KCSAN: data-race in bpf_prog_run_clear_cb / tracing_gen_ctx_irq_test

Status: moderation: reported on 2026/11/20 00:00
Subsystems: trace
Labels: race:benign prio:high
[Documentation on labels]
Reported-by: syzbot+a6f6c19c5a5b62f4363a@syzkaller.appspotmail.com
First crash: 2d22h, last: 2d10h
✨ AI-generated root cause summary:

A data race occurs on the 2-byte field task_struct::migration_disabled between an unmarked plain read in the tracing subsystem and an unmarked plain write in migrate_disable(). While a task running on CPU 1 executes tracing_gen_ctx_irq_test() with interrupts enabled, migration_disable_value() performs an unannotated read of current->migration_disabled. Concurrently on the same CPU, an APIC timer interrupt invokes softirq packet processing that executes a BPF socket filter, calling bpf_prog_run_pin_on_cpu() and inlined __migrate_disable(), which performs an unannotated write to the interrupted task's migration_disabled field. Because kernel/sched/Makefile disables KCSAN for sched core files, the race was exposed through the inlined definition of __migrate_disable() in include/linux/sched.h and the unannotated access in kernel/trace/trace.c.

▶ ▼ ✨ Full AI root cause analysis
Based on kernel commit 666539eecdf4:

Root Cause Analysis

Involved Functions, Structs, Fields, and Files


Technical Mechanism & Failure Breakdown

  1. Task-Context Read Path:

    • In kernel/trace/trace.c, tracing_gen_ctx() is invoked during trace event logging (in this instance, trace_syscall_exit()).
    • tracing_gen_ctx() calls local_save_flags() to record local interrupt flags without disabling local IRQs, and passes the status to tracing_gen_ctx_irq_test().
    • tracing_gen_ctx_irq_test() calls migration_disable_value(), which performs an unmarked, plain memory read:
      static unsigned short migration_disable_value(void)
      {
      #if defined(CONFIG_SMP)
          return current->migration_disabled;
      #else
          return 0;
      #endif
      }
      
    • Because interrupts remain enabled during this read, the CPU is subject to asynchronous interrupts. When KCSAN instruments this read, it sets up a watchpoint on &current->migration_disabled (0xffff8881035bc978) and inserts a microsecond delay (delay_access()).
  2. Interrupt / Softirq Write Path:

    • While the task on CPU 1 is delayed in KCSAN's watchpoint, an APIC timer interrupt occurs on the same CPU (sysvec_apic_timer_interrupt).
    • On interrupt exit (__irq_exit_rcu()), the kernel invokes pending softirqs (run_timer_softirq), executing the TCP delayed-ACK timer handler (tcp_delack_timer()).
    • The transmitted packet is copied to packet sockets via dev_queue_xmit_nit() -> packet_rcv().
    • In af_packet.c, run_filter() runs attached BPF filters by calling bpf_prog_run_clear_cb() -> bpf_prog_run_pin_on_cpu().
    • bpf_prog_run_pin_on_cpu() explicitly calls migrate_disable() to pin execution to the current CPU during BPF filter execution.
    • Because the softirq executes in the context of the interrupted task, current remains the interrupted task (Task 7698).
    • In __migrate_disable() (include/linux/sched.h:2496), the code performs an unmarked write:
      p->migration_disabled = 1;
      
      This write targets 0xffff8881035bc978 (the exact address monitored by KCSAN's read watchpoint on the same CPU).
    • Once BPF execution completes, migrate_enable() -> __migrate_enable() resets p->migration_disabled = 0, restoring the original state before the interrupt completes and returns to the interrupted task context.
  3. Instrumentation & LKMM Concurrency Violation:

    • While out-of-line scheduler core files in kernel/sched/ compile with KCSAN_SANITIZE := n, __migrate_disable() and __migrate_enable() are defined static inline in include/linux/sched.h. Consequently, when callers outside kernel/sched/ (such as net/packet/af_packet.c via include/linux/filter.h) inline them, KCSAN instrumentation is active.
    • p->migration_disabled is read and modified concurrently across contexts (and across CPUs by scheduler helpers like is_migration_disabled() and get_push_task()) using plain C load/store instructions without READ_ONCE(), WRITE_ONCE(), or data_race() annotations.
▶ ▼ ✨ AI Jobs (2)
ID Workflow Result Correct Bug Created Started Finished Revision
06a0421c assessment-security DenialOfService: ❌ Exploitable: ❌ FilesystemTrigger: ❌ FuzzingArtifact: ❌ MemoryCorruption: ❌ NetworkNeedsSetup: ✅ NetworkTrigger: ✅ PeripheralTrigger: ❌ RemoteTrigger: ✅ Unprivileged: ✅ UserNamespace: ✅ VMGuestTrigger: ❌ VMHostTrigger: ❌ ❓ KCSAN: data-race in bpf_prog_run_clear_cb / tracing_gen_ctx_irq_test 2026/11/19 02:48 2026/11/19 02:48 2026/11/19 03:14 2006bdcc
92867882 assessment-kcsan Benign: ✅ ❓ KCSAN: data-race in bpf_prog_run_clear_cb / tracing_gen_ctx_irq_test 2026/11/19 02:47 2026/11/19 02:47 2026/11/19 03:13 2006bdcc

