drm/Merge branch 'drm-ttm-glisse' of ../drm-radeon-next into drm-core-next

Merge topic branch containing Jerome's TTM changes, contains one change from
Konrad to swiotlb export.

* 'drm-ttm-glisse' of ../drm-radeon-next:
  drm/ttm: callback move_notify any time bo placement change v4
  drm/ttm: simplify memory accounting for ttm user v2
  drm/ttm: isolate dma data from ttm_tt V4
  drm/nouveau: enable the ttm dma pool when swiotlb is active V3
  drm/radeon/kms: enable the ttm dma pool if swiotlb is on V4
  drm/ttm: provide dma aware ttm page pool code V9
  drm/ttm: introduce callback for ttm_tt populate & unpopulate V4
  drm/ttm: merge ttm_backend and ttm_tt V5
  drm/ttm: page allocation use page array instead of list
  drm/ttm: test for dma_address array allocation failure
  drm/ttm: use ttm put pages function to properly restore cache attribute
  drm/ttm: remove unused backend flags field
  drm/ttm: remove split btw highmen and lowmem page
  drm/ttm: remove userspace backed ttm object support
  swiotlb: Expose swiotlb_nr_tlb function to modules

drivers/gpu/drm/nouveau/nouveau_bo.c

@@ -28,6 +28,7 @@
  */
 
 #include "drmP.h"
+#include "ttm/ttm_page_alloc.h"
 
 #include "nouveau_drm.h"
 #include "nouveau_drv.h"
@@ -92,6 +93,7 @@ nouveau_bo_new(struct drm_device *dev, int size, int align,
 {
 	struct drm_nouveau_private *dev_priv = dev->dev_private;
 	struct nouveau_bo *nvbo;
+	size_t acc_size;
 	int ret;
 
 	nvbo = kzalloc(sizeof(struct nouveau_bo), GFP_KERNEL);
@@ -114,9 +116,12 @@ nouveau_bo_new(struct drm_device *dev, int size, int align,
 	nvbo->bo.mem.num_pages = size >> PAGE_SHIFT;
 	nouveau_bo_placement_set(nvbo, flags, 0);
 
+	acc_size = ttm_bo_dma_acc_size(&dev_priv->ttm.bdev, size,
+				       sizeof(struct nouveau_bo));
+
 	ret = ttm_bo_init(&dev_priv->ttm.bdev, &nvbo->bo, size,
 			  ttm_bo_type_device, &nvbo->placement,
-			  align >> PAGE_SHIFT, 0, false, NULL, size,
+			  align >> PAGE_SHIFT, 0, false, NULL, acc_size,
 			  nouveau_bo_del_ttm);
 	if (ret) {
 		/* ttm will call nouveau_bo_del_ttm if it fails.. */
@@ -343,8 +348,10 @@ nouveau_bo_wr32(struct nouveau_bo *nvbo, unsigned index, u32 val)
 		*mem = val;
 }
 
-static struct ttm_backend *
-nouveau_bo_create_ttm_backend_entry(struct ttm_bo_device *bdev)
+static struct ttm_tt *
+nouveau_ttm_tt_create(struct ttm_bo_device *bdev,
+		      unsigned long size, uint32_t page_flags,
+		      struct page *dummy_read_page)
 {
 	struct drm_nouveau_private *dev_priv = nouveau_bdev(bdev);
 	struct drm_device *dev = dev_priv->dev;
@@ -352,11 +359,13 @@ nouveau_bo_create_ttm_backend_entry(struct ttm_bo_device *bdev)
 	switch (dev_priv->gart_info.type) {
 #if __OS_HAS_AGP
 	case NOUVEAU_GART_AGP:
-		return ttm_agp_backend_init(bdev, dev->agp->bridge);
+		return ttm_agp_tt_create(bdev, dev->agp->bridge,
+					 size, page_flags, dummy_read_page);
 #endif
 	case NOUVEAU_GART_PDMA:
 	case NOUVEAU_GART_HW:
-		return nouveau_sgdma_init_ttm(dev);
+		return nouveau_sgdma_create_ttm(bdev, size, page_flags,
+						dummy_read_page);
 	default:
 		NV_ERROR(dev, "Unknown GART type %d\n",
 			 dev_priv->gart_info.type);
@@ -806,10 +815,10 @@ nouveau_bo_move_ntfy(struct ttm_buffer_object *bo, struct ttm_mem_reg *new_mem)
 	struct nouveau_vma *vma;
 
 	list_for_each_entry(vma, &nvbo->vma_list, head) {
-		if (new_mem->mem_type == TTM_PL_VRAM) {
+		if (new_mem && new_mem->mem_type == TTM_PL_VRAM) {
 			nouveau_vm_map(vma, new_mem->mm_node);
 		} else
-		if (new_mem->mem_type == TTM_PL_TT &&
+		if (new_mem && new_mem->mem_type == TTM_PL_TT &&
 		    nvbo->page_shift == vma->vm->spg_shift) {
 			nouveau_vm_map_sg(vma, 0, new_mem->
 					  num_pages << PAGE_SHIFT,
@@ -1044,8 +1053,81 @@ nouveau_bo_fence(struct nouveau_bo *nvbo, struct nouveau_fence *fence)
 	nouveau_fence_unref(&old_fence);
 }
 
+static int
+nouveau_ttm_tt_populate(struct ttm_tt *ttm)
+{
+	struct ttm_dma_tt *ttm_dma = (void *)ttm;
+	struct drm_nouveau_private *dev_priv;
+	struct drm_device *dev;
+	unsigned i;
+	int r;
+
+	if (ttm->state != tt_unpopulated)
+		return 0;
+
+	dev_priv = nouveau_bdev(ttm->bdev);
+	dev = dev_priv->dev;
+
+#ifdef CONFIG_SWIOTLB
+	if (swiotlb_nr_tbl()) {
+		return ttm_dma_populate((void *)ttm, dev->dev);
+	}
+#endif
+
+	r = ttm_pool_populate(ttm);
+	if (r) {
+		return r;
+	}
+
+	for (i = 0; i < ttm->num_pages; i++) {
+		ttm_dma->dma_address[i] = pci_map_page(dev->pdev, ttm->pages[i],
+						   0, PAGE_SIZE,
+						   PCI_DMA_BIDIRECTIONAL);
+		if (pci_dma_mapping_error(dev->pdev, ttm_dma->dma_address[i])) {
+			while (--i) {
+				pci_unmap_page(dev->pdev, ttm_dma->dma_address[i],
+					       PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
+				ttm_dma->dma_address[i] = 0;
+			}
+			ttm_pool_unpopulate(ttm);
+			return -EFAULT;
+		}
+	}
+	return 0;
+}
+
+static void
+nouveau_ttm_tt_unpopulate(struct ttm_tt *ttm)
+{
+	struct ttm_dma_tt *ttm_dma = (void *)ttm;
+	struct drm_nouveau_private *dev_priv;
+	struct drm_device *dev;
+	unsigned i;
+
+	dev_priv = nouveau_bdev(ttm->bdev);
+	dev = dev_priv->dev;
+
+#ifdef CONFIG_SWIOTLB
+	if (swiotlb_nr_tbl()) {
+		ttm_dma_unpopulate((void *)ttm, dev->dev);
+		return;
+	}
+#endif
+
+	for (i = 0; i < ttm->num_pages; i++) {
+		if (ttm_dma->dma_address[i]) {
+			pci_unmap_page(dev->pdev, ttm_dma->dma_address[i],
+				       PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
+		}
+	}
+
+	ttm_pool_unpopulate(ttm);
+}
+
 struct ttm_bo_driver nouveau_bo_driver = {
-	.create_ttm_backend_entry = nouveau_bo_create_ttm_backend_entry,
+	.ttm_tt_create = &nouveau_ttm_tt_create,
+	.ttm_tt_populate = &nouveau_ttm_tt_populate,
+	.ttm_tt_unpopulate = &nouveau_ttm_tt_unpopulate,
 	.invalidate_caches = nouveau_bo_invalidate_caches,
 	.init_mem_type = nouveau_bo_init_mem_type,
 	.evict_flags = nouveau_bo_evict_flags,

