summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/amd/amdgpu
Commit message (Collapse)AuthorAgeFilesLines
* Merge tag 'amd-drm-next-6.5-2023-06-09' of ↵Dave Airlie2023-06-15180-3237/+17370
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 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
| * drm/amdgpu: add option params to enforce process isolation between graphics ↵Chong Li2023-06-095-23/+36
| | | | | | | | | | | | | | | | | | | | | | | | | | and compute enforce process isolation between graphics and compute via using the same reserved vmid. v2: remove params "struct amdgpu_vm *vm" from amdgpu_vmid_alloc_reserved and amdgpu_vmid_free_reserved. Signed-off-by: Chong Li <chongli2@amd.com> Reviewed-by: Christian Koenig <Christian.Koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdgpu: Wrap -Wunused-but-set-variable in cc-optionNathan Chancellor2023-06-091-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | -Wunused-but-set-variable was only supported in clang starting with 13.0.0, so earlier versions will emit a warning, which is turned into a hard error for the kernel to mirror GCC: error: unknown warning option '-Wunused-but-set-variable'; did you mean '-Wunused-const-variable'? [-Werror,-Wunknown-warning-option] The minimum supported version of clang for building the kernel is 11.0.0, so match the rest of the kernel and wrap -Wunused-but-set-variable in a cc-option call, so that it is only used when supported by the compiler. Closes: https://github.com/ClangBuiltLinux/linux/issues/1869 Fixes: 1b320ad3f5a8 ("drm/amd/amdgpu: introduce DRM_AMDGPU_WERROR") Signed-off-by: Nathan Chancellor <nathan@kernel.org> Signed-off-by: Hamza Mahfooz <hamza.mahfooz@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdgpu: add the accelerator PCIe classShiwu Zhang2023-06-092-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | Add the accelerator PCIe class and match the class in amdgpu for 0x1002 devices of that class. From PCI spec: "PCI Code and ID Assignment, r1.9, sec 1, 1.19" Signed-off-by: Shiwu Zhang <shiwu.zhang@amd.com> Acked-by: Lijo Lazar <lijo.lazar@amd.com> Acked-by: Bjorn Helgaas <bhelgaas@google.com> # pci_ids.h Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdkfd: fix and enable debugging for gfx11Jonathan Kim2023-06-093-2/+10
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | There are a couple of fixes required to enable gfx11 debugging. First, ADD_QUEUE.trap_en is an inappropriate place to toggle a per-process register so move it to SET_SHADER_DEBUGGER.trap_en. When ADD_QUEUE.skip_process_ctx_clear is set, MES will prioritize the SET_SHADER_DEBUGGER.trap_en setting. Second, to preserve correct save/restore priviledged wave states in coordination with the trap enablement setting, resume suspended waves early in the disable call. Signed-off-by: Jonathan Kim <jonathan.kim@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amd: Tighten permissions on VBIOS flashing attributesMario Limonciello2023-06-091-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | Non-root users shouldn't be able to try to trigger a VBIOS flash or query the flashing status. This should be reserved for users with the appropriate permissions. Cc: stable@vger.kernel.org Fixes: 8424f2ccb3c0 ("drm/amdgpu/psp: Add vbflash sysfs interface support") Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Mario Limonciello <mario.limonciello@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amd: Make sure image is written to trigger VBIOS image update flowMario Limonciello2023-06-091-0/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The VBIOS image update flow requires userspace to: 1) Write the image to `psp_vbflash` 2) Read `psp_vbflash` 3) Poll `psp_vbflash_status` to check for completion If userspace reads `psp_vbflash` before writing an image, it's possible that it causes problems that can put the dGPU into an invalid state. Explicitly check that an image has been written before letting a read succeed. Cc: stable@vger.kernel.org Fixes: 8424f2ccb3c0 ("drm/amdgpu/psp: Add vbflash sysfs interface support") Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Mario Limonciello <mario.limonciello@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdgpu: skip to resume rlcg for gc 9.4.3 in vf sideYang Wang2023-06-091-5/+10
