Merge tag 'drm-next-2019-09-18' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "This is the main pull request for 5.4-rc1 merge window. I don't think
  there is anything outstanding so next week should just be fixes, but
  we'll see if I missed anything. I landed some fixes earlier in the
  week but got delayed writing summary and sending it out, due to a mix
  of sick kid and jetlag!

  There are some fixes pending, but I'd rather get the main merge out of
  the way instead of delaying it longer.

  It's also pretty large in commit count and new amd header file size.
  The largest thing is four new amdgpu products (navi12/14, arcturus and
  renoir APU support).

  Otherwise it's pretty much lots of work across the board, i915 has
  started landing tigerlake support, lots of icelake fixes and lots of
  locking reworking for future gpu support, lots of header file rework
  (drmP.h is nearly gone), some old legacy hacks (DRM_WAIT_ON) have been
  put into the places they are needed.

  uapi:
   - content protection type property for HDCP

  core:
   - rework include dependencies
   - lots of drmP.h removals
   - link rate calculation robustness fix
   - make fb helper map only when required
   - add connector->DDC adapter link
   - DRM_WAIT_ON removed
   - drop DRM_AUTH usage from drivers

  dma-buf:
   - reservation object fence helper

  dma-fence:
   - shrink dma_fence struct
   - merge signal functions
   - store timestamps in dma_fence
   - selftests

  ttm:
   - embed drm_get_object struct into ttm_buffer_object
   - release_notify callback

  bridges:
   - sii902x - audio graph card support
   - tc358767 - aux data handling rework
   - ti-snd64dsi86 - debugfs support, DSI mode flags support

  panels:
   - Support for GiantPlus GPM940B0, Sharp LQ070Y3DG3B, Ortustech
     COM37H3M, Novatek NT39016, Sharp LS020B1DD01D, Raydium RM67191, Boe
     Himax8279d, Sharp LD-D5116Z01B
   - TI nspire, NEC NL8048HL11, LG Philips LB035Q02, Sharp LS037V7DW01,
     Sony ACX565AKM, Toppoly TD028TTEC1 Toppoly TD043MTEA1

  i915:
   - Initial tigerlake platform support
   - Locking simplification work, general all over refactoring.
   - Selftests
   - HDCP debug info improvements
   - DSI properties
   - Icelake display PLL fixes, colorspace fixes, bandwidth fixes, DSI
     suspend/resume
   - GuC fixes
   - Perf fixes
   - ElkhartLake enablement
   - DP MST fixes
   - GVT - command parser enhancements

  amdgpu:
   - add wipe memory on release flag for buffer creation
   - Navi12/14 support (may be marked experimental)
   - Arcturus support
   - Renoir APU support
   - mclk DPM for Navi
   - DC display fixes
   - Raven scatter/gather support
   - RAS support for GFX
   - Navi12 + Arcturus power features
   - GPU reset for Picasso
   - smu11 i2c controller support

  amdkfd:
   - navi12/14 support
   - Arcturus support

  radeon:
   - kexec fix

  nouveau:
   - improved display color management
   - detect lack of GPU power cables

  vmwgfx:
   - evicition priority support
   - remove unused security feature

  msm:
   - msm8998 display support
   - better async commit support for cursor updates

  etnaviv:
   - per-process address space support
   - performance counter fixes
   - softpin support

  mcde:
   - DCS transfers fix

  exynos:
   - drmP.h cleanup

  lima:
   - reduce logging

  kirin:
   - misc clenaups

  komeda:
   - dual-link support
   - DT memory regions

  hisilicon:
   - misc fixes

  imx:
   - IPUv3 image converter fixes
   - 32-bit RGB V4L2 pixel format support

  ingenic:
   - more support for panel related cases

  mgag200:
   - cursor support fix

  panfrost:
   - export GPU features register to userspace
   - gpu heap allocations
   - per-fd address space support

  pl111:
   - CLD pads wiring support removed from DT

  rockchip:
   - rework to use DRM PSR helpers
   - fix bug in VOP_WIN_GET macro
   - DSI DT binding rework

  sun4i:
   - improve support for color encoding and range
   - DDC enabled GPIO

  tinydrm:
   - rework SPI support
   - improve MIPI-DBI support
   - moved to drm/tiny

  vkms:
   - rework CRC tracking

  dw-hdmi:
   - get_eld and i2s improvements

  gm12u320:
   - misc fixes

  meson:
   - global code cleanup
   - vpu feature detect

  omap:
   - alpha/pixel blend mode properties

  rcar-du:
   - misc fixes"

