linux/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c
Hawking Zhang 878b9e944c drm/amdgpu: implement umc query error count callback
umc query_ras_error_count will be invoked to query
umc correctable and uncorrectable error. It will
reset the umc ras error counter after the query.

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: John Clements <John.Clements@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2021-04-09 16:50:58 -04:00

189 lines
6.5 KiB
C

/*
* Copyright 2021 Advanced Micro Devices, Inc.
*
* Permission is hereby granted, free of charge, to any person obtaining a
* copy of this software and associated documentation files (the "Software"),
* to deal in the Software without restriction, including without limitation
* the rights to use, copy, modify, merge, publish, distribute, sublicense,
* and/or sell copies of the Software, and to permit persons to whom the
* Software is furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
* OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
* ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
* OTHER DEALINGS IN THE SOFTWARE.
*
*/
#include "umc_v6_7.h"
#include "amdgpu_ras.h"
#include "amdgpu.h"
#include "umc/umc_6_7_0_offset.h"
#include "umc/umc_6_7_0_sh_mask.h"
static inline uint32_t get_umc_v6_7_reg_offset(struct amdgpu_device *adev,
uint32_t umc_inst,
uint32_t ch_inst)
{
return adev->umc.channel_offs * ch_inst + UMC_V6_7_INST_DIST * umc_inst;
}
static void umc_v6_7_query_correctable_error_count(struct amdgpu_device *adev,
uint32_t umc_reg_offset,
unsigned long *error_count)
{
uint32_t ecc_err_cnt_sel, ecc_err_cnt_sel_addr;
uint32_t ecc_err_cnt, ecc_err_cnt_addr;
uint64_t mc_umc_status;
uint32_t mc_umc_status_addr;
/* UMC 6_1_1 registers */
ecc_err_cnt_sel_addr =
SOC15_REG_OFFSET(UMC, 0, regUMCCH0_0_EccErrCntSel);
ecc_err_cnt_addr =
SOC15_REG_OFFSET(UMC, 0, regUMCCH0_0_EccErrCnt);
mc_umc_status_addr =
SOC15_REG_OFFSET(UMC, 0, regMCA_UMC_UMC0_MCUMC_STATUST0);
/* select the lower chip and check the error count */
ecc_err_cnt_sel = RREG32_PCIE((ecc_err_cnt_sel_addr + umc_reg_offset) * 4);
ecc_err_cnt_sel = REG_SET_FIELD(ecc_err_cnt_sel, UMCCH0_0_EccErrCntSel,
EccErrCntCsSel, 0);
WREG32_PCIE((ecc_err_cnt_sel_addr + umc_reg_offset) * 4, ecc_err_cnt_sel);
ecc_err_cnt = RREG32_PCIE((ecc_err_cnt_addr + umc_reg_offset) * 4);
*error_count +=
(REG_GET_FIELD(ecc_err_cnt, UMCCH0_0_EccErrCnt, EccErrCnt) -
UMC_V6_7_CE_CNT_INIT);
/* select the higher chip and check the err counter */
ecc_err_cnt_sel = REG_SET_FIELD(ecc_err_cnt_sel, UMCCH0_0_EccErrCntSel,
EccErrCntCsSel, 1);
WREG32_PCIE((ecc_err_cnt_sel_addr + umc_reg_offset) * 4, ecc_err_cnt_sel);
ecc_err_cnt = RREG32_PCIE((ecc_err_cnt_addr + umc_reg_offset) * 4);
*error_count +=
(REG_GET_FIELD(ecc_err_cnt, UMCCH0_0_EccErrCnt, EccErrCnt) -
UMC_V6_7_CE_CNT_INIT);
/* check for SRAM correctable error
MCUMC_STATUS is a 64 bit register */
mc_umc_status = RREG64_PCIE((mc_umc_status_addr + umc_reg_offset) * 4);
if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1 &&
REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, CECC) == 1)
