1 /*
2 * Copyright 2019 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 "amdgpu.h"
25 #include "umc_v6_7.h"
26
amdgpu_umc_convert_error_address(struct amdgpu_device * adev,struct ras_err_data * err_data,uint64_t err_addr,uint32_t ch_inst,uint32_t umc_inst)27 static int amdgpu_umc_convert_error_address(struct amdgpu_device *adev,
28 struct ras_err_data *err_data, uint64_t err_addr,
29 uint32_t ch_inst, uint32_t umc_inst)
30 {
31 switch (adev->ip_versions[UMC_HWIP][0]) {
32 case IP_VERSION(6, 7, 0):
33 umc_v6_7_convert_error_address(adev,
34 err_data, err_addr, ch_inst, umc_inst);
35 break;
36 default:
37 dev_warn(adev->dev,
38 "UMC address to Physical address translation is not supported\n");
39 return AMDGPU_RAS_FAIL;
40 }
41
42 return AMDGPU_RAS_SUCCESS;
43 }
44
amdgpu_umc_page_retirement_mca(struct amdgpu_device * adev,uint64_t err_addr,uint32_t ch_inst,uint32_t umc_inst)45 int amdgpu_umc_page_retirement_mca(struct amdgpu_device *adev,
46 uint64_t err_addr, uint32_t ch_inst, uint32_t umc_inst)
47 {
48 struct ras_err_data err_data = {0, 0, 0, NULL};
49 int ret = AMDGPU_RAS_FAIL;
50
51 err_data.err_addr =
52 kcalloc(adev->umc.max_ras_err_cnt_per_query,
53 sizeof(struct eeprom_table_record), GFP_KERNEL);
54 if (!err_data.err_addr) {
55 dev_warn(adev->dev,
56 "Failed to alloc memory for umc error record in MCA notifier!\n");
57 return AMDGPU_RAS_FAIL;
58 }
59
60 /*
61 * Translate UMC channel address to Physical address
62 */
63 ret = amdgpu_umc_convert_error_address(adev, &err_data, err_addr,
64 ch_inst, umc_inst);
65 if (ret)
66 goto out;
67
68 if (amdgpu_bad_page_threshold != 0) {
69 amdgpu_ras_add_bad_pages(adev, err_data.err_addr,
70 err_data.err_addr_cnt);
71 amdgpu_ras_save_bad_pages(adev, NULL);
72 }
73
74 out:
75 kfree(err_data.err_addr);
76 return ret;
77 }
78
amdgpu_umc_do_page_retirement(struct amdgpu_device * adev,void * ras_error_status,struct amdgpu_iv_entry * entry,bool reset)79 static int amdgpu_umc_do_page_retirement(struct amdgpu_device *adev,
80 void *ras_error_status,
81 struct amdgpu_iv_entry *entry,
82 bool reset)
83 {
84 struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status;
85 struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
86 int ret = 0;
87
88 kgd2kfd_set_sram_ecc_flag(adev->kfd.dev);
89 ret = amdgpu_dpm_get_ecc_info(adev, (void *)&(con->umc_ecc));
90 if (ret == -EOPNOTSUPP) {
91 if (adev->umc.ras && adev->umc.ras->ras_block.hw_ops &&
92 adev->umc.ras->ras_block.hw_ops->query_ras_error_count)
93 adev->umc.ras->ras_block.hw_ops->query_ras_error_count(adev, ras_error_status);
94
95 if (adev->umc.ras && adev->umc.ras->ras_block.hw_ops &&
96 adev->umc.ras->ras_block.hw_ops->query_ras_error_address &&
97 adev->umc.max_ras_err_cnt_per_query) {
98 err_data->err_addr =
99 kcalloc(adev->umc.max_ras_err_cnt_per_query,
100 sizeof(struct eeprom_table_record), GFP_KERNEL);
101
102 /* still call query_ras_error_address to clear error status
103 * even NOMEM error is encountered
104 */
105 if(!err_data->err_addr)
106 dev_warn(adev->dev, "Failed to alloc memory for "
107 "umc error address record!\n");
108
109 /* umc query_ras_error_address is also responsible for clearing
110 * error status
111 */
112 adev->umc.ras->ras_block.hw_ops->query_ras_error_address(adev, ras_error_status);
113 }
114 } else if (!ret) {
115 if (adev->umc.ras &&
116 adev->umc.ras->ecc_info_query_ras_error_count)
117 adev->umc.ras->ecc_info_query_ras_error_count(adev, ras_error_status);
118
119 if (adev->umc.ras &&
120 adev->umc.ras->ecc_info_query_ras_error_address &&
121 adev->umc.max_ras_err_cnt_per_query) {
122 err_data->err_addr =
123 kcalloc(adev->umc.max_ras_err_cnt_per_query,
124 sizeof(struct eeprom_table_record), GFP_KERNEL);
125
126 /* still call query_ras_error_address to clear error status
127 * even NOMEM error is encountered
128 */
129 if(!err_data->err_addr)
130 dev_warn(adev->dev, "Failed to alloc memory for "
131 "umc error address record!\n");
132
133 /* umc query_ras_error_address is also responsible for clearing
134 * error status
135 */
136 adev->umc.ras->ecc_info_query_ras_error_address(adev, ras_error_status);
137 }
138 }
139
140 /* only uncorrectable error needs gpu reset */
141 if (err_data->ue_count) {
