Re: [PATCH mptcp-next 2/2] selftests/bpf: Add getsockopt to inspect mptcp subflow

[Matthieu Baerts <matttbe@kernel.org>]

Hi Geliang,

Thank you for looking at that!

On 20/08/2024 10:44, Geliang Tang wrote:
> From: Geliang Tang <tanggeliang@kylinos.cn>
> 
> 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_rdonly_cast to cast a pointer to tcp_sock for readonly. It will allow

Do you mean bpf_core_cast() instead of bpf_rdonly_cast()? Or is it
indirectly used?

> to inspect all the fields in a tcp_sock.
> 
> Suggested-by: Martin KaFai Lau <martin.lau@kernel.org>
> Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
> ---
>  .../testing/selftests/bpf/prog_tests/mptcp.c  | 11 +++++++
>  tools/testing/selftests/bpf/progs/mptcp_bpf.h | 26 +++++++++++++++
>  .../selftests/bpf/progs/mptcp_subflow.c       | 32 +++++++++++++++++++
>  3 files changed, 69 insertions(+)
> 
> diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c
> index 69fdcb28249d..2178db94f764 100644
> --- a/tools/testing/selftests/bpf/prog_tests/mptcp.c
> +++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c
> @@ -383,6 +383,7 @@ static void run_subflow(char *new)
>  {
>  	int server_fd, client_fd, err;
>  	char cc[TCP_CA_NAME_MAX];
> +	unsigned int mark;
>  	socklen_t len;
>  
>  	server_fd = start_mptcp_server(AF_INET, ADDR_1, PORT_1, 0);
> @@ -407,6 +408,10 @@ static void run_subflow(char *new)
>  	ASSERT_OK(ss_search(ADDR_1, new), "ss_search new cc");
>  	ASSERT_OK(ss_search(ADDR_2, cc), "ss_search default cc");

I guess the next steps is to remove these 'ss_search()', right?

> +	len = sizeof(mark);
> +	err = getsockopt(client_fd, SOL_SOCKET, SO_MARK, &mark, &len);
> +	ASSERT_OK(err, "getsockopt(client_fd, SO_MARK)");
> +
>  	close(client_fd);
>  fail:
>  	close(server_fd);
> @@ -417,6 +422,7 @@ static void test_subflow(void)
>  	int cgroup_fd, prog_fd, err;
>  	struct mptcp_subflow *skel;
>  	struct nstoken *nstoken;
> +	struct bpf_link *link;
>  
>  	cgroup_fd = test__join_cgroup("/mptcp_subflow");
>  	if (!ASSERT_GE(cgroup_fd, 0, "join_cgroup: mptcp_subflow"))
> @@ -442,6 +448,10 @@ static void test_subflow(void)
>  	if (endpoint_init("subflow") < 0)
>  		goto close_netns;
>  
> +	link = bpf_program__attach_cgroup(skel->progs._getsockopt, cgroup_fd);
> +	if (!ASSERT_OK_PTR(link, "getsockopt prog"))

I don't know how it works: is this going to fail if the getsockopt
program set 'ctx->retval = -1'?

> +		goto close_netns;
> +
>  	run_subflow(skel->data->cc);
>  
>  close_netns:
> @@ -450,6 +460,7 @@ static void test_subflow(void)
>  	mptcp_subflow__destroy(skel);
>  close_cgroup:
>  	close(cgroup_fd);
> +	bpf_link__destroy(link);
>  }
>  
>  static struct nstoken *sched_init(char *flags, char *sched)
> diff --git a/tools/testing/selftests/bpf/progs/mptcp_bpf.h b/tools/testing/selftests/bpf/progs/mptcp_bpf.h
> index 782f36ed027e..2086170e7379 100644
> --- a/tools/testing/selftests/bpf/progs/mptcp_bpf.h
> +++ b/tools/testing/selftests/bpf/progs/mptcp_bpf.h
> @@ -7,6 +7,32 @@
>  
>  #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);	\
> +	     !list_entry_is_head(pos, head, member);			\
> +	     pos = list_next_entry(pos, member))

Out of curiosity, are these generic helpers not defined elsewhere? Is it
OK not to use the '_safe' version where the deletion of elements is
supported?

> +
> +#define mptcp_for_each_subflow(__msk, __subflow)			\
> +	list_for_each_entry(__subflow, &((__msk)->conn_list), node)
> +
>  extern void mptcp_subflow_set_scheduled(struct mptcp_subflow_context *subflow,
>  					bool scheduled) __ksym;
>  
> diff --git a/tools/testing/selftests/bpf/progs/mptcp_subflow.c b/tools/testing/selftests/bpf/progs/mptcp_subflow.c
> index bc572e1d6df8..c41418ab8db4 100644
> --- a/tools/testing/selftests/bpf/progs/mptcp_subflow.c
> +++ b/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 +58,34 @@ int mptcp_subflow(struct bpf_sock_ops *skops)
>  
>  	return 1;
>  }
> +
> +SEC("cgroup/getsockopt")
> +int _getsockopt(struct bpf_sockopt *ctx)

This name seems too generic while what is done here is specific to the
'subflow' test. Maybe: _check_getsockopt_subflows()?

(or _check_getsockopt_subflows_mark() and _check_getsockopt_subflow_cc()
see below)

> +{
> +	struct mptcp_sock *msk = bpf_core_cast(ctx->sk, struct mptcp_sock);

What happens if the 'sk' is not an 'msk'?
Does it check that the sk is indeed an MPTCP one? (how?)

> +	struct mptcp_subflow_context *subflow;
> +	int i = 0;
> +
> +	if (!msk || ctx->level != SOL_SOCKET || ctx->optname != SO_MARK)
> +		return 1;

Would it not be clearer to split the two checks? One dedicated to the
mark, when getsockopt(SO_MARK) is used, and one for the CC, when the
getsockopt(TCP_CONGESTION) is used? By doing that, we would know which
one had an issue, if any, not just "something wrong with getsockopt()"?

> +
> +	mptcp_for_each_subflow(msk, subflow) {

(might be better to use this helper in our WIP MPTCP BPF packets
scheduler examples, instead of converting them to a fixed array)

> +		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 (ssk->sk_mark != i + 1)
> +			ctx->retval = -1;
> +		if (ssk->sk_mark == 1 &&
> +		    __builtin_memcmp(icsk->icsk_ca_ops->name, cc, TCP_CA_NAME_MAX))
> +			ctx->retval = -1;
> +
> +		if (i++ >= MPTCP_SUBFLOWS_MAX)
> +			break;

I guess this part is needed for the verifier, right?
Somehow related to "cond_break" explained in this link?

  https://lwn.net/Articles/964381/


> +	}
> +
> +	return 1;
> +}

Cheers,
Matt
-- 
Sponsored by the NGI0 Core fund.