BPF List
 help / color / mirror / Atom feed
From: Martin KaFai Lau <kafai@fb.com>
To: <bpf@vger.kernel.org>, <netdev@vger.kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>,
	Andrii Nakryiko <andrii@kernel.org>,
	Daniel Borkmann <daniel@iogearbox.net>,
	David Miller <davem@davemloft.net>,
	Eric Dumazet <edumazet@google.com>,
	Jakub Kicinski <kuba@kernel.org>, <kernel-team@fb.com>,
	Paolo Abeni <pabeni@redhat.com>,
	Stanislav Fomichev <sdf@google.com>
Subject: [PATCH v4 bpf-next 11/15] bpf: Change bpf_setsockopt(SOL_TCP) to reuse do_tcp_setsockopt()
Date: Tue, 16 Aug 2022 23:18:19 -0700	[thread overview]
Message-ID: <20220817061819.4180146-1-kafai@fb.com> (raw)
In-Reply-To: <20220817061704.4174272-1-kafai@fb.com>

After the prep work in the previous patches,
this patch removes all the dup code from bpf_setsockopt(SOL_TCP)
and reuses the do_tcp_setsockopt().

The existing optname white-list is refactored into a new
function sol_tcp_setsockopt().  The sol_tcp_setsockopt()
also calls the bpf_sol_tcp_setsockopt() to handle
the TCP_BPF_XXX specific optnames.

bpf_setsockopt(TCP_SAVE_SYN) now also allows a value 2 to
save the eth header also and it comes for free from
do_tcp_setsockopt().

Reviewed-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
---
 include/net/tcp.h |  2 +
 net/core/filter.c | 97 +++++++++++++++--------------------------------
 net/ipv4/tcp.c    |  4 +-
 3 files changed, 34 insertions(+), 69 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index d10962b9f0d0..c03a50c72f40 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -405,6 +405,8 @@ __poll_t tcp_poll(struct file *file, struct socket *sock,
 int tcp_getsockopt(struct sock *sk, int level, int optname,
 		   char __user *optval, int __user *optlen);
 bool tcp_bpf_bypass_getsockopt(int level, int optname);
+int do_tcp_setsockopt(struct sock *sk, int level, int optname,
+		      sockptr_t optval, unsigned int optlen);
 int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
 		   unsigned int optlen);
 void tcp_set_keepalive(struct sock *sk, int val);
diff --git a/net/core/filter.c b/net/core/filter.c
index bb135d456a53..66877605bb78 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5086,6 +5086,34 @@ static int bpf_sol_tcp_setsockopt(struct sock *sk, int optname,
 	return 0;
 }
 
+static int sol_tcp_setsockopt(struct sock *sk, int optname,
+			      char *optval, int optlen)
+{
+	if (sk->sk_prot->setsockopt != tcp_setsockopt)
+		return -EINVAL;
+
+	switch (optname) {
+	case TCP_KEEPIDLE:
+	case TCP_KEEPINTVL:
+	case TCP_KEEPCNT:
+	case TCP_SYNCNT:
+	case TCP_WINDOW_CLAMP:
+	case TCP_USER_TIMEOUT:
+	case TCP_NOTSENT_LOWAT:
+	case TCP_SAVE_SYN:
+		if (optlen != sizeof(int))
+			return -EINVAL;
+		break;
+	case TCP_CONGESTION:
+		break;
+	default:
+		return bpf_sol_tcp_setsockopt(sk, optname, optval, optlen);
+	}
+
+	return do_tcp_setsockopt(sk, SOL_TCP, optname,
+				 KERNEL_SOCKPTR(optval), optlen);
+}
+
 static int __bpf_setsockopt(struct sock *sk, int level, int optname,
 			    char *optval, int optlen)
 {
@@ -5138,73 +5166,8 @@ static int __bpf_setsockopt(struct sock *sk, int level, int optname,
 		default:
 			ret = -EINVAL;
 		}
-	} else if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP &&
-		   sk->sk_prot->setsockopt == tcp_setsockopt) {
-		if (optname >= TCP_BPF_IW)
-			return bpf_sol_tcp_setsockopt(sk, optname,
-						      optval, optlen);
-
-		if (optname == TCP_CONGESTION) {
-			char name[TCP_CA_NAME_MAX];
-
-			strncpy(name, optval, min_t(long, optlen,
-						    TCP_CA_NAME_MAX-1));
-			name[TCP_CA_NAME_MAX-1] = 0;
-			ret = tcp_set_congestion_control(sk, name, false, true);
-		} else {
-			struct inet_connection_sock *icsk = inet_csk(sk);
-			struct tcp_sock *tp = tcp_sk(sk);
-
-			if (optlen != sizeof(int))
-				return -EINVAL;
-
-			val = *((int *)optval);
-			/* Only some options are supported */
-			switch (optname) {
-			case TCP_SAVE_SYN:
-				if (val < 0 || val > 1)
-					ret = -EINVAL;
-				else
-					tp->save_syn = val;
-				break;
-			case TCP_KEEPIDLE:
-				ret = tcp_sock_set_keepidle_locked(sk, val);
-				break;
-			case TCP_KEEPINTVL:
-				if (val < 1 || val > MAX_TCP_KEEPINTVL)
-					ret = -EINVAL;
-				else
-					tp->keepalive_intvl = val * HZ;
-				break;
-			case TCP_KEEPCNT:
-				if (val < 1 || val > MAX_TCP_KEEPCNT)
-					ret = -EINVAL;
-				else
-					tp->keepalive_probes = val;
-				break;
-			case TCP_SYNCNT:
-				if (val < 1 || val > MAX_TCP_SYNCNT)
-					ret = -EINVAL;
-				else
-					icsk->icsk_syn_retries = val;
-				break;
-			case TCP_USER_TIMEOUT:
-				if (val < 0)
-					ret = -EINVAL;
-				else
-					icsk->icsk_user_timeout = val;
-				break;
-			case TCP_NOTSENT_LOWAT:
-				tp->notsent_lowat = val;
-				sk->sk_write_space(sk);
-				break;
-			case TCP_WINDOW_CLAMP:
-				ret = tcp_set_window_clamp(sk, val);
-				break;
-			default:
-				ret = -EINVAL;
-			}
-		}
+	} else if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP) {
+		return sol_tcp_setsockopt(sk, optname, optval, optlen);
 	} else {
 		ret = -EINVAL;
 	}
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index cfed84b1883f..a6986f201f92 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3479,8 +3479,8 @@ int tcp_set_window_clamp(struct sock *sk, int val)
 /*
  *	Socket option code for TCP.
  */
-static int do_tcp_setsockopt(struct sock *sk, int level, int optname,
-		sockptr_t optval, unsigned int optlen)
+int do_tcp_setsockopt(struct sock *sk, int level, int optname,
+		      sockptr_t optval, unsigned int optlen)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
-- 
2.30.2


