Export limit exceeded: 25505 CVEs match your query. Please refine your search to export 10,000 CVEs or fewer.
Search
Search Results (25505 CVEs found)
| CVE | Vendors | Products | Updated | CVSS v3.1 |
|---|---|---|---|---|
| CVE-2026-43471 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 5.5 Medium |
| In the Linux kernel, the following vulnerability has been resolved: scsi: ufs: core: Fix possible NULL pointer dereference in ufshcd_add_command_trace() The kernel log indicates a crash in ufshcd_add_command_trace, due to a NULL pointer dereference when accessing hwq->id. This can happen if ufshcd_mcq_req_to_hwq() returns NULL. This patch adds a NULL check for hwq before accessing its id field to prevent a kernel crash. Kernel log excerpt: [<ffffffd5d192dc4c>] notify_die+0x4c/0x8c [<ffffffd5d1814e58>] __die+0x60/0xb0 [<ffffffd5d1814d64>] die+0x4c/0xe0 [<ffffffd5d181575c>] die_kernel_fault+0x74/0x88 [<ffffffd5d1864db4>] __do_kernel_fault+0x314/0x318 [<ffffffd5d2a3cdf8>] do_page_fault+0xa4/0x5f8 [<ffffffd5d2a3cd34>] do_translation_fault+0x34/0x54 [<ffffffd5d1864524>] do_mem_abort+0x50/0xa8 [<ffffffd5d2a297dc>] el1_abort+0x3c/0x64 [<ffffffd5d2a29718>] el1h_64_sync_handler+0x44/0xcc [<ffffffd5d181133c>] el1h_64_sync+0x80/0x88 [<ffffffd5d255c1dc>] ufshcd_add_command_trace+0x23c/0x320 [<ffffffd5d255bad8>] ufshcd_compl_one_cqe+0xa4/0x404 [<ffffffd5d2572968>] ufshcd_mcq_poll_cqe_lock+0xac/0x104 [<ffffffd5d11c7460>] ufs_mtk_mcq_intr+0x54/0x74 [ufs_mediatek_mod] [<ffffffd5d19ab92c>] __handle_irq_event_percpu+0xc8/0x348 [<ffffffd5d19abca8>] handle_irq_event+0x3c/0xa8 [<ffffffd5d19b1f0c>] handle_fasteoi_irq+0xf8/0x294 [<ffffffd5d19aa778>] generic_handle_domain_irq+0x54/0x80 [<ffffffd5d18102bc>] gic_handle_irq+0x1d4/0x330 [<ffffffd5d1838210>] call_on_irq_stack+0x44/0x68 [<ffffffd5d183af30>] do_interrupt_handler+0x78/0xd8 [<ffffffd5d2a29c00>] el1_interrupt+0x48/0xa8 [<ffffffd5d2a29ba8>] el1h_64_irq_handler+0x14/0x24 [<ffffffd5d18113c4>] el1h_64_irq+0x80/0x88 [<ffffffd5d2527fb4>] arch_local_irq_enable+0x4/0x1c [<ffffffd5d25282e4>] cpuidle_enter+0x34/0x54 [<ffffffd5d195a678>] do_idle+0x1dc/0x2f8 [<ffffffd5d195a7c4>] cpu_startup_entry+0x30/0x3c [<ffffffd5d18155c4>] secondary_start_kernel+0x134/0x1ac [<ffffffd5d18640bc>] __secondary_switched+0xc4/0xcc | ||||
| CVE-2026-43429 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 5.5 Medium |
| In the Linux kernel, the following vulnerability has been resolved: USB: usbtmc: Use usb_bulk_msg_killable() with user-specified timeouts The usbtmc driver accepts timeout values specified by the user in an ioctl command, and uses these timeouts for some usb_bulk_msg() calls. Since the user can specify arbitrarily long timeouts and usb_bulk_msg() uses unkillable waits, call usb_bulk_msg_killable() instead to avoid the possibility of the user hanging a kernel thread indefinitely. | ||||
| CVE-2026-43430 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 4.7 Medium |
| In the Linux kernel, the following vulnerability has been resolved: usb: yurex: fix race in probe The bbu member of the descriptor must be set to the value standing for uninitialized values before the URB whose completion handler sets bbu is submitted. Otherwise there is a window during which probing can overwrite already retrieved data. | ||||
| CVE-2026-43431 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 5.5 Medium |
| In the Linux kernel, the following vulnerability has been resolved: xhci: Fix NULL pointer dereference when reading portli debugfs files Michal reported and debgged a NULL pointer dereference bug in the recently added portli debugfs files Oops is caused when there are more port registers counted in xhci->max_ports than ports reported by Supported Protocol capabilities. This is possible if max_ports is more than maximum port number, or if there are gaps between ports of different speeds the 'Supported Protocol' capabilities. In such cases port->rhub will be NULL so we can't reach xhci behind it. Add an explicit NULL check for this case, and print portli in hex without dereferencing port->rhub. | ||||