| | | | | | | | | | | | | | | | skip to resume rlcg, because rlcg is already enabled in pf side. Signed-off-by: Yang Wang <kevinyang.wang@amd.com> Reviewed-by: Lijo Lazar <lijo.lazar@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdgpu: disable virtual display support on APP deviceYang Wang2023-06-091-1/+2
| | | | | | | | | | | | | | | | | | virtual display is not support on APP device. Signed-off-by: Yang Wang <kevinyang.wang@amd.com> Signed-off-by: Gavin Wan <gavin.wan@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdgpu: unmap and remove csa_va properlyLang Yu2023-06-093-5/+46
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Root PD BO should be reserved before unmap and remove a bo_va from VM otherwise lockdep will complain. v2: check fpriv->csa_va is not NULL instead of amdgpu_mcbp (christian) [14616.936827] WARNING: CPU: 6 PID: 1711 at drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c:1762 amdgpu_vm_bo_del+0x399/0x3f0 [amdgpu] [14616.937096] Call Trace: [14616.937097] <TASK> [14616.937102] amdgpu_driver_postclose_kms+0x249/0x2f0 [amdgpu] [14616.937187] drm_file_free+0x1d6/0x300 [drm] [14616.937207] drm_close_helper.isra.0+0x62/0x70 [drm] [14616.937220] drm_release+0x5e/0x100 [drm] [14616.937234] __fput+0x9f/0x280 [14616.937239] ____fput+0xe/0x20 [14616.937241] task_work_run+0x61/0x90 [14616.937246] exit_to_user_mode_prepare+0x215/0x220 [14616.937251] syscall_exit_to_user_mode+0x2a/0x60 [14616.937254] do_syscall_64+0x48/0x90 [14616.937257] entry_SYSCALL_64_after_hwframe+0x63/0xcd Signed-off-by: Lang Yu <Lang.Yu@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdgpu: add missing radeon secondary PCI IDAlex Deucher2023-06-091-0/+1
| | | | | | | | | | | | | | | | | | | | 0x5b70 is a missing RV370 secondary id. Add it so we don't try and probe it with amdgpu. Cc: michel@daenzer.net Reviewed-by: Michel Dänzer <mdaenzer@redhat.com> Tested-by: Michel Dänzer <mdaenzer@redhat.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdgpu: Set EEPROM ras infoStanley.Yang2023-06-092-0/+29
| | | | | | | | | | | | | | | | | | Set EEPROM ras info: rma status, health percent and bad page threshold. Signed-off-by: Stanley.Yang <Stanley.Yang@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdgpu: Calculate EEPROM table ras info bytes sumStanley.Yang2023-06-091-0/+19
| | | | | | | | | | | | | | | | It's more reasonable to check EEPROM table ras info bytes. Signed-off-by: Stanley.Yang <Stanley.Yang@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdgpu: Add support EEPROM table v2.1Stanley.Yang2023-06-093-15/+203
| | | | | | | | | | | | | | | | | | Add ras info to EEPROM table, app can analyse device ECC status without GPU driver through EEPROM table ras info. Signed-off-by: Stanley.Yang <Stanley.Yang@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdgpu: Support setting EEPROM table versionStanley.Yang2023-06-092-0/+8
| | | | | | | | | | | | | | | | | | Add setting EEPROM table version interface for umcv8.10, Add EEPROM table v2.1 to UMC v8.10. Signed-off-by: Stanley.Yang <Stanley.Yang@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdgpu: Add RAS table v2.1 macro definitionStanley.Yang2023-06-092-0/+14
| | | | | | | | | | | | | | | | Add RAS EEPROM table version 2.1 macro definition. Signed-off-by: Stanley.Yang <Stanley.Yang@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdgpu: Rename ras table versionStanley.Yang2023-06-092-3/+4
| | | | | | | | | | | | | | | | | | Rename RAS_TABLE_VER to RAS_TABLE_VER_V1, move RAS_TABLE_VER_V1 from amdgpu_ras_eeprom.c to amdgpu_ras_eeprom.h. Signed-off-by: Stanley.Yang <Stanley.Yang@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdgpu: Implement gfx9 patch functions for resubmissionJiadong Zhu2023-06-091-0/+80
| | | | | | | | | | | | | | | | | | Patch the packages including CONTEXT_CONTROL and WRITE_DATA for gfx9 during the resubmission scenario. Signed-off-by: Jiadong Zhu <Jiadong.Zhu@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdgpu: Modify indirect buffer packages for resubmissionJiadong Zhu2023-06-094-0/+102
| | | | | | | | | | | | | | | | | | | | | | | | | | | | When the preempted IB frame resubmitted to cp, we need to modify the frame data including: 1. set PRE_RESUME 1 in CONTEXT_CONTROL. 2. use meta data(DE and CE) read from CSA in WRITE_DATA. Add functions to save the location the first time IBs emitted and callback to patch the package when resubmission happens. Signed-off-by: Jiadong Zhu <Jiadong.Zhu@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdgpu/mmsch: Correct the definition for mmsch init headerEmily Deng2023-06-094-4/+8
