| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20250305034550.879255-3-edumazet@google.com>
Date: Wed, 5 Mar 2025 03:45:50 +0000
From: Eric Dumazet <edumazet@...gle.com>
To: "David S . Miller" <davem@...emloft.net>, Jakub Kicinski <kuba@...nel.org>,
Paolo Abeni <pabeni@...hat.com>
Cc: Neal Cardwell <ncardwell@...gle.com>, Kuniyuki Iwashima <kuniyu@...zon.com>,
Jason Xing <kernelxing@...cent.com>, Simon Horman <horms@...nel.org>, netdev@...r.kernel.org,
eric.dumazet@...il.com, Eric Dumazet <edumazet@...gle.com>
Subject: [PATCH net-next 2/2] inet: call inet6_ehashfn() once from inet6_hash_connect()
inet6_ehashfn() being called from __inet6_check_established()
has a big impact on performance, as shown in the Tested section.
After prior patch, we can compute the hash for port 0
from inet6_hash_connect(), and derive each hash in
__inet_hash_connect() from this initial hash:
hash(saddr, lport, daddr, dport) == hash(saddr, 0, daddr, dport) + lport
Apply the same principle for __inet_check_established(),
although inet_ehashfn() has a smaller cost.
Tested:
Server: ulimit -n 40000; neper/tcp_crr -T 200 -F 30000 -6 --nolog
Client: ulimit -n 40000; neper/tcp_crr -T 200 -F 30000 -6 --nolog -c -H server
Before this patch:
utime_start=0.286131
utime_end=4.378886
stime_start=11.952556
stime_end=1991.655533
num_transactions=1446830
latency_min=0.001061085
latency_max=12.075275028
latency_mean=0.376375302
latency_stddev=1.361969596
num_samples=306383
throughput=151866.56
perf top:
50.01% [kernel] [k] __inet6_check_established
20.65% [kernel] [k] __inet_hash_connect
15.81% [kernel] [k] inet6_ehashfn
2.92% [kernel] [k] rcu_all_qs
2.34% [kernel] [k] __cond_resched
0.50% [kernel] [k] _raw_spin_lock
0.34% [kernel] [k] sched_balance_trigger
0.24% [kernel] [k] queued_spin_lock_slowpath
After this patch:
utime_start=0.315047
utime_end=9.257617
stime_start=7.041489
stime_end=1923.688387
num_transactions=3057968
latency_min=0.003041375
latency_max=7.056589232
latency_mean=0.141075048 # Better latency metrics
latency_stddev=0.526900516
num_samples=312996
throughput=320677.21 # 111 % increase, and 229 % for the series
perf top: inet6_ehashfn is no longer seen.
39.67% [kernel] [k] __inet_hash_connect
37.06% [kernel] [k] __inet6_check_established
4.79% [kernel] [k] rcu_all_qs
3.82% [kernel] [k] __cond_resched
1.76% [kernel] [k] sched_balance_domains
0.82% [kernel] [k] _raw_spin_lock
0.81% [kernel] [k] sched_balance_rq
0.81% [kernel] [k] sched_balance_trigger
0.76% [kernel] [k] queued_spin_lock_slowpath
Signed-off-by: Eric Dumazet <edumazet@...gle.com>
---
include/net/inet_hashtables.h | 4 +++-
include/net/ip.h | 2 +-
net/ipv4/inet_hashtables.c | 26 ++++++++++++++++++--------
net/ipv6/inet6_hashtables.c | 15 +++++++++++----
4 files changed, 33 insertions(+), 14 deletions(-)
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index f447d61d95982090aac492b31e4199534970c4fb..949641e925398f741f2d4dda5898efc683b305dc 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -527,10 +527,12 @@ static inline void sk_rcv_saddr_set(struct sock *sk, __be32 addr)
int __inet_hash_connect(struct inet_timewait_death_row *death_row,
struct sock *sk, u64 port_offset,
+ u32 hash_port0,
int (*check_established)(struct inet_timewait_death_row *,
struct sock *, __u16,
struct inet_timewait_sock **,
- bool rcu_lookup));
+ bool rcu_lookup,
+ u32 hash));
int inet_hash_connect(struct inet_timewait_death_row *death_row,
struct sock *sk);
diff --git a/include/net/ip.h b/include/net/ip.h
index ce5e59957dd553697536ddf111bb1406d9d99408..8a48ade24620b4c8e2ebb4726f27a69aac7138b0 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -357,7 +357,7 @@ static inline void inet_get_local_port_range(const struct net *net, int *low, in
bool inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high);
#ifdef CONFIG_SYSCTL
-static inline bool inet_is_local_reserved_port(struct net *net, unsigned short port)
+static inline bool inet_is_local_reserved_port(const struct net *net, unsigned short port)
{
if (!net->ipv4.sysctl_local_reserved_ports)
return false;
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 3025d2b708852acd9744709a897fca17564523d5..1e3a9573c19834cc96d0b4cbf816f86433134450 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -538,7 +538,8 @@ EXPORT_SYMBOL_GPL(__inet_lookup_established);
static int __inet_check_established(struct inet_timewait_death_row *death_row,
