Re: [PATCH bpf] bpf, sockmap: Account for receive queue in FIONREAD without a verdict program

["Emil Tsalapatis" <emil@etsalapatis.com>]

On Wed Jul 8, 2026 at 12:41 AM EDT, Kumar Kartikeya Dwivedi wrote:
> On Tue Jul 7, 2026 at 7:19 PM CEST, Emil Tsalapatis wrote:
>> On Tue Jul 7, 2026 at 12:15 PM EDT, Mattia Meleleo via B4 Relay wrote:
>>> From: Mattia Meleleo <mattia.meleleo@coralogix.com>
>>>
>>> tcp_bpf_ioctl() answers SIOCINQ from psock->msg_tot_len, which only
>>> counts bytes in ingress_msg. Without a stream/skb verdict program
>>> nothing is diverted there: data stays in sk_receive_queue, so FIONREAD
>>> returns 0 even though read() returns data.
>>>
>>> Add tcp_inq() to the reported value when the psock has no verdict
>>> program. The two queues are disjoint, so bytes redirected into
>>> ingress_msg from other sockets stay correctly accounted through
>>> msg_tot_len.
>>>
>>> Add a selftest covering FIONREAD without a verdict program.
>>>
>>> Fixes: 929e30f93125 ("bpf, sockmap: Fix FIONREAD for sockmap")
>>> Signed-off-by: Mattia Meleleo <mattia.meleleo@coralogix.com>
>>
>> Reviewed-by: Emil Tsalapatis <emil@etsalapatis.com>
>>
>> I don't think the Sashiko READ_ONCE() recommendation is that important,
>> we're just checking for the pointers' existence and I don't see how the
>> reads can be moved/optimized out/merged in a way that breaks this code.
>>
>
> It would be necessary if the xchg() can happen even when the lock is held, at
> the very least, to suppress potential KCSAN warnings, I think. Even for the
> theoretical load tearing that causes false positive, it would be benign due to
> wrong accounting.
>

Fair enough, nothing wrong with adding the READ_ONCE since the set already
needed respinning.

>>> ---
>>>  net/ipv4/tcp_bpf.c                                 | 16 ++++++++-
>>>  .../selftests/bpf/prog_tests/sockmap_basic.c       | 39 ++++++++++++++++++++++
>>>  2 files changed, 54 insertions(+), 1 deletion(-)
>>>
>>> diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
>>> index cc0bd73f3..a001b1fff 100644
>>> --- a/net/ipv4/tcp_bpf.c
>>> +++ b/net/ipv4/tcp_bpf.c
>>> @@ -334,6 +334,7 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk,
>>>
>>>  static int tcp_bpf_ioctl(struct sock *sk, int cmd, int *karg)
>>>  {
>>> +	struct sk_psock *psock;
>>>  	bool slow;
>>>
>>>  	if (cmd != SIOCINQ)
>>> @@ -344,7 +345,20 @@ static int tcp_bpf_ioctl(struct sock *sk, int cmd, int *karg)
>>>  		return -EINVAL;
>>>
>>>  	slow = lock_sock_fast(sk);
>>> -	*karg = sk_psock_msg_inq(sk);
>>> +	psock = sk_psock_get(sk);
>>> +	if (unlikely(!psock)) {
>>> +		unlock_sock_fast(sk, slow);
>>> +		return tcp_ioctl(sk, cmd, karg);
>>> +	}
>>> +	*karg = sk_psock_get_msg_len_nolock(psock);
>>> +	/* Without a verdict program, ingress data is never diverted to
>>> +	 * ingress_msg: it stays in sk_receive_queue and is read through
>>> +	 * the fallback to tcp_recvmsg(), so account for it like
>>> +	 * tcp_ioctl() does.
>>> +	 */
>>> +	if (!psock->progs.stream_verdict && !psock->progs.skb_verdict)
>>> +		*karg += tcp_inq(sk);
>>> +	sk_psock_put(sk, psock);
>>>  	unlock_sock_fast(sk, slow);
>>>
>>>  	return 0;
>>> diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
>>> index cb3229711..f0f368201 100644
>>> --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
>>> +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
>>> @@ -1373,6 +1373,43 @@ static void test_sockmap_multi_channels(int sotype)
>>>  	test_sockmap_pass_prog__destroy(skel);
>>>  }
>>>
>>> +/* A socket in a sockmap without a verdict program keeps its ingress data
>>> + * in sk_receive_queue: FIONREAD must account for it.
>>> + */
>>> +static void test_sockmap_no_verdict_fionread(void)
>>> +{
>>> +	int err, map, zero = 0, sent, avail;
>>> +	int c0 = -1, c1 = -1, p0 = -1, p1 = -1;
>>> +	struct test_sockmap_pass_prog *skel;
>>> +	char buf[256] = "0123456789";
>>> +
>>> +	skel = test_sockmap_pass_prog__open_and_load();
>>> +	if (!ASSERT_OK_PTR(skel, "open_and_load"))
>>> +		return;
>>> +	map = bpf_map__fd(skel->maps.sock_map_rx);
>>> +
>>> +	err = create_socket_pairs(AF_INET, SOCK_STREAM, &c0, &c1, &p0, &p1);
>>> +	if (!ASSERT_OK(err, "create_socket_pairs()"))
>>> +		goto out;
>>> +
>>> +	err = bpf_map_update_elem(map, &zero, &c1, BPF_NOEXIST);
>>> +	if (!ASSERT_OK(err, "bpf_map_update_elem(c1)"))
>>> +		goto out_close;
>>> +
>>> +	sent = xsend(p1, &buf, sizeof(buf), 0);
>>> +	ASSERT_EQ(sent, sizeof(buf), "xsend(p1)");
>>> +	avail = wait_for_fionread(c1, sizeof(buf), IO_TIMEOUT_SEC);
>>> +	ASSERT_EQ(avail, sizeof(buf), "ioctl(FIONREAD)");
>>> +
>>> +out_close:
>>> +	close(c0);
>>> +	close(p0);
>>> +	close(c1);
>>> +	close(p1);
>>> +out:
>>> +	test_sockmap_pass_prog__destroy(skel);
>>> +}
>>> +
>>>  void test_sockmap_basic(void)
>>>  {
>>>  	if (test__start_subtest("sockmap create_update_free"))
>>> @@ -1415,6 +1452,8 @@ void test_sockmap_basic(void)
>>>  		test_sockmap_skb_verdict_shutdown();
>>>  	if (test__start_subtest("sockmap skb_verdict fionread"))
>>>  		test_sockmap_skb_verdict_fionread(true);
>>> +	if (test__start_subtest("sockmap no_verdict fionread"))
>>> +		test_sockmap_no_verdict_fionread();
>>>  	if (test__start_subtest("sockmap skb_verdict fionread on drop"))
>>>  		test_sockmap_skb_verdict_fionread(false);
>>>  	if (test__start_subtest("sockmap skb_verdict change tail"))
>>>
>>> ---
>>> base-commit: d2c9a99135da931377240942d44f3dea104cedb8
>>> change-id: 20260707-fionread-no-verdict-a4f8697ac9f9
>>>
>>> Best regards,
>>> --
>>> Mattia Meleleo <mattia.meleleo@coralogix.com>