In the Linux kernel, the following vulnerability has been resolved: xfrm: iptfs: only publish mode_data after clone setup iptfs_clone_state() stores x->mode_data before allocating the reorder window. If that allocation fails, the code frees the cloned state and returns -ENOMEM, leaving x->mode_data pointing at freed memory. The xfrm clone unwind later runs destroy_state() through x->mode_data, so the failed clone path tears down IPTFS state that clone_state() already freed. Keep the cloned IPTFS state private until all allocations succeed so failed clones leave x->mode_data unset. The destroy path already handles a NULL mode_data pointer.

In the Linux kernel, the following vulnerability has been resolved: KVM: x86: Add SRCU protection for reading PDPTRs in __get_sregs2() Add SRCU read-side protection when reading PDPTR registers in __get_sregs2(). Reading PDPTRs may trigger access to guest memory: kvm_pdptr_read() -> svm_cache_reg() -> load_pdptrs() -> kvm_vcpu_read_guest_page() -> kvm_vcpu_gfn_to_memslot() kvm_vcpu_gfn_to_memslot() dereferences memslots via __kvm_memslots(), which uses srcu_dereference_check() and requires either kvm->srcu or kvm->slots_lock to be held. Currently only vcpu->mutex is held, triggering lockdep warning: ============================= WARNING: suspicious RCU usage in kvm_vcpu_gfn_to_memslot 6.12.59+ #3 Not tainted include/linux/kvm_host.h:1062 suspicious rcu_dereference_check() usage! other info that might help us debug this: rcu_scheduler_active = 2, debug_locks = 1 1 lock held by syz.5.1717/15100: #0: ff1100002f4b00b0 (&vcpu->mutex){+.+.}-{3:3}, at: kvm_vcpu_ioctl+0x1d5/0x1590 Call Trace: <TASK> __dump_stack lib/dump_stack.c:94 [inline] dump_stack_lvl+0xf0/0x120 lib/dump_stack.c:120 lockdep_rcu_suspicious+0x1e3/0x270 kernel/locking/lockdep.c:6824 __kvm_memslots include/linux/kvm_host.h:1062 [inline] __kvm_memslots include/linux/kvm_host.h:1059 [inline] kvm_vcpu_memslots include/linux/kvm_host.h:1076 [inline] kvm_vcpu_gfn_to_memslot+0x518/0x5e0 virt/kvm/kvm_main.c:2617 kvm_vcpu_read_guest_page+0x27/0x50 virt/kvm/kvm_main.c:3302 load_pdptrs+0xff/0x4b0 arch/x86/kvm/x86.c:1065 svm_cache_reg+0x1c9/0x230 arch/x86/kvm/svm/svm.c:1688 kvm_pdptr_read arch/x86/kvm/kvm_cache_regs.h:141 [inline] __get_sregs2 arch/x86/kvm/x86.c:11784 [inline] kvm_arch_vcpu_ioctl+0x3e20/0x4aa0 arch/x86/kvm/x86.c:6279 kvm_vcpu_ioctl+0x856/0x1590 virt/kvm/kvm_main.c:4663 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:907 [inline] __se_sys_ioctl fs/ioctl.c:893 [inline] __x64_sys_ioctl+0x18b/0x210 fs/ioctl.c:893 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xbd/0x1d0 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f Found by Linux Verification Center (linuxtesting.org) with Syzkaller.

In the Linux kernel, the following vulnerability has been resolved: rust_binder: check ownership before using vma When installing missing pages (or zapping them), Rust Binder will look up the vma in the mm by address, and then call vm_insert_page (or zap_page_range_single). However, if the vma is closed and replaced with a different vma at the same address, this can lead to Rust Binder installing pages into the wrong vma. By installing the page into a writable vma, it becomes possible to write to your own binder pages, which are normally read-only. Although you're not supposed to be able to write to those pages, the intent behind the design of Rust Binder is that even if you get that ability, it should not lead to anything bad. Unfortunately, due to another bug, that is not the case. To fix this, store a pointer in vm_private_data and check that the vma returned by vma_lookup() has the right vm_ops and vm_private_data before trying to use the vma. This should ensure that Rust Binder will refuse to interact with any other VMA. The plan is to introduce more vma abstractions to avoid this unsafe access to vm_ops and vm_private_data, but for now let's start with the simplest possible fix. C Binder performs the same check in a slightly different way: it provides a vm_ops->close that sets a boolean to true, then checks that boolean after calling vma_lookup(), but this is more fragile than the solution in this patch. (We probably still want to do both, but the vm_ops->close callback will be added later as part of the follow-up vma API changes.) It's still possible to remap the vma so that pages appear in the right vma, but at the wrong offset, but this is a separate issue and will be fixed when Rust Binder gets a vm_ops->close callback.

