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>

3 files changed, 57 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index 648c031942e9..b25b41f50213 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -286,6 +286,8 @@ int amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(struct kgd_mem *mem,
 					     void **kptr, uint64_t *size);
 void amdgpu_amdkfd_gpuvm_unmap_gtt_bo_from_kernel(struct kgd_mem *mem);
 
+int amdgpu_amdkfd_map_gtt_bo_to_gart(struct amdgpu_device *adev, struct amdgpu_bo *bo);
+
 int amdgpu_amdkfd_gpuvm_restore_process_bos(void *process_info,
 					    struct dma_fence **ef);
 int amdgpu_amdkfd_gpuvm_get_vm_fault_info(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 8805bd1eed37..f3f9912fc51a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -2113,6 +2113,54 @@ int amdgpu_amdkfd_gpuvm_sync_memory(
 	return ret;
 }
 
+/**
+ * amdgpu_amdkfd_map_gtt_bo_to_gart - Map BO to GART and increment reference count
+ * @adev: Device to which allocated BO belongs
+ * @bo: Buffer object to be mapped
+ *
+ * Before return, bo reference count is incremented. To release the reference and unpin/
+ * unmap the BO, call amdgpu_amdkfd_free_gtt_mem.
+ */
+int amdgpu_amdkfd_map_gtt_bo_to_gart(struct amdgpu_device *adev, struct amdgpu_bo *bo)
+{
+	int ret;
+
+	ret = amdgpu_bo_reserve(bo, true);
+	if (ret) {
+		pr_err("Failed to reserve bo. ret %d\n", ret);
+		goto err_reserve_bo_failed;
+	}
+
+	ret = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT);
+	if (ret) {
+		pr_err("Failed to pin bo. ret %d\n", ret);
+		goto err_pin_bo_failed;
+	}
+
+	ret = amdgpu_ttm_alloc_gart(&bo->tbo);
+	if (ret) {
+		pr_err("Failed to bind bo to GART. ret %d\n", ret);
+		goto err_map_bo_gart_failed;
+	}
+
+	amdgpu_amdkfd_remove_eviction_fence(
+		bo, bo->kfd_bo->process_info->eviction_fence);
+
+	amdgpu_bo_unreserve(bo);
+
+	bo = amdgpu_bo_ref(bo);
+
+	return 0;
+
+err_map_bo_gart_failed:
+	amdgpu_bo_unpin(bo);
+err_pin_bo_failed:
+	amdgpu_bo_unreserve(bo);
+err_reserve_bo_failed:
+
+	return ret;
+}
+
 /** amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel() - Map a GTT BO for kernel CPU access
  *
  * @mem: Buffer object to be mapped for CPU access
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
index 42f5a61dd2ec..9c11219e925f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
@@ -33,6 +33,13 @@
 #define AMDGPU_MES_MAX_GFX_PIPES            2
 #define AMDGPU_MES_MAX_SDMA_PIPES           2
 
+#define AMDGPU_MES_API_VERSION_SHIFT	12
+#define AMDGPU_MES_FEAT_VERSION_SHIFT	24
+
+#define AMDGPU_MES_VERSION_MASK		0x00000fff
+#define AMDGPU_MES_API_VERSION_MASK	0x00fff000
+#define AMDGPU_MES_FEAT_VERSION_MASK	0xff000000
+
 enum amdgpu_mes_priority_level {
 	AMDGPU_MES_PRIORITY_LEVEL_LOW       = 0,
 	AMDGPU_MES_PRIORITY_LEVEL_NORMAL    = 1,