Sample crash report:
==================================================================
BUG: KCSAN: data-race in bpf_prog_run_clear_cb / tracing_gen_ctx_irq_test

write to 0xffff8881035bc978 of 2 bytes by interrupt on cpu 1:
 __migrate_disable include/linux/sched.h:2496 [inline]
 migrate_disable include/linux/sched.h:2512 [inline]
 bpf_prog_run_pin_on_cpu include/linux/filter.h:836 [inline]
 bpf_prog_run_clear_cb+0xb3/0x290 include/linux/filter.h:1119
 run_filter net/packet/af_packet.c:2111 [inline]
 packet_rcv+0x26e/0xba0 net/packet/af_packet.c:2184
 dev_queue_xmit_nit+0x4c4/0x510 net/core/dev.c:2678
 xmit_one net/core/dev.c:4064 [inline]
 dev_hard_start_xmit+0xb5/0x3d0 net/core/dev.c:4084
 sch_direct_xmit+0x1c4/0x360 net/sched/sch_generic.c:411
 __dev_xmit_skb net/core/dev.c:4419 [inline]
 __dev_queue_xmit+0xe7d/0x2020 net/core/dev.c:5058
 dev_queue_xmit include/linux/netdevice.h:3485 [inline]
 neigh_hh_output include/net/neighbour.h:538 [inline]
 neigh_output include/net/neighbour.h:552 [inline]
 ip_finish_output2+0x845/0x920 net/ipv4/ip_output.c:236
 __ip_finish_output net/ipv4/ip_output.c:-1 [inline]
 ip_finish_output+0x112/0x290 net/ipv4/ip_output.c:324
 NF_HOOK_COND include/linux/netfilter.h:314 [inline]
 ip_output+0xbd/0x1c0 net/ipv4/ip_output.c:437
 dst_output include/net/dst.h:472 [inline]
 ip_local_out net/ipv4/ip_output.c:131 [inline]
 __ip_queue_xmit+0xbf3/0xc30 net/ipv4/ip_output.c:533
 ip_queue_xmit+0x39/0x50 net/ipv4/ip_output.c:547
 __tcp_transmit_skb+0x1cad/0x2110 net/ipv4/tcp_output.c:1773
 __tcp_send_ack+0x288/0x3b0 net/ipv4/tcp_output.c:4577
 tcp_send_ack+0x29/0x30 net/ipv4/tcp_output.c:4583
 tcp_delack_timer_handler+0x238/0x270 net/ipv4/tcp_timer.c:347
 tcp_delack_timer+0x11d/0x230 net/ipv4/tcp_timer.c:378
 call_timer_fn+0x36/0x280 kernel/time/timer.c:1749
 expire_timers kernel/time/timer.c:1800 [inline]
 __run_timers kernel/time/timer.c:2375 [inline]
 __run_timer_base+0x40c/0x610 kernel/time/timer.c:2387
 run_timer_base kernel/time/timer.c:2396 [inline]
 run_timer_softirq+0x31/0x70 kernel/time/timer.c:2406
 handle_softirqs+0x109/0x310 kernel/softirq.c:669
 __do_softirq kernel/softirq.c:703 [inline]
 invoke_softirq kernel/softirq.c:542 [inline]
 __irq_exit_rcu+0x40/0xf0 kernel/softirq.c:786
 instr_sysvec_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1062 [inline]
 sysvec_apic_timer_interrupt+0x74/0x80 arch/x86/kernel/apic/apic.c:1062
 asm_sysvec_apic_timer_interrupt+0x1a/0x20 arch/x86/include/asm/idtentry.h:674
 rdtsc_ordered arch/x86/include/asm/tsc.h:57 [inline]
 delay_tsc+0x5b/0xa0 arch/x86/lib/delay.c:70
 udelay include/asm-generic/delay.h:64 [inline]
 delay_access kernel/kcsan/core.c:332 [inline]
 kcsan_setup_watchpoint+0x255/0x3f0 kernel/kcsan/core.c:622
 migration_disable_value kernel/trace/trace.c:1718 [inline]
 tracing_gen_ctx_irq_test+0xdd/0x110 kernel/trace/trace.c:1747
 tracing_gen_ctx_flags include/linux/trace_events.h:204 [inline]
 tracing_gen_ctx include/linux/trace_events.h:211 [inline]
 tracing_gen_ctx_dec include/linux/trace_events.h:218 [inline]
 trace_event_buffer_reserve+0xe4/0x180 kernel/trace/trace_events.c:720
 do_trace_event_raw_event_sys_exit include/trace/events/syscalls.h:44 [inline]
 trace_event_raw_event_sys_exit+0x60/0xf0 include/trace/events/syscalls.h:44
 __do_trace_sys_exit include/trace/events/syscalls.h:44 [inline]
 trace_sys_exit include/trace/events/syscalls.h:44 [inline]
 trace_syscall_exit+0xc2/0x120 kernel/entry/syscall-common.c:18
 syscall_exit_work include/linux/entry-common.h:269 [inline]
 syscall_exit_to_user_mode_work include/linux/entry-common.h:304 [inline]
 syscall_exit_to_user_mode include/linux/entry-common.h:341 [inline]
 do_syscall_64+0x361/0x3a0 arch/x86/entry/syscall_64.c:107
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

