From 7faee5c0d514162853a343d93e4a0b6bb8bfec21 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 5 Sep 2014 15:33:33 -0700 Subject: tcp: remove TCP_SKB_CB(skb)->when After commit 740b0f1841f6 ("tcp: switch rtt estimations to usec resolution"), we no longer need to maintain timestamps in two different fields. TCP_SKB_CB(skb)->when can be removed, as same information sits in skb_mstamp.stamp_jiffies Signed-off-by: Eric Dumazet Acked-by: Yuchung Cheng Signed-off-by: David S. Miller --- net/ipv4/tcp_timer.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'net/ipv4/tcp_timer.c') diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index df90cd1ce37f..a339e7ba05a4 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -135,10 +135,9 @@ static bool retransmits_timed_out(struct sock *sk, if (!inet_csk(sk)->icsk_retransmits) return false; - if (unlikely(!tcp_sk(sk)->retrans_stamp)) - start_ts = TCP_SKB_CB(tcp_write_queue_head(sk))->when; - else - start_ts = tcp_sk(sk)->retrans_stamp; + start_ts = tcp_sk(sk)->retrans_stamp; + if (unlikely(!start_ts)) + start_ts = tcp_skb_timestamp(tcp_write_queue_head(sk)); if (likely(timeout == 0)) { linear_backoff_thresh = ilog2(TCP_RTO_MAX/rto_base); -- cgit v1.2.3 From fcdd1cf4dd63aecf86c987d7f4ec7187be5c2fbc Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 22 Sep 2014 13:19:44 -0700 Subject: tcp: avoid possible arithmetic overflows icsk_rto is a 32bit field, and icsk_backoff can reach 15 by default, or more if some sysctl (eg tcp_retries2) are changed. Better use 64bit to perform icsk_rto << icsk_backoff operations As Joe Perches suggested, add a helper for this. Yuchung spotted the tcp_v4_err() case. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 9 +++++++++ net/ipv4/tcp_input.c | 5 +++-- net/ipv4/tcp_ipv4.c | 6 +++--- net/ipv4/tcp_output.c | 13 ++++++------- net/ipv4/tcp_timer.c | 4 ++-- 5 files changed, 23 insertions(+), 14 deletions(-) (limited to 'net/ipv4/tcp_timer.c') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 5fbe6568c3cf..848e85cb5c61 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -242,6 +242,15 @@ static inline void inet_csk_reset_xmit_timer(struct sock *sk, const int what, #endif } +static inline unsigned long +inet_csk_rto_backoff(const struct inet_connection_sock *icsk, + unsigned long max_when) +{ + u64 when = (u64)icsk->icsk_rto << icsk->icsk_backoff; + + return (unsigned long)min_t(u64, when, max_when); +} + struct sock *inet_csk_accept(struct sock *sk, int flags, int *err); struct request_sock *inet_csk_search_req(const struct sock *sk, diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 02fb66d4a018..13f3da4762e3 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3208,9 +3208,10 @@ static void tcp_ack_probe(struct sock *sk) * This function is not for random using! */ } else { + unsigned long when = inet_csk_rto_backoff(icsk, TCP_RTO_MAX); + inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0, - min(icsk->icsk_rto << icsk->icsk_backoff, TCP_RTO_MAX), - TCP_RTO_MAX); + when, TCP_RTO_MAX); } } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 006b045716d8..3b2e49cb2b61 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -430,9 +430,9 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) break; icsk->icsk_backoff--; - inet_csk(sk)->icsk_rto = (tp->srtt_us ? __tcp_set_rto(tp) : - TCP_TIMEOUT_INIT) << icsk->icsk_backoff; - tcp_bound_rto(sk); + icsk->icsk_rto = tp->srtt_us ? __tcp_set_rto(tp) : + TCP_TIMEOUT_INIT; + icsk->icsk_rto = inet_csk_rto_backoff(icsk, TCP_RTO_MAX); skb = tcp_write_queue_head(sk); BUG_ON(!skb); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 7f1280dcad57..8c61a7c0c889 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3279,6 +3279,7 @@ void tcp_send_probe0(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); + unsigned long probe_max; int err; err = tcp_write_wakeup(sk); @@ -3294,9 +3295,7 @@ void tcp_send_probe0(struct sock *sk) if (icsk->icsk_backoff < sysctl_tcp_retries2) icsk->icsk_backoff++; icsk->icsk_probes_out++; - inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0, - min(icsk->icsk_rto << icsk->icsk_backoff, TCP_RTO_MAX), - TCP_RTO_MAX); + probe_max = TCP_RTO_MAX; } else { /* If packet was not sent due to local congestion, * do not backoff and do not remember icsk_probes_out. @@ -3306,11 +3305,11 @@ void tcp_send_probe0(struct