*error_count += 1;
}
static void umc_v6_7_querry_uncorrectable_error_count(struct amdgpu_device *adev,
uint32_t umc_reg_offset,
unsigned long *error_count)
{
uint64_t mc_umc_status;
uint32_t mc_umc_status_addr;
mc_umc_status_addr =
SOC15_REG_OFFSET(UMC, 0, regMCA_UMC_UMC0_MCUMC_STATUST0);
/* check the MCUMC_STATUS */
mc_umc_status = RREG64_PCIE((mc_umc_status_addr + umc_reg_offset) * 4);
if ((REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1) &&
(REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Deferred) == 1 ||
REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1 ||
REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, PCC) == 1 ||
REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UC) == 1 ||
REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, TCC) == 1))
*error_count += 1;
}
static void umc_v6_7_reset_error_count_per_channel(struct amdgpu_device *adev,
uint32_t umc_reg_offset)
{
uint32_t ecc_err_cnt_addr;
uint32_t ecc_err_cnt_sel, ecc_err_cnt_sel_addr;
ecc_err_cnt_sel_addr =
SOC15_REG_OFFSET(UMC, 0,
regUMCCH0_0_EccErrCntSel);
ecc_err_cnt_addr =
SOC15_REG_OFFSET(UMC, 0,
regUMCCH0_0_EccErrCnt);
/* select the lower chip */
ecc_err_cnt_sel = RREG32_PCIE((ecc_err_cnt_sel_addr +
umc_reg_offset) * 4);
ecc_err_cnt_sel = REG_SET_FIELD(ecc_err_cnt_sel,
UMCCH0_0_EccErrCntSel,
EccErrCntCsSel, 0);
WREG32_PCIE((ecc_err_cnt_sel_addr + umc_reg_offset) * 4,
ecc_err_cnt_sel);
/* clear lower chip error count */
WREG32_PCIE((ecc_err_cnt_addr + umc_reg_offset) * 4,
UMC_V6_7_CE_CNT_INIT);
/* select the higher chip */
ecc_err_cnt_sel = RREG32_PCIE((ecc_err_cnt_sel_addr +
umc_reg_offset) * 4);
ecc_err_cnt_sel = REG_SET_FIELD(ecc_err_cnt_sel,
UMCCH0_0_EccErrCntSel,
EccErrCntCsSel, 1);
WREG32_PCIE((ecc_err_cnt_sel_addr + umc_reg_offset) * 4,
ecc_err_cnt_sel);
/* clear higher chip error count */
WREG32_PCIE((ecc_err_cnt_addr + umc_reg_offset) * 4,
UMC_V6_7_CE_CNT_INIT);
}
static void umc_v6_7_reset_error_count(struct amdgpu_device *adev)
{
uint32_t umc_inst = 0;
uint32_t ch_inst = 0;
uint32_t umc_reg_offset = 0;
LOOP_UMC_INST_AND_CH(umc_inst, ch_inst) {
umc_reg_offset = get_umc_v6_7_reg_offset(adev,
umc_inst,
ch_inst);
umc_v6_7_reset_error_count_per_channel(adev,
umc_reg_offset);
}
}
static void umc_v6_7_query_ras_error_count(struct amdgpu_device *adev,
void *ras_error_status)
{
struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status;
uint32_t umc_inst = 0;
uint32_t ch_inst = 0;
uint32_t umc_reg_offset = 0;
/*TODO: driver needs to toggle DF Cstate to ensure
* safe access of UMC registers. Will add the protection */
LOOP_UMC_INST_AND_CH(umc_inst, ch_inst) {
umc_reg_offset = get_umc_v6_7_reg_offset(adev,
umc_inst,
ch_inst);
umc_v6_7_query_correctable_error_count(adev,
umc_reg_offset,
&(err_data->ce_count));
umc_v6_7_querry_uncorrectable_error_count(adev,
umc_reg_offset,
&(err_data->ue_count));
}
umc_v6_7_reset_error_count(adev);
}
const struct amdgpu_umc_funcs umc_v6_7_funcs = {
.ras_late_init = amdgpu_umc_ras_late_init,
.query_ras_error_count = umc_v6_7_query_ras_error_count,
};