1 files changed, 417 insertions, 111 deletions

diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c
index ada2e90a2a6..7465ab0fd39 100644
--- a/drivers/gpu/drm/i915/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/i915_gem_stolen.c
@@ -26,9 +26,8 @@
  *
  */
 
-#include "drmP.h"
-#include "drm.h"
-#include "i915_drm.h"
+#include <drm/drmP.h>
+#include <drm/i915_drm.h>
 #include "i915_drv.h"
 
 /*
@@ -43,160 +42,467 @@
  * for is a boon.
  */
 
-#define PTE_ADDRESS_MASK		0xfffff000
-#define PTE_ADDRESS_MASK_HIGH		0x000000f0 /* i915+ */
-#define PTE_MAPPING_TYPE_UNCACHED	(0 << 1)
-#define PTE_MAPPING_TYPE_DCACHE		(1 << 1) /* i830 only */
-#define PTE_MAPPING_TYPE_CACHED		(3 << 1)
-#define PTE_MAPPING_TYPE_MASK		(3 << 1)
-#define PTE_VALID			(1 << 0)
-
-/**
- * i915_stolen_to_phys - take an offset into stolen memory and turn it into
- *                       a physical one
- * @dev: drm device
- * @offset: address to translate
- *
- * Some chip functions require allocations from stolen space and need the
- * physical address of the memory in question.
- */
-static unsigned long i915_stolen_to_phys(struct drm_device *dev, u32 offset)
+static unsigned long i915_stolen_to_physical(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct pci_dev *pdev = dev_priv->bridge_dev;
+	struct resource *r;
 	u32 base;
 
-#if 0
-	/* On the machines I have tested the Graphics Base of Stolen Memory
-	 * is unreliable, so compute the base by subtracting the stolen memory
-	 * from the Top of Low Usable DRAM which is where the BIOS places
-	 * the graphics stolen memory.
+	/* Almost universally we can find the Graphics Base of Stolen Memory
+	 * at offset 0x5c in the igfx configuration space. On a few (desktop)
+	 * machines this is also mirrored in the bridge device at different
+	 * locations, or in the MCHBAR. On gen2, the layout is again slightly
+	 * different with the Graphics Segment immediately following Top of
+	 * Memory (or Top of Usable DRAM). Note it appears that TOUD is only
+	 * reported by 865g, so we just use the top of memory as determined
+	 * by the e820 probe.
+	 *
+	 * XXX However gen2 requires an unavailable symbol.
 	 */
-	if (INTEL_INFO(dev)->gen > 3 || IS_G33(dev)) {
-		/* top 32bits are reserved = 0 */
-		pci_read_config_dword(pdev, 0xA4, &base);
-	} else {
-		/* XXX presume 8xx is the same as i915 */
-		pci_bus_read_config_dword(pdev->bus, 2, 0x5C, &base);
+	base = 0;
+	if (INTEL_INFO(dev)->gen >= 3) {
+		/* Read Graphics Base of Stolen Memory directly */
+		pci_read_config_dword(dev->pdev, 0x5c, &base);
+		base &= ~((1<<20) - 1);
+	} else { /* GEN2 */
+#if 0
+		/* Stolen is immediately above Top of Memory */
+		base = max_low_pfn_mapped << PAGE_SHIFT;
+#endif
 	}
-#else
-	if (INTEL_INFO(dev)->gen > 3 || IS_G33(dev)) {
-		u16 val;
-		pci_read_config_word(pdev, 0xb0, &val);
-		base = val >> 4 << 20;
-	} else {
-		u8 val;
-		pci_read_config_byte(pdev, 0x9c, &val);
-		base = val >> 3 << 27;
+
+	if (base == 0)
+		return 0;
+
+	/* make sure we don't clobber the GTT if it's within stolen memory */
+	if (INTEL_INFO(dev)->gen <= 4 && !IS_G33(dev) && !IS_G4X(dev)) {
+		struct {
+			u32 start, end;
+		} stolen[2] = {
+			{ .start = base, .end = base + dev_priv->gtt.stolen_size, },
+			{ .start = base, .end = base + dev_priv->gtt.stolen_size, },
+		};
+		u64 gtt_start, gtt_end;
+
+		gtt_start = I915_READ(PGTBL_CTL);
+		if (IS_GEN4(dev))
+			gtt_start = (gtt_start & PGTBL_ADDRESS_LO_MASK) |
+				(gtt_start & PGTBL_ADDRESS_HI_MASK) << 28;
+		else
+			gtt_start &= PGTBL_ADDRESS_LO_MASK;
+		gtt_end = gtt_start + gtt_total_entries(dev_priv->gtt) * 4;
+
+		if (gtt_start >= stolen[0].start && gtt_start < stolen[0].end)
+			stolen[0].end = gtt_start;
+		if (gtt_end > stolen[1].start && gtt_end <= stolen[1].end)
+			stolen[1].start = gtt_end;
+
+		/* pick the larger of the two chunks */
+		if (stolen[0].end - stolen[0].start >
+		    stolen[1].end - stolen[1].start) {
+			base = stolen[0].start;
+			dev_priv->gtt.stolen_size = stolen[0].end - stolen[0].start;
+		} else {
+			base = stolen[1].start;
+			dev_priv->gtt.stolen_size = stolen[1].end - stolen[1].start;
+		}
+
+		if (stolen[0].start != stolen[1].start ||
+		    stolen[0].end != stolen[1].end) {
+			DRM_DEBUG_KMS("GTT within stolen memory at 0x%llx-0x%llx\n",
+				      (unsigned long long) gtt_start,
+				      (unsigned long long) gtt_end - 1);
+			DRM_DEBUG_KMS("Stolen memory adjusted to 0x%x-0x%x\n",
+				      base, base + (u32) dev_priv->gtt.stolen_size - 1);
+		}
 	}
-	base -= dev_priv->mm.gtt->stolen_size;
-#endif
 
