Re: [Xen-devel] [PATCH v4 3/6] xen: add process_pending_softirqs_norcu() for keyhandlers

[Jan Beulich <jbeulich@xxxxxxxx>]

On 11.03.2020 10:47, Jürgen Groß wrote:
> On 11.03.20 10:36, Jan Beulich wrote:
>> On 11.03.2020 10:27, Jürgen Groß wrote:
>>> On 11.03.20 10:25, Jan Beulich wrote:
>>>> On 11.03.2020 07:07, Jürgen Groß wrote:
>>>>> On 10.03.20 18:02, Jan Beulich wrote:
>>>>>> On 10.03.2020 08:28, Juergen Gross wrote:
>>>>>>> --- a/xen/drivers/passthrough/amd/pci_amd_iommu.c
>>>>>>> +++ b/xen/drivers/passthrough/amd/pci_amd_iommu.c
>>>>>>> @@ -587,7 +587,7 @@ static void amd_dump_p2m_table_level(struct 
>>>>>>> page_info* pg, int level,
>>>>>>>             struct amd_iommu_pte *pde = &table_vaddr[index];
>>>>>>>     
>>>>>>>             if ( !(index % 2) )
>>>>>>> -            process_pending_softirqs();
>>>>>>> +            process_pending_softirqs_norcu();
>>>>>>
>>>>>> At the example of this - the property of holding an RCU lock is
>>>>>> entirely invisible here, as it's the generic
>>>>>> iommu_dump_p2m_table() which acquires it. This suggest to me that
>>>>>> going forward breaking this is going to be very likely. Couldn't
>>>>>> process_pending_softirqs() exclude RCU handling when finding
>>>>>> preempt_count() to return non-zero?
>>>>>
>>>>> This can be done, but then the non-debug build would require to have
>>>>> non-empty rcu lock functions.
>>>>
>>>> I guess I don't understand - I see only one version of them:
>>>>
>>>> #define rcu_read_lock(x)       ({ ((void)(x)); preempt_disable(); })
>>>> #define rcu_read_unlock(x)     ({ ((void)(x)); preempt_enable(); })
>>>>
>>>> Same for the preempt count adjustment operations.
>>>
>>> See patch 5.
>>
>> Which I haven't looked at yet, and which I also shouldn't need to
>> look at to understand the patch here. If this is a preparatory
>> change rather than some form of fix or improvement, then the
>> description should say so.
> 
> This was just meant as an answer to your question regarding considering
> preempt_count(). Just changing this patch here and then undoing the
> change again in patch 5 is no option IMO, so I gave a hint why using
> preempt_count() might be a bad idea.

I've briefly looked at patch 5, and I don't see why the counter you
introduce there couldn't also be maintained in non-debug builds.

Jan

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxxx
https://lists.xenproject.org/mailman/listinfo/xen-devel