Weak file permissions applied to the Aviatrix VPN Client through 2.2.10 installation directory on Windows and Linux allow a local attacker to execute arbitrary code by gaining elevated privileges through file modifications.

pam-python before 1.0.7-1 has an issue in regard to the default environment variable handling of Python, which could allow for local root escalation in certain PAM setups.

The inet_csk_clone_lock function in net/ipv4/inet_connection_sock.c in the Linux kernel through 4.10.15 allows attackers to cause a denial of service (double free) or possibly have unspecified other impact by leveraging use of the accept system call.

In the Linux kernel, the following vulnerability has been resolved: mm/kasan: fix double free for kasan pXds kasan_free_pxd() assumes the page table is always struct page aligned. But that's not always the case for all architectures. E.g. In case of powerpc with 64K pagesize, PUD table (of size 4096) comes from slab cache named pgtable-2^9. Hence instead of page_to_virt(pxd_page()) let's just directly pass the start of the pxd table which is passed as the 1st argument. This fixes the below double free kasan issue seen with PMEM: radix-mmu: Mapped 0x0000047d10000000-0x0000047f90000000 with 2.00 MiB pages ================================================================== BUG: KASAN: double-free in kasan_remove_zero_shadow+0x9c4/0xa20 Free of addr c0000003c38e0000 by task ndctl/2164 CPU: 34 UID: 0 PID: 2164 Comm: ndctl Not tainted 6.19.0-rc1-00048-gea1013c15392 #157 VOLUNTARY Hardware name: IBM,9080-HEX POWER10 (architected) 0x800200 0xf000006 of:IBM,FW1060.00 (NH1060_012) hv:phyp pSeries Call Trace: dump_stack_lvl+0x88/0xc4 (unreliable) print_report+0x214/0x63c kasan_report_invalid_free+0xe4/0x110 check_slab_allocation+0x100/0x150 kmem_cache_free+0x128/0x6e0 kasan_remove_zero_shadow+0x9c4/0xa20 memunmap_pages+0x2b8/0x5c0 devm_action_release+0x54/0x70 release_nodes+0xc8/0x1a0 devres_release_all+0xe0/0x140 device_unbind_cleanup+0x30/0x120 device_release_driver_internal+0x3e4/0x450 unbind_store+0xfc/0x110 drv_attr_store+0x78/0xb0 sysfs_kf_write+0x114/0x140 kernfs_fop_write_iter+0x264/0x3f0 vfs_write+0x3bc/0x7d0 ksys_write+0xa4/0x190 system_call_exception+0x190/0x480 system_call_vectored_common+0x15c/0x2ec ---- interrupt: 3000 at 0x7fff93b3d3f4 NIP: 00007fff93b3d3f4 LR: 00007fff93b3d3f4 CTR: 0000000000000000 REGS: c0000003f1b07e80 TRAP: 3000 Not tainted (6.19.0-rc1-00048-gea1013c15392) MSR: 800000000280f033 <SF,VEC,VSX,EE,PR,FP,ME,IR,DR,RI,LE> CR: 48888208 XER: 00000000 <...> NIP [00007fff93b3d3f4] 0x7fff93b3d3f4 LR [00007fff93b3d3f4] 0x7fff93b3d3f4 ---- interrupt: 3000 The buggy address belongs to the object at c0000003c38e0000 which belongs to the cache pgtable-2^9 of size 4096 The buggy address is located 0 bytes inside of 4096-byte region [c0000003c38e0000, c0000003c38e1000) The buggy address belongs to the physical page: page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x3c38c head: order:2 mapcount:0 entire_mapcount:0 nr_pages_mapped:0 pincount:0 memcg:c0000003bfd63e01 flags: 0x63ffff800000040(head|node=6|zone=0|lastcpupid=0x7ffff) page_type: f5(slab) raw: 063ffff800000040 c000000140058980 5deadbeef0000122 0000000000000000 raw: 0000000000000000 0000000080200020 00000000f5000000 c0000003bfd63e01 head: 063ffff800000040 c000000140058980 5deadbeef0000122 0000000000000000 head: 0000000000000000 0000000080200020 00000000f5000000 c0000003bfd63e01 head: 063ffff800000002 c00c000000f0e301 00000000ffffffff 00000000ffffffff head: ffffffffffffffff 0000000000000000 00000000ffffffff 0000000000000004 page dumped because: kasan: bad access detected [ 138.953636] [ T2164] Memory state around the buggy address: [ 138.953643] [ T2164] c0000003c38dff00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 138.953652] [ T2164] c0000003c38dff80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 138.953661] [ T2164] >c0000003c38e0000: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 138.953669] [ T2164] ^ [ 138.953675] [ T2164] c0000003c38e0080: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 138.953684] [ T2164] c0000003c38e0100: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 138.953692] [ T2164] ================================================================== [ 138.953701] [ T2164] Disabling lock debugging due to kernel taint

In Ubuntu's accountsservice an unprivileged local attacker can trigger a use-after-free vulnerability in accountsservice by sending a D-Bus message to the accounts-daemon process.

