aboutsummaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu
AgeCommit message (Collapse)AuthorFilesLines
2023-06-15drm/amd/amdgpu: enable W=1 for amdgpuHamza Mahfooz1-1/+12
We have a clean build with W=1 as of commit c168feed5d03 ("drm/amd/display/amdgpu_dm/amdgpu_dm_helpers: Move SYNAPTICS_DEVICE_ID into CONFIG_DRM_AMD_DC_DCN ifdef"). So, let's enable these checks unconditionally for the entire module to catch these errors during development. Cc: Alex Deucher <[email protected]> Cc: Nathan Chancellor <[email protected]> Tested-by: Nathan Chancellor <[email protected]> Reviewed-by: Nathan Chancellor <[email protected]> Signed-off-by: Hamza Mahfooz <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-15drm/amdgpu: Fix kdoc warningSrinivasan Shanmugam1-2/+2
Fixes the following gcc with W=1: drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c:76: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst * EEPROM Table structure v1 drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c:98: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst * EEPROM Table structrue v2.1 Cc: Christian König <[email protected]> Cc: Alex Deucher <[email protected]> Signed-off-by: Srinivasan Shanmugam <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-15drm/amdgpu: Rename DRM schedulers in amdgpu TTMMukul Joshi3-14/+14
Rename mman.entity to mman.high_pr to make the distinction clearer that this is a high priority scheduler. Similarly, rename the recently added mman.delayed to mman.low_pr to make it clear it is a low priority scheduler. No functional change in this patch. Signed-off-by: Mukul Joshi <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-15Merge tag 'amd-drm-next-6.5-2023-06-09' of ↵Dave Airlie180-3237/+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 <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2023-06-13Revert "drm/amdgpu: remove TOPDOWN flags when allocating VRAM in large bar ↵Arunpravin Paneer Selvam1-1/+1
system" This reverts commit c105518679b6e87232874ffc989ec403bee59664. This patch disables the TOPDOWN flag for APU and few dGPU cards which has the VRAM size equal to the BAR size. When we enable the TOPDOWN flag, we get the free blocks at the highest available memory region and we don't split the lower order blocks. This change is required to keep off the fragmentation related issues particularly in ASIC which has VRAM space <= 500MiB Hence, we are reverting this patch. Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2270 Signed-off-by: Arunpravin Paneer Selvam <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]> Cc: [email protected]
2023-06-13drm/amdgpu: vcn_4_0 set instance 0 init sched score to 1Sonny Jiang1-1/+5
Only vcn0 can process AV1 codecx. In order to use both vcn0 and vcn1 in h264/265 transcode to AV1 cases, set vcn0 sched score to 1 at initialization time. Signed-off-by: Sonny Jiang <[email protected]> Reviewed-by: Leo Liu <[email protected]> Signed-off-by: Alex Deucher <[email protected]> Cc: [email protected] # 6.1.x
2023-06-13drm/amd: Tighten permissions on VBIOS flashing attributesMario Limonciello1-2/+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: [email protected] Fixes: 8424f2ccb3c0 ("drm/amdgpu/psp: Add vbflash sysfs interface support") Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Mario Limonciello <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-13drm/amd: Make sure image is written to trigger VBIOS image update flowMario Limonciello1-0/+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: [email protected] Fixes: 8424f2ccb3c0 ("drm/amdgpu/psp: Add vbflash sysfs interface support") Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Mario Limonciello <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-13drm/amdgpu: add missing radeon secondary PCI IDAlex Deucher1-0/+1
0x5b70 is a missing RV370 secondary id. Add it so we don't try and probe it with amdgpu. Cc: [email protected] Reviewed-by: Michel Dänzer <[email protected]> Tested-by: Michel Dänzer <[email protected]> Signed-off-by: Alex Deucher <[email protected]> Cc: [email protected]
2023-06-13drm/amdgpu: Implement gfx9 patch functions for resubmissionJiadong Zhu1-0/+80
Patch the packages including CONTEXT_CONTROL and WRITE_DATA for gfx9 during the resubmission scenario. Signed-off-by: Jiadong Zhu <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]> Cc: [email protected] # 6.3.x
2023-06-13drm/amdgpu: Modify indirect buffer packages for resubmissionJiadong Zhu4-0/+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 <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]> Cc: [email protected] # 6.3.x
2023-06-13drm/amdgpu: Program gds backup address as zero if no gds allocatedJiadong Zhu1-5/+8