-	return base + offset;
-}
 
-static void i915_warn_stolen(struct drm_device *dev)
-{
-	DRM_INFO("not enough stolen space for compressed buffer, disabling\n");
-	DRM_INFO("hint: you may be able to increase stolen memory size in the BIOS to avoid this\n");
+	/* Verify that nothing else uses this physical address. Stolen
+	 * memory should be reserved by the BIOS and hidden from the
+	 * kernel. So if the region is already marked as busy, something
+	 * is seriously wrong.
+	 */
+	r = devm_request_mem_region(dev->dev, base, dev_priv->gtt.stolen_size,
+				    "Graphics Stolen Memory");
+	if (r == NULL) {
+		/*
+		 * One more attempt but this time requesting region from
+		 * base + 1, as we have seen that this resolves the region
+		 * conflict with the PCI Bus.
+		 * This is a BIOS w/a: Some BIOS wrap stolen in the root
+		 * PCI bus, but have an off-by-one error. Hence retry the
+		 * reservation starting from 1 instead of 0.
+		 */
+		r = devm_request_mem_region(dev->dev, base + 1,
+					    dev_priv->gtt.stolen_size - 1,
+					    "Graphics Stolen Memory");
+		if (r == NULL) {
+			DRM_ERROR("conflict detected with stolen region: [0x%08x - 0x%08x]\n",
+				  base, base + (uint32_t)dev_priv->gtt.stolen_size);
+			base = 0;
+		}
+	}
+
+	return base;
 }
 
-static void i915_setup_compression(struct drm_device *dev, int size)
+static int i915_setup_compression(struct drm_device *dev, int size)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_mm_node *compressed_fb, *uninitialized_var(compressed_llb);
-	unsigned long cfb_base;
-	unsigned long ll_base = 0;
-
-	/* Just in case the BIOS is doing something questionable. */
-	intel_disable_fbc(dev);
+	int ret;
 
-	compressed_fb = drm_mm_search_free(&dev_priv->mm.stolen, size, 4096, 0);
-	if (compressed_fb)
-		compressed_fb = drm_mm_get_block(compressed_fb, size, 4096);
+	compressed_fb = kzalloc(sizeof(*compressed_fb), GFP_KERNEL);
 	if (!compressed_fb)
-		goto err;
-
-	cfb_base = i915_stolen_to_phys(dev, compressed_fb->start);
-	if (!cfb_base)
-		goto err_fb;
-
-	if (!(IS_GM45(dev) || HAS_PCH_SPLIT(dev))) {
-		compressed_llb = drm_mm_search_free(&dev_priv->mm.stolen,
-						    4096, 4096, 0);
-		if (compressed_llb)
-			compressed_llb = drm_mm_get_block(compressed_llb,
-							  4096, 4096);
-		if (!compressed_llb)
-			goto err_fb;
-
-		ll_base = i915_stolen_to_phys(dev, compressed_llb->start);
-		if (!ll_base)
-			goto err_llb;
-	}
+		goto err_llb;
 
