From 4b7b492615cf3017190f55444f7016812b66611d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 13 Nov 2023 13:49:38 +0000 Subject: af_unix: fix use-after-free in unix_stream_read_actor() syzbot reported the following crash [1] After releasing unix socket lock, u->oob_skb can be changed by another thread. We must temporarily increase skb refcount to make sure this other thread will not free the skb under us. [1] BUG: KASAN: slab-use-after-free in unix_stream_read_actor+0xa7/0xc0 net/unix/af_unix.c:2866 Read of size 4 at addr ffff88801f3b9cc4 by task syz-executor107/5297 CPU: 1 PID: 5297 Comm: syz-executor107 Not tainted 6.6.0-syzkaller-15910-gb8e3a87a627b #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/09/2023 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xd9/0x1b0 lib/dump_stack.c:106 print_address_description mm/kasan/report.c:364 [inline] print_report+0xc4/0x620 mm/kasan/report.c:475 kasan_report+0xda/0x110 mm/kasan/report.c:588 unix_stream_read_actor+0xa7/0xc0 net/unix/af_unix.c:2866 unix_stream_recv_urg net/unix/af_unix.c:2587 [inline] unix_stream_read_generic+0x19a5/0x2480 net/unix/af_unix.c:2666 unix_stream_recvmsg+0x189/0x1b0 net/unix/af_unix.c:2903 sock_recvmsg_nosec net/socket.c:1044 [inline] sock_recvmsg+0xe2/0x170 net/socket.c:1066 ____sys_recvmsg+0x21f/0x5c0 net/socket.c:2803 ___sys_recvmsg+0x115/0x1a0 net/socket.c:2845 __sys_recvmsg+0x114/0x1e0 net/socket.c:2875 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_64+0x3f/0x110 arch/x86/entry/common.c:82 entry_SYSCALL_64_after_hwframe+0x63/0x6b RIP: 0033:0x7fc67492c559 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 51 18 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007fc6748ab228 EFLAGS: 00000246 ORIG_RAX: 000000000000002f RAX: ffffffffffffffda RBX: 000000000000001c RCX: 00007fc67492c559 RDX: 0000000040010083 RSI: 0000000020000140 RDI: 0000000000000004 RBP: 00007fc6749b6348 R08: 00007fc6748ab6c0 R09: 00007fc6748ab6c0 R10: 0000000000000000 R11: 0000000000000246 R12: 00007fc6749b6340 R13: 00007fc6749b634c R14: 00007ffe9fac52a0 R15: 00007ffe9fac5388 Allocated by task 5295: kasan_save_stack+0x33/0x50 mm/kasan/common.c:45 kasan_set_track+0x25/0x30 mm/kasan/common.c:52 __kasan_slab_alloc+0x81/0x90 mm/kasan/common.c:328 kasan_slab_alloc include/linux/kasan.h:188 [inline] slab_post_alloc_hook mm/slab.h:763 [inline] slab_alloc_node mm/slub.c:3478 [inline] kmem_cache_alloc_node+0x180/0x3c0 mm/slub.c:3523 __alloc_skb+0x287/0x330 net/core/skbuff.c:641 alloc_skb include/linux/skbuff.h:1286 [inline] alloc_skb_with_frags+0xe4/0x710 net/core/skbuff.c:6331 sock_alloc_send_pskb+0x7e4/0x970 net/core/sock.c:2780 sock_alloc_send_skb include/net/sock.h:1884 [inline] queue_oob net/unix/af_unix.c:2147 [inline] unix_stream_sendmsg+0xb5f/0x10a0 net/unix/af_unix.c:2301 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg+0xd5/0x180 net/socket.c:745 ____sys_sendmsg+0x6ac/0x940 net/socket.c:2584 ___sys_sendmsg+0x135/0x1d0 net/socket.c:2638 __sys_sendmsg+0x117/0x1e0 net/socket.c:2667 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_64+0x3f/0x110 arch/x86/entry/common.c:82 entry_SYSCALL_64_after_hwframe+0x63/0x6b Freed by task 5295: kasan_save_stack+0x33/0x50 mm/kasan/common.c:45 kasan_set_track+0x25/0x30 mm/kasan/common.c:52 kasan_save_free_info+0x2b/0x40 mm/kasan/generic.c:522 ____kasan_slab_free mm/kasan/common.c:236 [inline] ____kasan_slab_free+0x15b/0x1b0 mm/kasan/common.c:200 kasan_slab_free include/linux/kasan.h:164 [inline] slab_free_hook mm/slub.c:1800 [inline] slab_free_freelist_hook+0x114/0x1e0 mm/slub.c:1826 slab_free mm/slub.c:3809 [inline] kmem_cache_free+0xf8/0x340 mm/slub.c:3831 kfree_skbmem+0xef/0x1b0 net/core/skbuff.c:1015 __kfree_skb net/core/skbuff.c:1073 [inline] consume_skb net/core/skbuff.c:1288 [inline] consume_skb+0xdf/0x170 net/core/skbuff.c:1282 queue_oob net/unix/af_unix.c:2178 [inline] unix_stream_sendmsg+0xd49/0x10a0 net/unix/af_unix.c:2301 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg+0xd5/0x180 net/socket.c:745 ____sys_sendmsg+0x6ac/0x940 net/socket.c:2584 ___sys_sendmsg+0x135/0x1d0 net/socket.c:2638 __sys_sendmsg+0x117/0x1e0 net/socket.c:2667 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_64+0x3f/0x110 arch/x86/entry/common.c:82 entry_SYSCALL_64_after_hwframe+0x63/0x6b The buggy address belongs to the object at ffff88801f3b9c80 which belongs to the cache skbuff_head_cache of size 240 The buggy address is located 68 bytes inside of freed 240-byte region [ffff88801f3b9c80, ffff88801f3b9d70) The buggy address belongs to the physical page: page:ffffea00007cee40 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x1f3b9 flags: 0xfff00000000800(slab|node=0|zone=1|lastcpupid=0x7ff) page_type: 0xffffffff() raw: 00fff00000000800 ffff888142a60640 dead000000000122 0000000000000000 raw: 0000000000000000 00000000000c000c 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected page_owner tracks the page as allocated page last allocated via order 0, migratetype Unmovable, gfp_mask 0x12cc0(GFP_KERNEL|__GFP_NOWARN|__GFP_NORETRY), pid 5299, tgid 5283 (syz-executor107), ts 103803840339, free_ts 103600093431 set_page_owner include/linux/page_owner.h:31 [inline] post_alloc_hook+0x2cf/0x340 mm/page_alloc.c:1537 prep_new_page mm/page_alloc.c:1544 [inline] get_page_from_freelist+0xa25/0x36c0 mm/page_alloc.c:3312 __alloc_pages+0x1d0/0x4a0 mm/page_alloc.c:4568 alloc_pages_mpol+0x258/0x5f0 mm/mempolicy.c:2133 alloc_slab_page mm/slub.c:1870 [inline] allocate_slab+0x251/0x380 mm/slub.c:2017 new_slab mm/slub.c:2070 [inline] ___slab_alloc+0x8c7/0x1580 mm/slub.c:3223 __slab_alloc.constprop.0+0x56/0xa0 mm/slub.c:3322 __slab_alloc_node mm/slub.c:3375 [inline] slab_alloc_node mm/slub.c:3468 [inline] kmem_cache_alloc_node+0x132/0x3c0 mm/slub.c:3523 __alloc_skb+0x287/0x330 net/core/skbuff.c:641 alloc_skb include/linux/skbuff.h:1286 [inline] alloc_skb_with_frags+0xe4/0x710 net/core/skbuff.c:6331 sock_alloc_send_pskb+0x7e4/0x970 net/core/sock.c:2780 sock_alloc_send_skb include/net/sock.h:1884 [inline] queue_oob net/unix/af_unix.c:2147 [inline] unix_stream_sendmsg+0xb5f/0x10a0 net/unix/af_unix.c:2301 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg+0xd5/0x180 net/socket.c:745 ____sys_sendmsg+0x6ac/0x940 net/socket.c:2584 ___sys_sendmsg+0x135/0x1d0 net/socket.c:2638 __sys_sendmsg+0x117/0x1e0 net/socket.c:2667 page last free stack trace: reset_page_owner include/linux/page_owner.h:24 [inline] free_pages_prepare mm/page_alloc.c:1137 [inline] free_unref_page_prepare+0x4f8/0xa90 mm/page_alloc.c:2347 free_unref_page+0x33/0x3b0 mm/page_alloc.c:2487 __unfreeze_partials+0x21d/0x240 mm/slub.c:2655 qlink_free mm/kasan/quarantine.c:168 [inline] qlist_free_all+0x6a/0x170 mm/kasan/quarantine.c:187 kasan_quarantine_reduce+0x18e/0x1d0 mm/kasan/quarantine.c:294 __kasan_slab_alloc+0x65/0x90 mm/kasan/common.c:305 kasan_slab_alloc include/linux/kasan.h:188 [inline] slab_post_alloc_hook mm/slab.h:763 [inline] slab_alloc_node mm/slub.c:3478 [inline] slab_alloc mm/slub.c:3486 [inline] __kmem_cache_alloc_lru mm/slub.c:3493 [inline] kmem_cache_alloc+0x15d/0x380 mm/slub.c:3502 vm_area_dup+0x21/0x2f0 kernel/fork.c:500 __split_vma+0x17d/0x1070 mm/mmap.c:2365 split_vma mm/mmap.c:2437 [inline] vma_modify+0x25d/0x450 mm/mmap.c:2472 vma_modify_flags include/linux/mm.h:3271 [inline] mprotect_fixup+0x228/0xc80 mm/mprotect.c:635 do_mprotect_pkey+0x852/0xd60 mm/mprotect.c:809 __do_sys_mprotect mm/mprotect.c:830 [inline] __se_sys_mprotect mm/mprotect.c:827 [inline] __x64_sys_mprotect+0x78/0xb0 mm/mprotect.c:827 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_64+0x3f/0x110 arch/x86/entry/common.c:82 entry_SYSCALL_64_after_hwframe+0x63/0x6b Memory state around the buggy address: ffff88801f3b9b80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff88801f3b9c00: fb fb fb fb fb fb fc fc fc fc fc fc fc fc fc fc >ffff88801f3b9c80: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff88801f3b9d00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fc fc ffff88801f3b9d80: fc fc fc fc fc fc fc fc fa fb fb fb fb fb fb fb Fixes: 876c14ad014d ("af_unix: fix holding spinlock in oob handling") Reported-and-tested-by: syzbot+7a2d546fa43e49315ed3@syzkaller.appspotmail.com Signed-off-by: Eric Dumazet Cc: Rao Shoaib Reviewed-by: Rao shoaib Link: https://lore.kernel.org/r/20231113134938.168151-1-edumazet@google.com Signed-off-by: Paolo Abeni --- net/unix/af_unix.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'net/unix/af_unix.c') diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 45506a95b25f..a357dc5f2404 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2581,15 +2581,16 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state) if (!(state->flags & MSG_PEEK)) WRITE_ONCE(u->oob_skb, NULL); - + else + skb_get(oob_skb); unix_state_unlock(sk); chunk = state->recv_actor(oob_skb, 0, chunk, state); - if (!(state->flags & MSG_PEEK)) { + if (!(state->flags & MSG_PEEK)) UNIXCB(oob_skb).consumed += 1; - kfree_skb(oob_skb); - } + + consume_skb(oob_skb); mutex_unlock(&u->iolock); -- cgit v1.2.3 From 8866730aed5100f06d3d965c22f1c61f74942541 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 28 Nov 2023 17:25:56 -0800 Subject: bpf, sockmap: af_unix stream sockets need to hold ref for pair sock AF_UNIX stream sockets are a paired socket. So sending on one of the pairs will lookup the paired socket as part of the send operation. It is possible however to put just one of the pairs in a BPF map. This currently increments the refcnt on the sock in the sockmap to ensure it is not free'd by the stack before sockmap cleans up its state and stops any skbs being sent/recv'd to that socket. But we missed a case. If the peer socket is closed it will be free'd by the stack. However, the paired socket can still be referenced from BPF sockmap side because we hold a reference there. Then if we are sending traffic through BPF sockmap to that socket it will try to dereference the free'd pair in its send logic creating a use after free. And following splat: [59.900375] BUG: KASAN: slab-use-after-free in sk_wake_async+0x31/0x1b0 [59.901211] Read of size 8 at addr ffff88811acbf060 by task kworker/1:2/954 [...] [59.905468] Call Trace: [59.905787] [59.906066] dump_stack_lvl+0x130/0x1d0 [59.908877] print_report+0x16f/0x740 [59.910629] kasan_report+0x118/0x160 [59.912576] sk_wake_async+0x31/0x1b0 [59.913554] sock_def_readable+0x156/0x2a0 [59.914060] unix_stream_sendmsg+0x3f9/0x12a0 [59.916398] sock_sendmsg+0x20e/0x250 [59.916854] skb_send_sock+0x236/0xac0 [59.920527] sk_psock_backlog+0x287/0xaa0 To fix let BPF sockmap hold a refcnt on both the socket in the sockmap and its paired socket. It wasn't obvious how to contain the fix to bpf_unix logic. The primarily problem with keeping this logic in bpf_unix was: In the sock close() we could handle the deref by having a close handler. But, when we are destroying the psock through a map delete operation we wouldn't have gotten any signal thorugh the proto struct other than it being replaced. If we do the deref from the proto replace its too early because we need to deref the sk_pair after the backlog worker has been stopped. Given all this it seems best to just cache it at the end of the psock and eat 8B for the af_unix and vsock users. Notice dgram sockets are OK because they handle locking already. Fixes: 94531cfcbe79 ("af_unix: Add unix_stream_proto for sockmap") Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann Reviewed-by: Jakub Sitnicki Link: https://lore.kernel.org/bpf/20231129012557.95371-2-john.fastabend@gmail.com --- include/linux/skmsg.h | 1 + include/net/af_unix.h | 1 + net/core/skmsg.c | 2 ++ net/unix/af_unix.c | 2 -- net/unix/unix_bpf.c | 5 +++++ 5 files changed, 9 insertions(+), 2 deletions(-) (limited to 'net/unix/af_unix.c') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index c1637515a8a4..c953b8c0d2f4 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -106,6 +106,7 @@ struct sk_psock { struct mutex work_mutex; struct sk_psock_work_state work_state; struct delayed_work work; + struct sock *sk_pair; struct rcu_work rwork; }; diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 824c258143a3..49c4640027d8 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -75,6 +75,7 @@ struct unix_sock { }; #define unix_sk(ptr) container_of_const(ptr, struct unix_sock, sk) +#define unix_peer(sk) (unix_sk(sk)->peer) #define peer_wait peer_wq.wait diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 6c31eefbd777..93ecfceac1bc 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -826,6 +826,8 @@ static void sk_psock_destroy(struct work_struct *work) if (psock->sk_redir) sock_put(psock->sk_redir); + if (psock->sk_pair) + sock_put(psock->sk_pair); sock_put(psock->sk); kfree(psock); } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index a357dc5f2404..ac1f2bc18fc9 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -213,8 +213,6 @@ static inline bool unix_secdata_eq(struct scm_cookie *scm, struct sk_buff *skb) } #endif /* CONFIG_SECURITY_NETWORK */ -#define unix_peer(sk) (unix_sk(sk)->peer) - static inline int unix_our_peer(struct sock *sk, struct sock *osk) { return unix_peer(osk) == sk; diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c index 2f9d8271c6ec..7ea7c3a0d0d0 100644 --- a/net/unix/unix_bpf.c +++ b/net/unix/unix_bpf.c @@ -159,12 +159,17 @@ int unix_dgram_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool re int unix_stream_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) { + struct sock *sk_pair; + if (restore) { sk->sk_write_space = psock->saved_write_space; sock_replace_proto(sk, psock->sk_proto); return 0; } + sk_pair = unix_peer(sk); + sock_hold(sk_pair); + psock->sk_pair = sk_pair; unix_stream_bpf_check_needs_rebuild(psock->sk_proto); sock_replace_proto(sk, &unix_stream_bpf_prot); return 0; -- cgit v1.2.3