Merge tag 'drm-next-2019-03-06' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "This is the main drm pull request for the 5.1 merge window.

  The big changes I'd highlight are:
   - nouveau has HMM support now, there is finally an in-tree user so we
     can quieten down the rip it out people.
   - i915 now enables fastboot by default on Skylake+
   - Displayport Multistream support has been refactored and should
     hopefully be more reliable.

  Core:
   - header cleanups aiming towards removing drmP.h
   - dma-buf fence seqnos to 64-bits
   - common helper for DP mst hotplug for radeon,i915,amdgpu + new
     refcounting scheme
   - MST i2c improvements
   - drm_syncobj_cb removal
   - ARM FB compression fourcc
   - P010 + P016 fourcc
   - allwinner tiled format modifier
   - i2c over aux I2C_M_STOP support
   - DRM_AUTH handling fixes

  TTM:
   - ref/unref renaming

  New driver:
   - ARM komeda display driver

  scheduler:
   - refactor mirror list handling
   - rework hw fence processing
   - 0 run queue entity fix

  bridge:
   - TI DS90C185 LVDS bridge
   - thc631lvdm83d bridge improvements
   - cadence + allwinner DSI ported to generic phy

  panels:
   - Sitronix ST7701 panel
   - Kingdisplay KD097D04
   - LeMaker BL035-RGB-002
   - PDA 91-00156-A0
   - Innolux EE101IA-01D

  i915:
   - Enable fastboot by default on SKL+/VLV/CHV
   - Export RPCS configuration for ICL media driver
   - Coffelake PCI ID
   - CNL clocks setup fixes
   - ACPI/PMIC support for MIPI/DSI
   - Per-engine WA init for all engines
   - Shrinker locking fixes
   - Kerneldoc updates
   - Lots of ring improvements and reset fixes
   - Coffeelake GVT Support
   - VFIO GVT EDID Region support
   - runtime PM wakeref tracking
   - ILK->IVB primary plane enable delays
   - userptr mutex locking fixes
   - DSI fixes
   - LVDS/TV cleanups
   - HW readout fixes
   - LUT robustness fixes
   - ICL display and watermark fixes
   - gem mmap race fix

  amdgpu:
   - add scheduled dependencies interface
   - DCC on scanout surfaces
   - vega10/20 BACO support
   - Multiple IH rings on soc15
   - XGMI locking fixes
   - DC i2c/aux cleanups
   - runtime SMU debug interface
   - Kexec improvmeents
   - SR-IOV fixes
   - DC freesync + ABM fixes
   - GDS fixes
   - GPUVM fixes
   - vega20 PCIE DPM switching fixes
   - Context priority handling fixes

  radeon:
   - fix missing break in evergreen parser

  nouveau:
   - SVM support via HMM

  msm:
   - QCOM Compressed modifier support

  exynos:
   - s5pv210 rotator support

  imx:
   - zpos property support
   - pending update fixes

  v3d:
   - cache flush improvments

  vc4:
   - reflection support
   - HDMI overscan support

  tegra:
   - CEC refactoring
   - HDMI audio fixes
   - Tegra186 prep work
   - SOR crossbar device tree fixes

  sun4i:
   - implicit fencing support
   - YUV and scalar support improvements
   - A23 support
   - tiling fixes

  atmel-hlcdc:
   - clipping and rotation property fixes

  qxl:
   - BO and PRIME improvements
   - generic fbdev emulation

  dw-hdmi:
   - HDMI 2.0 2160p
   - YUV420 ouput

  rockchip:
   - implicit fencing support
   - reflection proerties

  virtio-gpu:
   - use generic fbdev emulation

  tilcdc:
   - cpufreq vs crtc init fix

  rcar-du:
   - R8A774C0 support
   - D3/E3 RGB output routing fixes and DPAD0 support
   - RA87744 LVDS support

  bochs:
   - atomic and generic fbdev emulation
   - ID mismatch error on bochs load

  meson:
   - remove firmware fbs"

* tag 'drm-next-2019-03-06' of git://anongit.freedesktop.org/drm/drm: (1130 commits)
  drm/amd/display: Use vrr friendly pageflip throttling in DC.
  drm/imx: only send commit done event when all state has been applied
  drm/imx: allow building under COMPILE_TEST
  drm/imx: imx-tve: depend on COMMON_CLK
  drm/imx: ipuv3-plane: add zpos property
  drm/imx: ipuv3-plane: add function to query atomic update status
  gpu: ipu-v3: prg: add function to get channel configure status
  gpu: ipu-v3: pre: add double buffer status readback
  drm/amdgpu: Bump amdgpu version for context priority override.
  drm/amdgpu/powerplay: fix typo in BACO header guards
  drm/amdgpu/powerplay: fix return codes in BACO code
  drm/amdgpu: add missing license on baco files
  drm/bochs: Fix the ID mismatch error
  drm/nouveau/dmem: use dma addresses during migration copies
  drm/nouveau/dmem: use physical vram addresses during migration copies
  drm/nouveau/dmem: extend copy function to allow direct use of physical addresses
  drm/nouveau/svm: new ioctl to migrate process memory to GPU memory
  drm/nouveau/dmem: device memory helpers for SVM
  drm/nouveau/svm: initial support for shared virtual memory
  drm/nouveau: prepare for enabling svm with existing userspace interfaces
  ...

