drm/amdkfd: CRIU Implement KFD checkpoint ioctl

This adds support to discover the  buffer objects that belong to a
process being checkpointed. The data corresponding to these buffer
objects is returned to user space plugin running under criu master
context which then stores this info to recreate these buffer objects
during a restore operation.

Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: David Yat Sin <david.yatsin@amd.com>
Signed-off-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

4 files changed, 34 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index ac841ae8f5cc..395ba9566afe 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -297,6 +297,7 @@ int amdgpu_amdkfd_get_tile_config(struct amdgpu_device *adev,
 				struct tile_config *config);
 void amdgpu_amdkfd_ras_poison_consumption_handler(struct amdgpu_device *adev,
 				bool reset);
+bool amdgpu_amdkfd_bo_mapped_to_dev(struct amdgpu_device *adev, struct kgd_mem *mem);
 #if IS_ENABLED(CONFIG_HSA_AMD)
 void amdgpu_amdkfd_gpuvm_init_mem_limits(void);
 void amdgpu_amdkfd_gpuvm_destroy_cb(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 5d00a6878ef2..5cf4bedca1d6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -2629,3 +2629,14 @@ int amdgpu_amdkfd_get_tile_config(struct amdgpu_device *adev,
 
 	return 0;
 }
+
+bool amdgpu_amdkfd_bo_mapped_to_dev(struct amdgpu_device *adev, struct kgd_mem *mem)
+{
+	struct kfd_mem_attachment *entry;
+
+	list_for_each_entry(entry, &mem->attachments, list) {
+		if (entry->is_mapped && entry->adev == adev)
+			return true;
+	}
+	return false;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 7cac4a69ba32..41d6f604813d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -1137,6 +1137,26 @@ static void amdgpu_ttm_tt_unpopulate(struct ttm_device *bdev,
 }
 
 /**
+ * amdgpu_ttm_tt_get_userptr - Return the userptr GTT ttm_tt for the current
+ * task
+ *
+ * @tbo: The ttm_buffer_object that contains the userptr
+ * @user_addr:  The returned value
+ */
+int amdgpu_ttm_tt_get_userptr(const struct ttm_buffer_object *tbo,
+			      uint64_t *user_addr)
+{
+	struct amdgpu_ttm_tt *gtt;
+
+	if (!tbo->ttm)
+		return -EINVAL;
+
+	gtt = (void *)tbo->ttm;
+	*user_addr = gtt->userptr;
+	return 0;
+}
+
+/**
  * amdgpu_ttm_tt_set_userptr - Initialize userptr GTT ttm_tt for the current
  * task
  *
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
index 0efc31e3a457..0e4ecc77db3f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
@@ -181,6 +181,8 @@ static inline bool amdgpu_ttm_tt_get_user_pages_done(struct ttm_tt *ttm)
 #endif
 
 void amdgpu_ttm_tt_set_user_pages(struct ttm_tt *ttm, struct page **pages);
+int amdgpu_ttm_tt_get_userptr(const struct ttm_buffer_object *tbo,
+			      uint64_t *user_addr);
 int amdgpu_ttm_tt_set_userptr(struct ttm_buffer_object *bo,
 			      uint64_t addr, uint32_t flags);
 bool amdgpu_ttm_tt_has_userptr(struct ttm_tt *ttm);