From 690939a558a76fae40ae1866f26b398f5c440559 Mon Sep 17 00:00:00 2001 From: Ignat Korchagin Date: Mon, 14 Oct 2024 16:38:01 +0100 Subject: [PATCH 1/9] Bluetooth: L2CAP: do not leave dangling sk pointer on error in l2cap_sock_create() mainline inclusion from mainline-v6.13-rc1 commit 7c4f78cdb8e7501e9f92d291a7d956591bf73be9 category: bugfix issue: #IBG4O6 CVE: CVE-2024-56605 Signed-off-by: wukuan --------------------------------------- bt_sock_alloc() allocates the sk object and attaches it to the provided sock object. On error l2cap_sock_alloc() frees the sk object, but the dangling pointer is still attached to the sock object, which may create use-after-free in other code. Signed-off-by: Ignat Korchagin Reviewed-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20241014153808.51894-3-ignat@cloudflare.com Signed-off-by: Jakub Kicinski Signed-off-by: wukuan --- net/bluetooth/l2cap_sock.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 756523e5402a..4493fc68efca 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -1875,6 +1875,7 @@ static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, chan = l2cap_chan_create(); if (!chan) { sk_free(sk); + sock->sk = NULL; return NULL; } -- Gitee From 191a98409aa98dab574fb94c9350c1fc65fa3933 Mon Sep 17 00:00:00 2001 From: Liu Jian Date: Tue, 12 Nov 2024 21:54:34 +0800 Subject: [PATCH 2/9] sunrpc: fix one UAF issue caused by sunrpc kernel tcp socket mainline inclusion from mainline-v6.13-rc1 commit 3f23f96528e8fcf8619895c4c916c52653892ec1 category: bugfix issue: NA CVE: CVE-2024-53168 Signed-off-by: wukuan --------------------------------------- BUG: KASAN: slab-use-after-free in tcp_write_timer_handler+0x156/0x3e0 Read of size 1 at addr ffff888111f322cd by task swapper/0/0 CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted 6.12.0-rc4-dirty #7 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 Call Trace: dump_stack_lvl+0x68/0xa0 print_address_description.constprop.0+0x2c/0x3d0 print_report+0xb4/0x270 kasan_report+0xbd/0xf0 tcp_write_timer_handler+0x156/0x3e0 tcp_write_timer+0x66/0x170 call_timer_fn+0xfb/0x1d0 __run_timers+0x3f8/0x480 run_timer_softirq+0x9b/0x100 handle_softirqs+0x153/0x390 __irq_exit_rcu+0x103/0x120 irq_exit_rcu+0xe/0x20 sysvec_apic_timer_interrupt+0x76/0x90 asm_sysvec_apic_timer_interrupt+0x1a/0x20 RIP: 0010:default_idle+0xf/0x20 Code: 4c 01 c7 4c 29 c2 e9 72 ff ff ff 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 f3 0f 1e fa 66 90 0f 00 2d 33 f8 25 00 fb f4 c3 cc cc cc cc 66 66 2e 0f 1f 84 00 00 00 00 00 90 90 90 90 90 RSP: 0018:ffffffffa2007e28 EFLAGS: 00000242 RAX: 00000000000f3b31 RBX: 1ffffffff4400fc7 RCX: ffffffffa09c3196 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffffff9f00590f RBP: 0000000000000000 R08: 0000000000000001 R09: ffffed102360835d R10: ffff88811b041aeb R11: 0000000000000001 R12: 0000000000000000 R13: ffffffffa202d7c0 R14: 0000000000000000 R15: 00000000000147d0 default_idle_call+0x6b/0xa0 cpuidle_idle_call+0x1af/0x1f0 do_idle+0xbc/0x130 cpu_startup_entry+0x33/0x40 rest_init+0x11f/0x210 start_kernel+0x39a/0x420 x86_64_start_reservations+0x18/0x30 x86_64_start_kernel+0x97/0xa0 common_startup_64+0x13e/0x141 Allocated by task 595: kasan_save_stack+0x24/0x50 kasan_save_track+0x14/0x30 __kasan_slab_alloc+0x87/0x90 kmem_cache_alloc_noprof+0x12b/0x3f0 copy_net_ns+0x94/0x380 create_new_namespaces+0x24c/0x500 unshare_nsproxy_namespaces+0x75/0xf0 ksys_unshare+0x24e/0x4f0 __x64_sys_unshare+0x1f/0x30 do_syscall_64+0x70/0x180 entry_SYSCALL_64_after_hwframe+0x76/0x7e Freed by task 100: kasan_save_stack+0x24/0x50 kasan_save_track+0x14/0x30 