drm/amdgpu: implement PRT for GFX6 v2

Enable/disable the handling globally for now and
print a warning when we enable it for the first time.

v2: write to the correct register, adjust bits to that hw generation
v3: fix compilation, add the missing register bit definitions
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/amdgpu.h

@@ -569,6 +569,7 @@ struct amdgpu_mc {
 	uint32_t		vram_type;
 	uint32_t                srbm_soft_reset;
 	struct amdgpu_mode_mc_save save;
+	bool			prt_warning;
 };
 
 /*

drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c

@@ -400,6 +400,60 @@ static void gmc_v6_0_set_fault_enable_default(struct amdgpu_device *adev,
 	WREG32(mmVM_CONTEXT1_CNTL, tmp);
 }
 
+ /**
+   + * gmc_v8_0_set_prt - set PRT VM fault
+   + *
+   + * @adev: amdgpu_device pointer
+   + * @enable: enable/disable VM fault handling for PRT
+   +*/
+static void gmc_v6_0_set_prt(struct amdgpu_device *adev, bool enable)
+{
+	u32 tmp;
+
+	if (enable && !adev->mc.prt_warning) {
+		dev_warn(adev->dev, "Disabling VM faults because of PRT request!\n");
+		adev->mc.prt_warning = true;
+	}
+
+	tmp = RREG32(mmVM_PRT_CNTL);
+	tmp = REG_SET_FIELD(tmp, VM_PRT_CNTL,
+			    CB_DISABLE_FAULT_ON_UNMAPPED_ACCESS,
+			    enable);
+	tmp = REG_SET_FIELD(tmp, VM_PRT_CNTL,
+			    TC_DISABLE_FAULT_ON_UNMAPPED_ACCESS,
+			    enable);
+	tmp = REG_SET_FIELD(tmp, VM_PRT_CNTL,
+			    L2_CACHE_STORE_INVALID_ENTRIES,
+			    enable);
+	tmp = REG_SET_FIELD(tmp, VM_PRT_CNTL,
+			    L1_TLB_STORE_INVALID_ENTRIES,
+			    enable);
+	WREG32(mmVM_PRT_CNTL, tmp);
+
+	if (enable) {
+		uint32_t low = AMDGPU_VA_RESERVED_SIZE >> AMDGPU_GPU_PAGE_SHIFT;
+		uint32_t high = adev->vm_manager.max_pfn;
+
+		WREG32(mmVM_PRT_APERTURE0_LOW_ADDR, low);
+		WREG32(mmVM_PRT_APERTURE1_LOW_ADDR, low);
+		WREG32(mmVM_PRT_APERTURE2_LOW_ADDR, low);
+		WREG32(mmVM_PRT_APERTURE3_LOW_ADDR, low);
+		WREG32(mmVM_PRT_APERTURE0_HIGH_ADDR, high);
+		WREG32(mmVM_PRT_APERTURE1_HIGH_ADDR, high);
+		WREG32(mmVM_PRT_APERTURE2_HIGH_ADDR, high);
+		WREG32(mmVM_PRT_APERTURE3_HIGH_ADDR, high);
+	} else {
+		WREG32(mmVM_PRT_APERTURE0_LOW_ADDR, 0xfffffff);
+		WREG32(mmVM_PRT_APERTURE1_LOW_ADDR, 0xfffffff);
+		WREG32(mmVM_PRT_APERTURE2_LOW_ADDR, 0xfffffff);
+		WREG32(mmVM_PRT_APERTURE3_LOW_ADDR, 0xfffffff);
+		WREG32(mmVM_PRT_APERTURE0_HIGH_ADDR, 0x0);
+		WREG32(mmVM_PRT_APERTURE1_HIGH_ADDR, 0x0);
+		WREG32(mmVM_PRT_APERTURE2_HIGH_ADDR, 0x0);
+		WREG32(mmVM_PRT_APERTURE3_HIGH_ADDR, 0x0);
+	}
+}
+
 static int gmc_v6_0_gart_enable(struct amdgpu_device *adev)
 {
 	int r, i;
@@ -1082,6 +1136,7 @@ static const struct amd_ip_funcs gmc_v6_0_ip_funcs = {
 static const struct amdgpu_gart_funcs gmc_v6_0_gart_funcs = {
 	.flush_gpu_tlb = gmc_v6_0_gart_flush_gpu_tlb,
 	.set_pte_pde = gmc_v6_0_gart_set_pte_pde,
+	.set_prt = gmc_v6_0_set_prt,
 };
 
 static const struct amdgpu_irq_src_funcs gmc_v6_0_irq_funcs = {

drivers/gpu/drm/amd/include/asic_reg/gmc/gmc_6_0_sh_mask.h

@@ -11891,5 +11891,9 @@
 #define VM_PRT_CNTL__L1_TLB_STORE_INVALID_ENTRIES__SHIFT 0x00000003
 #define VM_PRT_CNTL__L2_CACHE_STORE_INVALID_ENTRIES_MASK 0x00000004L
 #define VM_PRT_CNTL__L2_CACHE_STORE_INVALID_ENTRIES__SHIFT 0x00000002
+#define VM_PRT_CNTL__CB_DISABLE_FAULT_ON_UNMAPPED_ACCESS_MASK 0x00000001L
+#define VM_PRT_CNTL__CB_DISABLE_FAULT_ON_UNMAPPED_ACCESS__SHIFT 0x00000000
+#define VM_PRT_CNTL__TC_DISABLE_FAULT_ON_UNMAPPED_ACCESS_MASK 0x00000002L
+#define VM_PRT_CNTL__TC_DISABLE_FAULT_ON_UNMAPPED_ACCESS__SHIFT 0x00000001
 
 #endif