Merge tag 'drm-for-v4.17' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "Cannonlake and Vega12 support are probably the two major things. This
  pull lacks nouveau, Ben had some unforseen leave and a few other
  blockers so we'll see how things look or maybe leave it for this merge
  window.

  core:
   - Device links to handle sound/gpu pm dependency
   - Color encoding/range properties
   - Plane clipping into plane check helper
   - Backlight helpers
   - DP TP4 + HBR3 helper support

  amdgpu:
   - Vega12 support
   - Enable DC by default on all supported GPUs
   - Powerplay restructuring and cleanup
   - DC bandwidth calc updates
   - DC backlight on pre-DCE11
   - TTM backing store dropping support
   - SR-IOV fixes
   - Adding "wattman" like functionality
   - DC crc support
   - Improved DC dual-link handling

  amdkfd:
   - GPUVM support for dGPU
   - KFD events for dGPU
   - Enable PCIe atomics for dGPUs
   - HSA process eviction support
   - Live-lock fixes for process eviction
   - VM page table allocation fix for large-bar systems

  panel:
   - Raydium RM68200
   - AUO G104SN02 V2
   - KEO TX31D200VM0BAA
   - ARM Versatile panels

  i915:
   - Cannonlake support enabled
   - AUX-F port support added
   - Icelake base enabling until internal milestone of forcewake support
   - Query uAPI interface (used for GPU topology information currently)
   - Compressed framebuffer support for sprites
   - kmem cache shrinking when GPU is idle
   - Avoid boosting GPU when waited item is being processed already
   - Avoid retraining LSPCON link unnecessarily
   - Decrease request signaling latency
   - Deprecation of I915_SET_COLORKEY_NONE
   - Kerneldoc and compiler warning cleanup for upcoming CI enforcements
   - Full range ycbcr toggling
   - HDCP support

  i915/gvt:
   - Big refactor for shadow ppgtt
   - KBL context save/restore via LRI cmd (Weinan)
   - Properly unmap dma for guest page (Changbin)

  vmwgfx:
   - Lots of various improvements

  etnaviv:
   - Use the drm gpu scheduler
   - prep work for GC7000L support

  vc4:
   - fix alpha blending
   - Expose perf counters to userspace

  pl111:
   - Bandwidth checking/limiting
   - Versatile panel support

  sun4i:
   - A83T HDMI support
   - A80 support
   - YUV plane support
   - H3/H5 HDMI support

  omapdrm:
   - HPD support for DVI connector
   - remove lots of static variables

  msm:
   - DSI updates from 10nm / SDM845
   - fix for race condition with a3xx/a4xx fence completion irq
   - some refactoring/prep work for eventual a6xx support (ie. when we
     have a userspace)
   - a5xx debugfs enhancements
   - some mdp5 fixes/cleanups to prepare for eventually merging
     writeback
   - support (ie. when we have a userspace)

  tegra:
   - mmap() fixes for fbdev devices
   - Overlay plane for hw cursor fix
   - dma-buf cache maintenance support

  mali-dp:
   - YUV->RGB conversion support

  rockchip:
   - rk3399/chromebook fixes and improvements

  rcar-du:
   - LVDS support move to drm bridge
   - DT bindings for R8A77995
   - Driver/DT support for R8A77970

  tilcdc:
   - DRM panel support"

* tag 'drm-for-v4.17' of git://people.freedesktop.org/~airlied/linux: (1646 commits)
  drm/i915: Fix hibernation with ACPI S0 target state
  drm/i915/execlists: Use a locked clear_bit() for synchronisation with interrupt
  drm/i915: Specify which engines to reset following semaphore/event lockups
  drm/i915/dp: Write to SET_POWER dpcd to enable MST hub.
  drm/amdkfd: Use ordered workqueue to restore processes
  drm/amdgpu: Fix acquiring VM on large-BAR systems
  drm/amd/pp: clean header file hwmgr.h
  drm/amd/pp: use mlck_table.count for array loop index limit
  drm: Fix uabi regression by allowing garbage mode->type from userspace
  drm/amdgpu: Add an ATPX quirk for hybrid laptop
  drm/amdgpu: fix spelling mistake: "asssert" -> "assert"
  drm/amd/pp: Add new asic support in pp_psm.c
  drm/amd/pp: Clean up powerplay code on Vega12
  drm/amd/pp: Add smu irq handlers for legacy asics
  drm/amd/pp: Fix set wrong temperature range on smu7
  drm/amdgpu: Don't change preferred domian when fallback GTT v5
  drm/vmwgfx: Bump version patchlevel and date
  drm/vmwgfx: use monotonic event timestamps
  drm/vmwgfx: Unpin the screen object backup buffer when not used
  drm/vmwgfx: Stricter count of legacy surface device resources
  ...