| | | | | | | | | | | | | | | | | | For the header, it is version related, shouldn't use MAX_VCN_INSTANCES. Signed-off-by: Emily Deng <Emily.Deng@amd.com> Reviewed-by: Feifei Xu <Feifei.Xu@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdgpu: change reserved vram info printYiPeng Chai2023-06-091-3/+4
| | | | | | | | | | | | | | | | | | | | | | | | The link object of mgr->reserved_pages is the blocks variable in struct amdgpu_vram_reservation, not the link variable in struct drm_buddy_block. Signed-off-by: YiPeng Chai <YiPeng.Chai@amd.com> Reviewed-by: Arunpravin Paneer Selvam <Arunpravin.PaneerSelvam@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org
| * drm/amdgpu: fix xclk freq on CHIP_STONEYChia-I Wu2023-06-091-2/+9
| | | | | | | | | | | | | | | | | | According to Alex, most APUs from that time seem to have the same issue (vbios says 48Mhz, actual is 100Mhz). I only have a CHIP_STONEY so I limit the fixup to CHIP_STONEY Signed-off-by: Chia-I Wu <olvaffe@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * Revert "drm/amdgpu: switch to golden tsc registers for raven/raven2"Alex Deucher2023-06-091-40/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | This reverts commit f03eb1d26c2739b75580f58bbab4ab2d5d3eba46. This results in inconsistent timing reported via asynchronous GPU queries. Link: https://lists.freedesktop.org/archives/amd-gfx/2023-May/093731.html Cc: Jesse.Zhang@amd.com Cc: michel@daenzer.net Reviewed-by: Michel Dänzer <mdaenzer@redhat.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * Revert "drm/amdgpu: Differentiate between Raven2 and Raven/Picasso according ↵Alex Deucher2023-06-091-14/+19
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | to revision id" This reverts commit 9d2d1827af295fd6971786672c41c4dba3657154. This results in inconsistent timing reported via asynchronous GPU queries. Link: https://lists.freedesktop.org/archives/amd-gfx/2023-May/093731.html Cc: Jesse.Zhang@amd.com Cc: michel@daenzer.net Reviewed-by: Michel Dänzer <mdaenzer@redhat.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * Revert "drm/amdgpu: change the reference clock for raven/raven2"Alex Deucher2023-06-091-3/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | This reverts commit fbc24293ca16b3b9ef891fe32ccd04735a6f8dc1. This results in inconsistent timing reported via asynchronous GPU queries. Link: https://lists.freedesktop.org/archives/amd-gfx/2023-May/093731.html Cc: Jesse.Zhang@amd.com Cc: michel@daenzer.net Reviewed-by: Michel Dänzer <mdaenzer@redhat.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdgpu: convert vcn/jpeg logical mask to physical maskStanley.Yang2023-06-091-0/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | Changed from V1: Remove amdgpu_ras_logical_mask_to_physical_mask due to GET_MASK provides same feature. Support convert VCN/JPEG logical mask to physical mask. Signed-off-by: Stanley.Yang <Stanley.Yang@amd.com> Reviewed-by: Tao Zhou <tao.zhou1@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdgpu: support check vcn jpeg block maskStanley.Yang2023-06-091-1/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | Support VCN/JPEG instance mask checking, pass logical mask directly except GFX/SDMA/VCN/JPEG blocks. Changed from V1: correct a typo Signed-off-by: Stanley.Yang <Stanley.Yang@amd.com> Reviewed-by: Tao Zhou <tao.zhou1@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdgpu: pass xcc mask to ras taStanley.Yang2023-06-092-0/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | pass xcc mask to ras ta, ras ta will compare the mask with the one from chiplet topology. Changed from V1: Remove IP version checking. Set ras_cmd->ras_init_message.init_flags.xcc_mask directly due to xcc_mask is common structres to all the devices. Signed-off-by: Stanley.Yang <Stanley.Yang@amd.com> Reviewed-by: Tao Zhou <tao.zhou1@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdgpu: Mark 'kgd_gfx_aldebaran_clear_address_watch' & ↵Srinivasan Shanmugam2023-06-092-4/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 'kgd_gfx_v11_clear_address_watch' functions as static Below two functions cause a warning because they lack a prototype: drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c:164:10: warning: no previous prototype for ‘kgd_gfx_aldebaran_clear_address_watch’ [-Wmissing-prototypes] drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v11.c:782:10: warning: no previous prototype for ‘kgd_gfx_v11_clear_address_watch’ [-Wmissing-prototypes] There are no callers from other files, so just mark them as 'static'. Also fixes the following checks: CHECK: Alignment should match open parenthesis +static uint32_t kgd_gfx_aldebaran_clear_address_watch(struct amdgpu_device *adev, uint32_t watch_id) CHECK: Alignment should match open parenthesis +static uint32_t kgd_gfx_v11_clear_address_watch(struct amdgpu_device *adev, uint32_t watch_id) Cc: Felix Kuehling <Felix.Kuehling@amd.com> Cc: Christian König <christian.koenig@amd.com> Cc: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * amdgpu: validate offset_in_bo of drm_amdgpu_gem_vaChia-I Wu2023-06-091-8/+8
| | | | | | | | | | | | | | | | | | | | | | | | | | | | This is motivated by OOB access in amdgpu_vm_update_range when offset_in_bo+map_size overflows. v2: keep the validations in amdgpu_vm_bo_map v3: add the validations to amdgpu_vm_bo_map/amdgpu_vm_bo_replace_map rather than to amdgpu_gem_va_ioctl Fixes: 9f7eb5367d00 ("drm/amdgpu: actually use the VM map parameters") Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Chia-I Wu <olvaffe@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdgpu: fix debug wait on idle for gfx9.4.1Jonathan Kim2023-06-091-1/+1
| | | | | | | | | | | | | | | | | | Wait calls for amd_ip_block_type not amd_hw_ip_block_type. Reported-by: Hamza Mahfooz <hamza.mahfooz@amd.com> Signed-off-by: Jonathan Kim <jonathan.kim@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdkfd: add debug set and clear address watch points operationJonathan Kim2023-06-098-3/+278
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Shader read, write and atomic memory operations can be alerted to the debugger as an address watch exception. Allow the debugger to pass in a watch point to a particular memory address per device. Note that there exists only 4 watch points per devices to date, so have the KFD keep track of what watch points are allocated or not. Signed-off-by: Jonathan Kim <jonathan.kim@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdkfd: add debug suspend and resume process queues operationJonathan Kim2023-06-092-0/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In order to inspect waves from the saved context at any point during a debug session, the debugger must be able to preempt queues to trigger context save by suspending them. On queue suspend, the KFD will copy the context save header information so that the debugger can correctly crawl the appropriate size of the saved context. The debugger must then also be allowed to resume suspended queues. A queue that is newly created cannot be suspended because queue ids are recycled after destruction so the debugger needs to know that this has occurred. Query functions will be later added that will clear a given queue of its new queue status. A queue cannot be destroyed while it is suspended to preserve its saved context during debugger inspection. Have queue destruction block while a queue is suspended and unblocked when it is resumed. Likewise, if a queue is about to be destroyed, it cannot be suspended. Return the number of queues successfully suspended or resumed along with a per queue status array where the upper bits per queue status show that the request was invalid (new/destroyed queue suspend request, missing queue) or an error occurred (HWS in a fatal state so it can't suspend or resume queues). Signed-off-by: Jonathan Kim <jonathan.kim@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdkfd: add debug wave launch mode operationJonathan Kim2023-06-098-2/+84
| | | | | | | | | | | | | | | | | | | | Allow the debugger to set wave behaviour on to either normally operate, halt at launch, trap on every instruction, terminate immediately or stall on allocation. Signed-off-by: Jonathan Kim <jonathan.kim@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdkfd: add debug wave launch override operationJonathan Kim2023-06-098-2/+269