drivers/gpu/drm/nouveau/nouveau_debugfs.c

@@ -178,6 +178,7 @@ static struct drm_info_list nouveau_debugfs_list[] = {
 	{ "memory", nouveau_debugfs_memory_info, 0, NULL },
 	{ "vbios.rom", nouveau_debugfs_vbios_image, 0, NULL },
 	{ "ttm_page_pool", ttm_page_alloc_debugfs, 0, NULL },
+	{ "ttm_dma_page_pool", ttm_dma_page_alloc_debugfs, 0, NULL },
 };
 #define NOUVEAU_DEBUGFS_ENTRIES ARRAY_SIZE(nouveau_debugfs_list)
 

drivers/gpu/drm/nouveau/nouveau_drv.h

@@ -1000,7 +1000,10 @@ extern int nouveau_sgdma_init(struct drm_device *);
 extern void nouveau_sgdma_takedown(struct drm_device *);
 extern uint32_t nouveau_sgdma_get_physical(struct drm_device *,
 					   uint32_t offset);
-extern struct ttm_backend *nouveau_sgdma_init_ttm(struct drm_device *);
+extern struct ttm_tt *nouveau_sgdma_create_ttm(struct ttm_bo_device *bdev,
+					       unsigned long size,
+					       uint32_t page_flags,
+					       struct page *dummy_read_page);
 
 /* nouveau_debugfs.c */
 #if defined(CONFIG_DRM_NOUVEAU_DEBUG)

drivers/gpu/drm/nouveau/nouveau_mem.c

@@ -407,6 +407,12 @@ nouveau_mem_vram_init(struct drm_device *dev)
 	ret = pci_set_dma_mask(dev->pdev, DMA_BIT_MASK(dma_bits));
 	if (ret)
 		return ret;
+	ret = pci_set_consistent_dma_mask(dev->pdev, DMA_BIT_MASK(dma_bits));
+	if (ret) {
+		/* Reset to default value. */
+		pci_set_consistent_dma_mask(dev->pdev, DMA_BIT_MASK(32));
+	}
+
 
 	ret = nouveau_ttm_global_init(dev_priv);
 	if (ret)

drivers/gpu/drm/radeon/radeon.h

@@ -320,7 +320,6 @@ struct radeon_gart {
 	unsigned			table_size;
 	struct page			**pages;
 	dma_addr_t			*pages_addr;
-	bool				*ttm_alloced;
 	bool				ready;
 };
 

drivers/gpu/drm/radeon/radeon_device.c

@@ -765,8 +765,14 @@ int radeon_device_init(struct radeon_device *rdev,
 	r = pci_set_dma_mask(rdev->pdev, DMA_BIT_MASK(dma_bits));
 	if (r) {
 		rdev->need_dma32 = true;
+		dma_bits = 32;
 		printk(KERN_WARNING "radeon: No suitable DMA available.\n");
 	}
+	r = pci_set_consistent_dma_mask(rdev->pdev, DMA_BIT_MASK(dma_bits));
+	if (r) {
+		pci_set_consistent_dma_mask(rdev->pdev, DMA_BIT_MASK(32));
+		printk(KERN_WARNING "radeon: No coherent DMA available.\n");
+	}
 
 	/* Registers mapping */
 	/* TODO: block userspace mapping of io register */

drivers/gpu/drm/radeon/radeon_gart.c

@@ -157,9 +157,6 @@ void radeon_gart_unbind(struct radeon_device *rdev, unsigned offset,
 	p = t / (PAGE_SIZE / RADEON_GPU_PAGE_SIZE);
 	for (i = 0; i < pages; i++, p++) {
 		if (rdev->gart.pages[p]) {
-			if (!rdev->gart.ttm_alloced[p])
-				pci_unmap_page(rdev->pdev, rdev->gart.pages_addr[p],
-						PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
 			rdev->gart.pages[p] = NULL;
 			rdev->gart.pages_addr[p] = rdev->dummy_page.addr;
 			page_base = rdev->gart.pages_addr[p];
@@ -191,23 +188,7 @@ int radeon_gart_bind(struct radeon_device *rdev, unsigned offset,
 	p = t / (PAGE_SIZE / RADEON_GPU_PAGE_SIZE);
 
 	for (i = 0; i < pages; i++, p++) {
-		/* we reverted the patch using dma_addr in TTM for now but this
-		 * code stops building on alpha so just comment it out for now */
-		if (0) { /*dma_addr[i] != DMA_ERROR_CODE) */
-			rdev->gart.ttm_alloced[p] = true;
-			rdev->gart.pages_addr[p] = dma_addr[i];
-		} else {
-			/* we need to support large memory configurations */
-			/* assume that unbind have already been call on the range */
-			rdev->gart.pages_addr[p] = pci_map_page(rdev->pdev, pagelist[i],
-							0, PAGE_SIZE,
-							PCI_DMA_BIDIRECTIONAL);
-			if (pci_dma_mapping_error(rdev->pdev, rdev->gart.pages_addr[p])) {
-				/* FIXME: failed to map page (return -ENOMEM?) */
-				radeon_gart_unbind(rdev, offset, pages);
-				return -ENOMEM;
-			}
-		}
+		rdev->gart.pages_addr[p] = dma_addr[i];
 		rdev->gart.pages[p] = pagelist[i];
 		if (rdev->gart.ptr) {
 			page_base = rdev->gart.pages_addr[p];
@@ -274,12 +255,6 @@ int radeon_gart_init(struct radeon_device *rdev)
 		radeon_gart_fini(rdev);
 		return -ENOMEM;
 	}
-	rdev->gart.ttm_alloced = kzalloc(sizeof(bool) *
-					 rdev->gart.num_cpu_pages, GFP_KERNEL);
-	if (rdev->gart.ttm_alloced == NULL) {
-		radeon_gart_fini(rdev);
-		return -ENOMEM;
-	}
 	/* set GART entry to point to the dummy page by default */
 	for (i = 0; i < rdev->gart.num_cpu_pages; i++) {
 		rdev->gart.pages_addr[i] = rdev->dummy_page.addr;
@@ -296,10 +271,8 @@ void radeon_gart_fini(struct radeon_device *rdev)
 	rdev->gart.ready = false;
 	kfree(rdev->gart.pages);
 	kfree(rdev->gart.pages_addr);
-	kfree(rdev->gart.ttm_alloced);
 	rdev->gart.pages = NULL;
 	rdev->gart.pages_addr = NULL;
-	rdev->gart.ttm_alloced = NULL;
 
 	radeon_dummy_page_fini(rdev);
 }

drivers/gpu/drm/radeon/radeon_object.c

@@ -95,6 +95,7 @@ int radeon_bo_create(struct radeon_device *rdev,
 	enum ttm_bo_type type;
 	unsigned long page_align = roundup(byte_align, PAGE_SIZE) >> PAGE_SHIFT;
 	unsigned long max_size = 0;
+	size_t acc_size;
 	int r;
 
 	size = ALIGN(size, PAGE_SIZE);
@@ -117,6 +118,9 @@ int radeon_bo_create(struct radeon_device *rdev,
 		return -ENOMEM;
 	}
 
