Merge tag 'drm-for-v4.16' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "This seems to have been a comparatively quieter merge window, I assume
  due to holidays etc. The "biggest" change is AMD header cleanups, which
  merge/remove a bunch of them. The AMD gpu scheduler is now being made generic
  with the etnaviv driver wanting to reuse the code, hopefully other drivers
  can go in the same direction.

  Otherwise it's the usual lots of stuff in i915/amdgpu, not so much stuff
  elsewhere.

  Core:
   - Add .last_close and .output_poll_changed helpers to reduce driver footprints
   - Fix plane clipping
   - Improved debug printing support
   - Add panel orientation property
   - Update edid derived properties at edid setting
   - Reduction in fbdev driver footprint
   - Move amdgpu scheduler into core for other drivers to use.

  i915:
   - Selftest and IGT improvements
   - Fast boot prep work on IPS, pipe config
   - HW workarounds for Cannonlake, Geminilake
   - Cannonlake clock and HDMI2.0 fixes
   - GPU cache invalidation and context switch improvements
   - Display planes cleanup
   - New PMU interface for perf queries
   - New firmware support for KBL/SKL
   - Geminilake HW workaround for perforamce
   - Coffeelake stolen memory improvements
   - GPU reset robustness work
   - Cannonlake horizontal plane flipping
   - GVT work

  amdgpu/radeon:
   - RV and Vega header file cleanups (lots of lines gone!)
   - TTM operation context support
   - 48-bit GPUVM support for Vega/RV
   - ECC support for Vega
   - Resizeable BAR support
   - Multi-display sync support
   - Enable swapout for reserved BOs during allocation
   - S3 fixes on Raven
   - GPU reset cleanup and fixes
   - 2+1 level GPU page table

  amdkfd:
   - GFX7/8 SDMA user queues support
   - Hardware scheduling for multiple processes
   - dGPU prep work

  rcar:
   - Added R8A7743/5 support
   - System suspend/resume support

  sun4i:
   - Multi-plane support for YUV formats
   - A83T and LVDS support

  msm:
   - Devfreq support for GPU

  tegra:
   - Prep work for adding Tegra186 support
   - Tegra186 HDMI support
   - HDMI2.0 and zpos support by using generic helpers

  tilcdc:
   - Misc fixes

  omapdrm:
   - Support memory bandwidth limits
   - DSI command mode panel cleanups
   - DMM error handling

  exynos:
   - drop the old IPP subdriver.

  etnaviv:
   - Occlusion query fixes
   - Job handling fixes
   - Prep work for hooking in gpu scheduler

  armada:
   - Move closer to atomic modesetting
   - Allow disabling primary plane if overlay is full screen

  imx:
   - Format modifier support
   - Add tile prefetch to PRE
   - Runtime PM support for PRG

  ast:
   - fix LUT loading"

* tag 'drm-for-v4.16' of git://people.freedesktop.org/~airlied/linux: (1471 commits)
  drm/ast: Load lut in crtc_commit
  drm: Check for lessee in DROP_MASTER ioctl
  drm: fix gpu scheduler link order
  drm/amd/display: Demote error print to debug print when ATOM impl missing
  dma-buf: fix reservation_object_wait_timeout_rcu once more v2
  drm/amdgpu: Avoid leaking PM domain on driver unbind (v2)
  drm/amd/amdgpu: Add Polaris version check
  drm/amdgpu: Reenable manual GPU reset from sysfs
  drm/amdgpu: disable MMHUB power gating on raven
  drm/ttm: Don't unreserve swapped BOs that were previously reserved
  drm/ttm: Don't add swapped BOs to swap-LRU list
  drm/amdgpu: only check for ECC on Vega10
  drm/amd/powerplay: Fix smu_table_entry.handle type
  drm/ttm: add VADDR_FLAG_UPDATED_COUNT to correctly update dma_page global count
  drm: Fix PANEL_ORIENTATION_QUIRKS breaking the Kconfig DRM menuconfig
  drm/radeon: fill in rb backend map on evergreen/ni.
  drm/amdgpu/gfx9: fix ngg enablement to clear gds reserved memory (v2)
  drm/ttm: only free pages rather than update global memory count together
  drm/amdgpu: fix CPU based VM updates
  drm/amdgpu: fix typo in amdgpu_vce_validate_bo
  ...

