tcp: Save unnecessary inet_twsk_purge() calls.

While destroying netns, we call inet_twsk_purge() in tcp_sk_exit_batch()
and tcpv6_net_exit_batch() for AF_INET and AF_INET6.  These commands
trigger the kernel to walk through the potentially big ehash twice even
though the netns has no TIME_WAIT sockets.

  # ip netns add test
  # ip netns del test

  or

  # unshare -n /bin/true >/dev/null

When tw_refcount is 1, we need not call inet_twsk_purge() at least
for the net.  We can save such unneeded iterations if all netns in
net_exit_list have no TIME_WAIT sockets.  This change eliminates
the tax by the additional unshare() described in the next patch to
guarantee the per-netns ehash size.

Tested:

  # mount -t debugfs none /sys/kernel/debug/
  # echo cleanup_net > /sys/kernel/debug/tracing/set_ftrace_filter
  # echo inet_twsk_purge >> /sys/kernel/debug/tracing/set_ftrace_filter
  # echo function > /sys/kernel/debug/tracing/current_tracer
  # cat ./add_del_unshare.sh
  for i in `seq 1 40`
  do
      (for j in `seq 1 100` ; do  unshare -n /bin/true >/dev/null ; done) &
  done
  wait;
  # ./add_del_unshare.sh

Before the patch:

  # cat /sys/kernel/debug/tracing/trace_pipe
    kworker/u128:0-8       [031] ...1.   174.162765: cleanup_net <-process_one_work
    kworker/u128:0-8       [031] ...1.   174.240796: inet_twsk_purge <-cleanup_net
    kworker/u128:0-8       [032] ...1.   174.244759: inet_twsk_purge <-tcp_sk_exit_batch
    kworker/u128:0-8       [034] ...1.   174.290861: cleanup_net <-process_one_work
    kworker/u128:0-8       [039] ...1.   175.245027: inet_twsk_purge <-cleanup_net
    kworker/u128:0-8       [046] ...1.   175.290541: inet_twsk_purge <-tcp_sk_exit_batch
    kworker/u128:0-8       [037] ...1.   175.321046: cleanup_net <-process_one_work
    kworker/u128:0-8       [024] ...1.   175.941633: inet_twsk_purge <-cleanup_net
    kworker/u128:0-8       [025] ...1.   176.242539: inet_twsk_purge <-tcp_sk_exit_batch

After:

  # cat /sys/kernel/debug/tracing/trace_pipe
    kworker/u128:0-8       [038] ...1.   428.116174: cleanup_net <-process_one_work
    kworker/u128:0-8       [038] ...1.   428.262532: cleanup_net <-process_one_work
    kworker/u128:0-8       [030] ...1.   429.292645: cleanup_net <-process_one_work

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 15 insertions, 0 deletions

diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 2e53981252d9..98c576d4b671 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -347,6 +347,21 @@ void tcp_twsk_destructor(struct sock *sk)
 }
 EXPORT_SYMBOL_GPL(tcp_twsk_destructor);
 
+void tcp_twsk_purge(struct list_head *net_exit_list, int family)
+{
+	struct net *net;
+
+	list_for_each_entry(net, net_exit_list, exit_list) {
+		/* The last refcount is decremented in tcp_sk_exit_batch() */
+		if (refcount_read(&net->ipv4.tcp_death_row.tw_refcount) == 1)
+			continue;
+
+		inet_twsk_purge(&tcp_hashinfo, family);
+		break;
+	}
+}
+EXPORT_SYMBOL_GPL(tcp_twsk_purge);
+
 /* Warning : This function is called without sk_listener being locked.
  * Be sure to read socket fields once, as their value could change under us.
  */