Merge branch 'bpf-sockmap-fix-fionread-for-sockets-without-a-verdict-program'

Mattia Meleleo says:

====================
bpf, sockmap: Fix FIONREAD for sockets without a verdict program

Sockets added to a sockmap/sockhash with no stream/skb verdict program
attached answer FIONREAD with 0 even when unread data is pending in
sk_receive_queue. Fix tcp_bpf_ioctl() to account for the receive queue
in that case, and add a selftest.

Changes in v3:
- Remove unused sk_psock_msg_inq()
- Link to v2: https://patch.msgid.link/20260708-fionread-no-verdict-v2-0-29dd293621c7@coralogix.com

Changes in v2:
- Split the fix and the selftest into separate patches
- Use READ_ONCE() to read the verdict program pointers
- Link to v1: https://patch.msgid.link/20260707-fionread-no-verdict-v1-1-ce94a72357ec@coralogix.com

Signed-off-by: Mattia Meleleo <mattia.meleleo@coralogix.com>
---
====================

Link: https://patch.msgid.link/20260708-fionread-no-verdict-v3-0-b4ee31b3af53@coralogix.com
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
This commit is contained in:
Kumar Kartikeya Dwivedi
2026-07-15 11:10:15 +02:00
3 changed files with 55 additions and 15 deletions

View File

@@ -551,20 +551,6 @@ static inline void psock_progs_drop(struct sk_psock_progs *progs)
psock_set_prog(&progs->skb_verdict, NULL);
}
/* for tcp only, sk is locked */
static inline ssize_t sk_psock_msg_inq(struct sock *sk)
{
struct sk_psock *psock;
ssize_t inq = 0;
psock = sk_psock_get(sk);
if (likely(psock)) {
inq = sk_psock_get_msg_len_nolock(psock);
sk_psock_put(sk, psock);
}
return inq;
}
/* for udp only, sk is not locked */
static inline ssize_t sk_msg_first_len(struct sock *sk)
{

View File

@@ -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 +345,21 @@ 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 (!READ_ONCE(psock->progs.stream_verdict) &&
!READ_ONCE(psock->progs.skb_verdict))
*karg += tcp_inq(sk);
sk_psock_put(sk, psock);
unlock_sock_fast(sk, slow);
return 0;

View File

@@ -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"))