Merge tag 'drm-for-v4.14' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "This is the main drm pull request for 4.14 merge window.

  I'm sending this early, as my continuing journey into fatherhood is
  occurring really soon now, I'm going to be mostly useless for the next
  couple of weeks, though I may be able to read email, I doubt I'll be
  doing much patch applications or git sending. If anything urgent pops
  up I've asked Daniel/Jani/Alex/Sean to try and direct stuff towards
  you.

  Outside drm changes:

  Some rcar-du updates that touch the V4L tree, all acks should be in
  place. It adds one export to the radix tree code for new i915 use
  case. There are some minor AGP cleanups (don't see that too often).
  Changes to the vbox driver in staging to avoid breaking compilation.

  Summary:

  core:
   - Atomic helper fixes
   - Atomic UAPI fixes
   - Add YCBCR 4:2:0 support
   - Drop set_busid hook
   - Refactor fb_helper locking
   - Remove a bunch of internal APIs
   - Add a bunch of better default handlers
   - Format modifier/blob plane property added
   - More internal header refactoring
   - Make more internal API names consistent
   - Enhanced syncobj APIs (wait/signal/reset/create signalled)

  bridge:
   - Add Synopsys Designware MIPI DSI host bridge driver

  tiny:
   - Add Pervasive Displays RePaper displays
   - Add support for LEGO MINDSTORMS EV3 LCD

  i915:
   - Lots of GEN10/CNL  support patches
   - drm syncobj support
   - Skylake+ watermark refactoring
   - GVT vGPU 48-bit ppgtt support
   - GVT performance improvements
   - NOA change ioctl
   - CCS (color compression) scanout support
   - GPU reset improvements

  amdgpu:
   - Initial hugepage support
   - BO migration logic rework
   - Vega10 improvements
   - Powerplay fixes
   - Stop reprogramming the MC
   - Fixes for ACP audio on stoney
   - SR-IOV fixes/improvements
   - Command submission overhead improvements

  amdkfd:
   - Non-dGPU upstreaming patches
   - Scratch VA ioctl
   - Image tiling modes
   - Update PM4 headers for new firmware
   - Drop all BUG_ONs.

  nouveau:
   - GP108 modesetting support.
   - Disable MSI on big endian.

  vmwgfx:
   - Add fence fd support.

  msm:
   - Runtime PM improvements

  exynos:
   - NV12MT support
   - Refactor KMS drivers

  imx-drm:
   - Lock scanout channel to improve memory bw
   - Cleanups

  etnaviv:
   - GEM object population fixes

  tegra:
   - Prep work for Tegra186 support
   - PRIME mmap support

  sunxi:
   - HDMI support improvements
   - HDMI CEC support

  omapdrm:
   - HDMI hotplug IRQ support
   - Big driver cleanup
   - OMAP5 DSI support

  rcar-du:
   - vblank fixes
   - VSP1 updates

  arcgpu:
   - Minor fixes

  stm:
   - Add STM32 DSI controller driver

  dw_hdmi:
   - Add support for Rockchip RK3399
   - HDMI CEC support

  atmel-hlcdc:
   - Add 8-bit color support

  vc4:
   - Atomic fixes
   - New ioctl to attach a label to a buffer object
   - HDMI CEC support
   - Allow userspace to dictate rendering order on submit ioctl"

* tag 'drm-for-v4.14' of git://people.freedesktop.org/~airlied/linux: (1074 commits)
  drm/syncobj: Add a signal ioctl (v3)
  drm/syncobj: Add a reset ioctl (v3)
  drm/syncobj: Add a syncobj_array_find helper
  drm/syncobj: Allow wait for submit and signal behavior (v5)
  drm/syncobj: Add a CREATE_SIGNALED flag
  drm/syncobj: Add a callback mechanism for replace_fence (v3)
  drm/syncobj: add sync obj wait interface. (v8)
  i915: Use drm_syncobj_fence_get
  drm/syncobj: Add a race-free drm_syncobj_fence_get helper (v2)
  drm/syncobj: Rename fence_get to find_fence
  drm: kirin: Add mode_valid logic to avoid mode clocks we can't generate
  drm/vmwgfx: Bump the version for fence FD support
  drm/vmwgfx: Add export fence to file descriptor support
  drm/vmwgfx: Add support for imported Fence File Descriptor
  drm/vmwgfx: Prepare to support fence fd
  drm/vmwgfx: Fix incorrect command header offset at restart
  drm/vmwgfx: Support the NOP_ERROR command
  drm/vmwgfx: Restart command buffers after errors
  drm/vmwgfx: Move irq bottom half processing to threads
  drm/vmwgfx: Don't use drm_irq_[un]install
  ...

