Re: [Qemu-devel] [PATCH v7 04/13] vfio: Add save and load functions for VFIO PCI devices

[Kirti Wankhede <kwankhede@nvidia.com>]

Sorry for delay to respond.

On 7/11/2019 5:37 PM, Dr. David Alan Gilbert wrote:
> * Kirti Wankhede (kwankhede@nvidia.com) wrote:
>> These functions save and restore PCI device specific data - config
>> space of PCI device.
>> Tested save and restore with MSI and MSIX type.
>>
>> Signed-off-by: Kirti Wankhede <kwankhede@nvidia.com>
>> Reviewed-by: Neo Jia <cjia@nvidia.com>
>> ---
>>  hw/vfio/pci.c                 | 114 ++++++++++++++++++++++++++++++++++++++++++
>>  include/hw/vfio/vfio-common.h |   2 +
>>  2 files changed, 116 insertions(+)
>>
>> diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
>> index de0d286fc9dd..5fe4f8076cac 100644
>> --- a/hw/vfio/pci.c
>> +++ b/hw/vfio/pci.c
>> @@ -2395,11 +2395,125 @@ static Object *vfio_pci_get_object(VFIODevice *vbasedev)
>>      return OBJECT(vdev);
>>  }
>>  
>> +static void vfio_pci_save_config(VFIODevice *vbasedev, QEMUFile *f)
>> +{
>> +    VFIOPCIDevice *vdev = container_of(vbasedev, VFIOPCIDevice, vbasedev);
>> +    PCIDevice *pdev = &vdev->pdev;
>> +    uint16_t pci_cmd;
>> +    int i;
>> +
>> +    for (i = 0; i < PCI_ROM_SLOT; i++) {
>> +        uint32_t bar;
>> +
>> +        bar = pci_default_read_config(pdev, PCI_BASE_ADDRESS_0 + i * 4, 4);
>> +        qemu_put_be32(f, bar);
>> +    }
>> +
>> +    qemu_put_be32(f, vdev->interrupt);
>> +    if (vdev->interrupt == VFIO_INT_MSI) {
>> +        uint32_t msi_flags, msi_addr_lo, msi_addr_hi = 0, msi_data;
>> +        bool msi_64bit;
>> +
>> +        msi_flags = pci_default_read_config(pdev, pdev->msi_cap + PCI_MSI_FLAGS,
>> +                                            2);
>> +        msi_64bit = (msi_flags & PCI_MSI_FLAGS_64BIT);
>> +
>> +        msi_addr_lo = pci_default_read_config(pdev,
>> +                                         pdev->msi_cap + PCI_MSI_ADDRESS_LO, 4);
>> +        qemu_put_be32(f, msi_addr_lo);
>> +
>> +        if (msi_64bit) {
>> +            msi_addr_hi = pci_default_read_config(pdev,
>> +                                             pdev->msi_cap + PCI_MSI_ADDRESS_HI,
>> +                                             4);
>> +        }
>> +        qemu_put_be32(f, msi_addr_hi);
>> +
>> +        msi_data = pci_default_read_config(pdev,
>> +                pdev->msi_cap + (msi_64bit ? PCI_MSI_DATA_64 : PCI_MSI_DATA_32),
>> +                2);
>> +        qemu_put_be32(f, msi_data);
>> +    } else if (vdev->interrupt == VFIO_INT_MSIX) {
>> +        uint16_t offset;
>> +
>> +        /* save enable bit and maskall bit */
>> +        offset = pci_default_read_config(pdev,
>> +                                       pdev->msix_cap + PCI_MSIX_FLAGS + 1, 2);
>> +        qemu_put_be16(f, offset);
>> +        msix_save(pdev, f);
>> +    }
>> +    pci_cmd = pci_default_read_config(pdev, PCI_COMMAND, 2);
>> +    qemu_put_be16(f, pci_cmd);
>> +}
>> +
>> +static void vfio_pci_load_config(VFIODevice *vbasedev, QEMUFile *f)
>> +{
>> +    VFIOPCIDevice *vdev = container_of(vbasedev, VFIOPCIDevice, vbasedev);
>> +    PCIDevice *pdev = &vdev->pdev;
>> +    uint32_t interrupt_type;
>> +    uint32_t msi_flags, msi_addr_lo, msi_addr_hi = 0, msi_data;
>> +    uint16_t pci_cmd;
>> +    bool msi_64bit;
>> +    int i;
>> +
>> +    /* retore pci bar configuration */
>> +    pci_cmd = pci_default_read_config(pdev, PCI_COMMAND, 2);
>> +    vfio_pci_write_config(pdev, PCI_COMMAND,
>> +                        pci_cmd & (!(PCI_COMMAND_IO | PCI_COMMAND_MEMORY)), 2);
>> +    for (i = 0; i < PCI_ROM_SLOT; i++) {
>> +        uint32_t bar = qemu_get_be32(f);
>> +
>> +        vfio_pci_write_config(pdev, PCI_BASE_ADDRESS_0 + i * 4, bar, 4);
>> +    }
> 
> Is it possible to validate the bar's at all?  We just had a bug on a
> virtual device where one version was asking for a larger bar than the
> other; our validation caught this in some cases so we could tell that
> the guest had a BAR that was aligned at the wrong alignment.
> 

"Validate the bars" does that means validate size of bars?