kasan_save_free_info+0x3b/0x60 __kasan_slab_free+0x54/0x70 kmem_cache_free+0x156/0x5d0 cleanup_net+0x5d3/0x670 process_one_work+0x776/0xa90 worker_thread+0x2e2/0x560 kthread+0x1a8/0x1f0 ret_from_fork+0x34/0x60 ret_from_fork_asm+0x1a/0x30 Reproduction script: mkdir -p /mnt/nfsshare mkdir -p /mnt/nfs/netns_1 mkfs.ext4 /dev/sdb mount /dev/sdb /mnt/nfsshare systemctl restart nfs-server chmod 777 /mnt/nfsshare exportfs -i -o rw,no_root_squash *:/mnt/nfsshare ip netns add netns_1 ip link add name veth_1_peer type veth peer veth_1 ifconfig veth_1_peer 11.11.0.254 up ip link set veth_1 netns netns_1 ip netns exec netns_1 ifconfig veth_1 11.11.0.1 ip netns exec netns_1 /root/iptables -A OUTPUT -d 11.11.0.254 -p tcp \ --tcp-flags FIN FIN -j DROP (note: In my environment, a DESTROY_CLIENTID operation is always sent immediately, breaking the nfs tcp connection.) ip netns exec netns_1 timeout -s 9 300 mount -t nfs -o proto=tcp,vers=4.1 \ 11.11.0.254:/mnt/nfsshare /mnt/nfs/netns_1 ip netns del netns_1 The reason here is that the tcp socket in netns_1 (nfs side) has been shutdown and closed (done in xs_destroy), but the FIN message (with ack) is discarded, and the nfsd side keeps sending retransmission messages. As a result, when the tcp sock in netns_1 processes the received message, it sends the message (FIN message) in the sending queue, and the tcp timer is re-established. When the network namespace is deleted, the net structure accessed by tcp's timer handler function causes problems. To fix this problem, let's hold netns refcnt for the tcp kernel socket as done in other modules. This is an ugly hack which can easily be backported to earlier kernels. A proper fix which cleans up the interfaces will follow, but may not be so easy to backport. Fixes: 26abe14379f8 ("net: Modify sk_alloc to not reference count the netns of kernel sockets.") Signed-off-by: Liu Jian Acked-by: Jeff Layton Reviewed-by: Kuniyuki Iwashima Signed-off-by: Trond Myklebust Signed-off-by: wukuan --- net/sunrpc/svcsock.c | 4 ++++ net/sunrpc/xprtsock.c | 7 +++++++ 2 files changed, 11 insertions(+) diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 3d5ee042c501..d32ea69c10ff 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1474,6 +1474,10 @@ static struct svc_xprt *svc_create_socket(struct svc_serv *serv, newlen = error; if (protocol == IPPROTO_TCP) { + __netns_tracker_free(net, &sock->sk->ns_tracker, false); + sock->sk->sk_net_refcnt = 1; + get_net_track(net, &sock->sk->ns_tracker, GFP_KERNEL); + sock_inuse_add(net, 1); if ((error = kernel_listen(sock, 64)) < 0) goto bummer; } diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index ae5b5380f0f0..8dc8162be14d 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1834,6 +1834,13 @@ static struct socket *xs_create_sock(struct rpc_xprt *xprt, goto out; } + if (protocol == IPPROTO_TCP) { + __netns_tracker_free(xprt->xprt_net, &sock->sk->ns_tracker, false); + sock->sk->sk_net_refcnt = 1; + get_net_track(xprt->xprt_net, &sock->sk->ns_tracker, GFP_KERNEL); + sock_inuse_add(xprt->xprt_net, 1); + } + filp = sock_alloc_file(sock, O_NONBLOCK, NULL); if (IS_ERR(filp)) return ERR_CAST(filp); -- Gitee From ef67faeb3fd8aadd038389ad40cd63fa9965d881 Mon Sep 17 00:00:00 2001 From: Zijian Zhang Date: Wed, 6 Nov 2024 22:25:19 +0000 Subject: [PATCH 3/9] bpf, sockmap: Several fixes to bpf_msg_pop_data mainline inclusion from mainline-v6.13-rc1 commit 5d609ba262475db450ba69b8e8a557bd768ac07a category: bugfix issue: NA CVE: CVE-2024-56720 Signed-off-by: wukuan --------------------------------------- Several fixes to bpf_msg_pop_data, 1. In sk_msg_shift_left, we