-	dev_priv->cfb_size = size;
+	/* Try to over-allocate to reduce reallocations and fragmentation */
+	ret = drm_mm_insert_node(&dev_priv->mm.stolen, compressed_fb,
+				 size <<= 1, 4096, DRM_MM_SEARCH_DEFAULT);
+	if (ret)
+		ret = drm_mm_insert_node(&dev_priv->mm.stolen, compressed_fb,
+					 size >>= 1, 4096,
+					 DRM_MM_SEARCH_DEFAULT);
+	if (ret)
+		goto err_llb;
 
-	dev_priv->compressed_fb = compressed_fb;
 	if (HAS_PCH_SPLIT(dev))
 		I915_WRITE(ILK_DPFC_CB_BASE, compressed_fb->start);
 	else if (IS_GM45(dev)) {
 		I915_WRITE(DPFC_CB_BASE, compressed_fb->start);
 	} else {
-		I915_WRITE(FBC_CFB_BASE, cfb_base);
-		I915_WRITE(FBC_LL_BASE, ll_base);
-		dev_priv->compressed_llb = compressed_llb;
+		compressed_llb = kzalloc(sizeof(*compressed_llb), GFP_KERNEL);
+		if (!compressed_llb)
+			goto err_fb;
+
+		ret = drm_mm_insert_node(&dev_priv->mm.stolen, compressed_llb,
+					 4096, 4096, DRM_MM_SEARCH_DEFAULT);
+		if (ret)
+			goto err_fb;
+
+		dev_priv->fbc.compressed_llb = compressed_llb;
+
+		I915_WRITE(FBC_CFB_BASE,
+			   dev_priv->mm.stolen_base + compressed_fb->start);
+		I915_WRITE(FBC_LL_BASE,
+			   dev_priv->mm.stolen_base + compressed_llb->start);
 	}
 
-	DRM_DEBUG_KMS("FBC base 0x%08lx, ll base 0x%08lx, size %dM\n",
-		      cfb_base, ll_base, size >> 20);
-	return;
+	dev_priv->fbc.compressed_fb = compressed_fb;
+	dev_priv->fbc.size = size;
+
+	DRM_DEBUG_KMS("reserved %d bytes of contiguous stolen space for FBC\n",
+		      size);
+
+	return 0;
 
-err_llb:
-	drm_mm_put_block(compressed_llb);
 err_fb:
-	drm_mm_put_block(compressed_fb);
-err:
-	dev_priv->no_fbc_reason = FBC_STOLEN_TOO_SMALL;
-	i915_warn_stolen(dev);
+	kfree(compressed_llb);
+	drm_mm_remove_node(compressed_fb);
+err_llb:
+	kfree(compressed_fb);
+	pr_info_once("drm: not enough stolen space for compressed buffer (need %d more bytes), disabling. Hint: you may be able to increase stolen memory size in the BIOS to avoid this.\n", size);
+	return -ENOSPC;
+}
+
+int i915_gem_stolen_setup_compression(struct drm_device *dev, int size)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (!drm_mm_initialized(&dev_priv->mm.stolen))
+		return -ENODEV;
+
+	if (size < dev_priv->fbc.size)
+		return 0;
+
+	/* Release any current block */
+	i915_gem_stolen_cleanup_compression(dev);
+
+	return i915_setup_compression(dev, size);
 }
 
-static void i915_cleanup_compression(struct drm_device *dev)
+void i915_gem_stolen_cleanup_compression(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	drm_mm_put_block(dev_priv->compressed_fb);
-	if (dev_priv->compressed_llb)
-		drm_mm_put_block(dev_priv->compressed_llb);
+	if (dev_priv->fbc.size == 0)
+		return;
+
+	if (dev_priv->fbc.compressed_fb) {
+		drm_mm_remove_node(dev_priv->fbc.compressed_fb);
+		kfree(dev_priv->fbc.compressed_fb);
+	}
+
+	if (dev_priv->fbc.compressed_llb) {
+		drm_mm_remove_node(dev_priv->fbc.compressed_llb);
+		kfree(dev_priv->fbc.compressed_llb);
+	}
+
+	dev_priv->fbc.size = 0;
 }
 
 void i915_gem_cleanup_stolen(struct drm_device *dev)
 {
-	if (I915_HAS_FBC(dev) && i915_powersave)
-		i915_cleanup_compression(dev);
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (!drm_mm_initialized(&dev_priv->mm.stolen))
+		return;
+
+	i915_gem_stolen_cleanup_compression(dev);
+	drm_mm_takedown(&dev_priv->mm.stolen);
 }
 
