5 files changed, 32 insertions, 8 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index b4d9e6b4f583..9b4e6ad4a7df 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -457,7 +457,8 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
 
 	if (kfd->kfd2kgd->init_gtt_mem_allocation(
 			kfd->kgd, size, &kfd->gtt_mem,
-			&kfd->gtt_start_gpu_addr, &kfd->gtt_start_cpu_ptr)){
+			&kfd->gtt_start_gpu_addr, &kfd->gtt_start_cpu_ptr,
+			false)) {
 		dev_err(kfd_device, "Could not allocate %d bytes\n", size);
 		goto out;
 	}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
index 7a61f38c09e6..01494752c36a 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
@@ -62,9 +62,20 @@ int kfd_iommu_device_init(struct kfd_dev *kfd)
 	struct amd_iommu_device_info iommu_info;
 	unsigned int pasid_limit;
 	int err;
+	struct kfd_topology_device *top_dev;
 
-	if (!kfd->device_info->needs_iommu_device)
+	top_dev = kfd_topology_device_by_id(kfd->id);
+
+	/*
+	 * Overwrite ATS capability according to needs_iommu_device to fix
+	 * potential missing corresponding bit in CRAT of BIOS.
+	 */
+	if (!kfd->device_info->needs_iommu_device) {
+		top_dev->node_props.capability &= ~HSA_CAP_ATS_PRESENT;
 		return 0;
+	}
+
+	top_dev->node_props.capability |= HSA_CAP_ATS_PRESENT;
 
 	iommu_info.flags = 0;
 	err = amd_iommu_device_info(kfd->pdev, &iommu_info);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
index f5fc3675f21e..0cedb37cf513 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
@@ -88,7 +88,7 @@ static int init_mqd(struct mqd_manager *mm, void **mqd,
 				ALIGN(sizeof(struct v9_mqd), PAGE_SIZE),
 			&((*mqd_mem_obj)->gtt_mem),
 			&((*mqd_mem_obj)->gpu_addr),
-			(void *)&((*mqd_mem_obj)->cpu_ptr));
+			(void *)&((*mqd_mem_obj)->cpu_ptr), true);
 	} else
 		retval = kfd_gtt_sa_allocate(mm->dev, sizeof(struct v9_mqd),
 				mqd_mem_obj);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 05283c99d731..b0064b08aa11 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -782,6 +782,7 @@ int kfd_topology_add_device(struct kfd_dev *gpu);
 int kfd_topology_remove_device(struct kfd_dev *gpu);
 struct kfd_topology_device *kfd_topology_device_by_proximity_domain(
 						uint32_t proximity_domain);
+struct kfd_topology_device *kfd_topology_device_by_id(uint32_t gpu_id);
 struct kfd_dev *kfd_device_by_id(uint32_t gpu_id);
 struct kfd_dev *kfd_device_by_pci_dev(const struct pci_dev *pdev);
 int kfd_topology_enum_kfd_devices(uint8_t idx, struct kfd_dev **kdev);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index 19ecc8233d66..0dff66be8d7a 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -63,22 +63,33 @@ struct kfd_topology_device *kfd_topology_device_by_proximity_domain(
 	return device;
 }
 
-struct kfd_dev *kfd_device_by_id(uint32_t gpu_id)
+struct kfd_topology_device *kfd_topology_device_by_id(uint32_t gpu_id)
 {
-	struct kfd_topology_device *top_dev;
-	struct kfd_dev *device = NULL;
+	struct kfd_topology_device *top_dev = NULL;
+	struct kfd_topology_device *ret = NULL;
 
 	down_read(&topology_lock);
 
 	list_for_each_entry(top_dev, &topology_device_list, list)
 		if (top_dev->gpu_id == gpu_id) {
-			device = top_dev->gpu;
+			ret = top_dev;
 			break;
 		}
 
 	up_read(&topology_lock);
 
-	return device;
+	return ret;
+}
+
+struct kfd_dev *kfd_device_by_id(uint32_t gpu_id)
+{
+	struct kfd_topology_device *top_dev;
+
+	top_dev = kfd_topology_device_by_id(gpu_id);
+	if (!top_dev)
+		return NULL;
+
+	return top_dev->gpu;
 }
 
 struct kfd_dev *kfd_device_by_pci_dev(const struct pci_dev *pdev)