>> +    vfio_pci_write_config(pdev, PCI_COMMAND,
>> +                          pci_cmd | PCI_COMMAND_IO | PCI_COMMAND_MEMORY, 2);
> 
> Can you explain what this is for?  You write the command register at the
> end of the function with the original value; there's no guarantee that
> the device is using IO for example, so ORing it seems odd.
> 

IO space and memory space accesses are disabled before writing BAR
addresses, only those are enabled here.

> Also, are the other flags in COMMAND safe at this point - e.g. what
> about interrupts and stuff?
> 

COMMAND registers is saved from stop-and-copy phase, interrupt should be
disabled, then restoring here when vCPU are not yet running.

>> +    interrupt_type = qemu_get_be32(f);
>> +
>> +    if (interrupt_type == VFIO_INT_MSI) {
>> +        /* restore msi configuration */
>> +        msi_flags = pci_default_read_config(pdev,
>> +                                            pdev->msi_cap + PCI_MSI_FLAGS, 2);
>> +        msi_64bit = (msi_flags & PCI_MSI_FLAGS_64BIT);
>> +
>> +        vfio_pci_write_config(pdev, pdev->msi_cap + PCI_MSI_FLAGS,
>> +                              msi_flags & (!PCI_MSI_FLAGS_ENABLE), 2);
>> +
>> +        msi_addr_lo = qemu_get_be32(f);
>> +        vfio_pci_write_config(pdev, pdev->msi_cap + PCI_MSI_ADDRESS_LO,
>> +                              msi_addr_lo, 4);
>> +
>> +        msi_addr_hi = qemu_get_be32(f);
>> +        if (msi_64bit) {
>> +            vfio_pci_write_config(pdev, pdev->msi_cap + PCI_MSI_ADDRESS_HI,
>> +                                  msi_addr_hi, 4);
>> +        }
>> +        msi_data = qemu_get_be32(f);
>> +        vfio_pci_write_config(pdev,
>> +                pdev->msi_cap + (msi_64bit ? PCI_MSI_DATA_64 : PCI_MSI_DATA_32),
>> +                msi_data, 2);
>> +
>> +        vfio_pci_write_config(pdev, pdev->msi_cap + PCI_MSI_FLAGS,
>> +                              msi_flags | PCI_MSI_FLAGS_ENABLE, 2);
>> +    } else if (interrupt_type == VFIO_INT_MSIX) {
>> +        uint16_t offset = qemu_get_be16(f);
>> +
>> +        /* load enable bit and maskall bit */
>> +        vfio_pci_write_config(pdev, pdev->msix_cap + PCI_MSIX_FLAGS + 1,
>> +                              offset, 2);
>> +        msix_load(pdev, f);
>> +    }
>> +    pci_cmd = qemu_get_be16(f);
>> +    vfio_pci_write_config(pdev, PCI_COMMAND, pci_cmd, 2);
>> +}
>> +
>>  static VFIODeviceOps vfio_pci_ops = {
>>      .vfio_compute_needs_reset = vfio_pci_compute_needs_reset,
>>      .vfio_hot_reset_multi = vfio_pci_hot_reset_multi,
>>      .vfio_eoi = vfio_intx_eoi,
>>      .vfio_get_object = vfio_pci_get_object,
>> +    .vfio_save_config = vfio_pci_save_config,
>> +    .vfio_load_config = vfio_pci_load_config,
>>  };
>>  
>>  int vfio_populate_vga(VFIOPCIDevice *vdev, Error **errp)
>> diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
>> index 771b6d59a3db..ee72bd984a36 100644
>> --- a/include/hw/vfio/vfio-common.h
>> +++ b/include/hw/vfio/vfio-common.h
>> @@ -120,6 +120,8 @@ struct VFIODeviceOps {
>>      int (*vfio_hot_reset_multi)(VFIODevice *vdev);
>>      void (*vfio_eoi)(VFIODevice *vdev);
>>      Object *(*vfio_get_object)(VFIODevice *vdev);
>> +    void (*vfio_save_config)(VFIODevice *vdev, QEMUFile *f);
>> +    void (*vfio_load_config)(VFIODevice *vdev, QEMUFile *f);
>>  };
>>  
>>  typedef struct VFIOGroup {
>> -- 
>> 2.7.0
>>
> --
> Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK
>