sock *sk) */ if (!icsk->icsk_probes_out) icsk->icsk_probes_out = 1; - inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0, - min(icsk->icsk_rto << icsk->icsk_backoff, - TCP_RESOURCE_PROBE_INTERVAL), - TCP_RTO_MAX); + probe_max = TCP_RESOURCE_PROBE_INTERVAL; } + inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0, + inet_csk_rto_backoff(icsk, probe_max), + TCP_RTO_MAX); } int tcp_rtx_synack(struct sock *sk, struct request_sock *req) diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index a339e7ba05a4..b24360f6e293 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -180,7 +180,7 @@ static int tcp_write_timeout(struct sock *sk) retry_until = sysctl_tcp_retries2; if (sock_flag(sk, SOCK_DEAD)) { - const int alive = (icsk->icsk_rto < TCP_RTO_MAX); + const int alive = icsk->icsk_rto < TCP_RTO_MAX; retry_until = tcp_orphan_retries(sk, alive); do_reset = alive || @@ -294,7 +294,7 @@ static void tcp_probe_timer(struct sock *sk) max_probes = sysctl_tcp_retries2; if (sock_flag(sk, SOCK_DEAD)) { - const int alive = ((icsk->icsk_rto << icsk->icsk_backoff) < TCP_RTO_MAX); + const int alive = inet_csk_rto_backoff(icsk, TCP_RTO_MAX) < TCP_RTO_MAX; max_probes = tcp_orphan_retries(sk, alive); -- cgit v1.2.3 From b248230c34970a6c1c17c591d63b464e8d2cfc33 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Mon, 29 Sep 2014 13:20:38 -0700 Subject: tcp: abort orphan sockets stalling on zero window probes Currently we have two different policies for orphan sockets that repeatedly stall on zero window ACKs. If a socket gets a zero window ACK when it is transmitting data, the RTO is used to probe the window. The socket is aborted after roughly tcp_orphan_retries() retries (as in tcp_write_timeout()). But if the socket was idle when it received the zero window ACK, and later wants to send more data, we use the probe timer to probe the window. If the receiver always returns zero window ACKs, icsk_probes keeps getting reset in tcp_ack() and the orphan socket can stall forever until the system reaches the orphan limit (as commented in tcp_probe_timer()). This opens up a simple attack to create lots of hanging orphan sockets to burn the memory and the CPU, as demonstrated in the recent netdev post "TCP connection will hang in FIN_WAIT1 after closing if zero window is advertised." http://www.spinics.net/lists/netdev/msg296539.html This patch follows the design in RTO-based probe: we abort an orphan socket stalling on zero window when the probe timer reaches both the maximum backoff and the maximum RTO. For example, an 100ms RTT connection will timeout after roughly 153 seconds (0.3 + 0.6 + .... + 76.8) if the receiver keeps the window shut. If the orphan socket passes this check, but the system already has too many orphans (as in tcp_out_of_resources()), we still abort it but we'll also send an RST packet as the connection may still be active. In addition, we change TCP_USER_TIMEOUT to cover (life or dead) sockets stalled on zero-window probes. This changes the semantics of TCP_USER_TIMEOUT slightly because it previously only applies when the socket has pending transmission. Signed-off-by: Yuchung Cheng Signed-off-by: Eric Dumazet Signed-off-by: Neal Cardwell Reported-by: Andrey Dmitrov Signed-off-by: David S. Miller --- net/ipv4/tcp.c | 2 +- net/ipv4/tcp_timer.c | 41 +++++++++++++++++++++-------------------- 2 files changed, 22 insertions(+), 21 deletions(-) (limited to 'net/ipv4/tcp_timer.c') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 5c170340f684..26a6f113f00c 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2693,7 +2693,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, break; #endif case TCP_USER_TIMEOUT: - /* Cap the max timeout in ms TCP will retry/retrans + /* Cap the max time in ms TCP will retry or probe the window * before giving up and aborting (ETIMEDOUT) a connection. */ if (val < 0) diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index b24360f6e293..9b21ae8b2e31 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -52,7 +52,7 @@ static void tcp_write_err(struct sock *sk) * limit. * 2. If we have strong memory pressure. */ -static int tcp_out_of_resources(struct sock *sk, int do_reset) +static int tcp_out_of_resources(struct sock *sk, bool do_reset) { struct tcp_sock *tp = tcp_sk(sk); int shift = 0; @@ -72,7 +72,7 @@ static int