diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2024-03-13 18:34:05 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2024-03-13 18:34:05 -0700 |
| commit | 480e035fc4c714fb5536e64ab9db04fedc89e910 (patch) | |
| tree | 01341ee43abe7ecb8efb4e7bbbb1c3b3b50f7ec8 /drivers/gpu/drm/amd/pm | |
| parent | e5e038b7ae9da96b93974bf072ca1876899a01a3 (diff) | |
| parent | 119b225f01e4d3ce974cd3b4d982c76a380c796d (diff) | |
Merge tag 'drm-next-2024-03-13' of https://gitlab.freedesktop.org/drm/kernel
Pull drm updates from Dave Airlie:
"Highlights are usual, more AMD IP blocks for future hw, i915/xe
changes, Displayport tunnelling support for i915, msm YUV over DP
changes, new tests for ttm, but its mostly a lot of stuff all over the
place from lots of people.
core:
- EDID cleanups
- scheduler error handling fixes
- managed: add drmm_release_action() with tests
- add ratelimited drm debug print
- DPCD PSR early transport macro
- DP tunneling and bandwidth allocation helpers
- remove built-in edids
- dp: Avoid AUX transfers on powered-down displays
- dp: Add VSC SDP helpers
cross drivers:
- use new drm print helpers
- switch to ->read_edid callback
- gem: add stats for shared buffers plus updates to amdgpu, i915, xe
syncobj:
- fixes to waiting and sleeping
ttm:
- add tests
- fix errno codes
- simply busy-placement handling
- fix page decryption
media:
- tc358743: fix v4l device registration
video:
- move all kernel parameters for video behind CONFIG_VIDEO
sound:
- remove <drm/drm_edid.h> include from header
ci:
- add tests for msm
- fix apq8016 runner
efifb:
- use copy of global screen_info state
vesafb:
- use copy of global screen_info state
simplefb:
- fix logging
bridge:
- ite-6505: fix DP link-training bug
- samsung-dsim: fix error checking in probe
- samsung-dsim: add bsh-smm-s2/pro boards
- tc358767: fix regmap usage
- imx: add i.MX8MP HDMI PVI plus DT bindings
- imx: add i.MX8MP HDMI TX plus DT bindings
- sii902x: fix probing and unregistration
- tc358767: limit pixel PLL input range
- switch to new drm_bridge_read_edid() interface
panel:
- ltk050h3146w: error-handling fixes
- panel-edp: support delay between power-on and enable; use put_sync
in unprepare; support Mediatek MT8173 Chromebooks, BOE NV116WHM-N49
V8.0, BOE NV122WUM-N41, CSO MNC207QS1-1 plus DT bindings
- panel-lvds: support EDT ETML0700Z9NDHA plus DT bindings
- panel-novatek: FRIDA FRD400B25025-A-CTK plus DT bindings
- add BOE TH101MB31IG002-28A plus DT bindings
- add EDT ETML1010G3DRA plus DT bindings
- add Novatek NT36672E LCD DSI plus DT bindings
- nt36523: support 120Hz timings, fix includes
- simple: fix display timings on RK32FN48H
- visionox-vtdr6130: fix initialization
- add Powkiddy RGB10MAX3 plus DT bindings
- st7703: support panel rotation plus DT bindings
- add Himax HX83112A plus DT bindings
- ltk500hd1829: add support for ltk101b4029w and admatec 9904370
- simple: add BOE BP082WX1-100 8.2" panel plus DT bindungs
panel-orientation-quirks:
- GPD Win Mini
amdgpu:
- Validate DMABuf imports in compute VMs
- Add RAS ACA framework
- PSP 13 fixes
- Misc code cleanups
- Replay fixes
- Atom interpretor PS, WS bounds checking
- DML2 fixes
- Audio fixes
- DCN 3.5 Z state fixes
- Remove deprecated ida_simple usage
- UBSAN fixes
- RAS fixes
- Enable seq64 infrastructure
- DC color block enablement
- Documentation updates
- DC documentation updates
- DMCUB updates
- ATHUB 4.1 support
- LSDMA 7.0 support
- JPEG DPG support
- IH 7.0 support
- HDP 7.0 support
- VCN 5.0 support
- SMU 13.0.6 updates
- NBIO 7.11 updates
- SDMA 6.1 updates
- MMHUB 3.3 updates
- DCN 3.5.1 support
- NBIF 6.3.1 support
- VPE 6.1.1 support
amdkfd:
- Validate DMABuf imports in compute VMs
- SVM fixes
- Trap handler updates and enhancements
- Fix cache size reporting
- Relocate the trap handler
radeon:
- Atom interpretor PS, WS bounds checking
- Misc code cleanups
xe:
- new query for GuC submission version
- Remove unused persistent exec_queues
- Add vram frequency sysfs attributes
- Add the flag XE_VM_BIND_FLAG_DUMPABLE
- Drop pre-production workarounds
- Drop kunit tests for unsupported platforms
- Start pumbling SR-IOV support with memory based interrupts for VF
- Allow to map BO in GGTT with PAT index corresponding to XE_CACHE_UC
to work with memory based interrupts
- Add GuC Doorbells Manager as prep work SR-IOV
- Implement additional workarounds for xe2 and MTL
- Program a few registers according to perfomance guide spec for Xe2
- Fix remaining 32b build issues and enable it back
- Fix build with CONFIG_DEBUG_FS=n
- Fix warnings from GuC ABI headers
- Introduce Relay Communication for SR-IOV for VF <-> GuC <-> PF
- Release mmap mappings on rpm suspend
- Disable mid-thread preemption when not properly supported by
hardware
- Fix xe_exec by reserving extra fence slot for CPU bind
- Fix xe_exec with full long running exec queue
- Canonicalize addresses where needed for Xe2 and add to devcoredum
- Toggle USM support for Xe2
- Only allow 1 ufence per exec / bind IOCTL
- Add GuC firmware loading for Lunar Lake
- Add XE_VMA_PTE_64K VMA flag
i915:
- Add more ADL-N PCI IDs
- Enable fastboot also on older platforms
- Early transport for panel replay and PSR
- New ARL PCI IDs
- DP TPS4 PHY test pattern support
- Unify and improve VSC SDP for PSR and non-PSR cases
- Refactor memory regions and improve debug logging
- Rework global state serialization
- Remove unused CDCLK divider fields
- Unify HDCP connector logging format
- Use display instead of graphics version in display code
- Move VBT and opregion debugfs next to the implementation
- Abstract opregion interface, use opaque type
- MTL fixes
- HPD handling fixes
- Add GuC submission interface version query
- Atomically invalidate userptr on mmu-notifier
- Update handling of MMIO triggered reports
- Don't make assumptions about intel_wakeref_t type
- Extend driver code of Xe_LPG to Xe_LPG+
- Add flex arrays to struct i915_syncmap
- Allow for very slow HuC loading
- DP tunneling and bandwidth allocation support
msm:
- Correct bindings for MSM8976 and SM8650 platforms
- Start migration of MDP5 platforms to DPU driver
- X1E80100 MDSS support
- DPU:
- Improve DSC allocation, fixing several important corner cases
- Add support for SDM630/SDM660 platforms
- Simplify dpu_encoder_phys_ops
- Apply fixes targeting DSC support with a single DSC encoder
- Apply fixes for HCTL_EN timing configuration
- X1E80100 support
- Add support for YUV420 over DP
- GPU:
- fix sc7180 UBWC config
- fix a7xx LLC config
- new gpu support: a305B, a750, a702
- machine support: SM7150 (different power levels than other a618)
- a7xx devcoredump support
habanalabs:
- configure IRQ affinity according to NUMA node
