vfio/mlx5: Introduce device transitions of PRE_COPY

In order to support PRE_COPY, mlx5 driver is transferring multiple
states (images) of the device. e.g.: the source VF can save and transfer
multiple states, and the target VF will load them by that order.

The device is saving three kinds of states:
1) Initial state - when the device moves to PRE_COPY state.
2) Middle state - during PRE_COPY phase via VFIO_MIG_GET_PRECOPY_INFO.
   There can be multiple states of this type.
3) Final state - when the device moves to STOP_COPY state.

After moving to PRE_COPY state, user is holding the saving migf FD and
can use it. For example: user can start transferring data via read()
callback. Also, user can switch from PRE_COPY to STOP_COPY whenever he
sees it fits. This will invoke saving of final state.

This means that mlx5 VFIO device can be switched to STOP_COPY without
transferring any data in PRE_COPY state. Therefore, when the device
moves to STOP_COPY, mlx5 will store the final state on a dedicated queue
entry on the list.

Co-developed-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Link: https://lore.kernel.org/r/20221206083438.37807-9-yishaih@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>

1 files changed, 14 insertions, 2 deletions

diff --git a/drivers/vfio/pci/mlx5/cmd.h b/drivers/vfio/pci/mlx5/cmd.h
index 6e594689566e..34e61c7aa23d 100644
--- a/drivers/vfio/pci/mlx5/cmd.h
+++ b/drivers/vfio/pci/mlx5/cmd.h
@@ -38,6 +38,7 @@ struct mlx5vf_async_data {
 	struct work_struct work;
 	struct mlx5_vhca_data_buffer *buf;
 	int status;
+	u8 last_chunk:1;
 	void *out;
 };
 
@@ -47,9 +48,11 @@ struct mlx5_vf_migration_file {
 	enum mlx5_vf_migf_state state;
 
 	u32 pdn;
+	loff_t max_pos;
 	struct mlx5_vhca_data_buffer *buf;
 	spinlock_t list_lock;
 	struct list_head buf_list;
+	struct list_head avail_list;
 	struct mlx5vf_pci_core_device *mvdev;
 	wait_queue_head_t poll_wait;
 	struct completion save_comp;
@@ -129,10 +132,14 @@ struct mlx5vf_pci_core_device {
 	struct mlx5_core_dev *mdev;
 };
 
+enum {
+	MLX5VF_QUERY_INC = (1UL << 0),
+};
+
 int mlx5vf_cmd_suspend_vhca(struct mlx5vf_pci_core_device *mvdev, u16 op_mod);
 int mlx5vf_cmd_resume_vhca(struct mlx5vf_pci_core_device *mvdev, u16 op_mod);
 int mlx5vf_cmd_query_vhca_migration_state(struct mlx5vf_pci_core_device *mvdev,
-					  size_t *state_size);
+					  size_t *state_size, u8 query_flags);
 void mlx5vf_cmd_set_migratable(struct mlx5vf_pci_core_device *mvdev,
 			       const struct vfio_migration_ops *mig_ops,
 			       const struct vfio_log_ops *log_ops);
@@ -140,7 +147,8 @@ void mlx5vf_cmd_remove_migratable(struct mlx5vf_pci_core_device *mvdev);
 void mlx5vf_cmd_close_migratable(struct mlx5vf_pci_core_device *mvdev);
 int mlx5vf_cmd_save_vhca_state(struct mlx5vf_pci_core_device *mvdev,
 			       struct mlx5_vf_migration_file *migf,
-			       struct mlx5_vhca_data_buffer *buf);
+			       struct mlx5_vhca_data_buffer *buf, bool inc,
+			       bool track);
 int mlx5vf_cmd_load_vhca_state(struct mlx5vf_pci_core_device *mvdev,
 			       struct mlx5_vf_migration_file *migf,
 			       struct mlx5_vhca_data_buffer *buf);
@@ -151,6 +159,10 @@ struct mlx5_vhca_data_buffer *
 mlx5vf_alloc_data_buffer(struct mlx5_vf_migration_file *migf,
 			 size_t length, enum dma_data_direction dma_dir);
 void mlx5vf_free_data_buffer(struct mlx5_vhca_data_buffer *buf);
+struct mlx5_vhca_data_buffer *
+mlx5vf_get_data_buffer(struct mlx5_vf_migration_file *migf,
+		       size_t length, enum dma_data_direction dma_dir);
+void mlx5vf_put_data_buffer(struct mlx5_vhca_data_buffer *buf);
 int mlx5vf_add_migration_pages(struct mlx5_vhca_data_buffer *buf,
 			       unsigned int npages);
 void mlx5vf_state_mutex_unlock(struct mlx5vf_pci_core_device *mvdev);