From c10d9310edf5aa4a676991139d1a43ec7d87e56b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 29 Apr 2016 14:16:47 -0700 Subject: [PATCH 1/7] tcp: do not assume TCP code is non preemptible We want to to make TCP stack preemptible, as draining prequeue and backlog queues can take lot of time. Many SNMP updates were assuming that BH (and preemption) was disabled. Need to convert some __NET_INC_STATS() calls to NET_INC_STATS() and some __TCP_INC_STATS() to TCP_INC_STATS() Before using this_cpu_ptr(net->ipv4.tcp_sk) in tcp_v4_send_reset() and tcp_v4_send_ack(), we add an explicit preempt disabled section. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- net/ipv4/tcp.c | 2 +- net/ipv4/tcp_cdg.c | 20 ++++----- net/ipv4/tcp_cubic.c | 20 ++++----- net/ipv4/tcp_fastopen.c | 12 ++--- net/ipv4/tcp_input.c | 96 ++++++++++++++++++++-------------------- net/ipv4/tcp_ipv4.c | 14 +++--- net/ipv4/tcp_minisocks.c | 2 +- net/ipv4/tcp_output.c | 11 +++-- net/ipv4/tcp_recovery.c | 4 +- net/ipv4/tcp_timer.c | 10 +++-- net/ipv6/tcp_ipv6.c | 12 ++--- 11 files changed, 104 insertions(+), 99 deletions(-) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index cb4d1cabb42c4..b24c6ed4a04f3 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3095,7 +3095,7 @@ void tcp_done(struct sock *sk) struct request_sock *req = tcp_sk(sk)->fastopen_rsk; if (sk->sk_state == TCP_SYN_SENT || sk->sk_state == TCP_SYN_RECV) - __TCP_INC_STATS(sock_net(sk), TCP_MIB_ATTEMPTFAILS); + TCP_INC_STATS(sock_net(sk), TCP_MIB_ATTEMPTFAILS); tcp_set_state(sk, TCP_CLOSE); tcp_clear_xmit_timers(sk); diff --git a/net/ipv4/tcp_cdg.c b/net/ipv4/tcp_cdg.c index 3c00208c37f46..ccce8a55f1e1e 100644 --- a/net/ipv4/tcp_cdg.c +++ b/net/ipv4/tcp_cdg.c @@ -155,11 +155,11 @@ static void tcp_cdg_hystart_update(struct sock *sk) ca->last_ack = now_us; if (after(now_us, ca->round_start + base_owd)) { - __NET_INC_STATS(sock_net(sk), - LINUX_MIB_TCPHYSTARTTRAINDETECT); - __NET_ADD_STATS(sock_net(sk), - LINUX_MIB_TCPHYSTARTTRAINCWND, - tp->snd_cwnd); + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPHYSTARTTRAINDETECT); + NET_ADD_STATS(sock_net(sk), + LINUX_MIB_TCPHYSTARTTRAINCWND, + tp->snd_cwnd); tp->snd_ssthresh = tp->snd_cwnd; return; } @@ -174,11 +174,11 @@ static void tcp_cdg_hystart_update(struct sock *sk) 125U); if (ca->rtt.min > thresh) { - __NET_INC_STATS(sock_net(sk), - LINUX_MIB_TCPHYSTARTDELAYDETECT); - __NET_ADD_STATS(sock_net(sk), - LINUX_MIB_TCPHYSTARTDELAYCWND, - tp->snd_cwnd); + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPHYSTARTDELAYDETECT); + NET_ADD_STATS(sock_net(sk), + LINUX_MIB_TCPHYSTARTDELAYCWND, + tp->snd_cwnd); tp->snd_ssthresh = tp->snd_cwnd; } } diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 59155af9de5d4..0ce946e395e1b 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -402,11 +402,11 @@ static void hystart_update(struct sock *sk, u32 delay) ca->last_ack = now; if ((s32)(now - ca->round_start) > ca->delay_min >> 4) { ca->found |= HYSTART_ACK_TRAIN; - __NET_INC_STATS(sock_net(sk), - LINUX_MIB_TCPHYSTARTTRAINDETECT); - __NET_ADD_STATS(sock_net(sk), - LINUX_MIB_TCPHYSTARTTRAINCWND, - tp->snd_cwnd); + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPHYSTARTTRAINDETECT); + NET_ADD_STATS(sock_net(sk), + LINUX_MIB_TCPHYSTARTTRAINCWND, + tp->snd_cwnd); tp->snd_ssthresh = tp->snd_cwnd; } } @@ -423,11 +423,11 @@ static void hystart_update(struct sock *sk, u32 delay) if (ca->curr_rtt > ca->delay_min + HYSTART_DELAY_THRESH(ca->delay_min >> 3)) { ca->found |= HYSTART_DELAY; - __NET_INC_STATS(sock_net(sk), - LINUX_MIB_TCPHYSTARTDELAYDETECT); - __NET_ADD_STATS(sock_net(sk), - LINUX_MIB_TCPHYSTARTDELAYCWND, - tp->snd_cwnd); + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPHYSTARTDELAYDETECT); + NET_ADD_STATS(sock_net(sk), + LINUX_MIB_TCPHYSTARTDELAYCWND, + tp->snd_cwnd); tp->snd_ssthresh = tp->snd_cwnd; } } diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index a1498d507e42b..54d9f9b0120fe 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -255,9 +255,9 @@ static bool tcp_fastopen_queue_check(struct sock *sk) spin_lock(&fastopenq->lock); req1 = fastopenq->rskq_rst_head; if (!req1 || time_after(req1->rsk_timer.expires, jiffies)) { - spin_unlock(&fastopenq->lock); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENLISTENOVERFLOW); + spin_unlock(&fastopenq->lock); return false; } fastopenq->rskq_rst_head = req1->dl_next; @@ -282,7 +282,7 @@ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, struct sock *child; if (foc->len == 0) /* Client requests a cookie */ - __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENCOOKIEREQD); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENCOOKIEREQD); if (!