- move HBM MMU page tables inside the HBM
- improve device reset
- check extended PCIe errors
ivpu:
- updates to firmware API
- refactor BO allocation
imx:
- use devm_ functions during init
hisilicon:
- fix EDID includes
mgag200:
- improve ioremap usage
- convert to struct drm_edid
- Work around PCI write bursts
nouveau:
- disp: use kmemdup()
- fix EDID includes
- documentation fixes
qaic:
- fixes to BO handling
- make use of DRM managed release
- fix order of remove operations
rockchip:
- analogix_dp: get encoder port from DT
- inno_hdmi: support HDMI for RK3128
- lvds: error-handling fixes
ssd130x:
- support SSD133x plus DT bindings
tegra:
- fix error handling
tilcdc:
- make use of DRM managed release
v3d:
- show memory stats in debugfs
- Support display MMU page size
vc4:
- fix error handling in plane prepare_fb
- fix framebuffer test in plane helpers
virtio:
- add venus capset defines
vkms:
- fix OOB access when programming the LUT
- Kconfig improvements
vmwgfx:
- unmap surface before changing plane state
- fix memory leak in error handling
- documentation fixes
- list command SVGA_3D_CMD_DEFINE_GB_SURFACE_V4 as invalid
- fix null-pointer deref in execbuf
- refactor display-mode probing
- fix fencing for creating cursor MOBs
- fix cursor-memory lifetime
xlnx:
- fix live video input for ZynqMP DPSUB
lima:
- fix memory leak
loongson:
- fail if no VRAM present
meson:
- switch to new drm_bridge_read_edid() interface
renesas:
- add RZ/G2L DU support plus DT bindings
mxsfb:
- Use managed mode config
sun4i:
- HDMI: updates to atomic mode setting
mediatek:
- Add display driver for MT8188 VDOSYS1
- DSI driver cleanups
- Filter modes according to hardware capability
- Fix a null pointer crash in mtk_drm_crtc_finish_page_flip
etnaviv:
- enhancements for NPU and MRT support"
* tag 'drm-next-2024-03-13' of https://gitlab.freedesktop.org/drm/kernel: (1420 commits)
drm/amd/display: Removed redundant @ symbol to fix kernel-doc warnings in -next repo
drm/amd/pm: wait for completion of the EnableGfxImu message
drm/amdgpu/soc21: add mode2 asic reset for SMU IP v14.0.1
drm/amdgpu: add smu 14.0.1 support
drm/amdgpu: add VPE 6.1.1 discovery support
drm/amdgpu/vpe: add VPE 6.1.1 support
drm/amdgpu/vpe: don't emit cond exec command under collaborate mode
drm/amdgpu/vpe: add collaborate mode support for VPE
drm/amdgpu/vpe: add PRED_EXE and COLLAB_SYNC OPCODE
drm/amdgpu/vpe: add multi instance VPE support
drm/amdgpu/discovery: add nbif v6_3_1 ip block
drm/amdgpu: Add nbif v6_3_1 ip block support
drm/amdgpu: Add pcie v6_1_0 ip headers (v5)
drm/amdgpu: Add nbif v6_3_1 ip headers (v5)
arch/powerpc: Remove <linux/fb.h> from backlight code
macintosh/via-pmu-backlight: Include <linux/backlight.h>
fbdev/chipsfb: Include <linux/backlight.h>
drm/etnaviv: Restore some id values
drm/amdkfd: make kfd_class constant
drm/amdgpu: add ring timeout information in devcoredump
...
Diffstat (limited to 'drivers/gpu/drm/amd/pm')
18 files changed, 496 insertions, 125 deletions
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c index 6627ee07d52d..f84bfed50681 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c @@ -693,6 +693,21 @@ int amdgpu_dpm_send_hbm_bad_channel_flag(struct amdgpu_device *adev, uint32_t si return ret; } +int amdgpu_dpm_send_rma_reason(struct amdgpu_device *adev) +{ + struct smu_context *smu = adev->powerplay.pp_handle; + int ret; + + if (!is_support_sw_smu(adev)) + return -EOPNOTSUPP; + + mutex_lock(&adev->pm.mutex); + ret = smu_send_rma_reason(smu); + mutex_unlock(&adev->pm.mutex); + + return ret; +} + int amdgpu_dpm_get_dpm_freq_range(struct amdgpu_device *adev, enum pp_clock_type type, uint32_t *min, diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c index 39c5e1dfa275..f09b9d49297e 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c @@ -2034,6 +2034,63 @@ static int ss_bias_attr_update(struct amdgpu_device *adev, struct amdgpu_device_ return 0; } +static int pp_od_clk_voltage_attr_update(struct amdgpu_device *adev, struct amdgpu_device_attr *attr, + uint32_t mask, enum amdgpu_device_attr_states *states) +{ + uint32_t gc_ver = amdgpu_ip_version(adev, GC_HWIP, 0); + + *states = ATTR_STATE_SUPPORTED; + + if (!amdgpu_dpm_is_overdrive_supported(adev)) { + *states = ATTR_STATE_UNSUPPORTED; + return 0; + } + + /* Enable pp_od_clk_voltage node for gc 9.4.3 SRIOV/BM support */ + if (gc_ver == IP_VERSION(9, 4, 3)) { + if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev)) + *states = ATTR_STATE_UNSUPPORTED; + return 0; + } + + if (!(attr->flags & mask)) + *states = ATTR_STATE_UNSUPPORTED; + + return 0; +} + +static int pp_dpm_dcefclk_attr_update(struct amdgpu_device *adev, struct amdgpu_device_attr *attr, + uint32_t mask, enum amdgpu_device_attr_states *states) +{ + struct device_attribute *dev_attr = &attr->dev_attr; + uint32_t gc_ver; + + *states = ATTR_STATE_SUPPORTED; + + if (!(attr->flags & mask)) { + *states = ATTR_STATE_UNSUPPORTED; + return 0; + } + + gc_ver = amdgpu_ip_version(adev, GC_HWIP, 0); + /* dcefclk node is not available on gfx 11.0.3 sriov */ + if ((gc_ver == IP_VERSION(11, 0, 3) && amdgpu_sriov_is_pp_one_vf(adev)) || + gc_ver < IP_VERSION(9, 0, 0) || + !amdgpu_device_has_display_hardware(adev)) + *states = ATTR_STATE_UNSUPPORTED; + + /* SMU MP1 does not support dcefclk level setting, + * setting should not be allowed from VF if not in one VF mode. + */ + if (gc_ver >= IP_VERSION(10, 0, 0) || + (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))) { + dev_attr->attr.mode &= ~S_IWUGO; + dev_attr->store = NULL; + } + + return 0; +} + /* Following items will be read out to indicate current plpd policy: * - -1: none * - 0: disallow @@ -2113,12 +2170,14 @@ static struct amdgpu_device_attr amdgpu_device_attrs[] = { AMDGPU_DEVICE_ATTR_RW(pp_dpm_vclk1, ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF), AMDGPU_DEVICE_ATTR_RW(pp_dpm_dclk, ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF), AMDGPU_DEVICE_ATTR_RW(pp_dpm_dclk1, ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF), - AMDGPU_DEVICE_ATTR_RW(pp_dpm_dcefclk, ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF), + AMDGPU_DEVICE_ATTR_RW(pp_dpm_dcefclk, ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF, + .attr_update = pp_dpm_dcefclk_attr_update), AMDGPU_DEVICE_ATTR_RW(pp_dpm_pcie, ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF), AMDGPU_DEVICE_ATTR_RW(pp_sclk_od, ATTR_FLAG_BASIC), AMDGPU_DEVICE_ATTR_RW(pp_mclk_od, ATTR_FLAG_BASIC), AMDGPU_DEVICE_ATTR_RW(pp_power_profile_mode, ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF), - AMDGPU_DEVICE_ATTR_RW(pp_od_clk_voltage, ATTR_FLAG_BASIC), + AMDGPU_DEVICE_ATTR_RW(pp_od_clk_voltage, ATTR_FLAG_BASIC, + .attr_update = pp_od_clk_voltage_attr_update), AMDGPU_DEVICE_ATTR_RO(gpu_busy_percent, ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF), AMDGPU_DEVICE_ATTR_RO(mem_busy_percent, ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF), AMDGPU_DEVICE_ATTR_RO(pcie_bw, ATTR_FLAG_BASIC), @@ -2156,17 +2215,9 @@ static int default_attr_update(struct amdgpu_device *adev, struct amdgpu_device_ if (DEVICE_ATTR_IS(pp_dpm_socclk)) { if (gc_ver < IP_VERSION(9, 0, 0)) *states = ATTR_STATE_UNSUPPORTED; - } else if (DEVICE_ATTR_IS(pp_dpm_dcefclk)) { - if (gc_ver < IP_VERSION(9, 0, 0) || - !amdgpu_device_has_display_hardware(adev)) - *states = ATTR_STATE_UNSUPPORTED; } else if (DEVICE_ATTR_IS(pp_dpm_fclk)) { if (mp1_ver < IP_VERSION(10, 0, 0)) *states = ATTR_STATE_UNSUPPORTED; - } else if (DEVICE_ATTR_IS(pp_od_clk_voltage)) { - *states = ATTR_STATE_UNSUPPORTED; - if (amdgpu_dpm_is_overdrive_supported(adev)) - *states = ATTR_STATE_SUPPORTED; } else if (DEVICE_ATTR_IS(mem_busy_percent)) { if ((adev->flags & AMD_IS_APU && gc_ver != IP_VERSION(9, 4, 3)) || @@ -2174,7 +2225,8 @@ static int default_attr_update(struct amdgpu_device *adev, struct amdgpu_device_ *states = ATTR_STATE_UNSUPPORTED; } else if (DEVICE_ATTR_IS(pcie_bw)) { /* PCIe Perf counters won't work on APU nodes */ - if (adev->flags & AMD_IS_APU) + if (adev->flags & AMD_IS_APU || + !adev->asic_funcs->get_pcie_usage) *states = ATTR_STATE_UNSUPPORTED; } else if (DEVICE_ATTR_IS(unique_id)) { switch (gc_ver) { @@ -2280,14 +2332,6 @@ static int default_attr_update(struct amdgpu_device *adev, struct amdgpu_device_ break; } - if (DEVICE_ATTR_IS(pp_dpm_dcefclk)) { - /* SMU MP1 does not support dcefclk level setting */ - if (gc_ver >= IP_VERSION(10, 0, 0)) { - dev_attr->attr.mode &= ~S_IWUGO; - dev_attr->store = NULL; - } - } - /* setting should not be allowed from VF if not in one VF mode */ if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev)) { dev_attr->attr.mode &= ~S_IWUGO; diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h index 3047ffe7f244..621200e0823f 100644 --- a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h +++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h @@ -450,6 +450,7 @@ int amdgpu_pm_load_smu_firmware(struct amdgpu_device *adev, uint32_t *smu_versio int amdgpu_dpm_handle_passthrough_sbr(struct amdgpu_device *adev, bool enable); int amdgpu_dpm_send_hbm_bad_pages_num(struct amdgpu_device *adev, uint32_t size); int amdgpu_dpm_send_hbm_bad_channel_flag(struct amdgpu_device *adev, uint32_t size); +int amdgpu_dpm_send_rma_reason(struct amdgpu_device *adev); int amdgpu_dpm_get_dpm_freq_range(struct amdgpu_device *adev, enum pp_clock_type type, uint32_t *min, diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomctrl.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomctrl.c index f503e61faa60..b1b4c09c3467 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomctrl.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomctrl.c @@ -226,7 +226,7 @@ int atomctrl_set_engine_dram_timings_rv770( return amdgpu_atom_execute_table(adev->mode_info.atom_context, GetIndexIntoMasterTable(COMMAND, DynamicMemorySettings), - (uint32_t *)&engine_clock_parameters); + (uint32_t *)&engine_clock_parameters, sizeof(engine_clock_parameters)); } /* @@ -297,7 +297,7 @@ int atomctrl_get_memory_pll_dividers_si( result = amdgpu_atom_execute_table(adev->mode_info.atom_context, GetIndexIntoMasterTable(COMMAND, ComputeMemoryClockParam), - (uint32_t *)&mpll_parameters); + (uint32_t *)&mpll_parameters, sizeof(mpll_parameters)); if (0 == result) { mpll_param->mpll_fb_divider.clk_frac = @@ -345,7 +345,7 @@ int atomctrl_get_memory_pll_dividers_vi(struct pp_hwmgr *hwmgr, result = amdgpu_atom_execute_table(adev->mode_info.atom_context, GetIndexIntoMasterTable(COMMAND, ComputeMemoryClockParam), - (uint32_t *)&mpll_parameters); + (uint32_t *)&mpll_parameters, sizeof(mpll_parameters)); if (!result) mpll_param->mpll_post_divider = @@ -366,7 +366,7 @@ int atomctrl_get_memory_pll_dividers_ai(struct pp_hwmgr *hwmgr, result = amdgpu_atom_execute_table(adev->mode_info.atom_context, GetIndexIntoMasterTable(COMMAND, ComputeMemoryClockParam), - (uint32_t *)&mpll_parameters); + (uint32_t *)&mpll_parameters, sizeof(mpll_parameters)); /* VEGAM's mpll takes sometime to finish computing */ udelay(10); @@ -396,7 +396,7 @@ int atomctrl_get_engine_pll_dividers_kong(struct pp_hwmgr *hwmgr, result = amdgpu_atom_execute_table(adev->mode_info.atom_context, GetIndexIntoMasterTable(COMMAND, ComputeMemoryEnginePLL), - (uint32_t *)&pll_parameters); + (uint32_t *)&pll_parameters, sizeof(pll_parameters)); if (0 == result) { dividers->pll_post_divider = pll_parameters.ucPostDiv; @@ -420,7 +420,7 @@ int atomctrl_get_engine_pll_dividers_vi( result = amdgpu_atom_execute_table(adev->mode_info.atom_context, GetIndexIntoMasterTable(COMMAND, ComputeMemoryEnginePLL), - (uint32_t *)&pll_patameters); + (uint32_t *)&pll_patameters, sizeof(pll_patameters)); if (0 == result) { dividers->pll_post_divider = @@ -457,7 +457,7 @@ int atomctrl_get_engine_pll_dividers_ai(struct pp_hwmgr *hwmgr, result = amdgpu_atom_execute_table(adev->mode_info.atom_context, GetIndexIntoMasterTable(COMMAND, ComputeMemoryEnginePLL), - (uint32_t *)&pll_patameters); + (uint32_t *)&pll_patameters, sizeof(pll_patameters)); if (0 == result) { dividers->usSclk_fcw_frac = le16_to_cpu(pll_patameters.usSclk_fcw_frac); @@ -490,7 +490,7 @@ int atomctrl_get_dfs_pll_dividers_vi( result = amdgpu_atom_execute_table(adev->mode_info.atom_context, GetIndexIntoMasterTable(COMMAND, ComputeMemoryEnginePLL), - (uint32_t *)&pll_patameters); + (uint32_t *)&pll_patameters, sizeof(pll_patameters)); if (0 == result) { dividers->pll_post_divider = @@ -773,7 +773,7 @@ int atomctrl_calculate_voltage_evv_on_sclk( result = amdgpu_atom_execute_table(adev->mode_info.atom_context, GetIndexIntoMasterTable(COMMAND, ReadEfuseValue), - (uint32_t *)&sOutput_FuseValues); + (uint32_t *)&sOutput_FuseValues, sizeof(sOutput_FuseValues)); if (result) return result; @@ -794,7 +794,7 @@ int atomctrl_calculate_voltage_evv_on_sclk( result = amdgpu_atom_execute_table(adev->mode_info.atom_context, GetIndexIntoMasterTable(COMMAND, ReadEfuseValue), - (uint32_t *)&sOutput_FuseValues); + (uint32_t *)&sOutput_FuseValues, sizeof(sOutput_FuseValues)); if (result) return result; @@ -814,7 +814,7 @@ int atomctrl_calculate_voltage_evv_on_sclk( result = amdgpu_atom_execute_table(adev->mode_info.atom_context, GetIndexIntoMasterTable(COMMAND, ReadEfuseValue), - (uint32_t *)&sOutput_FuseValues); + (uint32_t *)&sOutput_FuseValues, sizeof(sOutput_FuseValues)); if (result) return result; @@ -835,7 +835,7 @@ int atomctrl_calculate_voltage_evv_on_sclk( result = amdgpu_atom_execute_table(adev->mode_info.atom_context, GetIndexIntoMasterTable(COMMAND, ReadEfuseValue), - (uint32_t *)&sOutput_FuseValues); + (uint32_t *)&sOutput_FuseValues, sizeof(sOutput_FuseValues)); if (result) return result; @@ -857,7 +857,7 @@ int atomctrl_calculate_voltage_evv_on_sclk( result = amdgpu_atom_execute_table(adev->mode_info.atom_context, GetIndexIntoMasterTable(COMMAND, ReadEfuseValue), - (uint32_t *)&sOutput_FuseValues); + (uint32_t *)&sOutput_FuseValues, sizeof(sOutput_FuseValues)); if (result) return result; @@ -878,7 +878,7 @@ int atomctrl_calculate_voltage_evv_on_sclk( result = amdgpu_atom_execute_table(adev->mode_info.atom_context, GetIndexIntoMasterTable(COMMAND, ReadEfuseValue), - (uint32_t *)&sOutput_FuseValues); + (uint32_t *)&sOutput_FuseValues, sizeof(sOutput_FuseValues)); if (result) return result; @@ -909,7 +909,7 @@ int atomctrl_calculate_voltage_evv_on_sclk( result = amdgpu_atom_execute_table(adev->mode_info.atom_context, GetIndexIntoMasterTable(COMMAND, ReadEfuseValue), - (uint32_t *)&sOutput_FuseValues); + (uint32_t *)&sOutput_FuseValues, sizeof(sOutput_FuseValues)); if (result) return result; @@ -1134,7 +1134,7 @@ int atomctrl_get_voltage_evv_on_sclk( result = amdgpu_atom_execute_table(adev->mode_info.atom_context, GetIndexIntoMasterTable(COMMAND, GetVoltageInfo), - (uint32_t *)&get_voltage_info_param_space); + (uint32_t *)&get_voltage_info_param_space, sizeof(get_voltage_info_param_space)); *voltage = result ? 0 : le16_to_cpu(((GET_EVV_VOLTAGE_INFO_OUTPUT_PARAMETER_V1_2 *) @@ -1179,7 +1179,7 @@ int atomctrl_get_voltage_evv(struct pp_hwmgr *hwmgr, result = amdgpu_atom_execute_table(adev->mode_info.atom_context, GetIndexIntoMasterTable(COMMAND, GetVoltageInfo), - (uint32_t *)&get_voltage_info_param_space); + (uint32_t *)&get_voltage_info_param_space, sizeof(get_voltage_info_param_space)); if (0 != result) return result; @@ -1359,7 +1359,7 @@ int atomctrl_read_efuse(struct pp_hwmgr *hwmgr, uint16_t start_index, result = amdgpu_atom_execute_table(adev->mode_info.atom_context, GetIndexIntoMasterTable(COMMAND, ReadEfuseValue), - (uint32_t *)&efuse_param); + (uint32_t *)&efuse_param, sizeof(efuse_param)); *efuse = result ? 0 : le32_to_cpu(efuse_param.ulEfuseValue) & mask; return result; @@ -1380,7 +1380,7 @@ int atomctrl_set_ac_timing_ai(struct pp_hwmgr *hwmgr, uint32_t memory_clock, result = amdgpu_atom_execute_table(adev->mode_info.atom_context, GetIndexIntoMasterTable(COMMAND, DynamicMemorySettings), - (uint32_t *)&memory_clock_parameters); + (uint32_t *)&memory_clock_parameters, sizeof(memory_clock_parameters)); return result; } @@ -1399,7 +1399,7 @@ int atomctrl_get_voltage_evv_on_sclk_ai(struct pp_hwmgr *hwmgr, uint8_t voltage_ result = amdgpu_atom_execute_table(adev->mode_info.atom_context, GetIndexIntoMasterTable(COMMAND, GetVoltageInfo), - (uint32_t *)&get_voltage_info_param_space); + (uint32_t *)&get_voltage_info_param_space, sizeof(get_voltage_info_param_space)); *voltage = result ? 0 : le32_to_cpu(((GET_EVV_VOLTAGE_INFO_OUTPUT_PARAMETER_V1_3 *)(&get_voltage_info_param_space))->ulVoltageLevel); @@ -1526,7 +1526,7 @@ int atomctrl_get_leakage_id_from_efuse(struct pp_hwmgr *hwmgr, uint16_t *virtual result = amdgpu_atom_execute_table(adev->mode_info.atom_context, GetIndexIntoMasterTable(COMMAND, SetVoltage), - (uint32_t *)voltage_parameters); + (uint32_t *)voltage_parameters, sizeof(*voltage_parameters)); *virtual_voltage_id = voltage_parameters->usVoltageLevel; diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomfwctrl.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomfwctrl.c index a47a47238e2b..82d540334318 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomfwctrl.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomfwctrl.c @@ -258,7 +258,7 @@ int pp_atomfwctrl_get_gpu_pll_dividers_vega10(struct pp_hwmgr *hwmgr, idx = GetIndexIntoMasterCmdTable(computegpuclockparam); if (amdgpu_atom_execute_table( - adev->mode_info.atom_context, idx, (uint32_t *)&pll_parameters)) + adev->mode_info.atom_context, idx, (uint32_t *)&pll_parameters, sizeof(pll_parameters))) return -EINVAL; pll_output = (struct compute_gpu_clock_output_parameter_v1_8 *) @@ -505,7 +505,7 @@ int pp_atomfwctrl_get_clk_information_by_clkid(struct pp_hwmgr *hwmgr, ix = GetIndexIntoMasterCmdTable(getsmuclockinfo); if (amdgpu_atom_execute_table( - adev->mode_info.atom_context, ix, (uint32_t *)¶meters)) + adev->mode_info.atom_context, ix, (uint32_t *)¶meters, sizeof(parameters))) return -EINVAL; output = (struct atom_get_smu_clock_info_output_parameters_v3_1 *)¶meters; diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index 0ad947df777a..246b211b1e85 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -712,6 +712,7 @@ static int smu_set_funcs(struct amdgpu_device *adev) smu_v13_0_7_set_ppt_funcs(smu); break; case IP_VERSION(14, 0, 0): + case IP_VERSION(14, 0, 1): smu_v14_0_0_set_ppt_funcs(smu); break; default: @@ -751,6 +752,7 @@ static int smu_early_init(void *handle) static int smu_set_default_dpm_table(struct smu_context *smu) { + struct amdgpu_device *adev = smu->adev; struct smu_power_context *smu_power = &smu->smu_power; struct smu_power_gate *power_gate = &smu_power->power_gate; int vcn_gate, jpeg_gate; @@ -759,25 +761,34 @@ static int smu_set_default_dpm_table(struct smu_context *smu) if (!smu->ppt_funcs->set_default_dpm_table) return 0; - vcn_gate = atomic_read(&power_gate->vcn_gated); - jpeg_gate = atomic_read(&power_gate->jpeg_gated); + if (adev->pg_flags & AMD_PG_SUPPORT_VCN) + vcn_gate = atomic_read(&power_gate->vcn_gated); + if (adev->pg_flags & AMD_PG_SUPPORT_JPEG) + jpeg_gate = atomic_read(&power_gate->jpeg_gated); - ret = smu_dpm_set_vcn_enable(smu, true); - if (ret) - return ret; + if (adev->pg_flags & AMD_PG_SUPPORT_VCN) { + ret = smu_dpm_set_vcn_enable(smu, true); + if (ret) + return ret; + } - ret = smu_dpm_set_jpeg_enable(smu, true); - if (ret) - goto err_out; + if (adev->pg_flags & AMD_PG_SUPPORT_JPEG) { + ret = smu_dpm_set_jpeg_enable(smu, true); + if (ret) + goto err_out; + } ret = smu->ppt_funcs->set_default_dpm_table(smu); if (ret) dev_err(smu->adev->dev, "Failed to setup default dpm clock tables!