From: Philo Lu <lulie@linux.alibaba.com>
To: netdev@vger.kernel.org
Cc: willemdebruijn.kernel@gmail.com, davem@davemloft.net,
edumazet@google.com, kuba@kernel.org, pabeni@redhat.com,
dsahern@kernel.org, horms@kernel.org, antony.antony@secunet.com,
steffen.klassert@secunet.com, linux-kernel@vger.kernel.org,
dust.li@linux.alibaba.com, jakub@cloudflare.com,
fred.cc@alibaba-inc.com, yubing.qiuyubing@alibaba-inc.com
Subject: [PATCH v6 net-next 4/4] ipv6/udp: Add 4-tuple hash for connected socket
Date: Thu, 31 Oct 2024 20:45:50 +0800 [thread overview]
Message-ID: <20241031124550.20227-5-lulie@linux.alibaba.com> (raw)
In-Reply-To: <20241031124550.20227-1-lulie@linux.alibaba.com>
Implement ipv6 udp hash4 like that in ipv4. The major difference is that
the hash value should be calculated with udp6_ehashfn(). Besides,
ipv4-mapped ipv6 address is handled before hash() and rehash().
Core procedures of hash/unhash/rehash are same as ipv4, and udpv4 and
udpv6 share the same udptable, so some functions in ipv4 hash4 can also
be shared.
Signed-off-by: Philo Lu <lulie@linux.alibaba.com>
Signed-off-by: Cambda Zhu <cambda@linux.alibaba.com>
Signed-off-by: Fred Chen <fred.cc@alibaba-inc.com>
Signed-off-by: Yubing Qiu <yubing.qiuyubing@alibaba-inc.com>
---
net/ipv6/udp.c | 96 ++++++++++++++++++++++++++++++++++++++++++++++++--
1 file changed, 94 insertions(+), 2 deletions(-)
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 1ea99d704e31..64f13f258fca 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -110,8 +110,17 @@ void udp_v6_rehash(struct sock *sk)
u16 new_hash = ipv6_portaddr_hash(sock_net(sk),
&sk->sk_v6_rcv_saddr,
inet_sk(sk)->inet_num);
+ u16 new_hash4;
- udp_lib_rehash(sk, new_hash, 0); /* 4-tuple hash not implemented */
+ if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)) {
+ new_hash4 = udp_ehashfn(sock_net(sk), sk->sk_rcv_saddr, sk->sk_num,
+ sk->sk_daddr, sk->sk_dport);
+ } else {
+ new_hash4 = udp6_ehashfn(sock_net(sk), &sk->sk_v6_rcv_saddr, sk->sk_num,
+ &sk->sk_v6_daddr, sk->sk_dport);
+ }
+
+ udp_lib_rehash(sk, new_hash, new_hash4);
}
static int compute_score(struct sock *sk, const struct net *net,
@@ -216,6 +225,71 @@ static struct sock *udp6_lib_lookup2(const struct net *net,
return result;
}
+#if IS_ENABLED(CONFIG_BASE_SMALL)
+static struct sock *udp6_lib_lookup4(const struct net *net,
+ const struct in6_addr *saddr, __be16 sport,
+ const struct in6_addr *daddr, unsigned int hnum,
+ int dif, int sdif, struct udp_table *udptable)
+{
+ return NULL;
+}
+
+static void udp6_hash4(struct sock *sk)
+{
+}
+#else /* !CONFIG_BASE_SMALL */
+static struct sock *udp6_lib_lookup4(const struct net *net,
+ const struct in6_addr *saddr, __be16 sport,
+ const struct in6_addr *daddr, unsigned int hnum,
+ int dif, int sdif, struct udp_table *udptable)
+{
+ const __portpair ports = INET_COMBINED_PORTS(sport, hnum);
+ const struct hlist_nulls_node *node;
+ struct udp_hslot *hslot4;
+ unsigned int hash4, slot;
+ struct udp_sock *up;
+ struct sock *sk;
+
+ hash4 = udp6_ehashfn(net, daddr, hnum, saddr, sport);
+ slot = hash4 & udptable->mask;
+ hslot4 = &udptable->hash4[slot];
+
+begin:
+ udp_lrpa_for_each_entry_rcu(up, node, &hslot4->nulls_head) {
+ sk = (struct sock *)up;
+ if (inet6_match(net, sk, saddr, daddr, ports, dif, sdif))
+ return sk;
+ }
+
+ /* if the nulls value we got at the end of this lookup is not the expected one, we must
+ * restart lookup. We probably met an item that was moved to another chain due to rehash.
