selftests/bpf: Add getsockopt to inspect mptcp subflow

This patch adds a "cgroup/getsockopt" way to inspect the subflows of a
mptcp socket.

mptcp_for_each_stubflow() and other helpers related to list_dentry are
added into progs/mptcp_bpf.h.

Add an extra "cgroup/getsockopt" prog to walk the msk->conn_list and use
bpf_core_cast to cast a pointer to tcp_sock for readonly. It will allow
to inspect all the fields in a tcp_sock.

Suggested-by: Martin KaFai Lau <[email protected]>
Signed-off-by: Geliang Tang <[email protected]>

Author: Geliang Tang

tools/testing/selftests/bpf/progs/mptcp_bpf.h

@@ -4,9 +4,44 @@
 
 #include <vmlinux.h>
 #include <bpf/bpf_core_read.h>
+#include "bpf_experimental.h"
 
 #define MPTCP_SUBFLOWS_MAX 8
 
+static inline int list_is_head(const struct list_head *list,
+			       const struct list_head *head)
+{
+	return list == head;
+}
+
+#define list_entry(ptr, type, member)					\
+	container_of(ptr, type, member)
+
+#define list_first_entry(ptr, type, member)				\
+	list_entry((ptr)->next, type, member)
+
+#define list_next_entry(pos, member)					\
+	list_entry((pos)->member.next, typeof(*(pos)), member)
+
+#define list_entry_is_head(pos, head, member)				\
+	list_is_head(&pos->member, (head))
+
+#define list_for_each_entry(pos, head, member)				\
+	for (pos = list_first_entry(head, typeof(*pos), member);	\
+	     cond_break, !list_entry_is_head(pos, head, member);	\
+	     pos = list_next_entry(pos, member))
+
+#define list_for_each_entry_safe(pos, n, head, member)			\
+	for (pos = list_first_entry(head, typeof(*pos), member),	\
+		n = list_next_entry(pos, member);			\
+	     cond_break, !list_entry_is_head(pos, head, member);	\
+	     pos = n, n = list_next_entry(n, member))
+
+#define mptcp_for_each_subflow(__msk, __subflow)			\
+	list_for_each_entry(__subflow, &((__msk)->conn_list), node)
+#define mptcp_for_each_subflow_safe(__msk, __subflow, __tmp)		\
+	list_for_each_entry_safe(__subflow, __tmp, &((__msk)->conn_list), node)
+
 extern void mptcp_subflow_set_scheduled(struct mptcp_subflow_context *subflow,
 					bool scheduled) __ksym;
 

tools/testing/selftests/bpf/progs/mptcp_subflow.c

@@ -4,6 +4,7 @@
 
 /* vmlinux.h, bpf_helpers.h and other 'define' */
 #include "bpf_tracing_net.h"
+#include "mptcp_bpf.h"
 
 char _license[] SEC("license") = "GPL";
 
@@ -57,3 +58,66 @@ int mptcp_subflow(struct bpf_sock_ops *skops)
 
 	return 1;
 }
+
+static int _check_getsockopt_subflows_mark(struct mptcp_sock *msk, struct bpf_sockopt *ctx)
+{
+	struct mptcp_subflow_context *subflow;
+	int *optval = ctx->optval;
+
+	mptcp_for_each_subflow(msk, subflow) {
+		struct sock *ssk;
+
+		ssk = mptcp_subflow_tcp_sock(bpf_core_cast(subflow,
+							   struct mptcp_subflow_context));
+
+		if (ctx->optval + sizeof(int) <= ctx->optval_end) {
+			*optval = ssk->sk_mark;
+			ctx->retval = 0;
+		}
+	}
+
+	return 1;
+}
+
+static int _check_getsockopt_subflow_cc(struct mptcp_sock *msk, struct bpf_sockopt *ctx)
+{
+	struct mptcp_subflow_context *subflow, *tmp;
+	char *optval = ctx->optval;
+
+	mptcp_for_each_subflow_safe(msk, subflow, tmp) {
+		struct inet_connection_sock *icsk;
+		struct sock *ssk;
+
+		ssk = mptcp_subflow_tcp_sock(bpf_core_cast(subflow,
+							   struct mptcp_subflow_context));
+		icsk = bpf_core_cast(ssk, struct inet_connection_sock);
+
+		if (ctx->optval + TCP_CA_NAME_MAX <= ctx->optval_end) {
+			__builtin_memcpy(optval, icsk->icsk_ca_ops->name, TCP_CA_NAME_MAX);
+			ctx->retval = 0;
+		}
+	}
+
+	return 1;
+}
+
+SEC("cgroup/getsockopt")
+int _getsockopt_subflow(struct bpf_sockopt *ctx)
+{
+	struct bpf_sock *sk = ctx->sk;
+	struct mptcp_sock *msk;
+
+	if (!sk || sk->protocol != IPPROTO_MPTCP)
+		return 1;
+
+	msk = bpf_core_cast(sk, struct mptcp_sock);
+	if (msk->pm.subflows != 1)
+		return 1;
+
+	if (ctx->level == SOL_SOCKET && ctx->optname == SO_MARK)
+		return _check_getsockopt_subflows_mark(msk, ctx);
+	if (ctx->level == SOL_TCP && ctx->optname == TCP_CONGESTION)
+		return _check_getsockopt_subflow_cc(msk, ctx);
+
+	return 1;
+}