1 files changed, 62 insertions, 47 deletions

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 61fc7e90a7da..d60f38adc4c4 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -144,9 +144,9 @@ int intel_sanitize_enable_ppgtt(struct drm_i915_private *dev_priv,
 	has_full_48bit_ppgtt = dev_priv->info.has_full_48bit_ppgtt;
 
 	if (intel_vgpu_active(dev_priv)) {
-		/* emulation is too hard */
+		/* GVT-g has no support for 32bit ppgtt */
 		has_full_ppgtt = false;
-		has_full_48bit_ppgtt = false;
+		has_full_48bit_ppgtt = intel_vgpu_has_full_48bit_ppgtt(dev_priv);
 	}
 
 	if (!has_aliasing_ppgtt)
@@ -180,10 +180,15 @@ int intel_sanitize_enable_ppgtt(struct drm_i915_private *dev_priv,
 		return 0;
 	}
 
-	if (INTEL_GEN(dev_priv) >= 8 && i915.enable_execlists && has_full_ppgtt)
-		return has_full_48bit_ppgtt ? 3 : 2;
-	else
-		return has_aliasing_ppgtt ? 1 : 0;
+	if (INTEL_GEN(dev_priv) >= 8 && i915.enable_execlists) {
+		if (has_full_48bit_ppgtt)
+			return 3;
+
+		if (has_full_ppgtt)
+			return 2;
+	}
+
+	return has_aliasing_ppgtt ? 1 : 0;
 }
 
 static int ppgtt_bind_vma(struct i915_vma *vma,
@@ -207,8 +212,7 @@ static int ppgtt_bind_vma(struct i915_vma *vma,
 	if (vma->obj->gt_ro)
 		pte_flags |= PTE_READ_ONLY;
 
-	vma->vm->insert_entries(vma->vm, vma->pages, vma->node.start,
-				cache_level, pte_flags);
+	vma->vm->insert_entries(vma->vm, vma, cache_level, pte_flags);
 
 	return 0;
 }
@@ -907,37 +911,35 @@ gen8_ppgtt_insert_pte_entries(struct i915_hw_ppgtt *ppgtt,
 }
 
 static void gen8_ppgtt_insert_3lvl(struct i915_address_space *vm,
-				   struct sg_table *pages,
-				   u64 start,
+				   struct i915_vma *vma,
 				   enum i915_cache_level cache_level,
 				   u32 unused)
 {
 	struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
 	struct sgt_dma iter = {
-		.sg = pages->sgl,
+		.sg = vma->pages->sgl,
 		.dma = sg_dma_address(iter.sg),
 		.max = iter.dma + iter.sg->length,
 	};
-	struct gen8_insert_pte idx = gen8_insert_pte(start);
+	struct gen8_insert_pte idx = gen8_insert_pte(vma->node.start);
 
 	gen8_ppgtt_insert_pte_entries(ppgtt, &ppgtt->pdp, &iter, &idx,
 				      cache_level);
 }
 
 static void gen8_ppgtt_insert_4lvl(struct i915_address_space *vm,
-				   struct sg_table *pages,
-				   u64 start,
+				   struct i915_vma *vma,
 				   enum i915_cache_level cache_level,
 				   u32 unused)
 {
 	struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
 	struct sgt_dma iter = {
-		.sg = pages->sgl,
+		.sg = vma->pages->sgl,
 		.dma = sg_dma_address(iter.sg),
 		.max = iter.dma + iter.sg->length,
 	};
 	struct i915_page_directory_pointer **pdps = ppgtt->pml4.pdps;
-	struct gen8_insert_pte idx = gen8_insert_pte(start);
+	struct gen8_insert_pte idx = gen8_insert_pte(vma->node.start);
 
 	while (gen8_ppgtt_insert_pte_entries(ppgtt, pdps[idx.pml4e++], &iter,
 					     &idx, cache_level))
@@ -1621,13 +1623,12 @@ static void gen6_ppgtt_clear_range(struct i915_address_space *vm,
 }
 