* tag 'drm-next-2019-09-18' of git://anongit.freedesktop.org/drm/drm: (2112 commits)
  drm/nouveau/bar/gm20b: Avoid BAR1 teardown during init
  drm/nouveau: Fix ordering between TTM and GEM release
  drm/nouveau/prime: Extend DMA reservation object lock
  drm/nouveau: Fix fallout from reservation object rework
  drm/nouveau/kms/nv50-: Don't create MSTMs for eDP connectors
  drm/i915: Use NOEVICT for first pass on attemping to pin a GGTT mmap
  drm/i915: to make vgpu ppgtt notificaiton as atomic operation
  drm/i915: Flush the existing fence before GGTT read/write
  drm/i915: Hold irq-off for the entire fake lock period
  drm/i915/gvt: update RING_START reg of vGPU when the context is submitted to i915
  drm/i915/gvt: update vgpu workload head pointer correctly
  drm/mcde: Fix DSI transfers
  drm/msm: Use the correct dma_sync calls harder
  drm/msm: remove unlikely() from WARN_ON() conditions
  drm/msm/dsi: Fix return value check for clk_get_parent
  drm/msm: add atomic traces
  drm/msm/dpu: async commit support
  drm/msm: async commit support
  drm/msm: split power control from prepare/complete_commit
  drm/msm: add kms->flush_commit()
  ...

1 files changed, 113 insertions, 7 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index c027e5e7713e..4d71537a960d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -32,6 +32,7 @@
 #include "psp_v3_1.h"
 #include "psp_v10_0.h"
 #include "psp_v11_0.h"
+#include "psp_v12_0.h"
 
 static void psp_set_funcs(struct amdgpu_device *adev);
 
@@ -53,13 +54,19 @@ static int psp_early_init(void *handle)
 		psp->autoload_supported = false;
 		break;
 	case CHIP_VEGA20:
+	case CHIP_ARCTURUS:
 		psp_v11_0_set_psp_funcs(psp);
 		psp->autoload_supported = false;
 		break;
 	case CHIP_NAVI10:
+	case CHIP_NAVI14:
+	case CHIP_NAVI12:
 		psp_v11_0_set_psp_funcs(psp);
 		psp->autoload_supported = true;
 		break;
+	case CHIP_RENOIR:
+		psp_v12_0_set_psp_funcs(psp);
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -137,8 +144,7 @@ psp_cmd_submit_buf(struct psp_context *psp,
 	memcpy(psp->cmd_buf_mem, cmd, sizeof(struct psp_gfx_cmd_resp));
 
 	index = atomic_inc_return(&psp->fence_value);
-	ret = psp_cmd_submit(psp, ucode, psp->cmd_buf_mc_addr,
-			     fence_mc_addr, index);
+	ret = psp_cmd_submit(psp, psp->cmd_buf_mc_addr, fence_mc_addr, index);
 	if (ret) {
 		atomic_dec(&psp->fence_value);
 		mutex_unlock(&psp->mutex);
@@ -162,8 +168,8 @@ psp_cmd_submit_buf(struct psp_context *psp,
 		if (ucode)
 			DRM_WARN("failed to load ucode id (%d) ",
 				  ucode->ucode_id);
-		DRM_WARN("psp command failed and response status is (%d)\n",
-			  psp->cmd_buf_mem->resp.status);
+		DRM_WARN("psp command failed and response status is (0x%X)\n",
+			  psp->cmd_buf_mem->resp.status & GFX_CMD_STATUS_MASK);
 		if (!timeout) {
 			mutex_unlock(&psp->mutex);
 			return -EINVAL;
@@ -233,6 +239,8 @@ static int psp_tmr_init(struct psp_context *psp)
 {
 	int ret;
 	int tmr_size;
+	void *tmr_buf;
+	void **pptr;
 
 	/*
 	 * According to HW engineer, they prefer the TMR address be "naturally
@@ -255,9 +263,10 @@ static int psp_tmr_init(struct psp_context *psp)
 		}
 	}
 
