In the Linux kernel, the following vulnerability has been resolved: media: mc, v4l2: serialize REINIT and REQBUFS with req_queue_mutex MEDIA_REQUEST_IOC_REINIT can run concurrently with VIDIOC_REQBUFS(0) queue teardown paths. This can race request object cleanup against vb2 queue cancellation and lead to use-after-free reports. We already serialize request queueing against STREAMON/OFF with req_queue_mutex. Extend that serialization to REQBUFS, and also take the same mutex in media_request_ioctl_reinit() so REINIT is in the same exclusion domain. This keeps request cleanup and queue cancellation from running in parallel for request-capable devices.

In the Linux kernel, the following vulnerability has been resolved: ASoC: sma1307: fix double free of devm_kzalloc() memory A previous change added NULL checks and cleanup for allocation failures in sma1307_setting_loaded(). However, the cleanup for mode_set entries is wrong. Those entries are allocated with devm_kzalloc(), so they are device-managed resources and must not be freed with kfree(). Manually freeing them in the error path can lead to a double free when devres later releases the same memory. Drop the manual kfree() loop and let devres handle the cleanup.

In the Linux kernel, the following vulnerability has been resolved: NFSD: Defer sub-object cleanup in export put callbacks svc_export_put() calls path_put() and auth_domain_put() immediately when the last reference drops, before the RCU grace period. RCU readers in e_show() and c_show() access both ex_path (via seq_path/d_path) and ex_client->name (via seq_escape) without holding a reference. If cache_clean removes the entry and drops the last reference concurrently, the sub-objects are freed while still in use, producing a NULL pointer dereference in d_path. Commit 2530766492ec ("nfsd: fix UAF when access ex_uuid or ex_stats") moved kfree of ex_uuid and ex_stats into the call_rcu callback, but left path_put() and auth_domain_put() running before the grace period because both may sleep and call_rcu callbacks execute in softirq context. Replace call_rcu/kfree_rcu with queue_rcu_work(), which defers the callback until after the RCU grace period and executes it in process context where sleeping is permitted. This allows path_put() and auth_domain_put() to be moved into the deferred callback alongside the other resource releases. Apply the same fix to expkey_put(), which has the identical pattern with ek_path and ek_client. A dedicated workqueue scopes the shutdown drain to only NFSD export release work items; flushing the shared system_unbound_wq would stall on unrelated work from other subsystems. nfsd_export_shutdown() uses rcu_barrier() followed by flush_workqueue() to ensure all deferred release callbacks complete before the export caches are destroyed. Reviwed-by: Jeff Layton <jlayton@kernel.org>

In the Linux kernel, the following vulnerability has been resolved: vfio/pci: Fix double free in dma-buf feature The error path through vfio_pci_core_feature_dma_buf() ignores its own advice to only use dma_buf_put() after dma_buf_export(), instead falling through the entire unwind chain. In the unlikely event that we encounter file descriptor exhaustion, this can result in an unbalanced refcount on the vfio device and double free of allocated objects. Avoid this by moving the "put" directly into the error path and return the errno rather than entering the unwind chain.

In the Linux kernel, the following vulnerability has been resolved: crypto: algif_aead - Revert to operating out-of-place This mostly reverts commit 72548b093ee3 except for the copying of the associated data. There is no benefit in operating in-place in algif_aead since the source and destination come from different mappings. Get rid of all the complexity added for in-place operation and just copy the AD directly.

In the Linux kernel, the following vulnerability has been resolved: team: fix header_ops type confusion with non-Ethernet ports Similar to commit 950803f72547 ("bonding: fix type confusion in bond_setup_by_slave()") team has the same class of header_ops type confusion. For non-Ethernet ports, team_setup_by_port() copies port_dev->header_ops directly. When the team device later calls dev_hard_header() or dev_parse_header(), these callbacks can run with the team net_device instead of the real lower device, so netdev_priv(dev) is interpreted as the wrong private type and can crash. The syzbot report shows a crash in bond_header_create(), but the root cause is in team: the topology is gre -> bond -> team, and team calls the inherited header_ops with its own net_device instead of the lower device, so bond_header_create() receives a team device and interprets netdev_priv() as bonding private data, causing a type confusion crash. Fix this by introducing team header_ops wrappers for create/parse, selecting a team port under RCU, and calling the lower device callbacks with port->dev, so each callback always sees the correct net_device context. Also pass the selected lower device to the lower parse callback, so recursion is bounded in stacked non-Ethernet topologies and parse callbacks always run with the correct device context.

In the Linux kernel, the following vulnerability has been resolved: tracing: Fix use-after-free in print_graph_function_flags during tracer switching Kairui reported a UAF issue in print_graph_function_flags() during ftrace stress testing [1]. This issue can be reproduced if puting a 'mdelay(10)' after 'mutex_unlock(&trace_types_lock)' in s_start(), and executing the following script: $ echo function_graph > current_tracer $ cat trace > /dev/null & $ sleep 5 # Ensure the 'cat' reaches the 'mdelay(10)' point $ echo timerlat > current_tracer The root cause lies in the two calls to print_graph_function_flags within print_trace_line during each s_show(): * One through 'iter->trace->print_line()'; * Another through 'event->funcs->trace()', which is hidden in print_trace_fmt() before print_trace_line returns. Tracer switching only updates the former, while the latter continues to use the print_line function of the old tracer, which in the script above is print_graph_function_flags. Moreover, when switching from the 'function_graph' tracer to the 'timerlat' tracer, s_start only calls graph_trace_close of the 'function_graph' tracer to free 'iter->private', but does not set it to NULL. This provides an opportunity for 'event->funcs->trace()' to use an invalid 'iter->private'. To fix this issue, set 'iter->private' to NULL immediately after freeing it in graph_trace_close(), ensuring that an invalid pointer is not passed to other tracers. Additionally, clean up the unnecessary 'iter->private = NULL' during each 'cat trace' when using wakeup and irqsoff tracers. [1] https://lore.kernel.org/all/20231112150030.84609-1-ryncsn@gmail.com/

In the Linux kernel, the following vulnerability has been resolved: spi: fix use-after-free on controller registration failure Make sure to deregister from driver core also in the unlikely event that per-cpu statistics allocation fails during controller registration to avoid use-after-free (of driver resources) and unclocked register accesses.

In the Linux kernel, the following vulnerability has been resolved: xfrm: Fix work re-schedule after cancel in xfrm_nat_keepalive_net_fini() After cancel_delayed_work_sync() is called from xfrm_nat_keepalive_net_fini(), xfrm_state_fini() flushes remaining states via __xfrm_state_delete(), which calls xfrm_nat_keepalive_state_updated() to re-schedule nat_keepalive_work. The following is a simple race scenario: cpu0 cpu1 cleanup_net() [Round 1] ops_undo_list() xfrm_net_exit() xfrm_nat_keepalive_net_fini() cancel_delayed_work_sync(nat_keepalive_work); xfrm_state_fini() xfrm_state_flush() xfrm_state_delete(x) __xfrm_state_delete(x) xfrm_nat_keepalive_state_updated(x) schedule_delayed_work(nat_keepalive_work); rcu_barrier(); net_complete_free(); net_passive_dec(net); llist_add(&net->defer_free_list, &defer_free_list); cleanup_net() [Round 2] rcu_barrier(); net_complete_free() kmem_cache_free(net_cachep, net); nat_keepalive_work() // on freed net To prevent this, cancel_delayed_work_sync() is replaced with disable_delayed_work_sync().

