From: Lorenz Bauer <lmb@isovalent.com>
To: "David S. Miller" <davem@davemloft.net>,
Eric Dumazet <edumazet@google.com>,
Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
David Ahern <dsahern@kernel.org>,
Willem de Bruijn <willemdebruijn.kernel@gmail.com>,
Alexei Starovoitov <ast@kernel.org>,
Daniel Borkmann <daniel@iogearbox.net>,
Andrii Nakryiko <andrii@kernel.org>,
Martin KaFai Lau <martin.lau@linux.dev>,
Song Liu <song@kernel.org>, Yonghong Song <yhs@fb.com>,
John Fastabend <john.fastabend@gmail.com>,
KP Singh <kpsingh@kernel.org>,
Stanislav Fomichev <sdf@google.com>, Hao Luo <haoluo@google.com>,
Jiri Olsa <jolsa@kernel.org>, Joe Stringer <joe@wand.net.nz>,
Mykola Lysenko <mykolal@fb.com>, Shuah Khan <shuah@kernel.org>,
Kuniyuki Iwashima <kuniyu@amazon.com>
Cc: Hemanth Malla <hemanthmalla@gmail.com>,
netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
bpf@vger.kernel.org, linux-kselftest@vger.kernel.org,
Lorenz Bauer <lmb@isovalent.com>
Subject: [PATCH bpf-next v2 3/6] net: remove duplicate reuseport_lookup functions
Date: Tue, 13 Jun 2023 11:14:58 +0100 [thread overview]
Message-ID: <20230613-so-reuseport-v2-3-b7c69a342613@isovalent.com> (raw)
In-Reply-To: <20230613-so-reuseport-v2-0-b7c69a342613@isovalent.com>
There are currently four copies of reuseport_lookup: one each for
(TCP, UDP)x(IPv4, IPv6). This forces us to duplicate all callers of
those functions as well. This is already the case for sk_lookup
helpers (inet,inet6,udp4,udp6)_lookup_run_bpf.
The only difference between the reuseport_lookup helpers is calling
a different hash function. Cut down the number of reuseport_lookup
functions to one per IP version by using the INDIRECT_CALL
infrastructure.
Signed-off-by: Lorenz Bauer <lmb@isovalent.com>
---
include/net/inet6_hashtables.h | 11 ++++++++++-
include/net/inet_hashtables.h | 15 +++++++++-----
net/ipv4/inet_hashtables.c | 22 ++++++++++++++-------
net/ipv4/udp.c | 37 +++++++++++-----------------------
net/ipv6/inet6_hashtables.c | 16 +++++++++++----
net/ipv6/udp.c | 45 +++++++++++++++---------------------------
6 files changed, 75 insertions(+), 71 deletions(-)
diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index 032ddab48f8f..49d586454287 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -48,12 +48,21 @@ struct sock *__inet6_lookup_established(struct net *net,
const u16 hnum, const int dif,
const int sdif);
+typedef u32 (*inet6_ehashfn_t)(const struct net *net,
+ const struct in6_addr *laddr, const u16 lport,
+ const struct in6_addr *faddr, const __be16 fport);
+
+u32 inet6_ehashfn(const struct net *net,
+ const struct in6_addr *laddr, const u16 lport,
+ const struct in6_addr *faddr, const __be16 fport);
+
struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk,
struct sk_buff *skb, int doff,
const struct in6_addr *saddr,
__be16 sport,
const struct in6_addr *daddr,
- unsigned short hnum);
+ unsigned short hnum,
+ inet6_ehashfn_t ehashfn);
struct sock *inet6_lookup_listener(struct net *net,
struct inet_hashinfo *hashinfo,
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 8734f3488f5d..51ab6a1a3601 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -379,10 +379,19 @@ struct sock *__inet_lookup_established(struct net *net,
const __be32 daddr, const u16 hnum,
const int dif, const int sdif);
+typedef u32 (*inet_ehashfn_t)(const struct net *net,
+ const __be32 laddr, const __u16 lport,
+ const __be32 faddr, const __be16 fport);
+
+u32 inet_ehashfn(const struct net *net,
+ const __be32 laddr, const __u16 lport,
+ const __be32 faddr, const __be16 fport);
+
struct sock *inet_lookup_reuseport(struct net *net, struct sock *sk,
struct sk_buff *skb, int doff,
__be32 saddr, __be16 sport,
- __be32 daddr, unsigned short hnum);
+ __be32 daddr, unsigned short hnum,
+ inet_ehashfn_t ehashfn);
static inline struct sock *
inet_lookup_established(struct net *net, struct inet_hashinfo *hashinfo,
@@ -453,10 +462,6 @@ static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo,
refcounted);
}
-u32 inet6_ehashfn(const struct net *net,
- const struct in6_addr *laddr, const u16 lport,
- const struct in6_addr *faddr, const __be16 fport);
-
static inline void sk_daddr_set(struct sock *sk, __be32 addr)
{
sk->sk_daddr = addr; /* alias of inet_daddr */
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 91f9210d4e83..1ec895fd9905 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -28,9 +28,9 @@
#include <net/tcp.h>
#include <net/sock_reuseport.h>
-static u32 inet_ehashfn(const struct net *net, const __be32 laddr,
- const __u16 lport, const __be32 faddr,
- const __be16 fport)
+u32 inet_ehashfn(const struct net *net, const __be32 laddr,
+ const __u16 lport, const __be32 faddr,
+ const __be16 fport)
{
static u32 inet_ehash_secret __read_mostly;
@@ -332,6 +332,10 @@ static inline int compute_score(struct sock *sk, struct net *net,
return score;
}
+INDIRECT_CALLABLE_DECLARE(u32 udp_ehashfn(const struct net *,
+ const __be32, const __u16,
+ const __be32, const __be16));
+
/**
* inet_lookup_reuseport() - execute reuseport logic on AF_INET socket if necessary.
