diff options
author | Martin KaFai Lau <kafai@fb.com> | 2022-05-12 03:06:05 +0300 |
---|---|---|
committer | Jakub Kicinski <kuba@kernel.org> | 2022-05-13 02:52:18 +0300 |
commit | cae3873c5b3a4fcd9706fb461ff4e91bdf1f0120 (patch) | |
tree | 54650bd157a612c462c1fb7856c1800babd1790b /include/net | |
parent | e8d0059000b20c4745c5b6a713f6adb269cff8ff (diff) | |
download | linux-cae3873c5b3a4fcd9706fb461ff4e91bdf1f0120.tar.xz |
net: inet: Retire port only listening_hash
The listen sk is currently stored in two hash tables,
listening_hash (hashed by port) and lhash2 (hashed by port and address).
After commit 0ee58dad5b06 ("net: tcp6: prefer listeners bound to an address")
and commit d9fbc7f6431f ("net: tcp: prefer listeners bound to an address"),
the TCP-SYN lookup fast path does not use listening_hash.
The commit 05c0b35709c5 ("tcp: seq_file: Replace listening_hash with lhash2")
also moved the seq_file (/proc/net/tcp) iteration usage from
listening_hash to lhash2.
There are still a few listening_hash usages left.
One of them is inet_reuseport_add_sock() which uses the listening_hash
to search a listen sk during the listen() system call. This turns
out to be very slow on use cases that listen on many different
VIPs at a popular port (e.g. 443). [ On top of the slowness in
adding to the tail in the IPv6 case ]. The latter patch has a
selftest to demonstrate this case.
This patch takes this chance to move all remaining listening_hash
usages to lhash2 and then retire listening_hash.
Since most changes need to be done together, it is hard to cut
the listening_hash to lhash2 switch into small patches. The
changes in this patch is highlighted here for the review
purpose.
1. Because of the listening_hash removal, lhash2 can use the
sk->sk_nulls_node instead of the icsk->icsk_listen_portaddr_node.
This will also keep the sk_unhashed() check to work as is
after stop adding sk to listening_hash.
The union is removed from inet_listen_hashbucket because
only nulls_head is needed.
2. icsk->icsk_listen_portaddr_node and its helpers are removed.
3. The current lhash2 users needs to iterate with sk_nulls_node
instead of icsk_listen_portaddr_node.
One case is in the inet[6]_lhash2_lookup().
Another case is the seq_file iterator in tcp_ipv4.c.
One thing to note is sk_nulls_next() is needed
because the old inet_lhash2_for_each_icsk_continue()
does a "next" first before iterating.
4. Move the remaining listening_hash usage to lhash2
inet_reuseport_add_sock() which this series is
trying to improve.
inet_diag.c and mptcp_diag.c are the final two
remaining use cases and is moved to lhash2 now also.
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'include/net')
-rw-r--r-- | include/net/inet_connection_sock.h | 2 | ||||
-rw-r--r-- | include/net/inet_hashtables.h | 41 |
2 files changed, 1 insertions, 42 deletions
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 3908296d103f..85cd695e7fd1 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -66,7 +66,6 @@ struct inet_connection_sock_af_ops { * @icsk_ulp_ops Pluggable ULP control hook * @icsk_ulp_data ULP private data * @icsk_clean_acked Clean acked data hook - * @icsk_listen_portaddr_node hash to the portaddr listener hashtable * @icsk_ca_state: Congestion control state * @icsk_retransmits: Number of unrecovered [RTO] timeouts * @icsk_pending: Scheduled timer event @@ -96,7 +95,6 @@ struct inet_connection_sock { const struct tcp_ulp_ops *icsk_ulp_ops; void __rcu *icsk_ulp_data; void (*icsk_clean_acked)(struct sock *sk, u32 acked_seq); - struct hlist_node icsk_listen_portaddr_node; unsigned int (*icsk_sync_mss)(struct sock *sk, u32 pmtu); __u8 icsk_ca_state:5, icsk_ca_initialized:1, diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 103fc7a30e60..1b8706719d4f 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -111,10 +111,7 @@ struct inet_bind_hashbucket { #define LISTENING_NULLS_BASE (1U << 29) struct inet_listen_hashbucket { spinlock_t lock; - union { - struct hlist_head head; - struct hlist_nulls_head nulls_head; - }; + struct hlist_nulls_head nulls_head; }; /* This is for listening sockets, thus all sockets which possess wildcards. */ @@ -142,32 +139,8 @@ struct inet_hashinfo { /* The 2nd listener table hashed by local port and address */ unsigned int lhash2_mask; struct inet_listen_hashbucket *lhash2; - - /* All the above members are written once at bootup and - * never written again _or_ are predominantly read-access. - * - * Now align to a new cache line as all the following members - * might be often dirty. - */ - /* All sockets in TCP_LISTEN state will be in listening_hash. - * This is the only table where wildcard'd TCP sockets can - * exist. listening_hash is only hashed by local port number. - * If lhash2 is initialized, the same socket will also be hashed - * to lhash2 by port and address. - */ - struct inet_listen_hashbucket listening_hash[INET_LHTABLE_SIZE] - ____cacheline_aligned_in_smp; }; -#define inet_lhash2_for_each_icsk_continue(__icsk) \ - hlist_for_each_entry_continue(__icsk, icsk_listen_portaddr_node) - -#define inet_lhash2_for_each_icsk(__icsk, list) \ - hlist_for_each_entry(__icsk, list, icsk_listen_portaddr_node) - -#define inet_lhash2_for_each_icsk_rcu(__icsk, list) \ - hlist_for_each_entry_rcu(__icsk, list, icsk_listen_portaddr_node) - static inline struct inet_listen_hashbucket * inet_lhash2_bucket(struct inet_hashinfo *h, u32 hash) { @@ -229,23 +202,11 @@ static inline u32 inet_bhashfn(const struct net *net, const __u16 lport, void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb, const unsigned short snum); -/* These can have wildcards, don't try too hard. */ -static inline u32 inet_lhashfn(const struct net *net, const unsigned short num) -{ - return (num + net_hash_mix(net)) & (INET_LHTABLE_SIZE - 1); -} - -static inline int inet_sk_listen_hashfn(const struct sock *sk) -{ - return inet_lhashfn(sock_net(sk), inet_sk(sk)->inet_num); -} - /* Caller must disable local BH processing. */ int __inet_inherit_port(const struct sock *sk, struct sock *child); void inet_put_port(struct sock *sk); -void inet_hashinfo_init(struct inet_hashinfo *h); void inet_hashinfo2_init(struct inet_hashinfo *h, const char *name, unsigned long numentries, int scale, unsigned long low_limit, |