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, 35 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
index e00d38d9160a..cc625e441fa0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
@@ -70,6 +70,19 @@ struct amdgpu_reset_control {
 	void (*async_reset)(struct work_struct *work);
 };
 
+
+enum amdgpu_reset_domain_type {
+	SINGLE_DEVICE,
+	XGMI_HIVE
+};
+
+struct amdgpu_reset_domain {
+	struct kref refcount;
+	struct workqueue_struct *wq;
+	enum amdgpu_reset_domain_type type;
+};
+
+
 int amdgpu_reset_init(struct amdgpu_device *adev);
 int amdgpu_reset_fini(struct amdgpu_device *adev);
 
@@ -82,4 +95,26 @@ int amdgpu_reset_perform_reset(struct amdgpu_device *adev,
 int amdgpu_reset_add_handler(struct amdgpu_reset_control *reset_ctl,
 			     struct amdgpu_reset_handler *handler);
 
+struct amdgpu_reset_domain *amdgpu_reset_create_reset_domain(enum amdgpu_reset_domain_type type,
+							     char *wq_name);
+
+void amdgpu_reset_destroy_reset_domain(struct kref *ref);
+
+static inline bool amdgpu_reset_get_reset_domain(struct amdgpu_reset_domain *domain)
+{
+	return kref_get_unless_zero(&domain->refcount) != 0;
+}
+
+static inline void amdgpu_reset_put_reset_domain(struct amdgpu_reset_domain *domain)
+{
+	kref_put(&domain->refcount, amdgpu_reset_destroy_reset_domain);
+}
+
+static inline bool amdgpu_reset_domain_schedule(struct amdgpu_reset_domain *domain,
+						struct work_struct *work)
+{
+	return queue_work(domain->wq, work);
+}
+
+
 #endif