Commit 3a9822d7 authored by David Yat Sin's avatar David Yat Sin Committed by Alex Deucher
Browse files

drm/amdkfd: CRIU checkpoint and restore queue control stack 



Checkpoint contents of queue control stacks on CRIU dump and restore them
during CRIU restore.

Reviewed-by: default avatarFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: default avatarDavid Yat Sin <david.yatsin@amd.com>
Signed-off-by: default avatarRajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Signed-off-by: default avatarAlex Deucher <alexander.deucher@amd.com>
parent 42c6c482

drivers/gpu/drm/amd/amdkfd/kfd_chardev.c

+1 −1
Original line number Diff line number Diff line
@@ -311,7 +311,7 @@ static int kfd_ioctl_create_queue(struct file *filep, struct kfd_process *p, 
			p->pasid,

			dev->id);



	err = pqm_create_queue(&p->pqm, dev, filep, &q_properties, &queue_id, NULL, NULL,

	err = pqm_create_queue(&p->pqm, dev, filep, &q_properties, &queue_id, NULL, NULL, NULL,

			&doorbell_offset_in_process);

	if (err != 0)

		goto err_create_queue;

drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c

+1 −1
Original line number Diff line number Diff line
@@ -185,7 +185,7 @@ static int dbgdev_register_diq(struct kfd_dbgdev *dbgdev) 
	properties.type = KFD_QUEUE_TYPE_DIQ;



	status = pqm_create_queue(dbgdev->pqm, dbgdev->dev, NULL,

				&properties, &qid, NULL, NULL, NULL);

				&properties, &qid, NULL, NULL, NULL, NULL);



	if (status) {

		pr_err("Failed to create DIQ\n");

drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c

+15 −7
Original line number Diff line number Diff line
@@ -323,7 +323,7 @@ static int create_queue_nocpsch(struct device_queue_manager *dqm, 
				struct queue *q,

				struct qcm_process_device *qpd,

				const struct kfd_criu_queue_priv_data *qd,

				const void *restore_mqd)

				const void *restore_mqd, const void *restore_ctl_stack)

{

	struct mqd_manager *mqd_mgr;

	int retval;
@@ -385,7 +385,8 @@ static int create_queue_nocpsch(struct device_queue_manager *dqm, 


	if (qd)

		mqd_mgr->restore_mqd(mqd_mgr, &q->mqd, q->mqd_mem_obj, &q->gart_mqd_addr,

				     &q->properties, restore_mqd);

				     &q->properties, restore_mqd, restore_ctl_stack,

				     qd->ctl_stack_size);

	else

		mqd_mgr->init_mqd(mqd_mgr, &q->mqd, q->mqd_mem_obj,

					&q->gart_mqd_addr, &q->properties);
@@ -1342,7 +1343,7 @@ static void destroy_kernel_queue_cpsch(struct device_queue_manager *dqm, 
static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,

			struct qcm_process_device *qpd,

			const struct kfd_criu_queue_priv_data *qd,

			const void *restore_mqd)

			const void *restore_mqd, const void *restore_ctl_stack)

{

	int retval;

	struct mqd_manager *mqd_mgr;
@@ -1391,7 +1392,8 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q, 


	if (qd)

		mqd_mgr->restore_mqd(mqd_mgr, &q->mqd, q->mqd_mem_obj, &q->gart_mqd_addr,

				     &q->properties, restore_mqd);

				     &q->properties, restore_mqd, restore_ctl_stack,

				     qd->ctl_stack_size);

	else

		mqd_mgr->init_mqd(mqd_mgr, &q->mqd, q->mqd_mem_obj,

					&q->gart_mqd_addr, &q->properties);
@@ -1799,7 +1801,8 @@ static int get_wave_state(struct device_queue_manager *dqm, 


static void get_queue_checkpoint_info(struct device_queue_manager *dqm,

			const struct queue *q,

			u32 *mqd_size)

			u32 *mqd_size,

			u32 *ctl_stack_size)

{

	struct mqd_manager *mqd_mgr;

	enum KFD_MQD_TYPE mqd_type =
@@ -1808,13 +1811,18 @@ static void get_queue_checkpoint_info(struct device_queue_manager *dqm, 
	dqm_lock(dqm);

	mqd_mgr = dqm->mqd_mgrs[mqd_type];

	*mqd_size = mqd_mgr->mqd_size;

	*ctl_stack_size = 0;



	if (q->properties.type == KFD_QUEUE_TYPE_COMPUTE && mqd_mgr->get_checkpoint_info)

		mqd_mgr->get_checkpoint_info(mqd_mgr, q->mqd, ctl_stack_size);



	dqm_unlock(dqm);

}



static int checkpoint_mqd(struct device_queue_manager *dqm,

			  const struct queue *q,

			  void *mqd)

			  void *mqd,

			  void *ctl_stack)

{

	struct mqd_manager *mqd_mgr;

	int r = 0;
@@ -1834,7 +1842,7 @@ static int checkpoint_mqd(struct device_queue_manager *dqm, 
		goto dqm_unlock;

	}



	mqd_mgr->checkpoint_mqd(mqd_mgr, q->mqd, mqd);

	mqd_mgr->checkpoint_mqd(mqd_mgr, q->mqd, mqd, ctl_stack);



dqm_unlock:

	dqm_unlock(dqm);

drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h

+6 −3
Original line number Diff line number Diff line
@@ -93,7 +93,8 @@ struct device_queue_manager_ops { 
				struct queue *q,

				struct qcm_process_device *qpd,

				const struct kfd_criu_queue_priv_data *qd,

				const void *restore_mqd);

				const void *restore_mqd,

				const void *restore_ctl_stack);



	int	(*destroy_queue)(struct device_queue_manager *dqm,

				struct qcm_process_device *qpd,
@@ -145,11 +146,13 @@ struct device_queue_manager_ops { 
	int (*reset_queues)(struct device_queue_manager *dqm,

					uint16_t pasid);

	void	(*get_queue_checkpoint_info)(struct device_queue_manager *dqm,

				  const struct queue *q, u32 *mqd_size);

				  const struct queue *q, u32 *mqd_size,

				  u32 *ctl_stack_size);



	int	(*checkpoint_mqd)(struct device_queue_manager *dqm,

				  const struct queue *q,

				  void *mqd);

				  void *mqd,

				  void *ctl_stack);

};



struct device_queue_manager_asic_ops {

drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h

+9 −2
Original line number Diff line number Diff line
@@ -100,12 +100,19 @@ struct mqd_manager { 
				  u32 *ctl_stack_used_size,

				  u32 *save_area_used_size);



	void	(*checkpoint_mqd)(struct mqd_manager *mm, void *mqd, void *mqd_dst);

	void	(*get_checkpoint_info)(struct mqd_manager *mm, void *mqd, uint32_t *ctl_stack_size);



	void	(*checkpoint_mqd)(struct mqd_manager *mm,

				  void *mqd,

				  void *mqd_dst,

				  void *ctl_stack_dst);



	void	(*restore_mqd)(struct mqd_manager *mm, void **mqd,

				struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,

				struct queue_properties *p,

				const void *mqd_src);

				const void *mqd_src,

				const void *ctl_stack_src,

				const u32 ctl_stack_size);



#if defined(CONFIG_DEBUG_FS)

	int	(*debugfs_show_mqd)(struct seq_file *m, void *data);