From b357a364c57c940ddb932224542494363df37378 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 23 Apr 2015 18:03:44 -0700 Subject: inet: fix possible panic in reqsk_queue_unlink() [ 3897.923145] BUG: unable to handle kernel NULL pointer dereference at 0000000000000080 [ 3897.931025] IP: [] reqsk_timer_handler+0x1a6/0x243 There is a race when reqsk_timer_handler() and tcp_check_req() call inet_csk_reqsk_queue_unlink() on the same req at the same time. Before commit fa76ce7328b2 ("inet: get rid of central tcp/dccp listener timer"), listener spinlock was held and race could not happen. To solve this bug, we change reqsk_queue_unlink() to not assume req must be found, and we return a status, to conditionally release a refcount on the request sock. This also means tcp_check_req() in non fastopen case might or not consume req refcount, so tcp_v6_hnd_req() & tcp_v4_hnd_req() have to properly handle this. (Same remark for dccp_check_req() and its callers) inet_csk_reqsk_queue_drop() is now too big to be inlined, as it is called 4 times in tcp and 3 times in dccp. Fixes: fa76ce7328b2 ("inet: get rid of central tcp/dccp listener timer") Signed-off-by: Eric Dumazet Reported-by: Yuchung Cheng Signed-off-by: David S. Miller --- net/ipv6/tcp_ipv6.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net/ipv6/tcp_ipv6.c') diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index ad51df8..b6575d6 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -946,7 +946,8 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk, struct sk_buff *skb) &ipv6_hdr(skb)->daddr, tcp_v6_iif(skb)); if (req) { nsk = tcp_check_req(sk, skb, req, false); - reqsk_put(req); + if (!nsk) + reqsk_put(req); return nsk; } nsk = __inet6_lookup_established(sock_net(sk), &tcp_hashinfo, -- cgit v1.1 From 21858cd02dabcf290564cbf4769b101eba54d7bb Mon Sep 17 00:00:00 2001 From: Florent Fourcot Date: Sat, 16 May 2015 00:24:59 +0200 Subject: tcp/ipv6: fix flow label setting in TIME_WAIT state commit 1d13a96c74fc ("ipv6: tcp: fix flowlabel value in ACK messages send from TIME_WAIT") added the flow label in the last TCP packets. Unfortunately, it was not casted properly. This patch replace the buggy shift with be32_to_cpu/cpu_to_be32. Fixes: 1d13a96c74fc ("ipv6: tcp: fix flowlabel value in ACK messages") Reported-by: Eric Dumazet Signed-off-by: Florent Fourcot Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv6/tcp_ipv6.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv6/tcp_ipv6.c') diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index b6575d6..3adffb3 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -914,7 +914,7 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, tcp_time_stamp + tcptw->tw_ts_offset, tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw), - tw->tw_tclass, (tw->tw_flowlabel << 12)); + tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel)); inet_twsk_put(tw); } -- cgit v1.1 From 2efd055c53c06b7e89c167c98069bab9afce7e59 Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Wed, 20 May 2015 16:35:41 -0700 Subject: tcp: add tcpi_segs_in and tcpi_segs_out to tcp_info This patch tracks the total number of inbound and outbound segments on a TCP socket. One may use this number to have an idea on connection quality when compared against the retransmissions. RFC4898 named these : tcpEStatsPerfSegsIn and tcpEStatsPerfSegsOut These are a 32bit field each and can be fetched both from TCP_INFO getsockopt() if one has a handle on a TCP socket, or from inet_diag netlink facility (iproute2/ss patch will follow) Note that tp->segs_out was placed near tp->snd_nxt for good data locality and minimal performance impact, while tp->segs_in was placed near tp->bytes_received for the same reason. Join work with Eric Dumazet. Note that received SYN are accounted on the listener, but sent SYNACK are not accounted. Signed-off-by: Marcelo Ricardo Leitner Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv6/tcp_ipv6.