+ */
+ if (get_nulls_value(node) != slot)
+ goto begin;
+
+ return NULL;
+}
+
+static void udp6_hash4(struct sock *sk)
+{
+ struct net *net = sock_net(sk);
+ unsigned int hash;
+
+ if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)) {
+ udp4_hash4(sk);
+ return;
+ }
+
+ if (sk_unhashed(sk) || ipv6_addr_any(&sk->sk_v6_rcv_saddr))
+ return;
+
+ hash = udp6_ehashfn(net, &sk->sk_v6_rcv_saddr, sk->sk_num,
+ &sk->sk_v6_daddr, sk->sk_dport);
+
+ udp_lib_hash4(sk, hash);
+}
+#endif /* CONFIG_BASE_SMALL */
+
/* rcu_read_lock() must be held */
struct sock *__udp6_lib_lookup(const struct net *net,
const struct in6_addr *saddr, __be16 sport,
@@ -231,6 +305,12 @@ struct sock *__udp6_lib_lookup(const struct net *net,
hash2 = ipv6_portaddr_hash(net, daddr, hnum);
hslot2 = udp_hashslot2(udptable, hash2);
+ if (udp_has_hash4(hslot2)) {
+ result = udp6_lib_lookup4(net, saddr, sport, daddr, hnum, dif, sdif, udptable);
+ if (result) /* udp6_lib_lookup4 return sk or NULL */
+ return result;
+ }
+
/* Lookup connected or non-wildcard sockets */
result = udp6_lib_lookup2(net, saddr, sport,
daddr, hnum, dif, sdif,
@@ -1166,6 +1246,18 @@ static int udpv6_pre_connect(struct sock *sk, struct sockaddr *uaddr,
return BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, &addr_len);
}
+static int udpv6_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+{
+ int res;
+
+ lock_sock(sk);
+ res = __ip6_datagram_connect(sk, uaddr, addr_len);
+ if (!res)
+ udp6_hash4(sk);
+ release_sock(sk);
+ return res;
+}
+
/**
* udp6_hwcsum_outgoing - handle outgoing HW checksumming
* @sk: socket we are sending on
@@ -1761,7 +1853,7 @@ struct proto udpv6_prot = {
.owner = THIS_MODULE,
.close = udp_lib_close,
.pre_connect = udpv6_pre_connect,
- .connect = ip6_datagram_connect,
+ .connect = udpv6_connect,
.disconnect = udp_disconnect,
.ioctl = udp_ioctl,
.init = udpv6_init_sock,
--
2.32.0.3.g01195cf9f
next prev parent reply other threads:[~2024-10-31 12:46 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-10-31 12:45 [PATCH v6 net-next 0/4] udp: Add 4-tuple hash for connected sockets Philo Lu
2024-10-31 12:45 ` [PATCH v6 net-next 1/4] net/udp: Add a new struct for hash2 slot Philo Lu
2024-10-31 12:45 ` [PATCH v6 net-next 2/4] net/udp: Add 4-tuple hash list basis Philo Lu
2024-10-31 12:45 ` [PATCH v6 net-next 3/4] ipv4/udp: Add 4-tuple hash for connected socket Philo Lu
2024-10-31 12:45 ` Philo Lu [this message]
2024-11-01 11:40 ` [PATCH v6 net-next 4/4] ipv6/udp: " Philo Lu
2024-11-01 16:48 ` Kuniyuki Iwashima
2024-11-01 16:47 ` kernel test robot
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20241031124550.20227-5-lulie@linux.alibaba.com \
--to=lulie@linux.alibaba.com \
--cc=antony.antony@secunet.com \
--cc=davem@davemloft.net \
--cc=dsahern@kernel.org \
--cc=dust.li@linux.alibaba.com \
--cc=edumazet@google.com \
--cc=fred.cc@alibaba-inc.com \
--cc=horms@kernel.org \
--cc=jakub@cloudflare.com \
--cc=kuba@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=steffen.klassert@secunet.com \
--cc=willemdebruijn.kernel@gmail.com \
--cc=yubing.qiuyubing@alibaba-inc.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox