vfio/mlx5: Fallback to STOP_COPY upon specific PRE_COPY error

Before a SAVE command is issued, a QUERY command is issued in order to
know the device data size.
In case PRE_COPY is used, the above commands are issued while the device
is running. Thus, it is possible that between the QUERY and the SAVE
commands the state of the device will be changed significantly and thus
the SAVE will fail.

Currently, if a SAVE command is failing, the driver will fail the
migration. In the above case, don't fail the migration, but don't allow
for new SAVEs to be executed while the device is in a RUNNING state.
Once the device will be moved to STOP_COPY, SAVE can be executed again
and the full device state will be read.

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/20221206083438.37807-14-yishaih@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>

drivers/vfio/pci/mlx5/cmd.c

@@ -84,6 +84,19 @@ int mlx5vf_cmd_query_vhca_migration_state(struct mlx5vf_pci_core_device *mvdev,
 		ret = wait_for_completion_interruptible(&mvdev->saving_migf->save_comp);
 		if (ret)
 			return ret;
+		if (mvdev->saving_migf->state ==
+		    MLX5_MIGF_STATE_PRE_COPY_ERROR) {
+			/*
+			 * In case we had a PRE_COPY error, only query full
+			 * image for final image
+			 */
+			if (!(query_flags & MLX5VF_QUERY_FINAL)) {
+				*state_size = 0;
+				complete(&mvdev->saving_migf->save_comp);
+				return 0;
+			}
+			query_flags &= ~MLX5VF_QUERY_INC;
+		}
 	}
 
 	MLX5_SET(query_vhca_migration_state_in, in, opcode,
@@ -442,7 +455,10 @@ void mlx5vf_mig_file_cleanup_cb(struct work_struct *_work)
 		mlx5vf_put_data_buffer(async_data->buf);
 		if (async_data->header_buf)
 			mlx5vf_put_data_buffer(async_data->header_buf);
-		migf->state = MLX5_MIGF_STATE_ERROR;
+		if (async_data->status == MLX5_CMD_STAT_BAD_RES_STATE_ERR)
+			migf->state = MLX5_MIGF_STATE_PRE_COPY_ERROR;
+		else
+			migf->state = MLX5_MIGF_STATE_ERROR;
 		wake_up_interruptible(&migf->poll_wait);
 	}
 	mutex_unlock(&migf->lock);
@@ -511,6 +527,8 @@ static void mlx5vf_save_callback(int status, struct mlx5_async_work *context)
 	 * The error and the cleanup flows can't run from an
 	 * interrupt context
 	 */
+	if (status == -EREMOTEIO)
+		status = MLX5_GET(save_vhca_state_out, async_data->out, status);
 	async_data->status = status;
 	queue_work(migf->mvdev->cb_wq, &async_data->work);
 }
@@ -534,6 +552,13 @@ int mlx5vf_cmd_save_vhca_state(struct mlx5vf_pci_core_device *mvdev,
 	if (err)
 		return err;
 
+	if (migf->state == MLX5_MIGF_STATE_PRE_COPY_ERROR)
+		/*
+		 * In case we had a PRE_COPY error, SAVE is triggered only for
+		 * the final image, read device full image.
+		 */
+		inc = false;
+
 	MLX5_SET(save_vhca_state_in, in, opcode,
 		 MLX5_CMD_OP_SAVE_VHCA_STATE);
 	MLX5_SET(save_vhca_state_in, in, op_mod, 0);

drivers/vfio/pci/mlx5/cmd.h

@@ -17,6 +17,7 @@
 
 enum mlx5_vf_migf_state {
 	MLX5_MIGF_STATE_ERROR = 1,
+	MLX5_MIGF_STATE_PRE_COPY_ERROR,
 	MLX5_MIGF_STATE_PRE_COPY,
 	MLX5_MIGF_STATE_SAVE_LAST,
 	MLX5_MIGF_STATE_COMPLETE,
@@ -157,6 +158,7 @@ struct mlx5vf_pci_core_device {
 
 enum {
 	MLX5VF_QUERY_INC = (1UL << 0),
+	MLX5VF_QUERY_FINAL = (1UL << 1),
 };
 
 int mlx5vf_cmd_suspend_vhca(struct mlx5vf_pci_core_device *mvdev, u16 op_mod);

drivers/vfio/pci/mlx5/main.c

@@ -219,6 +219,7 @@ static ssize_t mlx5vf_save_read(struct file *filp, char __user *buf, size_t len,
 		if (wait_event_interruptible(migf->poll_wait,
 				!list_empty(&migf->buf_list) ||
 				migf->state == MLX5_MIGF_STATE_ERROR ||
+				migf->state == MLX5_MIGF_STATE_PRE_COPY_ERROR ||
 				migf->state == MLX5_MIGF_STATE_PRE_COPY ||
 				migf->state == MLX5_MIGF_STATE_COMPLETE))
 			return -ERESTARTSYS;
@@ -238,7 +239,8 @@ static ssize_t mlx5vf_save_read(struct file *filp, char __user *buf, size_t len,
 		if (first_loop_call) {
 			first_loop_call = false;
 			/* Temporary end of file as part of PRE_COPY */
-			if (end_of_data && migf->state == MLX5_MIGF_STATE_PRE_COPY) {
+			if (end_of_data && (migf->state == MLX5_MIGF_STATE_PRE_COPY ||
+				migf->state == MLX5_MIGF_STATE_PRE_COPY_ERROR)) {
 				done = -ENOMSG;
 				goto out_unlock;
 			}
@@ -431,7 +433,7 @@ static int mlx5vf_pci_save_device_inc_data(struct mlx5vf_pci_core_device *mvdev)
 		return -ENODEV;
 
 	ret = mlx5vf_cmd_query_vhca_migration_state(mvdev, &length,
-						    MLX5VF_QUERY_INC);
+				MLX5VF_QUERY_INC | MLX5VF_QUERY_FINAL);
 	if (ret)
 		goto err;