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, 62 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 698bcb8ce61d..ead851413c0a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -107,14 +107,6 @@ struct amdgpu_pte_update_params {
 	 * DMA addresses to use for mapping, used during VM update by CPU
 	 */
 	dma_addr_t *pages_addr;
-
-	/**
-	 * @kptr:
-	 *
-	 * Kernel pointer of PD/PT BO that needs to be updated,
-	 * used during VM update by CPU
-	 */
-	void *kptr;
 };
 
 /**
@@ -623,6 +615,28 @@ void amdgpu_vm_get_pd_bo(struct amdgpu_vm *vm,
 	list_add(&entry->tv.head, validated);
 }
 
+void amdgpu_vm_del_from_lru_notify(struct ttm_buffer_object *bo)
+{
+	struct amdgpu_bo *abo;
+	struct amdgpu_vm_bo_base *bo_base;
+
+	if (!amdgpu_bo_is_amdgpu_bo(bo))
+		return;
+
+	if (bo->mem.placement & TTM_PL_FLAG_NO_EVICT)
+		return;
+
+	abo = ttm_to_amdgpu_bo(bo);
+	if (!abo->parent)
+		return;
+	for (bo_base = abo->vm_bo; bo_base; bo_base = bo_base->next) {
+		struct amdgpu_vm *vm = bo_base->vm;
+
+		if (abo->tbo.resv == vm->root.base.bo->tbo.resv)
+			vm->bulk_moveable = false;
+	}
+
+}
 /**
  * amdgpu_vm_move_to_lru_tail - move all BOs to the end of LRU
  *
@@ -686,8 +700,6 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	struct amdgpu_vm_bo_base *bo_base, *tmp;
 	int r = 0;
 
-	vm->bulk_moveable &= list_empty(&vm->evicted);
-
 	list_for_each_entry_safe(bo_base, tmp, &vm->evicted, vm_status) {
 		struct amdgpu_bo *bo = bo_base->bo;
 
@@ -801,15 +813,22 @@ static int amdgpu_vm_clear_bo(struct amdgpu_device *adev,
 		addr += ats_entries * 8;
 	}
 
-	if (entries)
+	if (entries) {
+		uint64_t value = 0;
+
+		/* Workaround for fault priority problem on GMC9 */
+		if (level == AMDGPU_VM_PTB && adev->asic_type >= CHIP_VEGA10)
+			value = AMDGPU_PTE_EXECUTABLE;
+
 		amdgpu_vm_set_pte_pde(adev, &job->ibs[0], addr, 0,
-				      entries, 0, 0);
+				      entries, 0, value);
+	}
 
 	amdgpu_ring_pad_ib(ring, &job->ibs[0]);
 
 	WARN_ON(job->ibs[0].length_dw > 64);
 	r = amdgpu_sync_resv(adev, &job->sync, bo->tbo.resv,
-			     AMDGPU_FENCE_OWNER_UNDEFINED, false);
+			     AMDGPU_FENCE_OWNER_KFD, false);
 	if (r)
 		goto error_free;
 
@@ -1313,31 +1332,6 @@ static void amdgpu_vm_cpu_set_ptes(struct amdgpu_pte_update_params *params,
 	}
 }
 
-
-/**
- * amdgpu_vm_wait_pd - Wait for PT BOs to be free.
- *
- * @adev: amdgpu_device pointer
- * @vm: related vm
- * @owner: fence owner
- *
- * Returns:
- * 0 on success, errno otherwise.
- */
-static int amdgpu_vm_wait_pd(struct amdgpu_device *adev, struct amdgpu_vm *vm,
-			     void *owner)
-{
-	struct amdgpu_sync sync;
-	int r;
-
-	amdgpu_sync_create(&sync);
-	amdgpu_sync_resv(adev, &sync, vm->root.base.bo->tbo.resv, owner, false);
-	r = amdgpu_sync_wait(&sync, true);
-	amdgpu_sync_free(&sync);
-
-	return r;
-}
-
 /**
  * amdgpu_vm_update_func - helper to call update function
  *
@@ -1432,7 +1426,8 @@ restart:
 	params.adev = adev;
 
 	if (vm->use_cpu_for_update) {
-		r = amdgpu_vm_wait_pd(adev, vm, AMDGPU_FENCE_OWNER_VM);
+		r = amdgpu_bo_sync_wait(vm->root.base.bo,
+					AMDGPU_FENCE_OWNER_VM, true);
 		if (unlikely(r))
 			return r;
 
@@ -1505,20 +1500,27 @@ error:
 }
 
 /**
- * amdgpu_vm_update_huge - figure out parameters for PTE updates
+ * amdgpu_vm_update_flags - figure out flags for PTE updates
  *
  * Make sure to set the right flags for the PTEs at the desired level.
  */
-static void amdgpu_vm_update_huge(struct amdgpu_pte_update_params *params,
-				  struct amdgpu_bo *bo, unsigned level,
-				  uint64_t pe, uint64_t addr,
-				  unsigned count, uint32_t incr,
-				  uint64_t flags)
+static void amdgpu_vm_update_flags(struct amdgpu_pte_update_params *params,
+				   struct amdgpu_bo *bo, unsigned level,
+				   uint64_t pe, uint64_t addr,
+				   unsigned count, uint32_t incr,
+				   uint64_t flags)
 