1 files changed, 35 insertions, 19 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index 8a8bc60cb6b4..407dd16cc35c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -40,26 +40,40 @@ void *amdgpu_xgmi_hive_try_lock(struct amdgpu_hive_info *hive)
 	return &hive->device_list;
 }
 
-struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev)
+struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev, int lock)
 {
 	int i;
 	struct amdgpu_hive_info *tmp;
 
 	if (!adev->gmc.xgmi.hive_id)
 		return NULL;
+
+	mutex_lock(&xgmi_mutex);
+
 	for (i = 0 ; i < hive_count; ++i) {
 		tmp = &xgmi_hives[i];
-		if (tmp->hive_id == adev->gmc.xgmi.hive_id)
+		if (tmp->hive_id == adev->gmc.xgmi.hive_id) {
+			if (lock)
+				mutex_lock(&tmp->hive_lock);
+			mutex_unlock(&xgmi_mutex);
 			return tmp;
+		}
 	}
-	if (i >= AMDGPU_MAX_XGMI_HIVE)
+	if (i >= AMDGPU_MAX_XGMI_HIVE) {
+		mutex_unlock(&xgmi_mutex);
 		return NULL;
+	}
 
 	/* initialize new hive if not exist */
 	tmp = &xgmi_hives[hive_count++];
 	tmp->hive_id = adev->gmc.xgmi.hive_id;
 	INIT_LIST_HEAD(&tmp->device_list);
 	mutex_init(&tmp->hive_lock);
+	mutex_init(&tmp->reset_lock);
+	if (lock)
+		mutex_lock(&tmp->hive_lock);
+
+	mutex_unlock(&xgmi_mutex);
 
 	return tmp;
 }
@@ -77,10 +91,6 @@ int amdgpu_xgmi_update_topology(struct amdgpu_hive_info *hive, struct amdgpu_dev
 			"XGMI: Set topology failure on device %llx, hive %llx, ret %d",
 			adev->gmc.xgmi.node_id,
 			adev->gmc.xgmi.hive_id, ret);
-	else
-		dev_info(adev->dev, "XGMI: Set topology for node %d, hive 0x%llx.\n",
-			 adev->gmc.xgmi.physical_node_id,
-				 adev->gmc.xgmi.hive_id);
 
 	return ret;
 }
@@ -111,10 +121,14 @@ int amdgpu_xgmi_add_device(struct amdgpu_device *adev)
 		return ret;
 	}
 
-	mutex_lock(&xgmi_mutex);
-	hive = amdgpu_get_xgmi_hive(adev);
-	if (!hive)
+	hive = amdgpu_get_xgmi_hive(adev, 1);
+	if (!hive) {
+		ret = -EINVAL;
+		dev_err(adev->dev,
+			"XGMI: node 0x%llx, can not match hive 0x%llx in the hive list.\n",
+			adev->gmc.xgmi.node_id, adev->gmc.xgmi.hive_id);
 		goto exit;
+	}
 
 	hive_topology = &hive->topology_info;
 
@@ -142,8 +156,11 @@ int amdgpu_xgmi_add_device(struct amdgpu_device *adev)
 			break;
 	}
 
+	dev_info(adev->dev, "XGMI: Add node %d, hive 0x%llx.\n",
+		 adev->gmc.xgmi.physical_node_id, adev->gmc.xgmi.hive_id);
+
+	mutex_unlock(&hive->hive_lock);
 exit:
-	mutex_unlock(&xgmi_mutex);
 	return ret;
 }
 
@@ -154,15 +171,14 @@ void amdgpu_xgmi_remove_device(struct amdgpu_device *adev)
 	if (!adev->gmc.xgmi.supported)
 		return;
 
-	mutex_lock(&xgmi_mutex);
-
-	hive = amdgpu_get_xgmi_hive(adev);
+	hive = amdgpu_get_xgmi_hive(adev, 1);
 	if (!hive)
-		goto exit;
+		return;
 
-	if (!(hive->number_devices--))
+	if (!(hive->number_devices--)) {
 		mutex_destroy(&hive->hive_lock);
-
-exit:
-	mutex_unlock(&xgmi_mutex);
+		mutex_destroy(&hive->reset_lock);
+	} else {
+		mutex_unlock(&hive->hive_lock);
+	}
 }