+	acc_size = ttm_bo_dma_acc_size(&rdev->mman.bdev, size,
+				       sizeof(struct radeon_bo));
+
 retry:
 	bo = kzalloc(sizeof(struct radeon_bo), GFP_KERNEL);
 	if (bo == NULL)
@@ -134,8 +138,8 @@ int radeon_bo_create(struct radeon_device *rdev,
 	/* Kernel allocation are uninterruptible */
 	mutex_lock(&rdev->vram_mutex);
 	r = ttm_bo_init(&rdev->mman.bdev, &bo->tbo, size, type,
-			&bo->placement, page_align, 0, !kernel, NULL, size,
-			&radeon_ttm_bo_destroy);
+			&bo->placement, page_align, 0, !kernel, NULL,
+			acc_size, &radeon_ttm_bo_destroy);
 	mutex_unlock(&rdev->vram_mutex);
 	if (unlikely(r != 0)) {
 		if (r != -ERESTARTSYS) {

drivers/gpu/drm/radeon/radeon_ttm.c

@@ -114,24 +114,6 @@ static void radeon_ttm_global_fini(struct radeon_device *rdev)
 	}
 }
 
-struct ttm_backend *radeon_ttm_backend_create(struct radeon_device *rdev);
-
-static struct ttm_backend*
-radeon_create_ttm_backend_entry(struct ttm_bo_device *bdev)
-{
-	struct radeon_device *rdev;
-
-	rdev = radeon_get_rdev(bdev);
-#if __OS_HAS_AGP
-	if (rdev->flags & RADEON_IS_AGP) {
-		return ttm_agp_backend_init(bdev, rdev->ddev->agp->bridge);
-	} else
-#endif
-	{
-		return radeon_ttm_backend_create(rdev);
-	}
-}
-
 static int radeon_invalidate_caches(struct ttm_bo_device *bdev, uint32_t flags)
 {
 	return 0;
@@ -515,8 +497,155 @@ static bool radeon_sync_obj_signaled(void *sync_obj, void *sync_arg)
 	return radeon_fence_signaled((struct radeon_fence *)sync_obj);
 }
 
+/*
+ * TTM backend functions.
+ */
+struct radeon_ttm_tt {
+	struct ttm_dma_tt		ttm;
+	struct radeon_device		*rdev;
+	u64				offset;
+};
+
+static int radeon_ttm_backend_bind(struct ttm_tt *ttm,
+				   struct ttm_mem_reg *bo_mem)
+{
+	struct radeon_ttm_tt *gtt = (void*)ttm;
+	int r;
+
+	gtt->offset = (unsigned long)(bo_mem->start << PAGE_SHIFT);
+	if (!ttm->num_pages) {
+		WARN(1, "nothing to bind %lu pages for mreg %p back %p!\n",
+		     ttm->num_pages, bo_mem, ttm);
+	}
+	r = radeon_gart_bind(gtt->rdev, gtt->offset,
+			     ttm->num_pages, ttm->pages, gtt->ttm.dma_address);
+	if (r) {
+		DRM_ERROR("failed to bind %lu pages at 0x%08X\n",
+			  ttm->num_pages, (unsigned)gtt->offset);
+		return r;
+	}
+	return 0;
+}
+
+static int radeon_ttm_backend_unbind(struct ttm_tt *ttm)
+{
+	struct radeon_ttm_tt *gtt = (void *)ttm;
+
+	radeon_gart_unbind(gtt->rdev, gtt->offset, ttm->num_pages);
+	return 0;
+}
+
+static void radeon_ttm_backend_destroy(struct ttm_tt *ttm)
+{
+	struct radeon_ttm_tt *gtt = (void *)ttm;
+
+	ttm_dma_tt_fini(&gtt->ttm);
+	kfree(gtt);
+}
+
+static struct ttm_backend_func radeon_backend_func = {
+	.bind = &radeon_ttm_backend_bind,
+	.unbind = &radeon_ttm_backend_unbind,
+	.destroy = &radeon_ttm_backend_destroy,
+};
+
+struct ttm_tt *radeon_ttm_tt_create(struct ttm_bo_device *bdev,
+				    unsigned long size, uint32_t page_flags,
+				    struct page *dummy_read_page)
+{
+	struct radeon_device *rdev;
+	struct radeon_ttm_tt *gtt;
+
+	rdev = radeon_get_rdev(bdev);
+#if __OS_HAS_AGP
+	if (rdev->flags & RADEON_IS_AGP) {
+		return ttm_agp_tt_create(bdev, rdev->ddev->agp->bridge,
+					 size, page_flags, dummy_read_page);
+	}
+#endif
+
+	gtt = kzalloc(sizeof(struct radeon_ttm_tt), GFP_KERNEL);
+	if (gtt == NULL) {
+		return NULL;
+	}
+	gtt->ttm.ttm.func = &radeon_backend_func;
+	gtt->rdev = rdev;
+	if (ttm_dma_tt_init(&gtt->ttm, bdev, size, page_flags, dummy_read_page)) {
+		kfree(gtt);
+		return NULL;
+	}
+	return &gtt->ttm.ttm;
+}
+
+static int radeon_ttm_tt_populate(struct ttm_tt *ttm)
+{
+	struct radeon_device *rdev;
+	struct radeon_ttm_tt *gtt = (void *)ttm;
+	unsigned i;
+	int r;
+
+	if (ttm->state != tt_unpopulated)
+		return 0;
+
+	rdev = radeon_get_rdev(ttm->bdev);
+
+#ifdef CONFIG_SWIOTLB
+	if (swiotlb_nr_tbl()) {
+		return ttm_dma_populate(&gtt->ttm, rdev->dev);
+	}
+#endif
+
+	r = ttm_pool_populate(ttm);
+	if (r) {
+		return r;
+	}
+
+	for (i = 0; i < ttm->num_pages; i++) {
+		gtt->ttm.dma_address[i] = pci_map_page(rdev->pdev, ttm->pages[i],
+						       0, PAGE_SIZE,
+						       PCI_DMA_BIDIRECTIONAL);
+		if (pci_dma_mapping_error(rdev->pdev, gtt->ttm.dma_address[i])) {
+			while (--i) {
+				pci_unmap_page(rdev->pdev, gtt->ttm.dma_address[i],
+					       PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
+				gtt->ttm.dma_address[i] = 0;
+			}
+			ttm_pool_unpopulate(ttm);
+			return -EFAULT;
+		}
+	}
+	return 0;
+}
+
+static void radeon_ttm_tt_unpopulate(struct ttm_tt *ttm)
+{
+	struct radeon_device *rdev;
+	struct radeon_ttm_tt *gtt = (void *)ttm;
+	unsigned i;
+
+	rdev = radeon_get_rdev(ttm->bdev);
+
+#ifdef CONFIG_SWIOTLB
+	if (swiotlb_nr_tbl()) {
+		ttm_dma_unpopulate(&gtt->ttm, rdev->dev);
+		return;
+	}
+#endif
+
+	for (i = 0; i < ttm->num_pages; i++) {
+		if (gtt->ttm.dma_address[i]) {
+			pci_unmap_page(rdev->pdev, gtt->ttm.dma_address[i],
+				       PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
+		}
+	}
+
+	ttm_pool_unpopulate(ttm);
+}
+
 static struct ttm_bo_driver radeon_bo_driver = {
-	.create_ttm_backend_entry = &radeon_create_ttm_backend_entry,
+	.ttm_tt_create = &radeon_ttm_tt_create,
+	.ttm_tt_populate = &radeon_ttm_tt_populate,
+	.ttm_tt_unpopulate = &radeon_ttm_tt_unpopulate,
 	.invalidate_caches = &radeon_invalidate_caches,
 	.init_mem_type = &radeon_init_mem_type,
 	.evict_flags = &radeon_evict_flags,
@@ -680,124 +809,6 @@ int radeon_mmap(struct file *filp, struct vm_area_struct *vma)
 }
 