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This operation allows the debugger to override the enabled HW exceptions on the device. On debug devices that only support the debugging of a single process, the HW exceptions are global and set through the SPI_GDBG_TRAP_MASK register. Because they are global, only address watch exceptions are allowed to be enabled. In other words, the debugger must preserve all non-address watch exception states in normal mode operation by barring a full replacement override or a non-address watch override request. For multi-process debugging, all HW exception overrides are per-VMID so all exceptions can be overridden or fully replaced. In order for the debugger to know what is permissible, returned the supported override mask back to the debugger along with the previously enable overrides. Signed-off-by: Jonathan Kim <jonathan.kim@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdkfd: update process interrupt handling for debug eventsJonathan Kim2023-06-092-0/+18
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The debugger must be notified by any debugger subscribed exception that comes from hardware interrupts. If a debugger session exits, any exceptions it subscribed to may still have interrupts in the interrupt ring buffer or KGD/KFD pipeline. To prevent a new session from inheriting stale interrupts, when a new queue is created, open an interrupt drain and allow the IH ring to drain from a timestamped checkpoint. Then inject a custom IV so that once the custom IV is picked up by the KFD, it's safe to close the drain and proceed with queue creation. The drain must also be on debug disable as SW interrupts may still be processed. Drain at this time and clear all the exception status. The debugger may also not be attached nor subscibed to certain exceptions so forward them directly to the runtime. GFX10 also requires its own IV processing, hence the creation of kfd_int_process_v10.c. This is because the IV from SQ interrupts are packed into a new continguous format unlike GFX9. To make this clear, a separate interrupting handling code file was created. Signed-off-by: Jonathan Kim <jonathan.kim@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdkfd: apply trap workaround for gfx11Jonathan Kim2023-06-092-5/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Due to a HW bug, waves in only half the shader arrays can enter trap. When starting a debug session, relocate all waves to the first shader array of each shader engine and mask off the 2nd shader array as unavailable. When ending a debug session, re-enable the 2nd shader array per shader engine. User CU masking per queue cannot be guaranteed to remain functional if requested during debugging (e.g. user cu mask requests only 2nd shader array as an available resource leading to zero HW resources available) nor can runtime be alerted of any of these changes during execution. Make user CU masking and debugging mutual exclusive with respect to availability. If the debugger tries to attach to a process with a user cu masked queue, return the runtime status as enabled but busy. If the debugger tries to attach and fails to reallocate queue waves to the first shader array of each shader engine, return the runtime status as enabled but with an error. In addition, like any other mutli-process debug supported devices, disable trap temporary setup per-process to avoid performance impact from setup overhead. Signed-off-by: Jonathan Kim <jonathan.kim@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdgpu: expose debug api for mesJonathan Kim2023-06-093-0/+64
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Similar to the F32 HWS, the RS64 HWS for GFX11 now supports a multi-process debug API. The skip_process_ctx_clear ADD_QUEUE requirement is to prevent the MES from clearing the process context when the first queue is added to the scheduler in order to maintain debug mode settings during queue preemption and restore. The MES clears the process context in this case due to an unresolved FW caching bug during normal mode operations. During debug mode, the KFD will hold a reference to the target process so the process context should never go stale and MES can afford to skip this requirement. Signed-off-by: Jonathan Kim <jonathan.kim@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdgpu: add configurable grace period for unmap queuesJonathan Kim2023-06-097-2/+104