In the Linux kernel, the following vulnerability has been resolved: drm/xe: always keep track of remap prev/next During 3D workload, user is reporting hitting: [ 413.361679] WARNING: drivers/gpu/drm/xe/xe_vm.c:1217 at vm_bind_ioctl_ops_unwind+0x1e2/0x2e0 [xe], CPU#7: vkd3d_queue/9925 [ 413.361944] CPU: 7 UID: 1000 PID: 9925 Comm: vkd3d_queue Kdump: loaded Not tainted 7.0.0-070000rc3-generic #202603090038 PREEMPT(lazy) [ 413.361949] RIP: 0010:vm_bind_ioctl_ops_unwind+0x1e2/0x2e0 [xe] [ 413.362074] RSP: 0018:ffffd4c25c3df930 EFLAGS: 00010282 [ 413.362077] RAX: 0000000000000000 RBX: ffff8f3ee817ed10 RCX: 0000000000000000 [ 413.362078] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 [ 413.362079] RBP: ffffd4c25c3df980 R08: 0000000000000000 R09: 0000000000000000 [ 413.362081] R10: 0000000000000000 R11: 0000000000000000 R12: ffff8f41fbf99380 [ 413.362082] R13: ffff8f3ee817e968 R14: 00000000ffffffef R15: ffff8f43d00bd380 [ 413.362083] FS: 00000001040ff6c0(0000) GS:ffff8f4696d89000(0000) knlGS:00000000330b0000 [ 413.362085] CS: 0010 DS: 002b ES: 002b CR0: 0000000080050033 [ 413.362086] CR2: 00007ddfc4747000 CR3: 00000002e6262005 CR4: 0000000000f72ef0 [ 413.362088] PKRU: 55555554 [ 413.362089] Call Trace: [ 413.362092] <TASK> [ 413.362096] xe_vm_bind_ioctl+0xa9a/0xc60 [xe] Which seems to hint that the vma we are re-inserting for the ops unwind is either invalid or overlapping with something already inserted in the vm. It shouldn't be invalid since this is a re-insertion, so must have worked before. Leaving the likely culprit as something already placed where we want to insert the vma. Following from that, for the case where we do something like a rebind in the middle of a vma, and one or both mapped ends are already compatible, we skip doing the rebind of those vma and set next/prev to NULL. As well as then adjust the original unmap va range, to avoid unmapping the ends. However, if we trigger the unwind path, we end up with three va, with the two ends never being removed and the original va range in the middle still being the shrunken size. If this occurs, one failure mode is when another unwind op needs to interact with that range, which can happen with a vector of binds. For example, if we need to re-insert something in place of the original va. In this case the va is still the shrunken version, so when removing it and then doing a re-insert it can overlap with the ends, which were never removed, triggering a warning like above, plus leaving the vm in a bad state. With that, we need two things here: 1) Stop nuking the prev/next tracking for the skip cases. Instead relying on checking for skip prev/next, where needed. That way on the unwind path, we now correctly remove both ends. 2) Undo the unmap va shrinkage, on the unwind path. With the two ends now removed the unmap va should expand back to the original size again, before re-insertion. v2: - Update the explanation in the commit message, based on an actual IGT of triggering this issue, rather than conjecture. - Also undo the unmap shrinkage, for the skip case. With the two ends now removed, the original unmap va range should expand back to the original range. v3: - Track the old start/range separately. vma_size/start() uses the va info directly. (cherry picked from commit aec6969f75afbf4e01fd5fb5850ed3e9c27043ac)

A heap out-of-bounds write vulnerability in the Linux kernel's Linux Kernel Performance Events (perf) component can be exploited to achieve local privilege escalation. If perf_read_group() is called while an event's sibling_list is smaller than its child's sibling_list, it can increment or write to memory locations outside of the allocated buffer. We recommend upgrading past commit 32671e3799ca2e4590773fd0e63aaa4229e50c06.

In the Linux kernel, the following vulnerability has been resolved: RDMA/efa: Fix use of completion ctx after free On admin queue completion handling, if the admin command completed with error we print data from the completion context. The issue is that we already freed the completion context in polling/interrupts handler which means we print data from context in an unknown state (it might be already used again). Change the admin submission flow so alloc/dealloc of the context will be symmetric and dealloc will be called after any potential use of the context.

In the Linux kernel, the following vulnerability has been resolved: spi: spi-fsl-lpspi: fix teardown order issue (UAF) There is a teardown order issue in the driver. The SPI controller is registered using devm_spi_register_controller(), which delays unregistration of the SPI controller until after the fsl_lpspi_remove() function returns. As the fsl_lpspi_remove() function synchronously tears down the DMA channels, a running SPI transfer triggers the following NULL pointer dereference due to use after free: | fsl_lpspi 42550000.spi: I/O Error in DMA RX | Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 [...] | Call trace: | fsl_lpspi_dma_transfer+0x260/0x340 [spi_fsl_lpspi] | fsl_lpspi_transfer_one+0x198/0x448 [spi_fsl_lpspi] | spi_transfer_one_message+0x49c/0x7c8 | __spi_pump_transfer_message+0x120/0x420 | __spi_sync+0x2c4/0x520 | spi_sync+0x34/0x60 | spidev_message+0x20c/0x378 [spidev] | spidev_ioctl+0x398/0x750 [spidev] [...] Switch from devm_spi_register_controller() to spi_register_controller() in fsl_lpspi_probe() and add the corresponding spi_unregister_controller() in fsl_lpspi_remove().

In the Linux kernel, the following vulnerability has been resolved: HID: bpf: prevent buffer overflow in hid_hw_request right now the returned value is considered to be always valid. However, when playing with HID-BPF, the return value can be arbitrary big, because it's the return value of dispatch_hid_bpf_raw_requests(), which calls the struct_ops and we have no guarantees that the value makes sense.

In the Linux kernel, the following vulnerability has been resolved: dmaengine: idxd: Fix possible invalid memory access after FLR In the case that the first Function Level Reset (FLR) concludes correctly, but in the second FLR the scratch area for the saved configuration cannot be allocated, it's possible for a invalid memory access to happen. Always set the deallocated scratch area to NULL after FLR completes.

In the Linux kernel, the following vulnerability has been resolved: can: isotp: fix tx.buf use-after-free in isotp_sendmsg() isotp_sendmsg() uses only cmpxchg() on so->tx.state to serialize access to so->tx.buf. isotp_release() waits for ISOTP_IDLE via wait_event_interruptible() and then calls kfree(so->tx.buf). If a signal interrupts the wait_event_interruptible() inside close() while tx.state is ISOTP_SENDING, the loop exits early and release proceeds to force ISOTP_SHUTDOWN and continues to kfree(so->tx.buf) while sendmsg may still be reading so->tx.buf for the final CAN frame in isotp_fill_dataframe(). The so->tx.buf can be allocated once when the standard tx.buf length needs to be extended. Move the kfree() of this potentially extended tx.buf to sk_destruct time when either isotp_sendmsg() and isotp_release() are done.

