Adding support to checkpoint/restore GWS(Global Wave Sync) queues.
Signed-off-by: David Yat Sin <david.yatsin@xxxxxxx>
---
drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 2 +-
drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 4 ++--
.../amd/amdkfd/kfd_process_queue_manager.c | 22 ++++++++++++++-----
3 files changed, 19 insertions(+), 9 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index e1e2362841f8..b2c72ddd9c1c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -1377,7 +1377,7 @@ static int kfd_ioctl_alloc_queue_gws(struct file *filep,
goto out_unlock;
}
- retval = pqm_set_gws(&p->pqm, args->queue_id, args->num_gws ? dev->gws : NULL);
+ retval = pqm_set_gws(&p->pqm, args->queue_id, args->num_gws ? dev->gws : NULL, false);
mutex_unlock(&p->mutex);
args->first_gws = 0;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index f36062be9ca8..3ec32675210c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -1102,7 +1102,7 @@ struct kfd_criu_queue_priv_data {
uint32_t priority;
uint32_t q_percent;
uint32_t doorbell_id;
- uint32_t is_gws;
+ uint32_t gws;
uint32_t sdma_id;
uint32_t eop_ring_buffer_size;
uint32_t ctx_save_restore_area_size;
@@ -1199,7 +1199,7 @@ int pqm_update_queue_properties(struct process_queue_manager *pqm, unsigned int
int pqm_update_mqd(struct process_queue_manager *pqm, unsigned int qid,
struct mqd_update_info *minfo);
int pqm_set_gws(struct process_queue_manager *pqm, unsigned int qid,
- void *gws);
+ void *gws, bool criu_restore);
struct kernel_queue *pqm_get_kernel_queue(struct process_queue_manager *pqm,
unsigned int qid);
struct queue *pqm_get_user_queue(struct process_queue_manager *pqm,
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index 6eca9509f2e3..3eb9d43fdaac 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -91,7 +91,7 @@ void kfd_process_dequeue_from_device(struct kfd_process_device *pdd)
}
int pqm_set_gws(struct process_queue_manager *pqm, unsigned int qid,
- void *gws)
+ void *gws, bool criu_restore)
{
struct kfd_dev *dev = NULL;
struct process_queue_node *pqn;
@@ -135,8 +135,14 @@ int pqm_set_gws(struct process_queue_manager *pqm, unsigned int qid,
pqn->q->gws = mem;
pdd->qpd.num_gws = gws ? dev->adev->gds.gws_size : 0;
- return pqn->q->device->dqm->ops.update_queue(pqn->q->device->dqm,
- pqn->q, NULL);
+ ret = pqn->q->device->dqm->ops.update_queue(pqn->q->device->dqm,
+ pqn->q, NULL);
+
+ if (!ret && criu_restore) {
+ dev->dqm->gws_queue_count++;
+ pdd->qpd.mapped_gws_queue = true;
+ }
+ return ret;
}
void kfd_process_dequeue_from_all_devices(struct kfd_process *p)
@@ -636,6 +642,8 @@ static int criu_checkpoint_queue(struct kfd_process_device *pdd,
q_data->ctx_save_restore_area_size =
q->properties.ctx_save_restore_area_size;
+ q_data->gws = !!q->gws;
+
ret = pqm_checkpoint_mqd(&pdd->process->pqm, q->properties.queue_id, mqd, ctl_stack);
if (ret) {
pr_err("Failed checkpoint queue_mqd (%d)\n", ret);
@@ -743,7 +751,6 @@ static void set_queue_properties_from_criu(struct queue_properties *qp,
struct kfd_criu_queue_priv_data *q_data)
{
qp->is_interop = false;
- qp->is_gws = q_data->is_gws;
qp->queue_percent = q_data->q_percent;
qp->priority = q_data->priority;
qp->queue_address = q_data->q_address;
@@ -826,12 +833,15 @@ int kfd_criu_restore_queue(struct kfd_process *p,
NULL);
if (ret) {
pr_err("Failed to create new queue err:%d\n", ret);
- ret = -EINVAL;
+ goto exit;
}
+ if (q_data->gws)
+ ret = pqm_set_gws(&p->pqm, q_data->q_id, pdd->dev->gws, true);
+
exit:
if (ret)
- pr_err("Failed to create queue (%d)\n", ret);
+ pr_err("Failed to restore queue (%d)\n", ret);
else
pr_debug("Queue id %d was restored successfully\n", queue_id);
--
2.30.2