* @net: network namespace.
@@ -342,6 +346,7 @@ static inline int compute_score(struct sock *sk, struct net *net,
* @sport: source port.
* @daddr: destination address.
* @hnum: destination port in host byte order.
+ * @ehashfn: hash function used to generate the fallback hash.
*
* Return: NULL if sk doesn't have SO_REUSEPORT set, otherwise a pointer to
* the selected sock or an error.
@@ -349,13 +354,15 @@ static inline int compute_score(struct sock *sk, struct net *net,
struct sock *inet_lookup_reuseport(struct net *net, struct sock *sk,
struct sk_buff *skb, int doff,
__be32 saddr, __be16 sport,
- __be32 daddr, unsigned short hnum)
+ __be32 daddr, unsigned short hnum,
+ inet_ehashfn_t ehashfn)
{
struct sock *reuse_sk = NULL;
u32 phash;
if (sk->sk_reuseport) {
- phash = inet_ehashfn(net, daddr, hnum, saddr, sport);
+ phash = INDIRECT_CALL_2(ehashfn, inet_ehashfn, udp_ehashfn,
+ net, daddr, hnum, saddr, sport);
reuse_sk = reuseport_select_sock(sk, phash, skb, doff);
}
return reuse_sk;
@@ -385,7 +392,7 @@ static struct sock *inet_lhash2_lookup(struct net *net,
score = compute_score(sk, net, hnum, daddr, dif, sdif);
if (score > hiscore) {
result = inet_lookup_reuseport(net, sk, skb, doff,
- saddr, sport, daddr, hnum);
+ saddr, sport, daddr, hnum, inet_ehashfn);
if (result)
return result;
@@ -414,7 +421,8 @@ static inline struct sock *inet_lookup_run_bpf(struct net *net,
if (no_reuseport || IS_ERR_OR_NULL(sk))
return sk;
- reuse_sk = inet_lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum);
+ reuse_sk = inet_lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum,
+ inet_ehashfn);
if (reuse_sk)
sk = reuse_sk;
return sk;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index fd3dae081f3a..10468fe144d0 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -405,9 +405,9 @@ static int compute_score(struct sock *sk, struct net *net,
return score;
}
-static u32 udp_ehashfn(const struct net *net, const __be32 laddr,
- const __u16 lport, const __be32 faddr,
- const __be16 fport)
+INDIRECT_CALLABLE_SCOPE
+u32 udp_ehashfn(const struct net *net, const __be32 laddr, const __u16 lport,
+ const __be32 faddr, const __be16 fport)
{
static u32 udp_ehash_secret __read_mostly;
@@ -417,22 +417,6 @@ static u32 udp_ehashfn(const struct net *net, const __be32 laddr,
udp_ehash_secret + net_hash_mix(net));
}
-static struct sock *lookup_reuseport(struct net *net, struct sock *sk,
- struct sk_buff *skb,
- __be32 saddr, __be16 sport,
- __be32 daddr, unsigned short hnum)
-{
- struct sock *reuse_sk = NULL;
- u32 hash;
-
- if (sk->sk_reuseport && sk->sk_state != TCP_ESTABLISHED) {
- hash = udp_ehashfn(net, daddr, hnum, saddr, sport);
- reuse_sk = reuseport_select_sock(sk, hash, skb,
- sizeof(struct udphdr));
- }
- return reuse_sk;
-}
-
/* called with rcu_read_lock() */
static struct sock *udp4_lib_lookup2(struct net *net,
__be32 saddr, __be16 sport,
@@ -450,11 +434,13 @@ static struct sock *udp4_lib_lookup2(struct net *net,
score = compute_score(sk, net, saddr, sport,
daddr, hnum, dif, sdif);
if (score > badness) {
- result = lookup_reuseport(net, sk, skb,
- saddr, sport, daddr, hnum);
- /* Fall back to scoring if group has connections */
- if (result && !reuseport_has_conns(sk))
- return result;
+ if (sk->sk_state != TCP_ESTABLISHED) {
+ result = inet_lookup_reuseport(net, sk, skb, sizeof(struct udphdr),
+ saddr, sport, daddr, hnum, udp_ehashfn);
+ /* Fall back to scoring if group has connections */
+ if (result && !reuseport_has_conns(sk))
+ return result;
+ }
result = result ? : sk;