read to 0xffff8881035bc978 of 2 bytes by task 7698 on cpu 1:
 migration_disable_value kernel/trace/trace.c:1718 [inline]
 tracing_gen_ctx_irq_test+0xdd/0x110 kernel/trace/trace.c:1747
 tracing_gen_ctx_flags include/linux/trace_events.h:204 [inline]
 tracing_gen_ctx include/linux/trace_events.h:211 [inline]
 tracing_gen_ctx_dec include/linux/trace_events.h:218 [inline]
 trace_event_buffer_reserve+0xe4/0x180 kernel/trace/trace_events.c:720
 do_trace_event_raw_event_sys_exit include/trace/events/syscalls.h:44 [inline]
 trace_event_raw_event_sys_exit+0x60/0xf0 include/trace/events/syscalls.h:44
 __do_trace_sys_exit include/trace/events/syscalls.h:44 [inline]
 trace_sys_exit include/trace/events/syscalls.h:44 [inline]
 trace_syscall_exit+0xc2/0x120 kernel/entry/syscall-common.c:18
 syscall_exit_work include/linux/entry-common.h:269 [inline]
 syscall_exit_to_user_mode_work include/linux/entry-common.h:304 [inline]
 syscall_exit_to_user_mode include/linux/entry-common.h:341 [inline]
 do_syscall_64+0x361/0x3a0 arch/x86/entry/syscall_64.c:107
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Reported by Kernel Concurrency Sanitizer on:
CPU: 1 UID: 0 PID: 7698 Comm: dhcpcd-run-hook Not tainted syzkaller #0 PREEMPT(lazy) 
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 11/06/2026
==================================================================