struct sock *sk, __u16 lport,
struct inet_timewait_sock **twp,
- bool rcu_lookup)
+ bool rcu_lookup,
+ u32 hash)
{
struct inet_hashinfo *hinfo = death_row->hashinfo;
struct inet_sock *inet = inet_sk(sk);
@@ -549,8 +550,6 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row,
int sdif = l3mdev_master_ifindex_by_index(net, dif);
INET_ADDR_COOKIE(acookie, saddr, daddr);
const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport);
- unsigned int hash = inet_ehashfn(net, daddr, lport,
- saddr, inet->inet_dport);
struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash);
struct inet_timewait_sock *tw = NULL;
const struct hlist_nulls_node *node;
@@ -1007,9 +1006,10 @@ static u32 *table_perturb;
int __inet_hash_connect(struct inet_timewait_death_row *death_row,
struct sock *sk, u64 port_offset,
+ u32 hash_port0,
int (*check_established)(struct inet_timewait_death_row *,
struct sock *, __u16, struct inet_timewait_sock **,
- bool rcu_lookup))
+ bool rcu_lookup, u32 hash))
{
struct inet_hashinfo *hinfo = death_row->hashinfo;
struct inet_bind_hashbucket *head, *head2;
@@ -1027,7 +1027,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
if (port) {
local_bh_disable();
- ret = check_established(death_row, sk, port, NULL, false);
+ ret = check_established(death_row, sk, port, NULL, false,
+ hash_port0 + port);
local_bh_enable();
return ret;
}
@@ -1071,7 +1072,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
rcu_read_unlock();
goto next_port;
}
- if (!check_established(death_row, sk, port, &tw, true))
+ if (!check_established(death_row, sk, port, &tw, true,
+ hash_port0 + port))
break;
rcu_read_unlock();
goto next_port;
@@ -1090,7 +1092,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
goto next_port_unlock;
WARN_ON(hlist_empty(&tb->bhash2));
if (!check_established(death_row, sk,
- port, &tw, false))
+ port, &tw, false,
+ hash_port0 + port))
goto ok;
goto next_port_unlock;
}
@@ -1197,11 +1200,18 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
int inet_hash_connect(struct inet_timewait_death_row *death_row,
struct sock *sk)
{
+ const struct inet_sock *inet = inet_sk(sk);
+ const struct net *net = sock_net(sk);
u64 port_offset = 0;
+ u32 hash_port0;
if (!inet_sk(sk)->inet_num)
port_offset = inet_sk_port_offset(sk);
- return __inet_hash_connect(death_row, sk, port_offset,
+
+ hash_port0 = inet_ehashfn(net, inet->inet_rcv_saddr, 0,
+ inet->inet_daddr, inet->inet_dport);
+
+ return __inet_hash_connect(death_row, sk, port_offset, hash_port0,
__inet_check_established);
}
EXPORT_SYMBOL_GPL(inet_hash_connect);
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 3d95f1e75a118ff8027d4ec0f33910d23b6af832..76ee521189eb77c48845eeeac9d50b3a93a250a6 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -264,7 +264,8 @@ EXPORT_SYMBOL_GPL(inet6_lookup);
static int __inet6_check_established(struct inet_timewait_death_row *death_row,
struct sock *sk, const __u16 lport,
struct inet_timewait_sock **twp,
- bool rcu_lookup)
+ bool rcu_lookup,
+ u32 hash)
{
struct inet_hashinfo *hinfo = death_row->hashinfo;
struct inet_sock *inet = inet_sk(sk);
@@ -274,8 +275,6 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row,
struct net *net = sock_net(sk);
const int sdif = l3mdev_master_ifindex_by_index(net, dif);
const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport);
- const unsigned int hash = inet6_ehashfn(net, daddr, lport, saddr,
- inet->inet_dport);
struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash);
struct inet_timewait_sock *tw = NULL;
const struct hlist_nulls_node *node;
@@ -354,11 +353,19 @@ static u64 inet6_sk_port_offset(const struct sock *sk)
int inet6_hash_connect(struct inet_timewait_death_row *death_row,
struct sock *sk)
{
+ const struct in6_addr *daddr = &sk->sk_v6_rcv_saddr;
+ const struct in6_addr *saddr = &sk->sk_v6_daddr;
+ const struct inet_sock *inet = inet_sk(sk);
+ const struct net *net = sock_net(sk);
u64 port_offset = 0;
+ u32 hash_port0;
if (!inet_sk(sk)->inet_num)
port_offset = inet6_sk_port_offset(sk);
- return __inet_hash_connect(death_row, sk, port_offset,
+
+ hash_port0 = inet6_ehashfn(net, daddr, 0, saddr, inet->inet_dport);
+
+ return __inet_hash_connect(death_row, sk, port_offset, hash_port0,
__inet6_check_established);
}
EXPORT_SYMBOL_GPL(inet6_hash_connect);
--
2.48.1.711.g2feabab25a-goog
Powered by blists - more mailing lists