In the Linux kernel, the following vulnerability has been resolved: gpib: fix use-after-free in IO ioctl handlers The IBRD, IBWRT, IBCMD, and IBWAIT ioctl handlers use a gpib_descriptor pointer after board->big_gpib_mutex has been released. A concurrent IBCLOSEDEV ioctl can free the descriptor via close_dev_ioctl() during this window, causing a use-after-free. The IO handlers (read_ioctl, write_ioctl, command_ioctl) explicitly release big_gpib_mutex before calling their handler. wait_ioctl() is called with big_gpib_mutex held, but ibwait() releases it internally when wait_mask is non-zero. In all four cases, the descriptor pointer obtained from handle_to_descriptor() becomes unprotected. Fix this by introducing a kernel-only descriptor_busy reference count in struct gpib_descriptor. Each handler atomically increments descriptor_busy under file_priv->descriptors_mutex before releasing the lock, and decrements it when done. close_dev_ioctl() checks descriptor_busy under the same lock and rejects the close with -EBUSY if the count is non-zero. A reference count rather than a simple flag is necessary because multiple handlers can operate on the same descriptor concurrently (e.g. IBRD and IBWAIT on the same handle from different threads). A separate counter is needed because io_in_progress can be cleared from unprivileged userspace via the IBWAIT ioctl (through general_ibstatus() with set_mask containing CMPL), which would allow an attacker to bypass a check based solely on io_in_progress. The new descriptor_busy counter is only modified by the kernel IO paths. The lock ordering is consistent (big_gpib_mutex -> descriptors_mutex) and the handlers only hold descriptors_mutex briefly during the lookup, so there is no deadlock risk and no impact on IO throughput.

A vulnerability exists in the memory management subsystem of the Linux kernel. The lock handling for accessing and updating virtual memory areas (VMAs) is incorrect, leading to use-after-free problems. This issue can be successfully exploited to execute arbitrary kernel code, escalate containers, and gain root privileges.

The sctp_v6_create_accept_sk function in net/sctp/ipv6.c in the Linux kernel through 4.11.1 mishandles inheritance, which allows local users to cause a denial of service or possibly have unspecified other impact via crafted system calls, a related issue to CVE-2017-8890.

The init script in the Debian x11-common package before 1:7.6+12 is vulnerable to a symlink attack that can lead to a privilege escalation during package installation.

In the Linux kernel before version 4.12, Kerberos 5 tickets decoded when using the RXRPC keys incorrectly assumes the size of a field. This could lead to the size-remaining variable wrapping and the data pointer going over the end of the buffer. This could possibly lead to memory corruption and possible privilege escalation.

drivers/char/virtio_console.c in the Linux kernel 4.9.x and 4.10.x before 4.10.12 interacts incorrectly with the CONFIG_VMAP_STACK option, which allows local users to cause a denial of service (system crash or memory corruption) or possibly have unspecified other impact by leveraging use of more than one virtual page for a DMA scatterlist.

In the Linux kernel, the following vulnerability has been resolved: perf/aux: Fix AUX buffer serialization Ole reported that event->mmap_mutex is strictly insufficient to serialize the AUX buffer, add a per RB mutex to fully serialize it. Note that in the lock order comment the perf_event::mmap_mutex order was already wrong, that is, it nesting under mmap_lock is not new with this patch.

There is a possible tty hijacking in shadow 4.x before 4.1.5 and sudo 1.x before 1.7.4 via "su - user -c program". The user session can be escaped to the parent session by using the TIOCSTI ioctl to push characters into the input buffer to be read by the next process.

The brcmf_cfg80211_mgmt_tx function in drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c in the Linux kernel before 4.12.3 allows local users to cause a denial of service (buffer overflow and system crash) or possibly gain privileges via a crafted NL80211_CMD_FRAME Netlink packet.

qfq_change_class in net/sched/sch_qfq.c in the Linux kernel before 6.2.13 allows an out-of-bounds write because lmax can exceed QFQ_MIN_LMAX.