1 files changed, 89 insertions, 103 deletions

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 2af65ecf2df8..c5f393870532 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -178,7 +178,7 @@ int intel_sanitize_enable_ppgtt(struct drm_i915_private *dev_priv,
 		return 0;
 	}
 
-	if (INTEL_GEN(dev_priv) >= 8 && i915_modparams.enable_execlists) {
+	if (HAS_LOGICAL_RING_CONTEXTS(dev_priv)) {
 		if (has_full_48bit_ppgtt)
 			return 3;
 
@@ -454,6 +454,14 @@ static void vm_free_pages_release(struct i915_address_space *vm,
 
 static void vm_free_page(struct i915_address_space *vm, struct page *page)
 {
+	/*
+	 * On !llc, we need to change the pages back to WB. We only do so
+	 * in bulk, so we rarely need to change the page attributes here,
+	 * but doing so requires a stop_machine() from deep inside arch/x86/mm.
+	 * To make detection of the possible sleep more likely, use an
+	 * unconditional might_sleep() for everybody.
+	 */
+	might_sleep();
 	if (!pagevec_add(&vm->free_pages, page))
 		vm_free_pages_release(vm, false);
 }
@@ -2154,7 +2162,7 @@ int i915_ppgtt_init_hw(struct drm_i915_private *dev_priv)
 	/* In the case of execlists, PPGTT is enabled by the context descriptor
 	 * and the PDPs are contained within the context itself.  We don't
 	 * need to do anything here. */
-	if (i915_modparams.enable_execlists)
+	if (HAS_LOGICAL_RING_CONTEXTS(dev_priv))
 		return 0;
 
 	if (!USES_PPGTT(dev_priv))
@@ -2248,35 +2256,62 @@ static bool needs_idle_maps(struct drm_i915_private *dev_priv)
 	return IS_GEN5(dev_priv) && IS_MOBILE(dev_priv) && intel_vtd_active();
 }
 
-void i915_check_and_clear_faults(struct drm_i915_private *dev_priv)
+static void gen6_check_and_clear_faults(struct drm_i915_private *dev_priv)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
-
-	if (INTEL_INFO(dev_priv)->gen < 6)
-		return;
+	u32 fault;
 
 	for_each_engine(engine, dev_priv, id) {
-		u32 fault_reg;
-		fault_reg = I915_READ(RING_FAULT_REG(engine));
-		if (fault_reg & RING_FAULT_VALID) {
+		fault = I915_READ(RING_FAULT_REG(engine));
+		if (fault & RING_FAULT_VALID) {
 			DRM_DEBUG_DRIVER("Unexpected fault\n"
 					 "\tAddr: 0x%08lx\n"
 					 "\tAddress space: %s\n"
 					 "\tSource ID: %d\n"
 					 "\tType: %d\n",
-					 fault_reg & PAGE_MASK,
-					 fault_reg & RING_FAULT_GTTSEL_MASK ? "GGTT" : "PPGTT",
-					 RING_FAULT_SRCID(fault_reg),
-					 RING_FAULT_FAULT_TYPE(fault_reg));
+					 fault & PAGE_MASK,
+					 fault & RING_FAULT_GTTSEL_MASK ? "GGTT" : "PPGTT",
+					 RING_FAULT_SRCID(fault),
+					 RING_FAULT_FAULT_TYPE(fault));
 			I915_WRITE(RING_FAULT_REG(engine),
-				   fault_reg & ~RING_FAULT_VALID);
+				   fault & ~RING_FAULT_VALID);
 		}
 	}
 