Crashes (25):
Time Kernel Commit Syzkaller Config Log Report Syz repro C repro VM info Assets (help?) Manager Title
2026/11/17 14:40 upstream 666539eecdf4 43af6cac .config console log report info [disk image] [vmlinux] [kernel image] ci2-upstream-kcsan-gce KCSAN: data-race in bpf_prog_run_clear_cb / tracing_gen_ctx_irq_test
2026/11/17 14:39 upstream 666539eecdf4 43af6cac .config console log report info [disk image] [vmlinux] [kernel image] ci2-upstream-kcsan-gce KCSAN: data-race in bpf_prog_run_clear_cb / tracing_gen_ctx_irq_test
2026/11/17 14:38 upstream 666539eecdf4 43af6cac .config console log report info [disk image] [vmlinux] [kernel image] ci2-upstream-kcsan-gce KCSAN: data-race in bpf_prog_run_clear_cb / tracing_gen_ctx_irq_test
2026/11/17 14:38 upstream 666539eecdf4 43af6cac .config console log report info [disk image] [vmlinux] [kernel image] ci2-upstream-kcsan-gce KCSAN: data-race in bpf_prog_run_clear_cb / tracing_gen_ctx_irq_test
2026/11/17 14:38 upstream 666539eecdf4 43af6cac .config console log report info [disk image] [vmlinux] [kernel image] ci2-upstream-kcsan-gce KCSAN: data-race in bpf_prog_run_clear_cb / tracing_gen_ctx_irq_test
2026/11/17 14:38 upstream 666539eecdf4 43af6cac .config console log report info [disk image] [vmlinux] [kernel image] ci2-upstream-kcsan-gce KCSAN: data-race in bpf_prog_run_clear_cb / tracing_gen_ctx_irq_test
2026/11/17 14:37 upstream 666539eecdf4 43af6cac .config console log report info [disk image] [vmlinux] [kernel image] ci2-upstream-kcsan-gce KCSAN: data-race in bpf_prog_run_clear_cb / tracing_gen_ctx_irq_test
2026/11/17 14:17 upstream 666539eecdf4 43af6cac .config console log report info [disk image] [vmlinux] [kernel image] ci2-upstream-kcsan-gce KCSAN: data-race in bpf_prog_run_clear_cb / tracing_gen_ctx_irq_test
2026/11/17 13:33 upstream 666539eecdf4 43af6cac .config console log report info [disk image] [vmlinux] [kernel image] ci2-upstream-kcsan-gce KCSAN: data-race in bpf_prog_run_clear_cb / tracing_gen_ctx_irq_test
2026/11/17 13:33 upstream 666539eecdf4 43af6cac .config console log report info [disk image] [vmlinux] [kernel image] ci2-upstream-kcsan-gce KCSAN: data-race in bpf_prog_run_clear_cb / tracing_gen_ctx_irq_test
2026/11/17 13:32 upstream 666539eecdf4 43af6cac .config console log report info [disk image] [vmlinux] [kernel image] ci2-upstream-kcsan-gce KCSAN: data-race in bpf_prog_run_clear_cb / tracing_gen_ctx_irq_test
2026/11/17 11:28 upstream 666539eecdf4 43af6cac .config console log report info [disk image] [vmlinux] [kernel image] ci2-upstream-kcsan-gce KCSAN: data-race in bpf_prog_run_clear_cb / tracing_gen_ctx_irq_test
2026/11/17 11:27 upstream 666539eecdf4 43af6cac .config console log report info [disk image] [vmlinux] [kernel image] ci2-upstream-kcsan-gce KCSAN: data-race in bpf_prog_run_clear_cb / tracing_gen_ctx_irq_test
2026/11/17 11:07 upstream 666539eecdf4 43af6cac .config console log report info [disk image] [vmlinux] [kernel image] ci2-upstream-kcsan-gce KCSAN: data-race in bpf_prog_run_clear_cb / tracing_gen_ctx_irq_test
2026/11/17 08:08 upstream 666539eecdf4 a3e64cfc .config console log report info [disk image] [vmlinux] [kernel image] ci2-upstream-kcsan-gce KCSAN: data-race in bpf_prog_run_clear_cb / tracing_gen_ctx_irq_test
2026/11/17 05:49 upstream 666539eecdf4 a3e64cfc .config console log report info [disk image] [vmlinux] [kernel image] ci2-upstream-kcsan-gce KCSAN: data-race in bpf_prog_run_clear_cb / tracing_gen_ctx_irq_test
2026/11/17 05:49 upstream 666539eecdf4 a3e64cfc .config console log report info [disk image] [vmlinux] [kernel image] ci2-upstream-kcsan-gce KCSAN: data-race in bpf_prog_run_clear_cb / tracing_gen_ctx_irq_test
2026/11/17 05:48 upstream 666539eecdf4 a3e64cfc .config console log report info [disk image] [vmlinux] [kernel image] ci2-upstream-kcsan-gce KCSAN: data-race in bpf_prog_run_clear_cb / tracing_gen_ctx_irq_test
2026/11/17 05:48 upstream 666539eecdf4 a3e64cfc .config console log report info [disk image] [vmlinux] [kernel image] ci2-upstream-kcsan-gce KCSAN: data-race in bpf_prog_run_clear_cb / tracing_gen_ctx_irq_test
2026/11/17 05:47 upstream 666539eecdf4 a3e64cfc .config console log report info [disk image] [vmlinux] [kernel image] ci2-upstream-kcsan-gce KCSAN: data-race in bpf_prog_run_clear_cb / tracing_gen_ctx_irq_test
2026/11/17 04:59 upstream 666539eecdf4 a3e64cfc .config console log report info [disk image] [vmlinux] [kernel image] ci2-upstream-kcsan-gce KCSAN: data-race in bpf_prog_run_clear_cb / tracing_gen_ctx_irq_test
2026/11/17 03:20 upstream 666539eecdf4 a3e64cfc .config console log report info [disk image] [vmlinux] [kernel image] ci2-upstream-kcsan-gce KCSAN: data-race in bpf_prog_run_clear_cb / tracing_gen_ctx_irq_test
2026/11/17 02:53 upstream 666539eecdf4 a3e64cfc .config console log report info [disk image] [vmlinux] [kernel image] ci2-upstream-kcsan-gce KCSAN: data-race in bpf_prog_run_clear_cb / tracing_gen_ctx_irq_test
2026/11/17 02:27 upstream 666539eecdf4 a3e64cfc .config console log report info [disk image] [vmlinux] [kernel image] ci2-upstream-kcsan-gce KCSAN: data-race in bpf_prog_run_clear_cb / tracing_gen_ctx_irq_test
2026/11/17 02:25 upstream 666539eecdf4 a3e64cfc .config console log report info [disk image] [vmlinux] [kernel image] ci2-upstream-kcsan-gce KCSAN: data-race in bpf_prog_run_clear_cb / tracing_gen_ctx_irq_test
* Struck through repros no longer work on HEAD.