[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <1478285672-3195-2-git-send-email-edumazet@google.com>
Date: Fri, 4 Nov 2016 11:54:31 -0700
From: Eric Dumazet <edumazet@...gle.com>
To: "David S . Miller" <davem@...emloft.net>
Cc: netdev <netdev@...r.kernel.org>,
Neal Cardwell <ncardwell@...gle.com>,
Yuchung Cheng <ycheng@...gle.com>,
Soheil Hassas Yeganeh <soheil@...gle.com>,
Eric Dumazet <edumazet@...gle.com>,
Eric Dumazet <eric.dumazet@...il.com>
Subject: [PATCH net-next 1/2] tcp: shortcut listeners in tcp_get_info()
Being lockless in tcp_get_info() is hard, because we need to add
specific synchronization in TCP fast path, like seqcount.
Following patch will change inet_diag_dump_icsk() to no longer
hold any lock for non listeners, so that we can properly acquire
socket lock in get_tcp_info() and let it return more consistent counters.
Signed-off-by: Eric Dumazet <edumazet@...gle.com>
Signed-off-by: Yuchung Cheng <ycheng@...gle.com>
Acked-by: Soheil Hassas Yeganeh <soheil@...gle.com>
Acked-by: Neal Cardwell <ncardwell@...gle.com>
---
net/ipv4/tcp.c | 41 ++++++++++++++++++++++++-----------------
1 file changed, 24 insertions(+), 17 deletions(-)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 3251fe71f39f..117982be0cab 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2721,6 +2721,27 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
info->tcpi_state = sk_state_load(sk);
+ /* Report meaningful fields for all TCP states, including listeners */
+ rate = READ_ONCE(sk->sk_pacing_rate);
+ rate64 = rate != ~0U ? rate : ~0ULL;
+ put_unaligned(rate64, &info->tcpi_pacing_rate);
+
+ rate = READ_ONCE(sk->sk_max_pacing_rate);
+ rate64 = rate != ~0U ? rate : ~0ULL;
+ put_unaligned(rate64, &info->tcpi_max_pacing_rate);
+
+ info->tcpi_reordering = tp->reordering;
+ info->tcpi_snd_cwnd = tp->snd_cwnd;
+
+ if (info->tcpi_state == TCP_LISTEN) {
+ /* listeners aliased fields :
+ * tcpi_unacked -> Number of children ready for accept()
+ * tcpi_sacked -> max backlog
+ */
+ info->tcpi_unacked = sk->sk_ack_backlog;
+ info->tcpi_sacked = sk->sk_max_ack_backlog;
+ return;
+ }
info->tcpi_ca_state = icsk->icsk_ca_state;
info->tcpi_retransmits = icsk->icsk_retransmits;
info->tcpi_probes = icsk->icsk_probes_out;
@@ -2748,13 +2769,9 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
info->tcpi_snd_mss = tp->mss_cache;
info->tcpi_rcv_mss = icsk->icsk_ack.rcv_mss;
- if (info->tcpi_state == TCP_LISTEN) {
- info->tcpi_unacked = sk->sk_ack_backlog;
- info->tcpi_sacked = sk->sk_max_ack_backlog;
- } else {
- info->tcpi_unacked = tp->packets_out;
- info->tcpi_sacked = tp->sacked_out;
- }
+ info->tcpi_unacked = tp->packets_out;
+ info->tcpi_sacked = tp->sacked_out;
+
info->tcpi_lost = tp->lost_out;
info->tcpi_retrans = tp->retrans_out;
info->tcpi_fackets = tp->fackets_out;
@@ -2768,23 +2785,13 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
info->tcpi_rtt = tp->srtt_us >> 3;
info->tcpi_rttvar = tp->mdev_us >> 2;
info->tcpi_snd_ssthresh = tp->snd_ssthresh;
- info->tcpi_snd_cwnd = tp->snd_cwnd;
info->tcpi_advmss = tp->advmss;
- info->tcpi_reordering = tp->reordering;
info->tcpi_rcv_rtt = jiffies_to_usecs(tp->rcv_rtt_est.rtt)>>3;
info->tcpi_rcv_space = tp->rcvq_space.space;
info->tcpi_total_retrans = tp->total_retrans;
- rate = READ_ONCE(sk->sk_pacing_rate);
- rate64 = rate != ~0U ? rate : ~0ULL;
- put_unaligned(rate64, &info->tcpi_pacing_rate);
-
- rate = READ_ONCE(sk->sk_max_pacing_rate);
- rate64 = rate != ~0U ? rate : ~0ULL;
- put_unaligned(rate64, &info->tcpi_max_pacing_rate);
-
do {
start = u64_stats_fetch_begin_irq(&tp->syncp);
put_unaligned(tp->bytes_acked, &info->tcpi_bytes_acked);
--
2.8.0.rc3.226.g39d4020
Powered by blists - more mailing lists