Export limit exceeded: 363759 CVEs match your query. Please refine your search to export 10,000 CVEs or fewer.
Search
Search Results (640 CVEs found)
| CVE | Vendors | Products | Updated | CVSS v3.1 |
|---|---|---|---|---|
| CVE-2026-6362 | 1 Google | 1 Chrome | 2026-05-26 | 4.3 Medium |
| Use after free in Codecs in Google Chrome prior to 147.0.7727.101 allowed a remote attacker to potentially perform out of bounds memory access via a crafted video file. (Chromium security severity: High) | ||||
| CVE-2026-43388 | 1 Linux | 1 Linux Kernel | 2026-05-26 | 7.8 High |
| In the Linux kernel, the following vulnerability has been resolved: mm/damon/core: clear walk_control on inactive context in damos_walk() damos_walk() sets ctx->walk_control to the caller-provided control structure before checking whether the context is running. If the context is inactive (damon_is_running() returns false), the function returns -EINVAL without clearing ctx->walk_control. This leaves a dangling pointer to a stack-allocated structure that will be freed when the caller returns. This is structurally identical to the bug fixed in commit f9132fbc2e83 ("mm/damon/core: remove call_control in inactive contexts") for damon_call(), which had the same pattern of linking a control object and returning an error without unlinking it. The dangling walk_control pointer can cause: 1. Use-after-free if the context is later started and kdamond dereferences ctx->walk_control (e.g., in damos_walk_cancel() which writes to control->canceled and calls complete()) 2. Permanent -EBUSY from subsequent damos_walk() calls, since the stale pointer is non-NULL Nonetheless, the real user impact is quite restrictive. The use-after-free is impossible because there is no damos_walk() callers who starts the context later. The permanent -EBUSY can actually confuse users, as DAMON is not running. But the symptom is kept only while the context is turned off. Turning it on again will make DAMON internally uses a newly generated damon_ctx object that doesn't have the invalid damos_walk_control pointer, so everything will work fine again. Fix this by clearing ctx->walk_control under walk_control_lock before returning -EINVAL, mirroring the fix pattern from f9132fbc2e83. | ||||
| CVE-2026-23454 | 1 Linux | 1 Linux Kernel | 2026-05-26 | 7.0 High |
| In the Linux kernel, the following vulnerability has been resolved: net: mana: fix use-after-free in mana_hwc_destroy_channel() by reordering teardown A potential race condition exists in mana_hwc_destroy_channel() where hwc->caller_ctx is freed before the HWC's Completion Queue (CQ) and Event Queue (EQ) are destroyed. This allows an in-flight CQ interrupt handler to dereference freed memory, leading to a use-after-free or NULL pointer dereference in mana_hwc_handle_resp(). mana_smc_teardown_hwc() signals the hardware to stop but does not synchronize against IRQ handlers already executing on other CPUs. The IRQ synchronization only happens in mana_hwc_destroy_cq() via mana_gd_destroy_eq() -> mana_gd_deregister_irq(). Since this runs after kfree(hwc->caller_ctx), a concurrent mana_hwc_rx_event_handler() can dereference freed caller_ctx (and rxq->msg_buf) in mana_hwc_handle_resp(). Fix this by reordering teardown to reverse-of-creation order: destroy the TX/RX work queues and CQ/EQ before freeing hwc->caller_ctx. This ensures all in-flight interrupt handlers complete before the memory they access is freed. | ||||
| CVE-2026-43059 | 1 Linux | 1 Linux Kernel | 2026-05-23 | 7.8 High |