((sysctl_tcp_fastopen & TFO_SERVER_ENABLE) && (syn_data || foc->len >= 0) && @@ -311,13 +311,13 @@ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, child = tcp_fastopen_create_child(sk, skb, dst, req); if (child) { foc->len = -1; - __NET_INC_STATS(sock_net(sk), - LINUX_MIB_TCPFASTOPENPASSIVE); + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPFASTOPENPASSIVE); return child; } - __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVEFAIL); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVEFAIL); } else if (foc->len > 0) /* Client presents an invalid cookie */ - __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVEFAIL); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVEFAIL); valid_foc.exp = foc->exp; *foc = valid_foc; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 1fb19c91e0919..ac85fb42a5a24 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -869,7 +869,7 @@ static void tcp_update_reordering(struct sock *sk, const int metric, else mib_idx = LINUX_MIB_TCPSACKREORDER; - __NET_INC_STATS(sock_net(sk), mib_idx); + NET_INC_STATS(sock_net(sk), mib_idx); #if FASTRETRANS_DEBUG > 1 pr_debug("Disorder%d %d %u f%u s%u rr%d\n", tp->rx_opt.sack_ok, inet_csk(sk)->icsk_ca_state, @@ -1062,7 +1062,7 @@ static bool tcp_check_dsack(struct sock *sk, const struct sk_buff *ack_skb, if (before(start_seq_0, TCP_SKB_CB(ack_skb)->ack_seq)) { dup_sack = true; tcp_dsack_seen(tp); - __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPDSACKRECV); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPDSACKRECV); } else if (num_sacks > 1) { u32 end_seq_1 = get_unaligned_be32(&sp[1].end_seq); u32 start_seq_1 = get_unaligned_be32(&sp[1].start_seq); @@ -1071,7 +1071,7 @@ static bool tcp_check_dsack(struct sock *sk, const struct sk_buff *ack_skb, !before(start_seq_0, start_seq_1)) { dup_sack = true; tcp_dsack_seen(tp); - __NET_INC_STATS(sock_net(sk), + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPDSACKOFORECV); } } @@ -1289,7 +1289,7 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, if (skb->len > 0) { BUG_ON(!tcp_skb_pcount(skb)); - __NET_INC_STATS(sock_net(sk), LINUX_MIB_SACKSHIFTED); + NET_INC_STATS(sock_net(sk), LINUX_MIB_SACKSHIFTED); return false; } @@ -1314,7 +1314,7 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, tcp_unlink_write_queue(skb, sk); sk_wmem_free_skb(sk, skb); - __NET_INC_STATS(sock_net(sk), LINUX_MIB_SACKMERGED); + NET_INC_STATS(sock_net(sk), LINUX_MIB_SACKMERGED); return true; } @@ -1473,7 +1473,7 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb, return skb; fallback: - __NET_INC_STATS(sock_net(sk), LINUX_MIB_SACKSHIFTFALLBACK); + NET_INC_STATS(sock_net(sk), LINUX_MIB_SACKSHIFTFALLBACK); return NULL; } @@ -1661,7 +1661,7 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, mib_idx = LINUX_MIB_TCPSACKDISCARD; } - __NET_INC_STATS(sock_net(sk), mib_idx); + NET_INC_STATS(sock_net(sk), mib_idx); if (i == 0) first_sack_index = -1; continue; @@ -1913,7 +1913,7 @@ void tcp_enter_loss(struct sock *sk) skb = tcp_write_queue_head(sk); is_reneg = skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED); if (is_reneg) { - __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSACKRENEGING); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSACKRENEGING); tp->sacked_out = 0; tp->fackets_out = 0; } @@ -2399,7 +2399,7 @@ static bool tcp_try_undo_recovery(struct sock *sk) else mib_idx = LINUX_MIB_TCPFULLUNDO; - __NET_INC_STATS(sock_net(sk), mib_idx); + NET_INC_STATS(sock_net(sk), mib_idx); } if (tp->snd_una == tp->high_seq && tcp_is_reno(tp)) { /* Hold old state until something *above* high_seq @@ -2421,7 +2421,7 @@ static bool tcp_try_undo_dsack(struct sock *sk) if (tp->undo_marker && !tp->undo_retrans) { DBGUNDO(sk, "D-SACK"); tcp_undo_cwnd_reduction(sk, false); - __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPDSACKUNDO); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPDSACKUNDO); return true; } return false; @@ -2436,9 +2436,9 @@ static bool tcp_try_undo_loss(struct sock *sk, bool frto_undo) tcp_undo_cwnd_reduction(sk, true); DBGUNDO(sk, "partial loss"); - __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPLOSSUNDO); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPLOSSUNDO); if (frto_undo) - __NET_INC_STATS(sock_net(sk), + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSPURIOUSRTOS); inet_csk(sk)->icsk_retransmits = 0; if (frto_undo || tcp_is_sack(tp)) @@ -2563,7 +2563,7 @@ static void tcp_mtup_probe_failed(struct sock *sk) icsk->icsk_mtup.search_high = icsk->icsk_mtup.probe_size - 1; icsk->icsk_mtup.probe_size = 0; - __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMTUPFAIL); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMTUPFAIL); } static void tcp_mtup_probe_success(struct sock *sk) @@ -2583,7 +2583,7 @@ static void tcp_mtup_probe_success(struct sock *sk) icsk->icsk_mtup.search_low = icsk->icsk_mtup.probe_size; icsk->icsk_mtup.probe_size = 0; tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); - __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMTUPSUCCESS); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMTUPSUCCESS); } /* Do a simple retransmit without using the backoff mechanisms in @@ -2647,7 +2647,7 @@ static void tcp_enter_recovery(struct sock *sk, bool ece_ack) else mib_idx = LINUX_MIB_TCPSACKRECOVERY; - __NET_INC_STATS(sock_net(sk), mib_idx); + NET_INC_STATS(sock_net(sk), mib_idx); tp->prior_ssthresh = 0; tcp_init_undo(tp); @@ -2740,7 +2740,7 @@ static bool tcp_try_undo_partial(struct sock *sk, const int acked) DBGUNDO(sk, "partial