Introduce vfio_device_put/vfio_device_get funtion for vfio device state save/restore usage.
For VFIO pci device status migrate, on the source side with funtion vfio_device_put to save the following states 1. pci configuration space addr0~addr5 2. pci configuration space msi_addr msi_data 3. pci device status fetch from device driver And on the target side with funtion vfio_device_get to restore the same states 1. re-setup the pci bar configuration 2. re-setup the pci device msi configuration 3. restore the pci device status Signed-off-by: Yulei Zhang <yulei.zh...@intel.com> --- hw/vfio/pci.c | 132 +++++++++++++++++++++++++++++++++++++++++++++ linux-headers/linux/vfio.h | 2 + 2 files changed, 134 insertions(+) diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c index 753da80..c0fc1d2 100644 --- a/hw/vfio/pci.c +++ b/hw/vfio/pci.c @@ -2959,6 +2959,118 @@ static void vfio_vm_change_state_handler(void *pv, int running, RunState state) vbasedev->device_state = dev_state; } +static int vfio_device_put(QEMUFile *f, void *pv, size_t size, VMStateField *field, + QJSON *vmdesc) +{ + VFIOPCIDevice *vdev = pv; + PCIDevice *pdev = &vdev->pdev; + int sz = vdev->device_state.size - VFIO_DEVICE_STATE_OFFSET; + uint8_t *buf = NULL; + uint32_t msi_cfg, msi_lo, msi_hi, msi_data, bar_cfg, i; + bool msi_64bit; + + for (i = 0; i < PCI_ROM_SLOT; i++) { + bar_cfg = pci_default_read_config(pdev, PCI_BASE_ADDRESS_0 + i*4, 4); + qemu_put_be32(f, bar_cfg); + } + + msi_cfg = pci_default_read_config(pdev, pdev->msi_cap + PCI_MSI_FLAGS, 2); + msi_64bit = !!(msi_cfg & PCI_MSI_FLAGS_64BIT); + + msi_lo = pci_default_read_config(pdev, pdev->msi_cap + PCI_MSI_ADDRESS_LO, 4); + qemu_put_be32(f, msi_lo); + + if (msi_64bit) { + msi_hi = pci_default_read_config(pdev, pdev->msi_cap + PCI_MSI_ADDRESS_HI, 4); + qemu_put_be32(f, msi_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); + + buf = g_malloc(sz); + if (buf == NULL) { + error_report("vfio: Failed to allocate memory for migrate\n"); + goto exit; + } + + if (pread(vdev->vbasedev.fd, buf, sz, + vdev->device_state.offset + VFIO_DEVICE_STATE_OFFSET) != sz) { + error_report("vfio: Failed to read Device State Region\n"); + goto exit; + } + + qemu_put_buffer(f, buf, sz); + +exit: + if (buf) + g_free(buf); + + return 0; +} + +static int vfio_device_get(QEMUFile *f, void *pv, size_t size, VMStateField *field) +{ + VFIOPCIDevice *vdev = pv; + PCIDevice *pdev = &vdev->pdev; + int sz = vdev->device_state.size - VFIO_DEVICE_STATE_OFFSET; + uint8_t *buf = NULL; + uint32_t ctl, msi_lo, msi_hi, msi_data, bar_cfg, i; + bool msi_64bit; + + /* retore pci bar configuration */ + ctl = pci_default_read_config(pdev, PCI_COMMAND, 2); + vfio_pci_write_config(pdev, PCI_COMMAND, + ctl & (!(PCI_COMMAND_IO | PCI_COMMAND_MEMORY)), 2); + for (i = 0; i < PCI_ROM_SLOT; i++) { + bar_cfg = qemu_get_be32(f); + vfio_pci_write_config(pdev, PCI_BASE_ADDRESS_0 + i*4, bar_cfg, 4); + } + vfio_pci_write_config(pdev, PCI_COMMAND, + ctl | PCI_COMMAND_IO | PCI_COMMAND_MEMORY, 2); + + /* restore msi configuration */ + ctl = pci_default_read_config(pdev, pdev->msi_cap + PCI_MSI_FLAGS, 2); + msi_64bit = !!(ctl & PCI_MSI_FLAGS_64BIT); + + vfio_pci_write_config(&vdev->pdev, + pdev->msi_cap + PCI_MSI_FLAGS, + ctl & (!PCI_MSI_FLAGS_ENABLE), 2); + + msi_lo = qemu_get_be32(f); + vfio_pci_write_config(pdev, pdev->msi_cap + PCI_MSI_ADDRESS_LO, msi_lo, 4); + + if (msi_64bit) { + msi_hi = qemu_get_be32(f); + vfio_pci_write_config(pdev, pdev->msi_cap + PCI_MSI_ADDRESS_HI, msi_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(&vdev->pdev, pdev->msi_cap + PCI_MSI_FLAGS, + ctl | PCI_MSI_FLAGS_ENABLE, 2); + + buf = g_malloc(sz); + if (buf == NULL) { + error_report("vfio: Failed to allocate memory for migrate\n"); + return -1; + } + + qemu_get_buffer(f, buf, sz); + if (pwrite(vdev->vbasedev.fd, buf, sz, + vdev->device_state.offset + VFIO_DEVICE_STATE_OFFSET) != sz) { + error_report("vfio: Failed to write Device State Region\n"); + return -1; + } + + if (buf) + g_free(buf); + return 0; +} + static void vfio_instance_init(Object *obj) { PCIDevice *pci_dev = PCI_DEVICE(obj); @@ -3003,9 +3115,29 @@ static Property vfio_pci_dev_properties[] = { DEFINE_PROP_END_OF_LIST(), }; +static VMStateInfo vfio_vmstate_info = { + .name = "vfio-state", + .get = vfio_device_get, + .put = vfio_device_put, +}; + static VMStateDescription vfio_pci_vmstate = { .name = "vfio-pci", .unmigratable = 1, + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + { + .name = "vfio dev", + .version_id = 0, + .field_exists = NULL, + .size = 0, + .info = &vfio_vmstate_info, + .flags = VMS_SINGLE, + .offset = 0, + }, + VMSTATE_END_OF_LIST() + }, }; static void vfio_pci_dev_class_init(ObjectClass *klass, void *data) diff --git a/linux-headers/linux/vfio.h b/linux-headers/linux/vfio.h index ae1b953..dbbe7e1 100644 --- a/linux-headers/linux/vfio.h +++ b/linux-headers/linux/vfio.h @@ -302,6 +302,8 @@ struct vfio_region_info_cap_type { #define VFIO_DEVICE_START 0 #define VFIO_DEVICE_STOP 1 +#define VFIO_DEVICE_STATE_OFFSET 1 + /** * VFIO_DEVICE_GET_IRQ_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 9, * struct vfio_irq_info) -- 2.7.4