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The HWS schedule allows a grace period for wave completion prior to preemption for better performance by avoiding CWSR on waves that can potentially complete quickly. The debugger, on the other hand, will want to inspect wave status immediately after it actively triggers preemption (a suspend function to be provided). To minimize latency between preemption and debugger wave inspection, allow immediate preemption by setting the grace period to 0. Note that setting the preepmtion grace period to 0 will result in an infinite grace period being set due to a CP FW bug so set it to 1 for now. Signed-off-by: Jonathan Kim <jonathan.kim@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdgpu: add gfx11 hw debug mode enable and disable callsJonathan Kim2023-06-091-0/+38
| | | | | | | | | | | | | | | | | | Implement the per-device calls to enable or disable HW debug mode for GFX11. Signed-off-by: Jonathan Kim <jonathan.kim@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdgpu: add gfx9.4.2 hw debug mode enable and disable callsJonathan Kim2023-06-091-1/+41
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | GFX9.4.2 now supports per-VMID debug mode controls registers (SPI_GDBG_PER_VMID_CNTL). Because the KFD lets the HWS handle PASID-VMID mapping, the KFD will forward all debug mode setting register writes to the HWS scheduler using a new MAP_PROCESS API, so instead of writing to registers, return the required register values that the HWS needs to write on debug enable and disable. Signed-off-by: Jonathan Kim <jonathan.kim@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdgpu: add gfx10 hw debug mode enable and disable callsJonathan Kim2023-06-093-145/+127
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Similar to GFX9 debug devices, set the hardware debug mode by draining the SPI appropriately prior the mode setting request. Because GFX10 has waves allocated by the work group boundary and each SE's SPI instances do not communicate, the SPI drain time is much longer. This long drain time will be fixed for GFX11 onwards. Also remove a bunch of deprecated misplaced references for GFX10.3. Signed-off-by: Jonathan Kim <jonathan.kim@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdgpu: add gfx9.4.1 hw debug mode enable and disable callsJonathan Kim2023-06-093-2/+121
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | On GFX9.4.1, the implicit wait count instruction on s_barrier is disabled by default in the driver during normal operation for performance requirements. There is a hardware bug in GFX9.4.1 where if the implicit wait count instruction after an s_barrier instruction is disabled, any wave that hits an exception may step over the s_barrier when returning from the trap handler with the barrier logic having no ability to be aware of this, thereby causing other waves to wait at the barrier indefinitely resulting in a shader hang. This bug has been corrected for GFX9.4.2 and onward. Since the debugger subscribes to hardware exceptions, in order to avoid this bug, the debugger must enable implicit wait count on s_barrier for a debug session and disable it on detach. In order to change this setting in the in the device global SQ_CONFIG register, the GFX pipeline must be idle. GFX9.4.1 as a compute device will either dispatch work through the compute ring buffers used for image post processing or through the hardware scheduler by the KFD. Have the KGD suspend and drain the compute ring buffer, then suspend the hardware scheduler and block any future KFD process job requests before changing the implicit wait count setting. Once set, resume all work. Signed-off-by: Jonathan Kim <jonathan.kim@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdgpu: add gfx9 hw debug mode enable and disable callsJonathan Kim2023-06-092-0/+101
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Implement the per-device calls to enable or disable HW debug mode for GFX9 prior to GFX9.4.1. GFX9.4.1 and onward will require their own enable/disable sequence as follow on patches. When hardware debug mode setting is requested, waves will inherit these settings in the Shader Processor Input's (SPI) Sequencer Global Block (SQG). This means that the KGD must drain all waves from the SPI into SQG (approximately 96 SPI clock cycles) prior to debug mode setting to ensure that the order of operations that the debugger expects with regards to debug mode setting transaction requests and wave inheritence of that mode is upheld. Also