 static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
-				      struct sg_table *pages,
-				      u64 start,
+				      struct i915_vma *vma,
 				      enum i915_cache_level cache_level,
 				      u32 flags)
 {
 	struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
-	unsigned first_entry = start >> PAGE_SHIFT;
+	unsigned first_entry = vma->node.start >> PAGE_SHIFT;
 	unsigned act_pt = first_entry / GEN6_PTES;
 	unsigned act_pte = first_entry % GEN6_PTES;
 	const u32 pte_encode = vm->pte_encode(0, cache_level, flags);
@@ -1635,7 +1636,7 @@ static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
 	gen6_pte_t *vaddr;
 
 	vaddr = kmap_atomic_px(ppgtt->pd.page_table[act_pt]);
-	iter.sg = pages->sgl;
+	iter.sg = vma->pages->sgl;
 	iter.dma = sg_dma_address(iter.sg);
 	iter.max = iter.dma + iter.sg->length;
 	do {
@@ -2090,8 +2091,7 @@ static void gen8_ggtt_insert_page(struct i915_address_space *vm,
 }
 
 static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
-				     struct sg_table *st,
-				     u64 start,
+				     struct i915_vma *vma,
 				     enum i915_cache_level level,
 				     u32 unused)
 {
@@ -2102,8 +2102,8 @@ static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
 	dma_addr_t addr;
 
 	gtt_entries = (gen8_pte_t __iomem *)ggtt->gsm;
-	gtt_entries += start >> PAGE_SHIFT;
-	for_each_sgt_dma(addr, sgt_iter, st)
+	gtt_entries += vma->node.start >> PAGE_SHIFT;
+	for_each_sgt_dma(addr, sgt_iter, vma->pages)
 		gen8_set_pte(gtt_entries++, pte_encode | addr);
 
 	wmb();
@@ -2137,17 +2137,16 @@ static void gen6_ggtt_insert_page(struct i915_address_space *vm,
  * mapped BAR (dev_priv->mm.gtt->gtt).
  */
 static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
-				     struct sg_table *st,
-				     u64 start,
+				     struct i915_vma *vma,
 				     enum i915_cache_level level,
 				     u32 flags)
 {
 	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
 	gen6_pte_t __iomem *entries = (gen6_pte_t __iomem *)ggtt->gsm;
-	unsigned int i = start >> PAGE_SHIFT;
+	unsigned int i = vma->node.start >> PAGE_SHIFT;
 	struct sgt_iter iter;
 	dma_addr_t addr;
-	for_each_sgt_dma(addr, iter, st)
+	for_each_sgt_dma(addr, iter, vma->pages)
 		iowrite32(vm->pte_encode(addr, level, flags), &entries[i++]);
 	wmb();
 
@@ -2229,8 +2228,7 @@ static void bxt_vtd_ggtt_insert_page__BKL(struct i915_address_space *vm,
 
 struct insert_entries {
 	struct i915_address_space *vm;
-	struct sg_table *st;
-	u64 start;
+	struct i915_vma *vma;
 	enum i915_cache_level level;
 };
 
@@ -2238,19 +2236,18 @@ static int bxt_vtd_ggtt_insert_entries__cb(void *_arg)
 {
 	struct insert_entries *arg = _arg;
 
-	gen8_ggtt_insert_entries(arg->vm, arg->st, arg->start, arg->level, 0);
+	gen8_ggtt_insert_entries(arg->vm, arg->vma, arg->level, 0);
 	bxt_vtd_ggtt_wa(arg->vm);
 
 	return 0;
 }
 
 static void bxt_vtd_ggtt_insert_entries__BKL(struct i915_address_space *vm,
-					     struct sg_table *st,
-					     u64 start,
+					     struct i915_vma *vma,
 					     enum i915_cache_level level,
 					     u32 unused)
 {
-	struct insert_entries arg = { vm, st, start, level };
+	struct insert_entries arg = { vm, vma, level };
 
 	stop_machine(bxt_vtd_ggtt_insert_entries__cb, &arg, NULL);
 }
@@ -2316,15 +2313,15 @@ static void i915_ggtt_insert_page(struct i915_address_space *vm,
 }
 
 static void i915_ggtt_insert_entries(struct i915_address_space *vm,
-				     struct sg_table *pages,
-				     u64 start,
+				     struct i915_vma *vma,
 				     enum i915_cache_level cache_level,
 				     u32 unused)
 {
 	unsigned int flags = (cache_level == I915_CACHE_NONE) ?
 		AGP_USER_MEMORY : AGP_USER_CACHED_MEMORY;
 