In the Linux kernel, the following vulnerability has been resolved: KVM: x86: Acquire kvm->srcu when handling KVM_SET_VCPU_EVENTS Grab kvm->srcu when processing KVM_SET_VCPU_EVENTS, as KVM will forcibly leave nested VMX/SVM if SMM mode is being toggled, and leaving nested VMX reads guest memory. Note, kvm_vcpu_ioctl_x86_set_vcpu_events() can also be called from KVM_RUN via sync_regs(), which already holds SRCU. I.e. trying to precisely use kvm_vcpu_srcu_read_lock() around the problematic SMM code would cause problems. Acquiring SRCU isn't all that expensive, so for simplicity, grab it unconditionally for KVM_SET_VCPU_EVENTS. ============================= WARNING: suspicious RCU usage 6.10.0-rc7-332d2c1d713e-next-vm #552 Not tainted ----------------------------- include/linux/kvm_host.h:1027 suspicious rcu_dereference_check() usage! other info that might help us debug this: rcu_scheduler_active = 2, debug_locks = 1 1 lock held by repro/1071: #0: ffff88811e424430 (&vcpu->mutex){+.+.}-{3:3}, at: kvm_vcpu_ioctl+0x7d/0x970 [kvm] stack backtrace: CPU: 15 PID: 1071 Comm: repro Not tainted 6.10.0-rc7-332d2c1d713e-next-vm #552 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015 Call Trace: <TASK> dump_stack_lvl+0x7f/0x90 lockdep_rcu_suspicious+0x13f/0x1a0 kvm_vcpu_gfn_to_memslot+0x168/0x190 [kvm] kvm_vcpu_read_guest+0x3e/0x90 [kvm] nested_vmx_load_msr+0x6b/0x1d0 [kvm_intel] load_vmcs12_host_state+0x432/0xb40 [kvm_intel] vmx_leave_nested+0x30/0x40 [kvm_intel] kvm_vcpu_ioctl_x86_set_vcpu_events+0x15d/0x2b0 [kvm] kvm_arch_vcpu_ioctl+0x1107/0x1750 [kvm] ? mark_held_locks+0x49/0x70 ? kvm_vcpu_ioctl+0x7d/0x970 [kvm] ? kvm_vcpu_ioctl+0x497/0x970 [kvm] kvm_vcpu_ioctl+0x497/0x970 [kvm] ? lock_acquire+0xba/0x2d0 ? find_held_lock+0x2b/0x80 ? do_user_addr_fault+0x40c/0x6f0 ? lock_release+0xb7/0x270 __x64_sys_ioctl+0x82/0xb0 do_syscall_64+0x6c/0x170 entry_SYSCALL_64_after_hwframe+0x4b/0x53 RIP: 0033:0x7ff11eb1b539 </TASK>

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)

In the Linux kernel, the following vulnerability has been resolved: rxrpc: proc: size address buffers for %pISpc output The AF_RXRPC procfs helpers format local and remote socket addresses into fixed 50-byte stack buffers with "%pISpc". That is too small for the longest current-tree IPv6-with-port form the formatter can produce. In lib/vsprintf.c, the compressed IPv6 path uses a dotted-quad tail not only for v4mapped addresses, but also for ISATAP addresses via ipv6_addr_is_isatap(). As a result, a case such as [ffff:ffff:ffff:ffff:0:5efe:255.255.255.255]:65535 is possible with the current formatter. That is 50 visible characters, so 51 bytes including the trailing NUL, which does not fit in the existing char[50] buffers used by net/rxrpc/proc.c. Size the buffers from the formatter's maximum textual form and switch the call sites to scnprintf(). Changes since v1: - correct the changelog to cite the actual maximum current-tree case explicitly - frame the proof around the ISATAP formatting path instead of the earlier mapped-v4 example

In the Linux kernel, the following vulnerability has been resolved: net/packet: fix TOCTOU race on mmap'd vnet_hdr in tpacket_snd() In tpacket_snd(), when PACKET_VNET_HDR is enabled, vnet_hdr points directly into the mmap'd TX ring buffer shared with userspace. The kernel validates the header via __packet_snd_vnet_parse() but then re-reads all fields later in virtio_net_hdr_to_skb(). A concurrent userspace thread can modify the vnet_hdr fields between validation and use, bypassing all safety checks. The non-TPACKET path (packet_snd()) already correctly copies vnet_hdr to a stack-local variable. All other vnet_hdr consumers in the kernel (tun.c, tap.c, virtio_net.c) also use stack copies. The TPACKET TX path is the only caller of virtio_net_hdr_to_skb() that reads directly from user-controlled shared memory. Fix this by copying vnet_hdr from the mmap'd ring buffer to a stack-local variable before validation and use, consistent with the approach used in packet_snd() and all other callers.

