Re: [PATCH v3 3/3] vfio: Avoid disabling and enabling vectors repeatedly in VFIO migration

[Shenming Lu <lushenming@huawei.com>]

On 2021/3/3 5:26, Alex Williamson wrote:
> 
> MST/Marcel,
> 
> Do you have an Ack or objection to exporting msix_masked() as below?

Or could we use msix_function_masked instead as below? :-)

if (!pdev->msix_function_masked) {
    for (nr = 0; nr < msix_nr_vectors_allocated(pdev); nr++) {
        if (!msix_is_masked(pdev, nr)) {
            max_vec = nr;
        }
    }
}

Thanks,
Shenming

> Thanks,
> 
> Alex
> 
> On Tue, 23 Feb 2021 10:22:25 +0800
> Shenming Lu <lushenming@huawei.com> wrote:
> 
>> In VFIO migration resume phase and some guest startups, there are
>> already unmasked vectors in the vector table when calling
>> vfio_msix_enable(). So in order to avoid inefficiently disabling
>> and enabling vectors repeatedly, let's allocate all needed vectors
>> first and then enable these unmasked vectors one by one without
>> disabling.
>>
>> Signed-off-by: Shenming Lu <lushenming@huawei.com>
>> ---
>>  hw/pci/msix.c         |  2 +-
>>  hw/vfio/pci.c         | 20 +++++++++++++++++---
>>  include/hw/pci/msix.h |  1 +
>>  3 files changed, 19 insertions(+), 4 deletions(-)
>>
>> diff --git a/hw/pci/msix.c b/hw/pci/msix.c
>> index ae9331cd0b..e057958fcd 100644
>> --- a/hw/pci/msix.c
>> +++ b/hw/pci/msix.c
>> @@ -131,7 +131,7 @@ static void msix_handle_mask_update(PCIDevice *dev, int vector, bool was_masked)
>>      }
>>  }
>>  
>> -static bool msix_masked(PCIDevice *dev)
>> +bool msix_masked(PCIDevice *dev)
>>  {
>>      return dev->config[dev->msix_cap + MSIX_CONTROL_OFFSET] & MSIX_MASKALL_MASK;
>>  }
>> diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
>> index f74be78209..088fd41926 100644
>> --- a/hw/vfio/pci.c
>> +++ b/hw/vfio/pci.c
>> @@ -569,6 +569,9 @@ static void vfio_msix_vector_release(PCIDevice *pdev, unsigned int nr)
>>  
>>  static void vfio_msix_enable(VFIOPCIDevice *vdev)
>>  {
>> +    PCIDevice *pdev = &vdev->pdev;
>> +    unsigned int nr, max_vec = 0;
>> +
>>      vfio_disable_interrupts(vdev);
>>  
>>      vdev->msi_vectors = g_new0(VFIOMSIVector, vdev->msix->entries);
>> @@ -587,11 +590,22 @@ static void vfio_msix_enable(VFIOPCIDevice *vdev)
>>       * triggering to userspace, then immediately release the vector, leaving
>>       * the physical device with no vectors enabled, but MSI-X enabled, just
>>       * like the guest view.
>> +     * If there are already unmasked vectors (in migration resume phase and
>> +     * some guest startups) which will be enabled soon, we can allocate all
>> +     * of them here to avoid inefficiently disabling and enabling vectors
>> +     * repeatedly later.
>>       */
>> -    vfio_msix_vector_do_use(&vdev->pdev, 0, NULL, NULL);
>> -    vfio_msix_vector_release(&vdev->pdev, 0);
>> +    if (!msix_masked(pdev)) {
>> +        for (nr = 0; nr < msix_nr_vectors_allocated(pdev); nr++) {
>> +            if (!msix_is_masked(pdev, nr)) {
>> +                max_vec = nr;
>> +            }
>> +        }
>> +    }
>> +    vfio_msix_vector_do_use(pdev, max_vec, NULL, NULL);
>> +    vfio_msix_vector_release(pdev, max_vec);
>>  
>> -    if (msix_set_vector_notifiers(&vdev->pdev, vfio_msix_vector_use,
>> +    if (msix_set_vector_notifiers(pdev, vfio_msix_vector_use,
>>                                    vfio_msix_vector_release, NULL)) {
>>          error_report("vfio: msix_set_vector_notifiers failed");
>>      }
>> diff --git a/include/hw/pci/msix.h b/include/hw/pci/msix.h
>> index 4c4a60c739..b3cd88e262 100644
>> --- a/include/hw/pci/msix.h
>> +++ b/include/hw/pci/msix.h
>> @@ -28,6 +28,7 @@ void msix_load(PCIDevice *dev, QEMUFile *f);
>>  
>>  int msix_enabled(PCIDevice *dev);
>>  int msix_present(PCIDevice *dev);
>> +bool msix_masked(PCIDevice *dev);
>>  
>>  bool msix_is_masked(PCIDevice *dev, unsigned vector);
>>  void msix_set_pending(PCIDevice *dev, unsigned vector);
> 
> .
>