Re: [PATCH mlx5-next 3/5] vfio/mlx5: Manage the VF attach/detach callback from the PF

[Alex Williamson <alex.williamson@redhat.com>]

On Wed, 27 Apr 2022 12:31:18 +0300
Yishai Hadas <yishaih@nvidia.com> wrote:

> Manage the VF attach/detach callback from the PF.
> 
> This lets the driver to enable parallel VFs migration as will be
> introduced in the next patch.
> 
> Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
> Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
> ---
>  drivers/vfio/pci/mlx5/cmd.c  | 59 +++++++++++++++++++++++++++++++++---
>  drivers/vfio/pci/mlx5/cmd.h  | 23 +++++++++++++-
>  drivers/vfio/pci/mlx5/main.c | 25 ++++-----------
>  3 files changed, 82 insertions(+), 25 deletions(-)
> 
> diff --git a/drivers/vfio/pci/mlx5/cmd.c b/drivers/vfio/pci/mlx5/cmd.c
> index d608b8167f58..1f84d7b9b9e5 100644
> --- a/drivers/vfio/pci/mlx5/cmd.c
> +++ b/drivers/vfio/pci/mlx5/cmd.c
> @@ -71,21 +71,70 @@ int mlx5vf_cmd_query_vhca_migration_state(struct pci_dev *pdev, u16 vhca_id,
>  	return ret;
>  }
>  
> -bool mlx5vf_cmd_is_migratable(struct pci_dev *pdev)
> +static int mlx5fv_vf_event(struct notifier_block *nb,
> +			   unsigned long event, void *data)
>  {
> -	struct mlx5_core_dev *mdev = mlx5_vf_get_core_dev(pdev);
> +	struct mlx5vf_pci_core_device *mvdev =
> +		container_of(nb, struct mlx5vf_pci_core_device, nb);
> +
> +	mutex_lock(&mvdev->state_mutex);
> +	switch (event) {
> +	case MLX5_PF_NOTIFY_ENABLE_VF:
> +		mvdev->mdev_detach = false;
> +		break;
> +	case MLX5_PF_NOTIFY_DISABLE_VF:
> +		mvdev->mdev_detach = true;
> +		break;
> +	default:
> +		break;
> +	}
> +	mlx5vf_state_mutex_unlock(mvdev);
> +	return 0;
> +}
> +
> +void mlx5vf_cmd_remove_migratable(struct mlx5vf_pci_core_device *mvdev)
> +{
> +	mlx5_sriov_blocking_notifier_unregister(mvdev->mdev, mvdev->vf_id,
> +						&mvdev->nb);
> +}
> +
> +bool mlx5vf_cmd_is_migratable(struct mlx5vf_pci_core_device *mvdev)

Why did the original implementation take a pdev knowing we're going to
gut it in the next patch to use an mvdev?  The diff would be easier to
read.

There's also quite a lot of setup here now, it's no longer a simple
test whether the device supports migration which makes the name
misleading.  This looks like a "setup migration" function that should
return 0/-errno.