tcp_out_of_resources(struct sock *sk, int do_reset) if ((s32)(tcp_time_stamp - tp->lsndtime) <= TCP_TIMEWAIT_LEN || /* 2. Window is closed. */ (!tp->snd_wnd && !tp->packets_out)) - do_reset = 1; + do_reset = true; if (do_reset) tcp_send_active_reset(sk, GFP_ATOMIC); tcp_done(sk); @@ -270,40 +270,41 @@ static void tcp_probe_timer(struct sock *sk) struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); int max_probes; + u32 start_ts; if (tp->packets_out || !tcp_send_head(sk)) { icsk->icsk_probes_out = 0; return; } - /* *WARNING* RFC 1122 forbids this - * - * It doesn't AFAIK, because we kill the retransmit timer -AK - * - * FIXME: We ought not to do it, Solaris 2.5 actually has fixing - * this behaviour in Solaris down as a bug fix. [AC] - * - * Let me to explain. icsk_probes_out is zeroed by incoming ACKs - * even if they advertise zero window. Hence, connection is killed only - * if we received no ACKs for normal connection timeout. It is not killed - * only because window stays zero for some time, window may be zero - * until armageddon and even later. We are in full accordance - * with RFCs, only probe timer combines both retransmission timeout - * and probe timeout in one bottle. --ANK + /* RFC 1122 4.2.2.17 requires the sender to stay open indefinitely as + * long as the receiver continues to respond probes. We support this by + * default and reset icsk_probes_out with incoming ACKs. But if the + * socket is orphaned or the user specifies TCP_USER_TIMEOUT, we + * kill the socket when the retry count and the time exceeds the + * corresponding system limit. We also implement similar policy when + * we use RTO to probe window in tcp_retransmit_timer(). */ - max_probes = sysctl_tcp_retries2; + start_ts = tcp_skb_timestamp(tcp_send_head(sk)); + if (!start_ts) + skb_mstamp_get(&tcp_send_head(sk)->skb_mstamp); + else if (icsk->icsk_user_timeout && + (s32)(tcp_time_stamp - start_ts) > icsk->icsk_user_timeout) + goto abort; + max_probes = sysctl_tcp_retries2; if (sock_flag(sk, SOCK_DEAD)) { const int alive = inet_csk_rto_backoff(icsk, TCP_RTO_MAX) < TCP_RTO_MAX; max_probes = tcp_orphan_retries(sk, alive); - - if (tcp_out_of_resources(sk, alive || icsk->icsk_probes_out <= max_probes)) + if (!alive && icsk->icsk_backoff >= max_probes) + goto abort; + if (tcp_out_of_resources(sk, true)) return; } if (icsk->icsk_probes_out > max_probes) { - tcp_write_err(sk); +abort: tcp_write_err(sk); } else { /* Only send another probe if we didn't close things up. */ tcp_send_probe0(sk); -- cgit v1.2.3 From ba7a46f16dd29f93303daeb1fee8af316c5a07f4 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 11 Nov 2014 10:59:17 -0800 Subject: net: Convert LIMIT_NETDEBUG to net_dbg_ratelimited Use the more common dynamic_debug capable net_dbg_ratelimited and remove the LIMIT_NETDEBUG macro. All messages are still ratelimited. Some KERN_ uses are changed to KERN_DEBUG. This may have some negative impact on messages that were emitted at KERN_INFO that are not not enabled at all unless DEBUG is defined or dynamic_debug is enabled. Even so, these messages are now _not_ emitted by default. This also eliminates the use of the net_msg_warn sysctl "/proc/sys/net/core/warnings". For backward compatibility, the sysctl is not removed, but it has no function. The extern declaration of net_msg_warn is removed from sock.h and made static in net/core/sysctl_net_core.c Miscellanea: o Update the sysctl documentation o Remove the embedded uses of pr_fmt o Coalesce format fragments o Realign arguments Signed-off-by: Joe Perches Signed-off-by: David S. Miller --- Documentation/sysctl/net.txt | 12 ++++++++---- include/net/sock.h | 7 ------- include/net/udplite.h | 6 +++--- net/core/sysctl_net_core.c | 2 ++ net/core/utils.c | 3 --- net/ipv4/icmp.c | 8 ++++---- net/ipv4/inet_fragment.c | 2 +- net/ipv4/ip_fragment.c | 3 +-- net/ipv4/tcp_input.c | 8 ++++---- net/ipv4/tcp_timer.c | 18 ++++++++++-------- net/ipv4/udp.c | 30 +++++++++++++++--------------- net/ipv6/addrconf.c | 6 ++---- net/ipv6/ah6.c | 7 +++---- net/ipv6/datagram.c | 4 ++-- net/ipv6/esp6.c | 4 ++-- net/ipv6/exthdrs.c | 18 +++++++++--------- net/ipv6/icmp.c | 15 +++++++-------- net/ipv6/mip6.c | 11 ++++++----- net/ipv6/netfilter.c | 2 +- net/ipv6/udp.c | 31 +++++++++++++------------------ net/phonet/af_phonet.c | 9 +++++---- net/phonet/pep-gprs.c | 3 +-- net/phonet/pep.c | 12 ++++++------ 23 files changed, 105 insertions(+), 116 deletions(-) (limited to 'net/ipv4/tcp_timer.c') diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt index 04892b821157..e26c607468a6 100644 --- a/Documentation/sysctl/net.txt +++ b/Documentation/sysctl/net.txt @@ -120,10 +120,14 @@ seconds. warnings -------- -This controls console messages from the networking stack that can occur because -of problems on the network like duplicate address or bad checksums. Normally, -this should be enabled, but if the problem persists the messages can be -disabled. +This sysctl is now unused. + +This was used to control console messages from the networking stack that +occur because of problems on the network like duplicate address or bad +checksums. + +These messages are now emitted at KERN_DEBUG and can generally be enabled +and controlled by the dynamic_debug facility. netdev_budget ------------- diff --git a/include/net/sock.h b/include/net/sock.h index 7789b59c0c40..83a669f83bae 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2288,13 +2288,6 @@ bool sk_ns_capable(const struct sock *sk, bool sk_capable(const struct sock *sk, int cap); bool sk_net_capable(const struct sock *sk, int cap); -/* - * Enable debug/info messages - */ -extern int net_msg_warn; -#define LIMIT_NETDEBUG(fmt, args...) \ - do { if (net_msg_warn && net_ratelimit()) printk(fmt,##args); } while(0) - extern __u32 sysctl_wmem_max; extern __u32 sysctl_rmem_max; diff --git a/include/net/udplite.h b/include/net/udplite.h index 2caadabcd07b..9a28a5179400 100644 --- a/include/net/udplite.h +++ b/include/net/udplite.h @@ -40,7 +40,7 @@ static inline int udplite_checksum_init(struct sk_buff *skb, struct udphdr *uh) * checksum. UDP-Lite (like IPv6) mandates checksums, hence packets * with a zero checksum field are illegal. */ if (uh->check == 0) { - LIMIT_NETDEBUG(KERN_DEBUG "UDPLite: zeroed checksum field\n"); + net_dbg_ratelimited("UDPLite: zeroed checksum field\n"); return 1; } @@ -52,8 +52,8 @@ static inline int udplite_checksum_init(struct sk_buff *skb, struct udphdr *uh) /* * Coverage length violates RFC 3828: log and discard silently. */ - LIMIT_NETDEBUG(KERN_DEBUG "UDPLite: bad csum coverage %d/%d\n", - cscov, skb->len); + net_dbg_ratelimited("UDPLite: bad csum coverage %d/%d\n", + cscov, skb->len); return 1; } else if (cscov < skb->len) { diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index cf9cd13509a7..f93f092fe226 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -26,6 +26,8 @@ static int zero = 0; static int one = 1; static int ushort_max = USHRT_MAX; +static int net_msg_warn; /* Unused, but still a sysctl */ + #ifdef CONFIG_RPS static int rps_sock_flow_sysctl(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) diff --git a/net/core/utils.c b/net/core/utils.c index efc76dd9dcd1..7b803884c162 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -33,9 +33,6 @@ #include #include -int net_msg_warn __read_mostly = 1; -EXPORT_SYMBOL(net_msg_warn); - DEFINE_RATELIMIT_STATE(net_ratelimit_state, 5 * HZ, 10); /* * All net warning printk()s should be guarded by this function. diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 5882f584910e..36b7bfa609d6 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -784,8 +784,8 @@ static void icmp_unreach(struct sk_buff *skb) */ switch (net->ipv4.sysctl_ip_no_pmtu_disc) { default: - LIMIT_NETDEBUG(KERN_INFO pr_fmt("%pI4: fragmentation needed and DF set\n"), - &iph->daddr); + net_dbg_ratelimited("%pI4: fragmentation needed and DF set\n", + &iph->daddr); break; case 2: goto out; @@ -798,8 +798,8 @@ static void icmp_unreach(struct sk_buff *skb) } break; case ICMP_SR_FAILED: - LIMIT_NETDEBUG(KERN_INFO pr_fmt("%pI4: Source Route Failed\n"), - &iph->daddr); + net_dbg_ratelimited("%pI4: Source Route Failed\n", + &iph->daddr); break; default: break; diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 19419b60cb37..e7920352646a 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -458,6 +458,6 @@ void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q, ". Dropping fragment.