should put_page 2. if (len == 0), return early is better 3. pop the entire sk_msg (last == msg->sg.size) should be supported 4. Fix for the value of variable "a" 5. In sk_msg_shift_left, after shifting, i has already pointed to the next element. Addtional sk_msg_iter_var_next may result in BUG. Fixes: 7246d8ed4dcc ("bpf: helper to pop data from messages") Signed-off-by: Zijian Zhang Reviewed-by: John Fastabend Link: https://lore.kernel.org/r/20241106222520.527076-8-zijianzhang@bytedance.com Signed-off-by: Martin KaFai Lau Signed-off-by: wukuan --- net/core/filter.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/net/core/filter.c b/net/core/filter.c index f20e79f2e054..61395535c91c 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2890,8 +2890,10 @@ static const struct bpf_func_proto bpf_msg_push_data_proto = { static void sk_msg_shift_left(struct sk_msg *msg, int i) { + struct scatterlist *sge = sk_msg_elem(msg, i); int prev; + put_page(sg_page(sge)); do { prev = i; sk_msg_iter_var_next(i); @@ -2928,6 +2930,9 @@ BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start, if (unlikely(flags)) return -EINVAL; + if (unlikely(len == 0)) + return 0; + /* First find the starting scatterlist element */ i = msg->sg.start; do { @@ -2940,7 +2945,7 @@ BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start, } while (i != msg->sg.end); /* Bounds checks: start and pop must be inside message */ - if (start >= offset + l || last >= msg->sg.size) + if (start >= offset + l || last > msg->sg.size) return -EINVAL; space = MAX_MSG_FRAGS - sk_msg_elem_used(msg); @@ -2969,12 +2974,12 @@ BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start, */ if (start != offset) { struct scatterlist *nsge, *sge = sk_msg_elem(msg, i); - int a = start; + int a = start - offset; int b = sge->length - pop - a; sk_msg_iter_var_next(i); - if (pop < sge->length - a) { + if (b > 0) { if (space) { sge->length = a; sk_msg_shift_right(msg, i); @@ -2993,7 +2998,6 @@ BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start, if (unlikely(!page)) return -ENOMEM; - sge->length = a; orig = sg_page(sge); from = sg_virt(sge); to = page_address(page); @@ -3003,7 +3007,7 @@ BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start, put_page(orig); } pop = 0; - } else if (pop >= sge->length - a) { + } else { pop -= (sge->length - a); sge->length = a; } @@ -3037,7 +3041,6 @@ BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start, pop -= sge->length; sk_msg_shift_left(msg, i); } - sk_msg_iter_var_next(i); } sk_mem_uncharge(msg->sk, len - pop); -- Gitee From 5eb7e0de37b724b23a4e21d9f938e9a433058c10 Mon Sep 17 00:00:00 2001 From: Yongliang Gao Date: Fri, 11 Oct 2024 12:31:53 +0800 Subject: [PATCH 4/9] rtc: check if __rtc_read_time was successful in rtc_timer_do_work() mainline inclusion from mainline-v6.13-rc1 commit e8ba8a2bc4f60a1065f23d6a0e7cbea945a0f40d category: bugfix issue: NA CVE: CVE-2024-56739 Signed-off-by: wukuan --------------------------------------- If the __rtc_read_time call fails,, the struct rtc_time tm; may contain uninitialized data, or an illegal date/time read from the RTC hardware. When calling rtc_tm_to_ktime later, the result may be a very large value (possibly KTIME_MAX). If there are periodic timers in rtc->timerqueue, they will continually expire, may causing kernel softlockup. Fixes: 6610e0893b8b ("RTC: Rework RTC code to use timerqueue for events") Signed-off-by: Yongliang Gao Acked-by: Jingqun Li Link: https://lore.kernel.org/r/20241011043153.3788112-1-leonylgao@gmail.com Signed-off-by: Alexandre Belloni Signed-off-by: wukuan --- drivers/rtc/interface.