From 9e115bb1d560270367c49758389076272c771ff1 Mon Sep 17 00:00:00 2001 From: Ignat Korchagin Date: Mon, 14 Oct 2024 16:38:01 +0100 Subject: [PATCH 1/7] 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: #IBG6Z0 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 864d1fbc829e95efe16aebff3a546489bdb1d592 Mon Sep 17 00:00:00 2001 From: Zijian Zhang Date: Wed, 6 Nov 2024 22:25:19 +0000 Subject: [PATCH 2/7] 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 f7ac0fe7e5d3..97abd0c98d79 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 c9a0bf1e10aa758123aaddd8a0dced0624091317 Mon Sep 17 00:00:00 2001 From: Yongliang Gao Date: Fri, 11 Oct 2024 12:31:53 +0800 Subject: [PATCH 3/7] 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 32d75a0a88994ff3016af133bf2027cc32dff3df Mon Sep 17 00:00:00 2001 From: Ignat Korchagin Date: Mon, 14 Oct 2024 16:38:05 +0100 Subject: [PATCH 4/7] 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 49f94700e2ab..17cc21b28755 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 39d05f4d78ac8e3d682eaa628e8584c4dc1f26f7 Mon Sep 17 00:00:00 2001 From: Ignat Korchagin Date: Mon, 14 Oct 2024 16:38:06 +0100 Subject: [PATCH 5/7] 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 1a294c45dc1f..a5578ba2f342 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -257,31 +257,29 @@ 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 3e3af6b21879e258839a834408e915c93f76d897 Mon Sep 17 00:00:00 2001 From: Jiri Wiesner Date: Thu, 28 Nov 2024 09:59:50 +0100 Subject: [PATCH 6/7] 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 ac746c1a26e1..0d0602ef584a 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2647,10 +2647,10 @@ 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 7277beade27a26b4b7f783e6d4acc71a8e73a217 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Thu, 10 Oct 2024 19:10:34 +0200 Subject: [PATCH 7/7] 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