In the Linux kernel, the following vulnerability has been resolved: net: fix fanout UAF in packet_release() via NETDEV_UP race `packet_release()` has a race window where `NETDEV_UP` can re-register a socket into a fanout group's `arr[]` array. The re-registration is not cleaned up by `fanout_release()`, leaving a dangling pointer in the fanout array. `packet_release()` does NOT zero `po->num` in its `bind_lock` section. After releasing `bind_lock`, `po->num` is still non-zero and `po->ifindex` still matches the bound device. A concurrent `packet_notifier(NETDEV_UP)` that already found the socket in `sklist` can re-register the hook. For fanout sockets, this re-registration calls `__fanout_link(sk, po)` which adds the socket back into `f->arr[]` and increments `f->num_members`, but does NOT increment `f->sk_ref`. The fix sets `po->num` to zero in `packet_release` while `bind_lock` is held to prevent NETDEV_UP from linking, preventing the race window. This bug was found following an additional audit with Claude Code based on CVE-2025-38617.

In the Linux kernel, the following vulnerability has been resolved: net: macb: use the current queue number for stats There's a potential mismatch between the memory reserved for statistics and the amount of memory written. gem_get_sset_count() correctly computes the number of stats based on the active queues, whereas gem_get_ethtool_stats() indiscriminately copies data using the maximum number of queues, and in the case the number of active queues is less than MACB_MAX_QUEUES, this results in a OOB write as observed in the KASAN splat. ================================================================== BUG: KASAN: vmalloc-out-of-bounds in gem_get_ethtool_stats+0x54/0x78 [macb] Write of size 760 at addr ffff80008080b000 by task ethtool/1027 CPU: [...] Tainted: [E]=UNSIGNED_MODULE Hardware name: raspberrypi rpi/rpi, BIOS 2025.10 10/01/2025 Call trace: show_stack+0x20/0x38 (C) dump_stack_lvl+0x80/0xf8 print_report+0x384/0x5e0 kasan_report+0xa0/0xf0 kasan_check_range+0xe8/0x190 __asan_memcpy+0x54/0x98 gem_get_ethtool_stats+0x54/0x78 [macb 926c13f3af83b0c6fe64badb21ec87d5e93fcf65] dev_ethtool+0x1220/0x38c0 dev_ioctl+0x4ac/0xca8 sock_do_ioctl+0x170/0x1d8 sock_ioctl+0x484/0x5d8 __arm64_sys_ioctl+0x12c/0x1b8 invoke_syscall+0xd4/0x258 el0_svc_common.constprop.0+0xb4/0x240 do_el0_svc+0x48/0x68 el0_svc+0x40/0xf8 el0t_64_sync_handler+0xa0/0xe8 el0t_64_sync+0x1b0/0x1b8 The buggy address belongs to a 1-page vmalloc region starting at 0xffff80008080b000 allocated at dev_ethtool+0x11f0/0x38c0 The buggy address belongs to the physical page: page: refcount:1 mapcount:0 mapping:0000000000000000 index:0xffff00000a333000 pfn:0xa333 flags: 0x7fffc000000000(node=0|zone=0|lastcpupid=0x1ffff) raw: 007fffc000000000 0000000000000000 dead000000000122 0000000000000000 raw: ffff00000a333000 0000000000000000 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff80008080b080: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffff80008080b100: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 >ffff80008080b180: 00 00 00 00 00 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 ^ ffff80008080b200: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 ffff80008080b280: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 ================================================================== Fix it by making sure the copied size only considers the active number of queues.

In the Linux kernel, the following vulnerability has been resolved: net: bonding: fix use-after-free in bond_xmit_broadcast() bond_xmit_broadcast() reuses the original skb for the last slave (determined by bond_is_last_slave()) and clones it for others. Concurrent slave enslave/release can mutate the slave list during RCU-protected iteration, changing which slave is "last" mid-loop. This causes the original skb to be double-consumed (double-freed). Replace the racy bond_is_last_slave() check with a simple index comparison (i + 1 == slaves_count) against the pre-snapshot slave count taken via READ_ONCE() before the loop. This preserves the zero-copy optimization for the last slave while making the "last" determination stable against concurrent list mutations. The UAF can trigger the following crash: ================================================================== BUG: KASAN: slab-use-after-free in skb_clone Read of size 8 at addr ffff888100ef8d40 by task exploit/147 CPU: 1 UID: 0 PID: 147 Comm: exploit Not tainted 7.0.0-rc3+ #4 PREEMPTLAZY Call Trace: <TASK> dump_stack_lvl (lib/dump_stack.c:123) print_report (mm/kasan/report.c:379 mm/kasan/report.c:482) kasan_report (mm/kasan/report.c:597) skb_clone (include/linux/skbuff.h:1724 include/linux/skbuff.h:1792 include/linux/skbuff.h:3396 net/core/skbuff.c:2108) bond_xmit_broadcast (drivers/net/bonding/bond_main.c:5334) bond_start_xmit (drivers/net/bonding/bond_main.c:5567 drivers/net/bonding/bond_main.c:5593) dev_hard_start_xmit (include/linux/netdevice.h:5325 include/linux/netdevice.h:5334 net/core/dev.c:3871 net/core/dev.c:3887) __dev_queue_xmit (include/linux/netdevice.h:3601 net/core/dev.c:4838) ip6_finish_output2 (include/net/neighbour.h:540 include/net/neighbour.h:554 net/ipv6/ip6_output.c:136) ip6_finish_output (net/ipv6/ip6_output.c:208 net/ipv6/ip6_output.c:219) ip6_output (net/ipv6/ip6_output.c:250) ip6_send_skb (net/ipv6/ip6_output.c:1985) udp_v6_send_skb (net/ipv6/udp.c:1442) udpv6_sendmsg (net/ipv6/udp.c:1733) __sys_sendto (net/socket.c:730 net/socket.c:742 net/socket.c:2206) __x64_sys_sendto (net/socket.c:2209) do_syscall_64 (arch/x86/entry/syscall_64.c:63 arch/x86/entry/syscall_64.c:94) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) </TASK> Allocated by task 147: Freed by task 147: The buggy address belongs to the object at ffff888100ef8c80 which belongs to the cache skbuff_head_cache of size 224 The buggy address is located 192 bytes inside of freed 224-byte region [ffff888100ef8c80, ffff888100ef8d60) Memory state around the buggy address: ffff888100ef8c00: fb fb fb fb fc fc fc fc fc fc fc fc fc fc fc fc ffff888100ef8c80: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff888100ef8d00: fb fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc ^ ffff888100ef8d80: fc fc fc fc fc fc fc fc fa fb fb fb fb fb fb fb ffff888100ef8e00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ==================================================================

A use-after-free exists in the Linux Kernel in tc_new_tfilter that could allow a local attacker to gain privilege escalation. The exploit requires unprivileged user namespaces. We recommend upgrading past commit 04c2a47ffb13c29778e2a14e414ad4cb5a5db4b5

In the Linux kernel, the following vulnerability has been resolved: iomap: Fix possible overflow condition in iomap_write_delalloc_scan folio_next_index() returns an unsigned long value which left shifted by PAGE_SHIFT could possibly cause an overflow on 32-bit system. Instead use folio_pos(folio) + folio_size(folio), which does this correctly.