In the Linux kernel, the following vulnerability has been resolved: drm/i915/gt: fix refcount underflow in intel_engine_park_heartbeat A use-after-free / refcount underflow is possible when the heartbeat worker and intel_engine_park_heartbeat() race to release the same engine->heartbeat.systole request. The heartbeat worker reads engine->heartbeat.systole and calls i915_request_put() on it when the request is complete, but clears the pointer in a separate, non-atomic step. Concurrently, a request retirement on another CPU can drop the engine wakeref to zero, triggering __engine_park() -> intel_engine_park_heartbeat(). If the heartbeat timer is pending at that point, cancel_delayed_work() returns true and intel_engine_park_heartbeat() reads the stale non-NULL systole pointer and calls i915_request_put() on it again, causing a refcount underflow: ``` <4> [487.221889] Workqueue: i915-unordered engine_retire [i915] <4> [487.222640] RIP: 0010:refcount_warn_saturate+0x68/0xb0 ... <4> [487.222707] Call Trace: <4> [487.222711] <TASK> <4> [487.222716] intel_engine_park_heartbeat.part.0+0x6f/0x80 [i915] <4> [487.223115] intel_engine_park_heartbeat+0x25/0x40 [i915] <4> [487.223566] __engine_park+0xb9/0x650 [i915] <4> [487.223973] ____intel_wakeref_put_last+0x2e/0xb0 [i915] <4> [487.224408] __intel_wakeref_put_last+0x72/0x90 [i915] <4> [487.224797] intel_context_exit_engine+0x7c/0x80 [i915] <4> [487.225238] intel_context_exit+0xf1/0x1b0 [i915] <4> [487.225695] i915_request_retire.part.0+0x1b9/0x530 [i915] <4> [487.226178] i915_request_retire+0x1c/0x40 [i915] <4> [487.226625] engine_retire+0x122/0x180 [i915] <4> [487.227037] process_one_work+0x239/0x760 <4> [487.227060] worker_thread+0x200/0x3f0 <4> [487.227068] ? __pfx_worker_thread+0x10/0x10 <4> [487.227075] kthread+0x10d/0x150 <4> [487.227083] ? __pfx_kthread+0x10/0x10 <4> [487.227092] ret_from_fork+0x3d4/0x480 <4> [487.227099] ? __pfx_kthread+0x10/0x10 <4> [487.227107] ret_from_fork_asm+0x1a/0x30 <4> [487.227141] </TASK> ``` Fix this by replacing the non-atomic pointer read + separate clear with xchg() in both racing paths. xchg() is a single indivisible hardware instruction that atomically reads the old pointer and writes NULL. This guarantees only one of the two concurrent callers obtains the non-NULL pointer and performs the put, the other gets NULL and skips it. (cherry picked from commit 13238dc0ee4f9ab8dafa2cca7295736191ae2f42)

In the Linux kernel, the following vulnerability has been resolved: misc: fastrpc: Fix double free of 'buf' in error path smatch warning: drivers/misc/fastrpc.c:1926 fastrpc_req_mmap() error: double free of 'buf' In fastrpc_req_mmap() error path, the fastrpc buffer is freed in fastrpc_req_munmap_impl() if unmap is successful. But in the end, there is an unconditional call to fastrpc_buf_free(). So the above case triggers the double free of fastrpc buf.

drivers/media/usb/dvb-usb/dw2102.c in the Linux kernel 4.9.x and 4.10.x before 4.10.4 interacts incorrectly with the CONFIG_VMAP_STACK option, which allows local users to cause a denial of service (system crash or memory corruption) or possibly have unspecified other impact by leveraging use of more than one virtual page for a DMA scatterlist.

Quick Emulator (Qemu) built with the VirtFS, host directory sharing via Plan 9 File System(9pfs) support, is vulnerable to an improper access control issue. It could occur while accessing virtfs metadata files in mapped-file security mode. A guest user could use this flaw to escalate their privileges inside guest.

Authentication Bypass vulnerability in Hitachi Ops Center Common Services.This issue affects Hitachi Ops Center Common Services: from 10.9.3-00 before 11.0.2-01.

The ipxitf_ioctl function in net/ipx/af_ipx.c in the Linux kernel through 4.11.1 mishandles reference counts, which allows local users to cause a denial of service (use-after-free) or possibly have unspecified other impact via a failed SIOCGIFADDR ioctl call for an IPX interface.

