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, 230 insertions, 0 deletions

diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
new file mode 100644
index 000000000000..9c7745b958d7
--- /dev/null
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -0,0 +1,230 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Facebook  */
+
+#include <linux/types.h>
+#include <linux/bpf_verifier.h>
+#include <linux/bpf.h>
+#include <linux/btf.h>
+#include <linux/filter.h>
+#include <net/tcp.h>
+
+static u32 optional_ops[] = {
+	offsetof(struct tcp_congestion_ops, init),
+	offsetof(struct tcp_congestion_ops, release),
+	offsetof(struct tcp_congestion_ops, set_state),
+	offsetof(struct tcp_congestion_ops, cwnd_event),
+	offsetof(struct tcp_congestion_ops, in_ack_event),
+	offsetof(struct tcp_congestion_ops, pkts_acked),
+	offsetof(struct tcp_congestion_ops, min_tso_segs),
+	offsetof(struct tcp_congestion_ops, sndbuf_expand),
+	offsetof(struct tcp_congestion_ops, cong_control),
+};
+
+static u32 unsupported_ops[] = {
+	offsetof(struct tcp_congestion_ops, get_info),
+};
+
+static const struct btf_type *tcp_sock_type;
+static u32 tcp_sock_id, sock_id;
+
+static int bpf_tcp_ca_init(struct btf *btf)
+{
+	s32 type_id;
+
+	type_id = btf_find_by_name_kind(btf, "sock", BTF_KIND_STRUCT);
+	if (type_id < 0)
+		return -EINVAL;
+	sock_id = type_id;
+
+	type_id = btf_find_by_name_kind(btf, "tcp_sock", BTF_KIND_STRUCT);
+	if (type_id < 0)
+		return -EINVAL;
+	tcp_sock_id = type_id;
+	tcp_sock_type = btf_type_by_id(btf, tcp_sock_id);
+
+	return 0;
+}
+
+static bool is_optional(u32 member_offset)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(optional_ops); i++) {
+		if (member_offset == optional_ops[i])
+			return true;
+	}
+
+	return false;
+}
+
+static bool is_unsupported(u32 member_offset)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(unsupported_ops); i++) {
+		if (member_offset == unsupported_ops[i])
+			return true;
+	}
+
+	return false;
+}
+
+extern struct btf *btf_vmlinux;
+
+static bool bpf_tcp_ca_is_valid_access(int off, int size,
+				       enum bpf_access_type type,
+				       const struct bpf_prog *prog,
+				       struct bpf_insn_access_aux *info)
+{
+	if (off < 0 || off >= sizeof(__u64) * MAX_BPF_FUNC_ARGS)
+		return false;
+	if (type != BPF_READ)
+		return false;
+	if (off % size != 0)
+		return false;
+
+	if (!btf_ctx_access(off, size, type, prog, info))
+		return false;
+
+	if (info->reg_type == PTR_TO_BTF_ID && info->btf_id == sock_id)
+		/* promote it to tcp_sock */
+		info->btf_id = tcp_sock_id;
+
+	return true;
+}
+
+static int bpf_tcp_ca_btf_struct_access(struct bpf_verifier_log *log,
+					const struct btf_type *t, int off,
+					int size, enum bpf_access_type atype,
+					u32 *next_btf_id)
+{
+	size_t end;
+
+	if (atype == BPF_READ)
+		return btf_struct_access(log, t, off, size, atype, next_btf_id);
+
+	if (t != tcp_sock_type) {
+		bpf_log(log, "only read is supported\n");
+		return -EACCES;
+	}
+
+	switch (off) {
+	case bpf_ctx_range(struct inet_connection_sock, icsk_ca_priv):
+		end = offsetofend(struct inet_connection_sock, icsk_ca_priv);
+		break;
+	case offsetof(struct inet_connection_sock, icsk_ack.pending):
+		end = offsetofend(struct inet_connection_sock,
