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>

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 735e957..27e8d37 100644 (file)
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -346,6 +346,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb);
 void tcp_rcv_space_adjust(struct sock *sk);
 int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp);
 void tcp_twsk_destructor(struct sock *sk);
+void tcp_twsk_purge(struct list_head *net_exit_list, int family);
 ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos,
                        struct pipe_inode_info *pipe, size_t len,
                        unsigned int flags);

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 9aa186a..73e6854 100644 (file)
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -3206,7 +3206,7 @@ static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list)
 {
        struct net *net;
 
-       inet_twsk_purge(&tcp_hashinfo, AF_INET);
+       tcp_twsk_purge(net_exit_list, AF_INET);
 
        list_for_each_entry(net, net_exit_list, exit_list) {
                WARN_ON_ONCE(!refcount_dec_and_test(&net->ipv4.tcp_death_row.tw_refcount));

diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 2e53981..98c576d 100644 (file)
--- 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.
  */

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index f9ed47e..06beed4 100644 (file)
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -2229,7 +2229,7 @@ static void __net_exit tcpv6_net_exit(struct net *net)
 
 static void __net_exit tcpv6_net_exit_batch(struct list_head *net_exit_list)
 {
-       inet_twsk_purge(&tcp_hashinfo, AF_INET6);
+       tcp_twsk_purge(net_exit_list, AF_INET6);
 }
 
 static struct pernet_operations tcpv6_net_ops = {