 int i915_gem_init_stolen(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	unsigned long prealloc_size = dev_priv->mm.gtt->stolen_size;
+	int bios_reserved = 0;
+
+#ifdef CONFIG_INTEL_IOMMU
+	if (intel_iommu_gfx_mapped && INTEL_INFO(dev)->gen < 8) {
+		DRM_INFO("DMAR active, disabling use of stolen memory\n");
+		return 0;
+	}
+#endif
+
+	if (dev_priv->gtt.stolen_size == 0)
+		return 0;
+
+	dev_priv->mm.stolen_base = i915_stolen_to_physical(dev);
+	if (dev_priv->mm.stolen_base == 0)
+		return 0;
+
+	DRM_DEBUG_KMS("found %zd bytes of stolen memory at %08lx\n",
+		      dev_priv->gtt.stolen_size, dev_priv->mm.stolen_base);
+
+	if (IS_VALLEYVIEW(dev))
+		bios_reserved = 1024*1024; /* top 1M on VLV/BYT */
+
+	if (WARN_ON(bios_reserved > dev_priv->gtt.stolen_size))
+		return 0;
 
 	/* Basic memrange allocator for stolen space */
-	drm_mm_init(&dev_priv->mm.stolen, 0, prealloc_size);
+	drm_mm_init(&dev_priv->mm.stolen, 0, dev_priv->gtt.stolen_size -
+		    bios_reserved);
 
-	/* Try to set up FBC with a reasonable compressed buffer size */
-	if (I915_HAS_FBC(dev) && i915_powersave) {
-		int cfb_size;
+	return 0;
+}
 
-		/* Leave 1M for line length buffer & misc. */
+static struct sg_table *
+i915_pages_create_for_stolen(struct drm_device *dev,
+			     u32 offset, u32 size)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct sg_table *st;
+	struct scatterlist *sg;
 
-		/* Try to get a 32M buffer... */
-		if (prealloc_size > (36*1024*1024))
-			cfb_size = 32*1024*1024;
-		else /* fall back to 7/8 of the stolen space */
-			cfb_size = prealloc_size * 7 / 8;
-		i915_setup_compression(dev, cfb_size);
+	DRM_DEBUG_DRIVER("offset=0x%x, size=%d\n", offset, size);
+	BUG_ON(offset > dev_priv->gtt.stolen_size - size);
+
+	/* We hide that we have no struct page backing our stolen object
+	 * by wrapping the contiguous physical allocation with a fake
+	 * dma mapping in a single scatterlist.
+	 */
+
+	st = kmalloc(sizeof(*st), GFP_KERNEL);
+	if (st == NULL)
+		return NULL;
+
+	if (sg_alloc_table(st, 1, GFP_KERNEL)) {
+		kfree(st);
+		return NULL;
 	}
 