It is firmware requirement to set gds_backup_addrlo and gds_backup_addrhi of DE meta both zero if no gds partition is allocated for the frame. Signed-off-by: Jiadong Zhu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]> Cc: [email protected] # 6.3.x
2023-06-13drm/amdgpu: Reset CP_VMID_PREEMPT after trailing fence signaledJiadong Zhu1-4/+4
When MEC executes unmap_queue for mid command buffer preemption, it will kick the write pointer of the gfx ring, set CP_VMID_PREEMPT to trigger the preemption and wait for CP_VMID_PREEMPT becomes zero after the preemption done. There is a race condition that PFP may excute the resetting command before MEC set CP_VMID_PREEMPT. As a result, hang happens as CP_VMID_PREEMPT is always 0xffff. To avoid this, we send resetting CP_VMID_PREEMPT command after the trailing fence is siganled and update gfx write pointer explicitly. Signed-off-by: Jiadong Zhu <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]> Cc: [email protected] # 6.3.x Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2535
2023-06-09drm/amdgpu: add option params to enforce process isolation between graphics ↵Chong Li5-23/+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 <[email protected]> Reviewed-by: Christian Koenig <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-09drm/amdgpu: Wrap -Wunused-but-set-variable in cc-optionNathan Chancellor1-1/+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 <[email protected]> Signed-off-by: Hamza Mahfooz <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-09drm/amdgpu: add the accelerator PCIe classShiwu Zhang2-2/+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 <[email protected]> Acked-by: Lijo Lazar <[email protected]> Acked-by: Bjorn Helgaas <[email protected]> # pci_ids.h Signed-off-by: Alex Deucher <[email protected]>
2023-06-09drm/amdkfd: fix and enable debugging for gfx11Jonathan Kim3-2/+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 <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-09drm/amd: Tighten permissions on VBIOS flashing attributesMario Limonciello1-2/+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: [email protected] Fixes: 8424f2ccb3c0 ("drm/amdgpu/psp: Add vbflash sysfs interface support") Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Mario Limonciello <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-09drm/amd: Make sure image is written to trigger VBIOS image update flowMario Limonciello1-0/+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: [email protected] Fixes: 8424f2ccb3c0 ("drm/amdgpu/psp: Add vbflash sysfs interface support") Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Mario Limonciello <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-09drm/amdgpu: skip to resume rlcg for gc 9.4.3 in vf sideYang Wang1-5/+10
skip to resume rlcg, because rlcg is already enabled in pf side. Signed-off-by: Yang Wang <[email protected]> Reviewed-by: Lijo Lazar <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-09drm/amdgpu: disable virtual display support on APP deviceYang Wang1-1/+2
virtual display is not support on APP device. Signed-off-by: Yang Wang <[email protected]> Signed-off-by: Gavin Wan <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-09drm/amdgpu: unmap and remove csa_va properlyLang Yu3-5/+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 <[email protected]> Acked-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-09drm/amdgpu: add missing radeon secondary PCI IDAlex Deucher1-0/+1
0x5b70 is a missing RV370 secondary id. Add it so we don't try and probe it with amdgpu. Cc: [email protected] Reviewed-by: Michel Dänzer <[email protected]> Tested-by: Michel Dänzer <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-09drm/amdgpu: Set EEPROM ras infoStanley.Yang2-0/+29
Set EEPROM ras info: rma status, health percent and bad page threshold. Signed-off-by: Stanley.Yang <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-09drm/amdgpu: Calculate EEPROM table ras info bytes sumStanley.Yang1-0/+19
It's more reasonable to check EEPROM table ras info bytes. Signed-off-by: Stanley.Yang <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-09drm/amdgpu: Add support EEPROM table v2.1Stanley.Yang3-15/+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 <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-09drm/amdgpu: Support setting EEPROM table versionStanley.Yang2-0/+8
Add setting EEPROM table version interface for umcv8.10, Add EEPROM table v2.1 to UMC v8.10. Signed-off-by: Stanley.Yang <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-09drm/amdgpu: Add RAS table v2.1 macro definitionStanley.Yang2-0/+14
Add RAS EEPROM table version 2.1 macro definition. Signed-off-by: Stanley.Yang <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-09drm/amdgpu: Rename ras table versionStanley.Yang2-3/+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 <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-09drm/amdgpu: Implement gfx9 patch functions for resubmissionJiadong Zhu1-0/+80
