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, 71 insertions, 50 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 2dfaf158ef07..fe1d7368c1e6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -28,8 +28,6 @@
 #include <linux/module.h>
 #include <linux/dma-buf.h>
 
-const struct kgd2kfd_calls *kgd2kfd;
-
 static const unsigned int compute_vmid_bitmap = 0xFF00;
 
 /* Total memory size in system memory and all GPU VRAM. Used to
@@ -47,12 +45,9 @@ int amdgpu_amdkfd_init(void)
 	amdgpu_amdkfd_total_mem_size *= si.mem_unit;
 
 #ifdef CONFIG_HSA_AMD
-	ret = kgd2kfd_init(KFD_INTERFACE_VERSION, &kgd2kfd);
-	if (ret)
-		kgd2kfd = NULL;
+	ret = kgd2kfd_init();
 	amdgpu_amdkfd_gpuvm_init_mem_limits();
 #else
-	kgd2kfd = NULL;
 	ret = -ENOENT;
 #endif
 
@@ -61,17 +56,13 @@ int amdgpu_amdkfd_init(void)
 
 void amdgpu_amdkfd_fini(void)
 {
-	if (kgd2kfd)
-		kgd2kfd->exit();
+	kgd2kfd_exit();
 }
 
 void amdgpu_amdkfd_device_probe(struct amdgpu_device *adev)
 {
 	const struct kfd2kgd_calls *kfd2kgd;
 
-	if (!kgd2kfd)
-		return;
-
 	switch (adev->asic_type) {
 #ifdef CONFIG_DRM_AMDGPU_CIK
 	case CHIP_KAVERI:
@@ -98,8 +89,8 @@ void amdgpu_amdkfd_device_probe(struct amdgpu_device *adev)
 		return;
 	}
 
-	adev->kfd.dev = kgd2kfd->probe((struct kgd_dev *)adev,
-				       adev->pdev, kfd2kgd);
+	adev->kfd.dev = kgd2kfd_probe((struct kgd_dev *)adev,
+				      adev->pdev, kfd2kgd);
 
 	if (adev->kfd.dev)
 		amdgpu_amdkfd_total_mem_size += adev->gmc.real_vram_size;
@@ -140,7 +131,7 @@ static void amdgpu_doorbell_get_kfd_info(struct amdgpu_device *adev,
 
 void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
 {
-	int i, n;
+	int i;
 	int last_valid_bit;
 
 	if (adev->kfd.dev) {
@@ -151,7 +142,9 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
 			.gpuvm_size = min(adev->vm_manager.max_pfn
 					  << AMDGPU_GPU_PAGE_SHIFT,
 					  AMDGPU_GMC_HOLE_START),
-			.drm_render_minor = adev->ddev->render->index
+			.drm_render_minor = adev->ddev->render->index,
+			.sdma_doorbell_idx = adev->doorbell_index.sdma_engine,
+
 		};
 
 		/* this is going to have a few of the MSBs set that we need to
@@ -181,44 +174,29 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
 				&gpu_resources.doorbell_aperture_size,
 				&gpu_resources.doorbell_start_offset);
 
-		if (adev->asic_type < CHIP_VEGA10) {
-			kgd2kfd->device_init(adev->kfd.dev, &gpu_resources);
-			return;
-		}
-
-		n = (adev->asic_type < CHIP_VEGA20) ? 2 : 8;
-
-		for (i = 0; i < n; i += 2) {
-			/* On SOC15 the BIF is involved in routing
-			 * doorbells using the low 12 bits of the
-			 * address. Communicate the assignments to
-			 * KFD. KFD uses two doorbell pages per
-			 * process in case of 64-bit doorbells so we
-			 * can use each doorbell assignment twice.
-			 */
-			gpu_resources.sdma_doorbell[0][i] =
-				adev->doorbell_index.sdma_engine0 + (i >> 1);
-			gpu_resources.sdma_doorbell[0][i+1] =
-				adev->doorbell_index.sdma_engine0 + 0x200 + (i >> 1);
-			gpu_resources.sdma_doorbell[1][i] =
-				adev->doorbell_index.sdma_engine1 + (i >> 1);
-			gpu_resources.sdma_doorbell[1][i+1] =
-				adev->doorbell_index.sdma_engine1 + 0x200 + (i >> 1);
-		}
-		/* Doorbells 0x0e0-0ff and 0x2e0-2ff are reserved for
-		 * SDMA, IH and VCN. So don't use them for the CP.
+		/* Since SOC15, BIF starts to statically use the
+		 * lower 12 bits of doorbell addresses for routing
+		 * based on settings in registers like
+		 * SDMA0_DOORBELL_RANGE etc..
+		 * In order to route a doorbell to CP engine, the lower
+		 * 12 bits of its address has to be outside the range
+		 * set for SDMA, VCN, and IH blocks.
 		 */
-		gpu_resources.reserved_doorbell_mask = 0x1e0;
-		gpu_resources.reserved_doorbell_val  = 0x0e0;
+		if (adev->asic_type >= CHIP_VEGA10) {
+			gpu_resources.non_cp_doorbells_start =
+					adev->doorbell_index.first_non_cp;
+			gpu_resources.non_cp_doorbells_end =
+					adev->doorbell_index.last_non_cp;
+		}
 