In the Linux kernel, the following vulnerability has been resolved: net/sched: act_ct: fix wild memory access when clearing fragments while testing re-assembly/re-fragmentation using act_ct, it's possible to observe a crash like the following one: KASAN: maybe wild-memory-access in range [0x0001000000000448-0x000100000000044f] CPU: 50 PID: 0 Comm: swapper/50 Tainted: G S 5.12.0-rc7+ #424 Hardware name: Dell Inc. PowerEdge R730/072T6D, BIOS 2.4.3 01/17/2017 RIP: 0010:inet_frag_rbtree_purge+0x50/0xc0 Code: 00 fc ff df 48 89 c3 31 ed 48 89 df e8 a9 7a 38 ff 4c 89 fe 48 89 df 49 89 c6 e8 5b 3a 38 ff 48 8d 7b 40 48 89 f8 48 c1 e8 03 <42> 80 3c 20 00 75 59 48 8d bb d0 00 00 00 4c 8b 6b 40 48 89 f8 48 RSP: 0018:ffff888c31449db8 EFLAGS: 00010203 RAX: 0000200000000089 RBX: 000100000000040e RCX: ffffffff989eb960 RDX: 0000000000000140 RSI: ffffffff97cfb977 RDI: 000100000000044e RBP: 0000000000000900 R08: 0000000000000000 R09: ffffed1186289350 R10: 0000000000000003 R11: ffffed1186289350 R12: dffffc0000000000 R13: 000100000000040e R14: 0000000000000000 R15: ffff888155e02160 FS: 0000000000000000(0000) GS:ffff888c31440000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00005600cb70a5b8 CR3: 0000000a2c014005 CR4: 00000000003706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <IRQ> inet_frag_destroy+0xa9/0x150 call_timer_fn+0x2d/0x180 run_timer_softirq+0x4fe/0xe70 __do_softirq+0x197/0x5a0 irq_exit_rcu+0x1de/0x200 sysvec_apic_timer_interrupt+0x6b/0x80 </IRQ> when act_ct temporarily stores an IP fragment, restoring the skb qdisc cb results in putting random data in FRAG_CB(), and this causes those "wild" memory accesses later, when the rbtree is purged. Never overwrite the skb cb in case tcf_ct_handle_fragments() returns -EINPROGRESS.

In the Linux kernel, the following vulnerability has been resolved: net/sched: act_skbmod: Skip non-Ethernet packets Currently tcf_skbmod_act() assumes that packets use Ethernet as their L2 protocol, which is not always the case. As an example, for CAN devices: $ ip link add dev vcan0 type vcan $ ip link set up vcan0 $ tc qdisc add dev vcan0 root handle 1: htb $ tc filter add dev vcan0 parent 1: protocol ip prio 10 \ matchall action skbmod swap mac Doing the above silently corrupts all the packets. Do not perform skbmod actions for non-Ethernet packets.

In the Linux kernel, the following vulnerability has been resolved: KVM: mmio: Fix use-after-free Read in kvm_vm_ioctl_unregister_coalesced_mmio BUG: KASAN: use-after-free in kvm_vm_ioctl_unregister_coalesced_mmio+0x7c/0x1ec arch/arm64/kvm/../../../virt/kvm/coalesced_mmio.c:183 Read of size 8 at addr ffff0000c03a2500 by task syz-executor083/4269 CPU: 5 PID: 4269 Comm: syz-executor083 Not tainted 5.10.0 #7 Hardware name: linux,dummy-virt (DT) Call trace: dump_backtrace+0x0/0x2d0 arch/arm64/kernel/stacktrace.c:132 show_stack+0x28/0x34 arch/arm64/kernel/stacktrace.c:196 __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x110/0x164 lib/dump_stack.c:118 print_address_description+0x78/0x5c8 mm/kasan/report.c:385 __kasan_report mm/kasan/report.c:545 [inline] kasan_report+0x148/0x1e4 mm/kasan/report.c:562 check_memory_region_inline mm/kasan/generic.c:183 [inline] __asan_load8+0xb4/0xbc mm/kasan/generic.c:252 kvm_vm_ioctl_unregister_coalesced_mmio+0x7c/0x1ec arch/arm64/kvm/../../../virt/kvm/coalesced_mmio.c:183 kvm_vm_ioctl+0xe30/0x14c4 arch/arm64/kvm/../../../virt/kvm/kvm_main.c:3755 vfs_ioctl fs/ioctl.c:48 [inline] __do_sys_ioctl fs/ioctl.c:753 [inline] __se_sys_ioctl fs/ioctl.c:739 [inline] __arm64_sys_ioctl+0xf88/0x131c fs/ioctl.c:739 __invoke_syscall arch/arm64/kernel/syscall.c:36 [inline] invoke_syscall arch/arm64/kernel/syscall.c:48 [inline] el0_svc_common arch/arm64/kernel/syscall.c:158 [inline] do_el0_svc+0x120/0x290 arch/arm64/kernel/syscall.c:220 el0_svc+0x1c/0x28 arch/arm64/kernel/entry-common.c:367 el0_sync_handler+0x98/0x170 arch/arm64/kernel/entry-common.c:383 el0_sync+0x140/0x180 arch/arm64/kernel/entry.S:670 Allocated by task 4269: stack_trace_save+0x80/0xb8 kernel/stacktrace.c:121 kasan_save_stack mm/kasan/common.c:48 [inline] kasan_set_track mm/kasan/common.c:56 [inline] __kasan_kmalloc+0xdc/0x120 mm/kasan/common.c:461 kasan_kmalloc+0xc/0x14 mm/kasan/common.c:475 kmem_cache_alloc_trace include/linux/slab.h:450 [inline] kmalloc include/linux/slab.h:552 [inline] kzalloc include/linux/slab.h:664 [inline] kvm_vm_ioctl_register_coalesced_mmio+0x78/0x1cc arch/arm64/kvm/../../../virt/kvm/coalesced_mmio.c:146 kvm_vm_ioctl+0x7e8/0x14c4 arch/arm64/kvm/../../../virt/kvm/kvm_main.c:3746 vfs_ioctl fs/ioctl.c:48 [inline] __do_sys_ioctl fs/ioctl.c:753 [inline] __se_sys_ioctl fs/ioctl.c:739 [inline] __arm64_sys_ioctl+0xf88/0x131c fs/ioctl.c:739 __invoke_syscall arch/arm64/kernel/syscall.c:36 [inline] invoke_syscall arch/arm64/kernel/syscall.c:48 [inline] el0_svc_common arch/arm64/kernel/syscall.c:158 [inline] do_el0_svc+0x120/0x290 arch/arm64/kernel/syscall.c:220 el0_svc+0x1c/0x28 arch/arm64/kernel/entry-common.c:367 el0_sync_handler+0x98/0x170 arch/arm64/kernel/entry-common.c:383 el0_sync+0x140/0x180 arch/arm64/kernel/entry.S:670 Freed by task 4269: stack_trace_save+0x80/0xb8 kernel/stacktrace.c:121 kasan_save_stack mm/kasan/common.c:48 [inline] kasan_set_track+0x38/0x6c mm/kasan/common.c:56 kasan_set_free_info+0x20/0x40 mm/kasan/generic.c:355 __kasan_slab_free+0x124/0x150 mm/kasan/common.c:422 kasan_slab_free+0x10/0x1c mm/kasan/common.c:431 slab_free_hook mm/slub.c:1544 [inline] slab_free_freelist_hook mm/slub.c:1577 [inline] slab_free mm/slub.c:3142 [inline] kfree+0x104/0x38c mm/slub.c:4124 coalesced_mmio_destructor+0x94/0xa4 arch/arm64/kvm/../../../virt/kvm/coalesced_mmio.c:102 kvm_iodevice_destructor include/kvm/iodev.h:61 [inline] kvm_io_bus_unregister_dev+0x248/0x280 arch/arm64/kvm/../../../virt/kvm/kvm_main.c:4374 kvm_vm_ioctl_unregister_coalesced_mmio+0x158/0x1ec arch/arm64/kvm/../../../virt/kvm/coalesced_mmio.c:186 kvm_vm_ioctl+0xe30/0x14c4 arch/arm64/kvm/../../../virt/kvm/kvm_main.c:3755 vfs_ioctl fs/ioctl.c:48 [inline] __do_sys_ioctl fs/ioctl.c:753 [inline] __se_sys_ioctl fs/ioctl.c:739 [inline] __arm64_sys_ioctl+0xf88/0x131c fs/ioctl.c:739 __invoke_syscall arch/arm64/kernel/syscall.c:36 [inline] invoke_syscall arch/arm64/kernel/sys ---truncated---

