Merge branch 'drm-next-4.12' of git://people.freedesktop.org/~agd5f/linux into drm-next

New stuff for 4.12:
- Preliminary vega10 support
- Support for multi-level page tables
- GPU sensor stuff for mesa
- job tracing improvements
- PRT support for sparse buffers
- Additional SR-IOV improvements
- ttm improvements
- misc bug fixes and code cleanups

* 'drm-next-4.12' of git://people.freedesktop.org/~agd5f/linux: (315 commits)
  drm/amdgpu: Fix 32bit x86 compilation warning
  drm/amdgpu: just disallow reading untouched registers
  drm/amdgpu: remove duplicate allowed reg CP_CPF_BUSY_STAT
  drm/amdgpu/soc15: enable psp block for SRIOV
  drm/amdgpu/soc15: bypass pp block for vf
  drm/amdgpu/psp: add check sOS sign
  drm/amd/amdgpu: Correct ring wptr address in debugfs (v2)
  drm/amdgpu: Fix multi-level page table bugs for large BOs v3
  drm/amdgpu: Fix Vega10 VM initialization
  drm/amdgpu: Make max_pfn 64-bit
  drm/amdgpu: drop GB_GPU_ID from the golden settings
  drm/amdgpu: fix vm pte pde flags to 64-bit for sdma (v3)
  drm/amd/amdgpu: fix Tonga S3 resume hang on rhel6.8
  drm/ttm: decrease ttm bo priority number
  drm/amd/amdgpu: fix performance drop when VRAM pressure
  drm/amdgpu: Couple small warning fixes
  drm/amdgpu: Clean up GFX 9 VM fault messages
  drm/amdgpu: Register UTCL2 as a source of VM faults
  drm/amdgpu/soc15: drop support for reading some registers
  drm/amdgpu/soc15: return cached values for some registers (v2)
  ...

1 files changed, 99 insertions, 13 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
index 0f0b38191fac..a1891c93cdbf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
@@ -217,10 +217,55 @@ bool amdgpu_ucode_hdr_version(union amdgpu_firmware_header *hdr,
 	return true;
 }
 
-static int amdgpu_ucode_init_single_fw(struct amdgpu_firmware_info *ucode,
-				uint64_t mc_addr, void *kptr)
+enum amdgpu_firmware_load_type
+amdgpu_ucode_get_load_type(struct amdgpu_device *adev, int load_type)
+{
+	switch (adev->asic_type) {
+#ifdef CONFIG_DRM_AMDGPU_SI
+	case CHIP_TAHITI:
+	case CHIP_PITCAIRN:
+	case CHIP_VERDE:
+	case CHIP_OLAND:
+		return AMDGPU_FW_LOAD_DIRECT;
+#endif
+#ifdef CONFIG_DRM_AMDGPU_CIK
+	case CHIP_BONAIRE:
+	case CHIP_KAVERI:
+	case CHIP_KABINI:
+	case CHIP_HAWAII:
+	case CHIP_MULLINS:
+		return AMDGPU_FW_LOAD_DIRECT;
+#endif
+	case CHIP_TOPAZ:
+	case CHIP_TONGA:
+	case CHIP_FIJI:
+	case CHIP_CARRIZO:
+	case CHIP_STONEY:
+	case CHIP_POLARIS10:
+	case CHIP_POLARIS11:
+	case CHIP_POLARIS12:
+		if (!load_type)
+			return AMDGPU_FW_LOAD_DIRECT;
+		else
+			return AMDGPU_FW_LOAD_SMU;
+	case CHIP_VEGA10:
+		if (!load_type)
+			return AMDGPU_FW_LOAD_DIRECT;
+		else
+			return AMDGPU_FW_LOAD_PSP;
+	default:
+		DRM_ERROR("Unknow firmware load type\n");
+	}
+
+	return AMDGPU_FW_LOAD_DIRECT;
+}
+
+static int amdgpu_ucode_init_single_fw(struct amdgpu_device *adev,
+				       struct amdgpu_firmware_info *ucode,
+				       uint64_t mc_addr, void *kptr)
 {
 	const struct common_firmware_header *header = NULL;
+	const struct gfx_firmware_header_v1_0 *cp_hdr = NULL;
 
 	if (NULL == ucode->fw)
 		return 0;
@@ -232,9 +277,36 @@ static int amdgpu_ucode_init_single_fw(struct amdgpu_firmware_info *ucode,
 		return 0;
 
