drm/i915: initialization/teardown for the aliasing ppgtt

This just adds the setup and teardown code for the ppgtt PDE and the
last-level pagetables, which are fixed for the entire lifetime, at
least for the moment.

v2: Kill the stray debug printk noted by and improve the pte
definitions as suggested by Chris Wilson.

v3: Clean up the aperture stealing code as noted by Ben Widawsky.

v4: Paint the init code in a more pleasing colour as suggest by Chris
Wilson.

v5: Explain the magic numbers noticed by Ben Widawsky.

Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Tested-by: Chris Wilson <chris@chris-wilson.co.uk>
Tested-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

drivers/gpu/drm/i915/i915_dma.c

@@ -1196,22 +1196,39 @@ static int i915_load_gem_init(struct drm_device *dev)
 	/* Basic memrange allocator for stolen space */
 	drm_mm_init(&dev_priv->mm.stolen, 0, prealloc_size);
 
-	/* Let GEM Manage all of the aperture.
-	 *
-	 * However, leave one page at the end still bound to the scratch page.
-	 * There are a number of places where the hardware apparently
-	 * prefetches past the end of the object, and we've seen multiple
-	 * hangs with the GPU head pointer stuck in a batchbuffer bound
-	 * at the last page of the aperture.  One page should be enough to
-	 * keep any prefetching inside of the aperture.
-	 */
-	i915_gem_do_init(dev, 0, mappable_size, gtt_size - PAGE_SIZE);
+	if (HAS_ALIASING_PPGTT(dev)) {
+		/* PPGTT pdes are stolen from global gtt ptes, so shrink the
+		 * aperture accordingly when using aliasing ppgtt. */
+		gtt_size -= I915_PPGTT_PD_ENTRIES*PAGE_SIZE;
+		/* For paranoia keep the guard page in between. */
+		gtt_size -= PAGE_SIZE;
+
+		i915_gem_do_init(dev, 0, mappable_size, gtt_size);
+
+		ret = i915_gem_init_aliasing_ppgtt(dev);
+		if (ret)
+			return ret;
+	} else {
+		/* Let GEM Manage all of the aperture.
+		 *
+		 * However, leave one page at the end still bound to the scratch
+		 * page.  There are a number of places where the hardware
+		 * apparently prefetches past the end of the object, and we've
+		 * seen multiple hangs with the GPU head pointer stuck in a
+		 * batchbuffer bound at the last page of the aperture.  One page
+		 * should be enough to keep any prefetching inside of the
+		 * aperture.
+		 */
+		i915_gem_do_init(dev, 0, mappable_size, gtt_size - PAGE_SIZE);
+	}
 
 	mutex_lock(&dev->struct_mutex);
 	ret = i915_gem_init_hw(dev);
 	mutex_unlock(&dev->struct_mutex);
-	if (ret)
+	if (ret) {
+		i915_gem_cleanup_aliasing_ppgtt(dev);
 		return ret;
+	}
 
 	/* Try to set up FBC with a reasonable compressed buffer size */
 	if (I915_HAS_FBC(dev) && i915_powersave) {
@@ -1298,6 +1315,7 @@ cleanup_gem:
 	mutex_lock(&dev->struct_mutex);
 	i915_gem_cleanup_ringbuffer(dev);
 	mutex_unlock(&dev->struct_mutex);
+	i915_gem_cleanup_aliasing_ppgtt(dev);
 cleanup_vga_switcheroo:
 	vga_switcheroo_unregister_client(dev->pdev);
 cleanup_vga_client:
@@ -2184,6 +2202,7 @@ int i915_driver_unload(struct drm_device *dev)
 		i915_gem_free_all_phys_object(dev);
 		i915_gem_cleanup_ringbuffer(dev);
 		mutex_unlock(&dev->struct_mutex);
+		i915_gem_cleanup_aliasing_ppgtt(dev);
 		if (I915_HAS_FBC(dev) && i915_powersave)
 			i915_cleanup_compression(dev);
 		drm_mm_takedown(&dev_priv->mm.stolen);

drivers/gpu/drm/i915/i915_drv.h

@@ -258,6 +258,16 @@ struct intel_device_info {
 	u8 has_llc:1;
 };
 