 
-/*
- * TTM backend functions.
- */
-struct radeon_ttm_backend {
-	struct ttm_backend		backend;
-	struct radeon_device		*rdev;
-	unsigned long			num_pages;
-	struct page			**pages;
-	struct page			*dummy_read_page;
-	dma_addr_t			*dma_addrs;
-	bool				populated;
-	bool				bound;
-	unsigned			offset;
-};
-
-static int radeon_ttm_backend_populate(struct ttm_backend *backend,
-				       unsigned long num_pages,
-				       struct page **pages,
-				       struct page *dummy_read_page,
-				       dma_addr_t *dma_addrs)
-{
-	struct radeon_ttm_backend *gtt;
-
-	gtt = container_of(backend, struct radeon_ttm_backend, backend);
-	gtt->pages = pages;
-	gtt->dma_addrs = dma_addrs;
-	gtt->num_pages = num_pages;
-	gtt->dummy_read_page = dummy_read_page;
-	gtt->populated = true;
-	return 0;
-}
-
-static void radeon_ttm_backend_clear(struct ttm_backend *backend)
-{
-	struct radeon_ttm_backend *gtt;
-
-	gtt = container_of(backend, struct radeon_ttm_backend, backend);
-	gtt->pages = NULL;
-	gtt->dma_addrs = NULL;
-	gtt->num_pages = 0;
-	gtt->dummy_read_page = NULL;
-	gtt->populated = false;
-	gtt->bound = false;
-}
-
-
-static int radeon_ttm_backend_bind(struct ttm_backend *backend,
-				   struct ttm_mem_reg *bo_mem)
-{
-	struct radeon_ttm_backend *gtt;
-	int r;
-
-	gtt = container_of(backend, struct radeon_ttm_backend, backend);
-	gtt->offset = bo_mem->start << PAGE_SHIFT;
-	if (!gtt->num_pages) {
-		WARN(1, "nothing to bind %lu pages for mreg %p back %p!\n",
-		     gtt->num_pages, bo_mem, backend);
-	}
-	r = radeon_gart_bind(gtt->rdev, gtt->offset,
-			     gtt->num_pages, gtt->pages, gtt->dma_addrs);
-	if (r) {
-		DRM_ERROR("failed to bind %lu pages at 0x%08X\n",
-			  gtt->num_pages, gtt->offset);
-		return r;
-	}
-	gtt->bound = true;
-	return 0;
-}
-
-static int radeon_ttm_backend_unbind(struct ttm_backend *backend)
-{
-	struct radeon_ttm_backend *gtt;
-
-	gtt = container_of(backend, struct radeon_ttm_backend, backend);
-	radeon_gart_unbind(gtt->rdev, gtt->offset, gtt->num_pages);
-	gtt->bound = false;
-	return 0;
-}
-
-static void radeon_ttm_backend_destroy(struct ttm_backend *backend)
-{
-	struct radeon_ttm_backend *gtt;
-
-	gtt = container_of(backend, struct radeon_ttm_backend, backend);
-	if (gtt->bound) {
-		radeon_ttm_backend_unbind(backend);
-	}
-	kfree(gtt);
-}
-
-static struct ttm_backend_func radeon_backend_func = {
-	.populate = &radeon_ttm_backend_populate,
-	.clear = &radeon_ttm_backend_clear,
-	.bind = &radeon_ttm_backend_bind,
-	.unbind = &radeon_ttm_backend_unbind,
-	.destroy = &radeon_ttm_backend_destroy,
-};
-
-struct ttm_backend *radeon_ttm_backend_create(struct radeon_device *rdev)
-{
-	struct radeon_ttm_backend *gtt;
-
-	gtt = kzalloc(sizeof(struct radeon_ttm_backend), GFP_KERNEL);
-	if (gtt == NULL) {
-		return NULL;
-	}
-	gtt->backend.bdev = &rdev->mman.bdev;
-	gtt->backend.flags = 0;
-	gtt->backend.func = &radeon_backend_func;
-	gtt->rdev = rdev;
-	gtt->pages = NULL;
-	gtt->num_pages = 0;
-	gtt->dummy_read_page = NULL;
-	gtt->populated = false;
-	gtt->bound = false;
-	return &gtt->backend;
-}
-
 #define RADEON_DEBUGFS_MEM_TYPES 2
 
 #if defined(CONFIG_DEBUG_FS)
@@ -820,8 +831,8 @@ static int radeon_mm_dump_table(struct seq_file *m, void *data)
 static int radeon_ttm_debugfs_init(struct radeon_device *rdev)
 {
 #if defined(CONFIG_DEBUG_FS)
-	static struct drm_info_list radeon_mem_types_list[RADEON_DEBUGFS_MEM_TYPES+1];
-	static char radeon_mem_types_names[RADEON_DEBUGFS_MEM_TYPES+1][32];
+	static struct drm_info_list radeon_mem_types_list[RADEON_DEBUGFS_MEM_TYPES+2];
+	static char radeon_mem_types_names[RADEON_DEBUGFS_MEM_TYPES+2][32];
 	unsigned i;
 
 	for (i = 0; i < RADEON_DEBUGFS_MEM_TYPES; i++) {
@@ -843,8 +854,17 @@ static int radeon_ttm_debugfs_init(struct radeon_device *rdev)
 	radeon_mem_types_list[i].name = radeon_mem_types_names[i];
 	radeon_mem_types_list[i].show = &ttm_page_alloc_debugfs;
 	radeon_mem_types_list[i].driver_features = 0;
-	radeon_mem_types_list[i].data = NULL;
-	return radeon_debugfs_add_files(rdev, radeon_mem_types_list, RADEON_DEBUGFS_MEM_TYPES+1);
+	radeon_mem_types_list[i++].data = NULL;
+#ifdef CONFIG_SWIOTLB
+	if (swiotlb_nr_tbl()) {
+		sprintf(radeon_mem_types_names[i], "ttm_dma_page_pool");
+		radeon_mem_types_list[i].name = radeon_mem_types_names[i];
+		radeon_mem_types_list[i].show = &ttm_dma_page_alloc_debugfs;
+		radeon_mem_types_list[i].driver_features = 0;
+		radeon_mem_types_list[i++].data = NULL;
+	}
+#endif
+	return radeon_debugfs_add_files(rdev, radeon_mem_types_list, i);
 
 #endif
 	return 0;

drivers/gpu/drm/ttm/Makefile

@@ -7,4 +7,8 @@ ttm-y := ttm_agp_backend.o ttm_memory.o ttm_tt.o ttm_bo.o \
 	ttm_object.o ttm_lock.o ttm_execbuf_util.o ttm_page_alloc.o \
 	ttm_bo_manager.o
 
+ifeq ($(CONFIG_SWIOTLB),y)
+ttm-y += ttm_page_alloc_dma.o
+endif
+
 obj-$(CONFIG_DRM_TTM) += ttm.o

drivers/gpu/drm/ttm/ttm_agp_backend.c

@@ -40,45 +40,33 @@
 #include <asm/agp.h>
 
 struct ttm_agp_backend {
-	struct ttm_backend backend;
+	struct ttm_tt ttm;
 	struct agp_memory *mem;
 	struct agp_bridge_data *bridge;
 };
 
-static int ttm_agp_populate(struct ttm_backend *backend,
-			    unsigned long num_pages, struct page **pages,
-			    struct page *dummy_read_page,
-			    dma_addr_t *dma_addrs)
+static int ttm_agp_bind(struct ttm_tt *ttm, struct ttm_mem_reg *bo_mem)
 {
-	struct ttm_agp_backend *agp_be =
-	    container_of(backend, struct ttm_agp_backend, backend);
-	struct page **cur_page, **last_page = pages + num_pages;
+	struct ttm_agp_backend *agp_be = container_of(ttm, struct ttm_agp_backend, ttm);
+	struct drm_mm_node *node = bo_mem->mm_node;
 	struct agp_memory *mem;
+	int ret, cached = (bo_mem->placement & TTM_PL_FLAG_CACHED);
+	unsigned i;
 
