diff options
| author | Dave Airlie <airlied@redhat.com> | 2023-06-15 14:11:22 +1000 |
|---|---|---|
| committer | Dave Airlie <airlied@redhat.com> | 2023-06-15 14:11:22 +1000 |
| commit | 901bdf5ea1a836400ee69aa32b04e9c209271ec7 (patch) | |
| tree | ccb1851c8a71e776dbccf1ccae132dc9b5f093c6 /drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c | |
| parent | ba57b9b11f78530146f02b776854b2b6b6d344a4 (diff) | |
| parent | 3b718dcaf163d17fe907ea098c8449e0cd6bc271 (diff) | |
| download | lwn-901bdf5ea1a836400ee69aa32b04e9c209271ec7.tar.gz lwn-901bdf5ea1a836400ee69aa32b04e9c209271ec7.zip | |
Merge tag 'amd-drm-next-6.5-2023-06-09' of https://gitlab.freedesktop.org/agd5f/linux into drm-next
amd-drm-next-6.5-2023-06-02:
amdgpu:
- SR-IOV fixes
- Warning fixes
- Misc code cleanups and spelling fixes
- DCN 3.2 updates
- Improved DC FAMS support for better power management
- Improved DC SubVP support for better power management
- DCN 3.1.x fixes
- Max IB size query
- DC GPU reset fixes
- RAS updates
- DCN 3.0.x fixes
- S/G display fixes
- CP shadow buffer support
- Implement connector force callback
- Z8 power improvements
- PSP 13.0.10 vbflash support
- Mode2 reset fixes
- Store MQDs in VRAM to improve queue switch latency
- VCN 3.x fixes
- JPEG 3.x fixes
- Enable DC_FP on LoongArch
- GFXOFF fixes
- GC 9.4.3 partition support
- SDMA 4.4.2 partition support
- VCN/JPEG 4.0.3 partition support
- VCN 4.0.3 updates
- NBIO 7.9 updates
- GC 9.4.3 updates
- Take NUMA into account when allocating memory
- Handle NUMA for partitions
- SMU 13.0.6 updates
- GC 9.4.3 RAS updates
- Stop including unused swiotlb.h
- SMU 13.0.7 fixes
- Fix clock output ordering on some APUs
- Clean up DC FPGA code
- GFX9 preemption fixes
- Misc irq fixes
- S0ix fixes
- Add new DRM_AMDGPU_WERROR config parameter to help with CI
- PCIe fix for RDNA2
- kdoc fixes
- Documentation updates
amdkfd:
- Query TTM mem limit rather than hardcoding it
- GC 9.4.3 partition support
- Handle NUMA for partitions
radeon:
- Fix possible double free
- Stop including unused swiotlb.h
- Fix possible division by zero
ttm:
- Add query for TTM mem limit
- Add NUMA awareness to pools
- Export ttm_pool_fini()
UAPI:
- Add new ctx query flag to better handle GPU resets
Mesa MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22290
- Add new interface to query and set shadow buffer for RDNA3
Mesa MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21986
- Add new INFO query for max IB size
Proposed userspace: https://gitlab.freedesktop.org/bnieuwenhuizen/mesa/-/commits/ib-rejection-v3
amd-drm-next-6.5-2023-06-09:
amdgpu:
- S0ix fixes
- Initial SMU13 Overdrive support
- kdoc fixes
- Misc clode cleanups
- Flexible array fixes
- Display OTG fixes
- SMU 13.0.6 updates
- Revert some broken clock counter updates
- Misc display fixes
- GFX9 preemption fixes
- Add support for newer EEPROM bad page table format
- Add missing radeon secondary id
- Add support for new colorspace KMS API
- CSA fix
- Stable pstate fixes for APUs
- make vbl interface admin only
- Handle PCI accelerator class
