vfio/migration: Add debugfs to live migration driver

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 vfio_dev|               |dst vfio_dev|
     +--+---------+               +--+---------+
        |      ^                     |      ^
        |      |                     |      |
        v      |                     |      |
   +-----------+----+           +-----------+----+
   |src dev debugfs |           |dst dev debugfs |
   +----------------+           +----------------+

The entire debugfs directory will be based on the definition of
the CONFIG_DEBUG_FS macro. If this macro is not enabled, the
interfaces in vfio.h will be empty definitions, and the creation
and initialization of the debugfs directory will not be executed.

   vfio
    |
    +---<dev_name1>
    |    +---migration
    |        +--state
    |
    +---<dev_name2>
         +---migration
             +--state

debugfs will create a public root directory "vfio" file.
then create a dev_name() file for each live migration device.
First, create a unified state acquisition file of "migration"
in this device directory.
Then, create a public live migration state lookup file "state".

Signed-off-by: Longfang Liu <liulongfang@huawei.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/r/20231106072225.28577-2-liulongfang@huawei.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>

5 files changed, 121 insertions, 0 deletions

diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig
index 6bda6dbb4878..ceae52fd7586 100644
--- a/drivers/vfio/Kconfig
+++ b/drivers/vfio/Kconfig
@@ -80,6 +80,16 @@ config VFIO_VIRQFD
 	select EVENTFD
 	default n
 
+config VFIO_DEBUGFS
+	bool "Export VFIO internals in DebugFS"
+	depends on DEBUG_FS
+	help
+	  Allows exposure of VFIO device internals. This option enables
+	  the use of debugfs by VFIO drivers as required. The device can
+	  cause the VFIO code create a top-level debug/vfio directory
+	  during initialization, and then populate a subdirectory with
+	  entries as required.
+
 source "drivers/vfio/pci/Kconfig"
 source "drivers/vfio/platform/Kconfig"
 source "drivers/vfio/mdev/Kconfig"
diff --git a/drivers/vfio/Makefile b/drivers/vfio/Makefile
index 68c05705200f..b2fc9fb499d8 100644
--- a/drivers/vfio/Makefile
+++ b/drivers/vfio/Makefile
@@ -7,6 +7,7 @@ vfio-$(CONFIG_VFIO_GROUP) += group.o
 vfio-$(CONFIG_IOMMUFD) += iommufd.o
 vfio-$(CONFIG_VFIO_CONTAINER) += container.o
 vfio-$(CONFIG_VFIO_VIRQFD) += virqfd.o
+vfio-$(CONFIG_VFIO_DEBUGFS) += debugfs.o
 