In the Linux kernel, the following vulnerability has been resolved: RDMA: Fix use-after-free in rxe_queue_cleanup On error handling path in rxe_qp_from_init() qp->sq.queue is freed and then rxe_create_qp() will drop last reference to this object. qp clean up function will try to free this queue one time and it causes UAF bug. Fix it by zeroing queue pointer after freeing queue in rxe_qp_from_init().

In the Linux kernel, the following vulnerability has been resolved: igb: Fix use-after-free error during reset Cleans the next descriptor to watch (next_to_watch) when cleaning the TX ring. Failure to do so can cause invalid memory accesses. If igb_poll() runs while the controller is reset this can lead to the driver try to free a skb that was already freed. (The crash is harder to reproduce with the igb driver, but the same potential problem exists as the code is identical to igc)

In the Linux kernel, the following vulnerability has been resolved: ubi: Fix race condition between ctrl_cdev_ioctl and ubi_cdev_ioctl Hulk Robot reported a KASAN report about use-after-free: ================================================================== BUG: KASAN: use-after-free in __list_del_entry_valid+0x13d/0x160 Read of size 8 at addr ffff888035e37d98 by task ubiattach/1385 [...] Call Trace: klist_dec_and_del+0xa7/0x4a0 klist_put+0xc7/0x1a0 device_del+0x4d4/0xed0 cdev_device_del+0x1a/0x80 ubi_attach_mtd_dev+0x2951/0x34b0 [ubi] ctrl_cdev_ioctl+0x286/0x2f0 [ubi] Allocated by task 1414: device_add+0x60a/0x18b0 cdev_device_add+0x103/0x170 ubi_create_volume+0x1118/0x1a10 [ubi] ubi_cdev_ioctl+0xb7f/0x1ba0 [ubi] Freed by task 1385: cdev_device_del+0x1a/0x80 ubi_remove_volume+0x438/0x6c0 [ubi] ubi_cdev_ioctl+0xbf4/0x1ba0 [ubi] [...] ================================================================== The lock held by ctrl_cdev_ioctl is ubi_devices_mutex, but the lock held by ubi_cdev_ioctl is ubi->device_mutex. Therefore, the two locks can be concurrent. ctrl_cdev_ioctl contains two operations: ubi_attach and ubi_detach. ubi_detach is bug-free because it uses reference counting to prevent concurrency. However, uif_init and uif_close in ubi_attach may race with ubi_cdev_ioctl. uif_init will race with ubi_cdev_ioctl as in the following stack. cpu1 cpu2 cpu3 _______________________|________________________|______________________ ctrl_cdev_ioctl ubi_attach_mtd_dev uif_init ubi_cdev_ioctl ubi_create_volume cdev_device_add ubi_add_volume // sysfs exist kill_volumes ubi_cdev_ioctl ubi_remove_volume cdev_device_del // first free ubi_free_volume cdev_del // double free cdev_device_del And uif_close will race with ubi_cdev_ioctl as in the following stack. cpu1 cpu2 cpu3 _______________________|________________________|______________________ ctrl_cdev_ioctl ubi_attach_mtd_dev uif_init ubi_cdev_ioctl ubi_create_volume cdev_device_add ubi_debugfs_init_dev //error goto out_uif; uif_close kill_volumes ubi_cdev_ioctl ubi_remove_volume cdev_device_del // first free ubi_free_volume // double free The cause of this problem is that commit 714fb87e8bc0 make device "available" before it becomes accessible via sysfs. Therefore, we roll back the modification. We will fix the race condition between ubi device creation and udev by removing ubi_get_device in vol_attribute_show and dev_attribute_show.This avoids accessing uninitialized ubi_devices[ubi_num]. ubi_get_device is used to prevent devices from being deleted during sysfs execution. However, now kernfs ensures that devices will not be deleted before all reference counting are released. The key process is shown in the following stack. device_del device_remove_attrs device_remove_groups sysfs_remove_groups sysfs_remove_group remove_files kernfs_remove_by_name kernfs_remove_by_name_ns __kernfs_remove kernfs_drain

In the Linux kernel, the following vulnerability has been resolved: HID: betop: fix slab-out-of-bounds Write in betop_probe Syzbot reported slab-out-of-bounds Write bug in hid-betopff driver. The problem is the driver assumes the device must have an input report but some malicious devices violate this assumption. So this patch checks hid_device's input is non empty before it's been used.

In the Linux kernel, the following vulnerability has been resolved: staging: greybus: uart: fix tty use after free User space can hold a tty open indefinitely and tty drivers must not release the underlying structures until the last user is gone. Switch to using the tty-port reference counter to manage the life time of the greybus tty state to avoid use after free after a disconnect.

In the Linux kernel, the following vulnerability has been resolved: spi: spi-zynqmp-gqspi: fix use-after-free in zynqmp_qspi_exec_op When handling op->addr, it is using the buffer "tmpbuf" which has been freed. This will trigger a use-after-free KASAN warning. Let's use temporary variables to store op->addr.val and op->cmd.opcode to fix this issue.

