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, 19 insertions, 10 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
index 7a33b93f9df6..21b14510882b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
@@ -48,6 +48,7 @@ struct svm_range_bo {
 	struct work_struct		eviction_work;
 	uint32_t			evicting;
 	struct work_struct		release_work;
+	struct kfd_node			*node;
 };
 
 enum svm_work_list_ops {
@@ -133,6 +134,7 @@ struct svm_range {
 	DECLARE_BITMAP(bitmap_aip, MAX_GPU_INSTANCE);
 	bool				validated_once;
 	bool				mapped_to_gpu;
+	bool				is_error_flag;
 };
 
 static inline void svm_range_lock(struct svm_range *prange)
@@ -163,16 +165,17 @@ int svm_ioctl(struct kfd_process *p, enum kfd_ioctl_svm_op op, uint64_t start,
 struct svm_range *svm_range_from_addr(struct svm_range_list *svms,
 				      unsigned long addr,
 				      struct svm_range **parent);
-struct amdgpu_device *svm_range_get_adev_by_id(struct svm_range *prange,
-					       uint32_t id);
-int svm_range_vram_node_new(struct amdgpu_device *adev,
-			    struct svm_range *prange, bool clear);
+struct kfd_node *svm_range_get_node_by_id(struct svm_range *prange,
+					  uint32_t gpu_id);
+int svm_range_vram_node_new(struct kfd_node *node, struct svm_range *prange,
+			    bool clear);
 void svm_range_vram_node_free(struct svm_range *prange);
 int svm_range_split_by_granularity(struct kfd_process *p, struct mm_struct *mm,
 			       unsigned long addr, struct svm_range *parent,
 			       struct svm_range *prange);
-int svm_range_restore_pages(struct amdgpu_device *adev,
-			    unsigned int pasid, uint64_t addr, bool write_fault);
+int svm_range_restore_pages(struct amdgpu_device *adev, unsigned int pasid,
+			    uint32_t vmid, uint32_t node_id, uint64_t addr,
+			    bool write_fault);
 int svm_range_schedule_evict_svm_bo(struct amdgpu_amdkfd_fence *fence);
 void svm_range_add_list_work(struct svm_range_list *svms,
 			     struct svm_range *prange, struct mm_struct *mm,
@@ -192,13 +195,14 @@ int kfd_criu_restore_svm(struct kfd_process *p,
 			 uint64_t max_priv_data_size);
 int kfd_criu_resume_svm(struct kfd_process *p);
 struct kfd_process_device *
-svm_range_get_pdd_by_adev(struct svm_range *prange, struct amdgpu_device *adev);
+svm_range_get_pdd_by_node(struct svm_range *prange, struct kfd_node *node);
 void svm_range_list_lock_and_flush_work(struct svm_range_list *svms, struct mm_struct *mm);
 
 /* SVM API and HMM page migration work together, device memory type
  * is initialized to not 0 when page migration register device memory.
  */
-#define KFD_IS_SVM_API_SUPPORTED(dev) ((dev)->pgmap.type != 0)
+#define KFD_IS_SVM_API_SUPPORTED(adev) ((adev)->kfd.pgmap.type != 0 ||\
+					(adev)->gmc.is_app_apu)
 
 void svm_range_bo_unref_async(struct svm_range_bo *svm_bo);
 
@@ -219,8 +223,9 @@ static inline void svm_range_list_fini(struct kfd_process *p)
 }
 
 static inline int svm_range_restore_pages(struct amdgpu_device *adev,
-					  unsigned int pasid, uint64_t addr,
-					  bool write_fault)
+					  unsigned int pasid,
+					  uint32_t client_id, uint32_t node_id,
+					  uint64_t addr, bool write_fault)
 {
 	return -EFAULT;
 }
@@ -261,6 +266,10 @@ static inline int kfd_criu_resume_svm(struct kfd_process *p)
 	return 0;
 }
 
+static inline void svm_range_set_max_pages(struct amdgpu_device *adev)
+{
+}
+
 #define KFD_IS_SVM_API_SUPPORTED(dev) false
 
 #endif /* IS_ENABLED(CONFIG_HSA_AMD_SVM) */