From: Lawrence Brakmo <brakmo@fb.com>
Date: Thu, 25 Jan 2018 16:14:09 -0800
Subject: bpf: Support passing args to sock_ops bpf function
Patch-mainline: v4.16-rc1
Git-commit: de525be2ca2734865d29c4b67ddd29913b214906
References: bsc#1109837
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>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
---
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 | 3 ++-
6 files changed, 43 insertions(+), 10 deletions(-)
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1005,6 +1005,7 @@ struct bpf_sock_ops_kern {
struct sock *sk;
u32 op;
union {
+ u32 args[4];
u32 reply;
u32 replylong[4];
};
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2033,7 +2033,7 @@ 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;
@@ -2046,6 +2046,8 @@ static inline int tcp_call_bpf(struct so
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)
@@ -2054,18 +2056,46 @@ static inline int tcp_call_bpf(struct so
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;
@@ -2076,7 +2106,7 @@ static inline u32 tcp_rwnd_init_bpf(stru
{
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;
@@ -2085,7 +2115,7 @@ static inline u32 tcp_rwnd_init_bpf(stru
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)
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -944,8 +944,9 @@ 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 */
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -430,7 +430,7 @@ void tcp_init_transfer(struct sock *sk,
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);
}
--- a/net/ipv4/tcp_nv.c
+++ b/net/ipv4/tcp_nv.c
@@ -148,7 +148,7 @@ 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% */
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3410,10 +3410,11 @@ int tcp_connect(struct sock *sk)
struct sk_buff *buff;
int err;
+ 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. */
- tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_CONNECT_CB);
tcp_connect_init(sk);
if (unlikely(tp->repair)) {