1 files changed, 70 insertions, 82 deletions

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 7e403eaa9e0f..21d72f695adb 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -543,9 +543,7 @@ static void fill_page_dma_32(struct i915_address_space *vm,
 static int
 setup_scratch_page(struct i915_address_space *vm, gfp_t gfp)
 {
-	struct page *page = NULL;
-	dma_addr_t addr;
-	int order;
+	unsigned long size;
 
 	/*
 	 * In order to utilize 64K pages for an object with a size < 2M, we will
@@ -559,48 +557,47 @@ setup_scratch_page(struct i915_address_space *vm, gfp_t gfp)
 	 * TODO: we should really consider write-protecting the scratch-page and
 	 * sharing between ppgtt
 	 */
+	size = I915_GTT_PAGE_SIZE_4K;
 	if (i915_vm_is_48bit(vm) &&
 	    HAS_PAGE_SIZES(vm->i915, I915_GTT_PAGE_SIZE_64K)) {
-		order = get_order(I915_GTT_PAGE_SIZE_64K);
-		page = alloc_pages(gfp | __GFP_ZERO | __GFP_NOWARN, order);
-		if (page) {
-			addr = dma_map_page(vm->dma, page, 0,
-					    I915_GTT_PAGE_SIZE_64K,
-					    PCI_DMA_BIDIRECTIONAL);
-			if (unlikely(dma_mapping_error(vm->dma, addr))) {
-				__free_pages(page, order);
-				page = NULL;
-			}
-
-			if (!IS_ALIGNED(addr, I915_GTT_PAGE_SIZE_64K)) {
-				dma_unmap_page(vm->dma, addr,
-					       I915_GTT_PAGE_SIZE_64K,
-					       PCI_DMA_BIDIRECTIONAL);
-				__free_pages(page, order);
-				page = NULL;
-			}
-		}
+		size = I915_GTT_PAGE_SIZE_64K;
+		gfp |= __GFP_NOWARN;
 	}
+	gfp |= __GFP_ZERO | __GFP_RETRY_MAYFAIL;
+
+	do {
+		int order = get_order(size);
+		struct page *page;
+		dma_addr_t addr;
 
-	if (!page) {
-		order = 0;
-		page = alloc_page(gfp | __GFP_ZERO);
+		page = alloc_pages(gfp, order);
 		if (unlikely(!page))
-			return -ENOMEM;
+			goto skip;
 
-		addr = dma_map_page(vm->dma, page, 0, PAGE_SIZE,
+		addr = dma_map_page(vm->dma, page, 0, size,
 				    PCI_DMA_BIDIRECTIONAL);
-		if (unlikely(dma_mapping_error(vm->dma, addr))) {
-			__free_page(page);
-			return -ENOMEM;
-		}
-	}
+		if (unlikely(dma_mapping_error(vm->dma, addr)))
+			goto free_page;
 
-	vm->scratch_page.page = page;
-	vm->scratch_page.daddr = addr;
-	vm->scratch_page.order = order;
+		if (unlikely(!IS_ALIGNED(addr, size)))
+			goto unmap_page;
 
