CVE-2022-49781— perf/x86/amd: Fix crash due to race between amd_pmu_enable_all, perf NMI and throttling
Get alerts for future matching vulnerabilitiesLog in to subscribe
I. Basic Information for CVE-2022-49781
Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗ Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.
Vulnerability Title
perf/x86/amd: Fix crash due to race between amd_pmu_enable_all, perf NMI and throttling
Source: NVD (National Vulnerability Database)
Vulnerability Description
In the Linux kernel, the following vulnerability has been resolved: perf/x86/amd: Fix crash due to race between amd_pmu_enable_all, perf NMI and throttling amd_pmu_enable_all() does: if (!test_bit(idx, cpuc->active_mask)) continue; amd_pmu_enable_event(cpuc->events[idx]); A perf NMI of another event can come between these two steps. Perf NMI handler internally disables and enables _all_ events, including the one which nmi-intercepted amd_pmu_enable_all() was in process of enabling. If that unintentionally enabled event has very low sampling period and causes immediate successive NMI, causing the event to be throttled, cpuc->events[idx] and cpuc->active_mask gets cleared by x86_pmu_stop(). This will result in amd_pmu_enable_event() getting called with event=NULL when amd_pmu_enable_all() resumes after handling the NMIs. This causes a kernel crash: BUG: kernel NULL pointer dereference, address: 0000000000000198 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page [...] Call Trace: <TASK> amd_pmu_enable_all+0x68/0xb0 ctx_resched+0xd9/0x150 event_function+0xb8/0x130 ? hrtimer_start_range_ns+0x141/0x4a0 ? perf_duration_warn+0x30/0x30 remote_function+0x4d/0x60 __flush_smp_call_function_queue+0xc4/0x500 flush_smp_call_function_queue+0x11d/0x1b0 do_idle+0x18f/0x2d0 cpu_startup_entry+0x19/0x20 start_secondary+0x121/0x160 secondary_startup_64_no_verify+0xe5/0xeb </TASK> amd_pmu_disable_all()/amd_pmu_enable_all() calls inside perf NMI handler were recently added as part of BRS enablement but I'm not sure whether we really need them. We can just disable BRS in the beginning and enable it back while returning from NMI. This will solve the issue by not enabling those events whose active_masks are set but are not yet enabled in hw pmu.
Source: NVD (National Vulnerability Database)
CVSS Information
N/A
Source: NVD (National Vulnerability Database)
Vulnerability Type
N/A
Source: NVD (National Vulnerability Database)
Vulnerability Title
Linux kernel 安全漏洞
Source: CNNVD (China National Vulnerability Database)
Vulnerability Description
Linux kernel是美国Linux基金会的开源操作系统Linux所使用的内核。 Linux kernel存在安全漏洞，该漏洞源于竞争条件，可能导致空指针解引用。
Source: CNNVD (China National Vulnerability Database)
CVSS Information
N/A
Source: CNNVD (China National Vulnerability Database)
Vulnerability Type
N/A
Source: CNNVD (China National Vulnerability Database)
Affected Products
II. Public POCs for CVE-2022-49781
| # | POC Description | Source Link | Shenlong Link |
|---|
AI-Generated POCPremium
No public POC found.
Login to generate AI POCIII. Intelligence Information for CVE-2022-49781
请登录查看更多情报信息。
Same Patch Batch · Linux · 2025-05-01 · 245 CVEs total
| CVE-2022-49854 | mctp: Fix an error handling path in mctp_init() | |
| CVE-2022-49837 | bpf: Fix memory leaks in __check_func_call | |
| CVE-2022-49838 | sctp: clear out_curr if all frag chunks of current msg are pruned | |
| CVE-2022-49840 | bpf, test_run: Fix alignment problem in bpf_prog_test_run_skb() | |
| CVE-2022-49839 | scsi: scsi_transport_sas: Fix error handling in sas_phy_add() | |
| CVE-2022-49841 | serial: imx: Add missing .thaw_noirq hook | |
| CVE-2022-49842 | ASoC: core: Fix use-after-free in snd_soc_exit() | |
| CVE-2022-49844 | can: dev: fix skb drop check | |
| CVE-2022-49845 | can: j1939: j1939_send_one(): fix missing CAN header initialization | |
| CVE-2022-49846 | udf: Fix a slab-out-of-bounds write bug in udf_find_entry() | |
| CVE-2022-49847 | net: ethernet: ti: am65-cpsw: Fix segmentation fault at module unload | |
| CVE-2022-49849 | btrfs: fix match incorrectly in dev_args_match_device | |
| CVE-2022-49848 | phy: qcom-qmp-combo: fix NULL-deref on runtime resume | |
| CVE-2022-49850 | nilfs2: fix deadlock in nilfs_count_free_blocks() | |
| CVE-2022-49851 | riscv: fix reserved memory setup | |
| CVE-2022-49852 | riscv: process: fix kernel info leakage | |
| CVE-2022-49862 | tipc: fix the msg->req tlv len check in tipc_nl_compat_name_table_dump_header | |
| CVE-2022-49864 | drm/amdkfd: Fix NULL pointer dereference in svm_migrate_to_ram() | |
| CVE-2022-49865 | ipv6: addrlabel: fix infoleak when sending struct ifaddrlblmsg to network | |
| CVE-2022-49863 | can: af_can: fix NULL pointer dereference in can_rx_register() |
Showing top 20 of 245 CVEs. View all on vendor page → →
IV. Related Vulnerabilities
Same product: Linux
- CVE-2026-43490
ksmbd: validate inherited ACE SID length - CVE-2026-43489
liveupdate: luo_file: remember retrieve() status - CVE-2026-43487
ata: libata-core: Disable LPM on ST1000DM010-2EP102 - CVE-2026-43488
usb: xhci: Prevent interrupt storm on host controller error - CVE-2026-43485
nouveau/gsp: drop WARN_ON in ACPI probes
Same vendor: Linux
- CVE-2026-43490
ksmbd: validate inherited ACE SID length - CVE-2026-43489
liveupdate: luo_file: remember retrieve() status - CVE-2026-43487
ata: libata-core: Disable LPM on ST1000DM010-2EP102 - CVE-2026-43488
usb: xhci: Prevent interrupt storm on host controller error - CVE-2026-43485
nouveau/gsp: drop WARN_ON in ACPI probes
V. Comments for CVE-2022-49781
No comments yet