On Fri, 1 Sep 2023 10:36:05 +0800
liulongfang <liulongfang@xxxxxxxxxx> wrote:
> From: Longfang Liu <liulongfang@xxxxxxxxxx>
>
> 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"
> Finally, create a directory file based on the device type,
> and then create the device's own debugging files under
> this directory file.
>
> Signed-off-by: Longfang Liu <liulongfang@xxxxxxxxxx>
> ---
> drivers/vfio/Makefile | 1 +
> drivers/vfio/vfio.h | 14 +++++++
> drivers/vfio/vfio_debugfs.c | 80 +++++++++++++++++++++++++++++++++++++
> drivers/vfio/vfio_main.c | 5 ++-
> include/linux/vfio.h | 7 ++++
> 5 files changed, 106 insertions(+), 1 deletion(-)
> create mode 100644 drivers/vfio/vfio_debugfs.c
>
> diff --git a/drivers/vfio/Makefile b/drivers/vfio/Makefile
> index c82ea032d352..7934ac829989 100644
> --- a/drivers/vfio/Makefile
> +++ b/drivers/vfio/Makefile
> @@ -8,6 +8,7 @@ vfio-$(CONFIG_VFIO_GROUP) += group.o
> vfio-$(CONFIG_IOMMUFD) += iommufd.o
> vfio-$(CONFIG_VFIO_CONTAINER) += container.o
> vfio-$(CONFIG_VFIO_VIRQFD) += virqfd.o
> +vfio-$(CONFIG_DEBUG_FS) += vfio_debugfs.o
>
> obj-$(CONFIG_VFIO_IOMMU_TYPE1) += vfio_iommu_type1.o
> obj-$(CONFIG_VFIO_IOMMU_SPAPR_TCE) += vfio_iommu_spapr_tce.o
> diff --git a/drivers/vfio/vfio.h b/drivers/vfio/vfio.h
> index 307e3f29b527..09b00757d0bb 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_DEBUG_FS
> +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_DEBUG_FS */
> +
> #endif
> diff --git a/drivers/vfio/vfio_debugfs.c b/drivers/vfio/vfio_debugfs.c
> new file mode 100644
> index 000000000000..cd6c01437475
> --- /dev/null
> +++ b/drivers/vfio/vfio_debugfs.c
> @@ -0,0 +1,80 @@
> +// 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;
> +
> + ret = vdev->mig_ops->migration_get_state(vdev, &state);
> + if (ret)
> + return -EINVAL;
> +
> + 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", "RUNNING_P2P");
> + break;
> + case VFIO_DEVICE_STATE_ERROR:
> + seq_printf(seq, "%s\n", "ERROR");
Please order these the same as enum vfio_device_mig_state, we're also
missing a couple states, ie. PRE_COPY and PRE_COPY_P2P. Can we use any
compiler tricks to create a build error when these are out of sync?
> + break;
> + default:
> + seq_printf(seq, "%s\n", "Invalid");
> + }
> +
> + return 0;
> +}
> +
> +void vfio_device_debugfs_init(struct vfio_device *vdev)
> +{
> + struct dentry *vfio_dev_migration = NULL;
> + struct device *dev = &vdev->device;
Nit, both of these could be defined within the scope of the mig_ops
test below.
> +
> + vdev->debug_root = debugfs_create_dir(dev_name(vdev->dev), vfio_debugfs_root);
> +
> + if (vdev->mig_ops) {
> + 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_main.c b/drivers/vfio/vfio_main.c
> index cfad824d9aa2..8a7456f89842 100644
> --- a/drivers/vfio/vfio_main.c
> +++ b/drivers/vfio/vfio_main.c
> @@ -309,7 +309,7 @@ static int __vfio_register_dev(struct vfio_device *device,
>
> /* Refcounting can't start until the driver calls register */
> refcount_set(&device->refcount, 1);
> -
> + vfio_device_debugfs_init(device);
> vfio_device_group_register(device);
>
> return 0;
> @@ -378,6 +378,7 @@ 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);
> }
init/exit calls should try to be symmetric, if we call init before
vfio_device_group_register() then we should call exit after
vfio_device_group_unregister(). In this case, why shouldn't init be
the last call in __vfio_register_dev() and exit the first call in
vfio_unregister_group_dev()?
> @@ -1662,6 +1663,7 @@ 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;
>
> @@ -1684,6 +1686,7 @@ static void __exit vfio_cleanup(void)
> vfio_virqfd_exit();
> vfio_group_cleanup();
> xa_destroy(&vfio_device_set_xa);
> + vfio_debugfs_remove_root();
> }
Same, if we create it last, let's remove it first. The above creates
it last and removes it last. Thanks,
Alex
>
> module_init(vfio_init);
> diff --git a/include/linux/vfio.h b/include/linux/vfio.h
> index 454e9295970c..769d7af86225 100644
> --- a/include/linux/vfio.h
> +++ b/include/linux/vfio.h
> @@ -69,6 +69,13 @@ struct vfio_device {
> u8 iommufd_attached:1;
> #endif
> u8 cdev_opened:1;
> +#ifdef CONFIG_DEBUG_FS
> + /*
> + * debug_root is a static property of the vfio_device
> + * which must be set prior to registering the vfio_device.
> + */
> + struct dentry *debug_root;
> +#endif
> };
>
> /**