 {
 	if (level != AMDGPU_VM_PTB) {
 		flags |= AMDGPU_PDE_PTE;
 		amdgpu_gmc_get_vm_pde(params->adev, level, &addr, &flags);
+
+	} else if (params->adev->asic_type >= CHIP_VEGA10 &&
+		   !(flags & AMDGPU_PTE_VALID) &&
+		   !(flags & AMDGPU_PTE_PRT)) {
+
+		/* Workaround for fault priority problem on GMC9 */
+		flags |= AMDGPU_PTE_EXECUTABLE;
 	}
 
 	amdgpu_vm_update_func(params, bo, pe, addr, count, incr, flags);
@@ -1675,9 +1677,9 @@ static int amdgpu_vm_update_ptes(struct amdgpu_pte_update_params *params,
 			uint64_t upd_end = min(entry_end, frag_end);
 			unsigned nptes = (upd_end - frag_start) >> shift;
 
-			amdgpu_vm_update_huge(params, pt, cursor.level,
-					      pe_start, dst, nptes, incr,
-					      flags | AMDGPU_PTE_FRAG(frag));
+			amdgpu_vm_update_flags(params, pt, cursor.level,
+					       pe_start, dst, nptes, incr,
+					       flags | AMDGPU_PTE_FRAG(frag));
 
 			pe_start += nptes * 8;
 			dst += (uint64_t)nptes * AMDGPU_GPU_PAGE_SIZE << shift;
@@ -1746,22 +1748,29 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
 	params.adev = adev;
 	params.vm = vm;
 
-	/* sync to everything on unmapping */
+	/* sync to everything except eviction fences on unmapping */
 	if (!(flags & AMDGPU_PTE_VALID))
-		owner = AMDGPU_FENCE_OWNER_UNDEFINED;
+		owner = AMDGPU_FENCE_OWNER_KFD;
 
 	if (vm->use_cpu_for_update) {
 		/* params.src is used as flag to indicate system Memory */
 		if (pages_addr)
 			params.src = ~0;
 
-		/* Wait for PT BOs to be free. PTs share the same resv. object
+		/* Wait for PT BOs to be idle. PTs share the same resv. object
 		 * as the root PD BO
 		 */
-		r = amdgpu_vm_wait_pd(adev, vm, owner);
+		r = amdgpu_bo_sync_wait(vm->root.base.bo, owner, true);
 		if (unlikely(r))
 			return r;
 
+		/* Wait for any BO move to be completed */
+		if (exclusive) {
+			r = dma_fence_wait(exclusive, true);
+			if (unlikely(r))
+				return r;
+		}
+
 		params.func = amdgpu_vm_cpu_set_ptes;
 		params.pages_addr = pages_addr;
 		return amdgpu_vm_update_ptes(&params, start, last + 1,
@@ -1775,13 +1784,12 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
 	/*
 	 * reserve space for two commands every (1 << BLOCK_SIZE)
 	 *  entries or 2k dwords (whatever is smaller)
-         *
-         * The second command is for the shadow pagetables.
 	 */
+	ncmds = ((nptes >> min(adev->vm_manager.block_size, 11u)) + 1);
+
+	/* The second command is for the shadow pagetables. */
 	if (vm->root.base.bo->shadow)
-		ncmds = ((nptes >> min(adev->vm_manager.block_size, 11u)) + 1) * 2;
-	else
-		ncmds = ((nptes >> min(adev->vm_manager.block_size, 11u)) + 1);
+		ncmds *= 2;
 
 	/* padding, etc. */
 	ndw = 64;
@@ -1800,10 +1808,11 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
 		ndw += ncmds * 10;
 
 		/* extra commands for begin/end fragments */
+		ncmds = 2 * adev->vm_manager.fragment_size;
 		if (vm->root.base.bo->shadow)
-		        ndw += 2 * 10 * adev->vm_manager.fragment_size * 2;
-		else
-		        ndw += 2 * 10 * adev->vm_manager.fragment_size;
+			ncmds *= 2;
+
+		ndw += 10 * ncmds;
 
 		params.func = amdgpu_vm_do_set_ptes;
 	}
@@ -3005,7 +3014,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	}
 	DRM_DEBUG_DRIVER("VM update mode is %s\n",
 			 vm->use_cpu_for_update ? "CPU" : "SDMA");
-	WARN_ONCE((vm->use_cpu_for_update & !amdgpu_gmc_vram_full_visible(&adev->gmc)),
+	WARN_ONCE((vm->use_cpu_for_update && !amdgpu_gmc_vram_full_visible(&adev->gmc)),
 		  "CPU update of VM recommended only for large BAR system\n");
 	vm->last_update = NULL;
 
@@ -3135,7 +3144,7 @@ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm, uns
 	vm->pte_support_ats = pte_support_ats;
 	DRM_DEBUG_DRIVER("VM update mode is %s\n",
 			 vm->use_cpu_for_update ? "CPU" : "SDMA");
-	WARN_ONCE((vm->use_cpu_for_update & !amdgpu_gmc_vram_full_visible(&adev->gmc)),
+	WARN_ONCE((vm->use_cpu_for_update && !amdgpu_gmc_vram_full_visible(&adev->gmc)),
 		  "CPU update of VM recommended only for large BAR system\n");
 
 	if (vm->pasid) {