In the Linux kernel, the following vulnerability has been resolved: nvmem: Fix shift-out-of-bound (UBSAN) with byte size cells If a cell has 'nbits' equal to a multiple of BITS_PER_BYTE the logic *p &= GENMASK((cell->nbits%BITS_PER_BYTE) - 1, 0); will become undefined behavior because nbits modulo BITS_PER_BYTE is 0, and we subtract one from that making a large number that is then shifted more than the number of bits that fit into an unsigned long. UBSAN reports this problem: UBSAN: shift-out-of-bounds in drivers/nvmem/core.c:1386:8 shift exponent 64 is too large for 64-bit type 'unsigned long' CPU: 6 PID: 7 Comm: kworker/u16:0 Not tainted 5.15.0-rc3+ #9 Hardware name: Google Lazor (rev3+) with KB Backlight (DT) Workqueue: events_unbound deferred_probe_work_func Call trace: dump_backtrace+0x0/0x170 show_stack+0x24/0x30 dump_stack_lvl+0x64/0x7c dump_stack+0x18/0x38 ubsan_epilogue+0x10/0x54 __ubsan_handle_shift_out_of_bounds+0x180/0x194 __nvmem_cell_read+0x1ec/0x21c nvmem_cell_read+0x58/0x94 nvmem_cell_read_variable_common+0x4c/0xb0 nvmem_cell_read_variable_le_u32+0x40/0x100 a6xx_gpu_init+0x170/0x2f4 adreno_bind+0x174/0x284 component_bind_all+0xf0/0x264 msm_drm_bind+0x1d8/0x7a0 try_to_bring_up_master+0x164/0x1ac __component_add+0xbc/0x13c component_add+0x20/0x2c dp_display_probe+0x340/0x384 platform_probe+0xc0/0x100 really_probe+0x110/0x304 __driver_probe_device+0xb8/0x120 driver_probe_device+0x4c/0xfc __device_attach_driver+0xb0/0x128 bus_for_each_drv+0x90/0xdc __device_attach+0xc8/0x174 device_initial_probe+0x20/0x2c bus_probe_device+0x40/0xa4 deferred_probe_work_func+0x7c/0xb8 process_one_work+0x128/0x21c process_scheduled_works+0x40/0x54 worker_thread+0x1ec/0x2a8 kthread+0x138/0x158 ret_from_fork+0x10/0x20 Fix it by making sure there are any bits to mask out.

In the Linux kernel, the following vulnerability has been resolved: mac80211: fix skb length check in ieee80211_scan_rx() Replace hard-coded compile-time constants for header length check with dynamic determination based on the frame type. Otherwise, we hit a validation WARN_ON in cfg80211 later. [style fixes, reword commit message]

In the Linux kernel, the following vulnerability has been resolved: RDMA/cma: Ensure rdma_addr_cancel() happens before issuing more requests The FSM can run in a circle allowing rdma_resolve_ip() to be called twice on the same id_priv. While this cannot happen without going through the work, it violates the invariant that the same address resolution background request cannot be active twice. CPU 1 CPU 2 rdma_resolve_addr(): RDMA_CM_IDLE -> RDMA_CM_ADDR_QUERY rdma_resolve_ip(addr_handler) #1 process_one_req(): for #1 addr_handler(): RDMA_CM_ADDR_QUERY -> RDMA_CM_ADDR_BOUND mutex_unlock(&id_priv->handler_mutex); [.. handler still running ..] rdma_resolve_addr(): RDMA_CM_ADDR_BOUND -> RDMA_CM_ADDR_QUERY rdma_resolve_ip(addr_handler) !! two requests are now on the req_list rdma_destroy_id(): destroy_id_handler_unlock(): _destroy_id(): cma_cancel_operation(): rdma_addr_cancel() // process_one_req() self removes it spin_lock_bh(&lock); cancel_delayed_work(&req->work); if (!list_empty(&req->list)) == true ! rdma_addr_cancel() returns after process_on_req #1 is done kfree(id_priv) process_one_req(): for #2 addr_handler(): mutex_lock(&id_priv->handler_mutex); !! Use after free on id_priv rdma_addr_cancel() expects there to be one req on the list and only cancels the first one. The self-removal behavior of the work only happens after the handler has returned. This yields a situations where the req_list can have two reqs for the same "handle" but rdma_addr_cancel() only cancels the first one. The second req remains active beyond rdma_destroy_id() and will use-after-free id_priv once it inevitably triggers. Fix this by remembering if the id_priv has called rdma_resolve_ip() and always cancel before calling it again. This ensures the req_list never gets more than one item in it and doesn't cost anything in the normal flow that never uses this strange error path.

In the Linux kernel, the following vulnerability has been resolved: serial: liteuart: fix use-after-free and memleak on unbind Deregister the port when unbinding the driver to prevent it from being used after releasing the driver data and leaking memory allocated by serial core.

In the Linux kernel, the following vulnerability has been resolved: can: pch_can: pch_can_rx_normal: fix use after free After calling netif_receive_skb(skb), dereferencing skb is unsafe. Especially, the can_frame cf which aliases skb memory is dereferenced just after the call netif_receive_skb(skb). Reordering the lines solves the issue.

In the Linux kernel, the following vulnerability has been resolved: tun: avoid double free in tun_free_netdev Avoid double free in tun_free_netdev() by moving the dev->tstats and tun->security allocs to a new ndo_init routine (tun_net_init()) that will be called by register_netdevice(). ndo_init is paired with the desctructor (tun_free_netdev()), so if there's an error in register_netdevice() the destructor will handle the frees. BUG: KASAN: double-free or invalid-free in selinux_tun_dev_free_security+0x1a/0x20 security/selinux/hooks.c:5605 CPU: 0 PID: 25750 Comm: syz-executor416 Not tainted 5.16.0-rc2-syzk #1 Hardware name: Red Hat KVM, BIOS Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x89/0xb5 lib/dump_stack.c:106 print_address_description.constprop.9+0x28/0x160 mm/kasan/report.c:247 kasan_report_invalid_free+0x55/0x80 mm/kasan/report.c:372 ____kasan_slab_free mm/kasan/common.c:346 [inline] __kasan_slab_free+0x107/0x120 mm/kasan/common.c:374 kasan_slab_free include/linux/kasan.h:235 [inline] slab_free_hook mm/slub.c:1723 [inline] slab_free_freelist_hook mm/slub.c:1749 [inline] slab_free mm/slub.c:3513 [inline] kfree+0xac/0x2d0 mm/slub.c:4561 selinux_tun_dev_free_security+0x1a/0x20 security/selinux/hooks.c:5605 security_tun_dev_free_security+0x4f/0x90 security/security.c:2342 tun_free_netdev+0xe6/0x150 drivers/net/tun.c:2215 netdev_run_todo+0x4df/0x840 net/core/dev.c:10627 rtnl_unlock+0x13/0x20 net/core/rtnetlink.c:112 __tun_chr_ioctl+0x80c/0x2870 drivers/net/tun.c:3302 tun_chr_ioctl+0x2f/0x40 drivers/net/tun.c:3311 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:874 [inline] __se_sys_ioctl fs/ioctl.c:860 [inline] __x64_sys_ioctl+0x19d/0x220 fs/ioctl.c:860 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3a/0x80 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae

In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: Fix even more out of bound writes from debugfs CVE-2021-42327 was fixed by: commit f23750b5b3d98653b31d4469592935ef6364ad67 Author: Thelford Williams <tdwilliamsiv@gmail.com> Date: Wed Oct 13 16:04:13 2021 -0400 drm/amdgpu: fix out of bounds write but amdgpu_dm_debugfs.c contains more of the same issue so fix the remaining ones. v2: * Add missing fix in dp_max_bpc_write (Harry Wentland)

In the Linux kernel, the following vulnerability has been resolved: ACPI: custom_method: fix potential use-after-free issue In cm_write(), buf is always freed when reaching the end of the function. If the requested count is less than table.length, the allocated buffer will be freed but subsequent calls to cm_write() will still try to access it. Remove the unconditional kfree(buf) at the end of the function and set the buf to NULL in the -EINVAL error path to match the rest of function.