-	return 0;
+		vm->scratch_page.page = page;
+		vm->scratch_page.daddr = addr;
+		vm->scratch_page.order = order;
+		return 0;
+
+unmap_page:
+		dma_unmap_page(vm->dma, addr, size, PCI_DMA_BIDIRECTIONAL);
+free_page:
+		__free_pages(page, order);
+skip:
+		if (size == I915_GTT_PAGE_SIZE_4K)
+			return -ENOMEM;
+
+		size = I915_GTT_PAGE_SIZE_4K;
+		gfp &= ~__GFP_NOWARN;
+	} while (1);
 }
 
 static void cleanup_scratch_page(struct i915_address_space *vm)
@@ -676,27 +673,22 @@ static void free_pd(struct i915_address_space *vm,
 static void gen8_initialize_pd(struct i915_address_space *vm,
 			       struct i915_page_directory *pd)
 {
-	unsigned int i;
-
 	fill_px(vm, pd,
 		gen8_pde_encode(px_dma(vm->scratch_pt), I915_CACHE_LLC));
-	for (i = 0; i < I915_PDES; i++)
-		pd->page_table[i] = vm->scratch_pt;
+	memset_p((void **)pd->page_table, vm->scratch_pt, I915_PDES);
 }
 
 static int __pdp_init(struct i915_address_space *vm,
 		      struct i915_page_directory_pointer *pdp)
 {
 	const unsigned int pdpes = i915_pdpes_per_pdp(vm);
-	unsigned int i;
 
 	pdp->page_directory = kmalloc_array(pdpes, sizeof(*pdp->page_directory),
 					    GFP_KERNEL | __GFP_NOWARN);
 	if (unlikely(!pdp->page_directory))
 		return -ENOMEM;
 
-	for (i = 0; i < pdpes; i++)
-		pdp->page_directory[i] = vm->scratch_pd;
+	memset_p((void **)pdp->page_directory, vm->scratch_pd, pdpes);
 
 	return 0;
 }
@@ -718,7 +710,7 @@ alloc_pdp(struct i915_address_space *vm)
 	struct i915_page_directory_pointer *pdp;
 	int ret = -ENOMEM;
 
-	WARN_ON(!use_4lvl(vm));
+	GEM_BUG_ON(!use_4lvl(vm));
 
 	pdp = kzalloc(sizeof(*pdp), GFP_KERNEL);
 	if (!pdp)
@@ -767,25 +759,22 @@ static void gen8_initialize_pdp(struct i915_address_space *vm,
 static void gen8_initialize_pml4(struct i915_address_space *vm,
 				 struct i915_pml4 *pml4)
 {
-	unsigned int i;
-
 	fill_px(vm, pml4,
 		gen8_pml4e_encode(px_dma(vm->scratch_pdp), I915_CACHE_LLC));
-	for (i = 0; i < GEN8_PML4ES_PER_PML4; i++)
-		pml4->pdps[i] = vm->scratch_pdp;
+	memset_p((void **)pml4->pdps, vm->scratch_pdp, GEN8_PML4ES_PER_PML4);
 }
 
 /* Broadwell Page Directory Pointer Descriptors */
-static int gen8_write_pdp(struct drm_i915_gem_request *req,
+static int gen8_write_pdp(struct i915_request *rq,
 			  unsigned entry,
 			  dma_addr_t addr)
 {
-	struct intel_engine_cs *engine = req->engine;
+	struct intel_engine_cs *engine = rq->engine;
 	u32 *cs;
 
 	BUG_ON(entry >= 4);
 
-	cs = intel_ring_begin(req, 6);
+	cs = intel_ring_begin(rq, 6);
 	if (IS_ERR(cs))
 		return PTR_ERR(cs);
 
@@ -795,20 +784,20 @@ static int gen8_write_pdp(struct drm_i915_gem_request *req,
 	*cs++ = MI_LOAD_REGISTER_IMM(1);
 	*cs++ = i915_mmio_reg_offset(GEN8_RING_PDP_LDW(engine, entry));
 	*cs++ = lower_32_bits(addr);
-	intel_ring_advance(req, cs);
+	intel_ring_advance(rq, cs);
 
 	return 0;
 }
 
 static int gen8_mm_switch_3lvl(struct i915_hw_ppgtt *ppgtt,
-			       struct drm_i915_gem_request *req)
+			       struct i915_request *rq)
 {
 	int i, ret;
 
 	for (i = GEN8_3LVL_PDPES - 1; i >= 0; i--) {
 		const dma_addr_t pd_daddr = i915_page_dir_dma_addr(ppgtt, i);
 