-	intel_gtt_insert_sg_entries(pages, start >> PAGE_SHIFT, flags);
+	intel_gtt_insert_sg_entries(vma->pages, vma->node.start >> PAGE_SHIFT,
+				    flags);
 }
 
 static void i915_ggtt_clear_range(struct i915_address_space *vm,
@@ -2353,8 +2350,7 @@ static int ggtt_bind_vma(struct i915_vma *vma,
 		pte_flags |= PTE_READ_ONLY;
 
 	intel_runtime_pm_get(i915);
-	vma->vm->insert_entries(vma->vm, vma->pages, vma->node.start,
-				cache_level, pte_flags);
+	vma->vm->insert_entries(vma->vm, vma, cache_level, pte_flags);
 	intel_runtime_pm_put(i915);
 
 	/*
@@ -2407,16 +2403,13 @@ static int aliasing_gtt_bind_vma(struct i915_vma *vma,
 				goto err_pages;
 		}
 
-		appgtt->base.insert_entries(&appgtt->base,
-					    vma->pages, vma->node.start,
-					    cache_level, pte_flags);
+		appgtt->base.insert_entries(&appgtt->base, vma, cache_level,
+					    pte_flags);
 	}
 
 	if (flags & I915_VMA_GLOBAL_BIND) {
 		intel_runtime_pm_get(i915);
-		vma->vm->insert_entries(vma->vm,
-					vma->pages, vma->node.start,
-					cache_level, pte_flags);
+		vma->vm->insert_entries(vma->vm, vma, cache_level, pte_flags);
 		intel_runtime_pm_put(i915);
 	}
 
@@ -2749,6 +2742,24 @@ static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size)
 	return 0;
 }
 
+static void cnl_setup_private_ppat(struct drm_i915_private *dev_priv)
+{
+	/* XXX: spec is unclear if this is still needed for CNL+ */
+	if (!USES_PPGTT(dev_priv)) {
+		I915_WRITE(GEN10_PAT_INDEX(0), GEN8_PPAT_UC);
+		return;
+	}
+
+	I915_WRITE(GEN10_PAT_INDEX(0), GEN8_PPAT_WB | GEN8_PPAT_LLC);
+	I915_WRITE(GEN10_PAT_INDEX(1), GEN8_PPAT_WC | GEN8_PPAT_LLCELLC);
+	I915_WRITE(GEN10_PAT_INDEX(2), GEN8_PPAT_WT | GEN8_PPAT_LLCELLC);
+	I915_WRITE(GEN10_PAT_INDEX(3), GEN8_PPAT_UC);
+	I915_WRITE(GEN10_PAT_INDEX(4), GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(0));
+	I915_WRITE(GEN10_PAT_INDEX(5), GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(1));
+	I915_WRITE(GEN10_PAT_INDEX(6), GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(2));
+	I915_WRITE(GEN10_PAT_INDEX(7), GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(3));
+}
+
 /* The GGTT and PPGTT need a private PPAT setup in order to handle cacheability
  * bits. When using advanced contexts each context stores its own PAT, but
  * writing this data shouldn't be harmful even in those cases. */
@@ -2863,7 +2874,9 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt)
 
 	ggtt->base.total = (size / sizeof(gen8_pte_t)) << PAGE_SHIFT;
 
-	if (IS_CHERRYVIEW(dev_priv) || IS_GEN9_LP(dev_priv))
+	if (INTEL_GEN(dev_priv) >= 10)
+		cnl_setup_private_ppat(dev_priv);
+	else if (IS_CHERRYVIEW(dev_priv) || IS_GEN9_LP(dev_priv))
 		chv_setup_private_ppat(dev_priv);
 	else
 		bdw_setup_private_ppat(dev_priv);
@@ -3145,7 +3158,9 @@ void i915_gem_restore_gtt_mappings(struct drm_i915_private *dev_priv)
 	ggtt->base.closed = false;
 
 	if (INTEL_GEN(dev_priv) >= 8) {
-		if (IS_CHERRYVIEW(dev_priv) || IS_GEN9_LP(dev_priv))
+		if (INTEL_GEN(dev_priv) >= 10)
+			cnl_setup_private_ppat(dev_priv);
+		else if (IS_CHERRYVIEW(dev_priv) || IS_GEN9_LP(dev_priv))
 			chv_setup_private_ppat(dev_priv);
 		else
 			bdw_setup_private_ppat(dev_priv);