bpf: tcp: Support tcp_congestion_ops in bpf

This patch makes "struct tcp_congestion_ops" to be the first user
of BPF STRUCT_OPS.  It allows implementing a tcp_congestion_ops
in bpf.

The BPF implemented tcp_congestion_ops can be used like
regular kernel tcp-cc through sysctl and setsockopt.  e.g.
[root@arch-fb-vm1 bpf]# sysctl -a | egrep congestion
net.ipv4.tcp_allowed_congestion_control = reno cubic bpf_cubic
net.ipv4.tcp_available_congestion_control = reno bic cubic bpf_cubic
net.ipv4.tcp_congestion_control = bpf_cubic

There has been attempt to move the TCP CC to the user space
(e.g. CCP in TCP).   The common arguments are faster turn around,
get away from long-tail kernel versions in production...etc,
which are legit points.

BPF has been the continuous effort to join both kernel and
userspace upsides together (e.g. XDP to gain the performance
advantage without bypassing the kernel).  The recent BPF
advancements (in particular BTF-aware verifier, BPF trampoline,
BPF CO-RE...) made implementing kernel struct ops (e.g. tcp cc)
possible in BPF.  It allows a faster turnaround for testing algorithm
in the production while leveraging the existing (and continue growing)
BPF feature/framework instead of building one specifically for
userspace TCP CC.

This patch allows write access to a few fields in tcp-sock
(in bpf_tcp_ca_btf_struct_access()).

The optional "get_info" is unsupported now.  It can be added
later.  One possible way is to output the info with a btf-id
to describe the content.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20200109003508.3856115-1-kafai@fb.com

1 files changed, 8 insertions, 8 deletions

diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 3737ec096650..3172e31987be 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -21,7 +21,7 @@ static DEFINE_SPINLOCK(tcp_cong_list_lock);
 static LIST_HEAD(tcp_cong_list);
 
 /* Simple linear search, don't expect many entries! */
-static struct tcp_congestion_ops *tcp_ca_find(const char *name)
+struct tcp_congestion_ops *tcp_ca_find(const char *name)
 {
 	struct tcp_congestion_ops *e;
 
@@ -162,7 +162,7 @@ void tcp_assign_congestion_control(struct sock *sk)
 
 	rcu_read_lock();
 	ca = rcu_dereference(net->ipv4.tcp_congestion_control);
-	if (unlikely(!try_module_get(ca->owner)))
+	if (unlikely(!bpf_try_module_get(ca, ca->owner)))
 		ca = &tcp_reno;
 	icsk->icsk_ca_ops = ca;
 	rcu_read_unlock();
@@ -208,7 +208,7 @@ void tcp_cleanup_congestion_control(struct sock *sk)
 
 	if (icsk->icsk_ca_ops->release)
 		icsk->icsk_ca_ops->release(sk);
-	module_put(icsk->icsk_ca_ops->owner);
+	bpf_module_put(icsk->icsk_ca_ops, icsk->icsk_ca_ops->owner);
 }
 
 /* Used by sysctl to change default congestion control */
@@ -222,12 +222,12 @@ int tcp_set_default_congestion_control(struct net *net, const char *name)
 	ca = tcp_ca_find_autoload(net, name);
 	if (!ca) {
 		ret = -ENOENT;
-	} else if (!try_module_get(ca->owner)) {
+	} else if (!bpf_try_module_get(ca, ca->owner)) {
 		ret = -EBUSY;
 	} else {
 		prev = xchg(&net->ipv4.tcp_congestion_control, ca);
 		if (prev)
-			module_put(prev->owner);
+			bpf_module_put(prev, prev->owner);
 
 		ca->flags |= TCP_CONG_NON_RESTRICTED;
 		ret = 0;
@@ -366,19 +366,19 @@ int tcp_set_congestion_control(struct sock *sk, const char *name, bool load,
 	} else if (!load) {
 		const struct tcp_congestion_ops *old_ca = icsk->icsk_ca_ops;
 
-		if (try_module_get(ca->owner)) {
+		if (bpf_try_module_get(ca, ca->owner)) {
 			if (reinit) {
 				tcp_reinit_congestion_control(sk, ca);
 			} else {
 				icsk->icsk_ca_ops = ca;
-				module_put(old_ca->owner);
+				bpf_module_put(old_ca, old_ca->owner);
 			}
 		} else {
 			err = -EBUSY;
 		}
 	} else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || cap_net_admin)) {
 		err = -EPERM;
-	} else if (!try_module_get(ca->owner)) {
+	} else if (!bpf_try_module_get(ca, ca->owner)) {
 		err = -EBUSY;
 	} else {
 		tcp_reinit_congestion_control(sk, ca);