In the Linux kernel, the following vulnerability has been resolved: NFSv4: Fix an Oops in pnfs_mark_request_commit() when doing O_DIRECT Fix an Oopsable condition in pnfs_mark_request_commit() when we're putting a set of writes on the commit list to reschedule them after a failed pNFS attempt.

In the Linux kernel, the following vulnerability has been resolved: i40e: Fix use-after-free in i40e_client_subtask() Currently the call to i40e_client_del_instance frees the object pf->cinst, however pf->cinst->lan_info is being accessed after the free. Fix this by adding the missing return. Addresses-Coverity: ("Read from pointer after free")

In the Linux kernel, the following vulnerability has been resolved: regmap: set debugfs_name to NULL after it is freed There is a upstream commit cffa4b2122f5("regmap:debugfs: Fix a memory leak when calling regmap_attach_dev") that adds a if condition when create name for debugfs_name. With below function invoking logical, debugfs_name is freed in regmap_debugfs_exit(), but it is not created again because of the if condition introduced by above commit. regmap_reinit_cache() regmap_debugfs_exit() ... regmap_debugfs_init() So, set debugfs_name to NULL after it is freed.

In the Linux kernel, the following vulnerability has been resolved: rtw88: Fix array overrun in rtw_get_tx_power_params() Using a kernel with the Undefined Behaviour Sanity Checker (UBSAN) enabled, the following array overrun is logged: ================================================================================ UBSAN: array-index-out-of-bounds in /home/finger/wireless-drivers-next/drivers/net/wireless/realtek/rtw88/phy.c:1789:34 index 5 is out of range for type 'u8 [5]' CPU: 2 PID: 84 Comm: kworker/u16:3 Tainted: G O 5.12.0-rc5-00086-gd88bba47038e-dirty #651 Hardware name: TOSHIBA TECRA A50-A/TECRA A50-A, BIOS Version 4.50 09/29/2014 Workqueue: phy0 ieee80211_scan_work [mac80211] Call Trace: dump_stack+0x64/0x7c ubsan_epilogue+0x5/0x40 __ubsan_handle_out_of_bounds.cold+0x43/0x48 rtw_get_tx_power_params+0x83a/drivers/net/wireless/realtek/rtw88/0xad0 [rtw_core] ? rtw_pci_read16+0x20/0x20 [rtw_pci] ? check_hw_ready+0x50/0x90 [rtw_core] rtw_phy_get_tx_power_index+0x4d/0xd0 [rtw_core] rtw_phy_set_tx_power_level+0xee/0x1b0 [rtw_core] rtw_set_channel+0xab/0x110 [rtw_core] rtw_ops_config+0x87/0xc0 [rtw_core] ieee80211_hw_config+0x9d/0x130 [mac80211] ieee80211_scan_state_set_channel+0x81/0x170 [mac80211] ieee80211_scan_work+0x19f/0x2a0 [mac80211] process_one_work+0x1dd/0x3a0 worker_thread+0x49/0x330 ? rescuer_thread+0x3a0/0x3a0 kthread+0x134/0x150 ? kthread_create_worker_on_cpu+0x70/0x70 ret_from_fork+0x22/0x30 ================================================================================ The statement where an array is being overrun is shown in the following snippet: if (rate <= DESC_RATE11M) tx_power = pwr_idx_2g->cck_base[group]; else ====> tx_power = pwr_idx_2g->bw40_base[group]; The associated arrays are defined in main.h as follows: struct rtw_2g_txpwr_idx { u8 cck_base[6]; u8 bw40_base[5]; struct rtw_2g_1s_pwr_idx_diff ht_1s_diff; struct rtw_2g_ns_pwr_idx_diff ht_2s_diff; struct rtw_2g_ns_pwr_idx_diff ht_3s_diff; struct rtw_2g_ns_pwr_idx_diff ht_4s_diff; }; The problem arises because the value of group is 5 for channel 14. The trivial increase in the dimension of bw40_base fails as this struct must match the layout of efuse. The fix is to add the rate as an argument to rtw_get_channel_group() and set the group for channel 14 to 4 if rate <= DESC_RATE11M. This patch fixes commit fa6dfe6bff24 ("rtw88: resolve order of tx power setting routines")

In the Linux kernel, the following vulnerability has been resolved: scsi: mpt3sas: Fix kernel panic during drive powercycle test While looping over shost's sdev list it is possible that one of the drives is getting removed and its sas_target object is freed but its sdev object remains intact. Consequently, a kernel panic can occur while the driver is trying to access the sas_address field of sas_target object without also checking the sas_target object for NULL.

In the Linux kernel, the following vulnerability has been resolved: net/tls: Fix flipped sign in tls_err_abort() calls sk->sk_err appears to expect a positive value, a convention that ktls doesn't always follow and that leads to memory corruption in other code. For instance, [kworker] tls_encrypt_done(..., err=<negative error from crypto request>) tls_err_abort(.., err) sk->sk_err = err; [task] splice_from_pipe_feed ... tls_sw_do_sendpage if (sk->sk_err) { ret = -sk->sk_err; // ret is positive splice_from_pipe_feed (continued) ret = actor(...) // ret is still positive and interpreted as bytes // written, resulting in underflow of buf->len and // sd->len, leading to huge buf->offset and bogus // addresses computed in later calls to actor() Fix all tls_err_abort() callers to pass a negative error code consistently and centralize the error-prone sign flip there, throwing in a warning to catch future misuse and uninlining the function so it really does only warn once.

In the Linux kernel, the following vulnerability has been resolved: comedi: vmk80xx: fix transfer-buffer overflows The driver uses endpoint-sized USB transfer buffers but up until recently had no sanity checks on the sizes. Commit e1f13c879a7c ("staging: comedi: check validity of wMaxPacketSize of usb endpoints found") inadvertently fixed NULL-pointer dereferences when accessing the transfer buffers in case a malicious device has a zero wMaxPacketSize. Make sure to allocate buffers large enough to handle also the other accesses that are done without a size check (e.g. byte 18 in vmk80xx_cnt_insn_read() for the VMK8061_MODEL) to avoid writing beyond the buffers, for example, when doing descriptor fuzzing. The original driver was for a low-speed device with 8-byte buffers. Support was later added for a device that uses bulk transfers and is presumably a full-speed device with a maximum 64-byte wMaxPacketSize.

