drm/amdkfd: Change the control stack MTYPE from UC to NC on GFX9

[ Upstream commit 15426dbb65c5b37680d27e84d58a1ed3b8532518 ]

CWSR fails on Raven if the control stack is MTYPE_UC, which is used
for regular GART mappings. As a workaround we map it using MTYPE_NC.

The MEC firmware expects the control stack at one page offset from the
start of the MQD so it is part of the MQD allocation on GFXv9. AMDGPU
added a memory allocation flag just for this purpose.

Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Yong Zhao <yong.zhao@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 305143fcc1ceed0d1231efa742864de460b608d0..1ac7933cccc53cf3af325574d581417c6d546c5a 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -245,7 +245,7 @@ int amdgpu_amdkfd_resume(struct amdgpu_device *adev)
 
 int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
                        void **mem_obj, uint64_t *gpu_addr,
-                       void **cpu_ptr)
+                       void **cpu_ptr, bool mqd_gfx9)
 {
        struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
        struct amdgpu_bo *bo = NULL;
@@ -261,6 +261,10 @@ int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
        bp.flags = AMDGPU_GEM_CREATE_CPU_GTT_USWC;
        bp.type = ttm_bo_type_kernel;
        bp.resv = NULL;
+
+       if (mqd_gfx9)
+               bp.flags |= AMDGPU_GEM_CREATE_MQD_GFX9;
+
        r = amdgpu_bo_create(adev, &bp, &bo);
        if (r) {
                dev_err(adev->dev,

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index a8418a3f4e9d3f28d39cff6ece0e9462c1b9845e..e3cf1c9fb3db0f6d57f1aeb8bc134507a3ac0f3c 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -129,7 +129,7 @@ bool amdgpu_amdkfd_is_kfd_vmid(struct amdgpu_device *adev, u32 vmid);
 /* Shared API */
 int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
                        void **mem_obj, uint64_t *gpu_addr,
-                       void **cpu_ptr);
+                       void **cpu_ptr, bool mqd_gfx9);
 void free_gtt_mem(struct kgd_dev *kgd, void *mem_obj);
 void get_local_mem_info(struct kgd_dev *kgd,
                        struct kfd_local_mem_info *mem_info);

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 7ee6cec2c06024182c00c06f4fc07a1f9b12a1c0..6881b5a9275f3a48d58c18533994d14d3faf4744 100644 (file)
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -423,7 +423,8 @@ 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_mqd_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
index 684054ff02cdc21f9b2b7e1218d2dc15cda5245a..8da079cc6fb9399b4e8d9e5befdffa87bef0069d 100644 (file)
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
@@ -63,7 +63,7 @@ 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/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
index 5733fbee07f7fd6cca26ac15d348117bad0bddfe..f56b7553e5ed18f09add003a441c702b7246ab8c 100644 (file)
--- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
@@ -266,7 +266,7 @@ struct tile_config {
 struct kfd2kgd_calls {
        int (*init_gtt_mem_allocation)(struct kgd_dev *kgd, size_t size,
                                        void **mem_obj, uint64_t *gpu_addr,
-                                       void **cpu_ptr);
+                                       void **cpu_ptr, bool mqd_gfx9);
 
        void (*free_gtt_mem)(struct kgd_dev *kgd, void *mem_obj);