| CVE-2026-43432 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 5.5 Medium |
| In the Linux kernel, the following vulnerability has been resolved: usb: xhci: Fix memory leak in xhci_disable_slot() xhci_alloc_command() allocates a command structure and, when the second argument is true, also allocates a completion structure. Currently, the error handling path in xhci_disable_slot() only frees the command structure using kfree(), causing the completion structure to leak. Use xhci_free_command() instead of kfree(). xhci_free_command() correctly frees both the command structure and the associated completion structure. Since the command structure is allocated with zero-initialization, command->in_ctx is NULL and will not be erroneously freed by xhci_free_command(). This bug was found using an experimental static analysis tool we are developing. The tool is based on the LLVM framework and is specifically designed to detect memory management issues. It is currently under active development and not yet publicly available, but we plan to open-source it after our research is published. The bug was originally detected on v6.13-rc1 using our static analysis tool, and we have verified that the issue persists in the latest mainline kernel. We performed build testing on x86_64 with allyesconfig using GCC=11.4.0. Since triggering these error paths in xhci_disable_slot() requires specific hardware conditions or abnormal state, we were unable to construct a test case to reliably trigger these specific error paths at runtime. | ||||
| CVE-2026-43454 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 7.8 High |
| In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_tables: Fix for duplicate device in netdev hooks When handling NETDEV_REGISTER notification, duplicate device registration must be avoided since the device may have been added by nft_netdev_hook_alloc() already when creating the hook. | ||||
| CVE-2026-43455 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 5.5 Medium |
| In the Linux kernel, the following vulnerability has been resolved: mctp: route: hold key->lock in mctp_flow_prepare_output() mctp_flow_prepare_output() checks key->dev and may call mctp_dev_set_key(), but it does not hold key->lock while doing so. mctp_dev_set_key() and mctp_dev_release_key() are annotated with __must_hold(&key->lock), so key->dev access is intended to be serialized by key->lock. The mctp_sendmsg() transmit path reaches mctp_flow_prepare_output() via mctp_local_output() -> mctp_dst_output() without holding key->lock, so the check-and-set sequence is racy. Example interleaving: CPU0 CPU1 ---- ---- mctp_flow_prepare_output(key, devA) if (!key->dev) // sees NULL mctp_flow_prepare_output( key, devB) if (!key->dev) // still NULL mctp_dev_set_key(devB, key) mctp_dev_hold(devB) key->dev = devB mctp_dev_set_key(devA, key) mctp_dev_hold(devA) key->dev = devA // overwrites devB Now both devA and devB references were acquired, but only the final key->dev value is tracked for release. One reference can be lost, causing a resource leak as mctp_dev_release_key() would only decrease the reference on one dev. Fix by taking key->lock around the key->dev check and mctp_dev_set_key() call. | ||||
| CVE-2026-31425 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 5.5 Medium |
| In the Linux kernel, the following vulnerability has been resolved: rds: ib: reject FRMR registration before IB connection is established rds_ib_get_mr() extracts the rds_ib_connection from conn->c_transport_data and passes it to rds_ib_reg_frmr() for FRWR memory registration. On a fresh outgoing connection, ic is allocated in rds_ib_conn_alloc() with i_cm_id = NULL because the connection worker has not yet called rds_ib_conn_path_connect() to create the rdma_cm_id. When sendmsg() with RDS_CMSG_RDMA_MAP is called on such a connection, the sendmsg path parses the control message before any connection establishment, allowing rds_ib_post_reg_frmr() to dereference ic->i_cm_id->qp and crash the kernel. The existing guard in rds_ib_reg_frmr() only checks for !ic (added in commit 9e630bcb7701), which does not catch this case since ic is