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/ipv6/tcp_ipv6.c') diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index b6575d6..beac6bf 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1421,6 +1421,7 @@ process: skb->dev = NULL; bh_lock_sock_nested(sk); + tcp_sk(sk)->segs_in += max_t(u16, 1, skb_shinfo(skb)->gso_segs); ret = 0; if (!sock_owned_by_user(sk)) { if (!tcp_prequeue(sk, skb)) -- cgit v1.1 From fd0273d7939f2ce3247f6aac5f6b9a0135d4cd39 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Fri, 22 May 2015 20:55:57 -0700 Subject: ipv6: Remove external dependency on rt6i_dst and rt6i_src This patch removes the assumptions that the returned rt is always a RTF_CACHE entry with the rt6i_dst and rt6i_src containing the destination and source address. The dst and src can be recovered from the calling site. We may consider to rename (rt6i_dst, rt6i_src) to (rt6i_key_dst, rt6i_key_src) later. Signed-off-by: Martin KaFai Lau Reviewed-by: Hannes Frederic Sowa Cc: Steffen Klassert Cc: Julian Anastasov Signed-off-by: David S. Miller --- net/ipv6/tcp_ipv6.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv6/tcp_ipv6.c') diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index fefe445..1a9390a 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -262,7 +262,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, rt = (struct rt6_info *) dst; if (tcp_death_row.sysctl_tw_recycle && !tp->rx_opt.ts_recent_stamp && - ipv6_addr_equal(&rt->rt6i_dst.addr, &sk->sk_v6_daddr)) + ipv6_addr_equal(&fl6.daddr, &sk->sk_v6_daddr)) tcp_fetch_timewait_stamp(sk, dst); icsk->icsk_ext_hdr_len = 0; -- cgit v1.1 From b197df4f0f3782782e9ea8996e91b65ae33e8dd9 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Fri, 22 May 2015 20:56:01 -0700 Subject: ipv6: Add rt6_get_cookie() function Instead of doing the rt6->rt6i_node check whenever we need to get the route's cookie. Refactor it into rt6_get_cookie(). It is a prep work to handle FLOWI_FLAG_KNOWN_NH and also percpu rt6_info later. Signed-off-by: Martin KaFai Lau Cc: Hannes Frederic Sowa Cc: Steffen Klassert Cc: Julian Anastasov Signed-off-by: David S. Miller --- net/ipv6/tcp_ipv6.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'net/ipv6/tcp_ipv6.c') diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 1a9390a..7be3d85 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -99,8 +99,7 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) dst_hold(dst); sk->sk_rx_dst = dst; inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; - if (rt->rt6i_node) - inet6_sk(sk)->rx_dst_cookie = rt->rt6i_node->fn_sernum; + inet6_sk(sk)->rx_dst_cookie = rt6_get_cookie(rt); } } -- cgit v1.1 From 12e25e1041d044d4204f2b7c54695e14e8ffb282 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 3 Jun 2015 23:49:21 -0700 Subject: tcp: remove redundant checks tcp_v4_rcv() checks the following before calling tcp_v4_do_rcv(): if (th->doff < sizeof(struct tcphdr) / 4) goto bad_packet; if (!pskb_may_pull(skb, th->doff * 4)) goto discard_it; So following check in tcp_v4_do_rcv() is redundant and "goto csum_err;" is wrong anyway. if (skb->len < tcp_hdrlen(skb) || ...) goto csum_err; A second check can be removed after no_tcp_socket label for same reason. Same tests can be removed in tcp_v6_do_rcv() Note : short tcp frames are not properly accounted in tcpInErrs MIB, because pskb_may_pull() failure simply drops incoming skb, we might fix this in a separate patch. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv6/tcp_ipv6.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/ipv6/tcp_ipv6.c') diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 7be3d85..b72e1ff 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1250,7 +1250,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) return 0; } - if (skb->len < tcp_hdrlen(skb) || tcp_checksum_complete(skb)) + if (tcp_checksum_complete(skb)) goto csum_err; if (sk->sk_state == TCP_LISTEN) { @@ -1442,7 +1442,7 @@ no_tcp_socket: tcp_v6_fill_cb(skb, hdr, th); - if (skb->len < (th->doff<<2) || tcp_checksum_complete(skb)) { + if (tcp_checksum_complete(skb)) { csum_error: TCP_INC_STATS_BH(net, TCP_MIB_CSUMERRORS); bad_packet: -- cgit v1.1 From 98da81a426a76c351f3c2854d5bc31f17bba3194 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 4 Jun 2015 08:01:12 -0700 Subject: tcp: remove redundant checks II For same reasons than in commit 12e25e1041d0 ("tcp: remove redundant checks"), we can remove redundant checks done for timewait sockets. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv6/tcp_ipv6.c | 4 ---- 1 file changed, 4 deletions(-) (limited to 'net/ipv6/tcp_ipv6.c') diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index b72e1ff..45a7176 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1467,10 +1467,6 @@ do_time_wait: tcp_v6_fill_cb(skb, hdr, th); - if (skb->len < (th->doff<<2)) { - inet_twsk_put(inet_twsk(sk)); - goto bad_packet; - } if (tcp_checksum_complete(skb)) { inet_twsk_put(inet_twsk(sk)); goto csum_error; -- cgit v1.1