  parent reply	other threads:[~2022-08-17  7:11 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-08-17  6:17 [PATCH v4 bpf-next 00/15] bpf: net: Remove duplicated code from bpf_setsockopt() Martin KaFai Lau
2022-08-17  6:17 ` [PATCH v4 bpf-next 01/15] net: Add sk_setsockopt() to take the sk ptr instead of the sock ptr Martin KaFai Lau
2022-08-17  6:17 ` [PATCH v4 bpf-next 02/15] bpf: net: Avoid sk_setsockopt() taking sk lock when called from bpf Martin KaFai Lau
2022-08-17  6:17 ` [PATCH v4 bpf-next 03/15] bpf: net: Consider has_current_bpf_ctx() when testing capable() in sk_setsockopt() Martin KaFai Lau
2022-08-17  6:17 ` [PATCH v4 bpf-next 04/15] bpf: net: Change do_tcp_setsockopt() to use the sockopt's lock_sock() and capable() Martin KaFai Lau
2022-08-17  6:17 ` [PATCH v4 bpf-next 05/15] bpf: net: Change do_ip_setsockopt() " Martin KaFai Lau
2022-08-17  6:17 ` [PATCH v4 bpf-next 06/15] bpf: net: Change do_ipv6_setsockopt() " Martin KaFai Lau
2022-08-17  6:17 ` [PATCH v4 bpf-next 07/15] bpf: Initialize the bpf_run_ctx in bpf_iter_run_prog() Martin KaFai Lau
2022-08-17  6:17 ` [PATCH v4 bpf-next 08/15] bpf: Embed kernel CONFIG check into the if statement in bpf_setsockopt Martin KaFai Lau
2022-08-17  6:18 ` [PATCH v4 bpf-next 09/15] bpf: Change bpf_setsockopt(SOL_SOCKET) to reuse sk_setsockopt() Martin KaFai Lau
2022-08-17  6:18 ` [PATCH v4 bpf-next 10/15] bpf: Refactor bpf specific tcp optnames to a new function Martin KaFai Lau
2022-08-17  6:18 ` Martin KaFai Lau [this message]
2022-08-17  6:18 ` [PATCH v4 bpf-next 12/15] bpf: Change bpf_setsockopt(SOL_IP) to reuse do_ip_setsockopt() Martin KaFai Lau
2022-08-17  6:18 ` [PATCH v4 bpf-next 13/15] bpf: Change bpf_setsockopt(SOL_IPV6) to reuse do_ipv6_setsockopt() Martin KaFai Lau
2022-08-17  6:18 ` [PATCH v4 bpf-next 14/15] bpf: Add a few optnames to bpf_setsockopt Martin KaFai Lau
2022-08-17  6:18 ` [PATCH v4 bpf-next 15/15] selftests/bpf: bpf_setsockopt tests Martin KaFai Lau
2022-08-19  0:20 ` [PATCH v4 bpf-next 00/15] bpf: net: Remove duplicated code from bpf_setsockopt() patchwork-bot+netdevbpf

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=20220817061819.4180146-1-kafai@fb.com \
    --to=kafai@fb.com \
    --cc=andrii@kernel.org \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=kernel-team@fb.com \
    --cc=kuba@kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=sdf@google.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