From b46f4eaa4f0ec38909fb0072eea3aeddb32f954e Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 5 Apr 2024 15:10:57 -0700 Subject: af_unix: Clear stale u->oob_skb. syzkaller started to report deadlock of unix_gc_lock after commit 4090fa373f0e ("af_unix: Replace garbage collection algorithm."), but it just uncovers the bug that has been there since commit 314001f0bf92 ("af_unix: Add OOB support"). The repro basically does the following. from socket import * from array import array c1, c2 = socketpair(AF_UNIX, SOCK_STREAM) c1.sendmsg([b'a'], [(SOL_SOCKET, SCM_RIGHTS, array("i", [c2.fileno()]))], MSG_OOB) c2.recv(1) # blocked as no normal data in recv queue c2.close() # done async and unblock recv() c1.close() # done async and trigger GC A socket sends its file descriptor to itself as OOB data and tries to receive normal data, but finally recv() fails due to async close(). The problem here is wrong handling of OOB skb in manage_oob(). When recvmsg() is called without MSG_OOB, manage_oob() is called to check if the peeked skb is OOB skb. In such a case, manage_oob() pops it out of the receive queue but does not clear unix_sock(sk)->oob_skb. This is wrong in terms of uAPI. Let's say we send "hello" with MSG_OOB, and "world" without MSG_OOB. The 'o' is handled as OOB data. When recv() is called twice without MSG_OOB, the OOB data should be lost. >>> from socket import * >>> c1, c2 = socketpair(AF_UNIX, SOCK_STREAM, 0) >>> c1.send(b'hello', MSG_OOB) # 'o' is OOB data 5 >>> c1.send(b'world') 5 >>> c2.recv(5) # OOB data is not received b'hell' >>> c2.recv(5) # OOB date is skipped b'world' >>> c2.recv(5, MSG_OOB) # This should return an error b'o' In the same situation, TCP actually returns -EINVAL for the last recv(). Also, if we do not clear unix_sk(sk)->oob_skb, unix_poll() always set EPOLLPRI even though the data has passed through by previous recv(). To avoid these issues, we must clear unix_sk(sk)->oob_skb when dequeuing it from recv queue. The reason why the old GC did not trigger the deadlock is because the old GC relied on the receive queue to detect the loop. When it is triggered, the socket with OOB data is marked as GC candidate because file refcount == inflight count (1). However, after traversing all inflight sockets, the socket still has a positive inflight count (1), thus the socket is excluded from candidates. Then, the old GC lose the chance to garbage-collect the socket. With the old GC, the repro continues to create true garbage that will never be freed nor detected by kmemleak as it's linked to the global inflight list. That's why we couldn't even notice the issue. Fixes: 314001f0bf92 ("af_unix: Add OOB support") Reported-by: syzbot+7f7f201cc2668a8fd169@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=7f7f201cc2668a8fd169 Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20240405221057.2406-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- net/unix/af_unix.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'net/unix') diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 5b41e2321209..d032eb5fa6df 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2665,7 +2665,9 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk, } } else if (!(flags & MSG_PEEK)) { skb_unlink(skb, &sk->sk_receive_queue); - consume_skb(skb); + WRITE_ONCE(u->oob_skb, NULL); + if (!WARN_ON_ONCE(skb_unref(skb))) + kfree_skb(skb); skb = skb_peek(&sk->sk_receive_queue); } } -- cgit v1.2.3 From 47d8ac011fe1c9251070e1bd64cb10b48193ec51 Mon Sep 17 00:00:00 2001 From: Michal Luczaj Date: Tue, 9 Apr 2024 22:09:39 +0200 Subject: af_unix: Fix garbage collector racing against connect() Garbage collector does not take into account the risk of embryo getting enqueued during the garbage collection. If such embryo has a peer that carries SCM_RIGHTS, two consecutive passes of scan_children() may see a different set of children. Leading to an incorrectly elevated inflight count, and then a dangling pointer within the gc_inflight_list. sockets are AF_UNIX/SOCK_STREAM S is an unconnected socket L is a listening in-flight socket bound to addr, not in fdtable V's fd will be passed via sendmsg(), gets inflight count bumped connect(S, addr) sendmsg(S, [V]); close(V) __unix_gc() ---------------- ------------------------- ----------- NS = unix_create1() skb1 = sock_wmalloc(NS) L = unix_find_other(addr) unix_state_lock(L) unix_peer(S) = NS // V count=1 inflight=0 NS = unix_peer(S) skb2 = sock_alloc() skb_queue_tail(NS, skb2[V]) // V became in-flight // V count=2 inflight=1 close(V) // V count=1 inflight=1 // GC candidate condition met for u in gc_inflight_list: if (total_refs == inflight_refs) add u to gc_candidates // gc_candidates={L, V} for u in gc_candidates: scan_children(u, dec_inflight) // embryo (skb1) was not // reachable from L yet, so V's // inflight remains unchanged __skb_queue_tail(L, skb1) unix_state_unlock(L) for u in gc_candidates: if (u.inflight) scan_children(u, inc_inflight_move_tail) // V count=1 inflight=2 (!) If there is a GC-candidate listening socket, lock/unlock its state. This makes GC wait until the end of any ongoing connect() to that socket. After flipping the lock, a possibly SCM-laden embryo is already enqueued. And if there is another embryo coming, it can not possibly carry SCM_RIGHTS. At this point, unix_inflight() can not happen because unix_gc_lock is already taken. Inflight graph remains unaffected. Fixes: 1fd05ba5a2f2 ("[AF_UNIX]: Rewrite garbage collector, fixes race.") Signed-off-by: Michal Luczaj Reviewed-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/20240409201047.1032217-1-mhal@rbox.co Signed-off-by: Paolo Abeni --- net/unix/garbage.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) (limited to 'net/unix') diff --git a/net/unix/garbage.c b/net/unix/garbage.c index fa39b6265238..6433a414acf8 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -274,11 +274,22 @@ static void __unix_gc(struct work_struct *work) * receive queues. Other, non candidate sockets _can_ be * added to queue, so we must make sure only to touch * candidates. + * + * Embryos, though never candidates themselves, affect which + * candidates are reachable by the garbage collector. Before + * being added to a listener's queue, an embryo may already + * receive data carrying SCM_RIGHTS, potentially making the + * passed socket a candidate that is not yet reachable by the + * collector. It becomes reachable once the embryo is + * enqueued. Therefore, we must ensure that no SCM-laden + * embryo appears in a (candidate) listener's queue between + * consecutive scan_children() calls. */ list_for_each_entry_safe(u, next, &gc_inflight_list, link) { + struct sock *sk = &u->sk; long total_refs; - total_refs = file_count(u->sk.sk_socket->file); + total_refs = file_count(sk->sk_socket->file); WARN_ON_ONCE(!u->inflight); WARN_ON_ONCE(total_refs < u->inflight); @@ -286,6 +297,11 @@ static void __unix_gc(struct work_struct *work) list_move_tail(&u->link, &gc_candidates); __set_bit(UNIX_GC_CANDIDATE, &u->gc_flags); __set_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags); + + if (sk->sk_state == TCP_LISTEN) { + unix_state_lock(sk); + unix_state_unlock(sk); + } } } -- cgit v1.2.3