drm/amdgpu: Rework reset domain to be refcounted.

The reset domain contains register access semaphor
now and so needs to be present as long as each device
in a hive needs it and so it cannot be binded to XGMI
hive life cycle.
Adress this by making reset domain refcounted and pointed
by each member of the hive and the hive itself.

v4:

Fix crash on boot witrh XGMI hive by adding type to reset_domain.
XGMI will only create a new reset_domain if prevoius was of single
device type meaning it's first boot. Otherwsie it will take a
refocunt to exsiting reset_domain from the amdgou device.

Add a wrapper around reset_domain->refcount get/put
and a wrapper around send to reset wq (Lijo)

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Link: https://www.spinics.net/lists/amd-gfx/msg74121.html

1 files changed, 40 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c
index 02afd4115675..91864947063f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c
@@ -96,3 +96,43 @@ int amdgpu_reset_perform_reset(struct amdgpu_device *adev,
 	return reset_handler->restore_hwcontext(adev->reset_cntl,
 						reset_context);
 }
+
+
+void amdgpu_reset_destroy_reset_domain(struct kref *ref)
+{
+	struct amdgpu_reset_domain *reset_domain = container_of(ref,
+								struct amdgpu_reset_domain,
+								refcount);
+	if (reset_domain->wq)
+		destroy_workqueue(reset_domain->wq);
+
+	kvfree(reset_domain);
+}
+
+struct amdgpu_reset_domain *amdgpu_reset_create_reset_domain(enum amdgpu_reset_domain_type type,
+							     char *wq_name)
+{
+	struct amdgpu_reset_domain *reset_domain;
+
+	reset_domain = kvzalloc(sizeof(struct amdgpu_reset_domain), GFP_KERNEL);
+	if (!reset_domain) {
+		DRM_ERROR("Failed to allocate amdgpu_reset_domain!");
+		return NULL;
+	}
+
+	reset_domain->type = type;
+	kref_init(&reset_domain->refcount);
+
+	reset_domain->wq = create_singlethread_workqueue(wq_name);
+	if (!reset_domain->wq) {
+		DRM_ERROR("Failed to allocate wq for amdgpu_reset_domain!");
+		amdgpu_reset_put_reset_domain(reset_domain);
+		return NULL;
+
+	}
+
+	return reset_domain;
+}
+
+
+