| In the Linux kernel, the following vulnerability has been resolved: Bluetooth: MGMT: Fix list corruption and UAF in command complete handlers Commit 302a1f674c00 ("Bluetooth: MGMT: Fix possible UAFs") introduced mgmt_pending_valid(), which not only validates the pending command but also unlinks it from the pending list if it is valid. This change in semantics requires updates to several completion handlers to avoid list corruption and memory safety issues. This patch addresses two left-over issues from the aforementioned rework: 1. In mgmt_add_adv_patterns_monitor_complete(), mgmt_pending_remove() is replaced with mgmt_pending_free() in the success path. Since mgmt_pending_valid() already unlinks the command at the beginning of the function, calling mgmt_pending_remove() leads to a double list_del() and subsequent list corruption/kernel panic. 2. In set_mesh_complete(), the use of mgmt_pending_foreach() in the error path is removed. Since the current command is already unlinked by mgmt_pending_valid(), this foreach loop would incorrectly target other pending mesh commands, potentially freeing them while they are still being processed concurrently (leading to UAFs). The redundant mgmt_cmd_status() is also simplified to use cmd->opcode directly. | ||||
| CVE-2026-43060 | 1 Linux | 1 Linux Kernel | 2026-05-22 | 7.8 High |
| In the Linux kernel, the following vulnerability has been resolved: netfilter: nft_ct: drop pending enqueued packets on removal Packets sitting in nfqueue might hold a reference to: - templates that specify the conntrack zone, because a percpu area is used and module removal is possible. - conntrack timeout policies and helper, where object removal leave a stale reference. Since these objects can just go away, drop enqueued packets to avoid stale reference to them. If there is a need for finer grain removal, this logic can be revisited to make selective packet drop upon dependencies. | ||||
| CVE-2026-43402 | 1 Linux | 1 Linux Kernel | 2026-05-21 | 9.8 Critical |
| In the Linux kernel, the following vulnerability has been resolved: kthread: consolidate kthread exit paths to prevent use-after-free Guillaume reported crashes via corrupted RCU callback function pointers during KUnit testing. The crash was traced back to the pidfs rhashtable conversion which replaced the 24-byte rb_node with an 8-byte rhash_head in struct pid, shrinking it from 160 to 144 bytes. struct kthread (without CONFIG_BLK_CGROUP) is also 144 bytes. With CONFIG_SLAB_MERGE_DEFAULT and SLAB_HWCACHE_ALIGN both round up to 192 bytes and share the same slab cache. struct pid.rcu.func and struct kthread.affinity_node both sit at offset 0x78. When a kthread exits via make_task_dead() it bypasses kthread_exit() and misses the affinity_node cleanup. free_kthread_struct() frees the memory while the node is still linked into the global kthread_affinity_list. A subsequent list_del() by another kthread writes through dangling list pointers into the freed and reused memory, corrupting the pid's rcu.func pointer. Instead of patching free_kthread_struct() to handle the missed cleanup, consolidate all kthread exit paths. Turn kthread_exit() into a macro that calls do_exit() and add kthread_do_exit() which is called from do_exit() for any task with PF_KTHREAD set. This guarantees that kthread-specific cleanup always happens regardless of the exit path - make_task_dead(), direct do_exit(), or kthread_exit(). Replace __to_kthread() with a new tsk_is_kthread() accessor in the public header. Export do_exit() since module code using the kthread_exit() macro now needs it directly. | ||||
| CVE-2026-43412 | 1 Linux | 1 Linux Kernel | 2026-05-21 | 5.5 Medium |
