Re: [Qemu-devel] [PATCH v4 08/10] vfio: vote the function 0 to do host bus reset when aer occurred

[Chen Fan <chen.fan.fnst@cn.fujitsu.com>]

On 03/22/2016 05:40 AM, Alex Williamson wrote:
> On Mon, 21 Mar 2016 18:08:44 +0800
> Cao jin <caoj.fnst@cn.fujitsu.com> wrote:
>
>> From: Chen Fan <chen.fan.fnst@cn.fujitsu.com>
>>
>> Due to all devices assigned to VM on the same way as host if enable
>> aer, so we can easily do the hot reset by selecting the function #0
>> to do the hot reset.
>>
>> Signed-off-by: Chen Fan <chen.fan.fnst@cn.fujitsu.com>
>> ---
>>   hw/vfio/pci.c | 50 ++++++++++++++++++++++++++++++++++++++++++++++++++
>>   hw/vfio/pci.h |  2 ++
>>   2 files changed, 52 insertions(+)
>>
>> diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
>> index 9902c87..718cde7 100644
>> --- a/hw/vfio/pci.c
>> +++ b/hw/vfio/pci.c
>> @@ -1900,6 +1900,8 @@ static void vfio_check_hot_bus_reset(VFIOPCIDevice *vdev, Error **errp)
>>       /* List all affected devices by bus reset */
>>       devices = &info->devices[0];
>>   
>> +    vdev->single_depend_dev = (info->count == 1);
>> +
>>       /* Verify that we have all the groups required */
>>       for (i = 0; i < info->count; i++) {
>>           PCIHostDeviceAddress host;
>> @@ -2608,11 +2610,36 @@ static void vfio_put_device(VFIOPCIDevice *vdev)
>>   static void vfio_err_notifier_handler(void *opaque)
>>   {
>>       VFIOPCIDevice *vdev = opaque;
>> +    PCIDevice *pdev = &vdev->pdev;
>>   
>>       if (!event_notifier_test_and_clear(&vdev->err_notifier)) {
>>           return;
>>       }
>>   
>> +    if (vdev->features & VFIO_FEATURE_ENABLE_AER) {
>> +        VFIOPCIDevice *tmp;
>> +        PCIDevice *dev;
>> +        int devfn;
>> +
>> +        /*
>> +         * If one device has aer capability on a bus, when aer occurred,
>> +         * we should notify all devices on the bus there was an aer arrived,
>> +         * then we are able to vote the device #0 to do host bus reset.
>> +         */
>> +        for (devfn = 0; devfn < 8; devfn++) {
> ARI?
>
>> +            dev = pci_find_device(pdev->bus, pci_bus_num(pdev->bus),
>> +                      PCI_DEVFN(PCI_SLOT(pdev->devfn), devfn));
>> +            if (!dev) {
>> +                continue;
>> +            }
>> +            if (!object_dynamic_cast(OBJECT(dev), "vfio-pci")) {
>> +                continue;
>> +            }
>> +            tmp = DO_UPCAST(VFIOPCIDevice, pdev, dev);
>> +            tmp->aer_occurred = true;
>> +        }
>> +    }
>> +
>>       /*
>>        * TBD. Retrieve the error details and decide what action
>>        * needs to be taken. One of the actions could be to pass
>> @@ -3075,6 +3102,29 @@ static void vfio_pci_reset(DeviceState *dev)
>>   
>>       trace_vfio_pci_reset(vdev->vbasedev.name);
>>   
>> +    if (vdev->aer_occurred) {
>> +        PCIDevice *br = pci_bridge_get_device(pdev->bus);
>> +
>> +        if (br &&
>> +            (pci_get_word(br->config + PCI_BRIDGE_CONTROL) &
>> +             PCI_BRIDGE_CTL_BUS_RESET)) {
>> +            /* simply voting the function 0 to do hot bus reset */
>> +            if (pci_get_function_0(pdev) == pdev) {
>> +                if (vdev->features & VFIO_FEATURE_ENABLE_AER) {
>> +                    vfio_pci_hot_reset(vdev, vdev->single_depend_dev);
>> +                } else {
>> +                    /* if this device has not AER capability, code
>> +                     * coming here indicates there is another function
>> +                     * on the bus has AER capability.
>> +                     * */
> This shouldn't be possible, right?
>
>> +                    vfio_pci_hot_reset(vdev, false);
>> +                }
>> +            }
>> +            vdev->aer_occurred = false;
>> +            return;
>> +        }
>> +    }
> Why do we care than an AER occurred now?  Can't we simply test:
>
>      if (vdev->features & VFIO_FEATURE_ENABLE_AER &&
>          pci_get_function_0(pdev) == pdev) {
>          PCIDevice *br = pci_bridge_get_device(pdev->bus);
>
>          if (pci_get_word(br->config + PCI_BRIDGE_CONTROL) &
>              PCI_BRIDGE_CTL_BUS_RESET)) {
>
>              vfio_pci_hot_reset(vdev, vdev->single_depend_dev);
>              return;
>          }
>      }
I think this is not practicable, not_function_0 device can't
pass the condition, it would do reset normally. but our intention
is doing nothing for them, and direct return.
I will change this in next version.

Thanks,
CHen

>
>> +
>>       vfio_pci_pre_reset(vdev);
>>   
>>       if (vdev->resetfn && !vdev->resetfn(vdev)) {
>> diff --git a/hw/vfio/pci.h b/hw/vfio/pci.h
>> index db7c6d5..17c75b8 100644
>> --- a/hw/vfio/pci.h
>> +++ b/hw/vfio/pci.h
>> @@ -143,6 +143,8 @@ typedef struct VFIOPCIDevice {
>>       bool no_kvm_intx;
>>       bool no_kvm_msi;
>>       bool no_kvm_msix;
>> +    bool aer_occurred;
>> +    bool single_depend_dev;
>>   } VFIOPCIDevice;
>>   
>>   uint32_t vfio_pci_read_config(PCIDevice *pdev, uint32_t addr, int len);
>
>
> .
>