diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2021-04-28 10:01:40 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2021-04-28 10:01:40 -0700 |
commit | 68a32ba14177d4a21c4a9a941cf1d7aea86d436f (patch) | |
tree | 945c20860766c22b19d1806d5b5db5b37bc65b65 /drivers/gpu/drm/amd/amdgpu/umc_v6_7.c | |
parent | 3aa139aa9fdc138a84243dc49dc18d9b40e1c6e4 (diff) | |
parent | a1a1ca70deb3ec600eeabb21de7f3f48aaae5695 (diff) |
Merge tag 'drm-next-2021-04-28' of git://anongit.freedesktop.org/drm/drm
Pull drm updates from Dave Airlie:
"The usual lots of work all over the place.
i915 has gotten some Alderlake work and prelim DG1 code, along with a
major locking rework over the GEM code, and brings back the property
of timing out long running jobs using a watchdog. amdgpu has some
Alderbran support (new GPU), freesync HDMI support along with a lot
other fixes.
Outside of the drm, there is a new printf specifier added which should
have all the correct acks/sobs:
- printk fourcc modifier support added %p4cc
Summary:
core:
- drm_crtc_commit_wait
- atomic plane state helpers reworked for full state
- dma-buf heaps API rework
- edid: rework and improvements for displayid
dp-mst:
- better topology logging
bridge:
- Chipone ICN6211
- Lontium LT8912B
- anx7625 regulator support
panel:
- fix lt9611 4k panels handling
simple-kms:
- add plane state helpers
ttm:
- debugfs support
- removal of unused sysfs
- ignore signaled moved fences
- ioremap buffer according to mem caching
i915:
- Alderlake S enablement
- Conversion to dma_resv_locking
- Bring back watchdog timeout support
- legacy ioctl cleanups
- add GEM TDDO and RFC process
- DG1 LMEM preparation work
- intel_display.c refactoring
- Gen9/TGL PCH combination support
- eDP MSO Support
- multiple PSR instance support
- Link training debug updates
- Disable PSR2 support on JSL/EHL
- DDR5/LPDDR5 support for bw calcs
- LSPCON limited to gen9/10 platforms
- HSW/BDW async flip/VTd corruption workaround
- SAGV watermark fixes
- SNB hard hang on ring resume fix
- Limit imported dma-buf size
- move to use new tasklet API
- refactor KBL/TGL/ADL-S display/gt steppings
- refactoring legacy DP/HDMI, FB plane code out
amdgpu:
- uapi: add ioctl to query video capabilities
- Iniital AMD Freesync HDMI support
- Initial Adebaran support
- 10bpc dithering improvements
- DCN secure display support
- Drop legacy IO BAR requirements
- PCIE/S0ix/RAS/Prime/Reset fixes
- Display ASSR support
- SMU gfx busy queues for RV/PCO
- Initial LTTPR display work
amdkfd:
- MMU notifier fixes
- APU fixes
radeon:
- debugfs cleanps
- fw error handling ifix
- Flexible array cleanups
msm:
- big DSI phy/pll cleanup
- sc7280 initial support
- commong bandwidth scaling path
- shrinker locking contention fixes
- unpin/swap support for GEM objcets
ast:
- cursor plane handling reworked
tegra:
- don't register DP AUX channels before connectors
zynqmp:
- fix OOB struct padding memset
gma500:
- drop ttm and medfield support
exynos:
- request_irq cleanup function
mediatek:
- fine tune line time for EOTp
- MT8192 dpi support
- atomic crtc config updates
- don't support HDMI connector creation
mxsdb:
- imx8mm support
panfrost:
- MMU IRQ handling rework
qxl:
- locking fixes
- resource deallocation changes
sun4i:
- add alpha properties to UI/VI layers
vc4:
- RPi4 CEC support
vmwgfx:
- doc cleanups
arc:
- moved to drm/tiny"
* tag 'drm-next-2021-04-28' of git://anongit.freedesktop.org/drm/drm: (1390 commits)
drm/ttm: Don't count pages in SG BOs against pages_limit
drm/ttm: fix return value check
drm/bridge: lt8912b: fix incorrect handling of of_* return values
drm: bridge: fix LONTIUM use of mipi_dsi_() functions
drm: bridge: fix ANX7625 use of mipi_dsi_() functions
drm/amdgpu: page retire over debugfs mechanism
drm/radeon: Fix a missing check bug in radeon_dp_mst_detect()
drm/amd/display: Fix the Wunused-function warning
drm/radeon/r600: Fix variables that are not used after assignment
drm/amdgpu/smu7: fix CAC setting on TOPAZ
drm/amd/display: Update DCN302 SR Exit Latency
drm/amdgpu: enable ras eeprom on aldebaran
drm/amdgpu: RAS harvest on driver load
drm/amdgpu: add ras aldebaran ras eeprom driver
drm/amd/pm: increase time out value when sending msg to SMU
drm/amdgpu: add DMUB outbox event IRQ source define/complete/debug flag
drm/amd/pm: add the callback to get vbios bootup values for vangogh
drm/radeon: Fix size overflow
drm/amdgpu: Fix size overflow
drm/amdgpu: move mmhub ras_func init to ip specific file
...