allocated early and is always non-NULL once the connection object exists. KASAN: null-ptr-deref in range [0x0000000000000010-0x0000000000000017] RIP: 0010:rds_ib_post_reg_frmr+0x50e/0x920 Call Trace: rds_ib_post_reg_frmr (net/rds/ib_frmr.c:167) rds_ib_map_frmr (net/rds/ib_frmr.c:252) rds_ib_reg_frmr (net/rds/ib_frmr.c:430) rds_ib_get_mr (net/rds/ib_rdma.c:615) __rds_rdma_map (net/rds/rdma.c:295) rds_cmsg_rdma_map (net/rds/rdma.c:860) rds_sendmsg (net/rds/send.c:1363) ____sys_sendmsg do_syscall_64 Add a check in rds_ib_get_mr() that verifies ic, i_cm_id, and qp are all non-NULL before proceeding with FRMR registration, mirroring the guard already present in rds_ib_post_inv(). Return -ENODEV when the connection is not ready, which the existing error handling in rds_cmsg_send() converts to -EAGAIN for userspace retry and triggers rds_conn_connect_if_down() to start the connection worker. | ||||
| CVE-2026-24206 | 2 Linux, Nvidia | 2 Linux Kernel, Triton Inference Server | 2026-05-20 | 7.3 High |
| NVIDIA Triton Inference Server contains a vulnerability where an attacker could cause an authentication bypass. A successful exploit of this vulnerability might lead to escalation of privileges, denial of service, or information disclosure. | ||||
| CVE-2026-24209 | 2 Linux, Nvidia | 2 Linux Kernel, Triton Inference Server | 2026-05-20 | 7.5 High |
| NVIDIA Triton Inference Server contains a vulnerability where an attacker could cause a path traversal issue. A successful exploit of this vulnerability might lead to denial of service. | ||||
| CVE-2026-24210 | 2 Linux, Nvidia | 2 Linux Kernel, Triton Inference Server | 2026-05-20 | 7.5 High |
| NVIDIA Triton Inference Server contains a vulnerability where an attacker could cause an integer overflow. A successful exploit of this vulnerability might lead to denial of service. | ||||
| 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-2026-31410 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 5.5 Medium |
| In the Linux kernel, the following vulnerability has been resolved: ksmbd: use volume UUID in FS_OBJECT_ID_INFORMATION Use sb->s_uuid for a proper volume identifier as the primary choice. For filesystems that do not provide a UUID, fall back to stfs.f_fsid obtained from vfs_statfs(). | ||||
| CVE-2026-43481 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 7.8 High |
| In the Linux kernel, the following vulnerability has been resolved: net-shapers: don't free reply skb after genlmsg_reply() genlmsg_reply() hands the reply skb to netlink, and netlink_unicast() consumes it on all return paths, whether the skb is queued successfully or freed on an error path. net_shaper_nl_get_doit() and net_shaper_nl_cap_get_doit() currently jump to free_msg after genlmsg_reply() fails and call nlmsg_free(msg), which can hit the same skb twice. Return the genlmsg_reply() error directly and keep free_msg only for pre-reply failures. | ||||
| CVE-2026-43380 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 7.8 High |
| In the Linux kernel, the following vulnerability has been resolved: hwmon: (pmbus/q54sj108a2) fix stack overflow in debugfs read The q54sj108a2_debugfs_read function suffers from a stack buffer overflow due to incorrect arguments passed to bin2hex(). The function currently passes 'data' as the destination and 'data_char' as the source. Because bin2hex() converts each input byte into two hex characters, a 32-byte block read results in 64 bytes of output. Since 'data' is only 34 bytes (I2C_SMBUS_BLOCK_MAX + 2), this writes 30 bytes past the end of the buffer onto the stack. Additionally, the arguments were swapped: it was reading from the zero-initialized 'data_char' and writing to 'data', resulting in all-zero output regardless of the actual I2C read. Fix this by: 1. Expanding 'data_char' to 66 bytes to safely hold the hex output. 2. Correcting the bin2hex() argument order and using the actual read count. 3. Using a pointer to select the correct output buffer for the final simple_read_from_buffer call. | ||||
| 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-2026-31412 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 5.5 Medium |