badness = score;
@@ -480,7 +466,8 @@ static struct sock *udp4_lookup_run_bpf(struct net *net,
if (no_reuseport || IS_ERR_OR_NULL(sk))
return sk;
- reuse_sk = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum);
+ reuse_sk = inet_lookup_reuseport(net, sk, skb, sizeof(struct udphdr),
+ saddr, sport, daddr, hnum, udp_ehashfn);
if (reuse_sk)
sk = reuse_sk;
return sk;
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 208998694ae3..a350ee40141c 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -111,6 +111,10 @@ static inline int compute_score(struct sock *sk, struct net *net,
return score;
}
+INDIRECT_CALLABLE_DECLARE(u32 udp6_ehashfn(const struct net *,
+ const struct in6_addr *, const u16,
+ const struct in6_addr *, const __be16));
+
/**
* inet6_lookup_reuseport() - execute reuseport logic on AF_INET6 socket if necessary.
* @net: network namespace.
@@ -121,6 +125,7 @@ static inline int compute_score(struct sock *sk, struct net *net,
* @sport: source port.
* @daddr: destination address.
* @hnum: destination port in host byte order.
+ * @ehashfn: hash function used to generate the fallback hash.
*
* Return: NULL if sk doesn't have SO_REUSEPORT set, otherwise a pointer to
* the selected sock or an error.
@@ -130,13 +135,15 @@ struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk,
const struct in6_addr *saddr,
__be16 sport,
const struct in6_addr *daddr,
- unsigned short hnum)
+ unsigned short hnum,
+ inet6_ehashfn_t ehashfn)
{
struct sock *reuse_sk = NULL;
u32 phash;
if (sk->sk_reuseport) {
- phash = inet6_ehashfn(net, daddr, hnum, saddr, sport);
+ phash = INDIRECT_CALL_2(ehashfn, inet6_ehashfn, udp6_ehashfn,
+ net, daddr, hnum, saddr, sport);
reuse_sk = reuseport_select_sock(sk, phash, skb, doff);
}
return reuse_sk;
@@ -159,7 +166,7 @@ static struct sock *inet6_lhash2_lookup(struct net *net,
score = compute_score(sk, net, hnum, daddr, dif, sdif);
if (score > hiscore) {
result = inet6_lookup_reuseport(net, sk, skb, doff,
- saddr, sport, daddr, hnum);
+ saddr, sport, daddr, hnum, inet6_ehashfn);
if (result)
return result;
@@ -190,7 +197,8 @@ static inline struct sock *inet6_lookup_run_bpf(struct net *net,
if (no_reuseport || IS_ERR_OR_NULL(sk))
return sk;
- reuse_sk = inet6_lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum);
+ reuse_sk = inet6_lookup_reuseport(net, sk, skb, doff,
+ saddr, sport, daddr, hnum, inet6_ehashfn);
if (reuse_sk)
sk = reuse_sk;
return sk;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index e5a337e6b970..2af3a595f38a 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -70,11 +70,12 @@ int udpv6_init_sock(struct sock *sk)
return 0;
}
-static u32 udp6_ehashfn(const struct net *net,
- const struct in6_addr *laddr,
- const u16 lport,
- const struct in6_addr *faddr,
- const __be16 fport)
+INDIRECT_CALLABLE_SCOPE
+u32 udp6_ehashfn(const struct net *net,
+ const struct in6_addr *laddr,
+ const u16 lport,
+ const struct in6_addr *faddr,
+ const __be16 fport)
{
static u32 udp6_ehash_secret __read_mostly;
static u32 udp_ipv6_hash_secret __read_mostly;
@@ -159,24 +160,6 @@ static int compute_score(struct sock *sk, struct net *net,
return score;
}
-static struct sock *lookup_reuseport(struct net *net, struct sock *sk,
- struct sk_buff *skb,
- const struct in6_addr *saddr,
- __be16 sport,
- const struct in6_addr *daddr,
- unsigned int hnum)
-{
- struct sock *reuse_sk = NULL;
- u32 hash;
-
- if (sk->sk_reuseport && sk->sk_state != TCP_ESTABLISHED) {
- hash = udp6_ehashfn(net, daddr, hnum, saddr, sport);
