netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Lawrence Brakmo <brakmo@fb.com>
To: netdev <netdev@vger.kernel.org>
Cc: Kernel Team <kernel-team@fb.com>, Blake Matheny <bmatheny@fb.com>,
	Alexei Starovoitov <ast@fb.com>,
	Daniel Borkmann <daniel@iogearbox.net>,
	Eric Dumazet <eric.dumazet@gmail.com>,
	Neal Cardwell <ncardwell@google.com>,
	Yuchung Cheng <ycheng@google.com>
Subject: [PATCH bpf-next v9 05/12] bpf: Support passing args to sock_ops bpf function
Date: Wed, 24 Jan 2018 18:37:05 -0800	[thread overview]
Message-ID: <20180125023712.3038949-6-brakmo@fb.com> (raw)
In-Reply-To: <20180125023712.3038949-1-brakmo@fb.com>

Adds support for passing up to 4 arguments to sock_ops bpf functions. It
reusues the reply union, so the bpf_sock_ops structures are not
increased in size.

Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
---
 include/linux/filter.h   |  1 +
 include/net/tcp.h        | 40 +++++++++++++++++++++++++++++++++++-----
 include/uapi/linux/bpf.h |  5 +++--
 net/ipv4/tcp.c           |  2 +-
 net/ipv4/tcp_nv.c        |  2 +-
 net/ipv4/tcp_output.c    |  2 +-
 6 files changed, 42 insertions(+), 10 deletions(-)

diff --git a/include/linux/filter.h b/include/linux/filter.h
index daa5a67..20384c4 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1003,6 +1003,7 @@ struct bpf_sock_ops_kern {
 	struct	sock *sk;
 	u32	op;
 	union {
+		u32 args[4];
 		u32 reply;
 		u32 replylong[4];
 	};
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 6092eaf..093e967 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2006,7 +2006,7 @@ void tcp_cleanup_ulp(struct sock *sk);
  * program loaded).
  */
 #ifdef CONFIG_BPF
-static inline int tcp_call_bpf(struct sock *sk, int op)
+static inline int tcp_call_bpf(struct sock *sk, int op, u32 nargs, u32 *args)
 {
 	struct bpf_sock_ops_kern sock_ops;
 	int ret;
@@ -2019,6 +2019,8 @@ static inline int tcp_call_bpf(struct sock *sk, int op)
 
 	sock_ops.sk = sk;
 	sock_ops.op = op;
+	if (nargs > 0)
+		memcpy(sock_ops.args, args, nargs * sizeof(*args));
 
 	ret = BPF_CGROUP_RUN_PROG_SOCK_OPS(&sock_ops);
 	if (ret == 0)
@@ -2027,18 +2029,46 @@ static inline int tcp_call_bpf(struct sock *sk, int op)
 		ret = -1;
 	return ret;
 }
+
+static inline int tcp_call_bpf_2arg(struct sock *sk, int op, u32 arg1, u32 arg2)
+{
+	u32 args[2] = {arg1, arg2};
+
+	return tcp_call_bpf(sk, op, 2, args);
+}
+
+static inline int tcp_call_bpf_3arg(struct sock *sk, int op, u32 arg1, u32 arg2,
+				    u32 arg3)
+{
+	u32 args[3] = {arg1, arg2, arg3};
+
+	return tcp_call_bpf(sk, op, 3, args);
+}
+
 #else
-static inline int tcp_call_bpf(struct sock *sk, int op)
+static inline int tcp_call_bpf(struct sock *sk, int op, u32 nargs, u32 *args)
 {
 	return -EPERM;
 }
+
+static inline int tcp_call_bpf_2arg(struct sock *sk, int op, u32 arg1, u32 arg2)
+{
+	return -EPERM;
+}
+
+static inline int tcp_call_bpf_3arg(struct sock *sk, int op, u32 arg1, u32 arg2,
+				    u32 arg3)
+{
+	return -EPERM;
+}
+
 #endif
 
 static inline u32 tcp_timeout_init(struct sock *sk)
 {
 	int timeout;
 
-	timeout = tcp_call_bpf(sk, BPF_SOCK_OPS_TIMEOUT_INIT);
+	timeout = tcp_call_bpf(sk, BPF_SOCK_OPS_TIMEOUT_INIT, 0, NULL);
 
 	if (timeout <= 0)
 		timeout = TCP_TIMEOUT_INIT;
@@ -2049,7 +2079,7 @@ static inline u32 tcp_rwnd_init_bpf(struct sock *sk)
 {
 	int rwnd;
 
-	rwnd = tcp_call_bpf(sk, BPF_SOCK_OPS_RWND_INIT);
+	rwnd = tcp_call_bpf(sk, BPF_SOCK_OPS_RWND_INIT, 0, NULL);
 
 	if (rwnd < 0)
 		rwnd = 0;
@@ -2058,7 +2088,7 @@ static inline u32 tcp_rwnd_init_bpf(struct sock *sk)
 
 static inline bool tcp_bpf_ca_needs_ecn(struct sock *sk)
 {
-	return (tcp_call_bpf(sk, BPF_SOCK_OPS_NEEDS_ECN) == 1);
+	return (tcp_call_bpf(sk, BPF_SOCK_OPS_NEEDS_ECN, 0, NULL) == 1);
 }
 