Patch the packages including CONTEXT_CONTROL and WRITE_DATA for gfx9 during the resubmission scenario. Signed-off-by: Jiadong Zhu <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-09drm/amdgpu: Modify indirect buffer packages for resubmissionJiadong Zhu4-0/+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 <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-09drm/amdgpu/mmsch: Correct the definition for mmsch init headerEmily Deng4-4/+8
For the header, it is version related, shouldn't use MAX_VCN_INSTANCES. Signed-off-by: Emily Deng <[email protected]> Reviewed-by: Feifei Xu <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-09drm/amdgpu: change reserved vram info printYiPeng Chai1-3/+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 <[email protected]> Reviewed-by: Arunpravin Paneer Selvam <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]> Cc: [email protected]
2023-06-09drm/amdgpu: fix xclk freq on CHIP_STONEYChia-I Wu1-2/+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 <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-09Revert "drm/amdgpu: switch to golden tsc registers for raven/raven2"Alex Deucher1-40/+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: [email protected] Cc: [email protected] Reviewed-by: Michel Dänzer <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-09Revert "drm/amdgpu: Differentiate between Raven2 and Raven/Picasso according ↵Alex Deucher1-14/+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: [email protected] Cc: [email protected] Reviewed-by: Michel Dänzer <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-09Revert "drm/amdgpu: change the reference clock for raven/raven2"Alex Deucher1-3/+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: [email protected] Cc: [email protected] Reviewed-by: Michel Dänzer <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-09drm/amdgpu: convert vcn/jpeg logical mask to physical maskStanley.Yang1-0/+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 <[email protected]> Reviewed-by: Tao Zhou <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-09drm/amdgpu: support check vcn jpeg block maskStanley.Yang1-1/+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 <[email protected]> Reviewed-by: Tao Zhou <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-09drm/amdgpu: pass xcc mask to ras taStanley.Yang2-0/+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 <[email protected]> Reviewed-by: Tao Zhou <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-09drm/amdgpu: Mark 'kgd_gfx_aldebaran_clear_address_watch' & ↵Srinivasan Shanmugam2-4/+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 <[email protected]> Cc: Christian König <[email protected]> Cc: Alex Deucher <[email protected]> Signed-off-by: Srinivasan Shanmugam <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-09amdgpu: validate offset_in_bo of drm_amdgpu_gem_vaChia-I Wu1-8/+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 <[email protected]> Signed-off-by: Chia-I Wu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-09drm/amdgpu: fix debug wait on idle for gfx9.4.1Jonathan Kim1-1/+1
Wait calls for amd_ip_block_type not amd_hw_ip_block_type. Reported-by: Hamza Mahfooz <[email protected]> Signed-off-by: Jonathan Kim <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-09drm/amdkfd: add debug set and clear address watch points operationJonathan Kim8-3/+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 <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-09drm/amdkfd: add debug suspend and resume process queues operationJonathan Kim2-0/+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 <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-09drm/amdkfd: add debug wave launch mode operationJonathan Kim8-2/+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 <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-09drm/amdkfd: add debug wave launch override operationJonathan Kim8-2/+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 <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-09drm/amdkfd: update process interrupt handling for debug eventsJonathan Kim2-0/+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 <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-09drm/amdkfd: apply trap workaround for gfx11Jonathan Kim2-5/+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 <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-06-09drm/amdgpu: expose debug api for mesJonathan Kim3-0/+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 <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
Powered by cgit, Gruvboxed by Blaster4385.