Re: [Qemu-devel] [PATCH v4 03/13] vfio: Add save and load functions for VFIO PCI devices

[Kirti Wankhede <kwankhede@nvidia.com>]

On 6/21/2019 5:42 AM, Yan Zhao wrote:
> On Thu, Jun 20, 2019 at 10:37:31PM +0800, Kirti Wankhede 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 | 112 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
>>  hw/vfio/pci.h |  29 +++++++++++++++
>>  2 files changed, 141 insertions(+)
>>
>> diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
>> index ce3fe96efe2c..09a0821a5b1c 100644
>> --- a/hw/vfio/pci.c
>> +++ b/hw/vfio/pci.c
>> @@ -1187,6 +1187,118 @@ void vfio_pci_write_config(PCIDevice *pdev,
>>      }
>>  }
>>  
>> +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);
>> +}
>> +
>> +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);
>> +    }
>> +    vfio_pci_write_config(pdev, PCI_COMMAND,
>> +                          pci_cmd | PCI_COMMAND_IO | PCI_COMMAND_MEMORY, 2);
>> +
>> +    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);
>> +}
>> +
> per the previous discussion, pci config state save/restore are better
> defined in fileds of VMStateDescription.
> 
> 

With that route there is no pre-copy phase and we do want pre-copy phase
for VFIO devices. Vendor driver can skip pre-copy phase by doing nothing
on any read/write operation during pre-copy phase.

Thanks,
Kirti

>>  /*
>>   * Interrupt setup
>>   */
>> diff --git a/hw/vfio/pci.h b/hw/vfio/pci.h
>> index 834a90d64686..847be5f56478 100644
>> --- a/hw/vfio/pci.h
>> +++ b/hw/vfio/pci.h
>> @@ -19,6 +19,7 @@
>>  #include "qemu/queue.h"
>>  #include "qemu/timer.h"
>>  
>> +#ifdef CONFIG_LINUX
>>  #define PCI_ANY_ID (~0)
>>  
>>  struct VFIOPCIDevice;
>> @@ -202,4 +203,32 @@ void vfio_display_reset(VFIOPCIDevice *vdev);
>>  int vfio_display_probe(VFIOPCIDevice *vdev, Error **errp);
>>  void vfio_display_finalize(VFIOPCIDevice *vdev);
>>  
>> +void vfio_pci_save_config(VFIODevice *vbasedev, QEMUFile *f);
>> +void vfio_pci_load_config(VFIODevice *vbasedev, QEMUFile *f);
>> +
>> +static inline Object *vfio_pci_get_object(VFIODevice *vbasedev)
>> +{
>> +    VFIOPCIDevice *vdev = container_of(vbasedev, VFIOPCIDevice, vbasedev);
>> +
>> +    return OBJECT(vdev);
>> +}
>> +
>> +#else
>> +static inline void vfio_pci_save_config(VFIODevice *vbasedev, QEMUFile *f)
>> +{
>> +    g_assert(false);
>> +}
>> +
>> +static inline void vfio_pci_load_config(VFIODevice *vbasedev, QEMUFile *f)
>> +{
>> +    g_assert(false);
>> +}
>> +
>> +static inline Object *vfio_pci_get_object(VFIODevice *vbasedev)
>> +{
>> +    return NULL;
>> +}
>> +
>> +#endif
>> +
>>  #endif /* HW_VFIO_VFIO_PCI_H */
>> -- 
>> 2.7.0
>>