 obj-$(CONFIG_VFIO_IOMMU_TYPE1) += vfio_iommu_type1.o
 obj-$(CONFIG_VFIO_IOMMU_SPAPR_TCE) += vfio_iommu_spapr_tce.o
diff --git a/drivers/vfio/debugfs.c b/drivers/vfio/debugfs.c
new file mode 100644
index 000000000000..298bd866f157
--- /dev/null
+++ b/drivers/vfio/debugfs.c
@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2023, HiSilicon Ltd.
+ */
+
+#include <linux/device.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/vfio.h>
+#include "vfio.h"
+
+static struct dentry *vfio_debugfs_root;
+
+static int vfio_device_state_read(struct seq_file *seq, void *data)
+{
+	struct device *vf_dev = seq->private;
+	struct vfio_device *vdev = container_of(vf_dev,
+						struct vfio_device, device);
+	enum vfio_device_mig_state state;
+	int ret;
+
+	BUILD_BUG_ON(VFIO_DEVICE_STATE_NR !=
+		     VFIO_DEVICE_STATE_PRE_COPY_P2P + 1);
+
+	ret = vdev->mig_ops->migration_get_state(vdev, &state);
+	if (ret)
+		return -EINVAL;
+
+	switch (state) {
+	case VFIO_DEVICE_STATE_ERROR:
+		seq_puts(seq, "ERROR\n");
+		break;
+	case VFIO_DEVICE_STATE_STOP:
+		seq_puts(seq, "STOP\n");
+		break;
+	case VFIO_DEVICE_STATE_RUNNING:
+		seq_puts(seq, "RUNNING\n");
+		break;
+	case VFIO_DEVICE_STATE_STOP_COPY:
+		seq_puts(seq, "STOP_COPY\n");
+		break;
+	case VFIO_DEVICE_STATE_RESUMING:
+		seq_puts(seq, "RESUMING\n");
+		break;
+	case VFIO_DEVICE_STATE_RUNNING_P2P:
+		seq_puts(seq, "RUNNING_P2P\n");
+		break;
+	case VFIO_DEVICE_STATE_PRE_COPY:
+		seq_puts(seq, "PRE_COPY\n");
+		break;
+	case VFIO_DEVICE_STATE_PRE_COPY_P2P:
+		seq_puts(seq, "PRE_COPY_P2P\n");
+		break;
+	default:
+		seq_puts(seq, "Invalid\n");
+	}
+
+	return 0;
+}
+
+void vfio_device_debugfs_init(struct vfio_device *vdev)
+{
+	struct device *dev = &vdev->device;
+
+	vdev->debug_root = debugfs_create_dir(dev_name(vdev->dev),
+					      vfio_debugfs_root);
+
+	if (vdev->mig_ops) {
+		struct dentry *vfio_dev_migration = NULL;
+
+		vfio_dev_migration = debugfs_create_dir("migration",
+							vdev->debug_root);
+		debugfs_create_devm_seqfile(dev, "state", vfio_dev_migration,
+					    vfio_device_state_read);
+	}
+}
+
+void vfio_device_debugfs_exit(struct vfio_device *vdev)
+{
+	debugfs_remove_recursive(vdev->debug_root);
+}
+
+void vfio_debugfs_create_root(void)
+{
+	vfio_debugfs_root = debugfs_create_dir("vfio", NULL);
+}
+
+void vfio_debugfs_remove_root(void)
+{
+	debugfs_remove_recursive(vfio_debugfs_root);
+	vfio_debugfs_root = NULL;
+}
diff --git a/drivers/vfio/vfio.h b/drivers/vfio/vfio.h
index 307e3f29b527..bde84ad344e5 100644
--- a/drivers/vfio/vfio.h
+++ b/drivers/vfio/vfio.h
@@ -448,4 +448,18 @@ static inline void vfio_device_put_kvm(struct vfio_device *device)
 }
 #endif
 
+#ifdef CONFIG_VFIO_DEBUGFS
+void vfio_debugfs_create_root(void);
+void vfio_debugfs_remove_root(void);
+
+void vfio_device_debugfs_init(struct vfio_device *vdev);
+void vfio_device_debugfs_exit(struct vfio_device *vdev);
+#else
+static inline void vfio_debugfs_create_root(void) { }
+static inline void vfio_debugfs_remove_root(void) { }
+
+static inline void vfio_device_debugfs_init(struct vfio_device *vdev) { }
+static inline void vfio_device_debugfs_exit(struct vfio_device *vdev) { }
+#endif /* CONFIG_VFIO_DEBUGFS */
+
 #endif
diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c
index 8d4995ada74a..1cc93aac99a2 100644
--- a/drivers/vfio/vfio_main.c
+++ b/drivers/vfio/vfio_main.c
@@ -311,6 +311,7 @@ static int __vfio_register_dev(struct vfio_device *device,
 	refcount_set(&device->refcount, 1);
 
 	vfio_device_group_register(device);
+	vfio_device_debugfs_init(device);
 
 	return 0;
 err_out:
@@ -378,6 +379,7 @@ void vfio_unregister_group_dev(struct vfio_device *device)
 		}
 	}
 
+	vfio_device_debugfs_exit(device);
 	/* Balances vfio_device_set_group in register path */
 	vfio_device_remove_group(device);
 }
@@ -1676,6 +1678,7 @@ static int __init vfio_init(void)
 	if (ret)
 		goto err_alloc_dev_chrdev;
 
+	vfio_debugfs_create_root();
 	pr_info(DRIVER_DESC " version: " DRIVER_VERSION "\n");
 	return 0;
 
@@ -1691,6 +1694,7 @@ err_virqfd:
 
 static void __exit vfio_cleanup(void)
 {
+	vfio_debugfs_remove_root();
 	ida_destroy(&vfio.device_ida);
 	vfio_cdev_cleanup();
 	class_destroy(vfio.device_class);