| 1 | // SPDX-License-Identifier: MIT |
| 2 | /* |
| 3 | * Copyright 2025 Advanced Micro Devices, Inc. |
| 4 | * |
| 5 | * Permission is hereby granted, free of charge, to any person obtaining a |
| 6 | * copy of this software and associated documentation files (the "Software"), |
| 7 | * to deal in the Software without restriction, including without limitation |
| 8 | * the rights to use, copy, modify, merge, publish, distribute, sublicense, |
| 9 | * and/or sell copies of the Software, and to permit persons to whom the |
| 10 | * Software is furnished to do so, subject to the following conditions: |
| 11 | * |
| 12 | * The above copyright notice and this permission notice shall be included in |
| 13 | * all copies or substantial portions of the Software. |
| 14 | * |
| 15 | * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR |
| 16 | * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, |
| 17 | * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL |
| 18 | * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR |
| 19 | * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, |
| 20 | * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR |
| 21 | * OTHER DEALINGS IN THE SOFTWARE. |
| 22 | * |
| 23 | */ |
| 24 | #include "amdgpu_smu.h" |
| 25 | #include "amdgpu_reset.h" |
| 26 | #include "amdgpu_ras_mp1_v13_0.h" |
| 27 | |
| 28 | #define RAS_MP1_MSG_QueryValidMcaCeCount 0x3A |
| 29 | #define RAS_MP1_MSG_McaBankCeDumpDW 0x3B |
| 30 | |
| 31 | static int mp1_v13_0_get_valid_bank_count(struct ras_core_context *ras_core, |
| 32 | u32 msg, u32 *count) |
| 33 | { |
| 34 | struct amdgpu_device *adev = (struct amdgpu_device *)ras_core->dev; |
| 35 | u32 smu_msg; |
| 36 | int ret = 0; |
| 37 | |
| 38 | if (!count) |
| 39 | return -EINVAL; |
| 40 | |
| 41 | smu_msg = (msg == RAS_MP1_MSG_QueryValidMcaCeCount) ? |
| 42 | SMU_MSG_QueryValidMcaCeCount : SMU_MSG_QueryValidMcaCount; |
| 43 | |
| 44 | if (down_read_trylock(sem: &adev->reset_domain->sem)) { |
| 45 | ret = amdgpu_smu_ras_send_msg(adev, msg: smu_msg, param: 0, readarg: count); |
| 46 | up_read(sem: &adev->reset_domain->sem); |
| 47 | } else { |
| 48 | ret = -RAS_CORE_GPU_IN_MODE1_RESET; |
| 49 | } |
| 50 | |
| 51 | if (ret) |
| 52 | *count = 0; |
| 53 | |
| 54 | return ret; |
| 55 | } |
| 56 | |
| 57 | static int mp1_v13_0_dump_valid_bank(struct ras_core_context *ras_core, |
| 58 | u32 msg, u32 idx, u32 reg_idx, u64 *val) |
| 59 | { |
| 60 | struct amdgpu_device *adev = (struct amdgpu_device *)ras_core->dev; |
| 61 | uint32_t data[2] = {0, 0}; |
| 62 | uint32_t param; |
| 63 | int ret = 0; |
| 64 | int i, offset; |
| 65 | u32 smu_msg = (msg == RAS_MP1_MSG_McaBankCeDumpDW) ? |
| 66 | SMU_MSG_McaBankCeDumpDW : SMU_MSG_McaBankDumpDW; |
| 67 | |
| 68 | if (down_read_trylock(sem: &adev->reset_domain->sem)) { |
| 69 | offset = reg_idx * 8; |
| 70 | for (i = 0; i < ARRAY_SIZE(data); i++) { |
| 71 | param = ((idx & 0xffff) << 16) | ((offset + (i << 2)) & 0xfffc); |
| 72 | ret = amdgpu_smu_ras_send_msg(adev, msg: smu_msg, param, readarg: &data[i]); |
| 73 | if (ret) { |
| 74 | RAS_DEV_ERR(adev, "ACA failed to read register[%d], offset:0x%x\n" , |
| 75 | reg_idx, offset); |
| 76 | break; |
| 77 | } |
| 78 | } |
| 79 | up_read(sem: &adev->reset_domain->sem); |
| 80 | |
| 81 | if (!ret) |
| 82 | *val = (uint64_t)data[1] << 32 | data[0]; |
| 83 | } else { |
| 84 | ret = -RAS_CORE_GPU_IN_MODE1_RESET; |
| 85 | } |
| 86 | |
| 87 | return ret; |
| 88 | } |
| 89 | |
| 90 | const struct ras_mp1_sys_func amdgpu_ras_mp1_sys_func_v13_0 = { |
| 91 | .mp1_get_valid_bank_count = mp1_v13_0_get_valid_bank_count, |
| 92 | .mp1_dump_valid_bank = mp1_v13_0_dump_valid_bank, |
| 93 | }; |
| 94 | |
| 95 | |