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

1 files changed, 48 insertions, 11 deletions

diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
index 5cb3e8634739..d0df3381539f 100644
--- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
@@ -230,28 +230,30 @@ struct kfd2kgd_calls {
 	/* Register access functions */
 	void (*program_sh_mem_settings)(struct amdgpu_device *adev, uint32_t vmid,
 			uint32_t sh_mem_config,	uint32_t sh_mem_ape1_base,
-			uint32_t sh_mem_ape1_limit, uint32_t sh_mem_bases);
+			uint32_t sh_mem_ape1_limit, uint32_t sh_mem_bases,
+			uint32_t inst);
 
 	int (*set_pasid_vmid_mapping)(struct amdgpu_device *adev, u32 pasid,
-					unsigned int vmid);
+					unsigned int vmid, uint32_t inst);
 
-	int (*init_interrupts)(struct amdgpu_device *adev, uint32_t pipe_id);
+	int (*init_interrupts)(struct amdgpu_device *adev, uint32_t pipe_id,
+			uint32_t inst);
 
 	int (*hqd_load)(struct amdgpu_device *adev, void *mqd, uint32_t pipe_id,
 			uint32_t queue_id, uint32_t __user *wptr,
 			uint32_t wptr_shift, uint32_t wptr_mask,
-			struct mm_struct *mm);
+			struct mm_struct *mm, uint32_t inst);
 
 	int (*hiq_mqd_load)(struct amdgpu_device *adev, void *mqd,
 			    uint32_t pipe_id, uint32_t queue_id,
-			    uint32_t doorbell_off);
+			    uint32_t doorbell_off, uint32_t inst);
 
 	int (*hqd_sdma_load)(struct amdgpu_device *adev, void *mqd,
 			     uint32_t __user *wptr, struct mm_struct *mm);
 
 	int (*hqd_dump)(struct amdgpu_device *adev,
 			uint32_t pipe_id, uint32_t queue_id,
-			uint32_t (**dump)[2], uint32_t *n_regs);
+			uint32_t (**dump)[2], uint32_t *n_regs, uint32_t inst);
 
 	int (*hqd_sdma_dump)(struct amdgpu_device *adev,
 			     uint32_t engine_id, uint32_t queue_id,
@@ -259,12 +261,12 @@ struct kfd2kgd_calls {
 
 	bool (*hqd_is_occupied)(struct amdgpu_device *adev,
 				uint64_t queue_address, uint32_t pipe_id,
-				uint32_t queue_id);
+				uint32_t queue_id, uint32_t inst);
 
 	int (*hqd_destroy)(struct amdgpu_device *adev, void *mqd,
 				enum kfd_preempt_type reset_type,
 				unsigned int timeout, uint32_t pipe_id,
-				uint32_t queue_id);
+				uint32_t queue_id, uint32_t inst);
 
 	bool (*hqd_sdma_is_occupied)(struct amdgpu_device *adev, void *mqd);
 
@@ -273,7 +275,7 @@ struct kfd2kgd_calls {
 
 	int (*wave_control_execute)(struct amdgpu_device *adev,
 					uint32_t gfx_index_val,
-					uint32_t sq_cmd);
+					uint32_t sq_cmd, uint32_t inst);
 	bool (*get_atc_vmid_pasid_mapping_info)(struct amdgpu_device *adev,
 					uint8_t vmid,
 					uint16_t *p_pasid);
@@ -289,10 +291,45 @@ struct kfd2kgd_calls {
 			uint32_t vmid, uint64_t page_table_base);
 	uint32_t (*read_vmid_from_vmfault_reg)(struct amdgpu_device *adev);
 
+	uint32_t (*enable_debug_trap)(struct amdgpu_device *adev,
+					bool restore_dbg_registers,
+					uint32_t vmid);
+	uint32_t (*disable_debug_trap)(struct amdgpu_device *adev,
+					bool keep_trap_enabled,
+					uint32_t vmid);
+	int (*validate_trap_override_request)(struct amdgpu_device *adev,
+					uint32_t trap_override,
+					uint32_t *trap_mask_supported);
+	uint32_t (*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 (*set_wave_launch_mode)(struct amdgpu_device *adev,
+					uint8_t wave_launch_mode,
+					uint32_t vmid);
+	uint32_t (*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 (*clear_address_watch)(struct amdgpu_device *adev,
+			uint32_t watch_id);
+	void (*get_iq_wait_times)(struct amdgpu_device *adev,
+			uint32_t *wait_times);
+	void (*build_grace_period_packet_info)(struct amdgpu_device *adev,
+			uint32_t wait_times,
+			uint32_t grace_period,
+			uint32_t *reg_offset,
+			uint32_t *reg_data);
 	void (*get_cu_occupancy)(struct amdgpu_device *adev, int pasid,
-			int *wave_cnt, int *max_waves_per_cu);
+			int *wave_cnt, int *max_waves_per_cu, uint32_t inst);
 	void (*program_trap_handler_settings)(struct amdgpu_device *adev,
-			uint32_t vmid, uint64_t tba_addr, uint64_t tma_addr);
+			uint32_t vmid, uint64_t tba_addr, uint64_t tma_addr,
+			uint32_t inst);
 };
 
 #endif	/* KGD_KFD_INTERFACE_H_INCLUDED */