| In the Linux kernel, the following vulnerability has been resolved: ASoC: qcom: qdsp6: Fix q6apm remove ordering during ADSP stop and start During ADSP stop and start, the kernel crashes due to the order in which ASoC components are removed. On ADSP stop, the q6apm-audio .remove callback unloads topology and removes PCM runtimes during ASoC teardown. This deletes the RTDs that contain the q6apm DAI components before their removal pass runs, leaving those components still linked to the card and causing crashes on the next rebind. Fix this by ensuring that all dependent (child) components are removed first, and the q6apm component is removed last. [ 48.105720] Unable to handle kernel NULL pointer dereference at virtual address 00000000000000d0 [ 48.114763] Mem abort info: [ 48.117650] ESR = 0x0000000096000004 [ 48.121526] EC = 0x25: DABT (current EL), IL = 32 bits [ 48.127010] SET = 0, FnV = 0 [ 48.130172] EA = 0, S1PTW = 0 [ 48.133415] FSC = 0x04: level 0 translation fault [ 48.138446] Data abort info: [ 48.141422] ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000 [ 48.147079] CM = 0, WnR = 0, TnD = 0, TagAccess = 0 [ 48.152354] GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 [ 48.157859] user pgtable: 4k pages, 48-bit VAs, pgdp=00000001173cf000 [ 48.164517] [00000000000000d0] pgd=0000000000000000, p4d=0000000000000000 [ 48.171530] Internal error: Oops: 0000000096000004 [#1] SMP [ 48.177348] Modules linked in: q6prm_clocks q6apm_lpass_dais q6apm_dai snd_q6dsp_common q6prm snd_q6apm 8021q garp mrp stp llc snd_soc_hdmi_codec apr pdr_interface phy_qcom_edp fastrpc qcom_pd_mapper rpmsg_ctrl qrtr_smd rpmsg_char qcom_pdr_msg qcom_iris v4l2_mem2mem videobuf2_dma_contig ath11k_pci msm ubwc_config at24 ath11k videobuf2_memops mac80211 ocmem videobuf2_v4l2 libarc4 drm_gpuvm mhi qrtr videodev drm_exec snd_soc_sc8280xp gpu_sched videobuf2_common nvmem_qcom_spmi_sdam snd_soc_qcom_sdw drm_dp_aux_bus qcom_q6v5_pas qcom_spmi_temp_alarm snd_soc_qcom_common rtc_pm8xxx qcom_pon drm_display_helper cec qcom_pil_info qcom_stats soundwire_bus drm_client_lib mc dispcc0_sa8775p videocc_sa8775p qcom_q6v5 camcc_sa8775p snd_soc_dmic phy_qcom_sgmii_eth snd_soc_max98357a i2c_qcom_geni snd_soc_core dwmac_qcom_ethqos llcc_qcom icc_bwmon qcom_sysmon snd_compress qcom_refgen_regulator coresight_stm stmmac_platform snd_pcm_dmaengine qcom_common coresight_tmc stmmac coresight_replicator qcom_glink_smem coresight_cti stm_core [ 48.177444] coresight_funnel snd_pcm ufs_qcom phy_qcom_qmp_usb gpi phy_qcom_snps_femto_v2 coresight phy_qcom_qmp_ufs qcom_wdt gpucc_sa8775p pcs_xpcs mdt_loader qcom_ice icc_osm_l3 qmi_helpers snd_timer snd soundcore display_connector qcom_rng nvmem_reboot_mode drm_kms_helper phy_qcom_qmp_pcie sha256 cfg80211 rfkill socinfo fuse drm backlight ipv6 [ 48.301059] CPU: 2 UID: 0 PID: 293 Comm: kworker/u32:2 Not tainted 6.19.0-rc6-dirty #10 PREEMPT [ 48.310081] Hardware name: Qualcomm Technologies, Inc. Lemans EVK (DT) [ 48.316782] Workqueue: pdr_notifier_wq pdr_notifier_work [pdr_interface] [ 48.323672] pstate: 20400005 (nzCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 48.330825] pc : mutex_lock+0xc/0x54 [ 48.334514] lr : soc_dapm_shutdown_dapm+0x44/0x174 [snd_soc_core] [ 48.340794] sp : ffff800084ddb7b0 [ 48.344207] x29: ffff800084ddb7b0 x28: ffff00009cd9cf30 x27: ffff00009cd9cc00 [ 48.351544] x26: ffff000099610190 x25: ffffa31d2f19c810 x24: ffffa31d2f185098 [ 48.358869] x23: ffff800084ddb7f8 x22: 0000000000000000 x21: 00000000000000d0 [ 48.366198] x20: ffff00009ba6c338 x19: ffff00009ba6c338 x18: 00000000ffffffff [ 48.373528] x17: 000000040044ffff x16: ffffa31d4ae6dca8 x15: 072007740775076f [ 48.380853] x14: 0765076d07690774 x13: 00313a323a656369 x12: 767265733a637673 [ 48.388182] x11: 00000000000003f9 x10: ffffa31d4c7dea98 x9 : 0000000000000001 [ 48.395519] x8 : ffff00009a2aadc0 x7 : 0000000000000003 x6 : 0000000000000000 [ 48.402854] x5 : 0000000000000 ---truncated--- | ||||
