From d900f3d20cc3169ce42ec72acc850e662a4d4db2 Mon Sep 17 00:00:00 2001 From: Liu Jian Date: Fri, 3 Mar 2023 16:09:46 +0800 Subject: bpf, sockmap: Fix an infinite loop error when len is 0 in tcp_bpf_recvmsg_parser() When the buffer length of the recvmsg system call is 0, we got the flollowing soft lockup problem: watchdog: BUG: soft lockup - CPU#3 stuck for 27s! [a.out:6149] CPU: 3 PID: 6149 Comm: a.out Kdump: loaded Not tainted 6.2.0+ #30 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.15.0-1 04/01/2014 RIP: 0010:remove_wait_queue+0xb/0xc0 Code: 5e 41 5f c3 cc cc cc cc 0f 1f 80 00 00 00 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 f3 0f 1e fa 0f 1f 44 00 00 41 57 <41> 56 41 55 41 54 55 48 89 fd 53 48 89 f3 4c 8d 6b 18 4c 8d 73 20 RSP: 0018:ffff88811b5978b8 EFLAGS: 00000246 RAX: 0000000000000000 RBX: ffff88811a7d3780 RCX: ffffffffb7a4d768 RDX: dffffc0000000000 RSI: ffff88811b597908 RDI: ffff888115408040 RBP: 1ffff110236b2f1b R08: 0000000000000000 R09: ffff88811a7d37e7 R10: ffffed10234fa6fc R11: 0000000000000001 R12: ffff88811179b800 R13: 0000000000000001 R14: ffff88811a7d38a8 R15: ffff88811a7d37e0 FS: 00007f6fb5398740(0000) GS:ffff888237180000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020000000 CR3: 000000010b6ba002 CR4: 0000000000370ee0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: tcp_msg_wait_data+0x279/0x2f0 tcp_bpf_recvmsg_parser+0x3c6/0x490 inet_recvmsg+0x280/0x290 sock_recvmsg+0xfc/0x120 ____sys_recvmsg+0x160/0x3d0 ___sys_recvmsg+0xf0/0x180 __sys_recvmsg+0xea/0x1a0 do_syscall_64+0x3f/0x90 entry_SYSCALL_64_after_hwframe+0x72/0xdc The logic in tcp_bpf_recvmsg_parser is as follows: msg_bytes_ready: copied = sk_msg_recvmsg(sk, psock, msg, len, flags); if (!copied) { wait data; goto msg_bytes_ready; } In this case, "copied" always is 0, the infinite loop occurs. According to the Linux system call man page, 0 should be returned in this case. Therefore, in tcp_bpf_recvmsg_parser(), if the length is 0, directly return. Also modify several other functions with the same problem. Fixes: 1f5be6b3b063 ("udp: Implement udp_bpf_recvmsg() for sockmap") Fixes: 9825d866ce0d ("af_unix: Implement unix_dgram_bpf_recvmsg()") Fixes: c5d2177a72a1 ("bpf, sockmap: Fix race in ingress receive verdict with redirect to self") Fixes: 604326b41a6f ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Liu Jian Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Cc: Jakub Sitnicki Link: https://lore.kernel.org/bpf/20230303080946.1146638-1-liujian56@huawei.com --- net/unix/unix_bpf.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'net/unix') diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c index e9bf15513961..2f9d8271c6ec 100644 --- a/net/unix/unix_bpf.c +++ b/net/unix/unix_bpf.c @@ -54,6 +54,9 @@ static int unix_bpf_recvmsg(struct sock *sk, struct msghdr *msg, struct sk_psock *psock; int copied; + if (!len) + return 0; + psock = sk_psock_get(sk); if (unlikely(!psock)) return __unix_recvmsg(sk, msg, len, flags); -- cgit v1.2.3 From 2aab4b96900272885bc157f8b236abf1cdc02e08 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 7 Mar 2023 16:45:30 +0000 Subject: af_unix: fix struct pid leaks in OOB support syzbot reported struct pid leak [1]. Issue is that queue_oob() calls maybe_add_creds() which potentially holds a reference on a pid. But skb->destructor is not set (either directly or by calling unix_scm_to_skb()) This means that subsequent kfree_skb() or consume_skb() would leak this reference. In this fix, I chose to fully support scm even for the OOB message. [1] BUG: memory leak unreferenced object 0xffff8881053e7f80 (size 128): comm "syz-executor242", pid 5066, jiffies 4294946079 (age 13.220s) hex dump (first 32 bytes): 01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [] alloc_pid+0x6a/0x560 kernel/pid.c:180 [] copy_process+0x169f/0x26c0 kernel/fork.c:2285 [] kernel_clone+0xf7/0x610 kernel/fork.c:2684 [] __do_sys_clone+0x7c/0xb0 kernel/fork.c:2825 [] do_syscall_x64 arch/x86/entry/common.c:50 [inline] [] do_syscall_64+0x39/0xb0 arch/x86/entry/common.c:80 [] entry_SYSCALL_64_after_hwframe+0x63/0xcd Fixes: 314001f0bf92 ("af_unix: Add OOB support") Reported-by: syzbot+7699d9e5635c10253a27@syzkaller.appspotmail.com Signed-off-by: Eric Dumazet Cc: Rao Shoaib Reviewed-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/20230307164530.771896-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/unix/af_unix.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'net/unix') diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 347122c3575e..0b0f18ecce44 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2105,7 +2105,8 @@ out: #define UNIX_SKB_FRAGS_SZ (PAGE_SIZE << get_order(32768)) #if IS_ENABLED(CONFIG_AF_UNIX_OOB) -static int queue_oob(struct socket *sock, struct msghdr *msg, struct sock *other) +static int queue_oob(struct socket *sock, struct msghdr *msg, struct sock *other, + struct scm_cookie *scm, bool fds_sent) { struct unix_sock *ousk = unix_sk(other); struct sk_buff *skb; @@ -2116,6 +2117,11 @@ static int queue_oob(struct socket *sock, struct msghdr *msg, struct sock *other if (!skb) return err; + err = unix_scm_to_skb(scm, skb, !fds_sent); + if (err < 0) { + kfree_skb(skb); + return err; + } skb_put(skb, 1); err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, 1); @@ -2243,7 +2249,7 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, #if IS_ENABLED(CONFIG_AF_UNIX_OOB) if (msg->msg_flags & MSG_OOB) { - err = queue_oob(sock, msg, other); + err = queue_oob(sock, msg, other, &scm, fds_sent); if (err) goto out_err; sent++; -- cgit v1.2.3