Re: [PATCH] torture: Forgive SMT-control failures in CPU-hotplug testing

[Paul E. McKenney]

On Thu, Nov 12, 2026 at 12:52:20PM -0500, Joel Fernandes wrote:
> The onoff task ends rcutorture with "End of test: RCU_HOTPLUG" if any
> CPU-hotplug attempt fails, other than -EBUSY during boot.  Toggling
> /sys/devices/system/cpu/smt/control while onoff runs causes two failures
> that are not the test's fault.  cpu_up() returns -EPERM for an SMT thread
> that SMT control keeps offline, and device_online() and device_offline()
> return 1 when the toggle already did the operation.
> 
> Repro: in a 16-vCPU guest (8 cores, 2 threads), run
> "modprobe rcutorture onoff_interval=1 gp_exp=0" while looping
> "echo off/on > smt/control" for 120 seconds.  This ended in RCU_HOTPLUG,
> with no reader errors.  With this change it ends in SUCCESS.
> 
> Forgive these like boot-time -EBUSY, by not counting the attempt.
> 
> Signed-off-by: Joel Fernandes <joelagnelf@xxxxxxxxxx>

Reviewed-by: Paul E. McKenney <paulmck@xxxxxxxxxx>

> ---
>  kernel/torture.c | 40 ++++++++++++++++++++++++++++------------
>  1 file changed, 28 insertions(+), 12 deletions(-)
> 
> diff --git a/kernel/torture.c b/kernel/torture.c
> index 8c4e6b2fe8ba..b860c99e9ca7 100644
> --- a/kernel/torture.c
> +++ b/kernel/torture.c
> @@ -194,6 +194,24 @@ int torture_num_online_cpus(void)
>  }
>  EXPORT_SYMBOL_GPL(torture_num_online_cpus);
>  
> +/*
> + * If the CPU-hotplug failure is not the torture test's fault, return a
> + * string saying why it is forgiven.  Otherwise, return NULL.
> + */
> +static const char *torture_onoff_forgive(int ret)
> +{
> +	// PCI probe frequently disables hotplug during boot.
> +	if (!rcu_inkernel_boot_has_ended() && ret == -EBUSY)
> +		return " (-EBUSY forgiven during boot)";
> +	// Hotplug is forbidden, for example by SMT control.
> +	if (ret == -EPERM)
> +		return " (-EPERM forgiven, hotplug forbidden)";
> +	// Something else, such as SMT control, already did the operation.
> +	if (ret == 1)
> +		return " (already in requested state, forgiven)";
> +	return NULL;
> +}
> +
>  /*
>   * Attempt to take a CPU offline.  Return false if the CPU is already
>   * offline or if it is not subject to CPU-hotplug operations.  The
> @@ -204,7 +222,7 @@ bool torture_offline(int cpu, long *n_offl_attempts, long *n_offl_successes,
>  {
>  	unsigned long delta;
>  	int ret;
> -	char *s;
> +	const char *s;
>  	unsigned long starttime;
>  
>  	if (!cpu_online(cpu) || !cpu_is_hotpluggable(cpu))
> @@ -220,12 +238,11 @@ bool torture_offline(int cpu, long *n_offl_attempts, long *n_offl_successes,
>  	(*n_offl_attempts)++;
>  	ret = remove_cpu(cpu);
>  	if (ret) {
> -		s = "";
> -		if (!rcu_inkernel_boot_has_ended() && ret == -EBUSY) {
> -			// PCI probe frequently disables hotplug during boot.
> +		s = torture_onoff_forgive(ret);
> +		if (s)
>  			(*n_offl_attempts)--;
> -			s = " (-EBUSY forgiven during boot)";
> -		}
> +		else
> +			s = "";
>  		if (verbose)
>  			pr_alert("%s" TORTURE_FLAG
>  				 "torture_onoff task: offline %d failed%s: errno %d\n",
> @@ -266,7 +283,7 @@ bool torture_online(int cpu, long *n_onl_attempts, long *n_onl_successes,
>  {
>  	unsigned long delta;
>  	int ret;
> -	char *s;
> +	const char *s;
>  	unsigned long starttime;
>  
>  	if (cpu_online(cpu) || !cpu_is_hotpluggable(cpu))
> @@ -280,12 +297,11 @@ bool torture_online(int cpu, long *n_onl_attempts, long *n_onl_successes,
>  	(*n_onl_attempts)++;
>  	ret = add_cpu(cpu);
>  	if (ret) {
> -		s = "";
> -		if (!rcu_inkernel_boot_has_ended() && ret == -EBUSY) {
> -			// PCI probe frequently disables hotplug during boot.
> +		s = torture_onoff_forgive(ret);
> +		if (s)
>  			(*n_onl_attempts)--;
> -			s = " (-EBUSY forgiven during boot)";
> -		}
> +		else
> +			s = "";
>  		if (verbose)
>  			pr_alert("%s" TORTURE_FLAG
>  				 "torture_onoff task: online %d failed%s: errno %d\n",
> -- 
> 2.54.0
> 
>