+#define I915_PPGTT_PD_ENTRIES 512
+#define I915_PPGTT_PT_ENTRIES 1024
+struct i915_hw_ppgtt {
+	unsigned num_pd_entries;
+	struct page **pt_pages;
+	uint32_t pd_offset;
+	dma_addr_t *pt_dma_addr;
+	dma_addr_t scratch_page_dma_addr;
+};
+
 enum no_fbc_reason {
 	FBC_NO_OUTPUT, /* no outputs enabled to compress */
 	FBC_STOLEN_TOO_SMALL, /* not enough space to hold compressed buffers */
@@ -578,6 +588,9 @@ typedef struct drm_i915_private {
 		struct io_mapping *gtt_mapping;
 		int gtt_mtrr;
 
+		/** PPGTT used for aliasing the PPGTT with the GTT */
+		struct i915_hw_ppgtt *aliasing_ppgtt;
+
 		struct shrinker inactive_shrinker;
 
 		/**
@@ -973,6 +986,8 @@ struct drm_i915_file_private {
 #define HAS_LLC(dev)            (INTEL_INFO(dev)->has_llc)
 #define I915_NEED_GFX_HWS(dev)	(INTEL_INFO(dev)->need_gfx_hws)
 
+#define HAS_ALIASING_PPGTT(dev)	(INTEL_INFO(dev)->gen >=6)
+
 #define HAS_OVERLAY(dev)		(INTEL_INFO(dev)->has_overlay)
 #define OVERLAY_NEEDS_PHYSICAL(dev)	(INTEL_INFO(dev)->overlay_needs_physical)
 
@@ -1232,6 +1247,9 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
 				    enum i915_cache_level cache_level);
 
 /* i915_gem_gtt.c */
+int __must_check i915_gem_init_aliasing_ppgtt(struct drm_device *dev);
+void i915_gem_cleanup_aliasing_ppgtt(struct drm_device *dev);
+
 void i915_gem_restore_gtt_mappings(struct drm_device *dev);
 int __must_check i915_gem_gtt_bind_object(struct drm_i915_gem_object *obj);
 void i915_gem_gtt_rebind_object(struct drm_i915_gem_object *obj,

drivers/gpu/drm/i915/i915_gem_gtt.c

@@ -29,6 +29,145 @@
 #include "i915_trace.h"
 #include "intel_drv.h"
 