-	/* Engine specific init may not have been done till this point. */
-	if (dev_priv->engine[RCS])
-		POSTING_READ(RING_FAULT_REG(dev_priv->engine[RCS]));
+	POSTING_READ(RING_FAULT_REG(dev_priv->engine[RCS]));
+}
+
+static void gen8_check_and_clear_faults(struct drm_i915_private *dev_priv)
+{
+	u32 fault = I915_READ(GEN8_RING_FAULT_REG);
+
+	if (fault & RING_FAULT_VALID) {
+		DRM_DEBUG_DRIVER("Unexpected fault\n"
+				 "\tAddr: 0x%08lx\n"
+				 "\tEngine ID: %d\n"
+				 "\tSource ID: %d\n"
+				 "\tType: %d\n",
+				 fault & PAGE_MASK,
+				 GEN8_RING_FAULT_ENGINE_ID(fault),
+				 RING_FAULT_SRCID(fault),
+				 RING_FAULT_FAULT_TYPE(fault));
+		I915_WRITE(GEN8_RING_FAULT_REG,
+			   fault & ~RING_FAULT_VALID);
+	}
+
+	POSTING_READ(GEN8_RING_FAULT_REG);
+}
+
+void i915_check_and_clear_faults(struct drm_i915_private *dev_priv)
+{
+	/* From GEN8 onwards we only have one 'All Engine Fault Register' */
+	if (INTEL_GEN(dev_priv) >= 8)
+		gen8_check_and_clear_faults(dev_priv);
+	else if (INTEL_GEN(dev_priv) >= 6)
+		gen6_check_and_clear_faults(dev_priv);
+	else
+		return;
 }
 
 void i915_gem_suspend_gtt_mappings(struct drm_i915_private *dev_priv)
@@ -2877,7 +2912,7 @@ void i915_ggtt_cleanup_hw(struct drm_i915_private *dev_priv)
 	mutex_unlock(&dev_priv->drm.struct_mutex);
 
 	arch_phys_wc_del(ggtt->mtrr);
-	io_mapping_fini(&ggtt->mappable);
+	io_mapping_fini(&ggtt->iomap);
 }
 
 static unsigned int gen6_get_total_gtt_size(u16 snb_gmch_ctl)
@@ -2914,50 +2949,6 @@ static unsigned int chv_get_total_gtt_size(u16 gmch_ctrl)
 	return 0;
 }
 
-static size_t gen6_get_stolen_size(u16 snb_gmch_ctl)
-{
-	snb_gmch_ctl >>= SNB_GMCH_GMS_SHIFT;
-	snb_gmch_ctl &= SNB_GMCH_GMS_MASK;
-	return (size_t)snb_gmch_ctl << 25; /* 32 MB units */
-}
-
-static size_t gen8_get_stolen_size(u16 bdw_gmch_ctl)
-{
-	bdw_gmch_ctl >>= BDW_GMCH_GMS_SHIFT;
-	bdw_gmch_ctl &= BDW_GMCH_GMS_MASK;
-	return (size_t)bdw_gmch_ctl << 25; /* 32 MB units */
-}
-
-static size_t chv_get_stolen_size(u16 gmch_ctrl)
-{
-	gmch_ctrl >>= SNB_GMCH_GMS_SHIFT;
-	gmch_ctrl &= SNB_GMCH_GMS_MASK;
-
-	/*
-	 * 0x0  to 0x10: 32MB increments starting at 0MB
-	 * 0x11 to 0x16: 4MB increments starting at 8MB
-	 * 0x17 to 0x1d: 4MB increments start at 36MB
-	 */
-	if (gmch_ctrl < 0x11)
-		return (size_t)gmch_ctrl << 25;
-	else if (gmch_ctrl < 0x17)
-		return (size_t)(gmch_ctrl - 0x11 + 2) << 22;
-	else
-		return (size_t)(gmch_ctrl - 0x17 + 9) << 22;
-}
-
-static size_t gen9_get_stolen_size(u16 gen9_gmch_ctl)
-{
-	gen9_gmch_ctl >>= BDW_GMCH_GMS_SHIFT;
-	gen9_gmch_ctl &= BDW_GMCH_GMS_MASK;
-
-	if (gen9_gmch_ctl < 0xf0)
-		return (size_t)gen9_gmch_ctl << 25; /* 32 MB units */
-	else
-		/* 4MB increments starting at 0xf0 for 4MB */
-		return (size_t)(gen9_gmch_ctl - 0xf0 + 1) << 22;
-}
-
 static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size)
 {
 	struct drm_i915_private *dev_priv = ggtt->base.i915;
@@ -3041,7 +3032,7 @@ const struct intel_ppat_entry *
 intel_ppat_get(struct drm_i915_private *i915, u8 value)
 {
 	struct intel_ppat *ppat = &i915->ppat;
-	struct intel_ppat_entry *entry;
+	struct intel_ppat_entry *entry = NULL;
 	unsigned int scanned, best_score;
 	int i;
 
