Re: [PATCH v4 3/5] hisi_acc_vfio_pci: register debugfs for hisilicon migration driver

[Jason Gunthorpe]

On Fri, Dec 02, 2022 at 05:26:23PM +0800, Longfang Liu wrote:
> On the debugfs framework of VFIO, register the debug function
> for the live migration driver of the hisilicon accelerator device.
> 
> On the basis of the original public debug function, a private debug
> function is added, so that the single-step debugging function
> during live migration can be realized.
> 
> Signed-off-by: Longfang Liu <liulongfang@xxxxxxxxxx>
> ---
>  .../vfio/pci/hisilicon/hisi_acc_vfio_pci.c    | 250 ++++++++++++++++++
>  .../vfio/pci/hisilicon/hisi_acc_vfio_pci.h    |   9 +
>  drivers/vfio/pci/vfio_pci_debugfs.c           |  10 +-
>  3 files changed, 268 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
> index eb18edffbd5f..0f35cde6e8ec 100644
> --- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
> +++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
> @@ -15,6 +15,7 @@
>  #include <linux/anon_inodes.h>
>  
>  #include "hisi_acc_vfio_pci.h"
> +#include "../vfio_pci_debugfs.h"
>  
>  /* Return 0 on VM acc device ready, -ETIMEDOUT hardware timeout */
>  static int qm_wait_dev_not_ready(struct hisi_qm *qm)
> @@ -609,6 +610,18 @@ hisi_acc_check_int_state(struct hisi_acc_vf_core_device *hisi_acc_vdev)
>  	}
>  }
>  
> +static void hisi_acc_vf_migf_save(struct hisi_acc_vf_migration_file *src_migf,
> +	struct hisi_acc_vf_migration_file *dst_migf)
> +{
> +	if (!dst_migf)
> +		return;
> +
> +	dst_migf->disabled = false;
> +	dst_migf->total_length = src_migf->total_length;
> +	memcpy(&dst_migf->vf_data, &src_migf->vf_data,
> +		    sizeof(struct acc_vf_data));
> +}
> +
>  static void hisi_acc_vf_disable_fd(struct hisi_acc_vf_migration_file *migf)
>  {
>  	mutex_lock(&migf->lock);
> @@ -621,12 +634,16 @@ static void hisi_acc_vf_disable_fd(struct hisi_acc_vf_migration_file *migf)
>  static void hisi_acc_vf_disable_fds(struct hisi_acc_vf_core_device *hisi_acc_vdev)
>  {
>  	if (hisi_acc_vdev->resuming_migf) {
> +		hisi_acc_vf_migf_save(hisi_acc_vdev->resuming_migf,
> +						hisi_acc_vdev->debug_migf);
>  		hisi_acc_vf_disable_fd(hisi_acc_vdev->resuming_migf);
>  		fput(hisi_acc_vdev->resuming_migf->filp);
>  		hisi_acc_vdev->resuming_migf = NULL;
>  	}
>  
>  	if (hisi_acc_vdev->saving_migf) {
> +		hisi_acc_vf_migf_save(hisi_acc_vdev->saving_migf,
> +						hisi_acc_vdev->debug_migf);
>  		hisi_acc_vf_disable_fd(hisi_acc_vdev->saving_migf);
>  		fput(hisi_acc_vdev->saving_migf->filp);
>  		hisi_acc_vdev->saving_migf = NULL;
> @@ -1188,6 +1205,231 @@ static long hisi_acc_vfio_pci_ioctl(struct vfio_device *core_vdev, unsigned int
>  	return vfio_pci_core_ioctl(core_vdev, cmd, arg);
>  }
>  
> +static int hisi_acc_vf_debug_io(struct vfio_device *vdev)
> +{
> +	struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_get_vf_dev(vdev);
> +	struct hisi_qm *vf_qm = &hisi_acc_vdev->vf_qm;
> +	struct device *dev = vdev->dev;
> +	u64 data;
> +	int ret;
> +
> +	data = readl(vf_qm->io_base + QM_MB_CMD_SEND_BASE);
> +	dev_info(dev, "debug mailbox val: 0x%llx\n", data);
> +
> +	ret = qm_wait_dev_not_ready(vf_qm);
> +	if (ret)
> +		dev_err(dev, "VF device not ready!\n");

debugfs has helpers for this, you should use debugfs_print_regs32()

> +static int hisi_acc_vf_debug_resume(struct vfio_device *vdev)
> +{
> +	struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_get_vf_dev(vdev);
> +	struct hisi_acc_vf_migration_file *migf = hisi_acc_vdev->debug_migf;
> +	struct device *dev = vdev->dev;
> +	int ret;
> +
> +	ret = vf_qm_state_save(hisi_acc_vdev, migf);
> +	if (ret) {
> +		dev_err(dev, "failed to save device data!\n");
> +		return -EINVAL;
> +	}
> +
> +	ret = vf_qm_check_match(hisi_acc_vdev, migf);
> +	if (ret) {
> +		dev_err(dev, "failed to match the VF!\n");
> +		return -EINVAL;
> +	}
> +
> +	ret = vf_qm_load_data(hisi_acc_vdev, migf);
> +	if (ret) {
> +		dev_err(dev, "failed to recover the VF!\n");
> +		return -EINVAL;
> +	}
> +
> +	vf_qm_fun_reset(&hisi_acc_vdev->vf_qm);
> +	dev_info(dev, "successful to resume device data!\n");
> +
> +	return 0;
> +}

This doesn't seem like it belongs in debugfs at all, please just write
a test progam using normal vfio ioctls to do these steps and put in
the kernel selftests directory.

> +static int hisi_acc_vf_debug_save(struct vfio_device *vdev)
> +{
> +	struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_get_vf_dev(vdev);
> +	struct hisi_acc_vf_migration_file *migf = hisi_acc_vdev->debug_migf;
> +	struct device *dev = vdev->dev;
> +	int ret;
> +
> +	ret = vf_qm_state_save(hisi_acc_vdev, migf);
> +	if (ret) {
> +		dev_err(dev, "failed to save device data!\n");
> +		return -EINVAL;
> +	}
> +	dev_info(dev, "successful to save device data!\n");
> +
> +	return 0;
> +}

Ditto, I don't think debugfs should be accessing the device state
independently of the main FSM.

Jason