A few functions are in the call chain of rcu_momentary_dyntick_idle()
which is executed in multi_cpu_stop() and marked notrace. They are running
in traced when ftrace modify code. This may cause non-ftrace_modify_code
CPUs stall:
[ 72.686113] rcu: INFO: rcu_preempt detected stalls on CPUs/tasks:
[ 72.687344] rcu: 1-...!: (0 ticks this GP) idle=14f/1/0x4000000000000000 softirq=3397/3397 fqs=0
[ 72.687800] rcu: 3-...!: (0 ticks this GP) idle=ee9/1/0x4000000000000000 softirq=5168/5168 fqs=0
[ 72.688280] (detected by 0, t=8137 jiffies, g=5889, q=2 ncpus=4)
[ 72.688739] Task dump for CPU 1:
[ 72.688991] task:migration/1 state:R running task stack: 0 pid: 19 ppid: 2 flags:0x00000000
[ 72.689594] Stopper: multi_cpu_stop+0x0/0x18c <- stop_machine_cpuslocked+0x128/0x174
[ 72.690242] Call Trace:
[ 72.690603] Task dump for CPU 3:
[ 72.690761] task:migration/3 state:R running task stack: 0 pid: 29 ppid: 2 flags:0x00000000
[ 72.691135] Stopper: multi_cpu_stop+0x0/0x18c <- stop_machine_cpuslocked+0x128/0x174
[ 72.691474] Call Trace:
[ 72.691733] rcu: rcu_preempt kthread timer wakeup didn't happen for 8136 jiffies! g5889 f0x0 RCU_GP_WAIT_FQS(5) ->state=0x402
[ 72.692180] rcu: Possible timer handling issue on cpu=2 timer-softirq=594
[ 72.692485] rcu: rcu_preempt kthread starved for 8137 jiffies! g5889 f0x0 RCU_GP_WAIT_FQS(5) ->state=0x402 ->cpu=2
[ 72.692876] rcu: Unless rcu_preempt kthread gets sufficient CPU time, OOM is now expected behavior.
[ 72.693232] rcu: RCU grace-period kthread stack dump:
[ 72.693433] task:rcu_preempt state:I stack: 0 pid: 14 ppid: 2 flags:0x00000000
[ 72.693788] Call Trace:
[ 72.694018] [<ffffffff807f3740>] schedule+0x56/0xc2
[ 72.694306] [<ffffffff807f9cd8>] schedule_timeout+0x82/0x184
[ 72.694539] [<ffffffff8007c456>] rcu_gp_fqs_loop+0x19a/0x318
[ 72.694809] [<ffffffff8007e408>] rcu_gp_kthread+0x11a/0x140
[ 72.695325] [<ffffffff800324d6>] kthread+0xee/0x118
[ 72.695657] [<ffffffff8000398a>] ret_from_exception+0x0/0x14
[ 72.696089] rcu: Stack dump where RCU GP kthread last ran:
[ 72.696383] Task dump for CPU 2:
[ 72.696562] task:migration/2 state:R running task stack: 0 pid: 24 ppid: 2 flags:0x00000000
[ 72.697059] Stopper: multi_cpu_stop+0x0/0x18c <- stop_machine_cpuslocked+0x128/0x174
[ 72.697471] Call Trace:
Mark rcu_preempt_deferred_qs(), rcu_preempt_need_deferred_qs() and
rcu_preempt_deferred_qs_irqrestore() notrace to avoid this.
Signed-off-by: Patrick Wang <patrick.wang.shcn@xxxxxxxxx>
---
kernel/rcu/tree_plugin.h | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index c3d212bc5338..07b3e656aedd 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -460,7 +460,7 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp)
* be quite short, for example, in the case of the call from
* rcu_read_unlock_special().
*/
-static void
+notrace static void
rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags)
{
bool empty_exp;
@@ -581,7 +581,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags)
* is disabled. This function cannot be expected to understand these
* nuances, so the caller must handle them.
*/
-static bool rcu_preempt_need_deferred_qs(struct task_struct *t)
+notrace static bool rcu_preempt_need_deferred_qs(struct task_struct *t)
{
return (__this_cpu_read(rcu_data.cpu_no_qs.b.exp) ||
READ_ONCE(t->rcu_read_unlock_special.s)) &&
@@ -595,7 +595,7 @@ static bool rcu_preempt_need_deferred_qs(struct task_struct *t)
* evaluate safety in terms of interrupt, softirq, and preemption
* disabling.
*/
-static void rcu_preempt_deferred_qs(struct task_struct *t)
+notrace static void rcu_preempt_deferred_qs(struct task_struct *t)
{
unsigned long flags;
--
2.25.1
