drm/amdkfd: Enable GFX11 usermode queue oversubscription

Starting with GFX11, MES requires wptr BOs to be GTT allocated/mapped to
GART for usermode queues in order to support oversubscription. In the
case that work is submitted to an unmapped queue, MES must have a GART
wptr address to determine whether the queue should be mapped.

This change is accompanied with changes in MES and is applicable for
MES_API_VERSION >= 2.

v3:
- Use amdgpu_vm_bo_lookup_mapping for wptr_bo mapping lookup
- Move wptr_bo refcount increment to amdgpu_amdkfd_map_gtt_bo_to_gart
- Remove list_del_init from amdgpu_amdkfd_map_gtt_bo_to_gart
- Cleanup/fix create_queue wptr_bo error handling
v4:
- Add MES version shift/mask defines to amdgpu_mes.h
- Change version check from MES_VERSION to MES_API_VERSION
- Add check in kfd_ioctl_create_queue before wptr bo pin/GART map to
ensure bo is a single page.

Signed-off-by: Graham Sider <Graham.Sider@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Philip Yang <Philip.Yang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

5 files changed, 68 insertions, 8 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 3bcf9bf29acb..d07588230ed6 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -299,6 +299,7 @@ static int kfd_ioctl_create_queue(struct file *filep, struct kfd_process *p,
 	struct kfd_process_device *pdd;
 	struct queue_properties q_properties;
 	uint32_t doorbell_offset_in_process = 0;
+	struct amdgpu_bo *wptr_bo = NULL;
 
 	memset(&q_properties, 0, sizeof(struct queue_properties));
 
@@ -326,12 +327,49 @@ static int kfd_ioctl_create_queue(struct file *filep, struct kfd_process *p,
 		goto err_bind_process;
 	}
 
+	/* Starting with GFX11, wptr BOs must be mapped to GART for MES to determine work
+	 * on unmapped queues for usermode queue oversubscription (no aggregated doorbell)
+	 */
+	if (dev->shared_resources.enable_mes &&
+			((dev->adev->mes.sched_version & AMDGPU_MES_API_VERSION_MASK)
+			>> AMDGPU_MES_API_VERSION_SHIFT) >= 2) {
+		struct amdgpu_bo_va_mapping *wptr_mapping;
+		struct amdgpu_vm *wptr_vm;
+
+		wptr_vm = drm_priv_to_vm(pdd->drm_priv);
+		err = amdgpu_bo_reserve(wptr_vm->root.bo, false);
+		if (err)
+			goto err_wptr_map_gart;
+
+		wptr_mapping = amdgpu_vm_bo_lookup_mapping(
+				wptr_vm, args->write_pointer_address >> PAGE_SHIFT);
+		amdgpu_bo_unreserve(wptr_vm->root.bo);
+		if (!wptr_mapping) {
+			pr_err("Failed to lookup wptr bo\n");
+			err = -EINVAL;
+			goto err_wptr_map_gart;
+		}
+
+		wptr_bo = wptr_mapping->bo_va->base.bo;
+		if (wptr_bo->tbo.base.size > PAGE_SIZE) {
+			pr_err("Requested GART mapping for wptr bo larger than one page\n");
+			err = -EINVAL;
+			goto err_wptr_map_gart;
+		}
+
+		err = amdgpu_amdkfd_map_gtt_bo_to_gart(dev->adev, wptr_bo);
+		if (err) {
+			pr_err("Failed to map wptr bo to GART\n");
+			goto err_wptr_map_gart;
+		}
+	}
+
 	pr_debug("Creating queue for PASID 0x%x on gpu 0x%x\n",
 			p->pasid,
 			dev->id);
 
-	err = pqm_create_queue(&p->pqm, dev, filep, &q_properties, &queue_id, NULL, NULL, NULL,
-			&doorbell_offset_in_process);
+	err = pqm_create_queue(&p->pqm, dev, filep, &q_properties, &queue_id, wptr_bo,
+			NULL, NULL, NULL, &doorbell_offset_in_process);
 	if (err != 0)
 		goto err_create_queue;
 
@@ -363,6 +401,9 @@ static int kfd_ioctl_create_queue(struct file *filep, struct kfd_process *p,
 	return 0;
 
 err_create_queue:
+	if (wptr_bo)
+		amdgpu_amdkfd_free_gtt_mem(dev->adev, wptr_bo);
+err_wptr_map_gart:
 err_bind_process:
 err_pdd:
 	mutex_unlock(&p->mutex);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 213246a5b4e4..299927a4959b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -177,6 +177,7 @@ static int add_queue_mes(struct device_queue_manager *dqm, struct queue *q,
 	struct kfd_process_device *pdd = qpd_to_pdd(qpd);
 	struct mes_add_queue_input queue_input;
 	int r, queue_type;
+	uint64_t wptr_addr_off;
 