+				  icsk_ack.pending);
+		break;
+	case offsetof(struct tcp_sock, snd_cwnd):
+		end = offsetofend(struct tcp_sock, snd_cwnd);
+		break;
+	case offsetof(struct tcp_sock, snd_cwnd_cnt):
+		end = offsetofend(struct tcp_sock, snd_cwnd_cnt);
+		break;
+	case offsetof(struct tcp_sock, snd_ssthresh):
+		end = offsetofend(struct tcp_sock, snd_ssthresh);
+		break;
+	case offsetof(struct tcp_sock, ecn_flags):
+		end = offsetofend(struct tcp_sock, ecn_flags);
+		break;
+	default:
+		bpf_log(log, "no write support to tcp_sock at off %d\n", off);
+		return -EACCES;
+	}
+
+	if (off + size > end) {
+		bpf_log(log,
+			"write access at off %d with size %d beyond the member of tcp_sock ended at %zu\n",
+			off, size, end);
+		return -EACCES;
+	}
+
+	return NOT_INIT;
+}
+
+static const struct bpf_func_proto *
+bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id,
+			  const struct bpf_prog *prog)
+{
+	return bpf_base_func_proto(func_id);
+}
+
+static const struct bpf_verifier_ops bpf_tcp_ca_verifier_ops = {
+	.get_func_proto		= bpf_tcp_ca_get_func_proto,
+	.is_valid_access	= bpf_tcp_ca_is_valid_access,
+	.btf_struct_access	= bpf_tcp_ca_btf_struct_access,
+};
+
+static int bpf_tcp_ca_init_member(const struct btf_type *t,
+				  const struct btf_member *member,
+				  void *kdata, const void *udata)
+{
+	const struct tcp_congestion_ops *utcp_ca;
+	struct tcp_congestion_ops *tcp_ca;
+	size_t tcp_ca_name_len;
+	int prog_fd;
+	u32 moff;
+
+	utcp_ca = (const struct tcp_congestion_ops *)udata;
+	tcp_ca = (struct tcp_congestion_ops *)kdata;
+
+	moff = btf_member_bit_offset(t, member) / 8;
+	switch (moff) {
+	case offsetof(struct tcp_congestion_ops, flags):
+		if (utcp_ca->flags & ~TCP_CONG_MASK)
+			return -EINVAL;
+		tcp_ca->flags = utcp_ca->flags;
+		return 1;
+	case offsetof(struct tcp_congestion_ops, name):
+		tcp_ca_name_len = strnlen(utcp_ca->name, sizeof(utcp_ca->name));
+		if (!tcp_ca_name_len ||
+		    tcp_ca_name_len == sizeof(utcp_ca->name))
+			return -EINVAL;
+		if (tcp_ca_find(utcp_ca->name))
+			return -EEXIST;
+		memcpy(tcp_ca->name, utcp_ca->name, sizeof(tcp_ca->name));
+		return 1;
+	}
+
+	if (!btf_type_resolve_func_ptr(btf_vmlinux, member->type, NULL))
+		return 0;
+
+	/* Ensure bpf_prog is provided for compulsory func ptr */
+	prog_fd = (int)(*(unsigned long *)(udata + moff));
+	if (!prog_fd && !is_optional(moff) && !is_unsupported(moff))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int bpf_tcp_ca_check_member(const struct btf_type *t,
+				   const struct btf_member *member)
+{
+	if (is_unsupported(btf_member_bit_offset(t, member) / 8))
+		return -ENOTSUPP;
+	return 0;
+}
+
+static int bpf_tcp_ca_reg(void *kdata)
+{
+	return tcp_register_congestion_control(kdata);
+}
+
+static void bpf_tcp_ca_unreg(void *kdata)
+{
+	tcp_unregister_congestion_control(kdata);
+}
+
+/* Avoid sparse warning.  It is only used in bpf_struct_ops.c. */
+extern struct bpf_struct_ops bpf_tcp_congestion_ops;
+
+struct bpf_struct_ops bpf_tcp_congestion_ops = {
+	.verifier_ops = &bpf_tcp_ca_verifier_ops,
+	.reg = bpf_tcp_ca_reg,
+	.unreg = bpf_tcp_ca_unreg,
+	.check_member = bpf_tcp_ca_check_member,
+	.init_member = bpf_tcp_ca_init_member,
+	.init = bpf_tcp_ca_init,
+	.name = "tcp_congestion_ops",
+};