1 files changed, 128 insertions, 134 deletions

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 926a1e2dd23..dca614de71b 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -28,7 +28,7 @@
 #include "i915_trace.h"
 #include "intel_drv.h"
 
-typedef uint32_t gtt_pte_t;
+typedef uint32_t gen6_gtt_pte_t;
 
 /* PPGTT stuff */
 #define GEN6_GTT_ADDR_ENCODE(addr)	((addr) | (((addr) >> 28) & 0xff0))
@@ -44,11 +44,11 @@ typedef uint32_t gtt_pte_t;
 #define GEN6_PTE_CACHE_LLC_MLC		(3 << 1)
 #define GEN6_PTE_ADDR_ENCODE(addr)	GEN6_GTT_ADDR_ENCODE(addr)
 
-static inline gtt_pte_t gen6_pte_encode(struct drm_device *dev,
-					dma_addr_t addr,
-					enum i915_cache_level level)
+static inline gen6_gtt_pte_t gen6_pte_encode(struct drm_device *dev,
+					     dma_addr_t addr,
+					     enum i915_cache_level level)
 {
-	gtt_pte_t pte = GEN6_PTE_VALID;
+	gen6_gtt_pte_t pte = GEN6_PTE_VALID;
 	pte |= GEN6_PTE_ADDR_ENCODE(addr);
 
 	switch (level) {
@@ -72,18 +72,85 @@ static inline gtt_pte_t gen6_pte_encode(struct drm_device *dev,
 		BUG();
 	}
 
-
 	return pte;
 }
 
+static int gen6_ppgtt_enable(struct drm_device *dev)
+{
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	uint32_t pd_offset;
+	struct intel_ring_buffer *ring;
+	struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
+	gen6_gtt_pte_t __iomem *pd_addr;
+	uint32_t pd_entry;
+	int i;
+
+	pd_addr = (gen6_gtt_pte_t __iomem*)dev_priv->gtt.gsm +
+		ppgtt->pd_offset / sizeof(gen6_gtt_pte_t);
+	for (i = 0; i < ppgtt->num_pd_entries; i++) {
+		dma_addr_t pt_addr;
+
+		pt_addr = ppgtt->pt_dma_addr[i];
+		pd_entry = GEN6_PDE_ADDR_ENCODE(pt_addr);
+		pd_entry |= GEN6_PDE_VALID;
+
+		writel(pd_entry, pd_addr + i);
+	}
+	readl(pd_addr);
+
+	pd_offset = ppgtt->pd_offset;
+	pd_offset /= 64; /* in cachelines, */
+	pd_offset <<= 16;
+
+	if (INTEL_INFO(dev)->gen == 6) {
+		uint32_t ecochk, gab_ctl, ecobits;
+
+		ecobits = I915_READ(GAC_ECO_BITS);
+		I915_WRITE(GAC_ECO_BITS, ecobits | ECOBITS_SNB_BIT |
+					 ECOBITS_PPGTT_CACHE64B);
+
+		gab_ctl = I915_READ(GAB_CTL);
+		I915_WRITE(GAB_CTL, gab_ctl | GAB_CTL_CONT_AFTER_PAGEFAULT);
+
+		ecochk = I915_READ(GAM_ECOCHK);
+		I915_WRITE(GAM_ECOCHK, ecochk | ECOCHK_SNB_BIT |
+				       ECOCHK_PPGTT_CACHE64B);
+		I915_WRITE(GFX_MODE, _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE));
+	} else if (INTEL_INFO(dev)->gen >= 7) {
+		uint32_t ecochk, ecobits;
+
+		ecobits = I915_READ(GAC_ECO_BITS);
+		I915_WRITE(GAC_ECO_BITS, ecobits | ECOBITS_PPGTT_CACHE64B);
+
+		ecochk = I915_READ(GAM_ECOCHK);
+		if (IS_HASWELL(dev)) {
+			ecochk |= ECOCHK_PPGTT_WB_HSW;
+		} else {
+			ecochk |= ECOCHK_PPGTT_LLC_IVB;
+			ecochk &= ~ECOCHK_PPGTT_GFDT_IVB;
+		}
+		I915_WRITE(GAM_ECOCHK, ecochk);
+		/* GFX_MODE is per-ring on gen7+ */
+	}
+
+	for_each_ring(ring, dev_priv, i) {
+		if (INTEL_INFO(dev)->gen >= 7)
+			I915_WRITE(RING_MODE_GEN7(ring),
+				   _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE));
+
+		I915_WRITE(RING_PP_DIR_DCLV(ring), PP_DIR_DCLV_2G);
+		I915_WRITE(RING_PP_DIR_BASE(ring), pd_offset);
+	}
+	return 0;
+}
+
 /* PPGTT support for Sandybdrige/Gen6 and later */
 static void gen6_ppgtt_clear_range(struct i915_hw_ppgtt *ppgtt,
 				   unsigned first_entry,
 				   unsigned num_entries)
 {
-	gtt_pte_t *pt_vaddr;
-	gtt_pte_t scratch_pte;
-	unsigned act_pd = first_entry / I915_PPGTT_PT_ENTRIES;
+	gen6_gtt_pte_t *pt_vaddr, scratch_pte;
+	unsigned act_pt = first_entry / I915_PPGTT_PT_ENTRIES;
 	unsigned first_pte = first_entry % I915_PPGTT_PT_ENTRIES;
 	unsigned last_pte, i;
 
