{"dataType":"CVE_RECORD","dataVersion":"5.1","cveMetadata":{"cveId":"CVE-2024-56559","assignerOrgId":"416baaa9-dc9f-4396-8d5f-8c081fb06d67","state":"PUBLISHED","assignerShortName":"Linux","dateReserved":"2024-12-27T14:03:05.993Z","datePublished":"2024-12-27T14:23:04.688Z","dateUpdated":"2025-05-04T09:58:20.171Z"},"containers":{"cna":{"providerMetadata":{"orgId":"416baaa9-dc9f-4396-8d5f-8c081fb06d67","shortName":"Linux","dateUpdated":"2025-05-04T09:58:20.171Z"},"descriptions":[{"lang":"en","value":"In the Linux kernel, the following vulnerability has been resolved:\n\nmm/vmalloc: combine all TLB flush operations of KASAN shadow virtual address into one operation\n\nWhen compiling kernel source 'make -j $(nproc)' with the up-and-running\nKASAN-enabled kernel on a 256-core machine, the following soft lockup is\nshown:\n\nwatchdog: BUG: soft lockup - CPU#28 stuck for 22s! [kworker/28:1:1760]\nCPU: 28 PID: 1760 Comm: kworker/28:1 Kdump: loaded Not tainted 6.10.0-rc5 #95\nWorkqueue: events drain_vmap_area_work\nRIP: 0010:smp_call_function_many_cond+0x1d8/0xbb0\nCode: 38 c8 7c 08 84 c9 0f 85 49 08 00 00 8b 45 08 a8 01 74 2e 48 89 f1 49 89 f7 48 c1 e9 03 41 83 e7 07 4c 01 e9 41 83 c7 03 f3 90 <0f> b6 01 41 38 c7 7c 08 84 c0 0f 85 d4 06 00 00 8b 45 08 a8 01 75\nRSP: 0018:ffffc9000cb3fb60 EFLAGS: 00000202\nRAX: 0000000000000011 RBX: ffff8883bc4469c0 RCX: ffffed10776e9949\nRDX: 0000000000000002 RSI: ffff8883bb74ca48 RDI: ffffffff8434dc50\nRBP: ffff8883bb74ca40 R08: ffff888103585dc0 R09: ffff8884533a1800\nR10: 0000000000000004 R11: ffffffffffffffff R12: ffffed1077888d39\nR13: dffffc0000000000 R14: ffffed1077888d38 R15: 0000000000000003\nFS: 0000000000000000(0000) GS:ffff8883bc400000(0000) knlGS:0000000000000000\nCS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033\nCR2: 00005577b5c8d158 CR3: 0000000004850000 CR4: 0000000000350ef0\nCall Trace:\n \n ? watchdog_timer_fn+0x2cd/0x390\n ? __pfx_watchdog_timer_fn+0x10/0x10\n ? __hrtimer_run_queues+0x300/0x6d0\n ? sched_clock_cpu+0x69/0x4e0\n ? __pfx___hrtimer_run_queues+0x10/0x10\n ? srso_return_thunk+0x5/0x5f\n ? ktime_get_update_offsets_now+0x7f/0x2a0\n ? srso_return_thunk+0x5/0x5f\n ? srso_return_thunk+0x5/0x5f\n ? hrtimer_interrupt+0x2ca/0x760\n ? __sysvec_apic_timer_interrupt+0x8c/0x2b0\n ? sysvec_apic_timer_interrupt+0x6a/0x90\n \n \n ? asm_sysvec_apic_timer_interrupt+0x16/0x20\n ? smp_call_function_many_cond+0x1d8/0xbb0\n ? __pfx_do_kernel_range_flush+0x10/0x10\n on_each_cpu_cond_mask+0x20/0x40\n flush_tlb_kernel_range+0x19b/0x250\n ? srso_return_thunk+0x5/0x5f\n ? kasan_release_vmalloc+0xa7/0xc0\n purge_vmap_node+0x357/0x820\n ? __pfx_purge_vmap_node+0x10/0x10\n __purge_vmap_area_lazy+0x5b8/0xa10\n drain_vmap_area_work+0x21/0x30\n process_one_work+0x661/0x10b0\n worker_thread+0x844/0x10e0\n ? srso_return_thunk+0x5/0x5f\n ? __kthread_parkme+0x82/0x140\n ? __pfx_worker_thread+0x10/0x10\n kthread+0x2a5/0x370\n ? __pfx_kthread+0x10/0x10\n ret_from_fork+0x30/0x70\n ? __pfx_kthread+0x10/0x10\n ret_from_fork_asm+0x1a/0x30\n \n\nDebugging Analysis:\n\n 1. The following ftrace log shows that the lockup CPU spends too much\n time iterating vmap_nodes and flushing TLB when purging vm_area\n structures. (Some info is trimmed).