\n"); - smu_dpm_set_jpeg_enable(smu, !jpeg_gate); + if (adev->pg_flags & AMD_PG_SUPPORT_JPEG) + smu_dpm_set_jpeg_enable(smu, !jpeg_gate); err_out: - smu_dpm_set_vcn_enable(smu, !vcn_gate); + if (adev->pg_flags & AMD_PG_SUPPORT_VCN) + smu_dpm_set_vcn_enable(smu, !vcn_gate); + return ret; } @@ -1885,6 +1896,7 @@ static int smu_disable_dpms(struct smu_context *smu) case IP_VERSION(13, 0, 4): case IP_VERSION(13, 0, 11): case IP_VERSION(14, 0, 0): + case IP_VERSION(14, 0, 1): return 0; default: break; @@ -3669,3 +3681,13 @@ int smu_send_hbm_bad_channel_flag(struct smu_context *smu, uint32_t size) return ret; } + +int smu_send_rma_reason(struct smu_context *smu) +{ + int ret = 0; + + if (smu->ppt_funcs && smu->ppt_funcs->send_rma_reason) + ret = smu->ppt_funcs->send_rma_reason(smu); + + return ret; +} diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h index 66e84defd0b6..a870bdd49a4e 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h @@ -1342,6 +1342,11 @@ struct pptable_funcs { int (*send_hbm_bad_pages_num)(struct smu_context *smu, uint32_t size); /** + * @send_rma_reason: message rma reason event to SMU. + */ + int (*send_rma_reason)(struct smu_context *smu); + + /** * @get_ecc_table: message SMU to get ECC INFO table. */ ssize_t (*get_ecc_info)(struct smu_context *smu, void *table); @@ -1588,5 +1593,6 @@ int smu_stb_collect_info(struct smu_context *smu, void *buff, uint32_t size); void amdgpu_smu_stb_debug_fs_init(struct amdgpu_device *adev); int smu_send_hbm_bad_pages_num(struct smu_context *smu, uint32_t size); int smu_send_hbm_bad_channel_flag(struct smu_context *smu, uint32_t size); +int smu_send_rma_reason(struct smu_context *smu); #endif #endif diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_ppsmc.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_ppsmc.h index 509e3cd483fb..86758051cb93 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_ppsmc.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_ppsmc.h @@ -91,7 +91,8 @@ #define PPSMC_MSG_QueryValidMcaCeCount 0x3A #define PPSMC_MSG_McaBankCeDumpDW 0x3B #define PPSMC_MSG_SelectPLPDMode 0x40 -#define PPSMC_Message_Count 0x41 +#define PPSMC_MSG_RmaDueToBadPageThreshold 0x43 +#define PPSMC_Message_Count 0x44 //PPSMC Reset Types for driver msg argument #define PPSMC_RESET_TYPE_DRIVER_MODE_1_RESET 0x1 diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h index 953a767613b1..a941fdbf78b6 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h @@ -261,7 +261,8 @@ __SMU_DUMMY_MAP(SetSoftMaxVpe), \ __SMU_DUMMY_MAP(SetSoftMinVpe), \ __SMU_DUMMY_MAP(GetMetricsVersion), \ - __SMU_DUMMY_MAP(EnableUCLKShadow), + __SMU_DUMMY_MAP(EnableUCLKShadow), \ + __SMU_DUMMY_MAP(RmaDueToBadPageThreshold), #undef __SMU_DUMMY_MAP #define __SMU_DUMMY_MAP(type) SMU_MSG_##type diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c index bcad42534da4..1d96eb274d72 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c @@ -2272,8 +2272,8 @@ static uint16_t arcturus_get_current_pcie_link_speed(struct smu_context *smu) /* TODO: confirm this on real target */ esm_ctrl = RREG32_PCIE(smnPCIE_ESM_CTRL); - if ((esm_ctrl >> 15) & 0x1FFFF) - return (uint16_t)(((esm_ctrl >> 8) & 0x3F) + 128); + if ((esm_ctrl >> 15) & 0x1) + return (uint16_t)(((esm_ctrl >> 8) & 0x7F) + 128); return smu_v11_0_get_current_pcie_link_speed(smu); } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c index c7bfa68bf00f..f6545093bfc1 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c @@ -514,7 +514,7 @@ static int smu_v11_0_atom_get_smu_clockinfo(struct amdgpu_device *adev, getsmuclockinfo); ret = amdgpu_atom_execute_table(adev->mode_info.atom_context, index, - (uint32_t *)&input); + (uint32_t *)&input, sizeof(input)); if (ret) return -EINVAL; @@ -1432,24 +1432,24 @@ static int smu_v11_0_irq_process(struct amdgpu_device *adev, dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU HW CTF!\n"); orderly_poweroff(true); } else if (client_id == SOC15_IH_CLIENTID_MP1) { - if (src_id == 0xfe) { + if (src_id == SMU_IH_INTERRUPT_ID_TO_DRIVER) { /* ACK SMUToHost interrupt */ data = RREG32_SOC15(MP1, 0, mmMP1_SMN_IH_SW_INT_CTRL); data = REG_SET_FIELD(data, MP1_SMN_IH_SW_INT_CTRL, INT_ACK, 1); WREG32_SOC15(MP1, 0, mmMP1_SMN_IH_SW_INT_CTRL, data); switch (ctxid) { - case 0x3: + case SMU_IH_INTERRUPT_CONTEXT_ID_AC: dev_dbg(adev->dev, "Switched to AC mode!\n"); schedule_work(&smu->interrupt_work); adev->pm.ac_power = true; break; - case 0x4: + case SMU_IH_INTERRUPT_CONTEXT_ID_DC: dev_dbg(adev->dev, "Switched to DC mode!\n"); schedule_work(&smu->interrupt_work); adev->pm.ac_power = false; break; - case 0x7: + case SMU_IH_INTERRUPT_CONTEXT_ID_THERMAL_THROTTLING: /* * Increment the throttle interrupt counter */ @@ -1462,6 +1462,10 @@ static int smu_v11_0_irq_process(struct amdgpu_device *adev, schedule_work(&smu->throttling_logging_work); break; + default: + dev_dbg(adev->dev, "Unhandled context id %d from client:%d!\n", + ctxid, client_id); + break; } } } @@ -1504,7 +1508,7 @@ int smu_v11_0_register_irq_handler(struct smu_context *smu) return ret; ret = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_MP1, - 0xfe, + SMU_IH_INTERRUPT_ID_TO_DRIVER, irq_src); if (ret) return ret; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c index 5e408a195860..ed15f5a0fd11 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c @@ -301,7 +301,7 @@ static int smu_v12_0_atom_get_smu_clockinfo(struct amdgpu_device *adev, getsmuclockinfo); ret = amdgpu_atom_execute_table(adev->mode_info.atom_context, index, - (uint32_t *)&input); + (uint32_t *)&input, sizeof(input)); if (ret) return -EINVAL; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c index dd9bcbd630a1..f41ac6465f2a 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c @@ -1682,8 +1682,8 @@ static int aldebaran_get_current_pcie_link_speed(struct smu_context *smu) /* TODO: confirm this on real target */ esm_ctrl = RREG32_PCIE(smnPCIE_ESM_CTRL); - if ((esm_ctrl >> 15) & 0x1FFFF) - return (((esm_ctrl >> 8) & 0x3F) + 128); + if ((esm_ctrl >> 15) & 0x1) + return (((esm_ctrl >> 8) & 0x7F) + 128); return smu_v13_0_get_current_pcie_link_speed(smu); } @@ -1746,10 +1746,12 @@ static ssize_t aldebaran_get_gpu_metrics(struct smu_context *smu, gpu_metrics->current_fan_speed = 0; - gpu_metrics->pcie_link_width = - smu_v13_0_get_current_pcie_link_width(smu); - gpu_metrics->pcie_link_speed = - aldebaran_get_current_pcie_link_speed(smu); + if (!amdgpu_sriov_vf(smu->adev)) { + gpu_metrics->pcie_link_width = + smu_v13_0_get_current_pcie_link_width(smu); + gpu_metrics->pcie_link_speed = + aldebaran_get_current_pcie_link_speed(smu); + } gpu_metrics->system_clock_counter = ktime_get_boottime_ns(); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c index c486182ff275..48170bb5112e 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c @@ -1369,24 +1369,24 @@ static int smu_v13_0_irq_process(struct amdgpu_device *adev, dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU HW CTF!