On Sat, Dec 17, 2022 at 02:32:44PM +0800, Longfang Liu wrote:
There are multiple devices, software and operational steps involved in the process of live migration. An error occurred on any node may cause the live migration operation to fail. This complex process makes it very difficult to locate and analyze the cause when the function fails.
In order to quickly locate the cause of the problem when the live migration fails, I added a set of debugfs to the vfio live migration driver.
+------------------------------------------+ | | | | | QEMU | | | | | +-----+-------------------------+----------+ | ^ | ^ v | v | +-----+--+ +-----+--+ | src VF | | dst VF | +-+------+ +-+------+ | ^ | ^ v | v | +-------+-+------+ +-------+-+------+ |Debugfs|state | |Debugfs|state | +-------+--------+ +-------+--------+ | debug_root | | debug_root | +-------+--------+ +-------+--------+
debugfs will create a public root directory "vfio_mig" file. then create a "debug_root" file for each live migration VF device. state file: used to get the status of the live migration device. debug_root: used to create your own custom debug files for live migration device drivers.
The live migration function of the current device can be tested by operating the debug files, and the functional status of the equipment and software at each stage can be tested step by step without performing the complete live migration function. And after the live migration is performed, the migration device data of the live migration can be obtained through the debug files.
Signed-off-by: Longfang Liu liulongfang@huawei.com
drivers/vfio/pci/Makefile | 4 ++ drivers/vfio/pci/vfio_pci_core.c | 3 ++ drivers/vfio/pci/vfio_pci_debugfs.c | 76 +++++++++++++++++++++++++++++ drivers/vfio/pci/vfio_pci_debugfs.h | 30 ++++++++++++ include/linux/vfio.h | 6 +++ 5 files changed, 119 insertions(+) create mode 100644 drivers/vfio/pci/vfio_pci_debugfs.c create mode 100644 drivers/vfio/pci/vfio_pci_debugfs.h
diff --git a/drivers/vfio/pci/Makefile b/drivers/vfio/pci/Makefile index 24c524224da5..efe032623664 100644 --- a/drivers/vfio/pci/Makefile +++ b/drivers/vfio/pci/Makefile @@ -4,6 +4,10 @@ vfio-pci-core-y := vfio_pci_core.o vfio_pci_intrs.o vfio_pci_rdwr.o vfio_pci_con vfio-pci-core-$(CONFIG_VFIO_PCI_ZDEV_KVM) += vfio_pci_zdev.o obj-$(CONFIG_VFIO_PCI_CORE) += vfio-pci-core.o
+ifneq ($(CONFIG_DEBUG_FS),)
- vfio-pci-core-y += vfio_pci_debugfs.o
+endif
This is now how makefile should be written
vfio-pci-core-$(CONFIG_DEBUG_FS) += vfio_pci_debugfs.o
+static int vfio_pci_vf_state_read(struct seq_file *seq, void *data) +{
- struct device *vf_dev = seq->private;
- struct vfio_pci_core_device *core_device = dev_get_drvdata(vf_dev);
- struct vfio_device *vdev = &core_device->vdev;
- enum vfio_device_mig_state state;
- (void)vdev->mig_ops->migration_get_state(vdev, &state);
Do not use (void) like this, and why not handle the error?
- switch (state) {
- case VFIO_DEVICE_STATE_RUNNING:
seq_printf(seq, "%s\n", "RUNNING");break;- case VFIO_DEVICE_STATE_STOP_COPY:
seq_printf(seq, "%s\n", "STOP_COPY");break;- case VFIO_DEVICE_STATE_STOP:
seq_printf(seq, "%s\n", "STOP");break;- case VFIO_DEVICE_STATE_RESUMING:
seq_printf(seq, "%s\n", "RESUMING");break;- case VFIO_DEVICE_STATE_RUNNING_P2P:
seq_printf(seq, "%s\n", "RESUMING_P2P");break;- case VFIO_DEVICE_STATE_ERROR:
seq_printf(seq, "%s\n", "ERROR");break;- default:
seq_printf(seq, "%s\n", "Invalid");- }
- return 0;
+}
+void vfio_pci_vf_debugfs_init(struct vfio_device *vdev) +{
- struct device *dev = vdev->dev;
- vdev->debug_root = debugfs_create_dir(dev_name(dev), vfio_pci_debugfs_root);
- debugfs_create_devm_seqfile(dev, "state", vdev->debug_root,
vfio_pci_vf_state_read);+} +EXPORT_SYMBOL_GPL(vfio_pci_vf_debugfs_init);
+void vfio_pci_vf_debugfs_exit(struct vfio_device *vdev) +{
- debugfs_remove_recursive(vdev->debug_root);
+} +EXPORT_SYMBOL_GPL(vfio_pci_vf_debugfs_exit);
+void vfio_pci_debugfs_create_root(void) +{
- vfio_pci_debugfs_root = debugfs_create_dir("vfio_mig", NULL);
+} +EXPORT_SYMBOL_GPL(vfio_pci_debugfs_create_root);
+void vfio_pci_debugfs_remove_root(void) +{
- debugfs_remove_recursive(vfio_pci_debugfs_root);
- vfio_pci_debugfs_root = NULL;
+} +EXPORT_SYMBOL_GPL(vfio_pci_debugfs_remove_root);
Why are these exported symbols? The core code should handle this on its own.
If the device defines migration_get_state() then the debugfs should be created.
Mabye you need an op to populate the driver's debugfs to also trigger creating the directory
Jason