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c index 146056858135..930586b1cc57 100644 --- a/drivers/rtc/interface.c +++ b/drivers/rtc/interface.c @@ -906,13 +906,18 @@ void rtc_timer_do_work(struct work_struct *work) struct timerqueue_node *next; ktime_t now; struct rtc_time tm; + int err; struct rtc_device *rtc = container_of(work, struct rtc_device, irqwork); mutex_lock(&rtc->ops_lock); again: - __rtc_read_time(rtc, &tm); + err = __rtc_read_time(rtc, &tm); + if (err) { + mutex_unlock(&rtc->ops_lock); + return; + } now = rtc_tm_to_ktime(tm); while ((next = timerqueue_getnext(&rtc->timerqueue))) { if (next->expires > now) -- Gitee From 33367d14dc06d885271193dd20052a060d16f8a2 Mon Sep 17 00:00:00 2001 From: Ignat Korchagin Date: Mon, 14 Oct 2024 16:38:05 +0100 Subject: [PATCH 5/9] net: inet: do not leave a dangling sk pointer in inet_create() mainline inclusion from mainline-v6.13-rc1 commit 9365fa510c6f82e3aa550a09d0c5c6b44dbc78ff category: bugfix issue: NA CVE: CVE-2024-56601 Signed-off-by: wukuan --------------------------------------- sock_init_data() attaches the allocated sk object to the provided sock object. If inet_create() fails later, the sk object is freed, but the sock object retains the dangling pointer, which may create use-after-free later. Clear the sk pointer in the sock object on error. Signed-off-by: Ignat Korchagin Reviewed-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20241014153808.51894-7-ignat@cloudflare.com Signed-off-by: Jakub Kicinski Signed-off-by: wukuan --- net/ipv4/af_inet.c | 22 ++++++++++------------ 1 file changed, 10 insertions(+), 12 deletions(-) diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index fe8ff31545a5..39683614fb0f 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -376,32 +376,30 @@ static int inet_create(struct net *net, struct socket *sock, int protocol, inet->inet_sport = htons(inet->inet_num); /* Add to protocol hash chains. */ err = sk->sk_prot->hash(sk); - if (err) { - sk_common_release(sk); - goto out; - } + if (err) + goto out_sk_release; } if (sk->sk_prot->init) { err = sk->sk_prot->init(sk); - if (err) { - sk_common_release(sk); - goto out; - } + if (err) + goto out_sk_release; } if (!kern) { err = BPF_CGROUP_RUN_PROG_INET_SOCK(sk); - if (err) { - sk_common_release(sk); - goto out; - } + if (err) + goto out_sk_release; } out: return err; out_rcu_unlock: rcu_read_unlock(); goto out; +out_sk_release: + sk_common_release(sk); + sock->sk = NULL; + goto out; } -- Gitee From 37fb3cfea7e7799aba63ca3f3f74060ccb2ebe0c Mon Sep 17 00:00:00 2001 From: Ignat Korchagin Date: Mon, 14 Oct 2024 16:38:06 +0100 Subject: [PATCH 6/9] net: inet6: do not leave a dangling sk pointer in inet6_create() mainline inclusion from mainline-v6.13-rc1 commit 9df99c395d0f55fb444ef39f4d6f194ca437d884 category: bugfix issue: NA CVE: CVE-2024-56600 Signed-off-by: wukuan --------------------------------------- sock_init_data() attaches the allocated sk pointer to the provided sock object. If inet6_create() fails later, the sk object is released, but the sock object retains the dangling sk pointer, which may cause use-after-free later. Clear the sock sk pointer on error. Signed-off-by: Ignat Korchagin Reviewed-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20241014153808.51894-8-ignat@cloudflare.com Signed-off-by: Jakub Kicinski Signed-off-by: wukuan --- net/ipv6/af_inet6.c | 22 ++++++++++------------ 1 file changed, 10 insertions(+), 12 deletions(-) diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 0979a4b15f26..a97c2bbbcb83 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -254,31 +254,29 @@ static int inet6_create(struct net *net, struct socket *sock, int protocol, */ inet->inet_sport = htons(inet->inet_num); err = sk->sk_prot->hash(sk); - if (err) { - sk_common_release(sk); - goto out; - } + if (err) + goto out_sk_release; } if (sk->sk_prot->init) { err = sk->sk_prot->init(sk); - if (err) { - sk_common_release(sk); - goto out; - } + if (err) + goto out_sk_release; } if (!kern) { err = BPF_CGROUP_RUN_PROG_INET_SOCK(sk); - if (err) { - sk_common_release(sk); - goto out; - } + if (err) + goto out_sk_release; } out: return err; out_rcu_unlock: rcu_read_unlock(); goto out; +out_sk_release: + sk_common_release(sk); + sock->sk = NULL; + goto out; } static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, -- Gitee From f1f5b9fe66b811e810d0d043589a37136cd4279f Mon Sep 17 00:00:00 2001 From: Dmitry Antipov Date: Fri, 1 Nov 2024 14:44:10 +0300 Subject: [PATCH 7/9] Bluetooth: fix use-after-free in device_for_each_child() mainline inclusion from mainline-v6.13-rc1 commit 27aabf27fd014ae037cc179c61b0bee7cff55b3d category: bugfix issue: NA CVE: CVE-2024-53237 Signed-off-by: wukuan --------------------------------------- Syzbot has reported the following KASAN splat: BUG: KASAN: slab-use-after-free in device_for_each_child+0x18f/0x1a0 Read of size 8 at addr ffff88801f605308 by task kbnepd bnep0/4980 CPU: 0 UID: 0 PID: 4980 Comm: kbnepd bnep0 Not tainted 6.12.0-rc4-00161-gae90f6a6170d #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.3-2.fc40 04/01/2014 Call Trace: dump_stack_lvl+0x100/0x190 ? device_for_each_child+0x18f/0x1a0 print_report+0x13a/0x4cb ? __virt_addr_valid+0x5e/0x590 ? __phys_addr+0xc6/0x150 ? device_for_each_child+0x18f/0x1a0 kasan_report+0xda/0x110 ? device_for_each_child+0x18f/0x1a0 ? __pfx_dev_memalloc_noio+0x10/0x10 device_for_each_child+0x18f/0x1a0 ? __pfx_device_for_each_child+0x10/0x10 pm_runtime_set_memalloc_noio+0xf2/0x180 netdev_unregister_kobject+0x1ed/0x270 unregister_netdevice_many_notify+0x123c/0x1d80 ? __mutex_trylock_common+0xde/0x250 ? __pfx_unregister_netdevice_many_notify+0x10/0x10 ? trace_contention_end+0xe6/0x140 ? __mutex_lock+0x4e7/0x8f0 ? __pfx_lock_acquire.part.0+0x10/0x10 ? rcu_is_watching+0x12/0xc0 ? unregister_netdev+0x12/0x30 unregister_netdevice_queue+0x30d/0x3f0 ? __pfx_unregister_netdevice_queue+0x10/0x10 ? __pfx_down_write+0x10/0x10 unregister_netdev+0x1c/0x30 bnep_session+0x1fb3/0x2ab0 ? __pfx_bnep_session+0x10/0x10 ? __pfx_lock_release+0x10/0x10 ? __pfx_woken_wake_function+0x10/0x10 ? __kthread_parkme+0x132/0x200 ? __pfx_bnep_session+0x10/0x10 ? kthread+0x13a/0x370 ? __pfx_bnep_session+0x10/0x10 kthread+0x2b7/0x370 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x48/0x80 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1a/0x30 Allocated by task 4974: kasan_save_stack+0x30/0x50 kasan_save_track+0x14/0x30 __kasan_kmalloc+0xaa/0xb0 __kmalloc_noprof+0x1d1/0x440 hci_alloc_dev_priv+0x1d/0x2820 __vhci_create_device+0xef/0x7d0 vhci_write+0x2c7/0x480 vfs_write+0x6a0/0xfc0 ksys_write+0x12f/0x260 do_syscall_64+0xc7/0x250 entry_SYSCALL_64_after_hwframe+0x77/0x7f Freed by task 4979: kasan_save_stack+0x30/0x50 kasan_save_track+0x14/0x30 kasan_save_free_info+0x3b/0x60 __kasan_slab_free+0x4f/0x70 kfree+0x141/0x490 hci_release_dev+0x4d9/0x600 bt_host_release+0x6a/0xb0 device_release+0xa4/0x240 kobject_put+0x1ec/0x5a0 put_device+0x1f/0x30 vhci_release+0x81/0xf0 __fput+0x3f6/0xb30 task_work_run+0x151/0x250 do_exit+0xa79/0x2c30 do_group_exit+0xd5/0x2a0 get_signal+0x1fcd/0x2210 arch_do_signal_or_restart+0x93/0x780 syscall_exit_to_user_mode+0x140/0x290 do_syscall_64+0xd4/0x250 