-		kgd2kfd->device_init(adev->kfd.dev, &gpu_resources);
+		kgd2kfd_device_init(adev->kfd.dev, &gpu_resources);
 	}
 }
 
 void amdgpu_amdkfd_device_fini(struct amdgpu_device *adev)
 {
 	if (adev->kfd.dev) {
-		kgd2kfd->device_exit(adev->kfd.dev);
+		kgd2kfd_device_exit(adev->kfd.dev);
 		adev->kfd.dev = NULL;
 	}
 }
@@ -227,13 +205,13 @@ void amdgpu_amdkfd_interrupt(struct amdgpu_device *adev,
 		const void *ih_ring_entry)
 {
 	if (adev->kfd.dev)
-		kgd2kfd->interrupt(adev->kfd.dev, ih_ring_entry);
+		kgd2kfd_interrupt(adev->kfd.dev, ih_ring_entry);
 }
 
 void amdgpu_amdkfd_suspend(struct amdgpu_device *adev)
 {
 	if (adev->kfd.dev)
-		kgd2kfd->suspend(adev->kfd.dev);
+		kgd2kfd_suspend(adev->kfd.dev);
 }
 
 int amdgpu_amdkfd_resume(struct amdgpu_device *adev)
@@ -241,7 +219,7 @@ int amdgpu_amdkfd_resume(struct amdgpu_device *adev)
 	int r = 0;
 
 	if (adev->kfd.dev)
-		r = kgd2kfd->resume(adev->kfd.dev);
+		r = kgd2kfd_resume(adev->kfd.dev);
 
 	return r;
 }
@@ -251,7 +229,7 @@ int amdgpu_amdkfd_pre_reset(struct amdgpu_device *adev)
 	int r = 0;
 
 	if (adev->kfd.dev)
-		r = kgd2kfd->pre_reset(adev->kfd.dev);
+		r = kgd2kfd_pre_reset(adev->kfd.dev);
 
 	return r;
 }
@@ -261,7 +239,7 @@ int amdgpu_amdkfd_post_reset(struct amdgpu_device *adev)
 	int r = 0;
 
 	if (adev->kfd.dev)
-		r = kgd2kfd->post_reset(adev->kfd.dev);
+		r = kgd2kfd_post_reset(adev->kfd.dev);
 
 	return r;
 }
@@ -619,4 +597,47 @@ struct kfd2kgd_calls *amdgpu_amdkfd_gfx_9_0_get_functions(void)
 {
 	return NULL;
 }
+
+struct kfd_dev *kgd2kfd_probe(struct kgd_dev *kgd, struct pci_dev *pdev,
+			      const struct kfd2kgd_calls *f2g)
+{
+	return NULL;
+}
+
+bool kgd2kfd_device_init(struct kfd_dev *kfd,
+			 const struct kgd2kfd_shared_resources *gpu_resources)
+{
+	return false;
+}
+
+void kgd2kfd_device_exit(struct kfd_dev *kfd)
+{
+}
+
+void kgd2kfd_exit(void)
+{
+}
+
+void kgd2kfd_suspend(struct kfd_dev *kfd)
+{
+}
+
+int kgd2kfd_resume(struct kfd_dev *kfd)
+{
+	return 0;
+}
+
+int kgd2kfd_pre_reset(struct kfd_dev *kfd)
+{
+	return 0;
+}
+
+int kgd2kfd_post_reset(struct kfd_dev *kfd)
+{
+	return 0;
+}
+
+void kgd2kfd_interrupt(struct kfd_dev *kfd, const void *ih_ring_entry)
+{
+}
 #endif