@@ -96,7 +163,7 @@ static void gen6_ppgtt_clear_range(struct i915_hw_ppgtt *ppgtt,
 		if (last_pte > I915_PPGTT_PT_ENTRIES)
 			last_pte = I915_PPGTT_PT_ENTRIES;
 
-		pt_vaddr = kmap_atomic(ppgtt->pt_pages[act_pd]);
+		pt_vaddr = kmap_atomic(ppgtt->pt_pages[act_pt]);
 
 		for (i = first_pte; i < last_pte; i++)
 			pt_vaddr[i] = scratch_pte;
@@ -105,7 +172,7 @@ static void gen6_ppgtt_clear_range(struct i915_hw_ppgtt *ppgtt,
 
 		num_entries -= last_pte - first_pte;
 		first_pte = 0;
-		act_pd++;
+		act_pt++;
 	}
 }
 
@@ -114,43 +181,27 @@ static void gen6_ppgtt_insert_entries(struct i915_hw_ppgtt *ppgtt,
 				      unsigned first_entry,
 				      enum i915_cache_level cache_level)
 {
-	gtt_pte_t *pt_vaddr;
-	unsigned act_pd = first_entry / I915_PPGTT_PT_ENTRIES;
-	unsigned first_pte = first_entry % I915_PPGTT_PT_ENTRIES;
-	unsigned i, j, m, segment_len;
-	dma_addr_t page_addr;
-	struct scatterlist *sg;
-
-	/* init sg walking */
-	sg = pages->sgl;
-	i = 0;
-	segment_len = sg_dma_len(sg) >> PAGE_SHIFT;
-	m = 0;
-
-	while (i < pages->nents) {
-		pt_vaddr = kmap_atomic(ppgtt->pt_pages[act_pd]);
-
-		for (j = first_pte; j < I915_PPGTT_PT_ENTRIES; j++) {
-			page_addr = sg_dma_address(sg) + (m << PAGE_SHIFT);
-			pt_vaddr[j] = gen6_pte_encode(ppgtt->dev, page_addr,
-						      cache_level);
-
-			/* grab the next page */
-			if (++m == segment_len) {
-				if (++i == pages->nents)
-					break;
-
-				sg = sg_next(sg);
-				segment_len = sg_dma_len(sg) >> PAGE_SHIFT;
-				m = 0;
-			}
-		}
+	gen6_gtt_pte_t *pt_vaddr;
+	unsigned act_pt = first_entry / I915_PPGTT_PT_ENTRIES;
+	unsigned act_pte = first_entry % I915_PPGTT_PT_ENTRIES;
+	struct sg_page_iter sg_iter;
 
-		kunmap_atomic(pt_vaddr);
+	pt_vaddr = kmap_atomic(ppgtt->pt_pages[act_pt]);
+	for_each_sg_page(pages->sgl, &sg_iter, pages->nents, 0) {
+		dma_addr_t page_addr;
 
-		first_pte = 0;
-		act_pd++;
+		page_addr = sg_page_iter_dma_address(&sg_iter);
+		pt_vaddr[act_pte] = gen6_pte_encode(ppgtt->dev, page_addr,
+						    cache_level);
+		if (++act_pte == I915_PPGTT_PT_ENTRIES) {
+			kunmap_atomic(pt_vaddr);
+			act_pt++;
+			pt_vaddr = kmap_atomic(ppgtt->pt_pages[act_pt]);
+			act_pte = 0;
+
+		}
 	}
+	kunmap_atomic(pt_vaddr);
 }
 
 static void gen6_ppgtt_cleanup(struct i915_hw_ppgtt *ppgtt)
@@ -182,10 +233,10 @@ static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
 	/* 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 =
-		gtt_total_entries(dev_priv->gtt) - I915_PPGTT_PD_ENTRIES;
+       first_pd_entry_in_global_pt = gtt_total_entries(dev_priv->gtt);
 
 	ppgtt->num_pd_entries = I915_PPGTT_PD_ENTRIES;
+	ppgtt->enable = gen6_ppgtt_enable;
 	ppgtt->clear_range = gen6_ppgtt_clear_range;
 	ppgtt->insert_entries = gen6_ppgtt_insert_entries;
 	ppgtt->cleanup = gen6_ppgtt_cleanup;
@@ -219,12 +270,10 @@ static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
 		ppgtt->pt_dma_addr[i] = pt_addr;
 	}
 