| CVE-2026-43440 | 1 Linux | 1 Linux Kernel | 2026-05-21 | 7.8 High |
| In the Linux kernel, the following vulnerability has been resolved: net/mana: Null service_wq on setup error to prevent double destroy In mana_gd_setup() error path, set gc->service_wq to NULL after destroy_workqueue() to match the cleanup in mana_gd_cleanup(). This prevents a use-after-free if the workqueue pointer is checked after a failed setup. | ||||
| CVE-2026-43447 | 1 Linux | 1 Linux Kernel | 2026-05-21 | 7.8 High |
| In the Linux kernel, the following vulnerability has been resolved: iavf: fix PTP use-after-free during reset Commit 7c01dbfc8a1c5f ("iavf: periodically cache PHC time") introduced a worker to cache PHC time, but failed to stop it during reset or disable. This creates a race condition where `iavf_reset_task()` or `iavf_disable_vf()` free adapter resources (AQ) while the worker is still running. If the worker triggers `iavf_queue_ptp_cmd()` during teardown, it accesses freed memory/locks, leading to a crash. Fix this by calling `iavf_ptp_release()` before tearing down the adapter. This ensures `ptp_clock_unregister()` synchronously cancels the worker and cleans up the chardev before the backing resources are destroyed. | ||||
| CVE-2026-9111 | 4 Apple, Google, Linux and 1 more | 4 Macos, Chrome, Linux Kernel and 1 more | 2026-05-21 | 8.8 High |
| Use after free in WebRTC in Google Chrome on Linux prior to 148.0.7778.179 allowed a remote attacker to execute arbitrary code via a crafted HTML page. (Chromium security severity: Critical) | ||||
| CVE-2026-9112 | 4 Apple, Google, Linux and 1 more | 4 Macos, Chrome, Linux Kernel and 1 more | 2026-05-21 | 8.8 High |
| Use after free in GPU in Google Chrome on Windows prior to 148.0.7778.179 allowed a remote attacker to execute arbitrary code inside a sandbox via a crafted HTML page. (Chromium security severity: High) | ||||
| CVE-2026-9114 | 4 Apple, Google, Linux and 1 more | 4 Macos, Chrome, Linux Kernel and 1 more | 2026-05-21 | 8.8 High |
| Use after free in QUIC in Google Chrome on prior to 148.0.7778.179 allowed a remote attacker to execute arbitrary code inside a sandbox via malicious network traffic. (Chromium security severity: High) | ||||
| CVE-2026-9118 | 4 Apple, Google, Linux and 1 more | 4 Macos, Chrome, Linux Kernel and 1 more | 2026-05-21 | 8.8 High |
| Use after free in XR in Google Chrome on Windows prior to 148.0.7778.179 allowed a remote attacker to execute arbitrary code via a crafted HTML page. (Chromium security severity: High) | ||||
| CVE-2026-43473 | 1 Linux | 1 Linux Kernel | 2026-05-21 | 5.5 Medium |
| In the Linux kernel, the following vulnerability has been resolved: scsi: mpi3mr: Add NULL checks when resetting request and reply queues The driver encountered a crash during resource cleanup when the reply and request queues were NULL due to freed memory. This issue occurred when the creation of reply or request queues failed, and the driver freed the memory first, but attempted to mem set the content of the freed memory, leading to a system crash. Add NULL pointer checks for reply and request queues before accessing the reply/request memory during cleanup | ||||
| CVE-2026-3591 | 1 Isc | 1 Bind | 2026-05-21 | 5.4 Medium |