-	mem = agp_allocate_memory(agp_be->bridge, num_pages, AGP_USER_MEMORY);
+	mem = agp_allocate_memory(agp_be->bridge, ttm->num_pages, AGP_USER_MEMORY);
 	if (unlikely(mem == NULL))
 		return -ENOMEM;
 
 	mem->page_count = 0;
-	for (cur_page = pages; cur_page < last_page; ++cur_page) {
-		struct page *page = *cur_page;
+	for (i = 0; i < ttm->num_pages; i++) {
+		struct page *page = ttm->pages[i];
+
 		if (!page)
-			page = dummy_read_page;
+			page = ttm->dummy_read_page;
 
 		mem->pages[mem->page_count++] = page;
 	}
 	agp_be->mem = mem;
-	return 0;
-}
-
-static int ttm_agp_bind(struct ttm_backend *backend, struct ttm_mem_reg *bo_mem)
-{
-	struct ttm_agp_backend *agp_be =
-	    container_of(backend, struct ttm_agp_backend, backend);
-	struct drm_mm_node *node = bo_mem->mm_node;
-	struct agp_memory *mem = agp_be->mem;
-	int cached = (bo_mem->placement & TTM_PL_FLAG_CACHED);
-	int ret;
 
 	mem->is_flushed = 1;
 	mem->type = (cached) ? AGP_USER_CACHED_MEMORY : AGP_USER_MEMORY;
@@ -90,50 +78,38 @@ static int ttm_agp_bind(struct ttm_backend *backend, struct ttm_mem_reg *bo_mem)
 	return ret;
 }
 
-static int ttm_agp_unbind(struct ttm_backend *backend)
+static int ttm_agp_unbind(struct ttm_tt *ttm)
 {
-	struct ttm_agp_backend *agp_be =
-	    container_of(backend, struct ttm_agp_backend, backend);
-
-	if (agp_be->mem->is_bound)
-		return agp_unbind_memory(agp_be->mem);
-	else
-		return 0;
-}
+	struct ttm_agp_backend *agp_be = container_of(ttm, struct ttm_agp_backend, ttm);
 
-static void ttm_agp_clear(struct ttm_backend *backend)
-{
-	struct ttm_agp_backend *agp_be =
-	    container_of(backend, struct ttm_agp_backend, backend);
-	struct agp_memory *mem = agp_be->mem;
-
-	if (mem) {
-		ttm_agp_unbind(backend);
-		agp_free_memory(mem);
+	if (agp_be->mem) {
+		if (agp_be->mem->is_bound)
+			return agp_unbind_memory(agp_be->mem);
+		agp_free_memory(agp_be->mem);
+		agp_be->mem = NULL;
 	}
-	agp_be->mem = NULL;
+	return 0;
 }
 
-static void ttm_agp_destroy(struct ttm_backend *backend)
+static void ttm_agp_destroy(struct ttm_tt *ttm)
 {
-	struct ttm_agp_backend *agp_be =
-	    container_of(backend, struct ttm_agp_backend, backend);
+	struct ttm_agp_backend *agp_be = container_of(ttm, struct ttm_agp_backend, ttm);
 
 	if (agp_be->mem)
-		ttm_agp_clear(backend);
+		ttm_agp_unbind(ttm);
 	kfree(agp_be);
 }
 
 static struct ttm_backend_func ttm_agp_func = {
-	.populate = ttm_agp_populate,
-	.clear = ttm_agp_clear,
 	.bind = ttm_agp_bind,
 	.unbind = ttm_agp_unbind,
 	.destroy = ttm_agp_destroy,
 };
 
-struct ttm_backend *ttm_agp_backend_init(struct ttm_bo_device *bdev,
-					 struct agp_bridge_data *bridge)
+struct ttm_tt *ttm_agp_tt_create(struct ttm_bo_device *bdev,
+				 struct agp_bridge_data *bridge,
+				 unsigned long size, uint32_t page_flags,
+				 struct page *dummy_read_page)
 {
 	struct ttm_agp_backend *agp_be;
 
@@ -143,10 +119,14 @@ struct ttm_backend *ttm_agp_backend_init(struct ttm_bo_device *bdev,
 
 	agp_be->mem = NULL;
 	agp_be->bridge = bridge;
-	agp_be->backend.func = &ttm_agp_func;
-	agp_be->backend.bdev = bdev;
-	return &agp_be->backend;
+	agp_be->ttm.func = &ttm_agp_func;
+
+	if (ttm_tt_init(&agp_be->ttm, bdev, size, page_flags, dummy_read_page)) {
+		return NULL;
+	}
+
+	return &agp_be->ttm;
 }
-EXPORT_SYMBOL(ttm_agp_backend_init);
+EXPORT_SYMBOL(ttm_agp_tt_create);
 
 #endif

drivers/gpu/drm/ttm/ttm_bo.c

@@ -137,6 +137,7 @@ static void ttm_bo_release_list(struct kref *list_kref)
 	struct ttm_buffer_object *bo =
 	    container_of(list_kref, struct ttm_buffer_object, list_kref);
 	struct ttm_bo_device *bdev = bo->bdev;
+	size_t acc_size = bo->acc_size;
 
 	BUG_ON(atomic_read(&bo->list_kref.refcount));
 	BUG_ON(atomic_read(&bo->kref.refcount));
@@ -152,9 +153,9 @@ static void ttm_bo_release_list(struct kref *list_kref)
 	if (bo->destroy)
 		bo->destroy(bo);
 	else {
-		ttm_mem_global_free(bdev->glob->mem_glob, bo->acc_size);
 		kfree(bo);
 	}
+	ttm_mem_global_free(bdev->glob->mem_glob, acc_size);
 }
 
 int ttm_bo_wait_unreserved(struct ttm_buffer_object *bo, bool interruptible)
@@ -337,27 +338,11 @@ static int ttm_bo_add_ttm(struct ttm_buffer_object *bo, bool zero_alloc)
 		if (zero_alloc)
 			page_flags |= TTM_PAGE_FLAG_ZERO_ALLOC;
 	case ttm_bo_type_kernel:
-		bo->ttm = ttm_tt_create(bdev, bo->num_pages << PAGE_SHIFT,
-					page_flags, glob->dummy_read_page);
+		bo->ttm = bdev->driver->ttm_tt_create(bdev, bo->num_pages << PAGE_SHIFT,
+						      page_flags, glob->dummy_read_page);
 		if (unlikely(bo->ttm == NULL))
 			ret = -ENOMEM;
 		break;
-	case ttm_bo_type_user:
-		bo->ttm = ttm_tt_create(bdev, bo->num_pages << PAGE_SHIFT,
-					page_flags | TTM_PAGE_FLAG_USER,
-					glob->dummy_read_page);
-		if (unlikely(bo->ttm == NULL)) {
-			ret = -ENOMEM;
-			break;
-		}
-
-		ret = ttm_tt_set_user(bo->ttm, current,
-				      bo->buffer_start, bo->num_pages);
-		if (unlikely(ret != 0)) {
-			ttm_tt_destroy(bo->ttm);
-			bo->ttm = NULL;
-		}
-		break;
 	default:
 		printk(KERN_ERR TTM_PFX "Illegal buffer object type\n");
 		ret = -EINVAL;
@@ -419,9 +404,6 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo,
 		}
 	}
 
-	if (bdev->driver->move_notify)
-		bdev->driver->move_notify(bo, mem);
-
 	if (!(old_man->flags & TTM_MEMTYPE_FLAG_FIXED) &&
 	    !(new_man->flags & TTM_MEMTYPE_FLAG_FIXED))
 		ret = ttm_bo_move_ttm(bo, evict, no_wait_reserve, no_wait_gpu, mem);
@@ -434,6 +416,9 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo,
 	if (ret)
 		goto out_err;
 
