amdgpu_vf_error.c 3.1 KB

12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485
  1. /*
  2. * Copyright 2017 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. #include "amdgpu.h"
  24. #include "amdgpu_vf_error.h"
  25. #include "mxgpu_ai.h"
  26. #define AMDGPU_VF_ERROR_ENTRY_SIZE 16
  27. /* struct error_entry - amdgpu VF error information. */
  28. struct amdgpu_vf_error_buffer {
  29. int read_count;
  30. int write_count;
  31. uint16_t code[AMDGPU_VF_ERROR_ENTRY_SIZE];
  32. uint16_t flags[AMDGPU_VF_ERROR_ENTRY_SIZE];
  33. uint64_t data[AMDGPU_VF_ERROR_ENTRY_SIZE];
  34. };
  35. struct amdgpu_vf_error_buffer admgpu_vf_errors;
  36. void amdgpu_vf_error_put(uint16_t sub_error_code, uint16_t error_flags, uint64_t error_data)
  37. {
  38. int index;
  39. uint16_t error_code = AMDGIM_ERROR_CODE(AMDGIM_ERROR_CATEGORY_VF, sub_error_code);
  40. index = admgpu_vf_errors.write_count % AMDGPU_VF_ERROR_ENTRY_SIZE;
  41. admgpu_vf_errors.code [index] = error_code;
  42. admgpu_vf_errors.flags [index] = error_flags;
  43. admgpu_vf_errors.data [index] = error_data;
  44. admgpu_vf_errors.write_count ++;
  45. }
  46. void amdgpu_vf_error_trans_all(struct amdgpu_device *adev)
  47. {
  48. /* u32 pf2vf_flags = 0; */
  49. u32 data1, data2, data3;
  50. int index;
  51. if ((NULL == adev) || (!amdgpu_sriov_vf(adev)) || (!adev->virt.ops) || (!adev->virt.ops->trans_msg)) {
  52. return;
  53. }
  54. /*
  55. TODO: Enable these code when pv2vf_info is merged
  56. AMDGPU_FW_VRAM_PF2VF_READ (adev, feature_flags, &pf2vf_flags);
  57. if (!(pf2vf_flags & AMDGIM_FEATURE_ERROR_LOG_COLLECT)) {
  58. return;
  59. }
  60. */
  61. /* The errors are overlay of array, correct read_count as full. */
  62. if (admgpu_vf_errors.write_count - admgpu_vf_errors.read_count > AMDGPU_VF_ERROR_ENTRY_SIZE) {
  63. admgpu_vf_errors.read_count = admgpu_vf_errors.write_count - AMDGPU_VF_ERROR_ENTRY_SIZE;
  64. }
  65. while (admgpu_vf_errors.read_count < admgpu_vf_errors.write_count) {
  66. index =admgpu_vf_errors.read_count % AMDGPU_VF_ERROR_ENTRY_SIZE;
  67. data1 = AMDGIM_ERROR_CODE_FLAGS_TO_MAILBOX (admgpu_vf_errors.code[index], admgpu_vf_errors.flags[index]);
  68. data2 = admgpu_vf_errors.data[index] & 0xFFFFFFFF;
  69. data3 = (admgpu_vf_errors.data[index] >> 32) & 0xFFFFFFFF;
  70. adev->virt.ops->trans_msg(adev, IDH_LOG_VF_ERROR, data1, data2, data3);
  71. admgpu_vf_errors.read_count ++;
  72. }
  73. }