Linux Kernel nftables Use-After-Free Local Privilege Escalation Vulnerability; `nft_chain_lookup_byid()` failed to check whether a chain was active and CAP_NET_ADMIN is in any user or network namespace

An issue was discovered in the Linux kernel before 4.20.2. An out-of-bounds access exists in the function build_audio_procunit in the file sound/usb/mixer.c.

The ip_cmsg_recv_checksum function in net/ipv4/ip_sockglue.c in the Linux kernel before 4.10.1 has incorrect expectations about skb data layout, which allows local users to cause a denial of service (buffer over-read) or possibly have unspecified other impact via crafted system calls, as demonstrated by use of the MSG_MORE flag in conjunction with loopback UDP transmission.

The packet_set_ring function in net/packet/af_packet.c in the Linux kernel through 4.10.6 does not properly validate certain block-size data, which allows local users to cause a denial of service (integer signedness error and out-of-bounds write), or gain privileges (if the CAP_NET_RAW capability is held), via crafted system calls.

The sg_ioctl function in drivers/scsi/sg.c in the Linux kernel through 4.10.4 allows local users to cause a denial of service (stack-based buffer overflow) or possibly have unspecified other impact via a large command size in an SG_NEXT_CMD_LEN ioctl call, leading to out-of-bounds write access in the sg_write function.

A use-after-free flaw was found in the Linux kernel’s pipes functionality in how a user performs manipulations with the pipe post_one_notification() after free_pipe_info() that is already called. This flaw allows a local user to crash or potentially escalate their privileges on the system.

In the Linux kernel, the following vulnerability has been resolved: netrom: fix double-free in nr_route_frame() In nr_route_frame(), old_skb is immediately freed without checking if nr_neigh->ax25 pointer is NULL. Therefore, if nr_neigh->ax25 is NULL, the caller function will free old_skb again, causing a double-free bug. Therefore, to prevent this, we need to modify it to check whether nr_neigh->ax25 is NULL before freeing old_skb.

In the Linux kernel, the following vulnerability has been resolved: vt: discard stale unicode buffer on alt screen exit after resize When enter_alt_screen() saves vc_uni_lines into vc_saved_uni_lines and sets vc_uni_lines to NULL, a subsequent console resize via vc_do_resize() skips reallocating the unicode buffer because vc_uni_lines is NULL. However, vc_saved_uni_lines still points to the old buffer allocated for the original dimensions. When leave_alt_screen() later restores vc_saved_uni_lines, the buffer dimensions no longer match vc_rows/vc_cols. Any operation that iterates over the unicode buffer using the current dimensions (e.g. csi_J clearing the screen) will access memory out of bounds, causing a kernel oops: BUG: unable to handle page fault for address: 0x0000002000000020 RIP: 0010:csi_J+0x133/0x2d0 The faulting address 0x0000002000000020 is two adjacent u32 space characters (0x20) interpreted as a pointer, read from the row data area past the end of the 25-entry pointer array in a buffer allocated for 80x25 but accessed with 240x67 dimensions. Fix this by checking whether the console dimensions changed while in the alternate screen. If they did, free the stale saved buffer instead of restoring it. The unicode screen will be lazily rebuilt via vc_uniscr_check() when next needed.

The xfrm_replay_verify_len function in net/xfrm/xfrm_user.c in the Linux kernel through 4.10.6 does not validate certain size data after an XFRM_MSG_NEWAE update, which allows local users to obtain root privileges or cause a denial of service (heap-based out-of-bounds access) by leveraging the CAP_NET_ADMIN capability, as demonstrated during a Pwn2Own competition at CanSecWest 2017 for the Ubuntu 16.10 linux-image-* package 4.8.0.41.52.

In the Linux kernel, the following vulnerability has been resolved: net: bcmasp: fix double free of WoL irq We do not need to free wol_irq since it was instantiated with devm_request_irq(). So devres will free for us.

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: usb: usbtmc: Flush anchored URBs in usbtmc_release When calling usbtmc_release, pending anchored URBs must be flushed or killed to prevent use-after-free errors (e.g. in the HCD giveback path). Call usbtmc_draw_down() to allow anchored URBs to be completed.

In the Linux kernel, the following vulnerability has been resolved: misc: fastrpc: possible double-free of cctx->remote_heap fastrpc_init_create_static_process() may free cctx->remote_heap on the err_map path but does not clear the pointer. Later, fastrpc_rpmsg_remove() frees cctx->remote_heap again if it is non-NULL, which can lead to a double-free if the INIT_CREATE_STATIC ioctl hits the error path and the rpmsg device is subsequently removed/unbound. Clear cctx->remote_heap after freeing it in the error path to prevent the later cleanup from freeing it again. This issue was found by an in-house analysis workflow that extracts AST-based information and runs static checks, with LLM assistance for triage, and was confirmed by manual code review. No hardware testing was performed.