 #if IS_ENABLED(CONFIG_SMC)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 406c19d..8d5874c 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -952,8 +952,9 @@ struct bpf_map_info {
 struct bpf_sock_ops {
 	__u32 op;
 	union {
-		__u32 reply;
-		__u32 replylong[4];
+		__u32 args[4];		/* Optionally passed to bpf program */
+		__u32 reply;		/* Returned by bpf program	    */
+		__u32 replylong[4];	/* Optionally returned by bpf prog  */
 	};
 	__u32 family;
 	__u32 remote_ip4;	/* Stored in network byte order */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index d7cf861..88b6244 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -463,7 +463,7 @@ void tcp_init_transfer(struct sock *sk, int bpf_op)
 	tcp_mtup_init(sk);
 	icsk->icsk_af_ops->rebuild_header(sk);
 	tcp_init_metrics(sk);
-	tcp_call_bpf(sk, bpf_op);
+	tcp_call_bpf(sk, bpf_op, 0, NULL);
 	tcp_init_congestion_control(sk);
 	tcp_init_buffer_space(sk);
 }
diff --git a/net/ipv4/tcp_nv.c b/net/ipv4/tcp_nv.c
index 0b5a05b..ddbce73 100644
--- a/net/ipv4/tcp_nv.c
+++ b/net/ipv4/tcp_nv.c
@@ -146,7 +146,7 @@ static void tcpnv_init(struct sock *sk)
 	 * within a datacenter, where we have reasonable estimates of
 	 * RTTs
 	 */
-	base_rtt = tcp_call_bpf(sk, BPF_SOCK_OPS_BASE_RTT);
+	base_rtt = tcp_call_bpf(sk, BPF_SOCK_OPS_BASE_RTT, 0, NULL);
 	if (base_rtt > 0) {
 		ca->nv_base_rtt = base_rtt;
 		ca->nv_lower_bound_rtt = (base_rtt * 205) >> 8; /* 80% */
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 95461f0..d12f7f7 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3469,7 +3469,7 @@ int tcp_connect(struct sock *sk)
 	struct sk_buff *buff;
 	int err;
 
-	tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_CONNECT_CB);
+	tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_CONNECT_CB, 0, NULL);
 
 	if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk))
 		return -EHOSTUNREACH; /* Routing failure or similar. */
-- 
2.9.5

  parent reply	other threads:[~2018-01-25  2:37 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-01-25  2:37 [PATCH bpf-next v9 00/12] bpf: More sock_ops callbacks Lawrence Brakmo
2018-01-25  2:37 ` [PATCH bpf-next v9 01/12] bpf: Only reply field should be writeable Lawrence Brakmo
2018-01-25  2:37 ` [PATCH bpf-next v9 02/12] bpf: Make SOCK_OPS_GET_TCP size independent Lawrence Brakmo
2018-01-25  2:37 ` [PATCH bpf-next v9 03/12] bpf: Make SOCK_OPS_GET_TCP struct independent Lawrence Brakmo
2018-01-25  2:37 ` [PATCH bpf-next v9 04/12] bpf: Add write access to tcp_sock and sock fields Lawrence Brakmo
2018-01-25  2:37 ` Lawrence Brakmo [this message]
2018-01-25  2:37 ` [PATCH bpf-next v9 06/12] bpf: Adds field bpf_sock_ops_cb_flags to tcp_sock Lawrence Brakmo
2018-01-25  2:37 ` [PATCH bpf-next v9 07/12] bpf: Add sock_ops RTO callback Lawrence Brakmo
2018-01-25  2:37 ` [PATCH bpf-next v9 08/12] bpf: Add support for reading sk_state and more Lawrence Brakmo
2018-01-25  2:37 ` [PATCH bpf-next v9 09/12] bpf: Add sock_ops R/W access to tclass Lawrence Brakmo
2018-01-25  2:37 ` [PATCH bpf-next v9 10/12] bpf: Add BPF_SOCK_OPS_RETRANS_CB Lawrence Brakmo
2018-01-25  2:37 ` [PATCH bpf-next v9 11/12] bpf: Add BPF_SOCK_OPS_STATE_CB Lawrence Brakmo
2018-01-25  2:37 ` [PATCH bpf-next v9 12/12] bpf: add selftest for tcpbpf Lawrence Brakmo

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=20180125023712.3038949-6-brakmo@fb.com \
    --to=brakmo@fb.com \
    --cc=ast@fb.com \
    --cc=bmatheny@fb.com \
    --cc=daniel@iogearbox.net \
    --cc=eric.dumazet@gmail.com \
    --cc=kernel-team@fb.com \
    --cc=ncardwell@google.com \
    --cc=netdev@vger.kernel.org \
    --cc=ycheng@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;
as well as URLs for NNTP newsgroup(s).