From: Kuniyuki Iwashima <kuniyu@amazon.com>
To: <lmb@isovalent.com>
Cc: <andrii@kernel.org>, <ast@kernel.org>, <bpf@vger.kernel.org>,
<daniel@iogearbox.net>, <davem@davemloft.net>,
<dsahern@kernel.org>, <edumazet@google.com>, <haoluo@google.com>,
<hemanthmalla@gmail.com>, <joe@wand.net.nz>,
<john.fastabend@gmail.com>, <jolsa@kernel.org>,
<kpsingh@kernel.org>, <kuba@kernel.org>, <kuniyu@amazon.com>,
<linux-kernel@vger.kernel.org>, <linux-kselftest@vger.kernel.org>,
<martin.lau@linux.dev>, <mykolal@fb.com>,
<netdev@vger.kernel.org>, <pabeni@redhat.com>, <sdf@google.com>,
<shuah@kernel.org>, <song@kernel.org>,
<willemdebruijn.kernel@gmail.com>, <yhs@fb.com>
Subject: Re: [PATCH bpf-next v3 5/7] net: remove duplicate sk_lookup helpers
Date: Mon, 26 Jun 2023 13:02:38 -0700 [thread overview]
Message-ID: <20230626200238.75316-1-kuniyu@amazon.com> (raw)
In-Reply-To: <20230613-so-reuseport-v3-5-907b4cbb7b99@isovalent.com>
From: Lorenz Bauer <lmb@isovalent.com>
Date: Mon, 26 Jun 2023 16:09:02 +0100
> Now that inet[6]_lookup_reuseport are parameterised on the ehashfn
> we can remove two sk_lookup helpers.
>
> Signed-off-by: Lorenz Bauer <lmb@isovalent.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
> ---
> include/net/inet6_hashtables.h | 9 +++++++++
> include/net/inet_hashtables.h | 7 +++++++
> net/ipv4/inet_hashtables.c | 26 +++++++++++++-------------
> net/ipv4/udp.c | 32 +++++---------------------------
> net/ipv6/inet6_hashtables.c | 31 ++++++++++++++++---------------
> net/ipv6/udp.c | 34 +++++-----------------------------
> 6 files changed, 55 insertions(+), 84 deletions(-)
>
> diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
> index 49d586454287..4d2a1a3c0be7 100644
> --- a/include/net/inet6_hashtables.h
> +++ b/include/net/inet6_hashtables.h
> @@ -73,6 +73,15 @@ struct sock *inet6_lookup_listener(struct net *net,
> const unsigned short hnum,
> const int dif, const int sdif);
>
> +struct sock *inet6_lookup_run_sk_lookup(struct net *net,
> + int protocol,
> + struct sk_buff *skb, int doff,
> + const struct in6_addr *saddr,
> + const __be16 sport,
> + const struct in6_addr *daddr,
> + const u16 hnum, const int dif,
> + inet6_ehashfn_t ehashfn);
> +
> static inline struct sock *__inet6_lookup(struct net *net,
> struct inet_hashinfo *hashinfo,
> struct sk_buff *skb, int doff,
> diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
> index 51ab6a1a3601..aa02f1db1f86 100644
> --- a/include/net/inet_hashtables.h
> +++ b/include/net/inet_hashtables.h
> @@ -393,6 +393,13 @@ struct sock *inet_lookup_reuseport(struct net *net, struct sock *sk,
> __be32 daddr, unsigned short hnum,
> inet_ehashfn_t ehashfn);
>
> +struct sock *inet_lookup_run_sk_lookup(struct net *net,
> + int protocol,
> + struct sk_buff *skb, int doff,
> + __be32 saddr, __be16 sport,
> + __be32 daddr, u16 hnum, const int dif,
> + inet_ehashfn_t ehashfn);
> +
> static inline struct sock *
> inet_lookup_established(struct net *net, struct inet_hashinfo *hashinfo,
> const __be32 saddr, const __be16 sport,
> diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
> index 0dd768ab22d9..34e44a096795 100644
> --- a/net/ipv4/inet_hashtables.c
> +++ b/net/ipv4/inet_hashtables.c
> @@ -405,25 +405,23 @@ static struct sock *inet_lhash2_lookup(struct net *net,
> return result;
> }
>
> -static inline struct sock *inet_lookup_run_bpf(struct net *net,
> - struct inet_hashinfo *hashinfo,
> - struct sk_buff *skb, int doff,
> - __be32 saddr, __be16 sport,
> - __be32 daddr, u16 hnum, const int dif)
> +struct sock *inet_lookup_run_sk_lookup(struct net *net,
> + int protocol,
> + struct sk_buff *skb, int doff,
> + __be32 saddr, __be16 sport,
> + __be32 daddr, u16 hnum, const int dif,
> + inet_ehashfn_t ehashfn)
> {
> struct sock *sk, *reuse_sk;
> bool no_reuseport;
>
> - if (hashinfo != net->ipv4.tcp_death_row.hashinfo)
