mirror of
https://github.com/torvalds/linux.git
synced 2026-08-03 05:44:14 +02:00
3163f635b2
Warning happened in rb_end_commit() at code:
if (RB_WARN_ON(cpu_buffer, !local_read(&cpu_buffer->committing)))
WARNING: CPU: 0 PID: 139 at kernel/trace/ring_buffer.c:3142
rb_commit+0x402/0x4a0
Call Trace:
ring_buffer_unlock_commit+0x42/0x250
trace_buffer_unlock_commit_regs+0x3b/0x250
trace_event_buffer_commit+0xe5/0x440
trace_event_buffer_reserve+0x11c/0x150
trace_event_raw_event_sched_switch+0x23c/0x2c0
__traceiter_sched_switch+0x59/0x80
__schedule+0x72b/0x1580
schedule+0x92/0x120
worker_thread+0xa0/0x6f0
It is because the race between writing event into cpu buffer and swapping
cpu buffer through file per_cpu/cpu0/snapshot:
Write on CPU 0 Swap buffer by per_cpu/cpu0/snapshot on CPU 1
-------- --------
tracing_snapshot_write()
[...]
ring_buffer_lock_reserve()
cpu_buffer = buffer->buffers[cpu]; // 1. Suppose find 'cpu_buffer_a';
[...]
rb_reserve_next_event()
[...]
ring_buffer_swap_cpu()
if (local_read(&cpu_buffer_a->committing))
goto out_dec;
if (local_read(&cpu_buffer_b->committing))
goto out_dec;
buffer_a->buffers[cpu] = cpu_buffer_b;
buffer_b->buffers[cpu] = cpu_buffer_a;
// 2. cpu_buffer has swapped here.
rb_start_commit(cpu_buffer);
if (unlikely(READ_ONCE(cpu_buffer->buffer)
!= buffer)) { // 3. This check passed due to 'cpu_buffer->buffer'
[...] // has not changed here.
return NULL;
}
cpu_buffer_b->buffer = buffer_a;
cpu_buffer_a->buffer = buffer_b;
[...]
// 4. Reserve event from 'cpu_buffer_a'.
ring_buffer_unlock_commit()
[...]
cpu_buffer = buffer->buffers[cpu]; // 5. Now find 'cpu_buffer_b' !!!
rb_commit(cpu_buffer)
rb_end_commit() // 6. WARN for the wrong 'committing' state !!!
Based on above analysis, we can easily reproduce by following testcase:
``` bash
#!/bin/bash
dmesg -n 7
sysctl -w kernel.panic_on_warn=1
TR=/sys/kernel/tracing
echo 7 > ${TR}/buffer_size_kb
echo "sched:sched_switch" > ${TR}/set_event
while [ true ]; do
echo 1 > ${TR}/per_cpu/cpu0/snapshot
done &
while [ true ]; do
echo 1 > ${TR}/per_cpu/cpu0/snapshot
done &
while [ true ]; do
echo 1 > ${TR}/per_cpu/cpu0/snapshot
done &
```
To fix it, IIUC, we can use smp_call_function_single() to do the swap on
the target cpu where the buffer is located, so that above race would be
avoided.
Link: https://lore.kernel.org/linux-trace-kernel/20230831132739.4070878-1-zhengyejian1@huawei.com
Cc: <mhiramat@kernel.org>
Fixes:
|
||
|---|---|---|
| .. | ||
| rv | ||
| blktrace.c | ||
| bpf_trace.c | ||
| bpf_trace.h | ||
| error_report-traces.c | ||
| fgraph.c | ||
| fprobe.c | ||
| ftrace_internal.h | ||
| ftrace.c | ||
| Kconfig | ||
| kprobe_event_gen_test.c | ||
| Makefile | ||
| pid_list.c | ||
| pid_list.h | ||
| power-traces.c | ||
| preemptirq_delay_test.c | ||
| rethook.c | ||
| ring_buffer_benchmark.c | ||
| ring_buffer.c | ||
| rpm-traces.c | ||
| synth_event_gen_test.c | ||
| trace_benchmark.c | ||
| trace_benchmark.h | ||
| trace_boot.c | ||
| trace_branch.c | ||
| trace_clock.c | ||
| trace_dynevent.c | ||
| trace_dynevent.h | ||
| trace_entries.h | ||
| trace_eprobe.c | ||
| trace_event_perf.c | ||
| trace_events_filter_test.h | ||
| trace_events_filter.c | ||
| trace_events_hist.c | ||
| trace_events_inject.c | ||
| trace_events_synth.c | ||
| trace_events_trigger.c | ||
| trace_events_user.c | ||
| trace_events.c | ||
| trace_export.c | ||
| trace_fprobe.c | ||
| trace_functions_graph.c | ||
| trace_functions.c | ||
| trace_hwlat.c | ||
| trace_irqsoff.c | ||
| trace_kdb.c | ||
| trace_kprobe_selftest.c | ||
| trace_kprobe_selftest.h | ||
| trace_kprobe.c | ||
| trace_mmiotrace.c | ||
| trace_nop.c | ||
| trace_osnoise.c | ||
| trace_output.c | ||
| trace_output.h | ||
| trace_preemptirq.c | ||
| trace_printk.c | ||
| trace_probe_kernel.h | ||
| trace_probe_tmpl.h | ||
| trace_probe.c | ||
| trace_probe.h | ||
| trace_recursion_record.c | ||
| trace_sched_switch.c | ||
| trace_sched_wakeup.c | ||
| trace_selftest_dynamic.c | ||
| trace_selftest.c | ||
| trace_seq.c | ||
| trace_stack.c | ||
| trace_stat.c | ||
| trace_stat.h | ||
| trace_synth.h | ||
| trace_syscalls.c | ||
| trace_uprobe.c | ||
| trace.c | ||
| trace.h | ||
| tracing_map.c | ||
| tracing_map.h | ||