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, 78 insertions, 36 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index d11eba09eadd..65aae75f80fd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -25,7 +25,7 @@
 #include "amdgpu.h"
 #include "amdgpu_xgmi.h"
 #include "amdgpu_smu.h"
-
+#include "df/df_3_6_offset.h"
 
 static DEFINE_MUTEX(xgmi_mutex);
 
@@ -131,9 +131,37 @@ static ssize_t amdgpu_xgmi_show_device_id(struct device *dev,
 
 }
 
+#define AMDGPU_XGMI_SET_FICAA(o)	((o) | 0x456801)
+static ssize_t amdgpu_xgmi_show_error(struct device *dev,
+				      struct device_attribute *attr,
+				      char *buf)
+{
+	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = ddev->dev_private;
+	uint32_t ficaa_pie_ctl_in, ficaa_pie_status_in;
+	uint64_t fica_out;
+	unsigned int error_count = 0;
+
+	ficaa_pie_ctl_in = AMDGPU_XGMI_SET_FICAA(0x200);
+	ficaa_pie_status_in = AMDGPU_XGMI_SET_FICAA(0x208);
 
-static DEVICE_ATTR(xgmi_device_id, S_IRUGO, amdgpu_xgmi_show_device_id, NULL);
+	fica_out = adev->df_funcs->get_fica(adev, ficaa_pie_ctl_in);
+	if (fica_out != 0x1f)
+		pr_err("xGMI error counters not enabled!\n");
+
+	fica_out = adev->df_funcs->get_fica(adev, ficaa_pie_status_in);
+
+	if ((fica_out & 0xffff) == 2)
+		error_count = ((fica_out >> 62) & 0x1) + (fica_out >> 63);
 
+	adev->df_funcs->set_fica(adev, ficaa_pie_status_in, 0, 0);
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", error_count);
+}
+
+
+static DEVICE_ATTR(xgmi_device_id, S_IRUGO, amdgpu_xgmi_show_device_id, NULL);
+static DEVICE_ATTR(xgmi_error, S_IRUGO, amdgpu_xgmi_show_error, NULL);
 
 static int amdgpu_xgmi_sysfs_add_dev_info(struct amdgpu_device *adev,
 					 struct amdgpu_hive_info *hive)
@@ -148,6 +176,12 @@ static int amdgpu_xgmi_sysfs_add_dev_info(struct amdgpu_device *adev,
 		return ret;
 	}
 
+	/* Create xgmi error file */
+	ret = device_create_file(adev->dev, &dev_attr_xgmi_error);
+	if (ret)
+		pr_err("failed to create xgmi_error\n");
+
+
 	/* Create sysfs link to hive info folder on the first device */
 	if (adev != hive->adev) {
 		ret = sysfs_create_link(&adev->dev->kobj, hive->kobj,
@@ -248,7 +282,7 @@ int amdgpu_xgmi_set_pstate(struct amdgpu_device *adev, int pstate)
 
 	dev_dbg(adev->dev, "Set xgmi pstate %d.\n", pstate);
 
-	if (is_support_sw_smu(adev))
+	if (is_support_sw_smu_xgmi(adev))
 		ret = smu_set_xgmi_pstate(&adev->smu, pstate);
 	if (ret)
 		dev_err(adev->dev,
@@ -296,23 +330,28 @@ int amdgpu_xgmi_add_device(struct amdgpu_device *adev)
 	struct amdgpu_xgmi	*entry;
 	struct amdgpu_device *tmp_adev = NULL;
 
-	int count = 0, ret = -EINVAL;
+	int count = 0, ret = 0;
 
 	if (!adev->gmc.xgmi.supported)
 		return 0;
 
-	ret = psp_xgmi_get_node_id(&adev->psp, &adev->gmc.xgmi.node_id);
-	if (ret) {
-		dev_err(adev->dev,
-			"XGMI: Failed to get node id\n");
-		return ret;
-	}
+	if (amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_PSP)) {
+		ret = psp_xgmi_get_hive_id(&adev->psp, &adev->gmc.xgmi.hive_id);
+		if (ret) {
+			dev_err(adev->dev,
+				"XGMI: Failed to get hive id\n");
+			return ret;
+		}
 
-	ret = psp_xgmi_get_hive_id(&adev->psp, &adev->gmc.xgmi.hive_id);
-	if (ret) {
-		dev_err(adev->dev,
-			"XGMI: Failed to get hive id\n");
-		return ret;
+		ret = psp_xgmi_get_node_id(&adev->psp, &adev->gmc.xgmi.node_id);
+		if (ret) {
+			dev_err(adev->dev,
+				"XGMI: Failed to get node id\n");
+			return ret;
+		}
+	} else {
+		adev->gmc.xgmi.hive_id = 16;
+		adev->gmc.xgmi.node_id = adev->gmc.xgmi.physical_node_id + 16;
 	}
 
 	hive = amdgpu_get_xgmi_hive(adev, 1);
@@ -332,29 +371,32 @@ int amdgpu_xgmi_add_device(struct amdgpu_device *adev)
 	top_info->num_nodes = count;
 	hive->number_devices = count;
 
-	list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head) {
-		/* update node list for other device in the hive */
-		if (tmp_adev != adev) {
-			top_info = &tmp_adev->psp.xgmi_context.top_info;
-			top_info->nodes[count - 1].node_id = adev->gmc.xgmi.node_id;
-			top_info->num_nodes = count;
+	if (amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_PSP)) {
+		list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head) {
+			/* update node list for other device in the hive */
+			if (tmp_adev != adev) {
+				top_info = &tmp_adev->psp.xgmi_context.top_info;
+				top_info->nodes[count - 1].node_id =
+					adev->gmc.xgmi.node_id;
+				top_info->num_nodes = count;
+			}
+			ret = amdgpu_xgmi_update_topology(hive, tmp_adev);
+			if (ret)
+				goto exit;
 		}
-		ret = amdgpu_xgmi_update_topology(hive, tmp_adev);
-		if (ret)
-			goto exit;
-	}
 
-	/* get latest topology info for each device from psp */
-	list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head) {
-		ret = psp_xgmi_get_topology_info(&tmp_adev->psp, count,
-				&tmp_adev->psp.xgmi_context.top_info);
-		if (ret) {
-			dev_err(tmp_adev->dev,
-				"XGMI: Get topology failure on device %llx, hive %llx, ret %d",
-				tmp_adev->gmc.xgmi.node_id,
-				tmp_adev->gmc.xgmi.hive_id, ret);
-			/* To do : continue with some node failed or disable the whole hive */
-			goto exit;
+		/* get latest topology info for each device from psp */
+		list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head) {
+			ret = psp_xgmi_get_topology_info(&tmp_adev->psp, count,
+					&tmp_adev->psp.xgmi_context.top_info);
+			if (ret) {
+				dev_err(tmp_adev->dev,
+					"XGMI: Get topology failure on device %llx, hive %llx, ret %d",
+					tmp_adev->gmc.xgmi.node_id,
+					tmp_adev->gmc.xgmi.hive_id, ret);
+				/* To do : continue with some node failed or disable the whole hive */
+				goto exit;
+			}
 		}
 	}