Re: [REGRESSION] CPUIDLE_FLAG_RCU_IDLE, blk_mq_freeze_queue_wait() and slow-stuck reboots

[Peter Zijlstra]

On Wed, Mar 15, 2023 at 12:16:06PM +0100, Peter Zijlstra wrote:

> So ARM has a weird 'rule' in that idle state 0 (wfi) should not have
> RCU_IDLE set, while others should have.
> 
> Of the dt_init_idle_driver() users:
> 
>  - cpuidle-arm: arm_enter_idle_state()
>  - cpuidle-big_little: bl_enter_powerdown() does ct_cpuidle_{enter,exit}()
>  - cpuidle-psci: psci_enter_idle_state() uses CPU_PM_CPU_IDLE_ENTER_PARAM_RCU()
>  - cpuidle-qcom-spm: spm_enter_idle_state() uses CPU_PM_CPU_IDLE_ENTER_PARAM()
>  - cpuidle-riscv-sbi: sbi_cpuidle_enter_state() uses CPU_PM_CPU_IDLE_ENTER_*_PARAM()
> 
> All of them start on index 1 and hence should have RCU_IDLE set, but at
> least the arm, qcom-spm and riscv-sbi don't actually appear to abide by
> the rules.
> 
> Fixing that gives me the below; does that help?

FWIW..  I got the meaning of CPU_PM_CPU_IDLE_*'s _RCU thing inverted
last week; they're actually ok as is.

Specifically _RCU wants the @low_level_idle_enter to do
ct_cpuidle_{enter,exit}(). And since the ones I audited didn't in fact
do that, they should not be using the _RCU version.