sync with OpenBSD -current

sys/dev/pci/drm/amd/amdgpu/amdgpu_vm.h

@@ -29,17 +29,20 @@
 #include <linux/rbtree.h>
 #include <drm/gpu_scheduler.h>
 #include <drm/drm_file.h>
-#include <drm/ttm/ttm_bo_driver.h>
+#include <drm/ttm/ttm_bo.h>
 #include <linux/sched/mm.h>
 
 #include "amdgpu_sync.h"
 #include "amdgpu_ring.h"
 #include "amdgpu_ids.h"
 
+struct drm_exec;
+
 struct amdgpu_bo_va;
 struct amdgpu_job;
 struct amdgpu_bo_list_entry;
 struct amdgpu_bo_vm;
+struct amdgpu_mem_stats;
 
 /*
  * GPUVM handling
@@ -83,7 +86,13 @@ struct amdgpu_bo_vm;
 /* PDE Block Fragment Size for VEGA10 */
 #define AMDGPU_PDE_BFS(a)	((uint64_t)a << 59)
 
+/* Flag combination to set no-retry with TF disabled */
+#define AMDGPU_VM_NORETRY_FLAGS	(AMDGPU_PTE_EXECUTABLE | AMDGPU_PDE_PTE | \
+				AMDGPU_PTE_TF)
 
+/* Flag combination to set no-retry with TF enabled */
+#define AMDGPU_VM_NORETRY_FLAGS_TF (AMDGPU_PTE_VALID | AMDGPU_PTE_SYSTEM | \
+				   AMDGPU_PTE_PRT)
 /* For GFX9 */
 #define AMDGPU_PTE_MTYPE_VG10(a)	((uint64_t)(a) << 57)
 #define AMDGPU_PTE_MTYPE_VG10_MASK	AMDGPU_PTE_MTYPE_VG10(3ULL)
@@ -110,18 +119,18 @@ struct amdgpu_bo_vm;
 /* Reserve 4MB VRAM for page tables */
 #define AMDGPU_VM_RESERVED_VRAM		(8ULL << 20)
 
-/* max number of VMHUB */
-#define AMDGPU_MAX_VMHUBS			3
-#define AMDGPU_GFXHUB_0				0
-#define AMDGPU_MMHUB_0				1
-#define AMDGPU_MMHUB_1				2
+/*
+ * max number of VMHUB
+ * layout: max 8 GFXHUB + 4 MMHUB0 + 1 MMHUB1
+ */
+#define AMDGPU_MAX_VMHUBS			13
+#define AMDGPU_GFXHUB(x)			(x)
+#define AMDGPU_MMHUB0(x)			(8 + x)
+#define AMDGPU_MMHUB1(x)			(8 + 4 + x)
 
 /* Reserve 2MB at top/bottom of address space for kernel use */
 #define AMDGPU_VA_RESERVED_SIZE			(2ULL << 20)
 
-/* max vmids dedicated for process */
-#define AMDGPU_VM_MAX_RESERVED_VMID	1
-
 /* See vm_update_mode */
 #define AMDGPU_VM_USE_CPU_FOR_GFX (1 << 0)
 #define AMDGPU_VM_USE_CPU_FOR_COMPUTE (1 << 1)
@@ -300,12 +309,14 @@ struct amdgpu_vm {
 	atomic64_t		tlb_seq;
 	struct dma_fence	*last_tlb_flush;
 
+	/* How many times we had to re-generate the page tables */
+	uint64_t		generation;
+
 	/* Last unlocked submission to the scheduler entities */
 	struct dma_fence	*last_unlocked;
 
 	unsigned int		pasid;
-	/* dedicated to vm */
-	struct amdgpu_vmid	*reserved_vmid[AMDGPU_MAX_VMHUBS];
+	bool			reserved_vmid[AMDGPU_MAX_VMHUBS];
 
 	/* Flag to indicate if VM tables are updated by CPU or GPU (SDMA) */
 	bool					use_cpu_for_update;
@@ -339,6 +350,9 @@ struct amdgpu_vm {
 	struct ttm_lru_bulk_move lru_bulk_move;
 	/* Flag to indicate if VM is used for compute */
 	bool			is_compute_context;
+
+	/* Memory partition number, -1 means any partition */
+	int8_t			mem_id;
 };
 
 struct amdgpu_vm_manager {
@@ -396,14 +410,14 @@ int amdgpu_vm_set_pasid(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 			u32 pasid);
 
 long amdgpu_vm_wait_idle(struct amdgpu_vm *vm, long timeout);
-int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm);
+int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, int32_t xcp_id);
 int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm);
 void amdgpu_vm_release_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm);
 void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm);
-void amdgpu_vm_get_pd_bo(struct amdgpu_vm *vm,
-			 struct list_head *validated,
-			 struct amdgpu_bo_list_entry *entry);
+int amdgpu_vm_lock_pd(struct amdgpu_vm *vm, struct drm_exec *exec,
+		      unsigned int num_fences);
 bool amdgpu_vm_ready(struct amdgpu_vm *vm);
+uint64_t amdgpu_vm_generation(struct amdgpu_device *adev, struct amdgpu_vm *vm);
 int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 			      int (*callback)(void *p, struct amdgpu_bo *bo),
 			      void *param);
@@ -465,19 +479,21 @@ void amdgpu_vm_check_compute_bug(struct amdgpu_device *adev);
 void amdgpu_vm_get_task_info(struct amdgpu_device *adev, u32 pasid,
 			     struct amdgpu_task_info *task_info);
 bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid,
-			    uint64_t addr, bool write_fault);
+			    u32 vmid, u32 node_id, uint64_t addr,
+			    bool write_fault);
 
 void amdgpu_vm_set_task_info(struct amdgpu_vm *vm);
 
 void amdgpu_vm_move_to_lru_tail(struct amdgpu_device *adev,
 				struct amdgpu_vm *vm);
-void amdgpu_vm_get_memory(struct amdgpu_vm *vm, uint64_t *vram_mem,
-				uint64_t *gtt_mem, uint64_t *cpu_mem);
+void amdgpu_vm_get_memory(struct amdgpu_vm *vm,
+			  struct amdgpu_mem_stats *stats);
 
 int amdgpu_vm_pt_clear(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 		       struct amdgpu_bo_vm *vmbo, bool immediate);
 int amdgpu_vm_pt_create(struct amdgpu_device *adev, struct amdgpu_vm *vm,
-			int level, bool immediate, struct amdgpu_bo_vm **vmbo);
+			int level, bool immediate, struct amdgpu_bo_vm **vmbo,
+			int32_t xcp_id);
 void amdgpu_vm_pt_free_root(struct amdgpu_device *adev, struct amdgpu_vm *vm);
 bool amdgpu_vm_pt_is_root_clean(struct amdgpu_device *adev,
 				struct amdgpu_vm *vm);
@@ -493,6 +509,8 @@ void amdgpu_vm_pt_free_work(struct work_struct *work);
 void amdgpu_debugfs_vm_bo_info(struct amdgpu_vm *vm, struct seq_file *m);
 #endif
 
+int amdgpu_vm_pt_map_tables(struct amdgpu_device *adev, struct amdgpu_vm *vm);
+
 /**
  * amdgpu_vm_tlb_seq - return tlb flush sequence number
  * @vm: the amdgpu_vm structure to query