Re: [PATCH 11/19] arm64: smp: Use generic HOTPLUG_SPLIT_STARTUP machinery for CPU onlining

[Jinjie Ruan <ruanjinjie@huawei.com>]

在 2026/9/8 0:40, Will Deacon 写道:
> In preparation for enabling parallel bringup of secondary CPUs on arm64,
> take the baby step of moving from HOTPLUG_CORE_SYNC_FULL to
> HOTPLUG_SPLIT_STARTUP.
> 
> Rework the cpu_die_early() path to use a private cpumask, otherwise
> clearing the incoming CPU from the present mask in the 'kick' stage will
> prevent the hotplug stage machine from progressing and
> arch_cpuhp_cleanup_kick_cpu() will not be called.
> 
> Signed-off-by: Will Deacon <will@kernel.org>
> ---
>  arch/arm64/Kconfig           | 2 +-
>  arch/arm64/include/asm/smp.h | 1 +
>  arch/arm64/kernel/smp.c      | 9 +++++----
>  3 files changed, 7 insertions(+), 5 deletions(-)
> 
> diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
> index 89d1f0f2269c..fd8cf792b7fd 100644
> --- a/arch/arm64/Kconfig
> +++ b/arch/arm64/Kconfig
> @@ -230,7 +230,7 @@ config ARM64
>  	select HAVE_SYSCALL_TRACEPOINTS
>  	select HAVE_KPROBES
>  	select HAVE_KRETPROBES
> -	select HOTPLUG_CORE_SYNC_FULL
> +	select HOTPLUG_SPLIT_STARTUP
>  	select HOTPLUG_SMT if HOTPLUG_CPU
>  	select IRQ_DOMAIN
>  	select IRQ_FORCED_THREADING
> diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
> index fe343c30d620..7b986a6a765b 100644
> --- a/arch/arm64/include/asm/smp.h
> +++ b/arch/arm64/include/asm/smp.h
> @@ -89,6 +89,7 @@ asmlinkage void secondary_start_kernel(void);
>  struct secondary_data {
>  	struct task_struct *task;
>  	long status;
> +	cpumask_t cpu_died_early_mask;
>  };
>  
>  extern struct secondary_data secondary_data;
> diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
> index 00362ed6e1ab..c5e9d5d5e003 100644
> --- a/arch/arm64/kernel/smp.c
> +++ b/arch/arm64/kernel/smp.c
> @@ -62,7 +62,7 @@
>   * so we need some other way of telling a new secondary core
>   * where to place its SVC stack
>   */
> -struct secondary_data secondary_data;
> +struct secondary_data secondary_data = {};
>  /* Number of CPUs which aren't online, but looping in kernel text. */
>  static int cpus_stuck_in_kernel;
>  
> @@ -108,7 +108,7 @@ static int boot_secondary(unsigned int cpu, struct task_struct *idle)
>  	return -EOPNOTSUPP;
>  }
>  
> -int __cpu_up(unsigned int cpu, struct task_struct *idle)
> +int arch_cpuhp_kick_ap_alive(unsigned int cpu, struct task_struct *idle)
>  {
>  	int ret;
>  
> @@ -146,6 +146,8 @@ void arch_cpuhp_cleanup_kick_cpu(unsigned int cpu, bool is_alive)
>  		cpus_stuck_in_kernel++;
>  		break;
>  	case CPU_KILL_ME:
> +		if (cpumask_test_cpu(cpu, &secondary_data.cpu_died_early_mask))
> +			set_cpu_present(cpu, false);

Should we set_cpu_present(cpu, false) in CPU_STUCK_IN_KERNEL case, as we
do not update to CPU_KILL_ME but CPU_STUCK_IN_KERNEL if
CONFIG_HOTPLUG_CPU is not enabled.

>  		if (!op_cpu_kill(cpu)) {
>  			pr_crit("CPU%u: died during early boot\n", cpu);
>  			break;
> @@ -406,8 +408,7 @@ void __noreturn cpu_die_early(void)
>  
>  	pr_crit("CPU%d: will not boot\n", cpu);
>  
> -	/* Mark this CPU absent */
> -	set_cpu_present(cpu, 0);
> +	cpumask_set_cpu(cpu, &secondary_data.cpu_died_early_mask);
>  
>  	if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) {
>  		update_cpu_boot_status(CPU_KILL_ME);