-		ret = gen8_write_pdp(req, i, pd_daddr);
+		ret = gen8_write_pdp(rq, i, pd_daddr);
 		if (ret)
 			return ret;
 	}
@@ -817,9 +806,9 @@ static int gen8_mm_switch_3lvl(struct i915_hw_ppgtt *ppgtt,
 }
 
 static int gen8_mm_switch_4lvl(struct i915_hw_ppgtt *ppgtt,
-			       struct drm_i915_gem_request *req)
+			       struct i915_request *rq)
 {
-	return gen8_write_pdp(req, 0, px_dma(&ppgtt->pml4));
+	return gen8_write_pdp(rq, 0, px_dma(&ppgtt->pml4));
 }
 
 /* PDE TLBs are a pain to invalidate on GEN8+. When we modify
@@ -1743,13 +1732,13 @@ static inline u32 get_pd_offset(struct i915_hw_ppgtt *ppgtt)
 }
 
 static int hsw_mm_switch(struct i915_hw_ppgtt *ppgtt,
-			 struct drm_i915_gem_request *req)
+			 struct i915_request *rq)
 {
-	struct intel_engine_cs *engine = req->engine;
+	struct intel_engine_cs *engine = rq->engine;
 	u32 *cs;
 
 	/* NB: TLBs must be flushed and invalidated before a switch */
-	cs = intel_ring_begin(req, 6);
+	cs = intel_ring_begin(rq, 6);
 	if (IS_ERR(cs))
 		return PTR_ERR(cs);
 
@@ -1759,19 +1748,19 @@ static int hsw_mm_switch(struct i915_hw_ppgtt *ppgtt,
 	*cs++ = i915_mmio_reg_offset(RING_PP_DIR_BASE(engine));
 	*cs++ = get_pd_offset(ppgtt);
 	*cs++ = MI_NOOP;
-	intel_ring_advance(req, cs);
+	intel_ring_advance(rq, cs);
 
 	return 0;
 }
 
 static int gen7_mm_switch(struct i915_hw_ppgtt *ppgtt,
-			  struct drm_i915_gem_request *req)
+			  struct i915_request *rq)
 {
-	struct intel_engine_cs *engine = req->engine;
+	struct intel_engine_cs *engine = rq->engine;
 	u32 *cs;
 
 	/* NB: TLBs must be flushed and invalidated before a switch */
-	cs = intel_ring_begin(req, 6);
+	cs = intel_ring_begin(rq, 6);
 	if (IS_ERR(cs))
 		return PTR_ERR(cs);
 
@@ -1781,16 +1770,16 @@ static int gen7_mm_switch(struct i915_hw_ppgtt *ppgtt,
 	*cs++ = i915_mmio_reg_offset(RING_PP_DIR_BASE(engine));
 	*cs++ = get_pd_offset(ppgtt);
 	*cs++ = MI_NOOP;
-	intel_ring_advance(req, cs);
+	intel_ring_advance(rq, cs);
 
 	return 0;
 }
 
 static int gen6_mm_switch(struct i915_hw_ppgtt *ppgtt,
-			  struct drm_i915_gem_request *req)
+			  struct i915_request *rq)
 {
-	struct intel_engine_cs *engine = req->engine;
-	struct drm_i915_private *dev_priv = req->i915;
+	struct intel_engine_cs *engine = rq->engine;
+	struct drm_i915_private *dev_priv = rq->i915;
 
 	I915_WRITE(RING_PP_DIR_DCLV(engine), PP_DIR_DCLV_2G);
 	I915_WRITE(RING_PP_DIR_BASE(engine), get_pd_offset(ppgtt));
@@ -2112,7 +2101,7 @@ static int __hw_ppgtt_init(struct i915_hw_ppgtt *ppgtt,
 	ppgtt->base.i915 = dev_priv;
 	ppgtt->base.dma = &dev_priv->drm.pdev->dev;
 