-	return 0;
+	sg = st->sgl;
+	sg->offset = 0;
+	sg->length = size;
+
+	sg_dma_address(sg) = (dma_addr_t)dev_priv->mm.stolen_base + offset;
+	sg_dma_len(sg) = size;
+
+	return st;
+}
+
+static int i915_gem_object_get_pages_stolen(struct drm_i915_gem_object *obj)
+{
+	BUG();
+	return -EINVAL;
+}
+
+static void i915_gem_object_put_pages_stolen(struct drm_i915_gem_object *obj)
+{
+	/* Should only be called during free */
+	sg_free_table(obj->pages);
+	kfree(obj->pages);
+}
+
+static const struct drm_i915_gem_object_ops i915_gem_object_stolen_ops = {
+	.get_pages = i915_gem_object_get_pages_stolen,
+	.put_pages = i915_gem_object_put_pages_stolen,
+};
+
+static struct drm_i915_gem_object *
+_i915_gem_object_create_stolen(struct drm_device *dev,
+			       struct drm_mm_node *stolen)
+{
+	struct drm_i915_gem_object *obj;
+
+	obj = i915_gem_object_alloc(dev);
+	if (obj == NULL)
+		return NULL;
+
+	drm_gem_private_object_init(dev, &obj->base, stolen->size);
+	i915_gem_object_init(obj, &i915_gem_object_stolen_ops);
+
+	obj->pages = i915_pages_create_for_stolen(dev,
+						  stolen->start, stolen->size);
+	if (obj->pages == NULL)
+		goto cleanup;
+
+	obj->has_dma_mapping = true;
+	i915_gem_object_pin_pages(obj);
+	obj->stolen = stolen;
+
+	obj->base.read_domains = I915_GEM_DOMAIN_CPU | I915_GEM_DOMAIN_GTT;
+	obj->cache_level = HAS_LLC(dev) ? I915_CACHE_LLC : I915_CACHE_NONE;
+
+	return obj;
+
+cleanup:
+	i915_gem_object_free(obj);
+	return NULL;
+}
+
+struct drm_i915_gem_object *
+i915_gem_object_create_stolen(struct drm_device *dev, u32 size)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_gem_object *obj;
+	struct drm_mm_node *stolen;
+	int ret;
+
+	if (!drm_mm_initialized(&dev_priv->mm.stolen))
+		return NULL;
+
+	DRM_DEBUG_KMS("creating stolen object: size=%x\n", size);
+	if (size == 0)
+		return NULL;
+
+	stolen = kzalloc(sizeof(*stolen), GFP_KERNEL);
+	if (!stolen)
+		return NULL;
+
+	ret = drm_mm_insert_node(&dev_priv->mm.stolen, stolen, size,
+				 4096, DRM_MM_SEARCH_DEFAULT);
+	if (ret) {
+		kfree(stolen);
+		return NULL;
+	}
+
+	obj = _i915_gem_object_create_stolen(dev, stolen);
+	if (obj)
+		return obj;
+
+	drm_mm_remove_node(stolen);
+	kfree(stolen);
+	return NULL;
+}
+
+struct drm_i915_gem_object *
+i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev,
+					       u32 stolen_offset,
+					       u32 gtt_offset,
+					       u32 size)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct i915_address_space *ggtt = &dev_priv->gtt.base;
+	struct drm_i915_gem_object *obj;
+	struct drm_mm_node *stolen;
+	struct i915_vma *vma;
+	int ret;
+
+	if (!drm_mm_initialized(&dev_priv->mm.stolen))
+		return NULL;
+
+	DRM_DEBUG_KMS("creating preallocated stolen object: stolen_offset=%x, gtt_offset=%x, size=%x\n",
+			stolen_offset, gtt_offset, size);
+
+	/* KISS and expect everything to be page-aligned */
+	BUG_ON(stolen_offset & 4095);
+	BUG_ON(size & 4095);
+
+	if (WARN_ON(size == 0))
+		return NULL;
+
+	stolen = kzalloc(sizeof(*stolen), GFP_KERNEL);
+	if (!stolen)
+		return NULL;
+
+	stolen->start = stolen_offset;
+	stolen->size = size;
+	ret = drm_mm_reserve_node(&dev_priv->mm.stolen, stolen);
+	if (ret) {
+		DRM_DEBUG_KMS("failed to allocate stolen space\n");
+		kfree(stolen);
+		return NULL;
+	}
+
+	obj = _i915_gem_object_create_stolen(dev, stolen);
+	if (obj == NULL) {
+		DRM_DEBUG_KMS("failed to allocate stolen object\n");
+		drm_mm_remove_node(stolen);
+		kfree(stolen);
+		return NULL;
+	}
+
+	/* Some objects just need physical mem from stolen space */
+	if (gtt_offset == I915_GTT_OFFSET_NONE)
+		return obj;
+
+	vma = i915_gem_obj_lookup_or_create_vma(obj, ggtt);
+	if (IS_ERR(vma)) {
+		ret = PTR_ERR(vma);
+		goto err_out;
+	}
+
+	/* To simplify the initialisation sequence between KMS and GTT,
+	 * we allow construction of the stolen object prior to
+	 * setting up the GTT space. The actual reservation will occur
+	 * later.
+	 */
+	vma->node.start = gtt_offset;
+	vma->node.size = size;
+	if (drm_mm_initialized(&ggtt->mm)) {
+		ret = drm_mm_reserve_node(&ggtt->mm, &vma->node);
+		if (ret) {
+			DRM_DEBUG_KMS("failed to allocate stolen GTT space\n");
+			goto err_vma;
+		}
+	}
+
+	obj->has_global_gtt_mapping = 1;
+
+	list_add_tail(&obj->global_list, &dev_priv->mm.bound_list);
+	list_add_tail(&vma->mm_list, &ggtt->inactive_list);
+	i915_gem_object_pin_pages(obj);
+
+	return obj;
+
+err_vma:
+	i915_gem_vma_destroy(vma);
+err_out:
+	drm_mm_remove_node(stolen);
+	kfree(stolen);
+	drm_gem_object_unreference(&obj->base);
+	return NULL;
+}
+
+void
+i915_gem_object_release_stolen(struct drm_i915_gem_object *obj)
+{
+	if (obj->stolen) {
+		drm_mm_remove_node(obj->stolen);
+		kfree(obj->stolen);
+		obj->stolen = NULL;
+	}
 }