Merge tag 'drm-for-v4.15' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "This is the main drm pull request for v4.15.

  Core:
   - Atomic object lifetime fixes
   - Atomic iterator improvements
   - Sparse/smatch fixes
   - Legacy kms ioctls to be interruptible
   - EDID override improvements
   - fb/gem helper cleanups
   - Simple outreachy patches
   - Documentation improvements
   - Fix dma-buf rcu races
   - DRM mode object leasing for improving VR use cases.
   - vgaarb improvements for non-x86 platforms.

  New driver:
   - tve200: Faraday Technology TVE200 block.

     This "TV Encoder" encodes a ITU-T BT.656 stream and can be found in
     the StorLink SL3516 (later Cortina Systems CS3516) as well as the
     Grain Media GM8180.

  New bridges:
   - SiI9234 support

  New panels:
   - S6E63J0X03, OTM8009A, Seiko 43WVF1G, 7" rpi touch panel, Toshiba
     LT089AC19000, Innolux AT043TN24

  i915:
   - Remove Coffeelake from alpha support
   - Cannonlake workarounds
   - Infoframe refactoring for DisplayPort
   - VBT updates
   - DisplayPort vswing/emph/buffer translation refactoring
   - CCS fixes
   - Restore GPU clock boost on missed vblanks
   - Scatter list updates for userptr allocations
   - Gen9+ transition watermarks
   - Display IPC (Isochronous Priority Control)
   - Private PAT management
   - GVT: improved error handling and pci config sanitizing
   - Execlist refactoring
   - Transparent Huge Page support
   - User defined priorities support
   - HuC/GuC firmware refactoring
   - DP MST fixes
   - eDP power sequencing fixes
   - Use RCU instead of stop_machine
   - PSR state tracking support
   - Eviction fixes
   - BDW DP aux channel timeout fixes
   - LSPCON fixes
   - Cannonlake PLL fixes

  amdgpu:
   - Per VM BO support
   - Powerplay cleanups
   - CI powerplay support
   - PASID mgr for kfd
   - SR-IOV fixes
   - initial GPU reset for vega10
   - Prime mmap support
   - TTM updates
   - Clock query interface for Raven
   - Fence to handle ioctl
   - UVD encode ring support on Polaris
   - Transparent huge page DMA support
   - Compute LRU pipe tweaks
   - BO flag to allow buffers to opt out of implicit sync
   - CTX priority setting API
   - VRAM lost infrastructure plumbing

  qxl:
   - fix flicker since atomic rework

  amdkfd:
   - Further improvements from internal AMD tree
   - Usermode events
   - Drop radeon support

  nouveau:
   - Pascal temperature sensor support
   - Improved BAR2 handling
   - MMU rework to support Pascal MMU

  exynos:
   - Improved HDMI/mixer support
   - HDMI audio interface support

  tegra:
   - Prep work for tegra186
   - Cleanup/fixes

  msm:
   - Preemption support for a5xx
   - Display fixes for 8x96 (snapdragon 820)
   - Async cursor plane fixes
   - FW loading rework
   - GPU debugging improvements

  vc4:
   - Prep for DSI panels
   - fix T-format tiling scanout
   - New madvise ioctl

  Rockchip:
   - LVDS support

  omapdrm:
   - omap4 HDMI CEC support

  etnaviv:
   - GPU performance counters groundwork

  sun4i:
   - refactor driver load + TCON backend
   - HDMI improvements
   - A31 support
   - Misc fixes

  udl:
   - Probe/EDID read fixes.

  tilcdc:
   - Misc fixes.

  pl111:
   - Support more variants

  adv7511:
   - Improve EDID handling.
   - HDMI CEC support

  sii8620:
   - Add remote control support"

* tag 'drm-for-v4.15' of git://people.freedesktop.org/~airlied/linux: (1480 commits)
  drm/rockchip: analogix_dp: Use mutex rather than spinlock
  drm/mode_object: fix documentation for object lookups.
  drm/i915: Reorder context-close to avoid calling i915_vma_close() under RCU
  drm/i915: Move init_clock_gating() back to where it was
  drm/i915: Prune the reservation shared fence array
  drm/i915: Idle the GPU before shinking everything
  drm/i915: Lock llist_del_first() vs llist_del_all()
  drm/i915: Calculate ironlake intermediate watermarks correctly, v2.
  drm/i915: Disable lazy PPGTT page table optimization for vGPU
  drm/i915/execlists: Remove the priority "optimisation"
  drm/i915: Filter out spurious execlists context-switch interrupts
  drm/amdgpu: use irq-safe lock for kiq->ring_lock
  drm/amdgpu: bypass lru touch for KIQ ring submission
  drm/amdgpu: Potential uninitialized variable in amdgpu_vm_update_directories()
  drm/amdgpu: potential uninitialized variable in amdgpu_vce_ring_parse_cs()
  drm/amd/powerplay: initialize a variable before using it
  drm/amd/powerplay: suppress KASAN out of bounds warning in vega10_populate_all_memory_levels
  drm/amd/amdgpu: fix evicted VRAM bo adjudgement condition
  drm/vblank: Tune drm_crtc_accurate_vblank_count() WARN down to a debug
  drm/rockchip: add CONFIG_OF dependency for lvds
  ...

