diff options
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 38 |
1 files changed, 20 insertions, 18 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index ff5361f5c2d4..2dad7aa9a03b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -1811,7 +1811,8 @@ static void amdgpu_ras_log_on_err_counter(struct amdgpu_device *adev) amdgpu_ras_query_error_status(adev, &info); if (adev->ip_versions[MP0_HWIP][0] != IP_VERSION(11, 0, 2) && - adev->ip_versions[MP0_HWIP][0] != IP_VERSION(11, 0, 4)) { + adev->ip_versions[MP0_HWIP][0] != IP_VERSION(11, 0, 4) && + adev->ip_versions[MP0_HWIP][0] != IP_VERSION(13, 0, 0)) { if (amdgpu_ras_reset_error_status(adev, info.head.block)) dev_warn(adev->dev, "Failed to reset error counter and error status"); } @@ -1949,6 +1950,7 @@ static void amdgpu_ras_do_recovery(struct work_struct *work) reset_context.method = AMD_RESET_METHOD_NONE; reset_context.reset_req_dev = adev; clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags); + clear_bit(AMDGPU_SKIP_MODE2_RESET, &reset_context.flags); amdgpu_device_gpu_recover(ras->adev, NULL, &reset_context); } @@ -2718,7 +2720,8 @@ int amdgpu_ras_pre_fini(struct amdgpu_device *adev) /* Need disable ras on all IPs here before ip [hw/sw]fini */ - amdgpu_ras_disable_all_features(adev, 0); + if (con->features) + amdgpu_ras_disable_all_features(adev, 0); amdgpu_ras_recovery_fini(adev); return 0; } @@ -2831,11 +2834,8 @@ static int amdgpu_bad_page_notifier(struct notifier_block *nb, struct mce *m = (struct mce *)data; struct amdgpu_device *adev = NULL; uint32_t gpu_id = 0; - uint32_t umc_inst = 0; - uint32_t ch_inst, channel_index = 0; + uint32_t umc_inst = 0, ch_inst = 0; struct ras_err_data err_data = {0, 0, 0, NULL}; - struct eeprom_table_record err_rec; - uint64_t retired_page; /* * If the error was generated in UMC_V2, which belongs to GPU UMCs, @@ -2874,21 +2874,22 @@ static int amdgpu_bad_page_notifier(struct notifier_block *nb, dev_info(adev->dev, "Uncorrectable error detected in UMC inst: %d, chan_idx: %d", umc_inst, ch_inst); + err_data.err_addr = + kcalloc(adev->umc.max_ras_err_cnt_per_query, + sizeof(struct eeprom_table_record), GFP_KERNEL); + if (!err_data.err_addr) { + dev_warn(adev->dev, + "Failed to alloc memory for umc error record in mca notifier!\n"); + return NOTIFY_DONE; + } + /* * Translate UMC channel address to Physical address */ - channel_index = - adev->umc.channel_idx_tbl[umc_inst * adev->umc.channel_inst_num - + ch_inst]; - - retired_page = ADDR_OF_8KB_BLOCK(m->addr) | - ADDR_OF_256B_BLOCK(channel_index) | - OFFSET_IN_256B_BLOCK(m->addr); - - memset(&err_rec, 0x0, sizeof(struct eeprom_table_record)); - err_data.err_addr = &err_rec; - amdgpu_umc_fill_error_record(&err_data, m->addr, - retired_page, channel_index, umc_inst); + if (adev->umc.ras && + adev->umc.ras->convert_ras_error_address) + adev->umc.ras->convert_ras_error_address(adev, + &err_data, m->addr, ch_inst, umc_inst); if (amdgpu_bad_page_threshold != 0) { amdgpu_ras_add_bad_pages(adev, err_data.err_addr, @@ -2896,6 +2897,7 @@ static int amdgpu_bad_page_notifier(struct notifier_block *nb, amdgpu_ras_save_bad_pages(adev); } + kfree(err_data.err_addr); return NOTIFY_OK; } |