Merge branch 'bpf-tcp-fix-bpf_sock_destroy-on-time_wait-and-listener-socks'

Jiayuan Chen says:

====================
bpf,tcp: Fix bpf_sock_destroy() on TIME_WAIT and listener socks

Fix two bugs in bpf_sock_destroy(). One is an out-of-bounds read of
sk->sk_protocol on TIME_WAIT and NEW_SYN_RECV socks, since the field is
not in struct sock_common. The other is a might_sleep splat when
destroying a listener with children in its accept queue, the
cond_resched() in inet_csk_listen_stop() runs under the iterator's
rcu_read_lock(). Patch 3 adds a subtest for each.

v2 -> v3:
 - Patch 1: add Reviewed-by from Kuniyuki.
 - Patch 2: reword why cond_resched() has to go, it can reschedule or
   report a bogus quiescent state there.
 - Patch 2: keep the cond_resched() for the non-BPF path rather than
   removing it as Kuniyuki suggested. VOLUNTARY and NONE are still
   there on some arches, and on x86 in stable where this goes, so a
   big listener close() still relies on it. Can go once those modes
   are gone.
 - Selftest: don't leak the fd if accept() unexpectedly succeeds.
v2: https://lore.kernel.org/bpf/20260906074135.185212-1-jiayuan.chen@linux.dev/

v1 -> v2:
 - Patch 1: fix the return comment too.
 - Patch 2: new.
 - Selftest: server recv()s EOF before close so the FINs can't cross,
   comment style, keep the blank line before RUN_TESTS(), add the
   tcp_listen_pending subtest.
v1: https://lore.kernel.org/bpf/20260903125306.299943-1-jiayuan.chen@linux.dev/
====================

Link: https://patch.msgid.link/20260910112107.148770-1-jiayuan.chen@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

net/core/filter.c

@@ -12913,8 +12913,9 @@ __bpf_kfunc_start_defs();
  * @sock: Pointer to socket to be destroyed
  *
  * Return:
- * On error, may return EPROTONOSUPPORT, EINVAL.
- * EPROTONOSUPPORT if protocol specific destroy handler is not supported.
+ * On error, may return EOPNOTSUPP, or whatever the protocol specific
+ * destroy handler returns.
+ * EOPNOTSUPP if protocol specific destroy handler is not supported.
  * 0 otherwise
  */
 __bpf_kfunc int bpf_sock_destroy(struct sock_common *sock)
@@ -12926,8 +12927,12 @@ __bpf_kfunc int bpf_sock_destroy(struct sock_common *sock)
 	 * Supporting protocols will need to acquire sock lock in the BPF context
 	 * prior to invoking this kfunc.
 	 */
-	if (!sk->sk_prot->diag_destroy || (sk->sk_protocol != IPPROTO_TCP &&
-					   sk->sk_protocol != IPPROTO_UDP))
+	if (!sk->sk_prot->diag_destroy)
+		return -EOPNOTSUPP;
+
+	if (sk_fullsock(sk) &&
+	    sk->sk_protocol != IPPROTO_TCP &&
+	    sk->sk_protocol != IPPROTO_UDP)
 		return -EOPNOTSUPP;
 
 	return sk->sk_prot->diag_destroy(sk, ECONNABORTED);

net/ipv4/inet_connection_sock.c

@@ -1520,7 +1520,8 @@ void inet_csk_listen_stop(struct sock *sk)
 		local_bh_enable();
 		sock_put(child);
 
-		cond_resched();
+		if (!has_current_bpf_ctx())
+			cond_resched();
 	}
 	if (queue->fastopenq.rskq_rst_head) {
 		/* Free all the reqs queued in rskq_rst_head. */

tools/testing/selftests/bpf/prog_tests/sock_destroy.c

@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <poll.h>
 #include <test_progs.h>
 #include <bpf/bpf_endian.h>
 
@@ -110,6 +111,122 @@ static void test_tcp_server(struct sock_destroy_prog *skel)
 		close(serv);
 }
 