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/umc_v6_7.c')
-rw-r--r-- | drivers/gpu/drm/amd/amdgpu/umc_v6_7.c | 281 |
1 files changed, 281 insertions, 0 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c b/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c new file mode 100644 index 000000000000..3a8f787374c0 --- /dev/null +++ b/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c @@ -0,0 +1,281 @@ +/* + * 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_umc.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); +} + +static void umc_v6_7_query_error_address(struct amdgpu_device *adev, + struct ras_err_data *err_data, + uint32_t umc_reg_offset, + uint32_t ch_inst, + uint32_t umc_inst) +{ + uint32_t mc_umc_status_addr; + uint64_t mc_umc_status, err_addr, retired_page, mc_umc_addrt0; + struct eeprom_table_record *err_rec; + uint32_t channel_index; + + mc_umc_status_addr = + SOC15_REG_OFFSET(UMC, 0, regMCA_UMC_UMC0_MCUMC_STATUST0); + mc_umc_addrt0 = + SOC15_REG_OFFSET(UMC, 0, regMCA_UMC_UMC0_MCUMC_ADDRT0); + + mc_umc_status = RREG64_PCIE((mc_umc_status_addr + umc_reg_offset) * 4); + + if (mc_umc_status == 0) + return; + + if (!err_data->err_addr) { + /* clear umc status */ + WREG64_PCIE((mc_umc_status_addr + umc_reg_offset) * 4, 0x0ULL); + return; + } + + err_rec = &err_data->err_addr[err_data->err_addr_cnt]; + + channel_index = + adev->umc.channel_idx_tbl[umc_inst * adev->umc.channel_inst_num + ch_inst]; + + /* calculate error address if ue/ce error is detected */ + 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, UECC) == 1 || + REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, CECC) == 1)) { + + err_addr = RREG64_PCIE((mc_umc_addrt0 + umc_reg_offset) * 4); + err_addr = REG_GET_FIELD(err_addr, MCA_UMC_UMC0_MCUMC_ADDRT0, ErrorAddr); + + /* translate umc channel address to soc pa, 3 parts are included */ + retired_page = ADDR_OF_8KB_BLOCK(err_addr) | + ADDR_OF_256B_BLOCK(channel_index) | + OFFSET_IN_256B_BLOCK(err_addr); + + /* we only save ue error information currently, ce is skipped */ + if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) + == 1) { + err_rec->address = err_addr; + /* page frame address is saved */ + err_rec->retired_page = retired_page >> AMDGPU_GPU_PAGE_SHIFT; + err_rec->ts = (uint64_t)ktime_get_real_seconds(); + err_rec->err_type = AMDGPU_RAS_EEPROM_ERR_NON_RECOVERABLE; + err_rec->cu = 0; + err_rec->mem_channel = channel_index; + err_rec->mcumc_id = umc_inst; + + err_data->err_addr_cnt++; + } + } + + /* clear umc status */ + WREG64_PCIE((mc_umc_status_addr + umc_reg_offset) * 4, 0x0ULL); +} + +static void umc_v6_7_query_ras_error_address(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 resgisters. Will add the protection + * when firmware interface is ready */ + 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_error_address(adev, + err_data, + umc_reg_offset, + ch_inst, + umc_inst); + } +} + +const struct amdgpu_umc_ras_funcs umc_v6_7_ras_funcs = { + .ras_late_init = amdgpu_umc_ras_late_init, + .ras_fini = amdgpu_umc_ras_fini, + .query_ras_error_count = umc_v6_7_query_ras_error_count, + .query_ras_error_address = umc_v6_7_query_ras_error_address, +}; |