ensure that exception overrides are reset to their original state prior to debug enable or disable. Signed-off-by: Jonathan Kim <jonathan.kim@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amd: Make lack of `ACPI_FADT_LOW_POWER_S0` or `CONFIG_AMD_PMC` louder ↵Mario Limonciello2023-06-091-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | during suspend path Users have reported that s2idle wasn't working on OEM Phoenix systems, but it was root caused to be because `CONFIG_AMD_PMC` wasn't set in the distribution kernel config. To make this more apparent, raise the messaging to err instead of warn. Link: https://bugzilla.kernel.org/show_bug.cgi?id=217497 Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Mario Limonciello <mario.limonciello@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdgpu: setup hw debug registers on driver initializationJonathan Kim2023-06-094-0/+60
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Add missing debug trap registers references and initialize all debug registers on boot by clearing the hardware exception overrides and the wave allocation ID index. The debugger requires that TTMPs 6 & 7 save the dispatch ID to map waves onto dispatch during compute context inspection. In order to correctly set this up, set the special reserved CP bit by default whenever the MQD is initailized. Signed-off-by: Jonathan Kim <jonathan.kim@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdgpu: fix Null pointer dereference error in amdgpu_device_recover_vramHoratio Zhang2023-06-092-7/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | Use the function of amdgpu_bo_vm_destroy to handle the resource release of shadow bo. During the amdgpu_mes_self_test, shadow bo released, but vmbo->shadow_list was not, which caused a null pointer reference error in amdgpu_device_recover_vram when GPU reset. Fixes: 6c032c37ac3e ("drm/amdgpu: Fix vram recover doesn't work after whole GPU reset (v2)") Signed-off-by: xinhui pan <xinhui.pan@amd.com> Signed-off-by: Horatio Zhang <Hongkun.Zhang@amd.com> Acked-by: Feifei Xu <Feifei.Xu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdgpu: Fix up kdoc in amdgpu_device.cSrinivasan Shanmugam2023-06-091-4/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Fix these warnings by deleting the deviant arguments. gcc with W=1 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c:799: warning: Excess function parameter 'pcie_index' description in 'amdgpu_device_indirect_wreg' drivers/gpu/drm/amd/amdgpu/amdgpu_device.c:799: warning: Excess function parameter 'pcie_data' description in 'amdgpu_device_indirect_wreg' drivers/gpu/drm/amd/amdgpu/amdgpu_device.c:870: warning: Excess function parameter 'pcie_index' description in 'amdgpu_device_indirect_wreg64' drivers/gpu/drm/amd/amdgpu/amdgpu_device.c:870: warning: Excess function parameter 'pcie_data' description in 'amdgpu_device_indirect_wreg64' Cc: Christian König <christian.koenig@amd.com> Cc: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amdgpu: Fix up kdoc 'ring' parameter in sdma_v6_0_ring_pad_ibSrinivasan Shanmugam2023-06-091-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | Fix this warning by adding 'ring' arguments to kdoc. gcc with W=1 drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c:1128: warning: Function parameter or member 'ring' not described in 'sdma_v6_0_ring_pad_ib' Cc: Felix Kuehling <Felix.Kuehling@amd.com> Cc: Christian König <christian.koenig@amd.com> Cc: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/amd/amdgpu: introduce DRM_AMDGPU_WERRORHamza Mahfooz2023-06-092-0/+19
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | We want to do -Werror builds on our CI. However, non-amdgpu breakages have prevented us from doing so thus far. Also, there are a number of additional checks that we should enable, that the community cares about and are hidden behind -Wextra. So, define DRM_AMDGPU_WERROR to only enable -Werror for the amdgpu kernel module and enable -Wextra while disabling all of the checks that are too noisy. Cc: Alex Deucher <alexander.deucher@amd.com> Cc: Kenny Ho <kenny.ho@amd.com> Suggested-by: Jani Nikula <jani.nikula@linux.intel.com> Reviewed-by: Kenny Ho <Kenny.Ho@amd.com> Signed-off-by: Hamza Mahfooz <hamza.mahfooz@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
generated by cgit v1.2.3 (git 2.46.0) at 2025-04-27 00:15:52 +0000