> - return NULL; /* only TCP is supported */
> -
> - no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_TCP, saddr, sport,
> + no_reuseport = bpf_sk_lookup_run_v4(net, protocol, saddr, sport,
> daddr, hnum, dif, &sk);
> if (no_reuseport || IS_ERR_OR_NULL(sk))
> return sk;
>
> reuse_sk = inet_lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum,
> - inet_ehashfn);
> + ehashfn);
> if (reuse_sk)
> sk = reuse_sk;
> return sk;
> @@ -441,9 +439,11 @@ struct sock *__inet_lookup_listener(struct net *net,
> unsigned int hash2;
>
> /* Lookup redirect from BPF */
> - if (static_branch_unlikely(&bpf_sk_lookup_enabled)) {
> - result = inet_lookup_run_bpf(net, hashinfo, skb, doff,
> - saddr, sport, daddr, hnum, dif);
> + if (static_branch_unlikely(&bpf_sk_lookup_enabled) &&
> + hashinfo == net->ipv4.tcp_death_row.hashinfo) {
> + result = inet_lookup_run_sk_lookup(net, IPPROTO_TCP, skb, doff,
> + saddr, sport, daddr, hnum, dif,
> + inet_ehashfn);
> if (result)
> goto done;
> }
> diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
> index 7258edece691..eb79268f216d 100644
> --- a/net/ipv4/udp.c
> +++ b/net/ipv4/udp.c
> @@ -464,30 +464,6 @@ static struct sock *udp4_lib_lookup2(struct net *net,
> return result;
> }
>
> -static struct sock *udp4_lookup_run_bpf(struct net *net,
> - struct udp_table *udptable,
> - struct sk_buff *skb,
> - __be32 saddr, __be16 sport,
> - __be32 daddr, u16 hnum, const int dif)
> -{
> - struct sock *sk, *reuse_sk;
> - bool no_reuseport;
> -
> - if (udptable != net->ipv4.udp_table)
> - return NULL; /* only UDP is supported */
> -
> - no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_UDP, saddr, sport,
> - daddr, hnum, dif, &sk);
> - if (no_reuseport || IS_ERR_OR_NULL(sk))
> - return sk;
> -
> - 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;
> -}
> -
> /* UDP is nearly always wildcards out the wazoo, it makes no sense to try
> * harder than this. -DaveM
> */
> @@ -512,9 +488,11 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
> goto done;
>
> /* Lookup redirect from BPF */
> - if (static_branch_unlikely(&bpf_sk_lookup_enabled)) {
> - sk = udp4_lookup_run_bpf(net, udptable, skb,
> - saddr, sport, daddr, hnum, dif);
> + if (static_branch_unlikely(&bpf_sk_lookup_enabled) &&
> + udptable == net->ipv4.udp_table) {
> + sk = inet_lookup_run_sk_lookup(net, IPPROTO_UDP, skb, sizeof(struct udphdr),
> + saddr, sport, daddr, hnum, dif,
> + udp_ehashfn);
> if (sk) {
> result = sk;
> goto done;
> diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
> index b5de1642bc51..e908aa3cb7ea 100644
> --- a/net/ipv6/inet6_hashtables.c
> +++ b/net/ipv6/inet6_hashtables.c
> @@ -179,31 +179,30 @@ static struct sock *inet6_lhash2_lookup(struct net *net,
> return result;
> }
>
> -static inline struct sock *inet6_lookup_run_bpf(struct net *net,
> - struct inet_hashinfo *hashinfo,
> - struct sk_buff *skb, int doff,
> - const struct in6_addr *saddr,
> - const __be16 sport,
> - const struct in6_addr *daddr,
> - const u16 hnum, const int dif)
> +struct sock *inet6_lookup_run_sk_lookup(struct net *net,
> + int protocol,
> + struct sk_buff *skb, int doff,
> + const struct in6_addr *saddr,
> + const __be16 sport,
> + const struct in6_addr *daddr,
> + const u16 hnum, const int dif,
> + inet6_ehashfn_t ehashfn)
> {
> struct sock *sk, *reuse_sk;
> bool no_reuseport;
>
> - if (hashinfo != net->ipv4.tcp_death_row.hashinfo)
> - return NULL; /* only TCP is supported */
> -
> - no_reuseport = bpf_sk_lookup_run_v6(net, IPPROTO_TCP, saddr, sport,
> + no_reuseport = bpf_sk_lookup_run_v6(net, protocol, saddr, sport,
> daddr, hnum, dif, &sk);
> if (no_reuseport || IS_ERR_OR_NULL(sk))
> return sk;
>
> reuse_sk = inet6_lookup_reuseport(net, sk, skb, doff,
> - saddr, sport, daddr, hnum, inet6_ehashfn);
> + saddr, sport, daddr, hnum, ehashfn);
> if (reuse_sk)
> sk = reuse_sk;
> return sk;
> }
> +EXPORT_SYMBOL_GPL(inet6_lookup_run_sk_lookup);