@@ -3064,7 +3055,7 @@ intel_ppat_get(struct drm_i915_private *i915, u8 value)
 	}
 
 	if (scanned == ppat->max_entries) {
-		if (!best_score)
+		if (!entry)
 			return ERR_PTR(-ENOSPC);
 
 		kref_get(&entry->ref);
@@ -3171,12 +3162,6 @@ static void cnl_setup_private_ppat(struct intel_ppat *ppat)
 	ppat->match = bdw_private_pat_match;
 	ppat->clear_value = GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(3);
 
-	/* XXX: spec is unclear if this is still needed for CNL+ */
-	if (!USES_PPGTT(ppat->i915)) {
-		__alloc_ppat_entry(ppat, 0, GEN8_PPAT_UC);
-		return;
-	}
-
 	__alloc_ppat_entry(ppat, 0, GEN8_PPAT_WB | GEN8_PPAT_LLC);
 	__alloc_ppat_entry(ppat, 1, GEN8_PPAT_WC | GEN8_PPAT_LLCELLC);
 	__alloc_ppat_entry(ppat, 2, GEN8_PPAT_WT | GEN8_PPAT_LLCELLC);
@@ -3303,8 +3288,10 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt)
 	int err;
 
 	/* TODO: We're not aware of mappable constraints on gen8 yet */
-	ggtt->mappable_base = pci_resource_start(pdev, 2);
-	ggtt->mappable_end = pci_resource_len(pdev, 2);
+	ggtt->gmadr =
+		(struct resource) DEFINE_RES_MEM(pci_resource_start(pdev, 2),
+						 pci_resource_len(pdev, 2));
+	ggtt->mappable_end = resource_size(&ggtt->gmadr);
 
 	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(39));
 	if (!err)
@@ -3315,13 +3302,10 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt)
 	pci_read_config_word(pdev, SNB_GMCH_CTRL, &snb_gmch_ctl);
 
 	if (INTEL_GEN(dev_priv) >= 9) {
-		ggtt->stolen_size = gen9_get_stolen_size(snb_gmch_ctl);
 		size = gen8_get_total_gtt_size(snb_gmch_ctl);
 	} else if (IS_CHERRYVIEW(dev_priv)) {
-		ggtt->stolen_size = chv_get_stolen_size(snb_gmch_ctl);
 		size = chv_get_total_gtt_size(snb_gmch_ctl);
 	} else {
-		ggtt->stolen_size = gen8_get_stolen_size(snb_gmch_ctl);
 		size = gen8_get_total_gtt_size(snb_gmch_ctl);
 	}
 
@@ -3361,14 +3345,16 @@ static int gen6_gmch_probe(struct i915_ggtt *ggtt)
 	u16 snb_gmch_ctl;
 	int err;
 
-	ggtt->mappable_base = pci_resource_start(pdev, 2);
-	ggtt->mappable_end = pci_resource_len(pdev, 2);
+	ggtt->gmadr =
+		(struct resource) DEFINE_RES_MEM(pci_resource_start(pdev, 2),
+						 pci_resource_len(pdev, 2));
+	ggtt->mappable_end = resource_size(&ggtt->gmadr);
 