entry_SYSCALL_64_after_hwframe+0x77/0x7f In 'hci_conn_del_sysfs()', 'device_unregister()' may be called when an underlying (kobject) reference counter is greater than 1. This means that reparenting (happened when the device is actually freed) is delayed and, during that delay, parent controller device (hciX) may be deleted. Since the latter may create a dangling pointer to freed parent, avoid that scenario by reparenting to NULL explicitly. Reported-by: syzbot+6cf5652d3df49fae2e3f@syzkaller.appspotmail.com Tested-by: syzbot+6cf5652d3df49fae2e3f@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=6cf5652d3df49fae2e3f Fixes: a85fb91e3d72 ("Bluetooth: Fix double free in hci_conn_cleanup") Signed-off-by: Dmitry Antipov Signed-off-by: Luiz Augusto von Dentz Signed-off-by: wukuan --- net/bluetooth/hci_sysfs.c | 15 ++++----------- 1 file changed, 4 insertions(+), 11 deletions(-) diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c index 266112c960ee..1b4d81ffb4b5 100644 --- a/net/bluetooth/hci_sysfs.c +++ b/net/bluetooth/hci_sysfs.c @@ -19,16 +19,6 @@ static const struct device_type bt_link = { .release = bt_link_release, }; -/* - * The rfcomm tty device will possibly retain even when conn - * is down, and sysfs doesn't support move zombie device, - * so we should move the device before conn device is destroyed. - */ -static int __match_tty(struct device *dev, void *data) -{ - return !strncmp(dev_name(dev), "rfcomm", 6); -} - void hci_conn_init_sysfs(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; @@ -71,10 +61,13 @@ void hci_conn_del_sysfs(struct hci_conn *conn) return; } + /* If there are devices using the connection as parent reset it to NULL + * before unregistering the device. + */ while (1) { struct device *dev; - dev = device_find_child(&conn->dev, NULL, __match_tty); + dev = device_find_any_child(&conn->dev); if (!dev) break; device_move(dev, NULL, DPM_ORDER_DEV_LAST); -- Gitee From c90cc535636f8481848e6d5028619edaabf20e8e Mon Sep 17 00:00:00 2001 From: Jiri Wiesner Date: Thu, 28 Nov 2024 09:59:50 +0100 Subject: [PATCH 8/9] net/ipv6: release expired exception dst cached in socket mainline inclusion from mainline-v6.13-rc2 commit 3301ab7d5aeb0fe270f73a3d4810c9d1b6a9f045 category: bugfix issue: NA CVE: CVE-2024-56644 Signed-off-by: wukuan --------------------------------------- Dst objects get leaked in ip6_negative_advice() when this function is executed for an expired IPv6 route located in the exception table. There are several conditions that must be fulfilled for the leak to occur: * an ICMPv6 packet indicating a change of the MTU for the path is received, resulting in an exception dst being created * a TCP connection that uses the exception dst for routing packets must start timing out so that TCP begins retransmissions * after the exception dst expires, the FIB6 garbage collector must not run before TCP executes ip6_negative_advice() for the expired exception dst When TCP executes ip6_negative_advice() for an exception dst that has expired and if no other socket holds a reference to the exception dst, the refcount of the exception dst is 2, which corresponds to the increment made by dst_init() and the increment made by the TCP socket for which the connection is timing out. The refcount made by the socket is never released. The refcount of the dst is decremented in sk_dst_reset() but that decrement is counteracted by a dst_hold() intentionally placed just before the sk_dst_reset() in ip6_negative_advice(). After ip6_negative_advice() has finished, there is no other object tied to the dst. The socket lost its reference stored in sk_dst_cache and the dst is no longer in the exception table. The exception dst becomes a leaked object. As a result of this dst leak, an unbalanced refcount is reported for the loopback device of a net namespace being destroyed under kernels that do not contain e5f80fcf869a ("ipv6: give an IPv6 dev to blackhole_netdev"): unregister_netdevice: waiting for lo to become free. Usage count = 2 Fix the dst leak by removing the dst_hold() in ip6_negative_advice(). The patch that introduced the dst_hold() in ip6_negative_advice() was 92f1655aa2b22 ("net: fix __dst_negative_advice() race"). But 92f1655aa2b22 merely refactored the code with regards to the dst refcount so the issue was present even before 92f1655aa2b22. The bug was introduced in 54c1a859efd9f ("ipv6: Don't drop cache route entry unless timer actually expired.") where the expired cached route is deleted and the sk_dst_cache member of the socket is set to NULL by calling dst_negative_advice() but the refcount belonging to the socket is left unbalanced. The IPv4 version - ipv4_negative_advice() - is not affected by this bug. When the TCP connection times out ipv4_negative_advice() merely resets the sk_dst_cache of the socket while decrementing the refcount of the exception dst. Fixes: 92f1655aa2b22 ("net: fix __dst_negative_advice() race") Fixes: 54c1a859efd9f ("ipv6: Don't drop cache route entry unless timer actually expired.") Link: https://lore.kernel.org/netdev/20241113105611.GA6723@incl/T/#u Signed-off-by: Jiri Wiesner Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20241128085950.GA4505@incl Signed-off-by: Jakub Kicinski Signed-off-by: wukuan --- net/ipv6/route.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index f41f9232857c..3a0f4e5040e1 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2644,10 +2644,10 @@ static void ip6_negative_advice(struct sock *sk, if (rt->rt6i_flags & RTF_CACHE) { rcu_read_lock(); if (rt6_check_expired(rt)) { - /* counteract the dst_release() in sk_dst_reset() */ - dst_hold(dst); + /* rt/dst can not be destroyed yet, + * because of rcu_read_lock() + */ sk_dst_reset(sk); - rt6_remove_exception_rt(rt); } rcu_read_unlock(); -- Gitee From cfca1215aeb5f61c30aaa290d1031f7069fecf0c Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Thu, 10 Oct 2024 19:10:34 +0200 Subject: [PATCH 9/9] PCI: Fix use-after-free of slot->bus on hot remove mainline inclusion from mainline-v6.13-rc1 commit c7acef99642b763ba585f4a43af999fcdbcc3dc4 category: bugfix issue: NA CVE: CVE-2024-53194 Signed-off-by: wukuan --------------------------------------- Dennis reports a boot crash on recent Lenovo laptops with a USB4 dock. Since commit 0fc70886569c ("thunderbolt: Reset USB4 v2 host router") and commit 59a54c5f3dbd ("thunderbolt: Reset topology created by the boot firmware"), USB4 v2 and v1 Host Routers are reset on probe of the thunderbolt driver. The reset clears the Presence Detect State and Data Link Layer Link Active bits at the USB4 Host Router's Root Port and thus causes hot removal of the dock. The crash occurs when pciehp is unbound from one of the dock's Downstream Ports: pciehp creates a pci_slot on bind and destroys it on unbind. The pci_slot contains a pointer to the pci_bus below the Downstream Port, but a reference on that pci_bus is never acquired. The pci_bus is destroyed before the pci_slot, so a use-after-free ensues when pci_slot_release() accesses slot->bus. In principle this should not happen because pci_stop_bus_device() unbinds pciehp (and therefore destroys the pci_slot) before the pci_bus is destroyed by pci_remove_bus_device(). However the