- reuse_sk = reuseport_select_sock(sk, hash, skb,
- sizeof(struct udphdr));
- }
- return reuse_sk;
-}
-
/* called with rcu_read_lock() */
static struct sock *udp6_lib_lookup2(struct net *net,
const struct in6_addr *saddr, __be16 sport,
@@ -193,11 +176,14 @@ static struct sock *udp6_lib_lookup2(struct net *net,
score = compute_score(sk, net, saddr, sport,
daddr, hnum, dif, sdif);
if (score > badness) {
- result = lookup_reuseport(net, sk, skb,
- saddr, sport, daddr, hnum);
- /* Fall back to scoring if group has connections */
- if (result && !reuseport_has_conns(sk))
- return result;
+ if (sk->sk_state != TCP_ESTABLISHED) {
+ result = inet6_lookup_reuseport(net, sk, skb, sizeof(struct udphdr),
+ saddr, sport, daddr, hnum,
+ udp6_ehashfn);
+ /* Fall back to scoring if group has connections */
+ if (result && !reuseport_has_conns(sk))
+ return result;
+ }
result = result ? : sk;
badness = score;
@@ -225,7 +211,8 @@ static inline struct sock *udp6_lookup_run_bpf(struct net *net,
if (no_reuseport || IS_ERR_OR_NULL(sk))
return sk;
- reuse_sk = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum);
+ reuse_sk = inet6_lookup_reuseport(net, sk, skb, sizeof(struct udphdr),
+ saddr, sport, daddr, hnum, udp6_ehashfn);
if (reuse_sk)
sk = reuse_sk;
return sk;
--
2.40.1
next prev parent reply other threads:[~2023-06-13 10:15 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-06-13 10:14 [PATCH bpf-next v2 0/6] Add SO_REUSEPORT support for TC bpf_sk_assign Lorenz Bauer
2023-06-13 10:14 ` [PATCH bpf-next v2 1/6] net: export inet_lookup_reuseport and inet6_lookup_reuseport Lorenz Bauer
2023-06-13 10:14 ` [PATCH bpf-next v2 2/6] net: document inet[6]_lookup_reuseport sk_state requirements Lorenz Bauer
2023-06-13 10:14 ` Lorenz Bauer [this message]
2023-06-13 15:32 ` [PATCH bpf-next v2 3/6] net: remove duplicate reuseport_lookup functions Simon Horman
2023-06-14 15:42 ` Lorenz Bauer
2023-06-15 7:21 ` Simon Horman
2023-06-13 17:26 ` kernel test robot
2023-06-13 18:56 ` Kuniyuki Iwashima
2023-06-14 15:25 ` Lorenz Bauer
2023-06-14 16:52 ` Kuniyuki Iwashima
2023-06-20 14:26 ` Lorenz Bauer
2023-06-20 18:31 ` Kuniyuki Iwashima
2023-06-21 8:01 ` Lorenz Bauer
2023-06-21 13:49 ` Lorenz Bauer
2023-06-21 15:00 ` Kuniyuki Iwashima
2023-06-13 10:14 ` [PATCH bpf-next v2 4/6] net: remove duplicate sk_lookup helpers Lorenz Bauer
2023-06-13 19:03 ` Kuniyuki Iwashima
2023-06-13 19:41 ` kernel test robot
2023-06-13 10:15 ` [PATCH bpf-next v2 5/6] bpf, net: Support SO_REUSEPORT sockets with bpf_sk_assign Lorenz Bauer
2023-06-13 17:26 ` kernel test robot
2023-06-13 10:15 ` [PATCH bpf-next v2 6/6] selftests/bpf: Test that SO_REUSEPORT can be used with sk_assign helper Lorenz Bauer
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=20230613-so-reuseport-v2-3-b7c69a342613@isovalent.com \
--to=lmb@isovalent.com \
--cc=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=davem@davemloft.net \
--cc=dsahern@kernel.org \
--cc=edumazet@google.com \
--cc=haoluo@google.com \
--cc=hemanthmalla@gmail.com \
--cc=joe@wand.net.nz \
--cc=john.fastabend@gmail.com \
--cc=jolsa@kernel.org \
--cc=kpsingh@kernel.org \
--cc=kuba@kernel.org \
--cc=kuniyu@amazon.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-kselftest@vger.kernel.org \
--cc=martin.lau@linux.dev \
--cc=mykolal@fb.com \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=sdf@google.com \
--cc=shuah@kernel.org \
--cc=song@kernel.org \
--cc=willemdebruijn.kernel@gmail.com \
--cc=yhs@fb.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.