recovery"); tcp_undo_cwnd_reduction(sk, true); - __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPPARTIALUNDO); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPPARTIALUNDO); tcp_try_keep_open(sk); return true; } @@ -3434,7 +3434,7 @@ bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb, s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time); if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) { - __NET_INC_STATS(net, mib_idx); + NET_INC_STATS(net, mib_idx); return true; /* rate-limited: don't send yet! */ } } @@ -3467,7 +3467,7 @@ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb) challenge_count = 0; } if (++challenge_count <= sysctl_tcp_challenge_ack_limit) { - __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPCHALLENGEACK); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPCHALLENGEACK); tcp_send_ack(sk); } } @@ -3516,7 +3516,7 @@ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag) tcp_set_ca_state(sk, TCP_CA_CWR); tcp_end_cwnd_reduction(sk); tcp_try_keep_open(sk); - __NET_INC_STATS(sock_net(sk), + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPLOSSPROBERECOVERY); } else if (!(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP | FLAG_DATA_SACKED))) { @@ -3621,14 +3621,14 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) tcp_in_ack_event(sk, CA_ACK_WIN_UPDATE); - __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHPACKS); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHPACKS); } else { u32 ack_ev_flags = CA_ACK_SLOWPATH; if (ack_seq != TCP_SKB_CB(skb)->end_seq) flag |= FLAG_DATA; else - __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPPUREACKS); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPPUREACKS); flag |= tcp_ack_update_window(sk, skb, ack, ack_seq); @@ -4131,7 +4131,7 @@ static void tcp_dsack_set(struct sock *sk, u32 seq, u32 end_seq) else mib_idx = LINUX_MIB_TCPDSACKOFOSENT; - __NET_INC_STATS(sock_net(sk), mib_idx); + NET_INC_STATS(sock_net(sk), mib_idx); tp->rx_opt.dsack = 1; tp->duplicate_sack[0].start_seq = seq; @@ -4155,7 +4155,7 @@ static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb) if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq && before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) { - __NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOST); + NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOST); tcp_enter_quickack_mode(sk); if (tcp_is_sack(tp) && sysctl_tcp_dsack) { @@ -4305,7 +4305,7 @@ static bool tcp_try_coalesce(struct sock *sk, atomic_add(delta, &sk->sk_rmem_alloc); sk_mem_charge(sk, delta); - __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVCOALESCE); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVCOALESCE); TCP_SKB_CB(to)->end_seq = TCP_SKB_CB(from)->end_seq; TCP_SKB_CB(to)->ack_seq = TCP_SKB_CB(from)->ack_seq; TCP_SKB_CB(to)->tcp_flags |= TCP_SKB_CB(from)->tcp_flags; @@ -4393,7 +4393,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) tcp_ecn_check_ce(tp, skb); if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) { - __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFODROP); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFODROP); tcp_drop(sk, skb); return; } @@ -4402,7 +4402,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) tp->pred_flags = 0; inet_csk_schedule_ack(sk); - __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOQUEUE); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOQUEUE); SOCK_DEBUG(sk, "out of order segment: rcv_next %X seq %X - %X\n", tp->rcv_nxt, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq); @@ -4457,7 +4457,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) if (skb1 && before(seq, TCP_SKB_CB(skb1)->end_seq)) { if (!after(end_seq, TCP_SKB_CB(skb1)->end_seq)) { /* All the bits are present. Drop. */ - __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOMERGE); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOMERGE); tcp_drop(sk, skb); skb = NULL; tcp_dsack_set(sk, seq, end_seq); @@ -4496,7 +4496,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) __skb_unlink(skb1, &tp->out_of_order_queue); tcp_dsack_extend(sk, TCP_SKB_CB(skb1)->seq, TCP_SKB_CB(skb1)->end_seq); - __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOMERGE); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOMERGE); tcp_drop(sk, skb1); } @@ -4661,7 +4661,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) if (!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) { /* A retransmit, 2nd most common case. Force an immediate ack. */ - __NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOST); + NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOST); tcp_dsack_set(sk, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq); out_of_window: @@ -4707,7 +4707,7 @@ static struct sk_buff *tcp_collapse_one(struct sock *sk, struct sk_buff *skb, __skb_unlink(skb, list); __kfree_skb(skb); - __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVCOLLAPSED); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVCOLLAPSED); return next; } @@ -4866,7 +4866,7 @@ static bool tcp_prune_ofo_queue(struct sock *sk) bool res = false; if (!skb_queue_empty(&tp->out_of_order_queue)) { - __NET_INC_STATS(sock_net(sk), LINUX_MIB_OFOPRUNED); + NET_INC_STATS(sock_net(sk), LINUX_MIB_OFOPRUNED); __skb_queue_purge(&tp->out_of_order_queue); /* Reset SACK state. A conforming SACK implementation will @@ -4895,7 +4895,7 @@ static int tcp_prune_queue(struct sock *sk) SOCK_DEBUG(sk, "prune_queue: c=%x\n", tp->copied_seq); - __NET_INC_STATS(sock_net(sk), LINUX_MIB_PRUNECALLED); + NET_INC_STATS(sock_net(sk), LINUX_MIB_PRUNECALLED); if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) tcp_clamp_window(sk); @@ -4925,7 +4925,7 @@ static int tcp_prune_queue(struct sock *sk) * drop receive data on the floor. It will get retransmitted * and hopefully then we'll have sufficient space. */ - __NET_INC_STATS(sock_net(sk), LINUX_MIB_RCVPRUNED); + NET_INC_STATS(sock_net(sk), LINUX_MIB_RCVPRUNED); /* Massive buffer overcommit. */ tp->pred_flags = 0; @@ -5184,7 +5184,7 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, if (tcp_fast_parse_options(skb, th, tp) && tp->rx_opt.saw_tstamp && tcp_paws_discard(sk, skb)) { if (!th->rst) { - __NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED); + NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED); if (!tcp_oow_rate_limited(sock_net(sk), skb, LINUX_MIB_TCPACKSKIPPEDPAWS, &tp->last_oow_ack_time)) @@ -5236,8 +5236,8 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, if (th->syn) { syn_challenge: if (syn_inerr) - __TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); - __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNCHALLENGE); + TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNCHALLENGE); tcp_send_challenge_ack(sk, skb); goto discard; } @@ -5352,7 +5352,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb, tcp_data_snd_check(sk); return; } else { /* Header too small */ - __TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); + TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); goto discard; } } else { @@ -5380,7 +5380,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb, __skb_pull(skb, tcp_header_len); tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq); - __NET_INC_STATS(sock_net(sk), + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHPHITSTOUSER); eaten = 1; } @@ -5403,7 +5403,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb, tcp_rcv_rtt_measure_ts(sk, skb); - __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHPHITS); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHPHITS); /* Bulk data transfer: receiver */ eaten = tcp_queue_rcv(sk, skb, tcp_header_len, @@ -5460,8 +5460,8 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb, return; csum_error: - __TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS); - __TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); + TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS); + TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); discard: tcp_drop(sk, skb); @@ -5553,13 +5553,13 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, break; } tcp_rearm_rto(sk); - __NET_INC_STATS(sock_net(sk), + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVEFAIL); return true; } tp->syn_data_acked = tp->syn_data; if (tp->syn_data_acked) - __NET_INC_STATS(sock_net(sk), + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVE); tcp_fastopen_add_skb(sk, synack); @@ -5595,7 +5595,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && !between(tp->rx_opt.rcv_tsecr, tp->retrans_stamp, tcp_time_stamp)) { - __NET_INC_STATS(sock_net(sk), + NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSACTIVEREJECTED); goto reset_and_undo; } @@ -5965,7 +5965,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq && after(TCP_SKB_CB(skb)->end_seq - th->fin, tp->rcv_nxt))) { tcp_done(sk); - __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONDATA); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONDATA); return 1; } @@ -6022,7 +6022,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) if (sk->sk_shutdown & RCV_SHUTDOWN) { if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq && after(TCP_SKB_CB(skb)->end_seq - th->fin, tp->rcv_nxt)) { - __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONDATA); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONDATA); tcp_reset(sk); return 1; } @@ -6224,7 +6224,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, * timeout. */ if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) { - __NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); + NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); goto drop; } @@ -6271,7 +6271,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, if (dst && strict && !tcp_peer_is_proven(req, dst, true, tmp_opt.saw_tstamp)) { - __NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED); + NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED); goto drop_and_release; } } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 87b173b563b0f..761bc492c5e30 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -692,6 +692,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) offsetof(struct inet_timewait_sock, tw_bound_dev_if)); arg.tos = ip_hdr(skb)->tos; + preempt_disable(); ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk), skb, &TCP_SKB_CB(skb)->header.h4.opt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, @@ -699,6 +700,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); __TCP_INC_STATS(net, TCP_MIB_OUTRSTS); + preempt_enable(); #ifdef CONFIG_TCP_MD5SIG out: @@ -774,12 +776,14 @@ static void tcp_v4_send_ack(struct net *net, if (oif) arg.bound_dev_if = oif; arg.tos = tos; + preempt_disable(); ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk), skb, &TCP_SKB_CB(skb)->header.h4.opt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len); __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); + preempt_enable(); } static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) @@ -1151,12 +1155,12 @@ static bool tcp_v4_inbound_md5_hash(const struct sock *sk, return false; if (hash_expected && !hash_location) { - __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND); return true; } if (!hash_expected && hash_location) { - __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED); return true; } @@ -1342,7 +1346,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, return newsk; exit_overflow: - __NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); + NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); exit_nonewsk: dst_release(dst); exit: @@ -1432,8 +1436,8 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) return 0; csum_err: - __TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS); - __TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); + TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS); + TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); goto discard; } EXPORT_SYMBOL(tcp_v4_do_rcv); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index ffbfecdae471f..4b95ec4ed2c8f 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -337,7 +337,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) * socket up. We've got bigger problems than * non-graceful socket closings. */ - __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPTIMEWAITOVERFLOW); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPTIMEWAITOVERFLOW); } tcp_update_metrics(sk); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 1a487ff95d4c0..25d527922b18d 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2221,14 +2221,13 @@ bool tcp_schedule_loss_probe(struct sock *sk) /* Thanks to skb fast clones, we can detect if a prior transmit of * a packet is still in a qdisc or driver queue. * In this case, there is very little point doing a retransmit ! - * Note: This is called from BH context only. */ static bool skb_still_in_host_queue(const struct sock *sk, const struct sk_buff *skb) { if (unlikely(skb_fclone_busy(sk, skb))) { - __NET_INC_STATS(sock_net(sk), - LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES); + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES); return true; } return false; @@ -2290,7 +2289,7 @@ void tcp_send_loss_probe(struct sock *sk) tp->tlp_high_seq = tp->snd_nxt; probe_sent: - __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPLOSSPROBES); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPLOSSPROBES); /* Reset s.t. tcp_rearm_rto will restart timer from now */ inet_csk(sk)->icsk_pending = 0; rearm_timer: @@ -2699,7 +2698,7 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) tp->retrans_stamp = tcp_skb_timestamp(skb); } else if (err != -EBUSY) { - __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL); } if (tp->undo_retrans < 0) @@ -2823,7 +2822,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk) if (tcp_retransmit_skb(sk, skb, segs)) return; - __NET_INC_STATS(sock_net(sk), mib_idx); + NET_INC_STATS(sock_net(sk), mib_idx); if (tcp_in_cwnd_reduction(sk)) tp->prr_out += tcp_skb_pcount(skb); diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c index e0d0afaf15be8..e36df4fcfeba3 100644 --- a/net/ipv4/tcp_recovery.c +++ b/net/ipv4/tcp_recovery.c @@ -65,8 +65,8 @@ int tcp_rack_mark_lost(struct sock *sk) if (scb->sacked & TCPCB_SACKED_RETRANS) { scb->sacked &= ~TCPCB_SACKED_RETRANS; tp->retrans_out -= tcp_skb_pcount(skb); - __NET_INC_STATS(sock_net(sk), - LINUX_MIB_TCPLOSTRETRANSMIT); + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPLOSTRETRANSMIT); } } else if (!(scb->sacked & TCPCB_RETRANS)) { /* Original data are sent sequentially so stop early diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 35f643d8ffbbd..debdd8b33e694 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -162,8 +162,8 @@ static int tcp_write_timeout(struct sock *sk) if (tp->syn_fastopen || tp->syn_data) tcp_fastopen_cache_set(sk, 0, NULL, true, 0); if (tp->syn_data && icsk->icsk_retransmits == 1) - __NET_INC_STATS(sock_net(sk), - LINUX_MIB_TCPFASTOPENACTIVEFAIL); + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPFASTOPENACTIVEFAIL); } retry_until = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries; syn_set = true; @@ -178,8 +178,8 @@ static int tcp_write_timeout(struct sock *sk) tp->bytes_acked <= tp->rx_opt.mss_clamp) { tcp_fastopen_cache_set(sk, 0, NULL, true, 