 	if (dqm->is_hws_hang)
 		return -EIO;
@@ -196,7 +197,13 @@ static int add_queue_mes(struct device_queue_manager *dqm, struct queue *q,
 					AMDGPU_MES_PRIORITY_LEVEL_NORMAL;
 	queue_input.doorbell_offset = q->properties.doorbell_off;
 	queue_input.mqd_addr = q->gart_mqd_addr;
-	queue_input.wptr_addr = (uint64_t)q->properties.write_ptr;
+
+	if (q->wptr_bo) {
+		wptr_addr_off = (uint64_t)q->properties.write_ptr - (uint64_t)q->wptr_bo->kfd_bo->va;
+		queue_input.wptr_addr = ((uint64_t)q->wptr_bo->tbo.resource->start << PAGE_SHIFT) + wptr_addr_off;
+	} else
+		queue_input.wptr_addr = (uint64_t)q->properties.write_ptr;
+
 	queue_input.paging = false;
 	queue_input.tba_addr = qpd->tba_addr;
 	queue_input.tma_addr = qpd->tma_addr;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
index 4e0387f591be..b8e14c2cc295 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
@@ -377,6 +377,8 @@ static void update_mqd_sdma(struct mqd_manager *mm, void *mqd,
 	m->sdmax_rlcx_rb_base_hi = upper_32_bits(q->queue_address >> 8);
 	m->sdmax_rlcx_rb_rptr_addr_lo = lower_32_bits((uint64_t)q->read_ptr);
 	m->sdmax_rlcx_rb_rptr_addr_hi = upper_32_bits((uint64_t)q->read_ptr);
+	m->sdmax_rlcx_rb_wptr_poll_addr_lo = lower_32_bits((uint64_t)q->write_ptr);
+	m->sdmax_rlcx_rb_wptr_poll_addr_hi = upper_32_bits((uint64_t)q->write_ptr);
 	m->sdmax_rlcx_doorbell_offset =
 		q->doorbell_off << SDMA0_QUEUE0_DOORBELL_OFFSET__OFFSET__SHIFT;
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 2585d6e61d42..4c4bbd493caa 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -571,6 +571,8 @@ struct queue {
 	void *gang_ctx_bo;
 	uint64_t gang_ctx_gpu_addr;
 	void *gang_ctx_cpu_ptr;
+
+	struct amdgpu_bo *wptr_bo;
 };
 
 enum KFD_MQD_TYPE {
@@ -1206,6 +1208,7 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 			    struct file *f,
 			    struct queue_properties *properties,
 			    unsigned int *qid,
+			    struct amdgpu_bo *wptr_bo,
 			    const struct kfd_criu_queue_priv_data *q_data,
 			    const void *restore_mqd,
 			    const void *restore_ctl_stack,
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 99f2a6412201..a46e2a37b4a6 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -180,7 +180,8 @@ void pqm_uninit(struct process_queue_manager *pqm)
 static int init_user_queue(struct process_queue_manager *pqm,
 				struct kfd_dev *dev, struct queue **q,
 				struct queue_properties *q_properties,
-				struct file *f, unsigned int qid)
+				struct file *f, struct amdgpu_bo *wptr_bo,
+				unsigned int qid)
 {
 	int retval;
 
@@ -210,6 +211,7 @@ static int init_user_queue(struct process_queue_manager *pqm,
 			goto cleanup;
 		}
 		memset((*q)->gang_ctx_cpu_ptr, 0, AMDGPU_MES_GANG_CTX_SIZE);
+		(*q)->wptr_bo = wptr_bo;
 	}
 
 	pr_debug("PQM After init queue");
@@ -226,6 +228,7 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 			    struct file *f,
 			    struct queue_properties *properties,
 			    unsigned int *qid,
+			    struct amdgpu_bo *wptr_bo,
 			    const struct kfd_criu_queue_priv_data *q_data,
 			    const void *restore_mqd,
 			    const void *restore_ctl_stack,
@@ -288,7 +291,7 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 		 * allocate_sdma_queue() in create_queue() has the
 		 * corresponding check logic.
 		 */
-		retval = init_user_queue(pqm, dev, &q, properties, f, *qid);
+		retval = init_user_queue(pqm, dev, &q, properties, f, wptr_bo, *qid);
 		if (retval != 0)
 			goto err_create_queue;
 		pqn->q = q;
@@ -309,7 +312,7 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 			goto err_create_queue;
 		}
 
-		retval = init_user_queue(pqm, dev, &q, properties, f, *qid);
+		retval = init_user_queue(pqm, dev, &q, properties, f, wptr_bo, *qid);
 		if (retval != 0)
 			goto err_create_queue;
 		pqn->q = q;
@@ -435,9 +438,13 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid)
 			pdd->qpd.num_gws = 0;
 		}
 
-		if (dev->shared_resources.enable_mes)
+		if (dev->shared_resources.enable_mes) {
 			amdgpu_amdkfd_free_gtt_mem(dev->adev,
 						   pqn->q->gang_ctx_bo);
+			if (pqn->q->wptr_bo)
+				amdgpu_amdkfd_free_gtt_mem(dev->adev, pqn->q->wptr_bo);
+
+		}
 		kfd_procfs_del_queue(pqn->q);
 		uninit_queue(pqn->q);
 	}
@@ -844,7 +851,7 @@ int kfd_criu_restore_queue(struct kfd_process *p,
 
 	print_queue_properties(&qp);
 
-	ret = pqm_create_queue(&p->pqm, pdd->dev, NULL, &qp, &queue_id, q_data, mqd, ctl_stack,
+	ret = pqm_create_queue(&p->pqm, pdd->dev, NULL, &qp, &queue_id, NULL, q_data, mqd, ctl_stack,
 				NULL);
 	if (ret) {
 		pr_err("Failed to create new queue err:%d\n", ret);