From 01b245ba016d44861690594e10f67e026ce8552f Mon Sep 17 00:00:00 2001 From: Jiayuan Chen Date: Thu, 10 Sep 2026 19:26:26 +0800 Subject: [PATCH 1/3] bpf: Fix out-of-bounds read of sk_protocol in bpf_sock_destroy() sk_protocol lives in struct sock, not in struct sock_common. A timewait or request sock handed to bpf_sock_destroy() by the tcp iterator is neither, so reading sk->sk_protocol runs past the object: ================================================================== BUG: KASAN: slab-out-of-bounds in bpf_sock_destroy+0xc7/0xe0 Read of size 2 at addr ffff8881047d11b4 by task test_progs/428 Tainted: [W]=WARN Call Trace: dump_stack_lvl+0x91/0xf0 print_report+0xd1/0x630 kasan_report+0xf3/0x130 __asan_report_load2_noabort+0x14/0x30 bpf_sock_destroy+0xc7/0xe0 bpf_prog_c3dd61f9d9cd9f37_iter_tcp6_timewait+0x9f/0xb7 bpf_iter_run_prog+0x538/0xde0 bpf_iter_tcp_seq_show+0x26b/0x4b0 bpf_seq_read+0x424/0x1210 vfs_read+0x197/0xe40 ksys_read+0x119/0x240 __x64_sys_read+0x72/0xc0 x64_sys_call+0x647/0x27e0 do_syscall_64+0xe5/0x610 entry_SYSCALL_64_after_hwframe+0x76/0x7e Only check sk_protocol on full socks. tcp_abort() already knows how to deal with TIME_WAIT and NEW_SYN_RECV socks. Also fix the comment, it never matched the code. Fixes: 4ddbcb886268 ("bpf: Add bpf_sock_destroy kfunc") Reported-by: Xiang Mei (Microsoft) Closes: https://lore.kernel.org/bpf/20260702224519.800135-1-xmei5@asu.edu/ Signed-off-by: Jiayuan Chen Reviewed-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/20260910112634.152195-1-jiayuan.chen@linux.dev Signed-off-by: Alexei Starovoitov --- net/core/filter.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/net/core/filter.c b/net/core/filter.c index 2a84f9d01131..cae43b999162 100644 --- a/net/core/filter.c +++ b/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); From eaab8cab451b9502ce224cd202550375b894a467 Mon Sep 17 00:00:00 2001 From: Jiayuan Chen Date: Thu, 10 Sep 2026 19:27:28 +0800 Subject: [PATCH 2/3] tcp: Skip cond_resched() in inet_csk_listen_stop() under BPF context bpf_sock_destroy() runs from the tcp iterator, under rcu_read_lock(). If the sock is a listener that still has children in its accept queue, tcp_abort() ends up in inet_csk_listen_stop() and the cond_resched() there trips the debug check: BUG: sleeping function called from invalid context at net/ipv4/inet_connection_sock.c:1523 in_atomic(): 0, irqs_disabled(): 0, non_block: 0, pid: 628, name: test_progs preempt_count: 0, expected: 0 RCU nest depth: 1, expected: 0 locks held by test_progs/628: 3, last CPU#3: #0: ffff8881158cee18 (&p->lock){+.+.}-{4:4}, at: bpf_seq_read+0x56/0x1210 #1: ffff8881106bb858 (sk_lock-AF_INET6){+.+.}-{0:0}, at: bpf_iter_tcp_seq_show+0x32b/0x4b0 #2: ffffffffb435af20 (rcu_read_lock){....}-{1:3}, at: bpf_iter_run_prog+0x46b/0xde0 CPU: 3 UID: 0 PID: 628 Comm: test_progs Tainted: G W 7.2.0+ #65 PREEMPT Tainted: [W]=WARN Call Trace: dump_stack_lvl+0xc1/0xf0 dump_stack+0x10/0x20 __might_resched+0x3d2/0x610 inet_csk_listen_stop+0x7b/0xbf0 tcp_abort+0x23b/0x3b0 bpf_sock_destroy+0xfc/0x140 bpf_prog_448133d24601754f_iter_tcp6_server+0x81/0x8a bpf_iter_run_prog+0x538/0xde0 bpf_iter_tcp_seq_show+0x26b/0x4b0 bpf_seq_read+0x424/0x1210 vfs_read+0x197/0xe40 ksys_read+0x119/0x240 __x64_sys_read+0x72/0xc0 x64_sys_call+0x647/0x27e0 do_syscall_64+0xe5/0x610 