-	if (INTEL_INFO(dev_priv)->gen < 8)
+	if (INTEL_GEN(dev_priv) < 8)
 		return gen6_ppgtt_init(ppgtt);
 	else
 		return gen8_ppgtt_init(ppgtt);
@@ -2260,9 +2249,9 @@ void i915_ppgtt_release(struct kref *kref)
 	trace_i915_ppgtt_release(&ppgtt->base);
 
 	/* vmas should already be unbound and destroyed */
-	WARN_ON(!list_empty(&ppgtt->base.active_list));
-	WARN_ON(!list_empty(&ppgtt->base.inactive_list));
-	WARN_ON(!list_empty(&ppgtt->base.unbound_list));
+	GEM_BUG_ON(!list_empty(&ppgtt->base.active_list));
+	GEM_BUG_ON(!list_empty(&ppgtt->base.inactive_list));
+	GEM_BUG_ON(!list_empty(&ppgtt->base.unbound_list));
 
 	ppgtt->base.cleanup(&ppgtt->base);
 	i915_address_space_fini(&ppgtt->base);
@@ -2370,9 +2359,10 @@ int i915_gem_gtt_prepare_pages(struct drm_i915_gem_object *obj,
 			       struct sg_table *pages)
 {
 	do {
-		if (dma_map_sg(&obj->base.dev->pdev->dev,
-			       pages->sgl, pages->nents,
-			       PCI_DMA_BIDIRECTIONAL))
+		if (dma_map_sg_attrs(&obj->base.dev->pdev->dev,
+				     pages->sgl, pages->nents,
+				     PCI_DMA_BIDIRECTIONAL,
+				     DMA_ATTR_NO_WARN))
 			return 0;
 
 		/* If the DMA remap fails, one cause can be that we have
@@ -2824,10 +2814,10 @@ int i915_gem_init_aliasing_ppgtt(struct drm_i915_private *i915)
 
 	i915->mm.aliasing_ppgtt = ppgtt;
 
-	WARN_ON(ggtt->base.bind_vma != ggtt_bind_vma);
+	GEM_BUG_ON(ggtt->base.bind_vma != ggtt_bind_vma);
 	ggtt->base.bind_vma = aliasing_gtt_bind_vma;
 
-	WARN_ON(ggtt->base.unbind_vma != ggtt_unbind_vma);
+	GEM_BUG_ON(ggtt->base.unbind_vma != ggtt_unbind_vma);
 	ggtt->base.unbind_vma = aliasing_gtt_unbind_vma;
 
 	return 0;
@@ -2918,7 +2908,7 @@ void i915_ggtt_cleanup_hw(struct drm_i915_private *dev_priv)
 	ggtt->base.closed = true;
 
 	mutex_lock(&dev_priv->drm.struct_mutex);
-	WARN_ON(!list_empty(&ggtt->base.active_list));
+	GEM_BUG_ON(!list_empty(&ggtt->base.active_list));
 	list_for_each_entry_safe(vma, vn, &ggtt->base.inactive_list, vm_link)
 		WARN_ON(i915_vma_unbind(vma));
 	mutex_unlock(&dev_priv->drm.struct_mutex);
@@ -3811,6 +3801,9 @@ i915_get_ggtt_vma_pages(struct i915_vma *vma)
 	GEM_BUG_ON(!i915_gem_object_has_pinned_pages(vma->obj));
 
 	switch (vma->ggtt_view.type) {
+	default:
+		GEM_BUG_ON(vma->ggtt_view.type);
+		/* fall through */
 	case I915_GGTT_VIEW_NORMAL:
 		vma->pages = vma->obj->mm.pages;
 		return 0;
@@ -3823,11 +3816,6 @@ i915_get_ggtt_vma_pages(struct i915_vma *vma)
 	case I915_GGTT_VIEW_PARTIAL:
 		vma->pages = intel_partial_pages(&vma->ggtt_view, vma->obj);
 		break;
-
-	default:
-		WARN_ONCE(1, "GGTT view %u not implemented!\n",
-			  vma->ggtt_view.type);
-		return -EINVAL;
 	}
 
 	ret = 0;