\n"); orderly_poweroff(true); } else if (client_id == SOC15_IH_CLIENTID_MP1) { - if (src_id == 0xfe) { + if (src_id == SMU_IH_INTERRUPT_ID_TO_DRIVER) { /* ACK SMUToHost interrupt */ data = RREG32_SOC15(MP1, 0, regMP1_SMN_IH_SW_INT_CTRL); data = REG_SET_FIELD(data, MP1_SMN_IH_SW_INT_CTRL, INT_ACK, 1); WREG32_SOC15(MP1, 0, regMP1_SMN_IH_SW_INT_CTRL, data); switch (ctxid) { - case 0x3: + case SMU_IH_INTERRUPT_CONTEXT_ID_AC: dev_dbg(adev->dev, "Switched to AC mode!\n"); smu_v13_0_ack_ac_dc_interrupt(smu); adev->pm.ac_power = true; break; - case 0x4: + case SMU_IH_INTERRUPT_CONTEXT_ID_DC: dev_dbg(adev->dev, "Switched to DC mode!\n"); smu_v13_0_ack_ac_dc_interrupt(smu); adev->pm.ac_power = false; break; - case 0x7: + case SMU_IH_INTERRUPT_CONTEXT_ID_THERMAL_THROTTLING: /* * Increment the throttle interrupt counter */ @@ -1399,7 +1399,7 @@ static int smu_v13_0_irq_process(struct amdgpu_device *adev, schedule_work(&smu->throttling_logging_work); break; - case 0x8: + case SMU_IH_INTERRUPT_CONTEXT_ID_FAN_ABNORMAL: high = smu->thermal_range.software_shutdown_temp + smu->thermal_range.software_shutdown_temp_offset; high = min_t(typeof(high), @@ -1416,7 +1416,7 @@ static int smu_v13_0_irq_process(struct amdgpu_device *adev, data = data & (~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK); WREG32_SOC15(THM, 0, regTHM_THERMAL_INT_CTRL, data); break; - case 0x9: + case SMU_IH_INTERRUPT_CONTEXT_ID_FAN_RECOVERY: high = min_t(typeof(high), SMU_THERMAL_MAXIMUM_ALERT_TEMP, smu->thermal_range.software_shutdown_temp); @@ -1429,6 +1429,10 @@ static int smu_v13_0_irq_process(struct amdgpu_device *adev, data = data & (~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK); WREG32_SOC15(THM, 0, regTHM_THERMAL_INT_CTRL, data); break; + default: + dev_dbg(adev->dev, "Unhandled context id %d from client:%d!\n", + ctxid, client_id); + break; } } } @@ -1473,7 +1477,7 @@ int smu_v13_0_register_irq_handler(struct smu_context *smu) return ret; ret = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_MP1, - 0xfe, + SMU_IH_INTERRUPT_ID_TO_DRIVER, irq_src); if (ret) return ret; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c index 7e1941cf1796..3957af057d54 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c @@ -45,6 +45,7 @@ #include <linux/pci.h> #include "amdgpu_ras.h" #include "amdgpu_mca.h" +#include "amdgpu_aca.h" #include "smu_cmn.h" #include "mp/mp_13_0_6_offset.h" #include "mp/mp_13_0_6_sh_mask.h" @@ -171,6 +172,7 @@ static const struct cmn2asic_msg_mapping smu_v13_0_6_message_map[SMU_MSG_MAX_COU MSG_MAP(McaBankDumpDW, PPSMC_MSG_McaBankDumpDW, 0), MSG_MAP(McaBankCeDumpDW, PPSMC_MSG_McaBankCeDumpDW, 0), MSG_MAP(SelectPLPDMode, PPSMC_MSG_SelectPLPDMode, 0), + MSG_MAP(RmaDueToBadPageThreshold, PPSMC_MSG_RmaDueToBadPageThreshold, 0), }; // clang-format on @@ -1438,7 +1440,10 @@ static int smu_v13_0_6_irq_process(struct amdgpu_device *adev, entry->src_data[1]); schedule_work(&smu->throttling_logging_work); } - + break; + default: + dev_dbg(adev->dev, "Unhandled context id %d from client:%d!\n", + ctxid, client_id); break; } } @@ -1574,6 +1579,8 @@ static int smu_v13_0_6_set_performance_level(struct smu_context *smu, struct smu_13_0_dpm_context *dpm_context = smu_dpm->dpm_context; struct smu_13_0_dpm_table *gfx_table = &dpm_context->dpm_tables.gfx_table; + struct smu_13_0_dpm_table *uclk_table = + &dpm_context->dpm_tables.uclk_table; struct smu_umd_pstate_table *pstate_table = &smu->pstate_table; int ret; @@ -1589,17 +1596,27 @@ static int smu_v13_0_6_set_performance_level(struct smu_context *smu, return 0; case AMD_DPM_FORCED_LEVEL_AUTO: - if ((gfx_table->min == pstate_table->gfxclk_pstate.curr.min) && - (gfx_table->max == pstate_table->gfxclk_pstate.curr.max)) - return 0; + if ((gfx_table->min != pstate_table->gfxclk_pstate.curr.min) || + (gfx_table->max != pstate_table->gfxclk_pstate.curr.max)) { + ret = smu_v13_0_6_set_gfx_soft_freq_limited_range( + smu, gfx_table->min, gfx_table->max); + if (ret) + return ret; - ret = smu_v13_0_6_set_gfx_soft_freq_limited_range( - smu, gfx_table->min, gfx_table->max); - if (ret) - return ret; + pstate_table->gfxclk_pstate.curr.min = gfx_table->min; + pstate_table->gfxclk_pstate.curr.max = gfx_table->max; + } + + if (uclk_table->max != pstate_table->uclk_pstate.curr.max) { + /* Min UCLK is not expected to be changed */ + ret = smu_v13_0_set_soft_freq_limited_range( + smu, SMU_UCLK, 0, uclk_table->max); + if (ret) + return ret; + pstate_table->uclk_pstate.curr.max = uclk_table->max; + } + pstate_table->uclk_pstate.custom.max = 0; - pstate_table->gfxclk_pstate.curr.min = gfx_table->min; - pstate_table->gfxclk_pstate.curr.max = gfx_table->max; return 0; case AMD_DPM_FORCED_LEVEL_MANUAL: return 0; @@ -1622,7 +1639,8 @@ static int smu_v13_0_6_set_soft_freq_limited_range(struct smu_context *smu, uint32_t max_clk; int ret = 0; - if (clk_type != SMU_GFXCLK && clk_type != SMU_SCLK) + if (clk_type != SMU_GFXCLK && clk_type != SMU_SCLK && + clk_type != SMU_UCLK) return -EINVAL; if ((smu_dpm->dpm_level != AMD_DPM_FORCED_LEVEL_MANUAL) && @@ -1632,18 +1650,31 @@ static int smu_v13_0_6_set_soft_freq_limited_range(struct smu_context *smu, if (smu_dpm->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) { if (min >= max) { dev_err(smu->adev->dev, - "Minimum GFX clk should be less than the maximum allowed clock\n"); + "Minimum clk should be less than the maximum allowed clock\n"); return -EINVAL; } - if ((min == pstate_table->gfxclk_pstate.curr.min) && - (max == pstate_table->gfxclk_pstate.curr.max)) - return 0; + if (clk_type == SMU_GFXCLK) { + if ((min == pstate_table->gfxclk_pstate.curr.min) && + (max == pstate_table->gfxclk_pstate.curr.max)) + return 0; - ret = smu_v13_0_6_set_gfx_soft_freq_limited_range(smu, min, max); - if (!ret) { - pstate_table->gfxclk_pstate.curr.min = min; - pstate_table->gfxclk_pstate.curr.max = max; + ret = smu_v13_0_6_set_gfx_soft_freq_limited_range( + smu, min, max); + if (!ret) { + pstate_table->gfxclk_pstate.curr.min = min; + pstate_table->gfxclk_pstate.curr.max = max; + } + } + + if (clk_type == SMU_UCLK) { + if (max == pstate_table->uclk_pstate.curr.max) + return 0; + /* Only max clock limiting is allowed for UCLK */ + ret = smu_v13_0_set_soft_freq_limited_range( + smu, SMU_UCLK, 0, max); + if (!ret) + pstate_table->uclk_pstate.curr.max = max; } return ret; @@ -1736,6 +1767,40 @@ static int smu_v13_0_6_usr_edit_dpm_table(struct smu_context *smu, return -EINVAL; } break; + case PP_OD_EDIT_MCLK_VDDC_TABLE: + if (size != 2) { + dev_err(smu->adev->dev, + "Input parameter number not correct\n"); + return -EINVAL; + } + + if (!smu_cmn_feature_is_enabled(smu, + SMU_FEATURE_DPM_UCLK_BIT)) { + dev_warn(smu->adev->dev, + "UCLK_LIMITS setting not supported!