| A use-after-return vulnerability exists in the `named` server when handling DNS queries signed with SIG(0). Using a specially-crafted DNS request, an attacker may be able to cause an ACL to improperly (mis)match an IP address. In a default-allow ACL (denying only specific IP addresses), this may lead to unauthorized access. Default-deny ACLs should fail-secure. This issue affects BIND 9 versions 9.20.0 through 9.20.20, 9.21.0 through 9.21.19, and 9.20.9-S1 through 9.20.20-S1. BIND 9 versions 9.18.0 through 9.18.46 and 9.18.11-S1 through 9.18.46-S1 are NOT affected. | ||||
| CVE-2026-3593 | 1 Isc | 1 Bind | 2026-05-21 | 7.4 High |
| A use-after-free vulnerability exists within the DNS-over-HTTPS implementation. This issue affects BIND 9 versions 9.20.0 through 9.20.22, 9.21.0 through 9.21.21, and 9.20.9-S1 through 9.20.22-S1. BIND 9 versions 9.18.0 through 9.18.48 and 9.18.11-S1 through 9.18.48-S1 are NOT affected. | ||||
| CVE-2026-31426 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 7 High |
| In the Linux kernel, the following vulnerability has been resolved: ACPI: EC: clean up handlers on probe failure in acpi_ec_setup() When ec_install_handlers() returns -EPROBE_DEFER on reduced-hardware platforms, it has already started the EC and installed the address space handler with the struct acpi_ec pointer as handler context. However, acpi_ec_setup() propagates the error without any cleanup. The caller acpi_ec_add() then frees the struct acpi_ec for non-boot instances, leaving a dangling handler context in ACPICA. Any subsequent AML evaluation that accesses an EC OpRegion field dispatches into acpi_ec_space_handler() with the freed pointer, causing a use-after-free: BUG: KASAN: slab-use-after-free in mutex_lock (kernel/locking/mutex.c:289) Write of size 8 at addr ffff88800721de38 by task init/1 Call Trace: <TASK> mutex_lock (kernel/locking/mutex.c:289) acpi_ec_space_handler (drivers/acpi/ec.c:1362) acpi_ev_address_space_dispatch (drivers/acpi/acpica/evregion.c:293) acpi_ex_access_region (drivers/acpi/acpica/exfldio.c:246) acpi_ex_field_datum_io (drivers/acpi/acpica/exfldio.c:509) acpi_ex_extract_from_field (drivers/acpi/acpica/exfldio.c:700) acpi_ex_read_data_from_field (drivers/acpi/acpica/exfield.c:327) acpi_ex_resolve_node_to_value (drivers/acpi/acpica/exresolv.c:392) </TASK> Allocated by task 1: acpi_ec_alloc (drivers/acpi/ec.c:1424) acpi_ec_add (drivers/acpi/ec.c:1692) Freed by task 1: kfree (mm/slub.c:6876) acpi_ec_add (drivers/acpi/ec.c:1751) The bug triggers on reduced-hardware EC platforms (ec->gpe < 0) when the GPIO IRQ provider defers probing. Once the stale handler exists, any unprivileged sysfs read that causes AML to touch an EC OpRegion (battery, thermal, backlight) exercises the dangling pointer. Fix this by calling ec_remove_handlers() in the error path of acpi_ec_setup() before clearing first_ec. ec_remove_handlers() checks each EC_FLAGS_* bit before acting, so it is safe to call regardless of how far ec_install_handlers() progressed: -ENODEV (handler not installed): only calls acpi_ec_stop() -EPROBE_DEFER (handler installed): removes handler, stops EC | ||||
| CVE-2026-31406 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 7.8 High |
| 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(). | ||||
| CVE-2026-43378 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 9.8 Critical |
| In the Linux kernel, the following vulnerability has been resolved: smb: server: fix use-after-free in smb2_open() The opinfo pointer obtained via rcu_dereference(fp->f_opinfo) is dereferenced after rcu_read_unlock(), creating a use-after-free window. | ||||
| CVE-2026-31389 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 7.8 High |
| 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. | ||||