\n"; if (PTR_ERR(q) == -ENOBUFS) - LIMIT_NETDEBUG(KERN_WARNING "%s%s", prefix, msg); + net_dbg_ratelimited("%s%s", prefix, msg); } EXPORT_SYMBOL(inet_frag_maybe_warn_overflow); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 4d964dadd655..e5b6d0ddcb58 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -618,8 +618,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, return 0; out_nomem: - LIMIT_NETDEBUG(KERN_ERR pr_fmt("queue_glue: no memory for gluing queue %p\n"), - qp); + net_dbg_ratelimited("queue_glue: no memory for gluing queue %p\n", qp); err = -ENOMEM; goto out_fail; out_oversize: diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 5f979c7f5135..d91436ba17ea 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5854,12 +5854,12 @@ static inline void pr_drop_req(struct request_sock *req, __u16 port, int family) struct inet_request_sock *ireq = inet_rsk(req); if (family == AF_INET) - LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("drop open request from %pI4/%u\n"), - &ireq->ir_rmt_addr, port); + net_dbg_ratelimited("drop open request from %pI4/%u\n", + &ireq->ir_rmt_addr, port); #if IS_ENABLED(CONFIG_IPV6) else if (family == AF_INET6) - LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("drop open request from %pI6/%u\n"), - &ireq->ir_v6_rmt_addr, port); + net_dbg_ratelimited("drop open request from %pI6/%u\n", + &ireq->ir_v6_rmt_addr, port); #endif } diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 9b21ae8b2e31..1829c7fbc77e 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -374,17 +374,19 @@ void tcp_retransmit_timer(struct sock *sk) */ struct inet_sock *inet = inet_sk(sk); if (sk->sk_family == AF_INET) { - LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("Peer %pI4:%u/%u unexpectedly shrunk window %u:%u (repaired)\n"), - &inet->inet_daddr, - ntohs(inet->inet_dport), inet->inet_num, - tp->snd_una, tp->snd_nxt); + net_dbg_ratelimited("Peer %pI4:%u/%u unexpectedly shrunk window %u:%u (repaired)\n", + &inet->inet_daddr, + ntohs(inet->inet_dport), + inet->inet_num, + tp->snd_una, tp->snd_nxt); } #if IS_ENABLED(CONFIG_IPV6) else if (sk->sk_family == AF_INET6) { - LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("Peer %pI6:%u/%u unexpectedly shrunk window %u:%u (repaired)\n"), - &sk->sk_v6_daddr, - ntohs(inet->inet_dport), inet->inet_num, - tp->snd_una, tp->snd_nxt); + net_dbg_ratelimited("Peer %pI6:%u/%u unexpectedly shrunk window %u:%u (repaired)\n", + &sk->sk_v6_daddr, + ntohs(inet->inet_dport), + inet->inet_num, + tp->snd_una, tp->snd_nxt); } #endif if (tcp_time_stamp - tp->rcv_tstamp > TCP_RTO_MAX) { diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index d13751685f44..1b6e9d5fadef 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1051,7 +1051,7 @@ back_from_confirm: /* ... which is an evident application bug. --ANK */ release_sock(sk); - LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("cork app bug 2\n")); + net_dbg_ratelimited("cork app bug 2\n"); err = -EINVAL; goto out; } @@ -1133,7 +1133,7 @@ int udp_sendpage(struct sock *sk, struct page *page, int offset, if (unlikely(!up->pending)) { release_sock(sk); - LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("udp cork app bug 3\n")); + net_dbg_ratelimited("udp cork app bug 3\n"); return -EINVAL; } @@ -1547,8 +1547,8 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) * provided by the application." */ if (up->pcrlen == 0) { /* full coverage was set */ - LIMIT_NETDEBUG(KERN_WARNING "UDPLite: partial coverage %d while full coverage %d requested\n", - UDP_SKB_CB(skb)->cscov, skb->len); + net_dbg_ratelimited("UDPLite: partial coverage %d while full coverage %d requested\n", + UDP_SKB_CB(skb)->cscov, skb->len); goto drop; } /* The next case involves violating the min. coverage requested @@ -1558,8 +1558,8 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) * Therefore the above ...()->partial_cov statement is essential. */ if (UDP_SKB_CB(skb)->cscov < up->pcrlen) { - LIMIT_NETDEBUG(KERN_WARNING "UDPLite: coverage %d too small, need min %d\n", - UDP_SKB_CB(skb)->cscov, up->pcrlen); + net_dbg_ratelimited("UDPLite: coverage %d too small, need min %d\n", + UDP_SKB_CB(skb)->cscov, up->pcrlen); goto drop; } } @@ -1828,11 +1828,11 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, return 0; short_packet: - LIMIT_NETDEBUG(KERN_DEBUG "UDP%s: short packet: From %pI4:%u %d/%d to %pI4:%u\n", - proto == IPPROTO_UDPLITE ? "Lite" : "", - &saddr, ntohs(uh->source), - ulen, skb->len, - &daddr, ntohs(uh->dest)); + net_dbg_ratelimited("UDP%s: short packet: From %pI4:%u %d/%d to %pI4:%u\n", + proto == IPPROTO_UDPLITE ? "Lite" : "", + &saddr, ntohs(uh->source), + ulen, skb->len, + &daddr, ntohs(uh->dest)); goto drop; csum_error: @@ -1840,10 +1840,10 @@ csum_error: * RFC1122: OK. Discards the bad packet silently (as far as * the network is concerned, anyway) as per 4.1.3.4 (MUST). */ - LIMIT_NETDEBUG(KERN_DEBUG "UDP%s: bad checksum. From %pI4:%u to %pI4:%u ulen %d\n", - proto == IPPROTO_UDPLITE ? "Lite" : "", - &saddr, ntohs(uh->source), &daddr, ntohs(uh->dest), - ulen); + net_dbg_ratelimited("UDP%s: bad checksum. From %pI4:%u to %pI4:%u ulen %d\n", + proto == IPPROTO_UDPLITE ? "Lite" : "", + &saddr, ntohs(uh->source), &daddr, ntohs(uh->dest), + ulen); UDP_INC_STATS_BH(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE); drop: UDP_INC_STATS_BH(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 06e897832a7a..251fcb48b216 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1411,10 +1411,8 @@ int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev, if (unlikely(score->addr_type == IPV6_ADDR_ANY || score->addr_type & IPV6_ADDR_MULTICAST)) { - LIMIT_NETDEBUG(KERN_DEBUG - "ADDRCONF: unspecified / multicast address " - "assigned as unicast address on %s", - dev->name); + net_dbg_ratelimited("ADDRCONF: unspecified / multicast address assigned as unicast address on %s", + dev->name); continue; } diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 6d16eb0e0c7f..8ab1989198f6 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -272,10 +272,9 @@ static int ipv6_clear_mutable_options(struct ipv6hdr *iph, int len, int dir) ipv6_rearrange_destopt(iph, exthdr.opth); case NEXTHDR_HOP: if (!zero_out_mutable_opts(exthdr.opth)) { - LIMIT_NETDEBUG( - KERN_WARNING "overrun %sopts\n", - nexthdr == NEXTHDR_HOP ? - "hop" : "dest"); + net_dbg_ratelimited("overrun %sopts\n", + nexthdr == NEXTHDR_HOP ? + "hop" : "dest"); return -EINVAL; } break; diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 5c6996e44b14..cc1139687fd7 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -893,8 +893,8 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk, break; } default: - LIMIT_NETDEBUG(KERN_DEBUG "invalid cmsg type: %d\n", - cmsg->cmsg_type); + net_dbg_ratelimited("invalid cmsg type: %d\n", + cmsg->cmsg_type); err = -EINVAL; goto exit_f; } diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index d21d7b22eebc..d2c2d749b6db 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -286,8 +286,8 @@ static int esp_input_done2(struct sk_buff *skb, int err) err = -EINVAL; padlen = nexthdr[0]; if (padlen + 2 + alen >= elen) { - LIMIT_NETDEBUG(KERN_WARNING "ipsec esp packet is garbage " - "padlen=%d, elen=%d\n", padlen + 2, elen - alen); + net_dbg_ratelimited("ipsec esp packet is garbage padlen=%d, elen=%d\n", + padlen + 2, elen - alen); goto out; } diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 601d896f22d0..a7bbbe45570b 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -184,7 +184,7 @@ static bool ipv6_dest_hao(struct sk_buff *skb, int optoff) int ret; if (opt->dsthao) { - LIMIT_NETDEBUG(KERN_DEBUG "hao duplicated\n"); + net_dbg_ratelimited("hao duplicated\n"); goto discard; } opt->dsthao = opt->dst1; @@ -193,14 +193,14 @@ static bool ipv6_dest_hao(struct sk_buff *skb, int optoff) hao = (struct ipv6_destopt_hao *)(skb_network_header(skb) + optoff); if (hao->length != 16) { - LIMIT_NETDEBUG( - KERN_DEBUG "hao invalid option length = %d\n", hao->length); + net_dbg_ratelimited("hao invalid option length = %d\n", + hao->length); goto discard; } if (!(ipv6_addr_type(&hao->addr) & IPV6_ADDR_UNICAST)) { - LIMIT_NETDEBUG( - KERN_DEBUG "hao is not an unicast addr: %pI6\n", &hao->addr); + net_dbg_ratelimited("hao is not an unicast addr: %pI6\n", + &hao->addr); goto discard; } @@ -551,8 +551,8 @@ static bool ipv6_hop_ra(struct sk_buff *skb, int optoff) memcpy(&IP6CB(skb)->ra, nh + optoff + 2, sizeof(IP6CB(skb)->ra)); return true; } - LIMIT_NETDEBUG(KERN_DEBUG "ipv6_hop_ra: wrong RA length %d\n", - nh[optoff + 1]); + net_dbg_ratelimited("ipv6_hop_ra: wrong RA length %d\n", + nh[optoff + 1]); kfree_skb(skb); return false; } @@ -566,8 +566,8 @@ static bool ipv6_hop_jumbo(struct sk_buff *skb, int optoff) u32 pkt_len; if (nh[optoff + 1] != 4 || (optoff & 3) != 2) { - LIMIT_NETDEBUG(KERN_DEBUG "ipv6_hop_jumbo: wrong jumbo opt length/alignment %d\n", - nh[optoff+1]); + net_dbg_ratelimited("ipv6_hop_jumbo: wrong jumbo opt length/alignment %d\n", + nh[optoff+1]); IP6_INC_STATS_BH(net, ipv6_skb_idev(skb), IPSTATS_MIB_INHDRERRORS); goto drop; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 62c1037d9e83..092934032077 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -338,7 +338,7 @@ static struct dst_entry *icmpv6_route_lookup(struct net *net, * anycast. */ if (((struct rt6_info *)dst)->rt6i_flags & RTF_ANYCAST) { - LIMIT_NETDEBUG(KERN_DEBUG "icmp6_send: acast source\n"); + net_dbg_ratelimited("icmp6_send: acast source\n"); dst_release(dst); return ERR_PTR(-EINVAL); } @@ -452,7 +452,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) * and anycast addresses will be checked later. */ if ((addr_type == IPV6_ADDR_ANY) || (addr_type & IPV6_ADDR_MULTICAST)) { - LIMIT_NETDEBUG(KERN_DEBUG "icmp6_send: addr_any/mcast source\n"); + net_dbg_ratelimited("icmp6_send: addr_any/mcast source\n"); return; } @@ -460,7 +460,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) * Never answer to a ICMP packet. */ if (is_ineligible(skb)) { - LIMIT_NETDEBUG(KERN_DEBUG "icmp6_send: no reply to icmp error\n"); + net_dbg_ratelimited("icmp6_send: no reply to icmp error\n"); return; } @@ -509,7 +509,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) len = skb->len - msg.offset; len = min_t(unsigned int, len, IPV6_MIN_MTU - sizeof(struct ipv6hdr) - sizeof(struct icmp6hdr)); if (len < 0) { - LIMIT_NETDEBUG(KERN_DEBUG "icmp: len problem\n"); + net_dbg_ratelimited("icmp: len problem\n"); goto out_dst_release; } @@ -706,9 +706,8 @@ static int icmpv6_rcv(struct sk_buff *skb) daddr = &ipv6_hdr(skb)->daddr; if (skb_checksum_validate(skb, IPPROTO_ICMPV6, ip6_compute_pseudo)) { - LIMIT_NETDEBUG(KERN_DEBUG - "ICMPv6 checksum failed [%pI6c > %pI6c]\n", - saddr, daddr); + net_dbg_ratelimited("ICMPv6 checksum failed [%pI6c > %pI6c]\n", + saddr, daddr); goto csum_error; } @@ -781,7 +780,7 @@ static int icmpv6_rcv(struct sk_buff *skb) if (type & ICMPV6_INFOMSG_MASK) break; - LIMIT_NETDEBUG(KERN_DEBUG "icmpv6: msg of unknown type\n"); + net_dbg_ratelimited("icmpv6: msg of unknown type\n"); /* * error of unknown type. diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c index f61429d391d3..b9779d441b12 100644 --- a/net/ipv6/mip6.c +++ b/net/ipv6/mip6.c @@ -97,16 +97,17 @@ static int mip6_mh_filter(struct sock *sk, struct sk_buff *skb) return -1; if (mh->ip6mh_hdrlen < mip6_mh_len(mh->ip6mh_type)) { - LIMIT_NETDEBUG(KERN_DEBUG "mip6: MH message too short: %d vs >=%d\n", - mh->ip6mh_hdrlen, mip6_mh_len(mh->ip6mh_type)); + net_dbg_ratelimited("mip6: MH message too short: %d vs >=%d\n", + mh->ip6mh_hdrlen, + mip6_mh_len(mh->ip6mh_type)); mip6_param_prob(skb, 0, offsetof(struct ip6_mh, ip6mh_hdrlen) + skb_network_header_len(skb)); return -1; } if (mh->ip6mh_proto != IPPROTO_NONE) { - LIMIT_NETDEBUG(KERN_DEBUG "mip6: MH invalid payload proto = %d\n", - mh->ip6mh_proto); + net_dbg_ratelimited("mip6: MH invalid payload proto = %d\n", + mh->ip6mh_proto); mip6_param_prob(skb, 0, offsetof(struct ip6_mh, ip6mh_proto) + skb_network_header_len(skb)); return -1; @@ -288,7 +289,7 @@ static int mip6_destopt_offset(struct xfrm_state *x, struct sk_buff *skb, * XXX: packet if HAO exists. */ if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0) { - LIMIT_NETDEBUG(KERN_WARNING "mip6: hao exists already, override\n"); + net_dbg_ratelimited("mip6: hao exists already, override\n"); return offset; } diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index d38e6a8d8b9f..398377a9d018 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -36,7 +36,7 @@ int ip6_route_me_harder(struct sk_buff *skb) err = dst->error; if (err) { IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); - LIMIT_NETDEBUG(KERN_DEBUG "ip6_route_me_harder: No more route.