+	if (bdev->driver->move_notify)
+		bdev->driver->move_notify(bo, mem);
+
 moved:
 	if (bo->evicted) {
 		ret = bdev->driver->invalidate_caches(bdev, bo->mem.placement);
@@ -472,6 +457,9 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo,
 
 static void ttm_bo_cleanup_memtype_use(struct ttm_buffer_object *bo)
 {
+	if (bo->bdev->driver->move_notify)
+		bo->bdev->driver->move_notify(bo, NULL);
+
 	if (bo->ttm) {
 		ttm_tt_unbind(bo->ttm);
 		ttm_tt_destroy(bo->ttm);
@@ -907,16 +895,12 @@ static uint32_t ttm_bo_select_caching(struct ttm_mem_type_manager *man,
 }
 
 static bool ttm_bo_mt_compatible(struct ttm_mem_type_manager *man,
-				 bool disallow_fixed,
 				 uint32_t mem_type,
 				 uint32_t proposed_placement,
 				 uint32_t *masked_placement)
 {
 	uint32_t cur_flags = ttm_bo_type_flags(mem_type);
 
-	if ((man->flags & TTM_MEMTYPE_FLAG_FIXED) && disallow_fixed)
-		return false;
-
 	if ((cur_flags & proposed_placement & TTM_PL_MASK_MEM) == 0)
 		return false;
 
@@ -961,7 +945,6 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 		man = &bdev->man[mem_type];
 
 		type_ok = ttm_bo_mt_compatible(man,
-						bo->type == ttm_bo_type_user,
 						mem_type,
 						placement->placement[i],
 						&cur_flags);
@@ -1009,7 +992,6 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 		if (!man->has_type)
 			continue;
 		if (!ttm_bo_mt_compatible(man,
-						bo->type == ttm_bo_type_user,
 						mem_type,
 						placement->busy_placement[i],
 						&cur_flags))
@@ -1179,6 +1161,17 @@ int ttm_bo_init(struct ttm_bo_device *bdev,
 {
 	int ret = 0;
 	unsigned long num_pages;
+	struct ttm_mem_global *mem_glob = bdev->glob->mem_glob;
+
+	ret = ttm_mem_global_alloc(mem_glob, acc_size, false, false);
+	if (ret) {
+		printk(KERN_ERR TTM_PFX "Out of kernel memory.\n");
+		if (destroy)
+			(*destroy)(bo);
+		else
+			kfree(bo);
+		return -ENOMEM;
+	}
 
 	size += buffer_start & ~PAGE_MASK;
 	num_pages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
@@ -1249,14 +1242,34 @@ int ttm_bo_init(struct ttm_bo_device *bdev,
 }
 EXPORT_SYMBOL(ttm_bo_init);
 
-static inline size_t ttm_bo_size(struct ttm_bo_global *glob,
-				 unsigned long num_pages)
+size_t ttm_bo_acc_size(struct ttm_bo_device *bdev,
+		       unsigned long bo_size,
+		       unsigned struct_size)
 {
-	size_t page_array_size = (num_pages * sizeof(void *) + PAGE_SIZE - 1) &
-	    PAGE_MASK;
+	unsigned npages = (PAGE_ALIGN(bo_size)) >> PAGE_SHIFT;
+	size_t size = 0;
 
-	return glob->ttm_bo_size + 2 * page_array_size;
+	size += ttm_round_pot(struct_size);
+	size += PAGE_ALIGN(npages * sizeof(void *));
+	size += ttm_round_pot(sizeof(struct ttm_tt));
+	return size;
 }
+EXPORT_SYMBOL(ttm_bo_acc_size);
+
+size_t ttm_bo_dma_acc_size(struct ttm_bo_device *bdev,
+			   unsigned long bo_size,
+			   unsigned struct_size)
+{
+	unsigned npages = (PAGE_ALIGN(bo_size)) >> PAGE_SHIFT;
+	size_t size = 0;
+
+	size += ttm_round_pot(struct_size);
+	size += PAGE_ALIGN(npages * sizeof(void *));
+	size += PAGE_ALIGN(npages * sizeof(dma_addr_t));
+	size += ttm_round_pot(sizeof(struct ttm_dma_tt));
+	return size;
+}
+EXPORT_SYMBOL(ttm_bo_dma_acc_size);
 
 int ttm_bo_create(struct ttm_bo_device *bdev,
 			unsigned long size,
@@ -1270,10 +1283,10 @@ int ttm_bo_create(struct ttm_bo_device *bdev,
 {
 	struct ttm_buffer_object *bo;
 	struct ttm_mem_global *mem_glob = bdev->glob->mem_glob;
+	size_t acc_size;
 	int ret;
 
-	size_t acc_size =
-	    ttm_bo_size(bdev->glob, (size + PAGE_SIZE - 1) >> PAGE_SHIFT);
+	acc_size = ttm_bo_acc_size(bdev, size, sizeof(struct ttm_buffer_object));
 	ret = ttm_mem_global_alloc(mem_glob, acc_size, false, false);
 	if (unlikely(ret != 0))
 		return ret;
@@ -1459,13 +1472,6 @@ int ttm_bo_global_init(struct drm_global_reference *ref)
 		goto out_no_shrink;
 	}
 
-	glob->ttm_bo_extra_size =
-		ttm_round_pot(sizeof(struct ttm_tt)) +
-		ttm_round_pot(sizeof(struct ttm_backend));
-
-	glob->ttm_bo_size = glob->ttm_bo_extra_size +
-		ttm_round_pot(sizeof(struct ttm_buffer_object));
-
 	atomic_set(&glob->bo_count, 0);
 
 	ret = kobject_init_and_add(

drivers/gpu/drm/ttm/ttm_bo_util.c

@@ -244,7 +244,7 @@ static int ttm_copy_io_ttm_page(struct ttm_tt *ttm, void *src,
 				unsigned long page,
 				pgprot_t prot)
 {
-	struct page *d = ttm_tt_get_page(ttm, page);
+	struct page *d = ttm->pages[page];
 	void *dst;
 
 	if (!d)
@@ -281,7 +281,7 @@ static int ttm_copy_ttm_io_page(struct ttm_tt *ttm, void *dst,
 				unsigned long page,
 				pgprot_t prot)
 {
-	struct page *s = ttm_tt_get_page(ttm, page);
+	struct page *s = ttm->pages[page];
 	void *src;
 
 	if (!s)
@@ -342,6 +342,12 @@ int ttm_bo_move_memcpy(struct ttm_buffer_object *bo,
 	if (old_iomap == NULL && ttm == NULL)
 		goto out2;
 
+	if (ttm->state == tt_unpopulated) {
+		ret = ttm->bdev->driver->ttm_tt_populate(ttm);
+		if (ret)
+			goto out1;
+	}
+
 	add = 0;
 	dir = 1;
 
@@ -439,6 +445,7 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
 	kref_init(&fbo->list_kref);
 	kref_init(&fbo->kref);
 	fbo->destroy = &ttm_transfered_destroy;
+	fbo->acc_size = 0;
 
 	*new_obj = fbo;
 	return 0;
@@ -502,10 +509,16 @@ static int ttm_bo_kmap_ttm(struct ttm_buffer_object *bo,
 {
 	struct ttm_mem_reg *mem = &bo->mem; pgprot_t prot;
 	struct ttm_tt *ttm = bo->ttm;
-	struct page *d;
-	int i;
+	int ret;
 
 	BUG_ON(!ttm);
+
+	if (ttm->state == tt_unpopulated) {
+		ret = ttm->bdev->driver->ttm_tt_populate(ttm);
+		if (ret)
+			return ret;
+	}
+
 	if (num_pages == 1 && (mem->placement & TTM_PL_FLAG_CACHED)) {
 		/*
 		 * We're mapping a single page, and the desired
@@ -513,18 +526,9 @@ static int ttm_bo_kmap_ttm(struct ttm_buffer_object *bo,
 		 */
 
 		map->bo_kmap_type = ttm_bo_map_kmap;
-		map->page = ttm_tt_get_page(ttm, start_page);
+		map->page = ttm->pages[start_page];
 		map->virtual = kmap(map->page);
 	} else {
-	    /*
-	     * Populate the part we're mapping;
-	     */
-		for (i = start_page; i < start_page + num_pages; ++i) {
-			d = ttm_tt_get_page(ttm, i);
-			if (!d)
-				return -ENOMEM;
-		}
-
 		/*
 		 * We need to use vmap to get the desired page protection
 		 * or to make the buffer object look contiguous.