+	pptr = amdgpu_sriov_vf(psp->adev) ? &tmr_buf : NULL;
 	ret = amdgpu_bo_create_kernel(psp->adev, tmr_size, PSP_TMR_SIZE,
 				      AMDGPU_GEM_DOMAIN_VRAM,
-				      &psp->tmr_bo, &psp->tmr_mc_addr, &psp->tmr_buf);
+				      &psp->tmr_bo, &psp->tmr_mc_addr, pptr);
 
 	return ret;
 }
@@ -831,7 +840,6 @@ static int psp_hw_start(struct psp_context *psp)
 				"XGMI: Failed to initialize XGMI session\n");
 	}
 
-
 	if (psp->adev->psp.ta_fw) {
 		ret = psp_ras_initialize(psp);
 		if (ret)
@@ -852,6 +860,24 @@ static int psp_get_fw_type(struct amdgpu_firmware_info *ucode,
 	case AMDGPU_UCODE_ID_SDMA1:
 		*type = GFX_FW_TYPE_SDMA1;
 		break;
+	case AMDGPU_UCODE_ID_SDMA2:
+		*type = GFX_FW_TYPE_SDMA2;
+		break;
+	case AMDGPU_UCODE_ID_SDMA3:
+		*type = GFX_FW_TYPE_SDMA3;
+		break;
+	case AMDGPU_UCODE_ID_SDMA4:
+		*type = GFX_FW_TYPE_SDMA4;
+		break;
+	case AMDGPU_UCODE_ID_SDMA5:
+		*type = GFX_FW_TYPE_SDMA5;
+		break;
+	case AMDGPU_UCODE_ID_SDMA6:
+		*type = GFX_FW_TYPE_SDMA6;
+		break;
+	case AMDGPU_UCODE_ID_SDMA7:
+		*type = GFX_FW_TYPE_SDMA7;
+		break;
 	case AMDGPU_UCODE_ID_CP_CE:
 		*type = GFX_FW_TYPE_CP_CE;
 		break;
@@ -920,6 +946,60 @@ static int psp_get_fw_type(struct amdgpu_firmware_info *ucode,
 	return 0;
 }
 