-	ppgtt->scratch_page_dma_addr = dev_priv->gtt.scratch_page_dma;
-
 	ppgtt->clear_range(ppgtt, 0,
 			   ppgtt->num_pd_entries*I915_PPGTT_PT_ENTRIES);
 
-	ppgtt->pd_offset = (first_pd_entry_in_global_pt)*sizeof(gtt_pte_t);
+	ppgtt->pd_offset = first_pd_entry_in_global_pt * sizeof(gen6_gtt_pte_t);
 
 	return 0;
 
@@ -256,8 +305,13 @@ static int i915_gem_init_aliasing_ppgtt(struct drm_device *dev)
 		return -ENOMEM;
 
 	ppgtt->dev = dev;
+	ppgtt->scratch_page_dma_addr = dev_priv->gtt.scratch_page_dma;
+
+	if (INTEL_INFO(dev)->gen < 8)
+		ret = gen6_ppgtt_init(ppgtt);
+	else
+		BUG();
 
-	ret = gen6_ppgtt_init(ppgtt);
 	if (ret)
 		kfree(ppgtt);
 	else
@@ -275,6 +329,7 @@ void i915_gem_cleanup_aliasing_ppgtt(struct drm_device *dev)
 		return;
 
 	ppgtt->cleanup(ppgtt);
+	dev_priv->mm.aliasing_ppgtt = NULL;
 }
 
 void i915_ppgtt_bind_object(struct i915_hw_ppgtt *ppgtt,
@@ -294,64 +349,6 @@ void i915_ppgtt_unbind_object(struct i915_hw_ppgtt *ppgtt,
 			   obj->base.size >> PAGE_SHIFT);
 }
 
-void i915_gem_init_ppgtt(struct drm_device *dev)
-{
-	drm_i915_private_t *dev_priv = dev->dev_private;
-	uint32_t pd_offset;
-	struct intel_ring_buffer *ring;
-	struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
-	gtt_pte_t __iomem *pd_addr;
-	uint32_t pd_entry;
-	int i;
-
-	if (!dev_priv->mm.aliasing_ppgtt)
-		return;
-
-
-	pd_addr = (gtt_pte_t __iomem*)dev_priv->gtt.gsm + ppgtt->pd_offset/sizeof(gtt_pte_t);
-	for (i = 0; i < ppgtt->num_pd_entries; i++) {
-		dma_addr_t pt_addr;
-
-		pt_addr = ppgtt->pt_dma_addr[i];
-		pd_entry = GEN6_PDE_ADDR_ENCODE(pt_addr);
-		pd_entry |= GEN6_PDE_VALID;
-
-		writel(pd_entry, pd_addr + i);
-	}
-	readl(pd_addr);
-
-	pd_offset = ppgtt->pd_offset;
-	pd_offset /= 64; /* in cachelines, */
-	pd_offset <<= 16;
-
-	if (INTEL_INFO(dev)->gen == 6) {
-		uint32_t ecochk, gab_ctl, ecobits;
-
-		ecobits = I915_READ(GAC_ECO_BITS);
-		I915_WRITE(GAC_ECO_BITS, ecobits | ECOBITS_PPGTT_CACHE64B);
-
-		gab_ctl = I915_READ(GAB_CTL);
-		I915_WRITE(GAB_CTL, gab_ctl | GAB_CTL_CONT_AFTER_PAGEFAULT);
-
-		ecochk = I915_READ(GAM_ECOCHK);
-		I915_WRITE(GAM_ECOCHK, ecochk | ECOCHK_SNB_BIT |
-				       ECOCHK_PPGTT_CACHE64B);
-		I915_WRITE(GFX_MODE, _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE));
-	} else if (INTEL_INFO(dev)->gen >= 7) {
-		I915_WRITE(GAM_ECOCHK, ECOCHK_PPGTT_CACHE64B);
-		/* GFX_MODE is per-ring on gen7+ */
-	}
-
-	for_each_ring(ring, dev_priv, i) {
-		if (INTEL_INFO(dev)->gen >= 7)
-			I915_WRITE(RING_MODE_GEN7(ring),
-				   _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE));
-
-		I915_WRITE(RING_PP_DIR_DCLV(ring), PP_DIR_DCLV_2G);
-		I915_WRITE(RING_PP_DIR_BASE(ring), pd_offset);
-	}
-}
-
 extern int intel_iommu_gfx_mapped;
 /* Certain Gen5 chipsets require require idling the GPU before
  * unmapping anything from the GTT when VT-d is enabled.
@@ -432,21 +429,16 @@ static void gen6_ggtt_insert_entries(struct drm_device *dev,
 				     enum i915_cache_level level)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct scatterlist *sg = st->sgl;
-	gtt_pte_t __iomem *gtt_entries =
-		(gtt_pte_t __iomem *)dev_priv->gtt.gsm + first_entry;
-	int unused, i = 0;
-	unsigned int len, m = 0;
+	gen6_gtt_pte_t __iomem *gtt_entries =
+		(gen6_gtt_pte_t __iomem *)dev_priv->gtt.gsm + first_entry;
+	int i = 0;
+	struct sg_page_iter sg_iter;
 	dma_addr_t addr;
 