> +{
> +	struct pci_dev *pdev = mvdev->core_device.pdev;
>  	bool migratable = false;
> +	int ret;
>  
> -	if (!mdev)
> +	mvdev->mdev = mlx5_vf_get_core_dev(pdev);
> +	if (!mvdev->mdev)
>  		return false;
> +	if (!MLX5_CAP_GEN(mvdev->mdev, migration))
> +		goto end;
> +	mvdev->vf_id = pci_iov_vf_id(pdev);
> +	if (mvdev->vf_id < 0)
> +		goto end;
>  
> -	if (!MLX5_CAP_GEN(mdev, migration))
> +	mutex_init(&mvdev->state_mutex);
> +	spin_lock_init(&mvdev->reset_lock);
> +	mvdev->nb.notifier_call = mlx5fv_vf_event;
> +	ret = mlx5_sriov_blocking_notifier_register(mvdev->mdev, mvdev->vf_id,
> +						    &mvdev->nb);
> +	if (ret)
>  		goto end;
>  
> +	mutex_lock(&mvdev->state_mutex);
> +	if (mvdev->mdev_detach)
> +		goto unreg;
> +
> +	mlx5vf_state_mutex_unlock(mvdev);
>  	migratable = true;
> +	goto end;
>  
> +unreg:
> +	mlx5vf_state_mutex_unlock(mvdev);
> +	mlx5_sriov_blocking_notifier_unregister(mvdev->mdev, mvdev->vf_id,
> +						&mvdev->nb);
>  end:
> -	mlx5_vf_put_core_dev(mdev);
> +	mlx5_vf_put_core_dev(mvdev->mdev);
>  	return migratable;
>  }
>  
> diff --git a/drivers/vfio/pci/mlx5/cmd.h b/drivers/vfio/pci/mlx5/cmd.h
> index 2da6a1c0ec5c..f47174eab4b8 100644
> --- a/drivers/vfio/pci/mlx5/cmd.h
> +++ b/drivers/vfio/pci/mlx5/cmd.h
> @@ -7,6 +7,7 @@
>  #define MLX5_VFIO_CMD_H
>  
>  #include <linux/kernel.h>
> +#include <linux/vfio_pci_core.h>
>  #include <linux/mlx5/driver.h>
>  
>  struct mlx5_vf_migration_file {
> @@ -24,14 +25,34 @@ struct mlx5_vf_migration_file {
>  	unsigned long last_offset;
>  };
>  
> +struct mlx5vf_pci_core_device {
> +	struct vfio_pci_core_device core_device;
> +	int vf_id;
> +	u16 vhca_id;
> +	u8 migrate_cap:1;
> +	u8 deferred_reset:1;
> +	/* protect migration state */
> +	struct mutex state_mutex;
> +	enum vfio_device_mig_state mig_state;
> +	/* protect the reset_done flow */
> +	spinlock_t reset_lock;
> +	struct mlx5_vf_migration_file *resuming_migf;
> +	struct mlx5_vf_migration_file *saving_migf;
> +	struct notifier_block nb;
> +	struct mlx5_core_dev *mdev;
> +	u8 mdev_detach:1;
> +};
> +
>  int mlx5vf_cmd_suspend_vhca(struct pci_dev *pdev, u16 vhca_id, u16 op_mod);
>  int mlx5vf_cmd_resume_vhca(struct pci_dev *pdev, u16 vhca_id, u16 op_mod);
>  int mlx5vf_cmd_query_vhca_migration_state(struct pci_dev *pdev, u16 vhca_id,
>  					  size_t *state_size);
>  int mlx5vf_cmd_get_vhca_id(struct pci_dev *pdev, u16 function_id, u16 *vhca_id);
> -bool mlx5vf_cmd_is_migratable(struct pci_dev *pdev);
> +bool mlx5vf_cmd_is_migratable(struct mlx5vf_pci_core_device *mvdev);
> +void mlx5vf_cmd_remove_migratable(struct mlx5vf_pci_core_device *mvdev);
>  int mlx5vf_cmd_save_vhca_state(struct pci_dev *pdev, u16 vhca_id,
>  			       struct mlx5_vf_migration_file *migf);
>  int mlx5vf_cmd_load_vhca_state(struct pci_dev *pdev, u16 vhca_id,
>  			       struct mlx5_vf_migration_file *migf);
> +void mlx5vf_state_mutex_unlock(struct mlx5vf_pci_core_device *mvdev);
>  #endif /* MLX5_VFIO_CMD_H */
> diff --git a/drivers/vfio/pci/mlx5/main.c b/drivers/vfio/pci/mlx5/main.c
> index 2578f61eaeae..445c516d38d9 100644
> --- a/drivers/vfio/pci/mlx5/main.c
> +++ b/drivers/vfio/pci/mlx5/main.c
> @@ -17,7 +17,6 @@
>  #include <linux/uaccess.h>
>  #include <linux/vfio.h>
>  #include <linux/sched/mm.h>
> -#include <linux/vfio_pci_core.h>
>  #include <linux/anon_inodes.h>
>  
>  #include "cmd.h"
> @@ -25,20 +24,6 @@
>  /* Arbitrary to prevent userspace from consuming endless memory */
>  #define MAX_MIGRATION_SIZE (512*1024*1024)
>  
> -struct mlx5vf_pci_core_device {
> -	struct vfio_pci_core_device core_device;
> -	u16 vhca_id;
> -	u8 migrate_cap:1;
> -	u8 deferred_reset:1;
> -	/* protect migration state */
> -	struct mutex state_mutex;
> -	enum vfio_device_mig_state mig_state;
> -	/* protect the reset_done flow */
> -	spinlock_t reset_lock;
> -	struct mlx5_vf_migration_file *resuming_migf;
> -	struct mlx5_vf_migration_file *saving_migf;
> -};
> -
>  static struct page *
>  mlx5vf_get_migration_page(struct mlx5_vf_migration_file *migf,
>  			  unsigned long offset)
> @@ -444,7 +429,7 @@ mlx5vf_pci_step_device_state_locked(struct mlx5vf_pci_core_device *mvdev,
>   * This function is called in all state_mutex unlock cases to
>   * handle a 'deferred_reset' if exists.
>   */
> -static void mlx5vf_state_mutex_unlock(struct mlx5vf_pci_core_device *mvdev)
> +void mlx5vf_state_mutex_unlock(struct mlx5vf_pci_core_device *mvdev)
>  {
>  again:
>  	spin_lock(&mvdev->reset_lock);
> @@ -597,13 +582,11 @@ static int mlx5vf_pci_probe(struct pci_dev *pdev,
>  		return -ENOMEM;
>  	vfio_pci_core_init_device(&mvdev->core_device, pdev, &mlx5vf_pci_ops);
>  
> -	if (pdev->is_virtfn && mlx5vf_cmd_is_migratable(pdev)) {
> +	if (pdev->is_virtfn && mlx5vf_cmd_is_migratable(mvdev)) {
>  		mvdev->migrate_cap = 1;
>  		mvdev->core_device.vdev.migration_flags =
>  			VFIO_MIGRATION_STOP_COPY |
>  			VFIO_MIGRATION_P2P;

Why do these aspects of setting up migration remain here?  Do we even
need this new function to have a return value?  It looks like all of
this and testing whether the pdev->is_virtfn could be pushed into the
new function, which could then return void.  Thanks,

Alex

> -		mutex_init(&mvdev->state_mutex);
> -		spin_lock_init(&mvdev->reset_lock);
>  	}
>  
>  	ret = vfio_pci_core_register_device(&mvdev->core_device);
> @@ -614,6 +597,8 @@ static int mlx5vf_pci_probe(struct pci_dev *pdev,
>  	return 0;
>  
>  out_free:
> +	if (mvdev->migrate_cap)
> +		mlx5vf_cmd_remove_migratable(mvdev);
>  	vfio_pci_core_uninit_device(&mvdev->core_device);
>  	kfree(mvdev);
>  	return ret;
> @@ -624,6 +609,8 @@ static void mlx5vf_pci_remove(struct pci_dev *pdev)
>  	struct mlx5vf_pci_core_device *mvdev = dev_get_drvdata(&pdev->dev);
>  
>  	vfio_pci_core_unregister_device(&mvdev->core_device);
> +	if (mvdev->migrate_cap)
> +		mlx5vf_cmd_remove_migratable(mvdev);
>  	vfio_pci_core_uninit_device(&mvdev->core_device);
>  	kfree(mvdev);
>  }