1 /* 2 * Copyright 2018 Advanced Micro Devices, Inc. 3 * 4 * Permission is hereby granted, free of charge, to any person obtaining a 5 * copy of this software and associated documentation files (the "Software"), 6 * to deal in the Software without restriction, including without limitation 7 * the rights to use, copy, modify, merge, publish, distribute, sublicense, 8 * and/or sell copies of the Software, and to permit persons to whom the 9 * Software is furnished to do so, subject to the following conditions: 10 * 11 * The above copyright notice and this permission notice shall be included in 12 * all copies or substantial portions of the Software. 13 * 14 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 15 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 16 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 17 * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR 18 * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, 19 * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR 20 * OTHER DEALINGS IN THE SOFTWARE. 21 * 22 * 23 */ 24 #include <linux/list.h> 25 #include "amdgpu.h" 26 #include "amdgpu_xgmi.h" 27 28 29 static DEFINE_MUTEX(xgmi_mutex); 30 31 #define AMDGPU_MAX_XGMI_HIVE 8 32 #define AMDGPU_MAX_XGMI_DEVICE_PER_HIVE 4 33 34 static struct amdgpu_hive_info xgmi_hives[AMDGPU_MAX_XGMI_HIVE]; 35 static unsigned hive_count = 0; 36 37 38 void *amdgpu_xgmi_hive_try_lock(struct amdgpu_hive_info *hive) 39 { 40 return &hive->device_list; 41 } 42 43 struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev) 44 { 45 int i; 46 struct amdgpu_hive_info *tmp; 47 48 if (!adev->gmc.xgmi.hive_id) 49 return NULL; 50 for (i = 0 ; i < hive_count; ++i) { 51 tmp = &xgmi_hives[i]; 52 if (tmp->hive_id == adev->gmc.xgmi.hive_id) 53 return tmp; 54 } 55 if (i >= AMDGPU_MAX_XGMI_HIVE) 56 return NULL; 57 58 /* initialize new hive if not exist */ 59 tmp = &xgmi_hives[hive_count++]; 60 tmp->hive_id = adev->gmc.xgmi.hive_id; 61 INIT_LIST_HEAD(&tmp->device_list); 62 mutex_init(&tmp->hive_lock); 63 64 return tmp; 65 } 66 67 int amdgpu_xgmi_update_topology(struct amdgpu_hive_info *hive, struct amdgpu_device *adev) 68 { 69 int ret = -EINVAL; 70 71 /* Each psp need to set the latest topology */ 72 ret = psp_xgmi_set_topology_info(&adev->psp, 73 hive->number_devices, 74 &hive->topology_info); 75 if (ret) 76 dev_err(adev->dev, 77 "XGMI: Set topology failure on device %llx, hive %llx, ret %d", 78 adev->gmc.xgmi.node_id, 79 adev->gmc.xgmi.hive_id, ret); 80 else 81 dev_info(adev->dev, "XGMI: Set topology for node %d, hive 0x%llx.\n", 82 adev->gmc.xgmi.physical_node_id, 83 adev->gmc.xgmi.hive_id); 84 85 return ret; 86 } 87 88 int amdgpu_xgmi_add_device(struct amdgpu_device *adev) 89 { 90 struct psp_xgmi_topology_info *hive_topology; 91 struct amdgpu_hive_info *hive; 92 struct amdgpu_xgmi *entry; 93 struct amdgpu_device *tmp_adev = NULL; 94 95 int count = 0, ret = -EINVAL; 96 97 if (!adev->gmc.xgmi.supported) 98 return 0; 99 100 ret = psp_xgmi_get_node_id(&adev->psp, &adev->gmc.xgmi.node_id); 101 if (ret) { 102 dev_err(adev->dev, 103 "XGMI: Failed to get node id\n"); 104 return ret; 105 } 106 107 ret = psp_xgmi_get_hive_id(&adev->psp, &adev->gmc.xgmi.hive_id); 108 if (ret) { 109 dev_err(adev->dev, 110 "XGMI: Failed to get hive id\n"); 111 return ret; 112 } 113 114 mutex_lock(&xgmi_mutex); 115 hive = amdgpu_get_xgmi_hive(adev); 116 if (!hive) 117 goto exit; 118 119 hive_topology = &hive->topology_info; 120 121 list_add_tail(&adev->gmc.xgmi.head, &hive->device_list); 122 list_for_each_entry(entry, &hive->device_list, head) 123 hive_topology->nodes[count++].node_id = entry->node_id; 124 hive->number_devices = count; 125 126 /* Each psp need to get the latest topology */ 127 list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head) { 128 ret = psp_xgmi_get_topology_info(&tmp_adev->psp, count, hive_topology); 129 if (ret) { 130 dev_err(tmp_adev->dev, 131 "XGMI: Get topology failure on device %llx, hive %llx, ret %d", 132 tmp_adev->gmc.xgmi.node_id, 133 tmp_adev->gmc.xgmi.hive_id, ret); 134 /* To do : continue with some node failed or disable the whole hive */ 135 break; 136 } 137 } 138 139 list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head) { 140 ret = amdgpu_xgmi_update_topology(hive, tmp_adev); 141 if (ret) 142 break; 143 } 144 145 exit: 146 mutex_unlock(&xgmi_mutex); 147 return ret; 148 } 149 150 void amdgpu_xgmi_remove_device(struct amdgpu_device *adev) 151 { 152 struct amdgpu_hive_info *hive; 153 154 if (!adev->gmc.xgmi.supported) 155 return; 156 157 mutex_lock(&xgmi_mutex); 158 159 hive = amdgpu_get_xgmi_hive(adev); 160 if (!hive) 161 goto exit; 162 163 if (!(hive->number_devices--)) 164 mutex_destroy(&hive->hive_lock); 165 166 exit: 167 mutex_unlock(&xgmi_mutex); 168 } 169