142 dev_info(adev->dev, "%ld uncorrectable hardware errors "
143 "detected in UMC block\n",
144 err_data->ue_count);
145
146 if ((amdgpu_bad_page_threshold != 0) &&
147 err_data->err_addr_cnt) {
148 amdgpu_ras_add_bad_pages(adev, err_data->err_addr,
149 err_data->err_addr_cnt);
150 amdgpu_ras_save_bad_pages(adev, &(err_data->ue_count));
151
152 amdgpu_dpm_send_hbm_bad_pages_num(adev, con->eeprom_control.ras_num_recs);
153
154 if (con->update_channel_flag == true) {
155 amdgpu_dpm_send_hbm_bad_channel_flag(adev, con->eeprom_control.bad_channel_bitmap);
156 con->update_channel_flag = false;
157 }
158 }
159
160 if (reset)
161 amdgpu_ras_reset_gpu(adev);
162 }
163
164 kfree(err_data->err_addr);
165 return AMDGPU_RAS_SUCCESS;
166 }
167
amdgpu_umc_poison_handler(struct amdgpu_device * adev,bool reset)168 int amdgpu_umc_poison_handler(struct amdgpu_device *adev, bool reset)
169 {
170 int ret = AMDGPU_RAS_SUCCESS;
171
172 if (!amdgpu_sriov_vf(adev)) {
173 if (!adev->gmc.xgmi.connected_to_cpu) {
174 struct ras_err_data err_data = {0, 0, 0, NULL};
175 struct ras_common_if head = {
176 .block = AMDGPU_RAS_BLOCK__UMC,
177 };
178 struct ras_manager *obj = amdgpu_ras_find_obj(adev, &head);
179
180 ret = amdgpu_umc_do_page_retirement(adev, &err_data, NULL, reset);
181
182 if (ret == AMDGPU_RAS_SUCCESS && obj) {
183 obj->err_data.ue_count += err_data.ue_count;
184 obj->err_data.ce_count += err_data.ce_count;
185 }
186 } else if (reset) {
187 /* MCA poison handler is only responsible for GPU reset,
188 * let MCA notifier do page retirement.
189 */
190 kgd2kfd_set_sram_ecc_flag(adev->kfd.dev);
191 amdgpu_ras_reset_gpu(adev);
192 }
193 } else {
194 if (adev->virt.ops && adev->virt.ops->ras_poison_handler)
195 adev->virt.ops->ras_poison_handler(adev);
196 else
197 dev_warn(adev->dev,
198 "No ras_poison_handler interface in SRIOV!\n");
199 }
200
201 return ret;
202 }
203
amdgpu_umc_process_ras_data_cb(struct amdgpu_device * adev,void * ras_error_status,struct amdgpu_iv_entry * entry)204 int amdgpu_umc_process_ras_data_cb(struct amdgpu_device *adev,
205 void *ras_error_status,
206 struct amdgpu_iv_entry *entry)
207 {
208 return amdgpu_umc_do_page_retirement(adev, ras_error_status, entry, true);
209 }
210
amdgpu_umc_ras_late_init(struct amdgpu_device * adev,struct ras_common_if * ras_block)211 int amdgpu_umc_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *ras_block)
212 {
213 int r;
214
215 r = amdgpu_ras_block_late_init(adev, ras_block);
216 if (r)
217 return r;
218
219 if (amdgpu_ras_is_supported(adev, ras_block->block)) {
220 r = amdgpu_irq_get(adev, &adev->gmc.ecc_irq, 0);
221 if (r)
222 goto late_fini;
223 }
224
225 /* ras init of specific umc version */
226 if (adev->umc.ras &&
227 adev->umc.ras->err_cnt_init)
228 adev->umc.ras->err_cnt_init(adev);
229
230 return 0;
231
232 late_fini:
233 amdgpu_ras_block_late_fini(adev, ras_block);
234 return r;
235 }
236
amdgpu_umc_process_ecc_irq(struct amdgpu_device * adev,struct amdgpu_irq_src * source,struct amdgpu_iv_entry * entry)237 int amdgpu_umc_process_ecc_irq(struct amdgpu_device *adev,
238 struct amdgpu_irq_src *source,
239 struct amdgpu_iv_entry *entry)
240 {
241 struct ras_common_if *ras_if = adev->umc.ras_if;
242 struct ras_dispatch_if ih_data = {
243 .entry = entry,
244 };
245
246 if (!ras_if)
247 return 0;
248
249 ih_data.head = *ras_if;
250
251 amdgpu_ras_interrupt_dispatch(adev, &ih_data);
252 return 0;
253 }
254
amdgpu_umc_fill_error_record(struct ras_err_data * err_data,uint64_t err_addr,uint64_t retired_page,uint32_t channel_index,uint32_t umc_inst)255 void amdgpu_umc_fill_error_record(struct ras_err_data *err_data,
256 uint64_t err_addr,
257 uint64_t retired_page,
258 uint32_t channel_index,
259 uint32_t umc_inst)
260 {
261 struct eeprom_table_record *err_rec =
262 &err_data->err_addr[err_data->err_addr_cnt];
263
264 err_rec->address = err_addr;
265 /* page frame address is saved */
266 err_rec->retired_page = retired_page >> AMDGPU_GPU_PAGE_SHIFT;
267 err_rec->ts = (uint64_t)ktime_get_real_seconds();
268 err_rec->err_type = AMDGPU_RAS_EEPROM_ERR_NON_RECOVERABLE;
269 err_rec->cu = 0;
270 err_rec->mem_channel = channel_index;
271 err_rec->mcumc_id = umc_inst;
272
273 err_data->err_addr_cnt++;
274 }
275