+static void psp_print_fw_hdr(struct psp_context *psp,
+			     struct amdgpu_firmware_info *ucode)
+{
+	struct amdgpu_device *adev = psp->adev;
+	const struct sdma_firmware_header_v1_0 *sdma_hdr =
+		(const struct sdma_firmware_header_v1_0 *)
+		adev->sdma.instance[ucode->ucode_id - AMDGPU_UCODE_ID_SDMA0].fw->data;
+	const struct gfx_firmware_header_v1_0 *ce_hdr =
+		(const struct gfx_firmware_header_v1_0 *)adev->gfx.ce_fw->data;
+	const struct gfx_firmware_header_v1_0 *pfp_hdr =
+		(const struct gfx_firmware_header_v1_0 *)adev->gfx.pfp_fw->data;
+	const struct gfx_firmware_header_v1_0 *me_hdr =
+		(const struct gfx_firmware_header_v1_0 *)adev->gfx.me_fw->data;
+	const struct gfx_firmware_header_v1_0 *mec_hdr =
+		(const struct gfx_firmware_header_v1_0 *)adev->gfx.mec_fw->data;
+	const struct rlc_firmware_header_v2_0 *rlc_hdr =
+		(const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data;
+	const struct smc_firmware_header_v1_0 *smc_hdr =
+		(const struct smc_firmware_header_v1_0 *)adev->pm.fw->data;
+
+	switch (ucode->ucode_id) {
+	case AMDGPU_UCODE_ID_SDMA0:
+	case AMDGPU_UCODE_ID_SDMA1:
+	case AMDGPU_UCODE_ID_SDMA2:
+	case AMDGPU_UCODE_ID_SDMA3:
+	case AMDGPU_UCODE_ID_SDMA4:
+	case AMDGPU_UCODE_ID_SDMA5:
+	case AMDGPU_UCODE_ID_SDMA6:
+	case AMDGPU_UCODE_ID_SDMA7:
+		amdgpu_ucode_print_sdma_hdr(&sdma_hdr->header);
+		break;
+	case AMDGPU_UCODE_ID_CP_CE:
+		amdgpu_ucode_print_gfx_hdr(&ce_hdr->header);
+		break;
+	case AMDGPU_UCODE_ID_CP_PFP:
+		amdgpu_ucode_print_gfx_hdr(&pfp_hdr->header);
+		break;
+	case AMDGPU_UCODE_ID_CP_ME:
+		amdgpu_ucode_print_gfx_hdr(&me_hdr->header);
+		break;
+	case AMDGPU_UCODE_ID_CP_MEC1:
+		amdgpu_ucode_print_gfx_hdr(&mec_hdr->header);
+		break;
+	case AMDGPU_UCODE_ID_RLC_G:
+		amdgpu_ucode_print_rlc_hdr(&rlc_hdr->header);
+		break;
+	case AMDGPU_UCODE_ID_SMC:
+		amdgpu_ucode_print_smc_hdr(&smc_hdr->header);
+		break;
+	default:
+		break;
+	}
+}
+
 static int psp_prep_load_ip_fw_cmd_buf(struct amdgpu_firmware_info *ucode,
 				       struct psp_gfx_cmd_resp *cmd)
 {
@@ -980,17 +1060,31 @@ out:
 		if (ucode->ucode_id == AMDGPU_UCODE_ID_SMC &&
 		    (psp_smu_reload_quirk(psp) || psp->autoload_supported))
 			continue;
+
 		if (amdgpu_sriov_vf(adev) &&
 		   (ucode->ucode_id == AMDGPU_UCODE_ID_SDMA0
 		    || ucode->ucode_id == AMDGPU_UCODE_ID_SDMA1
+		    || ucode->ucode_id == AMDGPU_UCODE_ID_SDMA2
+		    || ucode->ucode_id == AMDGPU_UCODE_ID_SDMA3
+		    || ucode->ucode_id == AMDGPU_UCODE_ID_SDMA4
+		    || ucode->ucode_id == AMDGPU_UCODE_ID_SDMA5
+		    || ucode->ucode_id == AMDGPU_UCODE_ID_SDMA6
+		    || ucode->ucode_id == AMDGPU_UCODE_ID_SDMA7
 		    || ucode->ucode_id == AMDGPU_UCODE_ID_RLC_G))
 			/*skip ucode loading in SRIOV VF */
 			continue;
+
 		if (psp->autoload_supported &&
 		    (ucode->ucode_id == AMDGPU_UCODE_ID_CP_MEC1_JT ||
 		     ucode->ucode_id == AMDGPU_UCODE_ID_CP_MEC2_JT))
 			/* skip mec JT when autoload is enabled */
 			continue;
+		/* Renoir only needs to load mec jump table one time */
+		if (adev->asic_type == CHIP_RENOIR &&
+		    ucode->ucode_id == AMDGPU_UCODE_ID_CP_MEC2_JT)
+			continue;
+
+		psp_print_fw_hdr(psp, ucode);
 
 		ret = psp_execute_np_fw_load(psp, ucode);
 		if (ret)
@@ -1115,6 +1209,8 @@ static int psp_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	struct psp_context *psp = &adev->psp;
+	void *tmr_buf;
+	void **pptr;
 
 	if (adev->gmc.xgmi.num_physical_nodes > 1 &&
 	    psp->xgmi_context.initialized == 1)
@@ -1125,7 +1221,8 @@ static int psp_hw_fini(void *handle)
 
 	psp_ring_destroy(psp, PSP_RING_TYPE__KM);
 
-	amdgpu_bo_free_kernel(&psp->tmr_bo, &psp->tmr_mc_addr, &psp->tmr_buf);
+	pptr = amdgpu_sriov_vf(psp->adev) ? &tmr_buf : NULL;
+	amdgpu_bo_free_kernel(&psp->tmr_bo, &psp->tmr_mc_addr, pptr);
 	amdgpu_bo_free_kernel(&psp->fw_pri_bo,
 			      &psp->fw_pri_mc_addr, &psp->fw_pri_buf);
 	amdgpu_bo_free_kernel(&psp->fence_buf_bo,
@@ -1329,3 +1426,12 @@ const struct amdgpu_ip_block_version psp_v11_0_ip_block =
 	.rev = 0,
 	.funcs = &psp_ip_funcs,
 };
+
+const struct amdgpu_ip_block_version psp_v12_0_ip_block =
+{
+	.type = AMD_IP_BLOCK_TYPE_PSP,
+	.major = 12,
+	.minor = 0,
+	.rev = 0,
+	.funcs = &psp_ip_funcs,
+};