[PATCH 01/33] PCI: Prepare to protect against concurrent isolated cpuset change

[Waiman Long]

On 12/28/25 10:23 PM, Zhang Qiao wrote:
> Hi, Weisbecker，
>
> 在 2025/12/24 21:44, Frederic Weisbecker 写道:
>> HK_TYPE_DOMAIN will soon integrate cpuset isolated partitions and
>> therefore be made modifiable at runtime. Synchronize against the cpumask
>> update using RCU.
>>
>> The RCU locked section includes both the housekeeping CPU target
>> election for the PCI probe work and the work enqueue.
>>
>> This way the housekeeping update side will simply need to flush the
>> pending related works after updating the housekeeping mask in order to
>> make sure that no PCI work ever executes on an isolated CPU. This part
>> will be handled in a subsequent patch.
>>
>> Signed-off-by: Frederic Weisbecker <frederic at kernel.org>
>> ---
>>   drivers/pci/pci-driver.c | 47 ++++++++++++++++++++++++++++++++--------
>>   1 file changed, 38 insertions(+), 9 deletions(-)
>>
>> diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
>> index 7c2d9d596258..786d6ce40999 100644
>> --- a/drivers/pci/pci-driver.c
>> +++ b/drivers/pci/pci-driver.c
>> @@ -302,9 +302,8 @@ struct drv_dev_and_id {
>>   	const struct pci_device_id *id;
>>   };
>>   
>> -static long local_pci_probe(void *_ddi)
>> +static int local_pci_probe(struct drv_dev_and_id *ddi)
>>   {
>> -	struct drv_dev_and_id *ddi = _ddi;
>>   	struct pci_dev *pci_dev = ddi->dev;
>>   	struct pci_driver *pci_drv = ddi->drv;
>>   	struct device *dev = &pci_dev->dev;
>> @@ -338,6 +337,19 @@ static long local_pci_probe(void *_ddi)
>>   	return 0;
>>   }
>>   
>> +struct pci_probe_arg {
>> +	struct drv_dev_and_id *ddi;
>> +	struct work_struct work;
>> +	int ret;
>> +};
>> +
>> +static void local_pci_probe_callback(struct work_struct *work)
>> +{
>> +	struct pci_probe_arg *arg = container_of(work, struct pci_probe_arg, work);
>> +
>> +	arg->ret = local_pci_probe(arg->ddi);
>> +}
>> +
>>   static bool pci_physfn_is_probed(struct pci_dev *dev)
>>   {
>>   #ifdef CONFIG_PCI_IOV
>> @@ -362,34 +374,51 @@ static int pci_call_probe(struct pci_driver *drv, struct pci_dev *dev,
>>   	dev->is_probed = 1;
>>   
>>   	cpu_hotplug_disable();
>> -
>>   	/*
>>   	 * Prevent nesting work_on_cpu() for the case where a Virtual Function
>>   	 * device is probed from work_on_cpu() of the Physical device.
>>   	 */
>>   	if (node < 0 || node >= MAX_NUMNODES || !node_online(node) ||
>>   	    pci_physfn_is_probed(dev)) {
>> -		cpu = nr_cpu_ids;
>> +		error = local_pci_probe(&ddi);
>>   	} else {
>>   		cpumask_var_t wq_domain_mask;
>> +		struct pci_probe_arg arg = { .ddi = &ddi };
>> +
>> +		INIT_WORK_ONSTACK(&arg.work, local_pci_probe_callback);
>>   
>>   		if (!zalloc_cpumask_var(&wq_domain_mask, GFP_KERNEL)) {
>>   			error = -ENOMEM;
> If we return from here, arg.work will not be destroyed.
>
>
Right. INIT_WORK_ONSTACK() should be called after successful 
cpumask_var_t allocation.

Cheers,
Longman

>>   			goto out;
>>   		}
>> +
>> +		/*
>> +		 * The target election and the enqueue of the work must be within
>> +		 * the same RCU read side section so that when the workqueue pool
>> +		 * is flushed after a housekeeping cpumask update, further readers
>> +		 * are guaranteed to queue the probing work to the appropriate
>> +		 * targets.
>> +		 */
>> +		rcu_read_lock();
>>   		cpumask_and(wq_domain_mask,
>>   			    housekeeping_cpumask(HK_TYPE_WQ),
>>   			    housekeeping_cpumask(HK_TYPE_DOMAIN));
>>   
>>   		cpu = cpumask_any_and(cpumask_of_node(node),
>>   				      wq_domain_mask);
>> +		if (cpu < nr_cpu_ids) {
>> +			schedule_work_on(cpu, &arg.work);
>> +			rcu_read_unlock();
>> +			flush_work(&arg.work);
>> +			error = arg.ret;
>> +		} else {
>> +			rcu_read_unlock();
>> +			error = local_pci_probe(&ddi);
>> +		}
>> +
>>   		free_cpumask_var(wq_domain_mask);
>> +		destroy_work_on_stack(&arg.work);
>>   	}
>> -
>> -	if (cpu < nr_cpu_ids)
>> -		error = work_on_cpu(cpu, local_pci_probe, &ddi);
>> -	else
>> -		error = local_pci_probe(&ddi);
>>   out:
>>   	dev->is_probed = 0;
>>   	cpu_hotplug_enable();
>>