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7fad39b28aca RSP: 002b:00007ffc381c61c0 EFLAGS: 00000246 ORIG_RAX: 0000000000000000 RAX: ffffffffffffffda RBX: 00007ffc381c6a88 RCX: 00007fad39b28aca RDX: 0000000000000032 RSI: 00007ffc381c6250 RDI: 0000000000000014 RBP: 00007ffc381c61e0 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000003 R13: 0000000000000000 R14: 000055f077c1bbb0 R15: 00007fad3a0f3000 The commit that added the kfunc already guards lock_sock() in tcp_abort() and udp_abort() with has_current_bpf_ctx(), but missed the listener path. Do the same for the cond_resched(). The loop runs inside the iterator's rcu_read_lock(), it must not reschedule or report a quiescent state there. Fixes: 4ddbcb886268 ("bpf: Add bpf_sock_destroy kfunc") Signed-off-by: Jiayuan Chen Link: https://lore.kernel.org/r/20260910112736.153710-1-jiayuan.chen@linux.dev Signed-off-by: Alexei Starovoitov --- net/ipv4/inet_connection_sock.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 6257459bcee2..6a30f1138454 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/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. */ From 8036d3a5a6589ef0721d15e7c03976bc3996f7a8 Mon Sep 17 00:00:00 2001 From: Jiayuan Chen Date: Thu, 10 Sep 2026 19:28:02 +0800 Subject: [PATCH 3/3] selftests/bpf: Test bpf_sock_destroy() on TIME_WAIT and listener socks Add two subtests. tcp_timewait: the client shuts down first and the server closes after it, so the client sock ends up in TIME_WAIT. A tcp iterator then finds the timewait sock by the cookie it inherited from the client sock and destroys it. Iterate once more to make sure it is gone. Without the first fix bpf_sock_destroy() reads past the timewait sock and KASAN complains. tcp_listen_pending: connect to a listener but never accept, so the child sits in the accept queue, then destroy the listener. Without the second fix the cond_resched() in inet_csk_listen_stop() trips the might_sleep check under rcu_read_lock(). ./test_progs -a sock_destroy #444/1 sock_destroy/tcp_client:OK #444/2 sock_destroy/tcp_server:OK #444/3 sock_destroy/tcp_listen_pending:OK #444/4 sock_destroy/tcp_timewait:OK #444/5 sock_destroy/udp_client:OK #444/6 sock_destroy/udp_server:OK #444/7 sock_destroy/trace_tcp_destroy_sock:OK #444 sock_destroy:OK Summary: 1/7 PASSED, 0 SKIPPED, 0/0 FAILED Signed-off-by: Jiayuan Chen Link: https://lore.kernel.org/r/20260910112810.153801-1-jiayuan.chen@linux.dev Signed-off-by: Alexei Starovoitov --- .../selftests/bpf/prog_tests/sock_destroy.c | 121 ++++++++++++++++++ .../selftests/bpf/progs/sock_destroy_prog.c | 30 +++++ 2 files changed, 151 insertions(+) diff --git a/tools/testing/selftests/bpf/prog_tests/sock_destroy.c b/tools/testing/selftests/bpf/prog_tests/sock_destroy.c index 9c11938fe597..78d642a02bdb 100644 --- a/tools/testing/selftests/bpf/prog_tests/sock_destroy.c +++ b/tools/testing/selftests/bpf/prog_tests/sock_destroy.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#include #include #include @@ -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")) diff --git a/tools/testing/selftests/bpf/progs/sock_destroy_prog.c b/tools/testing/selftests/bpf/progs/sock_destroy_prog.c index 9e0bf7a54cec..0a8887543218 100644 --- a/tools/testing/selftests/bpf/progs/sock_destroy_prog.c +++ b/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)