-	for_each_sg(st->sgl, sg, st->nents, unused) {
-		len = sg_dma_len(sg) >> PAGE_SHIFT;
-		for (m = 0; m < len; m++) {
-			addr = sg_dma_address(sg) + (m << PAGE_SHIFT);
-			iowrite32(gen6_pte_encode(dev, addr, level),
-				  &gtt_entries[i]);
-			i++;
-		}
+	for_each_sg_page(st->sgl, &sg_iter, st->nents, 0) {
+		addr = sg_page_iter_dma_address(&sg_iter);
+		iowrite32(gen6_pte_encode(dev, addr, level), &gtt_entries[i]);
+		i++;
 	}
 
 	/* XXX: This serves as a posting read to make sure that the PTE has
@@ -472,8 +464,8 @@ static void gen6_ggtt_clear_range(struct drm_device *dev,
 				  unsigned int num_entries)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	gtt_pte_t scratch_pte;
-	gtt_pte_t __iomem *gtt_base = (gtt_pte_t __iomem *) dev_priv->gtt.gsm + first_entry;
+	gen6_gtt_pte_t scratch_pte, __iomem *gtt_base =
+		(gen6_gtt_pte_t __iomem *) dev_priv->gtt.gsm + first_entry;
 	const int max_entries = gtt_total_entries(dev_priv->gtt) - first_entry;
 	int i;
 
@@ -647,9 +639,12 @@ void i915_gem_init_global_gtt(struct drm_device *dev)
 
 	if (intel_enable_ppgtt(dev) && HAS_ALIASING_PPGTT(dev)) {
 		int ret;
-		/* 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;
+
+		if (INTEL_INFO(dev)->gen <= 7) {
+			/* 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;
+		}
 
 		i915_gem_setup_global_gtt(dev, 0, mappable_size, gtt_size);
 
@@ -752,15 +747,17 @@ static int gen6_gmch_probe(struct drm_device *dev,
 	pci_read_config_word(dev->pdev, SNB_GMCH_CTRL, &snb_gmch_ctl);
 	gtt_size = gen6_get_total_gtt_size(snb_gmch_ctl);
 
-	if (IS_GEN7(dev))
+	if (IS_GEN7(dev) && !IS_VALLEYVIEW(dev))
 		*stolen = gen7_get_stolen_size(snb_gmch_ctl);
 	else
 		*stolen = gen6_get_stolen_size(snb_gmch_ctl);
 
-	*gtt_total = (gtt_size / sizeof(gtt_pte_t)) << PAGE_SHIFT;
+	*gtt_total = (gtt_size / sizeof(gen6_gtt_pte_t)) << PAGE_SHIFT;
+
+	/* For Modern GENs the PTEs and register space are split in the BAR */
+	gtt_bus_addr = pci_resource_start(dev->pdev, 0) +
+		(pci_resource_len(dev->pdev, 0) / 2);
 
-	/* For GEN6+ the PTEs for the ggtt live at 2MB + BAR0 */
-	gtt_bus_addr = pci_resource_start(dev->pdev, 0) + (2<<20);
 	dev_priv->gtt.gsm = ioremap_wc(gtt_bus_addr, gtt_size);
 	if (!dev_priv->gtt.gsm) {
 		DRM_ERROR("Failed to map the gtt page table\n");
@@ -817,7 +814,6 @@ int i915_gem_gtt_init(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct i915_gtt *gtt = &dev_priv->gtt;
-	unsigned long gtt_size;
 	int ret;
 
 	if (INTEL_INFO(dev)->gen <= 5) {
@@ -835,8 +831,6 @@ int i915_gem_gtt_init(struct drm_device *dev)
 	if (ret)
 		return ret;
 
-	gtt_size = (dev_priv->gtt.total >> PAGE_SHIFT) * sizeof(gtt_pte_t);
-
 	/* GMADR is the PCI mmio aperture into the global GTT. */
 	DRM_INFO("Memory usable by graphics device = %zdM\n",
 		 dev_priv->gtt.total >> 20);