drivers/gpu/drm/ttm/ttm_bo_vm.c

@@ -174,18 +174,23 @@ static int ttm_bo_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 		vma->vm_page_prot = (bo->mem.placement & TTM_PL_FLAG_CACHED) ?
 		    vm_get_page_prot(vma->vm_flags) :
 		    ttm_io_prot(bo->mem.placement, vma->vm_page_prot);
+
+		/* Allocate all page at once, most common usage */
+		if (ttm->bdev->driver->ttm_tt_populate(ttm)) {
+			retval = VM_FAULT_OOM;
+			goto out_io_unlock;
+		}
 	}
 
 	/*
 	 * Speculatively prefault a number of pages. Only error on
 	 * first page.
 	 */
-
 	for (i = 0; i < TTM_BO_VM_NUM_PREFAULT; ++i) {
 		if (bo->mem.bus.is_iomem)
 			pfn = ((bo->mem.bus.base + bo->mem.bus.offset) >> PAGE_SHIFT) + page_offset;
 		else {
-			page = ttm_tt_get_page(ttm, page_offset);
+			page = ttm->pages[page_offset];
 			if (unlikely(!page && i == 0)) {
 				retval = VM_FAULT_OOM;
 				goto out_io_unlock;

drivers/gpu/drm/ttm/ttm_memory.c

@@ -395,6 +395,7 @@ int ttm_mem_global_init(struct ttm_mem_global *glob)
 		       zone->name, (unsigned long long) zone->max_mem >> 10);
 	}
 	ttm_page_alloc_init(glob, glob->zone_kernel->max_mem/(2*PAGE_SIZE));
+	ttm_dma_page_alloc_init(glob, glob->zone_kernel->max_mem/(2*PAGE_SIZE));
 	return 0;
 out_no_zone:
 	ttm_mem_global_release(glob);
@@ -409,6 +410,7 @@ void ttm_mem_global_release(struct ttm_mem_global *glob)
 
 	/* let the page allocator first stop the shrink work. */
 	ttm_page_alloc_fini();
+	ttm_dma_page_alloc_fini();
 
 	flush_workqueue(glob->swap_queue);
 	destroy_workqueue(glob->swap_queue);

drivers/gpu/drm/ttm/ttm_page_alloc.c

@@ -619,8 +619,10 @@ static void ttm_page_pool_fill_locked(struct ttm_page_pool *pool,
  * @return count of pages still required to fulfill the request.
  */
 static unsigned ttm_page_pool_get_pages(struct ttm_page_pool *pool,
-		struct list_head *pages, int ttm_flags,
-		enum ttm_caching_state cstate, unsigned count)
+					struct list_head *pages,
+					int ttm_flags,
+					enum ttm_caching_state cstate,
+					unsigned count)
 {
 	unsigned long irq_flags;
 	struct list_head *p;
@@ -660,17 +662,67 @@ static unsigned ttm_page_pool_get_pages(struct ttm_page_pool *pool,
 	return count;
 }
 
+/* Put all pages in pages list to correct pool to wait for reuse */
+static void ttm_put_pages(struct page **pages, unsigned npages, int flags,
+			  enum ttm_caching_state cstate)
+{
+	unsigned long irq_flags;
+	struct ttm_page_pool *pool = ttm_get_pool(flags, cstate);
+	unsigned i;
+
+	if (pool == NULL) {
+		/* No pool for this memory type so free the pages */
+		for (i = 0; i < npages; i++) {
+			if (pages[i]) {
+				if (page_count(pages[i]) != 1)
+					printk(KERN_ERR TTM_PFX
+					       "Erroneous page count. "
+					       "Leaking pages.\n");
+				__free_page(pages[i]);
+				pages[i] = NULL;
+			}
+		}
+		return;
+	}
+
+	spin_lock_irqsave(&pool->lock, irq_flags);
+	for (i = 0; i < npages; i++) {
+		if (pages[i]) {
+			if (page_count(pages[i]) != 1)
+				printk(KERN_ERR TTM_PFX
+				       "Erroneous page count. "
+				       "Leaking pages.\n");
+			list_add_tail(&pages[i]->lru, &pool->list);
+			pages[i] = NULL;
+			pool->npages++;
+		}
+	}
+	/* Check that we don't go over the pool limit */
+	npages = 0;
+	if (pool->npages > _manager->options.max_size) {
+		npages = pool->npages - _manager->options.max_size;
+		/* free at least NUM_PAGES_TO_ALLOC number of pages
+		 * to reduce calls to set_memory_wb */
+		if (npages < NUM_PAGES_TO_ALLOC)
+			npages = NUM_PAGES_TO_ALLOC;
+	}
+	spin_unlock_irqrestore(&pool->lock, irq_flags);
+	if (npages)
+		ttm_page_pool_free(pool, npages);
+}
+
 /*
  * On success pages list will hold count number of correctly
  * cached pages.
  */
-int ttm_get_pages(struct list_head *pages, int flags,
-		  enum ttm_caching_state cstate, unsigned count,
-		  dma_addr_t *dma_address)
+static int ttm_get_pages(struct page **pages, unsigned npages, int flags,
+			 enum ttm_caching_state cstate)
 {
 	struct ttm_page_pool *pool = ttm_get_pool(flags, cstate);
+	struct list_head plist;
 	struct page *p = NULL;
 	gfp_t gfp_flags = GFP_USER;
+	unsigned count;
 	int r;
 
 	/* set zero flag for page allocation if required */
@@ -684,7 +736,7 @@ int ttm_get_pages(struct list_head *pages, int flags,
 		else
 			gfp_flags |= GFP_HIGHUSER;
 
-		for (r = 0; r < count; ++r) {
+		for (r = 0; r < npages; ++r) {
 			p = alloc_page(gfp_flags);
 			if (!p) {
 
@@ -693,87 +745,53 @@ int ttm_get_pages(struct list_head *pages, int flags,
 				return -ENOMEM;
 			}
 
-			list_add(&p->lru, pages);
+			pages[r] = p;
 		}
 		return 0;
 	}
 
-
 	/* combine zero flag to pool flags */
 	gfp_flags |= pool->gfp_flags;
 
 	/* First we take pages from the pool */
-	count = ttm_page_pool_get_pages(pool, pages, flags, cstate, count);
+	INIT_LIST_HEAD(&plist);
+	npages = ttm_page_pool_get_pages(pool, &plist, flags, cstate, npages);
+	count = 0;
+	list_for_each_entry(p, &plist, lru) {
+		pages[count++] = p;
+	}
 
 	/* clear the pages coming from the pool if requested */
 	if (flags & TTM_PAGE_FLAG_ZERO_ALLOC) {
-		list_for_each_entry(p, pages, lru) {
+		list_for_each_entry(p, &plist, lru) {
 			clear_page(page_address(p));
 		}
 	}
 
 	/* If pool didn't have enough pages allocate new one. */
-	if (count > 0) {
+	if (npages > 0) {
 		/* ttm_alloc_new_pages doesn't reference pool so we can run
 		 * multiple requests in parallel.
 		 **/
-		r = ttm_alloc_new_pages(pages, gfp_flags, flags, cstate, count);
+		INIT_LIST_HEAD(&plist);
+		r = ttm_alloc_new_pages(&plist, gfp_flags, flags, cstate, npages);
+		list_for_each_entry(p, &plist, lru) {
+			pages[count++] = p;
+		}
 		if (r) {
 			/* If there is any pages in the list put them back to
 			 * the pool. */
 			printk(KERN_ERR TTM_PFX
 			       "Failed to allocate extra pages "
 			       "for large request.");
-			ttm_put_pages(pages, 0, flags, cstate, NULL);
+			ttm_put_pages(pages, count, flags, cstate);
 			return r;
 		}
 	}
 