+static void test_tcp_listen_pending(struct sock_destroy_prog *skel)
+{
+	int serv = -1, clien = -1, accept_serv = -1, n, serv_port;
+	struct pollfd pfd = { .events = POLLIN };
+	char buf[1];
+
+	serv = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0);
+	if (!ASSERT_GE(serv, 0, "start_server"))
+		goto cleanup;
+	serv_port = get_socket_local_port(serv);
+	if (!ASSERT_GE(serv_port, 0, "get_sock_local_port"))
+		goto cleanup;
+	skel->bss->serv_port = (__be16)serv_port;
+
+	/*
+	 * Connect but never accept, so the child sits in the accept queue
+	 * of the listener. Wait until it's actually there.
+	 */
+	clien = connect_to_fd(serv, 0);
+	if (!ASSERT_GE(clien, 0, "connect_to_fd"))
+		goto cleanup;
+	pfd.fd = serv;
+	if (!ASSERT_EQ(poll(&pfd, 1, -1), 1, "poll listener"))
+		goto cleanup;
+
+	/* Run iterator program that destroys server sockets. */
+	start_iter_sockets(skel->progs.iter_tcp6_server);
+
+	accept_serv = accept(serv, NULL, NULL);
+	if (!ASSERT_LT(accept_serv, 0, "accept on destroyed listener"))
+		goto cleanup;
+	ASSERT_EQ(errno, EINVAL, "error code on destroyed listener");
+
+	/* The unaccepted child was reset along with the listener. */
+	n = recv(clien, buf, sizeof(buf), 0);
+	if (!ASSERT_LT(n, 0, "client recv on reset child"))
+		goto cleanup;
+	ASSERT_EQ(errno, ECONNRESET, "error code on reset child");
+
+cleanup:
+	if (clien != -1)
+		close(clien);
+	if (accept_serv != -1)
+		close(accept_serv);
+	if (serv != -1)
+		close(serv);
+}
+
+static void test_tcp_timewait(struct sock_destroy_prog *skel)
+{
+	int serv = -1, clien = -1, accept_serv = -1, n;
+	struct timeval tv = {};
+	char buf[1];
+
+	serv = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0);
+	if (!ASSERT_GE(serv, 0, "start_server"))
+		goto cleanup;
+
+	clien = connect_to_fd(serv, 0);
+	if (!ASSERT_GE(clien, 0, "connect_to_fd"))
+		goto cleanup;
+
+	accept_serv = accept(serv, NULL, NULL);
+	if (!ASSERT_GE(accept_serv, 0, "serv accept"))
+		goto cleanup;
+
+	/*
+	 * Active close from the client, then close the server side. Once
+	 * recv() sees EOF the server FIN has been processed and the client
+	 * sock is in TIME_WAIT. Block without timeout so a loaded CI box
+	 * can't race us.
+	 */
+	if (!ASSERT_OK(setsockopt(clien, SOL_SOCKET, SO_RCVTIMEO, &tv,
+				  sizeof(tv)), "clear rcvtimeo"))
+		goto cleanup;
+	if (!ASSERT_OK(shutdown(clien, SHUT_WR), "client shutdown"))
+		goto cleanup;
+
+	/*
+	 * Make sure the server has seen the client FIN before it closes,
+	 * so the two FINs never cross.
+	 */
+	n = recv(accept_serv, buf, sizeof(buf), 0);
+	if (!ASSERT_EQ(n, 0, "server recv EOF"))
+		goto cleanup;
+
+	close(accept_serv);
+	accept_serv = -1;
+
+	/* block until return EOF */
+	n = recv(clien, buf, sizeof(buf), 0);
+	if (!ASSERT_EQ(n, 0, "client recv EOF"))
+		goto cleanup;
+
+	/* Run iterator program that destroys the timewait client sock. */
+	skel->bss->tw_found = 0;
+	start_iter_sockets(skel->progs.iter_tcp6_timewait);
+	if (!ASSERT_EQ(skel->bss->tw_found, 1, "timewait sock found"))
+		goto cleanup;
+
+	ASSERT_OK(skel->bss->tw_destroy_err, "destroy timewait sock");
+
+	/* The destroyed timewait sock must be gone. */
+	skel->bss->tw_found = 0;
+	start_iter_sockets(skel->progs.iter_tcp6_timewait);
+	ASSERT_EQ(skel->bss->tw_found, 0, "timewait sock destroyed");
+
+cleanup:
+	if (clien != -1)
+		close(clien);
+	if (accept_serv != -1)
+		close(accept_serv);
+	if (serv != -1)
+		close(serv);
+}
+
 static void test_udp_client(struct sock_destroy_prog *skel)
 {
 	int serv = -1, clien = -1, n = 0;
@@ -204,6 +321,10 @@ void test_sock_destroy(void)
 		test_tcp_client(skel);
 	if (test__start_subtest("tcp_server"))
 		test_tcp_server(skel);
+	if (test__start_subtest("tcp_listen_pending"))
+		test_tcp_listen_pending(skel);
+	if (test__start_subtest("tcp_timewait"))
+		test_tcp_timewait(skel);
 	if (test__start_subtest("udp_client"))
 		test_udp_client(skel);
 	if (test__start_subtest("udp_server"))

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

@@ -7,6 +7,8 @@
 #include "bpf_tracing_net.h"
 
 __be16 serv_port = 0;
+int tw_found = 0;
+int tw_destroy_err = 0;
 
 int bpf_sock_destroy(struct sock_common *sk) __ksym;
 
@@ -100,6 +102,34 @@ int iter_tcp6_server(struct bpf_iter__tcp *ctx)
 	return 0;
 }
 
+SEC("iter/tcp")
+int iter_tcp6_timewait(struct bpf_iter__tcp *ctx)
+{
+	struct sock_common *sk_common = ctx->sk_common;
+	__u64 *val;
+	int key = 0;
+
+	if (!sk_common)
+		return 0;
+
+	if (sk_common->skc_family != AF_INET6)
+		return 0;
+
+	if (!bpf_skc_to_tcp_timewait_sock(sk_common))
+		return 0;
+
+	val = bpf_map_lookup_elem(&tcp_conn_sockets, &key);
+	if (!val)
+		return 0;
+	/* The timewait sock inherits the cookie of the closed client sock. */
+	if (bpf_get_socket_cookie(sk_common) != *val)
+		return 0;
+
+	tw_found++;
+	tw_destroy_err = bpf_sock_destroy(sk_common);
+
+	return 0;
+}
 
 SEC("iter/udp")
 int iter_udp6_client(struct bpf_iter__udp *ctx)