>
> struct sock *inet6_lookup_listener(struct net *net,
> struct inet_hashinfo *hashinfo,
> @@ -217,9 +216,11 @@ struct sock *inet6_lookup_listener(struct net *net,
> unsigned int hash2;
>
> /* Lookup redirect from BPF */
> - if (static_branch_unlikely(&bpf_sk_lookup_enabled)) {
> - result = inet6_lookup_run_bpf(net, hashinfo, skb, doff,
> - saddr, sport, daddr, hnum, dif);
> + if (static_branch_unlikely(&bpf_sk_lookup_enabled) &&
> + hashinfo == net->ipv4.tcp_death_row.hashinfo) {
> + result = inet6_lookup_run_sk_lookup(net, IPPROTO_TCP, skb, doff,
> + saddr, sport, daddr, hnum, dif,
> + inet6_ehashfn);
> if (result)
> goto done;
> }
> diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
> index ebac9200b15c..8a6d94cabee0 100644
> --- a/net/ipv6/udp.c
> +++ b/net/ipv6/udp.c
> @@ -205,32 +205,6 @@ static struct sock *udp6_lib_lookup2(struct net *net,
> return result;
> }
>
> -static inline struct sock *udp6_lookup_run_bpf(struct net *net,
> - struct udp_table *udptable,
> - struct sk_buff *skb,
> - const struct in6_addr *saddr,
> - __be16 sport,
> - const struct in6_addr *daddr,
> - u16 hnum, const int dif)
> -{
> - struct sock *sk, *reuse_sk;
> - bool no_reuseport;
> -
> - if (udptable != net->ipv4.udp_table)
> - return NULL; /* only UDP is supported */
> -
> - no_reuseport = bpf_sk_lookup_run_v6(net, IPPROTO_UDP, saddr, sport,
> - daddr, hnum, dif, &sk);
> - if (no_reuseport || IS_ERR_OR_NULL(sk))
> - return sk;
> -
> - 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;
> -}
> -
> /* rcu_read_lock() must be held */
> struct sock *__udp6_lib_lookup(struct net *net,
> const struct in6_addr *saddr, __be16 sport,
> @@ -255,9 +229,11 @@ struct sock *__udp6_lib_lookup(struct net *net,
> goto done;
>
> /* Lookup redirect from BPF */
> - if (static_branch_unlikely(&bpf_sk_lookup_enabled)) {
> - sk = udp6_lookup_run_bpf(net, udptable, skb,
> - saddr, sport, daddr, hnum, dif);
> + if (static_branch_unlikely(&bpf_sk_lookup_enabled) &&
> + udptable == net->ipv4.udp_table) {
> + sk = inet6_lookup_run_sk_lookup(net, IPPROTO_UDP, skb, sizeof(struct udphdr),
> + saddr, sport, daddr, hnum, dif,
> + udp6_ehashfn);
> if (sk) {
> result = sk;
> goto done;
>
> --
> 2.40.1
next prev parent reply other threads:[~2023-06-26 20:03 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-06-26 15:08 [PATCH bpf-next v3 0/7] Add SO_REUSEPORT support for TC bpf_sk_assign Lorenz Bauer
2023-06-26 15:08 ` [PATCH bpf-next v3 1/7] udp: re-score reuseport groups when connected sockets are present Lorenz Bauer
2023-06-26 17:25 ` Kuniyuki Iwashima
2023-06-26 15:08 ` [PATCH bpf-next v3 2/7] net: export inet_lookup_reuseport and inet6_lookup_reuseport Lorenz Bauer
2023-06-26 17:32 ` Kuniyuki Iwashima
2023-06-27 8:56 ` Lorenz Bauer
2023-06-27 10:19 ` Daniel Borkmann
2023-06-26 15:09 ` [PATCH bpf-next v3 3/7] net: document inet[6]_lookup_reuseport sk_state requirements Lorenz Bauer
2023-06-26 17:57 ` Kuniyuki Iwashima
2023-06-26 15:09 ` [PATCH bpf-next v3 4/7] net: remove duplicate reuseport_lookup functions Lorenz Bauer
2023-06-26 18:11 ` Kuniyuki Iwashima
2023-06-26 15:09 ` [PATCH bpf-next v3 5/7] net: remove duplicate sk_lookup helpers Lorenz Bauer
2023-06-26 20:02 ` Kuniyuki Iwashima [this message]
2023-06-26 15:09 ` [PATCH bpf-next v3 6/7] bpf, net: Support SO_REUSEPORT sockets with bpf_sk_assign Lorenz Bauer
2023-06-26 21:08 ` Kuniyuki Iwashima
2023-06-26 21:23 ` Kuniyuki Iwashima
2023-06-26 15:09 ` [PATCH bpf-next v3 7/7] 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=20230626200238.75316-1-kuniyu@amazon.com \
--to=kuniyu@amazon.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=linux-kernel@vger.kernel.org \
--cc=linux-kselftest@vger.kernel.org \
--cc=lmb@isovalent.com \
--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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).