In the Linux kernel, the following vulnerability has been resolved: usb: typec: ucsi: validate connector number in ucsi_notify_common() The connector number extracted from CCI via UCSI_CCI_CONNECTOR() is a 7-bit field (0-127) that is used to index into the connector array in ucsi_connector_change(). However, the array is only allocated for the number of connectors reported by the device (typically 2-4 entries). A malicious or malfunctioning device could report an out-of-range connector number in the CCI, causing an out-of-bounds array access in ucsi_connector_change(). Add a bounds check in ucsi_notify_common(), the central point where CCI is parsed after arriving from hardware, so that bogus connector numbers are rejected before they propagate further.

In the Linux kernel, the following vulnerability has been resolved: f2fs: fix UAF caused by decrementing sbi->nr_pages[] in f2fs_write_end_io() The xfstests case "generic/107" and syzbot have both reported a NULL pointer dereference. The concurrent scenario that triggers the panic is as follows: F2FS_WB_CP_DATA write callback umount - f2fs_write_checkpoint - f2fs_wait_on_all_pages(sbi, F2FS_WB_CP_DATA) - blk_mq_end_request - bio_endio - f2fs_write_end_io : dec_page_count(sbi, F2FS_WB_CP_DATA) : wake_up(&sbi->cp_wait) - kill_f2fs_super - kill_block_super - f2fs_put_super : iput(sbi->node_inode) : sbi->node_inode = NULL : f2fs_in_warm_node_list - is_node_folio // sbi->node_inode is NULL and panic The root cause is that f2fs_put_super() calls iput(sbi->node_inode) and sets sbi->node_inode to NULL after sbi->nr_pages[F2FS_WB_CP_DATA] is decremented to zero. As a result, f2fs_in_warm_node_list() may dereference a NULL node_inode when checking whether a folio belongs to the node inode, leading to a panic. This patch fixes the issue by calling f2fs_in_warm_node_list() before decrementing sbi->nr_pages[F2FS_WB_CP_DATA], thus preventing the use-after-free condition.

In the Linux kernel, the following vulnerability has been resolved: net/smc: fix double-free of smc_spd_priv when tee() duplicates splice pipe buffer smc_rx_splice() allocates one smc_spd_priv per pipe_buffer and stores the pointer in pipe_buffer.private. The pipe_buf_operations for these buffers used .get = generic_pipe_buf_get, which only increments the page reference count when tee(2) duplicates a pipe buffer. The smc_spd_priv pointer itself was not handled, so after tee() both the original and the cloned pipe_buffer share the same smc_spd_priv *. When both pipes are subsequently released, smc_rx_pipe_buf_release() is called twice against the same object: 1st call: kfree(priv) sock_put(sk) smc_rx_update_cons() [correct] 2nd call: kfree(priv) sock_put(sk) smc_rx_update_cons() [UAF] KASAN reports a slab-use-after-free in smc_rx_pipe_buf_release(), which then escalates to a NULL-pointer dereference and kernel panic via smc_rx_update_consumer() when it chases the freed priv->smc pointer: BUG: KASAN: slab-use-after-free in smc_rx_pipe_buf_release+0x78/0x2a0 Read of size 8 at addr ffff888004a45740 by task smc_splice_tee_/74 Call Trace: <TASK> dump_stack_lvl+0x53/0x70 print_report+0xce/0x650 kasan_report+0xc6/0x100 smc_rx_pipe_buf_release+0x78/0x2a0 free_pipe_info+0xd4/0x130 pipe_release+0x142/0x160 __fput+0x1c6/0x490 __x64_sys_close+0x4f/0x90 do_syscall_64+0xa6/0x1a0 entry_SYSCALL_64_after_hwframe+0x77/0x7f </TASK> BUG: kernel NULL pointer dereference, address: 0000000000000020 RIP: 0010:smc_rx_update_consumer+0x8d/0x350 Call Trace: <TASK> smc_rx_pipe_buf_release+0x121/0x2a0 free_pipe_info+0xd4/0x130 pipe_release+0x142/0x160 __fput+0x1c6/0x490 __x64_sys_close+0x4f/0x90 do_syscall_64+0xa6/0x1a0 entry_SYSCALL_64_after_hwframe+0x77/0x7f </TASK> Kernel panic - not syncing: Fatal exception Beyond the memory-safety problem, duplicating an SMC splice buffer is semantically questionable: smc_rx_update_cons() would advance the consumer cursor twice for the same data, corrupting receive-window accounting. A refcount on smc_spd_priv could fix the double-free, but the cursor-accounting issue would still need to be addressed separately. The .get callback is invoked by both tee(2) and splice_pipe_to_pipe() for partial transfers; both will now return -EFAULT. Users who need to duplicate SMC socket data must use a copy-based read path.

