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, 124 insertions, 20 deletions

diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 02d1a5eacb00..fbfab2f33023 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -54,12 +54,21 @@ i915_vma_retire(struct i915_gem_active *active,
 	if (--obj->active_count)
 		return;
 
+	/* Prune the shared fence arrays iff completely idle (inc. external) */
+	if (reservation_object_trylock(obj->resv)) {
+		if (reservation_object_test_signaled_rcu(obj->resv, true))
+			reservation_object_add_excl_fence(obj->resv, NULL);
+		reservation_object_unlock(obj->resv);
+	}
+
 	/* Bump our place on the bound list to keep it roughly in LRU order
 	 * so that we don't steal from recently used but inactive objects
 	 * (unless we are forced to ofc!)
 	 */
+	spin_lock(&rq->i915->mm.obj_lock);
 	if (obj->bind_count)
-		list_move_tail(&obj->global_link, &rq->i915->mm.bound_list);
+		list_move_tail(&obj->mm.link, &rq->i915->mm.bound_list);
+	spin_unlock(&rq->i915->mm.obj_lock);
 
 	obj->mm.dirty = true; /* be paranoid  */
 
@@ -266,6 +275,8 @@ int i915_vma_bind(struct i915_vma *vma, enum i915_cache_level cache_level,
 	if (bind_flags == 0)
 		return 0;
 
+	GEM_BUG_ON(!vma->pages);
+
 	trace_i915_vma_bind(vma, bind_flags);
 	ret = vma->vm->bind_vma(vma, cache_level, bind_flags);
 	if (ret)
@@ -278,13 +289,16 @@ int i915_vma_bind(struct i915_vma *vma, enum i915_cache_level cache_level,
 void __iomem *i915_vma_pin_iomap(struct i915_vma *vma)
 {
 	void __iomem *ptr;
+	int err;
 
 	/* Access through the GTT requires the device to be awake. */
 	assert_rpm_wakelock_held(vma->vm->i915);
 
 	lockdep_assert_held(&vma->vm->i915->drm.struct_mutex);
-	if (WARN_ON(!i915_vma_is_map_and_fenceable(vma)))
-		return IO_ERR_PTR(-ENODEV);
+	if (WARN_ON(!i915_vma_is_map_and_fenceable(vma))) {
+		err = -ENODEV;
+		goto err;
+	}
 
 	GEM_BUG_ON(!i915_vma_is_ggtt(vma));
 	GEM_BUG_ON((vma->flags & I915_VMA_GLOBAL_BIND) == 0);
@@ -294,14 +308,36 @@ void __iomem *i915_vma_pin_iomap(struct i915_vma *vma)
 		ptr = io_mapping_map_wc(&i915_vm_to_ggtt(vma->vm)->mappable,
 					vma->node.start,
 					vma->node.size);
-		if (ptr == NULL)
-			return IO_ERR_PTR(-ENOMEM);
+		if (ptr == NULL) {
+			err = -ENOMEM;
+			goto err;
+		}
 
 		vma->iomap = ptr;
 	}
 
 	__i915_vma_pin(vma);
+
+	err = i915_vma_pin_fence(vma);
+	if (err)
+		goto err_unpin;
+
 	return ptr;
+
+err_unpin:
+	__i915_vma_unpin(vma);
+err:
+	return IO_ERR_PTR(err);
+}
+
+void i915_vma_unpin_iomap(struct i915_vma *vma)
+{
+	lockdep_assert_held(&vma->obj->base.dev->struct_mutex);
+
+	GEM_BUG_ON(vma->iomap == NULL);
+
+	i915_vma_unpin_fence(vma);
+	i915_vma_unpin(vma);
 }
 
 void i915_vma_unpin_and_release(struct i915_vma **p_vma)
@@ -471,25 +507,64 @@ i915_vma_insert(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 	if (ret)
 		return ret;
 
+	GEM_BUG_ON(vma->pages);
+
+	ret = vma->vm->set_pages(vma);
+	if (ret)
+		goto err_unpin;
+
 	if (flags & PIN_OFFSET_FIXED) {
 		u64 offset = flags & PIN_OFFSET_MASK;
 		if (!IS_ALIGNED(offset, alignment) ||
 		    range_overflows(offset, size, end)) {
 			ret = -EINVAL;
-			goto err_unpin;
+			goto err_clear;
 		}
 
 		ret = i915_gem_gtt_reserve(vma->vm, &vma->node,
 					   size, offset, obj->cache_level,
 					   flags);
 		if (ret)
-			goto err_unpin;
+			goto err_clear;
 	} else {
+		/*
+		 * We only support huge gtt pages through the 48b PPGTT,
+		 * however we also don't want to force any alignment for
+		 * objects which need to be tightly packed into the low 32bits.
+		 *
+		 * Note that we assume that GGTT are limited to 4GiB for the
+		 * forseeable future. See also i915_ggtt_offset().
+		 */
+		if (upper_32_bits(end - 1) &&
+		    vma->page_sizes.sg > I915_GTT_PAGE_SIZE) {
+			/*
+			 * We can't mix 64K and 4K PTEs in the same page-table
+			 * (2M block), and so to avoid the ugliness and
+			 * complexity of coloring we opt for just aligning 64K
+			 * objects to 2M.
+			 */
+			u64 page_alignment =
+				rounddown_pow_of_two(vma->page_sizes.sg |
+						     I915_GTT_PAGE_SIZE_2M);
+
+			/*
+			 * Check we don't expand for the limited Global GTT
+			 * (mappable aperture is even more precious!). This
+			 * also checks that we exclude the aliasing-ppgtt.
+			 */
+			GEM_BUG_ON(i915_vma_is_ggtt(vma));
+
+			alignment = max(alignment, page_alignment);
+
+			if (vma->page_sizes.sg & I915_GTT_PAGE_SIZE_64K)
+				size = round_up(size, I915_GTT_PAGE_SIZE_2M);
+		}
+
 		ret = i915_gem_gtt_insert(vma->vm, &vma->node,
 					  size, alignment, obj->cache_level,
 					  start, end, flags);
 		if (ret)
-			goto err_unpin;
+			goto err_clear;
 