 	header = (const struct common_firmware_header *)ucode->fw->data;
-	memcpy(ucode->kaddr, (void *)((uint8_t *)ucode->fw->data +
-		le32_to_cpu(header->ucode_array_offset_bytes)),
-		le32_to_cpu(header->ucode_size_bytes));
+
+	cp_hdr = (const struct gfx_firmware_header_v1_0 *)ucode->fw->data;
+
+	if (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP ||
+	    (ucode->ucode_id != AMDGPU_UCODE_ID_CP_MEC1 &&
+	     ucode->ucode_id != AMDGPU_UCODE_ID_CP_MEC2 &&
+	     ucode->ucode_id != AMDGPU_UCODE_ID_CP_MEC1_JT &&
+	     ucode->ucode_id != AMDGPU_UCODE_ID_CP_MEC2_JT)) {
+		ucode->ucode_size = le32_to_cpu(header->ucode_size_bytes);
+
+		memcpy(ucode->kaddr, (void *)((uint8_t *)ucode->fw->data +
+					      le32_to_cpu(header->ucode_array_offset_bytes)),
+		       ucode->ucode_size);
+	} else if (ucode->ucode_id == AMDGPU_UCODE_ID_CP_MEC1 ||
+		   ucode->ucode_id == AMDGPU_UCODE_ID_CP_MEC2) {
+		ucode->ucode_size = le32_to_cpu(header->ucode_size_bytes) -
+			le32_to_cpu(cp_hdr->jt_size) * 4;
+
+		memcpy(ucode->kaddr, (void *)((uint8_t *)ucode->fw->data +
+					      le32_to_cpu(header->ucode_array_offset_bytes)),
+		       ucode->ucode_size);
+	} else if (ucode->ucode_id == AMDGPU_UCODE_ID_CP_MEC1_JT ||
+		   ucode->ucode_id == AMDGPU_UCODE_ID_CP_MEC2_JT) {
+		ucode->ucode_size = le32_to_cpu(cp_hdr->jt_size) * 4;
+
+		memcpy(ucode->kaddr, (void *)((uint8_t *)ucode->fw->data +
+					      le32_to_cpu(header->ucode_array_offset_bytes) +
+					      le32_to_cpu(cp_hdr->jt_offset) * 4),
+		       ucode->ucode_size);
+	}
 
 	return 0;
 }
@@ -260,10 +332,11 @@ static int amdgpu_ucode_patch_jt(struct amdgpu_firmware_info *ucode,
 			   (le32_to_cpu(header->jt_offset) * 4);
 	memcpy(dst_addr, src_addr, le32_to_cpu(header->jt_size) * 4);
 
+	ucode->ucode_size += le32_to_cpu(header->jt_size) * 4;
+
 	return 0;
 }
 
-
 int amdgpu_ucode_init_bo(struct amdgpu_device *adev)
 {
 	struct amdgpu_bo **bo = &adev->firmware.fw_buf;
@@ -303,20 +376,32 @@ int amdgpu_ucode_init_bo(struct amdgpu_device *adev)
 
 	amdgpu_bo_unreserve(*bo);
 
-	for (i = 0; i < AMDGPU_UCODE_ID_MAXIMUM; i++) {
+	memset(fw_buf_ptr, 0, adev->firmware.fw_size);
+
+	/*
+	 * if SMU loaded firmware, it needn't add SMC, UVD, and VCE
+	 * ucode info here
+	 */
+	if (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP)
+		adev->firmware.max_ucodes = AMDGPU_UCODE_ID_MAXIMUM - 4;
+	else
+		adev->firmware.max_ucodes = AMDGPU_UCODE_ID_MAXIMUM;
+
+	for (i = 0; i < adev->firmware.max_ucodes; i++) {
 		ucode = &adev->firmware.ucode[i];
 		if (ucode->fw) {
 			header = (const struct common_firmware_header *)ucode->fw->data;
-			amdgpu_ucode_init_single_fw(ucode, fw_mc_addr + fw_offset,
-						    fw_buf_ptr + fw_offset);
-			if (i == AMDGPU_UCODE_ID_CP_MEC1) {
+			amdgpu_ucode_init_single_fw(adev, ucode, fw_mc_addr + fw_offset,
+						    (void *)((uint8_t *)fw_buf_ptr + fw_offset));
+			if (i == AMDGPU_UCODE_ID_CP_MEC1 &&
+			    adev->firmware.load_type != AMDGPU_FW_LOAD_PSP) {
 				const struct gfx_firmware_header_v1_0 *cp_hdr;
 				cp_hdr = (const struct gfx_firmware_header_v1_0 *)ucode->fw->data;
 				amdgpu_ucode_patch_jt(ucode, fw_mc_addr + fw_offset,
 						    fw_buf_ptr + fw_offset);
 				fw_offset += ALIGN(le32_to_cpu(cp_hdr->jt_size) << 2, PAGE_SIZE);
 			}
-			fw_offset += ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE);
+			fw_offset += ALIGN(ucode->ucode_size, PAGE_SIZE);
 		}
 	}
 	return 0;
@@ -328,7 +413,8 @@ failed_pin:
 failed_reserve:
 	amdgpu_bo_unref(bo);
 failed:
-	adev->firmware.smu_load = false;
+	if (err)
+		adev->firmware.load_type = AMDGPU_FW_LOAD_DIRECT;
 
 	return err;
 }
@@ -338,7 +424,7 @@ int amdgpu_ucode_fini_bo(struct amdgpu_device *adev)
 	int i;
 	struct amdgpu_firmware_info *ucode = NULL;
 
-	for (i = 0; i < AMDGPU_UCODE_ID_MAXIMUM; i++) {
+	for (i = 0; i < adev->firmware.max_ucodes; i++) {
 		ucode = &adev->firmware.ucode[i];
 		if (ucode->fw) {
 			ucode->mc_addr = 0;