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: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/amdgpu.h

@@ -925,6 +925,10 @@ struct amdgpu_device {
 
 	int asic_reset_res;
 	struct work_struct		xgmi_reset_work;
+
+	/* counter of mapped memory through xgmi */
+	atomic_t			xgmi_map_counter;
+
 };
 
 static inline struct amdgpu_device *amdgpu_ttm_adev(struct ttm_bo_device *bdev)

drivers/gpu/drm/amd/amdgpu/amdgpu_device.c

@@ -1999,6 +1999,9 @@ 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)

drivers/gpu/drm/amd/amdgpu/amdgpu_object.h

@@ -54,6 +54,7 @@ struct amdgpu_bo_va_mapping {
 	uint64_t			__subtree_last;
 	uint64_t			offset;
 	uint64_t			flags;
+	bool				is_xgmi;
 };
 
 /* User space allocated BO in a VM */

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
@@ -2013,8 +2014,9 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev,
 	struct ttm_mem_reg *mem;
 	struct drm_mm_node *nodes;
 	struct dma_fence *exclusive, **last_update;
-	uint64_t flags;
 	struct amdgpu_device *bo_adev = adev;
+	bool is_xgmi = false;
+	uint64_t flags;
 	int r;
 
 	if (clear || !bo) {
@@ -2036,6 +2038,10 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev,
 	if (bo) {
 		flags = amdgpu_ttm_tt_pte_flags(adev, bo->tbo.ttm, mem);
 		bo_adev = amdgpu_ttm_adev(bo->tbo.bdev);
+		if (adev != bo_adev &&
+		    adev->gmc.xgmi.hive_id &&
+		    adev->gmc.xgmi.hive_id == bo_adev->gmc.xgmi.hive_id)
+			is_xgmi = true;
 	} else {
 		flags = 0x0;
 	}
@@ -2054,6 +2060,19 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev,
 	}
 
 	list_for_each_entry(mapping, &bo_va->invalids, list) {
+		if (mapping->is_xgmi != is_xgmi) {
+			if (is_xgmi) {
+				/* Adding an XGMI mapping to the PT */
+				if (atomic_inc_return(&adev->xgmi_map_counter) == 1)
+					amdgpu_xgmi_set_pstate(adev, 1);
+			} else {
+				/* Removing an XGMI mapping from the PT */
+				if (atomic_dec_return(&adev->xgmi_map_counter) == 0)
+					amdgpu_xgmi_set_pstate(adev, 0);
+			}
+			mapping->is_xgmi = is_xgmi;
+		}
+
 		r = amdgpu_vm_bo_split_mapping(adev, exclusive, pages_addr, vm,
 					       mapping, flags, bo_adev, nodes,
 					       last_update);
@@ -2271,6 +2290,13 @@ int amdgpu_vm_clear_freed(struct amdgpu_device *adev,
 		r = amdgpu_vm_bo_update_mapping(adev, NULL, NULL, vm,
 						mapping->start, mapping->last,
 						init_pte_value, 0, &f);
+
+		if (mapping->is_xgmi) {
+			/* Removing an XGMI mapping from the PT */
+			if (atomic_dec_return(&adev->xgmi_map_counter) == 0)
+				amdgpu_xgmi_set_pstate(adev, 0);
+		}
+
 		amdgpu_vm_free_mapping(adev, vm, mapping, f);
 		if (r) {
 			dma_fence_put(f);
@@ -2467,6 +2493,7 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev,
 	mapping->last = eaddr;
 	mapping->offset = offset;
 	mapping->flags = flags;
+	mapping->is_xgmi = false;
 
 	amdgpu_vm_bo_insert_map(adev, bo_va, mapping);
 

drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c

@@ -200,6 +200,7 @@ 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);
 
@@ -321,3 +322,17 @@ void amdgpu_xgmi_remove_device(struct amdgpu_device *adev)
 		mutex_unlock(&hive->hive_lock);
 	}
 }
+
+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;
+}

drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h

@@ -33,11 +33,13 @@ 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);
 
 #endif