With CONFIG_DEBUG_PREEMPT we observed reports like: BUG: using smp_processor_id() in preemptible caller is perf_ftrace_function_call+0x6f/0x2e0 CPU: 1 PID: 680 Comm: a.out Not tainted Call Trace: <TASK> dump_stack_lvl+0x8d/0xcf check_preemption_disabled+0x104/0x110 ? optimize_nops.isra.7+0x230/0x230 ? text_poke_bp_batch+0x9f/0x310 perf_ftrace_function_call+0x6f/0x2e0 ... __text_poke+0x5/0x620 text_poke_bp_batch+0x9f/0x310 This telling us the CPU could be changed after task is preempted, and the checking on CPU before preemption will be invalid. Since now ftrace_test_recursion_trylock() will help to disable the preemption, this patch just do the checking after trylock() to address the issue. CC: Steven Rostedt <rostedt@xxxxxxxxxxx> Reported-by: Abaci <abaci@xxxxxxxxxxxxxxxxx> Signed-off-by: Michael Wang <yun.wang@xxxxxxxxxxxxxxxxx> --- kernel/trace/trace_event_perf.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 6aed10e..fba8cb7 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -441,13 +441,13 @@ void perf_trace_buf_update(void *record, u16 type) if (!rcu_is_watching()) return; - if ((unsigned long)ops->private != smp_processor_id()) - return; - bit = ftrace_test_recursion_trylock(ip, parent_ip); if (bit < 0) return; + if ((unsigned long)ops->private != smp_processor_id()) + goto out; + event = container_of(ops, struct perf_event, ftrace_ops); /* -- 1.8.3.1