+/* PPGTT support for Sandybdrige/Gen6 and later */
+static void i915_ppgtt_clear_range(struct i915_hw_ppgtt *ppgtt,
+				   unsigned first_entry,
+				   unsigned num_entries)
+{
+	int i, j;
+	uint32_t *pt_vaddr;
+	uint32_t scratch_pte;
+
+	scratch_pte = GEN6_PTE_ADDR_ENCODE(ppgtt->scratch_page_dma_addr);
+	scratch_pte |= GEN6_PTE_VALID | GEN6_PTE_CACHE_LLC;
+
+	for (i = 0; i < ppgtt->num_pd_entries; i++) {
+		pt_vaddr = kmap_atomic(ppgtt->pt_pages[i]);
+
+		for (j = 0; j < I915_PPGTT_PT_ENTRIES; j++)
+			pt_vaddr[j] = scratch_pte;
+
+		kunmap_atomic(pt_vaddr);
+	}
+
+}
+
+int i915_gem_init_aliasing_ppgtt(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct i915_hw_ppgtt *ppgtt;
+	uint32_t pd_entry;
+	unsigned first_pd_entry_in_global_pt;
+	uint32_t __iomem *pd_addr;
+	int i;
+	int ret = -ENOMEM;
+
+	/* ppgtt PDEs reside in the global gtt pagetable, which has 512*1024
+	 * entries. For aliasing ppgtt support we just steal them at the end for
+	 * now. */
+	first_pd_entry_in_global_pt = 512*1024 - I915_PPGTT_PD_ENTRIES;
+
+	ppgtt = kzalloc(sizeof(*ppgtt), GFP_KERNEL);
+	if (!ppgtt)
+		return ret;
+
+	ppgtt->num_pd_entries = I915_PPGTT_PD_ENTRIES;
+	ppgtt->pt_pages = kzalloc(sizeof(struct page *)*ppgtt->num_pd_entries,
+				  GFP_KERNEL);
+	if (!ppgtt->pt_pages)
+		goto err_ppgtt;
+
+	for (i = 0; i < ppgtt->num_pd_entries; i++) {
+		ppgtt->pt_pages[i] = alloc_page(GFP_KERNEL);
+		if (!ppgtt->pt_pages[i])
+			goto err_pt_alloc;
+	}
+
+	if (dev_priv->mm.gtt->needs_dmar) {
+		ppgtt->pt_dma_addr = kzalloc(sizeof(dma_addr_t)
+						*ppgtt->num_pd_entries,
+					     GFP_KERNEL);
+		if (!ppgtt->pt_dma_addr)
+			goto err_pt_alloc;
+	}
+
+	pd_addr = dev_priv->mm.gtt->gtt + first_pd_entry_in_global_pt;
+	for (i = 0; i < ppgtt->num_pd_entries; i++) {
+		dma_addr_t pt_addr;
+		if (dev_priv->mm.gtt->needs_dmar) {
+			pt_addr = pci_map_page(dev->pdev, ppgtt->pt_pages[i],
+					       0, 4096,
+					       PCI_DMA_BIDIRECTIONAL);
+
+			if (pci_dma_mapping_error(dev->pdev,
+						  pt_addr)) {
+				ret = -EIO;
+				goto err_pd_pin;
+
+			}
+			ppgtt->pt_dma_addr[i] = pt_addr;
+		} else
+			pt_addr = page_to_phys(ppgtt->pt_pages[i]);
+
+		pd_entry = GEN6_PDE_ADDR_ENCODE(pt_addr);
+		pd_entry |= GEN6_PDE_VALID;
+
+		writel(pd_entry, pd_addr + i);
+	}
+	readl(pd_addr);
+
+	ppgtt->scratch_page_dma_addr = dev_priv->mm.gtt->scratch_page_dma;
+
+	i915_ppgtt_clear_range(ppgtt, 0,
+			       ppgtt->num_pd_entries*I915_PPGTT_PT_ENTRIES);
+
+	ppgtt->pd_offset = (first_pd_entry_in_global_pt)*sizeof(uint32_t);
+
+	dev_priv->mm.aliasing_ppgtt = ppgtt;
+
+	return 0;
+
+err_pd_pin:
+	if (ppgtt->pt_dma_addr) {
+		for (i--; i >= 0; i--)
+			pci_unmap_page(dev->pdev, ppgtt->pt_dma_addr[i],
+				       4096, PCI_DMA_BIDIRECTIONAL);
+	}
+err_pt_alloc:
+	kfree(ppgtt->pt_dma_addr);
+	for (i = 0; i < ppgtt->num_pd_entries; i++) {
+		if (ppgtt->pt_pages[i])
+			__free_page(ppgtt->pt_pages[i]);
+	}
+	kfree(ppgtt->pt_pages);
+err_ppgtt:
+	kfree(ppgtt);
+
+	return ret;
+}
+
+void i915_gem_cleanup_aliasing_ppgtt(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
+	int i;
+
+	if (!ppgtt)
+		return;
+
+	if (ppgtt->pt_dma_addr) {
+		for (i = 0; i < ppgtt->num_pd_entries; i++)
+			pci_unmap_page(dev->pdev, ppgtt->pt_dma_addr[i],
+				       4096, PCI_DMA_BIDIRECTIONAL);
+	}
+
+	kfree(ppgtt->pt_dma_addr);
+	for (i = 0; i < ppgtt->num_pd_entries; i++)
+		__free_page(ppgtt->pt_pages[i]);
+	kfree(ppgtt->pt_pages);
+	kfree(ppgtt);
+}
+
 /* XXX kill agp_type! */
 static unsigned int cache_level_to_agp_type(struct drm_device *dev,
 					    enum i915_cache_level cache_level)

drivers/gpu/drm/i915/i915_reg.h

@@ -92,6 +92,22 @@
 #define  GEN6_GRDOM_MEDIA		(1 << 2)
 #define  GEN6_GRDOM_BLT			(1 << 3)
 
+/* PPGTT stuff */
+#define GEN6_GTT_ADDR_ENCODE(addr)	((addr) | (((addr) >> 28) & 0xff0))
+
+#define GEN6_PDE_VALID			(1 << 0)
+#define GEN6_PDE_LARGE_PAGE		(2 << 0) /* use 32kb pages */
+/* gen6+ has bit 11-4 for physical addr bit 39-32 */
+#define GEN6_PDE_ADDR_ENCODE(addr)	GEN6_GTT_ADDR_ENCODE(addr)
+
+#define GEN6_PTE_VALID			(1 << 0)
+#define GEN6_PTE_UNCACHED		(1 << 1)
+#define GEN6_PTE_CACHE_LLC		(2 << 1)
+#define GEN6_PTE_CACHE_LLC_MLC		(3 << 1)
+#define GEN6_PTE_CACHE_BITS		(3 << 1)
+#define GEN6_PTE_GFDT			(1 << 3)
+#define GEN6_PTE_ADDR_ENCODE(addr)	GEN6_GTT_ADDR_ENCODE(addr)
+
 /* VGA stuff */
 
 #define VGA_ST01_MDA 0x3ba