summaryrefslogtreecommitdiffstats
path: root/net/ipv4/tcp_ipv4.c
diff options
context:
space:
mode:
authorMartin KaFai Lau <kafai@fb.com>2020-01-08 16:35:08 -0800
committerAlexei Starovoitov <ast@kernel.org>2020-01-09 08:46:18 -0800
commit0baf26b0fcd74bbfcef53c5d5e8bad2b99c8d0d2 (patch)
tree93c4e390a842dbf29bc83e53f5098c14cf07c869 /net/ipv4/tcp_ipv4.c
parent85d33df357b634649ddbe0a20fd2d0fc5732c3cb (diff)
downloadlinux-0baf26b0fcd74bbfcef53c5d5e8bad2b99c8d0d2.tar.bz2
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
Diffstat (limited to 'net/ipv4/tcp_ipv4.c')
-rw-r--r--net/ipv4/tcp_ipv4.c6
1 files changed, 4 insertions, 2 deletions
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 4adac9c75343..317ccca548a2 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2678,7 +2678,8 @@ static void __net_exit tcp_sk_exit(struct net *net)
int cpu;
if (net->ipv4.tcp_congestion_control)
- module_put(net->ipv4.tcp_congestion_control->owner);
+ bpf_module_put(net->ipv4.tcp_congestion_control,
+ net->ipv4.tcp_congestion_control->owner);
for_each_possible_cpu(cpu)
inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu));
@@ -2785,7 +2786,8 @@ static int __net_init tcp_sk_init(struct net *net)
/* Reno is always built in */
if (!net_eq(net, &init_net) &&
- try_module_get(init_net.ipv4.tcp_congestion_control->owner))
+ bpf_try_module_get(init_net.ipv4.tcp_congestion_control,
+ init_net.ipv4.tcp_congestion_control->owner))
net->ipv4.tcp_congestion_control = init_net.ipv4.tcp_congestion_control;
else
net->ipv4.tcp_congestion_control = &tcp_reno;