1 files changed, 130 insertions, 31 deletions

diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 595630d1fb9e..8d4a5be3b913 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -111,33 +111,119 @@ nouveau_name(struct drm_device *dev)
 		return nouveau_platform_name(to_platform_device(dev->dev));
 }
 
+static inline bool
+nouveau_cli_work_ready(struct dma_fence *fence, bool wait)
+{
+	if (!dma_fence_is_signaled(fence)) {
+		if (!wait)
+			return false;
+		WARN_ON(dma_fence_wait_timeout(fence, false, 2 * HZ) <= 0);
+	}
+	dma_fence_put(fence);
+	return true;
+}
+
+static void
+nouveau_cli_work_flush(struct nouveau_cli *cli, bool wait)
+{
+	struct nouveau_cli_work *work, *wtmp;
+	mutex_lock(&cli->lock);
+	list_for_each_entry_safe(work, wtmp, &cli->worker, head) {
+		if (!work->fence || nouveau_cli_work_ready(work->fence, wait)) {
+			list_del(&work->head);
+			work->func(work);
+		}
+	}
+	mutex_unlock(&cli->lock);
+}
+
+static void
+nouveau_cli_work_fence(struct dma_fence *fence, struct dma_fence_cb *cb)
+{
+	struct nouveau_cli_work *work = container_of(cb, typeof(*work), cb);
+	schedule_work(&work->cli->work);
+}
+
+void
+nouveau_cli_work_queue(struct nouveau_cli *cli, struct dma_fence *fence,
+		       struct nouveau_cli_work *work)
+{
+	work->fence = dma_fence_get(fence);
+	work->cli = cli;
+	mutex_lock(&cli->lock);
+	list_add_tail(&work->head, &cli->worker);
+	mutex_unlock(&cli->lock);
+	if (dma_fence_add_callback(fence, &work->cb, nouveau_cli_work_fence))
+		nouveau_cli_work_fence(fence, &work->cb);
+}
+
+static void
+nouveau_cli_work(struct work_struct *w)
+{
+	struct nouveau_cli *cli = container_of(w, typeof(*cli), work);
+	nouveau_cli_work_flush(cli, false);
+}
+
 static void
 nouveau_cli_fini(struct nouveau_cli *cli)
 {
-	nvkm_vm_ref(NULL, &nvxx_client(&cli->base)->vm, NULL);
+	nouveau_cli_work_flush(cli, true);
 	usif_client_fini(cli);
+	nouveau_vmm_fini(&cli->vmm);
+	nvif_mmu_fini(&cli->mmu);
 	nvif_device_fini(&cli->device);
+	mutex_lock(&cli->drm->master.lock);
 	nvif_client_fini(&cli->base);
+	mutex_unlock(&cli->drm->master.lock);
 }
 
 static int
 nouveau_cli_init(struct nouveau_drm *drm, const char *sname,
 		 struct nouveau_cli *cli)
 {
+	static const struct nvif_mclass
+	mems[] = {
+		{ NVIF_CLASS_MEM_GF100, -1 },
+		{ NVIF_CLASS_MEM_NV50 , -1 },
+		{ NVIF_CLASS_MEM_NV04 , -1 },
+		{}
+	};
+	static const struct nvif_mclass
+	mmus[] = {
+		{ NVIF_CLASS_MMU_GF100, -1 },
+		{ NVIF_CLASS_MMU_NV50 , -1 },
+		{ NVIF_CLASS_MMU_NV04 , -1 },
+		{}
+	};
+	static const struct nvif_mclass
+	vmms[] = {
+		{ NVIF_CLASS_VMM_GP100, -1 },
+		{ NVIF_CLASS_VMM_GM200, -1 },
+		{ NVIF_CLASS_VMM_GF100, -1 },
+		{ NVIF_CLASS_VMM_NV50 , -1 },
+		{ NVIF_CLASS_VMM_NV04 , -1 },
+		{}
+	};
 	u64 device = nouveau_name(drm->dev);
 	int ret;
 
 	snprintf(cli->name, sizeof(cli->name), "%s", sname);
-	cli->dev = drm->dev;
+	cli->drm = drm;
 	mutex_init(&cli->mutex);
 	usif_client_init(cli);
 