stacktrace provided by Dennis shows that pciehp is unbound from pci_remove_bus_device() instead of pci_stop_bus_device(). To understand the significance of this, one needs to know that the PCI core uses a two step process to remove a portion of the hierarchy: It first unbinds all drivers in the sub-hierarchy in pci_stop_bus_device() and then actually removes the devices in pci_remove_bus_device(). There is no precaution to prevent driver binding in-between pci_stop_bus_device() and pci_remove_bus_device(). In Dennis' case, it seems removal of the hierarchy by pciehp races with driver binding by pci_bus_add_devices(). pciehp is bound to the Downstream Port after pci_stop_bus_device() has run, so it is unbound by pci_remove_bus_device() instead of pci_stop_bus_device(). Because the pci_bus has already been destroyed at that point, accesses to it result in a use-after-free. One might conclude that driver binding needs to be prevented after pci_stop_bus_device() has run. However it seems risky that pci_slot points to pci_bus without holding a reference. Solely relying on correct ordering of driver unbind versus pci_bus destruction is certainly not defensive programming. If pci_slot has a need to access data in pci_bus, it ought to acquire a reference. Amend pci_create_slot() accordingly. Dennis reports that the crash is not reproducible with this change. Abridged stacktrace: pcieport 0000:00:07.0: PME: Signaling with IRQ 156 pcieport 0000:00:07.0: pciehp: Slot #12 AttnBtn- PwrCtrl- MRL- AttnInd- PwrInd- HotPlug+ Surprise+ Interlock- NoCompl+ IbPresDis- LLActRep+ pci_bus 0000:20: dev 00, created physical slot 12 pcieport 0000:00:07.0: pciehp: Slot(12): Card not present ... pcieport 0000:21:02.0: pciehp: pcie_disable_notification: SLOTCTRL d8 write cmd 0 Oops: general protection fault, probably for non-canonical address 0x6b6b6b6b6b6b6b6b: 0000 [#1] PREEMPT SMP NOPTI CPU: 13 UID: 0 PID: 134 Comm: irq/156-pciehp Not tainted 6.11.0-devel+ #1 RIP: 0010:dev_driver_string+0x12/0x40 pci_destroy_slot pciehp_remove pcie_port_remove_service device_release_driver_internal bus_remove_device device_del device_unregister remove_iter device_for_each_child pcie_portdrv_remove pci_device_remove device_release_driver_internal bus_remove_device device_del pci_remove_bus_device (recursive invocation) pci_remove_bus_device pciehp_unconfigure_device pciehp_disable_slot pciehp_handle_presence_or_link_change pciehp_ist Link: https://lore.kernel.org/r/4bfd4c0e976c1776cd08e76603903b338cf25729.1728579288.git.lukas@wunner.de Reported-by: Dennis Wassenberg Closes: https://lore.kernel.org/r/6de4b45ff2b32dd91a805ec02ec8ec73ef411bf6.camel@secunet.com/ Tested-by: Dennis Wassenberg Signed-off-by: Lukas Wunner Signed-off-by: Bjorn Helgaas Reviewed-by: Mika Westerberg Cc: stable@vger.kernel.org Signed-off-by: wukuan --- drivers/pci/slot.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/pci/slot.c b/drivers/pci/slot.c index ed2077e7470a..a42e2cf774fd 100644 --- a/drivers/pci/slot.c +++ b/drivers/pci/slot.c @@ -79,6 +79,7 @@ static void pci_slot_release(struct kobject *kobj) up_read(&pci_bus_sem); list_del(&slot->list); + pci_bus_put(slot->bus); kfree(slot); } @@ -260,7 +261,7 @@ struct pci_slot *pci_create_slot(struct pci_bus *parent, int slot_nr, goto err; } - slot->bus = parent; + slot->bus = pci_bus_get(parent); slot->number = slot_nr; slot->kobj.kset = pci_slots_kset; @@ -268,6 +269,7 @@ struct pci_slot *pci_create_slot(struct pci_bus *parent, int slot_nr, slot_name = make_slot_name(name); if (!slot_name) { err = -ENOMEM; + pci_bus_put(slot->bus); kfree(slot); goto err; } -- Gitee