From e9bd0cca09d13ac2f08d25e195203e42d4ad1ce8 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 7 Sep 2022 18:10:18 -0700 Subject: tcp: Don't allocate tcp_death_row outside of struct netns_ipv4. We will soon introduce an optional per-netns ehash and access hash tables via net->ipv4.tcp_death_row->hashinfo instead of &tcp_hashinfo in most places. It could harm the fast path because dereferences of two fields in net and tcp_death_row might incur two extra cache line misses. To save one dereference, let's place tcp_death_row back in netns_ipv4 and fetch hashinfo via net->ipv4.tcp_death_row"."hashinfo. Note tcp_death_row was initially placed in netns_ipv4, and commit fbb8295248e1 ("tcp: allocate tcp_death_row outside of struct netns_ipv4") changed it to a pointer so that we can fire TIME_WAIT timers after freeing net. However, we don't do so after commit 04c494e68a13 ("Revert "tcp/dccp: get rid of inet_twsk_purge()""), so we need not define tcp_death_row as a pointer. Also, we move refcount_dec_and_test(&tw_refcount) from tcp_sk_exit() to tcp_sk_exit_batch() as a debug check. Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- net/ipv4/tcp_ipv4.c | 19 +++++++------------ 1 file changed, 7 insertions(+), 12 deletions(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a07243f66d4c..3930b6a1e0d6 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -292,7 +292,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) * complete initialization after this. */ tcp_set_state(sk, TCP_SYN_SENT); - tcp_death_row = net->ipv4.tcp_death_row; + tcp_death_row = &net->ipv4.tcp_death_row; err = inet_hash_connect(tcp_death_row, sk); if (err) goto failure; @@ -3091,13 +3091,9 @@ EXPORT_SYMBOL(tcp_prot); static void __net_exit tcp_sk_exit(struct net *net) { - struct inet_timewait_death_row *tcp_death_row = net->ipv4.tcp_death_row; - if (net->ipv4.tcp_congestion_control) bpf_module_put(net->ipv4.tcp_congestion_control, net->ipv4.tcp_congestion_control->owner); - if (refcount_dec_and_test(&tcp_death_row->tw_refcount)) - kfree(tcp_death_row); } static int __net_init tcp_sk_init(struct net *net) @@ -3129,13 +3125,10 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_tw_reuse = 2; net->ipv4.sysctl_tcp_no_ssthresh_metrics_save = 1; - net->ipv4.tcp_death_row = kzalloc(sizeof(struct inet_timewait_death_row), GFP_KERNEL); - if (!net->ipv4.tcp_death_row) - return -ENOMEM; - refcount_set(&net->ipv4.tcp_death_row->tw_refcount, 1); + refcount_set(&net->ipv4.tcp_death_row.tw_refcount, 1); cnt = tcp_hashinfo.ehash_mask + 1; - net->ipv4.tcp_death_row->sysctl_max_tw_buckets = cnt / 2; - net->ipv4.tcp_death_row->hashinfo = &tcp_hashinfo; + net->ipv4.tcp_death_row.sysctl_max_tw_buckets = cnt / 2; + net->ipv4.tcp_death_row.hashinfo = &tcp_hashinfo; net->ipv4.sysctl_max_syn_backlog = max(128, cnt / 128); net->ipv4.sysctl_tcp_sack = 1; @@ -3201,8 +3194,10 @@ static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) inet_twsk_purge(&tcp_hashinfo, AF_INET); - list_for_each_entry(net, net_exit_list, exit_list) + list_for_each_entry(net, net_exit_list, exit_list) { + WARN_ON_ONCE(!refcount_dec_and_test(&net->ipv4.tcp_death_row.tw_refcount)); tcp_fastopen_ctx_destroy(net); + } } static struct pernet_operations __net_initdata tcp_sk_ops = { -- cgit