0); if (icsk->icsk_retransmits == net->ipv4.sysctl_tcp_retries1) - __NET_INC_STATS(sock_net(sk), - LINUX_MIB_TCPFASTOPENACTIVEFAIL); + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPFASTOPENACTIVEFAIL); } /* Black hole detection */ tcp_mtu_probing(icsk, sk); @@ -209,6 +209,7 @@ static int tcp_write_timeout(struct sock *sk) return 0; } +/* Called with BH disabled */ void tcp_delack_timer_handler(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); @@ -493,6 +494,7 @@ void tcp_retransmit_timer(struct sock *sk) out:; } +/* Called with BH disabled */ void tcp_write_timer_handler(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 52914714b923b..7bdc9c9c231b9 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -649,12 +649,12 @@ static bool tcp_v6_inbound_md5_hash(const struct sock *sk, return false; if (hash_expected && !hash_location) { - __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND); return true; } if (!hash_expected && hash_location) { - __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED); return true; } @@ -825,9 +825,9 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 if (!IS_ERR(dst)) { skb_dst_set(buff, dst); ip6_xmit(ctl_sk, buff, &fl6, NULL, tclass); - __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); + TCP_INC_STATS(net, TCP_MIB_OUTSEGS); if (rst) - __TCP_INC_STATS(net, TCP_MIB_OUTRSTS); + TCP_INC_STATS(net, TCP_MIB_OUTRSTS); return; } @@ -1276,8 +1276,8 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) kfree_skb(skb); return 0; csum_err: - __TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS); - __TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); + TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS); + TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); goto discard; From fb3477c0f45aad5dfb2de559949872770e6cd431 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 29 Apr 2016 14:16:48 -0700 Subject: [PATCH 2/7] tcp: do not block bh during prequeue processing AFAIK, nothing in current TCP stack absolutely wants BH being disabled once socket is owned by a thread running in process context. As mentioned in my prior patch ("tcp: give prequeue mode some care"), processing a batch of packets might take time, better not block BH at all. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- net/ipv4/tcp.c | 4 ---- net/ipv4/tcp_input.c | 30 ++---------------------------- 2 files changed, 2 insertions(+), 32 deletions(-) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index b24c6ed4a04f3..4787f86ae64cf 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1449,12 +1449,8 @@ static void tcp_prequeue_process(struct sock *sk) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPPREQUEUED); - /* RX process wants to run with disabled BHs, though it is not - * necessary */ - local_bh_disable(); while ((skb = __skb_dequeue(&tp->ucopy.prequeue)) != NULL) sk_backlog_rcv(sk, skb); - local_bh_enable(); /* Clear memory counter. */ tp->ucopy.memory = 0; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index ac85fb42a5a24..6171f92be0903 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4611,14 +4611,12 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) __set_current_state(TASK_RUNNING); - local_bh_enable(); if (!skb_copy_datagram_msg(skb, 0, tp->ucopy.msg, chunk)) { tp->ucopy.len -= chunk; tp->copied_seq += chunk; eaten = (chunk == skb->len); tcp_rcv_space_adjust(sk); } - local_bh_disable(); } if (eaten <= 0) { @@ -5134,7 +5132,6 @@ static int tcp_copy_to_iovec(struct sock *sk, struct sk_buff *skb, int hlen) int chunk = skb->len - hlen; int err; - local_bh_enable(); if (skb_csum_unnecessary(skb)) err = skb_copy_datagram_msg(skb, hlen, tp->ucopy.msg, chunk); else @@ -5146,32 +5143,9 @@ static int tcp_copy_to_iovec(struct sock *sk, struct sk_buff *skb, int hlen) tcp_rcv_space_adjust(sk); } - local_bh_disable(); return err; } -static __sum16 __tcp_checksum_complete_user(struct sock *sk, - struct sk_buff *skb) -{ - __sum16 result; - - if (sock_owned_by_user(sk)) { - local_bh_enable(); - result = __tcp_checksum_complete(skb); - local_bh_disable(); - } else { - result = __tcp_checksum_complete(skb); - } - return result; -} - -static inline bool tcp_checksum_complete_user(struct sock *sk, - struct sk_buff *skb) -{ - return !skb_csum_unnecessary(skb) && - __tcp_checksum_complete_user(sk, skb); -} - /* Does PAWS and seqno based validation of an incoming segment, flags will * play significant role here. */ @@ -5386,7 +5360,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb, } } if (!eaten) { - if (tcp_checksum_complete_user(sk, skb)) + if (tcp_checksum_complete(skb)) goto csum_error; if ((int)skb->truesize > sk->sk_forward_alloc) @@ -5430,7 +5404,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb, } slow_path: - if (len < (th->doff << 2) || tcp_checksum_complete_user(sk, skb)) + if (len < (th->doff << 2) || tcp_checksum_complete(skb)) goto csum_error; if (!th->ack && !th->rst && !th->syn) From 7309f8821fd65e8272ce82e852532b02967812da Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 29 Apr 2016 14:16:49 -0700 Subject: [PATCH 3/7] dccp: do not assume DCCP code is non preemptible DCCP uses the generic backlog code, and this will soon be changed to not disable BH when protocol is called back. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- net/dccp/input.c | 2 +- net/dccp/ipv4.c | 4 ++-- net/dccp/ipv6.c | 4 ++-- net/dccp/options.c | 2 +- 4 files changed, 6 insertions(+), 6 deletions(-) diff --git a/net/dccp/input.c b/net/dccp/input.c index 2437ecc13b82f..ba347184bda9b 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -359,7 +359,7 @@ static int __dccp_rcv_established(struct sock *sk, struct sk_buff *skb, goto discard; } - __DCCP_INC_STATS(DCCP_MIB_INERRS); + DCCP_INC_STATS(DCCP_MIB_INERRS); discard: __kfree_skb(skb); return 0; diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index a8164272e0f43..5c7e413a3ae40 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -533,8 +533,8 @@ static void dccp_v4_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb) bh_unlock_sock(ctl_sk); if (net_xmit_eval(err) == 0) { - __DCCP_INC_STATS(DCCP_MIB_OUTSEGS); - __DCCP_INC_STATS(DCCP_MIB_OUTRSTS); + DCCP_INC_STATS(DCCP_MIB_OUTSEGS); + DCCP_INC_STATS(DCCP_MIB_OUTRSTS); } out: dst_release(dst); diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 0f4eb4ea57a5f..d176f4e66369a 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -277,8 +277,8 @@ static void dccp_v6_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb) if (!IS_ERR(dst)) { skb_dst_set(skb, dst); ip6_xmit(ctl_sk, skb, &fl6, NULL, 0); - __DCCP_INC_STATS(DCCP_MIB_OUTSEGS); - __DCCP_INC_STATS(DCCP_MIB_OUTRSTS); + DCCP_INC_STATS(DCCP_MIB_OUTSEGS); + DCCP_INC_STATS(DCCP_MIB_OUTRSTS); return; } diff --git a/net/dccp/options.c b/net/dccp/options.c index b82b7ee9a1d2d..74d29c56c3670 100644 --- a/net/dccp/options.c +++ b/net/dccp/options.c @@ -253,7 +253,7 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq, return 0; out_invalid_option: - __DCCP_INC_STATS(DCCP_MIB_INVALIDOPT); + DCCP_INC_STATS(DCCP_MIB_INVALIDOPT); rc = DCCP_RESET_CODE_OPTION_ERROR; out_featneg_failed: DCCP_WARN("DCCP(%p): Option %d (len=%d) error=%u\n", sk, opt, len, rc); From e61da9e259ef887bd516ab08dfdf1c1261017e8e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 29 Apr 2016 14:16:50 -0700 Subject: [PATCH 4/7] udp: prepare for non BH masking at backlog processing UDP uses the generic socket backlog code, and this will soon be changed to not disable BH when protocol is called back. We need to use appropriate SNMP accessors. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- net/ipv4/udp.c | 4 ++-- net/ipv6/udp.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 093284c5c03be..f67f52ba48093 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1514,9 +1514,9 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) /* Note that an ENOMEM error is charged twice */ if (rc == -ENOMEM) - __UDP_INC_STATS(sock_net(sk), UDP_MIB_RCVBUFERRORS, + UDP_INC_STATS(sock_net(sk), UDP_MIB_RCVBUFERRORS, is_udplite); - __UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); + UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); kfree_skb(skb); trace_udp_fail_queue_rcv_skb(rc, sk); return -1; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 1ba5a74ac18fe..f911c63f79e67 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -570,9 +570,9 @@ static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) /* Note that an ENOMEM error is charged twice */ if (rc == -ENOMEM) - __UDP6_INC_STATS(sock_net(sk), + UDP6_INC_STATS(sock_net(sk), UDP_MIB_RCVBUFERRORS, is_udplite); - __UDP6_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); + UDP6_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); kfree_skb(skb); return -1; } From 860fbbc343bf05a71b31555579ff4878194be01b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 29 Apr 2016 14:16:51 -0700 Subject: [PATCH 5/7] sctp: prepare for socket backlog behavior change sctp_inq_push() will soon be called without BH being blocked when generic socket code flushes the socket backlog. It is very possible SCTP can be converted to not rely on BH, but this needs to be done by SCTP experts. Signed-off-by: Eric Dumazet Acked-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- net/sctp/inqueue.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index b335ffcef0b90..9d87bba0ff1d3 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -89,10 +89,12 @@ void sctp_inq_push(struct sctp_inq *q, struct sctp_chunk *chunk) * Eventually, we should clean up inqueue to not rely * on the BH related data structures. */ + local_bh_disable(); list_add_tail(&chunk->list, &q->in_chunk_list); if (chunk->asoc) chunk->asoc->stats.ipackets++; q->immediate.func(&q->immediate); + local_bh_enable(); } /* Peek at the next chunk on the inqeue. */ From 5413d1babe8f10de13d72496c12b862eef8ba613 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 29 Apr 2016 14:16:52 -0700 Subject: [PATCH 6/7] net: do not block BH while processing socket backlog Socket backlog processing is a major latency source. With current TCP socket sk_rcvbuf limits, I have sampled __release_sock() holding cpu for more than 5 ms, and packets being dropped by the NIC once ring buffer is filled. All users are now ready to be called from process context, we can unblock BH and let interrupts be serviced faster. cond_resched_softirq() could be removed, as it has no more user. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- net/core/sock.c | 22 ++++++++-------------- 1 file changed, 8 insertions(+), 14 deletions(-) diff --git a/net/core/sock.c b/net/core/sock.c index e16a5db853c6f..70744dbb6c3f8 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2019,33 +2019,27 @@ static void __release_sock(struct sock *sk) __releases(&sk->sk_lock.slock) __acquires(&sk->sk_lock.slock) { - struct sk_buff *skb = sk->sk_backlog.head; + struct sk_buff *skb, *next; - do { + while ((skb = sk->sk_backlog.head) != NULL) { sk->sk_backlog.head = sk->sk_backlog.tail = NULL; - bh_unlock_sock(sk); - do { - struct sk_buff *next = skb->next; + spin_unlock_bh(&sk->sk_lock.slock); + do { + next = skb->next; prefetch(next); WARN_ON_ONCE(skb_dst_is_noref(skb)); skb->next = NULL; sk_backlog_rcv(sk, skb); - /* - * We are in process context here with softirqs - * disabled, use cond_resched_softirq() to preempt. - * This is safe to do because we've taken the backlog - * queue private: - */ - cond_resched_softirq(); + cond_resched(); skb = next; } while (skb != NULL); - bh_lock_sock(sk); - } while ((skb = sk->sk_backlog.head) != NULL); + spin_lock_bh(&sk->sk_lock.slock); + } /* * Doing the zeroing here guarantee we can not loop forever From d41a69f1d390fa3f2546498103cdcd78b30676ff Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 29 Apr 2016 14:16:53 -0700 Subject: [PATCH 7/7] tcp: make tcp_sendmsg() aware of socket backlog Large sendmsg()/write() hold socket lock for the duration of the call, unless sk->sk_sndbuf limit is hit. This is bad because incoming packets are parked into socket backlog for a long time. Critical decisions like fast retransmit might be delayed. Receivers have to maintain a big out of order queue with additional cpu overhead, and also possible stalls in TX once windows are full. Bidirectional flows are particularly hurt since the backlog can become quite big if the copy from user space triggers IO (page faults) Some applications learnt to use sendmsg() (or sendmmsg()) with small chunks to avoid this issue. Kernel should know better, right ? Add a generic sk_flush_backlog() helper and use it right before a new skb is allocated. Typically we put 64KB of payload per skb (unless MSG_EOR is requested) and checking socket backlog every 64KB gives good results. As a matter of fact, tests with TSO/GSO disabled give very nice results, as we manage to keep a small write queue and smaller perceived rtt. Note that sk_flush_backlog() maintains socket ownership, so is not equivalent to a {release_sock(sk); lock_sock(sk);}, to ensure implicit atomicity rules that sendmsg() was giving to (possibly buggy) applications. In this simple implementation, I chose to not call tcp_release_cb(), but we might consider this later. Signed-off-by: Eric Dumazet Cc: Alexei Starovoitov Cc: Marcelo Ricardo Leitner Acked-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- include/net/sock.h | 11 +++++++++++ net/core/sock.c | 7 +++++++ net/ipv4/tcp.c | 8 ++++++-- 3 files changed, 24 insertions(+), 2 deletions(-) diff --git a/include/net/sock.h b/include/net/sock.h index 3df778ccaa820..1dbb1f9f7c1b4 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -926,6 +926,17 @@ void sk_stream_kill_queues(struct sock *sk); void sk_set_memalloc(struct sock *sk); void sk_clear_memalloc(struct sock *sk); +void __sk_flush_backlog(struct sock *sk); + +static inline bool sk_flush_backlog(struct sock *sk) +{ + if (unlikely(READ_ONCE(sk->sk_backlog.tail))) { + __sk_flush_backlog(sk); + return true; + } + return false; +} + int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb); struct request_sock_ops; diff --git a/net/core/sock.c b/net/core/sock.c index 70744dbb6c3f8..f615e93911707 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2048,6 +2048,13 @@ static void __release_sock(struct sock *sk) sk->sk_backlog.len = 0; } +void __sk_flush_backlog(struct sock *sk) +{ + spin_lock_bh(&sk->sk_lock.slock); + __release_sock(sk); + spin_unlock_bh(&sk->sk_lock.slock); +} + /** * sk_wait_data - wait for data to arrive at sk_receive_queue * @sk: sock to wait on diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 4787f86ae64cf..b945c2b046c5e 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1136,11 +1136,12 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) /* This should be in poll */ sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); - mss_now = tcp_send_mss(sk, &size_goal, flags); - /* Ok commence sending. */ copied = 0; +restart: + mss_now = tcp_send_mss(sk, &size_goal, flags); + err = -EPIPE; if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) goto out_err; @@ -1166,6 +1167,9 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) if (!sk_stream_memory_free(sk)) goto wait_for_sndbuf; + if (sk_flush_backlog(sk)) + goto restart; + skb = sk_stream_alloc_skb(sk, select_size(sk, sg), sk->sk_allocation,