In the Linux kernel, the following vulnerability has been resolved: ocfs2: fix use-after-free in ocfs2_fault() when VM_FAULT_RETRY filemap_fault() may drop the mmap_lock before returning VM_FAULT_RETRY, as documented in mm/filemap.c: "If our return value has VM_FAULT_RETRY set, it's because the mmap_lock may be dropped before doing I/O or by lock_folio_maybe_drop_mmap()." When this happens, a concurrent munmap() can call remove_vma() and free the vm_area_struct via RCU. The saved 'vma' pointer in ocfs2_fault() then becomes a dangling pointer, and the subsequent trace_ocfs2_fault() call dereferences it -- a use-after-free. Fix this by saving ip_blkno as a plain integer before calling filemap_fault(), and removing vma from the trace event. Since ip_blkno is copied by value before the lock can be dropped, it remains valid regardless of what happens to the vma or inode afterward.

In the Linux kernel, the following vulnerability has been resolved: wifi: wilc1000: fix u8 overflow in SSID scan buffer size calculation The variable valuesize is declared as u8 but accumulates the total length of all SSIDs to scan. Each SSID contributes up to 33 bytes (IEEE80211_MAX_SSID_LEN + 1), and with WILC_MAX_NUM_PROBED_SSID (10) SSIDs the total can reach 330, which wraps around to 74 when stored in a u8. This causes kmalloc to allocate only 75 bytes while the subsequent memcpy writes up to 331 bytes into the buffer, resulting in a 256-byte heap buffer overflow. Widen valuesize from u8 to u32 to accommodate the full range.

In the Linux kernel, the following vulnerability has been resolved: Input: uinput - fix circular locking dependency with ff-core A lockdep circular locking dependency warning can be triggered reproducibly when using a force-feedback gamepad with uinput (for example, playing ELDEN RING under Wine with a Flydigi Vader 5 controller): ff->mutex -> udev->mutex -> input_mutex -> dev->mutex -> ff->mutex The cycle is caused by four lock acquisition paths: 1. ff upload: input_ff_upload() holds ff->mutex and calls uinput_dev_upload_effect() -> uinput_request_submit() -> uinput_request_send(), which acquires udev->mutex. 2. device create: uinput_ioctl_handler() holds udev->mutex and calls uinput_create_device() -> input_register_device(), which acquires input_mutex. 3. device register: input_register_device() holds input_mutex and calls kbd_connect() -> input_register_handle(), which acquires dev->mutex. 4. evdev release: evdev_release() calls input_flush_device() under dev->mutex, which calls input_ff_flush() acquiring ff->mutex. Fix this by introducing a new state_lock spinlock to protect udev->state and udev->dev access in uinput_request_send() instead of acquiring udev->mutex. The function only needs to atomically check device state and queue an input event into the ring buffer via uinput_dev_event() -- both operations are safe under a spinlock (ktime_get_ts64() and wake_up_interruptible() do not sleep). This breaks the ff->mutex -> udev->mutex link since a spinlock is a leaf in the lock ordering and cannot form cycles with mutexes. To keep state transitions visible to uinput_request_send(), protect writes to udev->state in uinput_create_device() and uinput_destroy_device() with the same state_lock spinlock. Additionally, move init_completion(&request->done) from uinput_request_send() to uinput_request_submit() before uinput_request_reserve_slot(). Once the slot is allocated, uinput_flush_requests() may call complete() on it at any time from the destroy path, so the completion must be initialised before the request becomes visible. Lock ordering after the fix: ff->mutex -> state_lock (spinlock, leaf) udev->mutex -> state_lock (spinlock, leaf) udev->mutex -> input_mutex -> dev->mutex -> ff->mutex (no back-edge)

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: iio: gyro: mpu3050: Move iio_device_register() to correct location iio_device_register() should be at the end of the probe function to prevent race conditions. Place iio_device_register() at the end of the probe function and place iio_device_unregister() accordingly.

Integer overflow in the drm_mode_dirtyfb_ioctl function in drivers/gpu/drm/drm_crtc.c in the Direct Rendering Manager (DRM) subsystem in the Linux kernel before 3.1.5 allows local users to gain privileges or cause a denial of service (memory corruption) via a crafted ioctl call.