\n"); + net_dbg_ratelimited("ip6_route_me_harder: No more route\n"); dst_release(dst); return err; } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index d1fe36274906..0ba3de4f2368 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -660,15 +660,13 @@ int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) if ((is_udplite & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) { if (up->pcrlen == 0) { /* full coverage was set */ - LIMIT_NETDEBUG(KERN_WARNING "UDPLITE6: partial coverage" - " %d while full coverage %d requested\n", - UDP_SKB_CB(skb)->cscov, skb->len); + net_dbg_ratelimited("UDPLITE6: partial coverage %d while full coverage %d requested\n", + UDP_SKB_CB(skb)->cscov, skb->len); goto drop; } if (UDP_SKB_CB(skb)->cscov < up->pcrlen) { - LIMIT_NETDEBUG(KERN_WARNING "UDPLITE6: coverage %d " - "too small, need min %d\n", - UDP_SKB_CB(skb)->cscov, up->pcrlen); + net_dbg_ratelimited("UDPLITE6: coverage %d too small, need min %d\n", + UDP_SKB_CB(skb)->cscov, up->pcrlen); goto drop; } } @@ -761,9 +759,9 @@ static void udp6_csum_zero_error(struct sk_buff *skb) /* RFC 2460 section 8.1 says that we SHOULD log * this error. Well, it is reasonable. */ - LIMIT_NETDEBUG(KERN_INFO "IPv6: udp checksum is 0 for [%pI6c]:%u->[%pI6c]:%u\n", - &ipv6_hdr(skb)->saddr, ntohs(udp_hdr(skb)->source), - &ipv6_hdr(skb)->daddr, ntohs(udp_hdr(skb)->dest)); + net_dbg_ratelimited("IPv6: udp checksum is 0 for [%pI6c]:%u->[%pI6c]:%u\n", + &ipv6_hdr(skb)->saddr, ntohs(udp_hdr(skb)->source), + &ipv6_hdr(skb)->daddr, ntohs(udp_hdr(skb)->dest)); } /* @@ -931,14 +929,11 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, return 0; short_packet: - LIMIT_NETDEBUG(KERN_DEBUG "UDP%sv6: short packet: From [%pI6c]:%u %d/%d to [%pI6c]:%u\n", - proto == IPPROTO_UDPLITE ? "-Lite" : "", - saddr, - ntohs(uh->source), - ulen, - skb->len, - daddr, - ntohs(uh->dest)); + net_dbg_ratelimited("UDP%sv6: short packet: From [%pI6c]:%u %d/%d to [%pI6c]:%u\n", + proto == IPPROTO_UDPLITE ? "-Lite" : "", + saddr, ntohs(uh->source), + ulen, skb->len, + daddr, ntohs(uh->dest)); goto discard; csum_error: UDP6_INC_STATS_BH(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE); @@ -1290,7 +1285,7 @@ back_from_confirm: /* ... which is an evident application bug. --ANK */ release_sock(sk); - LIMIT_NETDEBUG(KERN_DEBUG "udp cork app bug 2\n"); + net_dbg_ratelimited("udp cork app bug 2\n"); err = -EINVAL; goto out; } diff --git a/net/phonet/af_phonet.c b/net/phonet/af_phonet.c index 5a940dbd74a3..32ab87d34828 100644 --- a/net/phonet/af_phonet.c +++ b/net/phonet/af_phonet.c @@ -426,16 +426,17 @@ static int phonet_rcv(struct sk_buff *skb, struct net_device *dev, out_dev = phonet_route_output(net, pn_sockaddr_get_addr(&sa)); if (!out_dev) { - LIMIT_NETDEBUG(KERN_WARNING"No Phonet route to %02X\n", - pn_sockaddr_get_addr(&sa)); + net_dbg_ratelimited("No Phonet route to %02X\n", + pn_sockaddr_get_addr(&sa)); goto out; } __skb_push(skb, sizeof(struct phonethdr)); skb->dev = out_dev; if (out_dev == dev) { - LIMIT_NETDEBUG(KERN_ERR"Phonet loop to %02X on %s\n", - pn_sockaddr_get_addr(&sa), dev->name); + net_dbg_ratelimited("Phonet loop to %02X on %s\n", + pn_sockaddr_get_addr(&sa), + dev->name); goto out_dev; } /* Some drivers (e.g. TUN) do not allocate HW header space */ diff --git a/net/phonet/pep-gprs.c b/net/phonet/pep-gprs.c index e9a83a637185..fa8237fdc57b 100644 --- a/net/phonet/pep-gprs.c +++ b/net/phonet/pep-gprs.c @@ -203,8 +203,7 @@ static netdev_tx_t gprs_xmit(struct sk_buff *skb, struct net_device *dev) len = skb->len; err = pep_write(sk, skb); if (err) { - LIMIT_NETDEBUG(KERN_WARNING"%s: TX error (%d)\n", - dev->name, err); + net_dbg_ratelimited("%s: TX error (%d)\n", dev->name, err); dev->stats.tx_aborted_errors++; dev->stats.tx_errors++; } else { diff --git a/net/phonet/pep.c b/net/phonet/pep.c index 44b2123e22b8..9cd069dfaf65 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -272,8 +272,8 @@ static int pipe_rcv_status(struct sock *sk, struct sk_buff *skb) hdr = pnp_hdr(skb); if (hdr->data[0] != PN_PEP_TYPE_COMMON) { - LIMIT_NETDEBUG(KERN_DEBUG"Phonet unknown PEP type: %u\n", - (unsigned int)hdr->data[0]); + net_dbg_ratelimited("Phonet unknown PEP type: %u\n", + (unsigned int)hdr->data[0]); return -EOPNOTSUPP; } @@ -304,8 +304,8 @@ static int pipe_rcv_status(struct sock *sk, struct sk_buff *skb) break; default: - LIMIT_NETDEBUG(KERN_DEBUG"Phonet unknown PEP indication: %u\n", - (unsigned int)hdr->data[1]); + net_dbg_ratelimited("Phonet unknown PEP indication: %u\n", + (unsigned int)hdr->data[1]); return -EOPNOTSUPP; } if (wake) @@ -451,8 +451,8 @@ static int pipe_do_rcv(struct sock *sk, struct sk_buff *skb) break; default: - LIMIT_NETDEBUG(KERN_DEBUG"Phonet unknown PEP message: %u\n", - hdr->message_id); + net_dbg_ratelimited("Phonet unknown PEP message: %u\n", + hdr->message_id); err = -EINVAL; } out: -- cgit v1.2.3