drm/amdgpu: XGMI pstate switch initial support

Driver vote low to high pstate switch whenever there is an outstanding
XGMI mapping request. Driver vote high to low pstate when all the
outstanding XGMI mapping is terminated.

Signed-off-by: shaoyunl <shaoyun.liu@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

6 files changed, 56 insertions, 1 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 865e067b1b5b..7cee269ec3e3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2018,6 +2018,10 @@ static void amdgpu_device_ip_late_init_func_handler(struct work_struct *work)
 	r = amdgpu_device_enable_mgpu_fan_boost();
 	if (r)
 		DRM_ERROR("enable mgpu fan boost failed (%d).\n", r);
+
+	/*set to low pstate by default */
+	amdgpu_xgmi_set_pstate(adev, 0);
+
 }
 
 static void amdgpu_device_delay_enable_gfx_off(struct work_struct *work)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
index 220a6a7b1bc1..c430e8259038 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
@@ -72,6 +72,8 @@ struct amdgpu_bo_va {
 
 	/* If the mappings are cleared or filled */
 	bool				cleared;
+
+	bool				is_xgmi;
 };
 
 struct amdgpu_bo {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index b7f937ceebee..a5c6a1e5fe74 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -34,6 +34,7 @@
 #include "amdgpu_trace.h"
 #include "amdgpu_amdkfd.h"
 #include "amdgpu_gmc.h"
+#include "amdgpu_xgmi.h"
 
 /**
  * DOC: GPUVM
@@ -2045,6 +2046,15 @@ struct amdgpu_bo_va *amdgpu_vm_bo_add(struct amdgpu_device *adev,
 	INIT_LIST_HEAD(&bo_va->valids);
 	INIT_LIST_HEAD(&bo_va->invalids);
 
+	if (bo && amdgpu_xgmi_same_hive(adev, amdgpu_ttm_adev(bo->tbo.bdev))) {
+		bo_va->is_xgmi = true;
+		mutex_lock(&adev->vm_manager.lock_pstate);
+		/* Power up XGMI if it can be potentially used */
+		if (++adev->vm_manager.xgmi_map_counter == 1)
+			amdgpu_xgmi_set_pstate(adev, 1);
+		mutex_unlock(&adev->vm_manager.lock_pstate);
+	}
+
 	return bo_va;
 }
 
@@ -2463,6 +2473,14 @@ void amdgpu_vm_bo_rmv(struct amdgpu_device *adev,
 	}
 
 	dma_fence_put(bo_va->last_pt_update);
+
+	if (bo && bo_va->is_xgmi) {
+		mutex_lock(&adev->vm_manager.lock_pstate);
+		if (--adev->vm_manager.xgmi_map_counter == 0)
+			amdgpu_xgmi_set_pstate(adev, 0);
+		mutex_unlock(&adev->vm_manager.lock_pstate);
+	}
+
 	kfree(bo_va);
 }
 
@@ -2970,6 +2988,9 @@ void amdgpu_vm_manager_init(struct amdgpu_device *adev)
 
 	idr_init(&adev->vm_manager.pasid_idr);
 	spin_lock_init(&adev->vm_manager.pasid_lock);
+
+	adev->vm_manager.xgmi_map_counter = 0;
+	mutex_init(&adev->vm_manager.lock_pstate);
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index 520122be798b..f586b38f3076 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -324,6 +324,10 @@ struct amdgpu_vm_manager {
 	 */
 	struct idr				pasid_idr;
 	spinlock_t				pasid_lock;
+
+	/* counter of mapped memory through xgmi */
+	uint32_t				xgmi_map_counter;
+	struct mutex				lock_pstate;
 };
 
 #define amdgpu_vm_copy_pte(adev, ib, pe, src, count) ((adev)->vm_manager.vm_pte_funcs->copy_pte((ib), (pe), (src), (count)))
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index fcc4b05c745c..336834797af3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -200,12 +200,26 @@ struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev, int lo
 
 	if (lock)
 		mutex_lock(&tmp->hive_lock);
-
+	tmp->pstate = -1;
 	mutex_unlock(&xgmi_mutex);
 
 	return tmp;
 }
 
+int amdgpu_xgmi_set_pstate(struct amdgpu_device *adev, int pstate)
+{
+	int ret = 0;
+	struct amdgpu_hive_info *hive = amdgpu_get_xgmi_hive(adev, 0);
+
+	if (!hive)
+		return 0;
+
+	if (hive->pstate == pstate)
+		return 0;
+	/* Todo : sent the message to SMU for pstate change */
+	return ret;
+}
+
 int amdgpu_xgmi_update_topology(struct amdgpu_hive_info *hive, struct amdgpu_device *adev)
 {
 	int ret = -EINVAL;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
index 24a3b0362f98..3e9c91e9a4bf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
@@ -33,11 +33,21 @@ struct amdgpu_hive_info {
 	struct kobject *kobj;
 	struct device_attribute dev_attr;
 	struct amdgpu_device *adev;
+	int pstate; /*0 -- low , 1 -- high , -1 unknown*/
 };
 
 struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev, int lock);
 int amdgpu_xgmi_update_topology(struct amdgpu_hive_info *hive, struct amdgpu_device *adev);
 int amdgpu_xgmi_add_device(struct amdgpu_device *adev);
 void amdgpu_xgmi_remove_device(struct amdgpu_device *adev);
+int amdgpu_xgmi_set_pstate(struct amdgpu_device *adev, int pstate);
+
+static inline bool amdgpu_xgmi_same_hive(struct amdgpu_device *adev,
+		struct amdgpu_device *bo_adev)
+{
+	return (adev != bo_adev &&
+		adev->gmc.xgmi.hive_id &&
+		adev->gmc.xgmi.hive_id == bo_adev->gmc.xgmi.hive_id);
+}
 
 #endif