| In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_mass_storage: Fix potential integer overflow in check_command_size_in_blocks() The `check_command_size_in_blocks()` function calculates the data size in bytes by left shifting `common->data_size_from_cmnd` by the block size (`common->curlun->blkbits`). However, it does not validate whether this shift operation will cause an integer overflow. Initially, the block size is set up in `fsg_lun_open()` , and the `common->data_size_from_cmnd` is set up in `do_scsi_command()`. During initialization, there is no integer overflow check for the interaction between two variables. So if a malicious USB host sends a SCSI READ or WRITE command requesting a large amount of data (`common->data_size_from_cmnd`), the left shift operation can wrap around. This results in a truncated data size, which can bypass boundary checks and potentially lead to memory corruption or out-of-bounds accesses. Fix this by using the check_shl_overflow() macro to safely perform the shift and catch any overflows. | ||||
| CVE-2026-31413 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 7.8 High |
| In the Linux kernel, the following vulnerability has been resolved: bpf: Fix unsound scalar forking in maybe_fork_scalars() for BPF_OR maybe_fork_scalars() is called for both BPF_AND and BPF_OR when the source operand is a constant. When dst has signed range [-1, 0], it forks the verifier state: the pushed path gets dst = 0, the current path gets dst = -1. For BPF_AND this is correct: 0 & K == 0. For BPF_OR this is wrong: 0 | K == K, not 0. The pushed path therefore tracks dst as 0 when the runtime value is K, producing an exploitable verifier/runtime divergence that allows out-of-bounds map access. Fix this by passing env->insn_idx (instead of env->insn_idx + 1) to push_stack(), so the pushed path re-executes the ALU instruction with dst = 0 and naturally computes the correct result for any opcode. | ||||
| CVE-2026-23464 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 5.5 Medium |
| In the Linux kernel, the following vulnerability has been resolved: soc: microchip: mpfs: Fix memory leak in mpfs_sys_controller_probe() In mpfs_sys_controller_probe(), if of_get_mtd_device_by_node() fails, the function returns immediately without freeing the allocated memory for sys_controller, leading to a memory leak. Fix this by jumping to the out_free label to ensure the memory is properly freed. Also, consolidate the error handling for the mbox_request_channel() failure case to use the same label. | ||||
| CVE-2026-23465 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 5.5 Medium |
| In the Linux kernel, the following vulnerability has been resolved: btrfs: log new dentries when logging parent dir of a conflicting inode If we log the parent directory of a conflicting inode, we are not logging the new dentries of the directory, so when we finish we have the parent directory's inode marked as logged but we did not log its new dentries. As a consequence if the parent directory is explicitly fsynced later and it does not have any new changes since we logged it, the fsync is a no-op and after a power failure the new dentries are missing. Example scenario: $ mkdir foo $ sync $rmdir foo $ mkdir dir1 $ mkdir dir2 # A file with the same name and parent as the directory we just deleted # and was persisted in a past transaction. So the deleted directory's # inode is a conflicting inode of this new file's inode. $ touch foo $ ln foo dir2/link # The fsync on dir2 will log the parent directory (".") because the # conflicting inode (deleted directory) does not exists anymore, but it # it does not log its new dentries (dir1). $ xfs_io -c "fsync" dir2 # This fsync on the parent directory is no-op, since the previous fsync # logged it (but without logging its new dentries). $ xfs_io -c "fsync" . <power failure> # After log replay dir1 is missing. Fix this by ensuring we log new dir dentries whenever we log the parent directory of a no longer existing conflicting inode. A test case for fstests will follow soon. | ||||