-	if (cli == &drm->client) {
+	INIT_WORK(&cli->work, nouveau_cli_work);
+	INIT_LIST_HEAD(&cli->worker);
+	mutex_init(&cli->lock);
+
+	if (cli == &drm->master) {
 		ret = nvif_driver_init(NULL, nouveau_config, nouveau_debug,
 				       cli->name, device, &cli->base);
 	} else {
-		ret = nvif_client_init(&drm->client.base, cli->name, device,
+		mutex_lock(&drm->master.lock);
+		ret = nvif_client_init(&drm->master.base, cli->name, device,
 				       &cli->base);
+		mutex_unlock(&drm->master.lock);
 	}
 	if (ret) {
 		NV_ERROR(drm, "Client allocation failed: %d\n", ret);
@@ -154,6 +240,38 @@ nouveau_cli_init(struct nouveau_drm *drm, const char *sname,
 		goto done;
 	}
 
+	ret = nvif_mclass(&cli->device.object, mmus);
+	if (ret < 0) {
+		NV_ERROR(drm, "No supported MMU class\n");
+		goto done;
+	}
+
+	ret = nvif_mmu_init(&cli->device.object, mmus[ret].oclass, &cli->mmu);
+	if (ret) {
+		NV_ERROR(drm, "MMU allocation failed: %d\n", ret);
+		goto done;
+	}
+
+	ret = nvif_mclass(&cli->mmu.object, vmms);
+	if (ret < 0) {
+		NV_ERROR(drm, "No supported VMM class\n");
+		goto done;
+	}
+
+	ret = nouveau_vmm_init(cli, vmms[ret].oclass, &cli->vmm);
+	if (ret) {
+		NV_ERROR(drm, "VMM allocation failed: %d\n", ret);
+		goto done;
+	}
+
+	ret = nvif_mclass(&cli->mmu.object, mems);
+	if (ret < 0) {
+		NV_ERROR(drm, "No supported MEM class\n");
+		goto done;
+	}
+
+	cli->mem = &mems[ret];
+	return 0;
 done:
 	if (ret)
 		nouveau_cli_fini(cli);
@@ -433,6 +551,10 @@ nouveau_drm_load(struct drm_device *dev, unsigned long flags)
 	dev->dev_private = drm;
 	drm->dev = dev;
 
+	ret = nouveau_cli_init(drm, "DRM-master", &drm->master);
+	if (ret)
+		return ret;
+
 	ret = nouveau_cli_init(drm, "DRM", &drm->client);
 	if (ret)
 		return ret;
@@ -456,21 +578,6 @@ nouveau_drm_load(struct drm_device *dev, unsigned long flags)
 
 	nouveau_vga_init(drm);
 
-	if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_TESLA) {
-		if (!nvxx_device(&drm->client.device)->mmu) {
-			ret = -ENOSYS;
-			goto fail_device;
-		}
-
-		ret = nvkm_vm_new(nvxx_device(&drm->client.device),
-				  0, (1ULL << 40), 0x1000, NULL,
-				  &drm->client.vm);
-		if (ret)
-			goto fail_device;
-
-		nvxx_client(&drm->client.base)->vm = drm->client.vm;
-	}
-
 	ret = nouveau_ttm_init(drm);
 	if (ret)
 		goto fail_ttm;
@@ -516,8 +623,8 @@ fail_bios:
 	nouveau_ttm_fini(drm);
 fail_ttm:
 	nouveau_vga_fini(drm);
-fail_device:
 	nouveau_cli_fini(&drm->client);
+	nouveau_cli_fini(&drm->master);
 	kfree(drm);
 	return ret;
 }
@@ -550,6 +657,7 @@ nouveau_drm_unload(struct drm_device *dev)
 	if (drm->hdmi_device)
 		pci_dev_put(drm->hdmi_device);
 	nouveau_cli_fini(&drm->client);
+	nouveau_cli_fini(&drm->master);
 	kfree(drm);
 }
 
@@ -618,7 +726,7 @@ nouveau_do_suspend(struct drm_device *dev, bool runtime)
 	}
 
 	NV_DEBUG(drm, "suspending object tree...\n");
-	ret = nvif_client_suspend(&drm->client.base);
+	ret = nvif_client_suspend(&drm->master.base);
 	if (ret)
 		goto fail_client;
 
@@ -642,7 +750,7 @@ nouveau_do_resume(struct drm_device *dev, bool runtime)
 	struct nouveau_drm *drm = nouveau_drm(dev);
 
 	NV_DEBUG(drm, "resuming object tree...\n");
-	nvif_client_resume(&drm->client.base);
+	nvif_client_resume(&drm->master.base);
 
 	NV_DEBUG(drm, "resuming fence...\n");
 	if (drm->fence && nouveau_fence(drm)->resume)
@@ -850,15 +958,6 @@ nouveau_drm_open(struct drm_device *dev, struct drm_file *fpriv)
 
 	cli->base.super = false;
 
-	if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_TESLA) {
-		ret = nvkm_vm_new(nvxx_device(&drm->client.device), 0,
-				  (1ULL << 40), 0x1000, NULL, &cli->vm);
-		if (ret)
-			goto done;
-
-		nvxx_client(&cli->base)->vm = cli->vm;
-	}
-
 	fpriv->driver_priv = cli;
 
 	mutex_lock(&drm->client.mutex);