 	/* 64/512MB is the current min/max we actually know of, but this is just
 	 * a coarse sanity check.
 	 */
 	if (ggtt->mappable_end < (64<<20) || ggtt->mappable_end > (512<<20)) {
-		DRM_ERROR("Unknown GMADR size (%llx)\n", ggtt->mappable_end);
+		DRM_ERROR("Unknown GMADR size (%pa)\n", &ggtt->mappable_end);
 		return -ENXIO;
 	}
 
@@ -3379,8 +3365,6 @@ static int gen6_gmch_probe(struct i915_ggtt *ggtt)
 		DRM_ERROR("Can't set DMA mask/consistent mask (%d)\n", err);
 	pci_read_config_word(pdev, SNB_GMCH_CTRL, &snb_gmch_ctl);
 
-	ggtt->stolen_size = gen6_get_stolen_size(snb_gmch_ctl);
-
 	size = gen6_get_total_gtt_size(snb_gmch_ctl);
 	ggtt->base.total = (size / sizeof(gen6_pte_t)) << PAGE_SHIFT;
 
@@ -3417,6 +3401,7 @@ static void i915_gmch_remove(struct i915_address_space *vm)
 static int i915_gmch_probe(struct i915_ggtt *ggtt)
 {
 	struct drm_i915_private *dev_priv = ggtt->base.i915;
+	phys_addr_t gmadr_base;
 	int ret;
 
 	ret = intel_gmch_probe(dev_priv->bridge_dev, dev_priv->drm.pdev, NULL);
@@ -3426,10 +3411,13 @@ static int i915_gmch_probe(struct i915_ggtt *ggtt)
 	}
 
 	intel_gtt_get(&ggtt->base.total,
-		      &ggtt->stolen_size,
-		      &ggtt->mappable_base,
+		      &gmadr_base,
 		      &ggtt->mappable_end);
 
+	ggtt->gmadr =
+		(struct resource) DEFINE_RES_MEM(gmadr_base,
+						 ggtt->mappable_end);
+
 	ggtt->do_idle_maps = needs_idle_maps(dev_priv);
 	ggtt->base.insert_page = i915_ggtt_insert_page;
 	ggtt->base.insert_entries = i915_ggtt_insert_entries;
@@ -3474,9 +3462,9 @@ int i915_ggtt_probe_hw(struct drm_i915_private *dev_priv)
 	 * currently don't have any bits spare to pass in this upper
 	 * restriction!
 	 */
-	if (HAS_GUC(dev_priv) && i915_modparams.enable_guc_loading) {
+	if (USES_GUC(dev_priv)) {
 		ggtt->base.total = min_t(u64, ggtt->base.total, GUC_GGTT_TOP);
-		ggtt->mappable_end = min(ggtt->mappable_end, ggtt->base.total);
+		ggtt->mappable_end = min_t(u64, ggtt->mappable_end, ggtt->base.total);
 	}
 
 	if ((ggtt->base.total - 1) >> 32) {
@@ -3484,21 +3472,21 @@ int i915_ggtt_probe_hw(struct drm_i915_private *dev_priv)
 			  " of address space! Found %lldM!\n",
 			  ggtt->base.total >> 20);
 		ggtt->base.total = 1ULL << 32;
-		ggtt->mappable_end = min(ggtt->mappable_end, ggtt->base.total);
+		ggtt->mappable_end = min_t(u64, ggtt->mappable_end, ggtt->base.total);
 	}
 
 	if (ggtt->mappable_end > ggtt->base.total) {
 		DRM_ERROR("mappable aperture extends past end of GGTT,"
-			  " aperture=%llx, total=%llx\n",
-			  ggtt->mappable_end, ggtt->base.total);
+			  " aperture=%pa, total=%llx\n",
+			  &ggtt->mappable_end, ggtt->base.total);
 		ggtt->mappable_end = ggtt->base.total;
 	}
 
