Merge tag 'drm-next-2019-11-27' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "Lots of stuff in here, though it hasn't been too insane this merge
  apart from dealing with the security fun.

  uapi:
   - export different colorspace properties on DP vs HDMI
   - new fourcc for ARM 16x16 block format
   - syncobj: allow querying last submitted timeline value
   - DRM_FORMAT_BIG_ENDIAN defined as unsigned

  core:
   - allow using gem vma manager in ttm
   - connector/encoder/bridge doc fixes
   - allow more than 3 encoders for a connector
   - displayport mst suspend/resume reprobing support
   - vram lazy unmapping, uniform vram mm and gem vram
   - edid cleanups + AVI informframe bar info
   - displayport helpers - dpcd parser added

  dp_cec:
   - Allow a connector to be associated with a cec device

  ttm:
   - pipelining with no_gpu_wait fix
   - always keep BOs on the LRU

  sched:
   - allow free_job routine to sleep

  i915:
   - Block userptr from mappable GTT
   - i915 perf uapi versioning
   - OA stream dynamic reconfiguration
   - make context persistence optional
   - introduce DRM_I915_UNSTABLE Kconfig
   - add fake lmem testing under unstable
   - BT.2020 support for DP MSA
   - struct mutex elimination
   - Tigerlake display/PLL/power management improvements
   - Jasper Lake PCH support
   - refactor PMU for multiple GPUs
   - Icelake firmware update
   - Split out vga + switcheroo code

  amdgpu:
   - implement dma-buf import/export without helpers
   - vega20 RAS enablement
   - DC i2c over aux fixes
   - renoir GPU reset
   - DC HDCP support
   - BACO support for CI/VI asics
   - MSI-X support
   - Arcturus EEPROM support
   - Arcturus VCN encode support
   - VCN dynamic powergating on RV/RV2

  amdkfd:
   - add navi12/14/renoir support to kfd

  radeon:
   - SI dpm fix ported from amdgpu
   - fix bad DMA on ppc platforms

  gma500:
   - memory leak fixes

  qxl:
   - convert to new gem mmap

  exynos:
   - build warning fix

  komeda:
   - add aclk sysfs attribute

  v3d:
   - userspace cleanup uapi change

  i810:
   - fix for underflow in dispatch ioctls

  ast:
   - refactor show_cursor

  mgag200:
   - refactor show_cursor

  arcgpu:
   - encoder finding improvements

  mediatek:
   - mipi_tx, dsi and partial crtc support for MT8183 SoC
   - rotation support

  meson:
   - add suspend/resume support

  omap:
   - misc refactors

  tegra:
   - DisplayPort support for Tegra 210, 186 and 194.
   - IOMMU-backed DMA API fixes

  panfrost:
   - fix lockdep issue
   - simplify devfreq integration

  rcar-du:
   - R8A774B1 SoC support
   - fixes for H2 ES2.0

  sun4i:
   - vcc-dsi regulator support

  virtio-gpu:
   - vmexit vs spinlock fix
   - move to gem shmem helpers
   - handle large command buffers with cma"

* tag 'drm-next-2019-11-27' of git://anongit.freedesktop.org/drm/drm: (1855 commits)
  drm/amdgpu: invalidate mmhub semaphore workaround in gmc9/gmc10
  drm/amdgpu: initialize vm_inv_eng0_sem for gfxhub and mmhub
  drm/amd/amdgpu/sriov skip RLCG s/r list for arcturus VF.
  drm/amd/amdgpu/sriov temporarily skip ras,dtm,hdcp for arcturus VF
  drm/amdgpu/gfx10: re-init clear state buffer after gpu reset
  merge fix for "ftrace: Rework event_create_dir()"
  drm/amdgpu: Update Arcturus golden registers
  drm/amdgpu/gfx10: fix out-of-bound mqd_backup array access
  drm/amdgpu/gfx10: explicitly wait for cp idle after halt/unhalt
  Revert "drm/amd/display: enable S/G for RAVEN chip"
  drm/amdgpu: disable gfxoff on original raven
  drm/amdgpu: remove experimental flag for Navi14
  drm/amdgpu: disable gfxoff when using register read interface
  drm/amdgpu/powerplay: properly set PP_GFXOFF_MASK (v2)
  drm/amdgpu: fix bad DMA from INTERRUPT_CNTL2
  drm/radeon: fix bad DMA from INTERRUPT_CNTL2
  drm/amd/display: Fix debugfs on MST connectors
  drm/amdgpu/nv: add asic func for fetching vbios from rom directly
  drm/amdgpu: put flush_delayed_work at first
  drm/amdgpu/vcn2.5: fix the enc loop with hw fini
  ...