\n\n kworker: funcgraph_entry: | drain_vmap_area_work() {\n kworker: funcgraph_entry: | mutex_lock() {\n kworker: funcgraph_entry: 1.092 us | __cond_resched();\n kworker: funcgraph_exit: 3.306 us | }\n ... ...\n kworker: funcgraph_entry: | flush_tlb_kernel_range() {\n ... ...\n kworker: funcgraph_exit: # 7533.649 us | }\n ... ...\n kworker: funcgraph_entry: 2.344 us | mutex_unlock();\n kworker: funcgraph_exit: $ 23871554 us | }\n\n The drain_vmap_area_work() spends over 23 seconds.\n\n There are 2805 flush_tlb_kernel_range() calls in the ftrace log.\n * One is called in __purge_vmap_area_lazy().\n * Others are called by purge_vmap_node->kasan_release_vmalloc.\n purge_vmap_node() iteratively releases kasan vmalloc\n allocations and flushes TLB for each vmap_area.\n - [Rough calculation] Each flush_tlb_kernel_range() runs\n about 7.5ms.\n -- 2804 * 7.5ms = 21.03 seconds.\n -- That's why a soft lock is triggered.\n\n 2. Extending the soft lockup time can work around the issue (For example,\n # echo\n---truncated---"}],"affected":[{"product":"Linux","vendor":"Linux","defaultStatus":"unaffected","repo":"https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git","programFiles":["include/linux/kasan.h","mm/kasan/shadow.c","mm/vmalloc.c"],"versions":[{"version":"282631cb2447318e2a55b41a665dbe8571c46d70","lessThan":"f9a18889aad9b4c19c6c4550c67ad4f9ed2a354f","status":"affected","versionType":"git"},{"version":"282631cb2447318e2a55b41a665dbe8571c46d70","lessThan":"9e9e085effe9b7e342138fde3cf8577d22509932","status":"affected","versionType":"git"}]},{"product":"Linux","vendor":"Linux","defaultStatus":"affected","repo":"https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git","programFiles":["include/linux/kasan.h","mm/kasan/shadow.c","mm/vmalloc.c"],"versions":[{"version":"6.9","status":"affected"},{"version":"0","lessThan":"6.9","status":"unaffected","versionType":"semver"},{"version":"6.12.4","lessThanOrEqual":"6.12.*","status":"unaffected","versionType":"semver"},{"version":"6.13","lessThanOrEqual":"*","status":"unaffected","versionType":"original_commit_for_fix"}]}],"cpeApplicability":[{"nodes":[{"operator":"OR","negate":false,"cpeMatch":[{"vulnerable":true,"criteria":"cpe:2.3:o:linux:linux_kernel:*:*:*:*:*:*:*:*","versionStartIncluding":"6.9","versionEndExcluding":"6.12.4"},{"vulnerable":true,"criteria":"cpe:2.3:o:linux:linux_kernel:*:*:*:*:*:*:*:*","versionStartIncluding":"6.9","versionEndExcluding":"6.13"}]}]}],"references":[{"url":"https://git.kernel.org/stable/c/f9a18889aad9b4c19c6c4550c67ad4f9ed2a354f"},{"url":"https://git.kernel.org/stable/c/9e9e085effe9b7e342138fde3cf8577d22509932"}],"title":"mm/vmalloc: combine all TLB flush operations of KASAN shadow virtual address into one operation","x_generator":{"engine":"bippy-1.2.0"}}}}