\n"); + return -EOPNOTSUPP; + } + + if (input[0] == 0) { + dev_info(smu->adev->dev, + "Setting min UCLK level is not supported"); + return -EINVAL; + } else if (input[0] == 1) { + if (input[1] > dpm_context->dpm_tables.uclk_table.max) { + dev_warn( + smu->adev->dev, + "Maximum UCLK (%ld) MHz specified is greater than the maximum allowed (%d) MHz\n", + input[1], + dpm_context->dpm_tables.uclk_table.max); + pstate_table->uclk_pstate.custom.max = + pstate_table->uclk_pstate.curr.max; + return -EINVAL; + } + + pstate_table->uclk_pstate.custom.max = input[1]; + } + break; + case PP_OD_RESTORE_DEFAULT_TABLE: if (size != 0) { dev_err(smu->adev->dev, @@ -1746,8 +1811,19 @@ static int smu_v13_0_6_usr_edit_dpm_table(struct smu_context *smu, min_clk = dpm_context->dpm_tables.gfx_table.min; max_clk = dpm_context->dpm_tables.gfx_table.max; - return smu_v13_0_6_set_soft_freq_limited_range( + ret = smu_v13_0_6_set_soft_freq_limited_range( smu, SMU_GFXCLK, min_clk, max_clk); + + if (ret) + return ret; + + min_clk = dpm_context->dpm_tables.uclk_table.min; + max_clk = dpm_context->dpm_tables.uclk_table.max; + ret = smu_v13_0_6_set_soft_freq_limited_range( + smu, SMU_UCLK, min_clk, max_clk); + if (ret) + return ret; + pstate_table->uclk_pstate.custom.max = 0; } break; case PP_OD_COMMIT_DPM_TABLE: @@ -1767,8 +1843,19 @@ static int smu_v13_0_6_usr_edit_dpm_table(struct smu_context *smu, min_clk = pstate_table->gfxclk_pstate.custom.min; max_clk = pstate_table->gfxclk_pstate.custom.max; - return smu_v13_0_6_set_soft_freq_limited_range( + ret = smu_v13_0_6_set_soft_freq_limited_range( smu, SMU_GFXCLK, min_clk, max_clk); + + if (ret) + return ret; + + if (!pstate_table->uclk_pstate.custom.max) + return 0; + + min_clk = pstate_table->uclk_pstate.curr.min; + max_clk = pstate_table->uclk_pstate.custom.max; + return smu_v13_0_6_set_soft_freq_limited_range( + smu, SMU_UCLK, min_clk, max_clk); } break; default: @@ -2060,8 +2147,8 @@ static int smu_v13_0_6_get_current_pcie_link_speed(struct smu_context *smu) /* TODO: confirm this on real target */ esm_ctrl = RREG32_PCIE(smnPCIE_ESM_CTRL); - if ((esm_ctrl >> 15) & 0x1FFFF) - return (((esm_ctrl >> 8) & 0x3F) + 128); + if ((esm_ctrl >> 15) & 0x1) + return (((esm_ctrl >> 8) & 0x7F) + 128); speed_level = (RREG32_PCIE(smnPCIE_LC_SPEED_CNTL) & PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE_MASK) @@ -2141,14 +2228,16 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table gpu_metrics->gfxclk_lock_status = GET_METRIC_FIELD(GfxLockXCDMak) >> GET_INST(GC, 0); if (!(adev->flags & AMD_IS_APU)) { - link_width_level = smu_v13_0_6_get_current_pcie_link_width_level(smu); - if (link_width_level > MAX_LINK_WIDTH) - link_width_level = 0; - - gpu_metrics->pcie_link_width = - DECODE_LANE_WIDTH(link_width_level); - gpu_metrics->pcie_link_speed = - smu_v13_0_6_get_current_pcie_link_speed(smu); + if (!amdgpu_sriov_vf(adev)) { + link_width_level = smu_v13_0_6_get_current_pcie_link_width_level(smu); + if (link_width_level > MAX_LINK_WIDTH) + link_width_level = 0; + + gpu_metrics->pcie_link_width = + DECODE_LANE_WIDTH(link_width_level); + gpu_metrics->pcie_link_speed = + smu_v13_0_6_get_current_pcie_link_speed(smu); + } gpu_metrics->pcie_bandwidth_acc = SMUQ10_ROUND(metrics_x->PcieBandwidthAcc[0]); gpu_metrics->pcie_bandwidth_inst = @@ -2219,8 +2308,8 @@ static int smu_v13_0_6_mode2_reset(struct smu_context *smu) ret = smu_cmn_send_msg_without_waiting(smu, (uint16_t)index, SMU_RESET_MODE_2); - /* This is similar to FLR, wait till max FLR timeout */ - msleep(100); + /* Reset takes a bit longer, wait for 200ms. */ + msleep(200); dev_dbg(smu->adev->dev, "restore config space...\n"); /* Restore the config space saved during init */ @@ -2376,6 +2465,24 @@ static int smu_v13_0_6_smu_send_hbm_bad_page_num(struct smu_context *smu, return ret; } +static int smu_v13_0_6_send_rma_reason(struct smu_context *smu) +{ + struct amdgpu_device *adev = smu->adev; + int ret; + + /* NOTE: the message is only valid on dGPU with pmfw 85.90.0 and above */ + if ((adev->flags & AMD_IS_APU) || smu->smc_fw_version < 0x00555a00) + return 0; + + ret = smu_cmn_send_smc_msg(smu, SMU_MSG_RmaDueToBadPageThreshold, NULL); + if (ret) + dev_err(smu->adev->dev, + "[%s] failed to send BadPageThreshold event to SMU\n", + __func__); + + return ret; +} + static int mca_smu_set_debug_mode(struct amdgpu_device *adev, bool enable) { struct smu_context *smu = adev->powerplay.pp_handle; @@ -2547,18 +2654,22 @@ static int mca_umc_mca_get_err_count(const struct mca_ras_info *mca_ras, struct enum amdgpu_mca_error_type type, struct mca_bank_entry *entry, uint32_t *count) { uint64_t status0; + uint32_t ext_error_code; + uint32_t odecc_err_cnt; status0 = entry->regs[MCA_REG_IDX_STATUS]; + ext_error_code = MCA_REG__STATUS__ERRORCODEEXT(status0); + odecc_err_cnt = MCA_REG__MISC0__ERRCNT(entry->regs[MCA_REG_IDX_MISC0]); if (!REG_GET_FIELD(status0, MCMP1_STATUST0, Val)) { *count = 0; return 0; } - if (type == AMDGPU_MCA_ERROR_TYPE_UE && umc_v12_0_is_uncorrectable_error(adev, status0)) - *count = 1; - else if (type == AMDGPU_MCA_ERROR_TYPE_CE && umc_v12_0_is_correctable_error(adev, status0)) - *count = 1; + if (umc_v12_0_is_deferred_error(adev, status0) || + umc_v12_0_is_uncorrectable_error(adev, status0) || + umc_v12_0_is_correctable_error(adev, status0)) + *count = (ext_error_code == 0) ? odecc_err_cnt : 1; return 0; } @@ -2857,6 +2968,143 @@ static const struct amdgpu_mca_smu_funcs smu_v13_0_6_mca_smu_funcs = { .mca_get_valid_mca_count = mca_smu_get_valid_mca_count, }; +static int aca_smu_set_debug_mode(struct amdgpu_device *adev, bool enable) +{ + struct smu_context *smu = adev->powerplay.pp_handle; + + return smu_v13_0_6_mca_set_debug_mode(smu, enable); +} + +static int smu_v13_0_6_get_valid_aca_count(struct smu_context *smu, enum aca_error_type type, u32 *count) +{ + uint32_t msg; + int ret; + + if (!count) + return -EINVAL; + + switch (type) { + case ACA_ERROR_TYPE_UE: + msg = SMU_MSG_QueryValidMcaCount; + break; + case ACA_ERROR_TYPE_CE: + msg = SMU_MSG_QueryValidMcaCeCount; + break; + default: + return -EINVAL; + } + + ret = smu_cmn_send_smc_msg(smu, msg, count); + if (ret) { + *count = 0; + return ret; + } + + return 0; +} + +static int aca_smu_get_valid_aca_count(struct amdgpu_device *adev, + enum aca_error_type type, u32 *count) +{ + struct smu_context *smu = adev->powerplay.pp_handle; + int ret; + + switch (type) { + case ACA_ERROR_TYPE_UE: + case ACA_ERROR_TYPE_CE: + ret = smu_v13_0_6_get_valid_aca_count(smu, type, count); + break; + default: + ret = -EINVAL; + break; + } + + return ret; +} + +static int __smu_v13_0_6_aca_bank_dump(struct smu_context *smu, enum aca_error_type type, + int idx, int offset, u32 *val) +{ + uint32_t msg, param; + + switch (type) { + case ACA_ERROR_TYPE_UE: + msg = SMU_MSG_McaBankDumpDW; + break; + case ACA_ERROR_TYPE_CE: + msg = SMU_MSG_McaBankCeDumpDW; + break; + default: + return -EINVAL; + } + + param = ((idx & 0xffff) << 16) | (offset & 0xfffc); + + return smu_cmn_send_smc_msg_with_param(smu, msg, param, (uint32_t *)val); +} + +static int smu_v13_0_6_aca_bank_dump(struct smu_context *smu, enum aca_error_type type, + int idx, int offset, u32 *val, int count) +{ + int ret, i; + + if (!val) + return -EINVAL; + + for (i = 0; i < count; i++) { + ret = __smu_v13_0_6_aca_bank_dump(smu, type, idx, offset + (i << 2), &val[i]); + if (ret) + return ret; + } + + return 0; +} + +static int aca_bank_read_reg(struct amdgpu_device *adev, enum aca_error_type type, + int idx, int reg_idx, u64 *val) +{ + struct smu_context *smu = adev->powerplay.pp_handle; + u32 data[2] = {0, 0}; + int ret; + + if (!val || reg_idx >= ACA_REG_IDX_COUNT) + return -EINVAL; + + ret = smu_v13_0_6_aca_bank_dump(smu, type, idx, reg_idx * 8, data, ARRAY_SIZE(data)); + if (ret) + return ret; + + *val = (u64)data[1] << 32 | data[0]; + + dev_dbg(adev->dev, "mca read bank reg: type:%s, index: %d, reg_idx: %d, val: 0x%016llx\n", + type == ACA_ERROR_TYPE_UE ? "UE" : "CE", idx, reg_idx, *val); + + return 0; +} + +static int aca_smu_get_valid_aca_bank(struct amdgpu_device *adev, + enum aca_error_type type, int idx, struct aca_bank *bank) +{ + int i, ret, count; + + count = min_t(int, 16, ARRAY_SIZE(bank->regs)); + for (i = 0; i < count; i++) { + ret = aca_bank_read_reg(adev, type, idx, i, &bank->regs[i]); + if (ret) + return ret; + } + + return 0; +} + +static const struct aca_smu_funcs smu_v13_0_6_aca_smu_funcs = { + .max_ue_bank_count = 12, + .max_ce_bank_count = 12, + .set_debug_mode = aca_smu_set_debug_mode, + .get_valid_aca_count = aca_smu_get_valid_aca_count, + .get_valid_aca_bank = aca_smu_get_valid_aca_bank, +}; + static int smu_v13_0_6_select_xgmi_plpd_policy(struct smu_context *smu, enum pp_xgmi_plpd_mode mode) { @@ -2895,13 +3143,6 @@ static int smu_v13_0_6_select_xgmi_plpd_policy(struct smu_context *smu, return ret; } -static ssize_t smu_v13_0_6_get_ecc_info(struct smu_context *smu, - void *table) -{ - /* Support ecc info by default */ - return 0; -} - static const struct pptable_funcs smu_v13_0_6_ppt_funcs = { /* init dpm */ .get_allowed_feature_mask = smu_v13_0_6_get_allowed_feature_mask, @@ -2956,7 +3197,7 @@ static const struct pptable_funcs smu_v13_0_6_ppt_funcs = { .i2c_init = smu_v13_0_6_i2c_control_init, .i2c_fini = smu_v13_0_6_i2c_control_fini, .send_hbm_bad_pages_num = smu_v13_0_6_smu_send_hbm_bad_page_num, - .get_ecc_info = smu_v13_0_6_get_ecc_info, + .send_rma_reason = smu_v13_0_6_send_rma_reason, }; void smu_v13_0_6_set_ppt_funcs(struct smu_context *smu) @@ -2969,4 +3210,5 @@ void smu_v13_0_6_set_ppt_funcs(struct smu_context *smu) smu->smc_driver_if_version = SMU13_0_6_DRIVER_IF_VERSION; smu_v13_0_set_smu_mailbox_registers(smu); amdgpu_mca_smu_init_funcs(smu->adev, &smu_v13_0_6_mca_smu_funcs); + amdgpu_aca_set_smu_funcs(smu->adev, &smu_v13_0_6_aca_smu_funcs); } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c index 6dae5ad74ff0..b06a3cc43305 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c @@ -53,6 +53,8 @@ MODULE_FIRMWARE("amdgpu/smu_14_0_2.bin"); +#define ENABLE_IMU_ARG_GFXOFF_ENABLE 1 + int smu_v14_0_init_microcode(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; @@ -231,6 +233,10 @@ int smu_v14_0_check_fw_version(struct smu_context *smu) case IP_VERSION(14, 0, 0): smu->smc_driver_if_version = SMU14_DRIVER_IF_VERSION_SMU_V14_0_0; break; + case IP_VERSION(14, 0, 1): + smu->smc_driver_if_version = SMU14_DRIVER_IF_VERSION_SMU_V14_0_0; + break; + default: dev_err(adev->dev, "smu unsupported IP version: 0x%x.\n", amdgpu_ip_version(adev, MP1_HWIP, 0)); @@ -734,6 +740,7 @@ int smu_v14_0_gfx_off_control(struct smu_context *smu, bool enable) switch (amdgpu_ip_version(adev, MP1_HWIP, 0)) { case IP_VERSION(14, 0, 2): case IP_VERSION(14, 0, 0): + case IP_VERSION(14, 0, 1): if (!(adev->pm.pp_feature & PP_GFXOFF_MASK)) return 0; if (enable) @@ -890,7 +897,7 @@ int smu_v14_0_register_irq_handler(struct smu_context *smu) // TODO: THM related ret = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_MP1, - 0xfe, + SMU_IH_INTERRUPT_ID_TO_DRIVER, irq_src); if (ret) return ret; @@ -1628,11 +1635,16 @@ int smu_v14_0_baco_exit(struct smu_context *smu) int smu_v14_0_set_gfx_power_up_by_imu(struct smu_context *smu) { uint16_t index; + struct amdgpu_device *adev = smu->adev; + + if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { + return smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_EnableGfxImu, + ENABLE_IMU_ARG_GFXOFF_ENABLE, NULL); + } index = smu_cmn_to_asic_specific_index(smu, CMN2ASIC_MAPPING_MSG, SMU_MSG_EnableGfxImu); - /* Param 1 to tell PMFW to enable GFXOFF feature */ - return smu_cmn_send_msg_without_waiting(smu, index, 1); + return smu_cmn_send_msg_without_waiting(smu, index, ENABLE_IMU_ARG_GFXOFF_ENABLE); } int smu_v14_0_set_default_dpm_tables(struct smu_context *smu) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c index 00cd615bbcdc..b8dbd4e25348 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c @@ -378,8 +378,15 @@ int smu_cmn_send_smc_msg_with_param(struct smu_context *smu, res = __smu_cmn_reg2errno(smu, reg); if (res != 0) __smu_cmn_reg_print_error(smu, reg, index, param, msg); - if (read_arg) + if (read_arg) { smu_cmn_read_arg(smu, read_arg); + dev_dbg(adev->dev, "smu send message: %s(%d) param: 0x%08x, resp: 0x%08x,\ + readval: 0x%08x\n", + smu_get_message_name(smu, msg), index, param, reg, *read_arg); + } else { + dev_dbg(adev->dev, "smu send message: %s(%d) param: 0x%08x, resp: 0x%08x\n", + smu_get_message_name(smu, msg), index, param, reg); + } Out: if (unlikely(adev->pm.smu_debug_mask & SMU_DEBUG_HALT_ON_ERROR) && res) { amdgpu_device_halt(adev); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h index cc590e27d88a..81bfce1406e5 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h +++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h @@ -30,6 +30,16 @@ #define FDO_PWM_MODE_STATIC 1 #define FDO_PWM_MODE_STATIC_RPM 5 +#define SMU_IH_INTERRUPT_ID_TO_DRIVER 0xFE +#define SMU_IH_INTERRUPT_CONTEXT_ID_BACO 0x2 +#define SMU_IH_INTERRUPT_CONTEXT_ID_AC 0x3 +#define SMU_IH_INTERRUPT_CONTEXT_ID_DC 0x4 +#define SMU_IH_INTERRUPT_CONTEXT_ID_AUDIO_D0 0x5 +#define SMU_IH_INTERRUPT_CONTEXT_ID_AUDIO_D3 0x6 +#define SMU_IH_INTERRUPT_CONTEXT_ID_THERMAL_THROTTLING 0x7 +#define SMU_IH_INTERRUPT_CONTEXT_ID_FAN_ABNORMAL 0x8 +#define SMU_IH_INTERRUPT_CONTEXT_ID_FAN_RECOVERY 0x9 + extern const int link_speed[]; /* Helper to Convert from PCIE Gen 1/2/3/4/5/6 to 0.1 GT/s speed units */ |