLAG_CAN_SLEEP, + inet_sk_flowi_flags(sk) | FLOWI_FLAG_CAN_SLEEP | + (inet->hdrincl ? FLOWI_FLAG_KNOWN_NH : 0), daddr, saddr, 0, 0); if (!inet->hdrincl) { -- cgit v1.2.3-70-g09d2 From eb8895debe1baba41fcb62c78a16f0c63c21662a Mon Sep 17 00:00:00 2001 From: Phil Oester Date: Tue, 27 Aug 2013 16:41:40 -0700 Subject: tcp: tcp_make_synack() should use sock_wmalloc In commit 90ba9b19 (tcp: tcp_make_synack() can use alloc_skb()), Eric changed the call to sock_wmalloc in tcp_make_synack to alloc_skb. In doing so, the netfilter owner match lost its ability to block the SYNACK packet on outbound listening sockets. Revert the change, restoring the owner match functionality. This closes netfilter bugzilla #847. Signed-off-by: Phil Oester Signed-off-by: David S. Miller --- net/ipv4/tcp_output.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index e2972993c67..170737a9d56 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2670,7 +2670,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, int tcp_header_size; int mss; - skb = alloc_skb(MAX_TCP_HEADER + 15, sk_gfp_atomic(sk, GFP_ATOMIC)); + skb = sock_wmalloc(sk, MAX_TCP_HEADER + 15, 1, GFP_ATOMIC); if (unlikely(!skb)) { dst_release(dst); return NULL; -- cgit v1.2.3-70-g09d2 From 737e828bdbdaf2f9d7de07f20a0308ac46ce5178 Mon Sep 17 00:00:00 2001 From: Li Hongjun Date: Wed, 28 Aug 2013 11:54:50 +0200 Subject: ipv4 tunnels: fix an oops when using ipip/sit with IPsec Since commit 3d7b46cd20e3 (ip_tunnel: push generic protocol handling to ip_tunnel module.), an Oops is triggered when an xfrm policy is configured on an IPv4 over IPv4 tunnel. xfrm4_policy_check() calls __xfrm_policy_check2(), which uses skb_dst(skb). But this field is NULL because iptunnel_pull_header() calls skb_dst_drop(skb). Signed-off-by: Li Hongjun Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- net/ipv4/ipip.c | 5 ++--- net/ipv6/sit.c | 6 ++---- 2 files changed, 4 insertions(+), 7 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 51fc2a1dcdd..b3ac3c3f621 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -190,15 +190,14 @@ static int ipip_rcv(struct sk_buff *skb) struct ip_tunnel *tunnel; const struct iphdr *iph; - if (iptunnel_pull_header(skb, 0, tpi.proto)) - goto drop; - iph = ip_hdr(skb); tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, iph->saddr, iph->daddr, 0); if (tunnel) { if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto drop; + if (iptunnel_pull_header(skb, 0, tpi.proto)) + goto drop; return ip_tunnel_rcv(tunnel, skb, &tpi, log_ecn_error); } diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index fbfc5a83867..21b25dd8466 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -645,11 +645,7 @@ static int ipip_rcv(struct sk_buff *skb) const struct iphdr *iph; struct ip_tunnel *tunnel; - if (iptunnel_pull_header(skb, 0, tpi.proto)) - goto drop; - iph = ip_hdr(skb); - tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, iph->saddr, iph->daddr); if (tunnel != NULL) { @@ -659,6 +655,8 @@ static int ipip_rcv(struct sk_buff *skb) if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto drop; + if (iptunnel_pull_header(skb, 0, tpi.proto)) + goto drop; return ip_tunnel_rcv(tunnel, skb, &tpi, log_ecn_error); } -- cgit v1.2.3-70-g09d2 From e2e5c4c07caf810d7849658dca42f598b3938e21 Mon Sep 17 00:00:00 2001 From: Dave Jones Date: Thu, 5 Sep 2013 13:43:34 -0400 Subject: tcp: Add missing braces to do_tcp_setsockopt Signed-off-by: Dave Jones Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- net/ipv4/tcp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index b2f6c74861a..95544e4028c 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2454,10 +2454,11 @@ static int do_tcp_setsockopt(struct sock *sk, int level, case TCP_THIN_DUPACK: if (val < 0 || val > 1) err = -EINVAL; - else + else { tp->thin_dupack = val; if (tp->thin_dupack) tcp_disable_early_retrans(tp); + } break; case TCP_REPAIR: -- cgit v1.2.3-70-g09d2