 		GEM_BUG_ON(vma->node.start < start);
 		GEM_BUG_ON(vma->node.start + vma->node.size > end);
@@ -497,13 +572,19 @@ i915_vma_insert(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 	GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
 	GEM_BUG_ON(!i915_gem_valid_gtt_space(vma, obj->cache_level));
 
-	list_move_tail(&obj->global_link, &dev_priv->mm.bound_list);
 	list_move_tail(&vma->vm_link, &vma->vm->inactive_list);
+
+	spin_lock(&dev_priv->mm.obj_lock);
+	list_move_tail(&obj->mm.link, &dev_priv->mm.bound_list);
 	obj->bind_count++;
+	spin_unlock(&dev_priv->mm.obj_lock);
+
 	GEM_BUG_ON(atomic_read(&obj->mm.pages_pin_count) < obj->bind_count);
 
 	return 0;
 
+err_clear:
+	vma->vm->clear_pages(vma);
 err_unpin:
 	i915_gem_object_unpin_pages(obj);
 	return ret;
@@ -512,20 +593,24 @@ err_unpin:
 static void
 i915_vma_remove(struct i915_vma *vma)
 {
+	struct drm_i915_private *i915 = vma->vm->i915;
 	struct drm_i915_gem_object *obj = vma->obj;
 
 	GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
 	GEM_BUG_ON(vma->flags & (I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND));
 
+	vma->vm->clear_pages(vma);
+
 	drm_mm_remove_node(&vma->node);
 	list_move_tail(&vma->vm_link, &vma->vm->unbound_list);
 
 	/* Since the unbound list is global, only move to that list if
 	 * no more VMAs exist.
 	 */
+	spin_lock(&i915->mm.obj_lock);
 	if (--obj->bind_count == 0)
-		list_move_tail(&obj->global_link,
-			       &to_i915(obj->base.dev)->mm.unbound_list);
+		list_move_tail(&obj->mm.link, &i915->mm.unbound_list);
+	spin_unlock(&i915->mm.obj_lock);
 
 	/* And finally now the object is completely decoupled from this vma,
 	 * we can drop its hold on the backing storage and allow it to be
@@ -569,8 +654,8 @@ int __i915_vma_do_pin(struct i915_vma *vma,
 
 err_remove:
 	if ((bound & I915_VMA_BIND_MASK) == 0) {
-		GEM_BUG_ON(vma->pages);
 		i915_vma_remove(vma);
+		GEM_BUG_ON(vma->pages);
 	}
 err_unpin:
 	__i915_vma_unpin(vma);
@@ -620,6 +705,30 @@ static void __i915_vma_iounmap(struct i915_vma *vma)
 	vma->iomap = NULL;
 }
 
+void i915_vma_revoke_mmap(struct i915_vma *vma)
+{
+	struct drm_vma_offset_node *node = &vma->obj->base.vma_node;
+	u64 vma_offset;
+
+	lockdep_assert_held(&vma->vm->i915->drm.struct_mutex);
+
+	if (!i915_vma_has_userfault(vma))
+		return;
+
+	GEM_BUG_ON(!i915_vma_is_map_and_fenceable(vma));
+	GEM_BUG_ON(!vma->obj->userfault_count);
+
+	vma_offset = vma->ggtt_view.partial.offset << PAGE_SHIFT;
+	unmap_mapping_range(vma->vm->i915->drm.anon_inode->i_mapping,
+			    drm_vma_node_offset_addr(node) + vma_offset,
+			    vma->size,
+			    1);
+
+	i915_vma_unset_userfault(vma);
+	if (!--vma->obj->userfault_count)
+		list_del(&vma->obj->userfault_link);
+}
+
 int i915_vma_unbind(struct i915_vma *vma)
 {
 	struct drm_i915_gem_object *obj = vma->obj;
@@ -683,11 +792,13 @@ int i915_vma_unbind(struct i915_vma *vma)
 			return ret;
 
 		/* Force a pagefault for domain tracking on next user access */
-		i915_gem_release_mmap(obj);
+		i915_vma_revoke_mmap(vma);
 
 		__i915_vma_iounmap(vma);
 		vma->flags &= ~I915_VMA_CAN_FENCE;
 	}
+	GEM_BUG_ON(vma->fence);
+	GEM_BUG_ON(i915_vma_has_userfault(vma));
 
 	if (likely(!vma->vm->closed)) {
 		trace_i915_vma_unbind(vma);
@@ -695,13 +806,6 @@ int i915_vma_unbind(struct i915_vma *vma)
 	}
 	vma->flags &= ~(I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND);
 
-	if (vma->pages != obj->mm.pages) {
-		GEM_BUG_ON(!vma->pages);
-		sg_free_table(vma->pages);
-		kfree(vma->pages);
-	}
-	vma->pages = NULL;
-
 	i915_vma_remove(vma);
 
 destroy: