Merge tag 'drm-for-v4.12' of git://people.freedesktop.org/~airlied/linux

Pull drm u pdates from Dave Airlie:
 "This is the main drm pull request for v4.12. Apart from two fixes
  pulls, everything should have been in drm-next for at least 2 weeks.

  The biggest thing in here is AMD released the public headers for their
  upcoming VEGA GPUs. These as always are quite a sizeable chunk of
  header files. They've also added initial non-display support for those
  GPUs, though they aren't available in production yet.

  Otherwise it's pretty much normal.

  New bridge drivers:
   - megachips-stdpxxxx-ge-b850v3-fw LVDS->DP++
   - generic LVDS bridge support.

  Core:
   - Displayport link train failure reporting to userspace
   - debugfs interface cleaned up
   - subsystem TODO in kerneldoc now
   - Extended fbdev support (flipping and vblank wait)
   - drm_platform removed
   - EDP CRC support in helper
   - HF-VSDB SCDC support in EDID parser
   - Lots of code cleanups and header extraction
   - Thunderbolt external GPU awareness
   - Atomic helper improvements
   - Documentation improvements

  panel:
   - Sitronix and Samsung new panel support

  amdgpu:
   - Preliminary vega10 support
   - Multi-level page table support
   - GPU sensor support for userspace
   - PRT support for sparse buffers
   - SR-IOV improvements
   - Non-contig VRAM CPU mapping

  i915:
   - Atomic modesetting enabled by default on Gen5+
   - LSPCON improvements
   - Atomic state handling for cdclk
   - GPU reset improvements
   - In-kernel unit tests
   - Geminilake improvements and color manager support
   - Designware i2c fixes
   - vblank evasion improvements
   - Hotplug safe connector iterators
   - GVT scheduler QoS support
   - GVT Kabylake support

  nouveau:
   - Acceleration support for Pascal (GP10x).
   - Rearchitecture of code handling proprietary signed firmware
   - Fix GTX 970 with odd MMU configuration
   - GP10B support
   - GP107 acceleration support

  vmwgfx:
   - Atomic modesetting support for vmwgfx

  omapdrm:
   - Support for render nodes
   - Refactor omapdss code
   - Fix some probe ordering issues
   - Fix too dark RGB565 rendering

  sunxi:
   - prelim rework for multiple pipes.

  mali-dp:
   - Color management support
   - Plane scaling
   - Power management improvements

  imx-drm:
   - Prefetch Resolve Engine/Gasket on i.MX6QP
   - Deferred plane disabling
   - Separate alpha support

  mediatek:
   - Mediatek SoC MT2701 support

  rcar-du:
   - Gen3 HDMI support

  msm:
   - 4k support for newer chips
   - OPP bindings for gpu
   - prep work for per-process pagetables

  vc4:
   - HDMI audio support
   - fixes

  qxl:
   - minor fixes.

  dw-hdmi:
   - PHY improvements
   - CSC fixes
   - Amlogic GX SoC support"

* tag 'drm-for-v4.12' of git://people.freedesktop.org/~airlied/linux: (1778 commits)
  drm/nouveau/fb/gf100-: Fix 32 bit wraparound in new ram detection
  drm/nouveau/secboot/gm20b: fix the error return code in gm20b_secboot_tegra_read_wpr()
  drm/nouveau/kms: Increase max retries in scanout position queries.
  drm/nouveau/bios/bitP: check that table is long enough for optional pointers
  drm/nouveau/fifo/nv40: no ctxsw for pre-nv44 mpeg engine
  drm: mali-dp: use div_u64 for expensive 64-bit divisions
  drm/i915: Confirm the request is still active before adding it to the await
  drm/i915: Avoid busy-spinning on VLV_GLTC_PW_STATUS mmio
  drm/i915/selftests: Allocate inode/file dynamically
  drm/i915: Fix system hang with EI UP masked on Haswell
  drm/i915: checking for NULL instead of IS_ERR() in mock selftests
  drm/i915: Perform link quality check unconditionally during long pulse
  drm/i915: Fix use after free in lpe_audio_platdev_destroy()
  drm/i915: Use the right mapping_gfp_mask for final shmem allocation
  drm/i915: Make legacy cursor updates more unsynced
  drm/i915: Apply a cond_resched() to the saturated signaler
  drm/i915: Park the signaler before sleeping
  drm: mali-dp: Check the mclk rate and allow up/down scaling
  drm: mali-dp: Enable image enhancement when scaling
  drm: mali-dp: Add plane upscaling support
  ...

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;