 	/* GMADR is the PCI mmio aperture into the global GTT. */
-	DRM_INFO("Memory usable by graphics device = %lluM\n",
-		 ggtt->base.total >> 20);
-	DRM_DEBUG_DRIVER("GMADR size = %lldM\n", ggtt->mappable_end >> 20);
-	DRM_DEBUG_DRIVER("GTT stolen size = %uM\n", ggtt->stolen_size >> 20);
+	DRM_DEBUG_DRIVER("GGTT size = %lluM\n", ggtt->base.total >> 20);
+	DRM_DEBUG_DRIVER("GMADR size = %lluM\n", (u64)ggtt->mappable_end >> 20);
+	DRM_DEBUG_DRIVER("DSM size = %lluM\n",
+			 (u64)resource_size(&intel_graphics_stolen_res) >> 20);
 	if (intel_vtd_active())
 		DRM_INFO("VT-d active for gfx access\n");
 
@@ -3527,14 +3515,14 @@ int i915_ggtt_init_hw(struct drm_i915_private *dev_priv)
 		ggtt->base.mm.color_adjust = i915_gtt_color_adjust;
 	mutex_unlock(&dev_priv->drm.struct_mutex);
 
-	if (!io_mapping_init_wc(&dev_priv->ggtt.mappable,
-				dev_priv->ggtt.mappable_base,
+	if (!io_mapping_init_wc(&dev_priv->ggtt.iomap,
+				dev_priv->ggtt.gmadr.start,
 				dev_priv->ggtt.mappable_end)) {
 		ret = -EIO;
 		goto out_gtt_cleanup;
 	}
 
-	ggtt->mtrr = arch_phys_wc_add(ggtt->mappable_base, ggtt->mappable_end);
+	ggtt->mtrr = arch_phys_wc_add(ggtt->gmadr.start, ggtt->mappable_end);
 
 	/*
 	 * Initialise stolen early so that we may reserve preallocated
@@ -3564,6 +3552,8 @@ void i915_ggtt_enable_guc(struct drm_i915_private *i915)
 	GEM_BUG_ON(i915->ggtt.invalidate != gen6_ggtt_invalidate);
 
 	i915->ggtt.invalidate = guc_ggtt_invalidate;
+
+	i915_ggtt_invalidate(i915);
 }
 
 void i915_ggtt_disable_guc(struct drm_i915_private *i915)
@@ -3572,6 +3562,8 @@ void i915_ggtt_disable_guc(struct drm_i915_private *i915)
 	GEM_BUG_ON(i915->ggtt.invalidate != guc_ggtt_invalidate);
 
 	i915->ggtt.invalidate = gen6_ggtt_invalidate;
+
+	i915_ggtt_invalidate(i915);
 }
 
 void i915_gem_restore_gtt_mappings(struct drm_i915_private *dev_priv)
@@ -3591,10 +3583,7 @@ void i915_gem_restore_gtt_mappings(struct drm_i915_private *dev_priv)
 		bool ggtt_bound = false;
 		struct i915_vma *vma;
 
-		list_for_each_entry(vma, &obj->vma_list, obj_link) {
-			if (vma->vm != &ggtt->base)
-				continue;
-
+		for_each_ggtt_vma(vma, obj) {
 			if (!i915_vma_unbind(vma))
 				continue;
 
@@ -3708,9 +3697,6 @@ intel_rotate_pages(struct intel_rotation_info *rot_info,
 				  rot_info->plane[i].stride, st, sg);
 	}
 
-	DRM_DEBUG_KMS("Created rotated page mapping for object size %zu (%ux%u tiles, %u pages)\n",
-		      obj->base.size, rot_info->plane[0].width, rot_info->plane[0].height, size);
-
 	kvfree(page_addr_list);
 
 	return st;
@@ -3720,8 +3706,8 @@ err_sg_alloc:
 err_st_alloc:
 	kvfree(page_addr_list);
 
-	DRM_DEBUG_KMS("Failed to create rotated mapping for object size %zu! (%ux%u tiles, %u pages)\n",
-		      obj->base.size, rot_info->plane[0].width, rot_info->plane[0].height, size);
+	DRM_DEBUG_DRIVER("Failed to create rotated mapping for object size %zu! (%ux%u tiles, %u pages)\n",
+			 obj->base.size, rot_info->plane[0].width, rot_info->plane[0].height, size);
 
 	return ERR_PTR(ret);
 }