In the Linux kernel, the following vulnerability has been resolved: Revert "Revert "block, bfq: honor already-setup queue merges"" A crash [1] happened to be triggered in conjunction with commit 2d52c58b9c9b ("block, bfq: honor already-setup queue merges"). The latter was then reverted by commit ebc69e897e17 ("Revert "block, bfq: honor already-setup queue merges""). Yet, the reverted commit was not the one introducing the bug. In fact, it actually triggered a UAF introduced by a different commit, and now fixed by commit d29bd41428cf ("block, bfq: reset last_bfqq_created on group change"). So, there is no point in keeping commit 2d52c58b9c9b ("block, bfq: honor already-setup queue merges") out. This commit restores it. [1] https://bugzilla.kernel.org/show_bug.cgi?id=214503

In the Linux kernel, the following vulnerability has been resolved: ext4: fix possible UAF when remounting r/o a mmp-protected file system After commit 618f003199c6 ("ext4: fix memory leak in ext4_fill_super"), after the file system is remounted read-only, there is a race where the kmmpd thread can exit, causing sbi->s_mmp_tsk to point at freed memory, which the call to ext4_stop_mmpd() can trip over. Fix this by only allowing kmmpd() to exit when it is stopped via ext4_stop_mmpd(). Bug-Report-Link: <20210629143603.2166962-1-yebin10@huawei.com>

In the Linux kernel, the following vulnerability has been resolved: media: staging/intel-ipu3: Fix set_fmt error handling If there in an error during a set_fmt, do not overwrite the previous sizes with the invalid config. Without this patch, v4l2-compliance ends up allocating 4GiB of RAM and causing the following OOPs [ 38.662975] ipu3-imgu 0000:00:05.0: swiotlb buffer is full (sz: 4096 bytes) [ 38.662980] DMA: Out of SW-IOMMU space for 4096 bytes at device 0000:00:05.0 [ 38.663010] general protection fault: 0000 [#1] PREEMPT SMP

In the Linux kernel, the following vulnerability has been resolved: Drivers: hv: vmbus: Use after free in __vmbus_open() The "open_info" variable is added to the &vmbus_connection.chn_msg_list, but the error handling frees "open_info" without removing it from the list. This will result in a use after free. First remove it from the list, and then free it.

In the Linux kernel, the following vulnerability has been resolved: pid: take a reference when initializing `cad_pid` During boot, kernel_init_freeable() initializes `cad_pid` to the init task's struct pid. Later on, we may change `cad_pid` via a sysctl, and when this happens proc_do_cad_pid() will increment the refcount on the new pid via get_pid(), and will decrement the refcount on the old pid via put_pid(). As we never called get_pid() when we initialized `cad_pid`, we decrement a reference we never incremented, can therefore free the init task's struct pid early. As there can be dangling references to the struct pid, we can later encounter a use-after-free (e.g. when delivering signals). This was spotted when fuzzing v5.13-rc3 with Syzkaller, but seems to have been around since the conversion of `cad_pid` to struct pid in commit 9ec52099e4b8 ("[PATCH] replace cad_pid by a struct pid") from the pre-KASAN stone age of v2.6.19. Fix this by getting a reference to the init task's struct pid when we assign it to `cad_pid`. Full KASAN splat below. ================================================================== BUG: KASAN: use-after-free in ns_of_pid include/linux/pid.h:153 [inline] BUG: KASAN: use-after-free in task_active_pid_ns+0xc0/0xc8 kernel/pid.c:509 Read of size 4 at addr ffff23794dda0004 by task syz-executor.0/273 CPU: 1 PID: 273 Comm: syz-executor.0 Not tainted 5.12.0-00001-g9aef892b2d15 #1 Hardware name: linux,dummy-virt (DT) Call trace: ns_of_pid include/linux/pid.h:153 [inline] task_active_pid_ns+0xc0/0xc8 kernel/pid.c:509 do_notify_parent+0x308/0xe60 kernel/signal.c:1950 exit_notify kernel/exit.c:682 [inline] do_exit+0x2334/0x2bd0 kernel/exit.c:845 do_group_exit+0x108/0x2c8 kernel/exit.c:922 get_signal+0x4e4/0x2a88 kernel/signal.c:2781 do_signal arch/arm64/kernel/signal.c:882 [inline] do_notify_resume+0x300/0x970 arch/arm64/kernel/signal.c:936 work_pending+0xc/0x2dc Allocated by task 0: slab_post_alloc_hook+0x50/0x5c0 mm/slab.h:516 slab_alloc_node mm/slub.c:2907 [inline] slab_alloc mm/slub.c:2915 [inline] kmem_cache_alloc+0x1f4/0x4c0 mm/slub.c:2920 alloc_pid+0xdc/0xc00 kernel/pid.c:180 copy_process+0x2794/0x5e18 kernel/fork.c:2129 kernel_clone+0x194/0x13c8 kernel/fork.c:2500 kernel_thread+0xd4/0x110 kernel/fork.c:2552 rest_init+0x44/0x4a0 init/main.c:687 arch_call_rest_init+0x1c/0x28 start_kernel+0x520/0x554 init/main.c:1064 0x0 Freed by task 270: slab_free_hook mm/slub.c:1562 [inline] slab_free_freelist_hook+0x98/0x260 mm/slub.c:1600 slab_free mm/slub.c:3161 [inline] kmem_cache_free+0x224/0x8e0 mm/slub.c:3177 put_pid.part.4+0xe0/0x1a8 kernel/pid.c:114 put_pid+0x30/0x48 kernel/pid.c:109 proc_do_cad_pid+0x190/0x1b0 kernel/sysctl.c:1401 proc_sys_call_handler+0x338/0x4b0 fs/proc/proc_sysctl.c:591 proc_sys_write+0x34/0x48 fs/proc/proc_sysctl.c:617 call_write_iter include/linux/fs.h:1977 [inline] new_sync_write+0x3ac/0x510 fs/read_write.c:518 vfs_write fs/read_write.c:605 [inline] vfs_write+0x9c4/0x1018 fs/read_write.c:585 ksys_write+0x124/0x240 fs/read_write.c:658 __do_sys_write fs/read_write.c:670 [inline] __se_sys_write fs/read_write.c:667 [inline] __arm64_sys_write+0x78/0xb0 fs/read_write.c:667 __invoke_syscall arch/arm64/kernel/syscall.c:37 [inline] invoke_syscall arch/arm64/kernel/syscall.c:49 [inline] el0_svc_common.constprop.1+0x16c/0x388 arch/arm64/kernel/syscall.c:129 do_el0_svc+0xf8/0x150 arch/arm64/kernel/syscall.c:168 el0_svc+0x28/0x38 arch/arm64/kernel/entry-common.c:416 el0_sync_handler+0x134/0x180 arch/arm64/kernel/entry-common.c:432 el0_sync+0x154/0x180 arch/arm64/kernel/entry.S:701 The buggy address belongs to the object at ffff23794dda0000 which belongs to the cache pid of size 224 The buggy address is located 4 bytes inside of 224-byte region [ff ---truncated---