amdkfd:
- Add debugger support for gdb
radeon:
- Fix possible UAF
drm:
- Add Colorspace functionality
UAPI:
- Add debugger interface for enabling gdb
Proposed userspace: https://github.com/ROCm-Developer-Tools/ROCdbgapi/tree/wip-dbgapi
- Add KMS colorspace API
Discussion: https://lists.freedesktop.org/archives/dri-devel/2023-June/408128.html
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230609174817.7764-1-alexander.deucher@amd.com
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c | 154 |
1 files changed, 153 insertions, 1 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c index 4485bb29bec9..60f9e027fb66 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c @@ -23,6 +23,149 @@ #include "amdgpu_amdkfd.h" #include "amdgpu_amdkfd_arcturus.h" #include "amdgpu_amdkfd_gfx_v9.h" +#include "gc/gc_9_4_2_offset.h" +#include "gc/gc_9_4_2_sh_mask.h" +#include <uapi/linux/kfd_ioctl.h> + +/* + * Returns TRAP_EN, EXCP_EN and EXCP_REPLACE. + * + * restore_dbg_registers is ignored here but is a general interface requirement + * for devices that support GFXOFF and where the RLC save/restore list + * does not support hw registers for debugging i.e. the driver has to manually + * initialize the debug mode registers after it has disabled GFX off during the + * debug session. + */ +static uint32_t kgd_aldebaran_enable_debug_trap(struct amdgpu_device *adev, + bool restore_dbg_registers, + uint32_t vmid) +{ + uint32_t data = 0; + + data = REG_SET_FIELD(data, SPI_GDBG_PER_VMID_CNTL, TRAP_EN, 1); + data = REG_SET_FIELD(data, SPI_GDBG_PER_VMID_CNTL, EXCP_EN, 0); + data = REG_SET_FIELD(data, SPI_GDBG_PER_VMID_CNTL, EXCP_REPLACE, 0); + + return data; +} + +/* returns TRAP_EN, EXCP_EN and EXCP_REPLACE. */ +static uint32_t kgd_aldebaran_disable_debug_trap(struct amdgpu_device *adev, + bool keep_trap_enabled, + uint32_t vmid) +{ + uint32_t data = 0; + + data = REG_SET_FIELD(data, SPI_GDBG_PER_VMID_CNTL, TRAP_EN, keep_trap_enabled); + data = REG_SET_FIELD(data, SPI_GDBG_PER_VMID_CNTL, EXCP_EN, 0); + data = REG_SET_FIELD(data, SPI_GDBG_PER_VMID_CNTL, EXCP_REPLACE, 0); + + return data; +} + +static int kgd_aldebaran_validate_trap_override_request(struct amdgpu_device *adev, + uint32_t trap_override, + uint32_t *trap_mask_supported) +{ + *trap_mask_supported &= KFD_DBG_TRAP_MASK_FP_INVALID | + KFD_DBG_TRAP_MASK_FP_INPUT_DENORMAL | + KFD_DBG_TRAP_MASK_FP_DIVIDE_BY_ZERO | + KFD_DBG_TRAP_MASK_FP_OVERFLOW | + KFD_DBG_TRAP_MASK_FP_UNDERFLOW | + KFD_DBG_TRAP_MASK_FP_INEXACT | + KFD_DBG_TRAP_MASK_INT_DIVIDE_BY_ZERO | + KFD_DBG_TRAP_MASK_DBG_ADDRESS_WATCH | + KFD_DBG_TRAP_MASK_DBG_MEMORY_VIOLATION; + + if (trap_override != KFD_DBG_TRAP_OVERRIDE_OR && + trap_override != KFD_DBG_TRAP_OVERRIDE_REPLACE) + return -EPERM; + + return 0; +} + +/* returns TRAP_EN, EXCP_EN and EXCP_RPLACE. */ +static uint32_t kgd_aldebaran_set_wave_launch_trap_override(struct amdgpu_device *adev, + uint32_t vmid, + uint32_t trap_override, + uint32_t trap_mask_bits, + uint32_t trap_mask_request, + uint32_t *trap_mask_prev, + uint32_t kfd_dbg_trap_cntl_prev) + +{ + uint32_t data = 0; + + *trap_mask_prev = REG_GET_FIELD(kfd_dbg_trap_cntl_prev, SPI_GDBG_PER_VMID_CNTL, EXCP_EN); + trap_mask_bits = (trap_mask_bits & trap_mask_request) | + (*trap_mask_prev & ~trap_mask_request); + + data = REG_SET_FIELD(data, SPI_GDBG_PER_VMID_CNTL, TRAP_EN, 1); + data = REG_SET_FIELD(data, SPI_GDBG_PER_VMID_CNTL, EXCP_EN, trap_mask_bits); + data = REG_SET_FIELD(data, SPI_GDBG_PER_VMID_CNTL, EXCP_REPLACE, trap_override); + + return data; +} + +static uint32_t kgd_aldebaran_set_wave_launch_mode(struct amdgpu_device *adev, + uint8_t wave_launch_mode, + uint32_t vmid) +{ + uint32_t data = 0; + + data = REG_SET_FIELD(data, SPI_GDBG_PER_VMID_CNTL, LAUNCH_MODE, wave_launch_mode); + + return data; +} + +#define TCP_WATCH_STRIDE (regTCP_WATCH1_ADDR_H - regTCP_WATCH0_ADDR_H) +static uint32_t kgd_gfx_aldebaran_set_address_watch( + struct amdgpu_device *adev, + uint64_t watch_address, + uint32_t watch_address_mask, + uint32_t watch_id, + uint32_t watch_mode, + uint32_t debug_vmid) +{ + uint32_t watch_address_high; + uint32_t watch_address_low; + uint32_t watch_address_cntl; + + watch_address_cntl = 0; + watch_address_low = lower_32_bits(watch_address); + watch_address_high = upper_32_bits(watch_address) & 0xffff; + + watch_address_cntl = REG_SET_FIELD(watch_address_cntl, + TCP_WATCH0_CNTL, + MODE, + watch_mode); + + watch_address_cntl = REG_SET_FIELD(watch_address_cntl, + TCP_WATCH0_CNTL, + MASK, + watch_address_mask >> 6); + + watch_address_cntl = REG_SET_FIELD(watch_address_cntl, + TCP_WATCH0_CNTL, + VALID, + 1); + + WREG32_RLC((SOC15_REG_OFFSET(GC, 0, regTCP_WATCH0_ADDR_H) + + (watch_id * TCP_WATCH_STRIDE)), + watch_address_high); + + WREG32_RLC((SOC15_REG_OFFSET(GC, 0, regTCP_WATCH0_ADDR_L) + + (watch_id * TCP_WATCH_STRIDE)), + watch_address_low); + + return watch_address_cntl; +} + +static uint32_t kgd_gfx_aldebaran_clear_address_watch(struct amdgpu_device *adev, + uint32_t watch_id) +{ + return 0; +} const struct kfd2kgd_calls aldebaran_kfd2kgd = { .program_sh_mem_settings = kgd_gfx_v9_program_sh_mem_settings, @@ -42,5 +185,14 @@ const struct kfd2kgd_calls aldebaran_kfd2kgd = { kgd_gfx_v9_get_atc_vmid_pasid_mapping_info, .set_vm_context_page_table_base = kgd_gfx_v9_set_vm_context_page_table_base, .get_cu_occupancy = kgd_gfx_v9_get_cu_occupancy, - .program_trap_handler_settings = kgd_gfx_v9_program_trap_handler_settings + .enable_debug_trap = kgd_aldebaran_enable_debug_trap, + .disable_debug_trap = kgd_aldebaran_disable_debug_trap, + .validate_trap_override_request = kgd_aldebaran_validate_trap_override_request, + .set_wave_launch_trap_override = kgd_aldebaran_set_wave_launch_trap_override, + .set_wave_launch_mode = kgd_aldebaran_set_wave_launch_mode, + .set_address_watch = kgd_gfx_aldebaran_set_address_watch, + .clear_address_watch = kgd_gfx_aldebaran_clear_address_watch, + .get_iq_wait_times = kgd_gfx_v9_get_iq_wait_times, + .build_grace_period_packet_info = kgd_gfx_v9_build_grace_period_packet_info, + .program_trap_handler_settings = kgd_gfx_v9_program_trap_handler_settings, }; |