1 files changed, 89 insertions, 3 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index 65aae75f80fd..61d13d8b7b20 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -25,6 +25,7 @@
 #include "amdgpu.h"
 #include "amdgpu_xgmi.h"
 #include "amdgpu_smu.h"
+#include "amdgpu_ras.h"
 #include "df/df_3_6_offset.h"
 
 static DEFINE_MUTEX(xgmi_mutex);
@@ -273,22 +274,55 @@ int amdgpu_xgmi_set_pstate(struct amdgpu_device *adev, int pstate)
 {
 	int ret = 0;
 	struct amdgpu_hive_info *hive = amdgpu_get_xgmi_hive(adev, 0);
+	struct amdgpu_device *tmp_adev;
+	bool update_hive_pstate = true;
+	bool is_high_pstate = pstate && adev->asic_type == CHIP_VEGA20;
 
 	if (!hive)
 		return 0;
 
-	if (hive->pstate == pstate)
-		return 0;
+	mutex_lock(&hive->hive_lock);
+
+	if (hive->pstate == pstate) {
+		adev->pstate = is_high_pstate ? pstate : adev->pstate;
+		goto out;
+	}
 
 	dev_dbg(adev->dev, "Set xgmi pstate %d.\n", pstate);
 
 	if (is_support_sw_smu_xgmi(adev))
 		ret = smu_set_xgmi_pstate(&adev->smu, pstate);
-	if (ret)
+	else if (adev->powerplay.pp_funcs &&
+		 adev->powerplay.pp_funcs->set_xgmi_pstate)
+		ret = adev->powerplay.pp_funcs->set_xgmi_pstate(adev->powerplay.pp_handle,
+								pstate);
+
+	if (ret) {
 		dev_err(adev->dev,
 			"XGMI: Set pstate failure on device %llx, hive %llx, ret %d",
 			adev->gmc.xgmi.node_id,
 			adev->gmc.xgmi.hive_id, ret);
+		goto out;
+	}
+
+	/* Update device pstate */
+	adev->pstate = pstate;
+
+	/*
+	 * Update the hive pstate only all devices of the hive
+	 * are in the same pstate
+	 */
+	list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head) {
+		if (tmp_adev->pstate != adev->pstate) {
+			update_hive_pstate = false;
+			break;
+		}
+	}
+	if (update_hive_pstate || is_high_pstate)
+		hive->pstate = pstate;
+
+out:
+	mutex_unlock(&hive->hive_lock);
 
 	return ret;
 }
@@ -363,6 +397,9 @@ int amdgpu_xgmi_add_device(struct amdgpu_device *adev)
 		goto exit;
 	}
 
+	/* Set default device pstate */
+	adev->pstate = -1;
+
 	top_info = &adev->psp.xgmi_context.top_info;
 
 	list_add_tail(&adev->gmc.xgmi.head, &hive->device_list);
@@ -437,3 +474,52 @@ void amdgpu_xgmi_remove_device(struct amdgpu_device *adev)
 		mutex_unlock(&hive->hive_lock);
 	}
 }
+
+int amdgpu_xgmi_ras_late_init(struct amdgpu_device *adev)
+{
+	int r;
+	struct ras_ih_if ih_info = {
+		.cb = NULL,
+	};
+	struct ras_fs_if fs_info = {
+		.sysfs_name = "xgmi_wafl_err_count",
+		.debugfs_name = "xgmi_wafl_err_inject",
+	};
+
+	if (!adev->gmc.xgmi.supported ||
+	    adev->gmc.xgmi.num_physical_nodes == 0)
+		return 0;
+
+	if (!adev->gmc.xgmi.ras_if) {
+		adev->gmc.xgmi.ras_if = kmalloc(sizeof(struct ras_common_if), GFP_KERNEL);
+		if (!adev->gmc.xgmi.ras_if)
+			return -ENOMEM;
+		adev->gmc.xgmi.ras_if->block = AMDGPU_RAS_BLOCK__XGMI_WAFL;
+		adev->gmc.xgmi.ras_if->type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE;
+		adev->gmc.xgmi.ras_if->sub_block_index = 0;
+		strcpy(adev->gmc.xgmi.ras_if->name, "xgmi_wafl");
+	}
+	ih_info.head = fs_info.head = *adev->gmc.xgmi.ras_if;
+	r = amdgpu_ras_late_init(adev, adev->gmc.xgmi.ras_if,
+				 &fs_info, &ih_info);
+	if (r || !amdgpu_ras_is_supported(adev, adev->gmc.xgmi.ras_if->block)) {
+		kfree(adev->gmc.xgmi.ras_if);
+		adev->gmc.xgmi.ras_if = NULL;
+	}
+
+	return r;
+}
+
+void amdgpu_xgmi_ras_fini(struct amdgpu_device *adev)
+{
+	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__XGMI_WAFL) &&
+			adev->gmc.xgmi.ras_if) {
+		struct ras_common_if *ras_if = adev->gmc.xgmi.ras_if;
+		struct ras_ih_if ih_info = {
+			.cb = NULL,
+		};
+
+		amdgpu_ras_late_fini(adev, ras_if, &ih_info);
+		kfree(ras_if);
+	}
+}