-
 	return 0;
 }
 
-/* Put all pages in pages list to correct pool to wait for reuse */
-void ttm_put_pages(struct list_head *pages, unsigned page_count, int flags,
-		   enum ttm_caching_state cstate, dma_addr_t *dma_address)
-{
-	unsigned long irq_flags;
-	struct ttm_page_pool *pool = ttm_get_pool(flags, cstate);
-	struct page *p, *tmp;
-
-	if (pool == NULL) {
-		/* No pool for this memory type so free the pages */
-
-		list_for_each_entry_safe(p, tmp, pages, lru) {
-			__free_page(p);
-		}
-		/* Make the pages list empty */
-		INIT_LIST_HEAD(pages);
-		return;
-	}
-	if (page_count == 0) {
-		list_for_each_entry_safe(p, tmp, pages, lru) {
-			++page_count;
-		}
-	}
-
-	spin_lock_irqsave(&pool->lock, irq_flags);
-	list_splice_init(pages, &pool->list);
-	pool->npages += page_count;
-	/* Check that we don't go over the pool limit */
-	page_count = 0;
-	if (pool->npages > _manager->options.max_size) {
-		page_count = pool->npages - _manager->options.max_size;
-		/* free at least NUM_PAGES_TO_ALLOC number of pages
-		 * to reduce calls to set_memory_wb */
-		if (page_count < NUM_PAGES_TO_ALLOC)
-			page_count = NUM_PAGES_TO_ALLOC;
-	}
-	spin_unlock_irqrestore(&pool->lock, irq_flags);
-	if (page_count)
-		ttm_page_pool_free(pool, page_count);
-}
-
 static void ttm_page_pool_init_locked(struct ttm_page_pool *pool, int flags,
 		char *name)
 {
@@ -836,6 +854,62 @@ void ttm_page_alloc_fini(void)
 	_manager = NULL;
 }
 
+int ttm_pool_populate(struct ttm_tt *ttm)
+{
+	struct ttm_mem_global *mem_glob = ttm->glob->mem_glob;
+	unsigned i;
+	int ret;
+
+	if (ttm->state != tt_unpopulated)
+		return 0;
+
+	for (i = 0; i < ttm->num_pages; ++i) {
+		ret = ttm_get_pages(&ttm->pages[i], 1,
+				    ttm->page_flags,
+				    ttm->caching_state);
+		if (ret != 0) {
+			ttm_pool_unpopulate(ttm);
+			return -ENOMEM;
+		}
+
+		ret = ttm_mem_global_alloc_page(mem_glob, ttm->pages[i],
+						false, false);
+		if (unlikely(ret != 0)) {
+			ttm_pool_unpopulate(ttm);
+			return -ENOMEM;
+		}
+	}
+
+	if (unlikely(ttm->page_flags & TTM_PAGE_FLAG_SWAPPED)) {
+		ret = ttm_tt_swapin(ttm);
+		if (unlikely(ret != 0)) {
+			ttm_pool_unpopulate(ttm);
+			return ret;
+		}
+	}
+
+	ttm->state = tt_unbound;
+	return 0;
+}
+EXPORT_SYMBOL(ttm_pool_populate);
+
+void ttm_pool_unpopulate(struct ttm_tt *ttm)
+{
+	unsigned i;
+
+	for (i = 0; i < ttm->num_pages; ++i) {
+		if (ttm->pages[i]) {
+			ttm_mem_global_free_page(ttm->glob->mem_glob,
+						 ttm->pages[i]);
+			ttm_put_pages(&ttm->pages[i], 1,
+				      ttm->page_flags,
+				      ttm->caching_state);
+		}
+	}
+	ttm->state = tt_unpopulated;
+}
+EXPORT_SYMBOL(ttm_pool_unpopulate);
+
 int ttm_page_alloc_debugfs(struct seq_file *m, void *data)
 {
 	struct ttm_page_pool *p;

drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c

@@ -28,6 +28,7 @@
 #include "vmwgfx_drv.h"
 #include "ttm/ttm_bo_driver.h"
 #include "ttm/ttm_placement.h"
+#include "ttm/ttm_page_alloc.h"
 
 static uint32_t vram_placement_flags = TTM_PL_FLAG_VRAM |
 	TTM_PL_FLAG_CACHED;
@@ -139,85 +140,63 @@ struct ttm_placement vmw_srf_placement = {
 	.busy_placement = gmr_vram_placement_flags
 };
 
-struct vmw_ttm_backend {
-	struct ttm_backend backend;
-	struct page **pages;
-	unsigned long num_pages;
+struct vmw_ttm_tt {
+	struct ttm_tt ttm;
 	struct vmw_private *dev_priv;
 	int gmr_id;
 };
 
-static int vmw_ttm_populate(struct ttm_backend *backend,
-			    unsigned long num_pages, struct page **pages,
-			    struct page *dummy_read_page,
-			    dma_addr_t *dma_addrs)
+static int vmw_ttm_bind(struct ttm_tt *ttm, struct ttm_mem_reg *bo_mem)
 {
-	struct vmw_ttm_backend *vmw_be =
-	    container_of(backend, struct vmw_ttm_backend, backend);
-
-	vmw_be->pages = pages;
-	vmw_be->num_pages = num_pages;
-
-	return 0;
-}
-
-static int vmw_ttm_bind(struct ttm_backend *backend, struct ttm_mem_reg *bo_mem)
-{
-	struct vmw_ttm_backend *vmw_be =
-	    container_of(backend, struct vmw_ttm_backend, backend);
+	struct vmw_ttm_tt *vmw_be = container_of(ttm, struct vmw_ttm_tt, ttm);
 
 	vmw_be->gmr_id = bo_mem->start;
 
-	return vmw_gmr_bind(vmw_be->dev_priv, vmw_be->pages,
-			    vmw_be->num_pages, vmw_be->gmr_id);
+	return vmw_gmr_bind(vmw_be->dev_priv, ttm->pages,
+			    ttm->num_pages, vmw_be->gmr_id);
 }
 
-static int vmw_ttm_unbind(struct ttm_backend *backend)
+static int vmw_ttm_unbind(struct ttm_tt *ttm)
 {
-	struct vmw_ttm_backend *vmw_be =
-	    container_of(backend, struct vmw_ttm_backend, backend);
+	struct vmw_ttm_tt *vmw_be = container_of(ttm, struct vmw_ttm_tt, ttm);
 
 	vmw_gmr_unbind(vmw_be->dev_priv, vmw_be->gmr_id);
 	return 0;
 }
 
-static void vmw_ttm_clear(struct ttm_backend *backend)
+static void vmw_ttm_destroy(struct ttm_tt *ttm)
 {
-	struct vmw_ttm_backend *vmw_be =
-		container_of(backend, struct vmw_ttm_backend, backend);
-
-	vmw_be->pages = NULL;
-	vmw_be->num_pages = 0;
-}
-
-static void vmw_ttm_destroy(struct ttm_backend *backend)
-{
-	struct vmw_ttm_backend *vmw_be =
-	    container_of(backend, struct vmw_ttm_backend, backend);
+	struct vmw_ttm_tt *vmw_be = container_of(ttm, struct vmw_ttm_tt, ttm);
 
+	ttm_tt_fini(ttm);
 	kfree(vmw_be);
 }
 
 static struct ttm_backend_func vmw_ttm_func = {
-	.populate = vmw_ttm_populate,
-	.clear = vmw_ttm_clear,
 	.bind = vmw_ttm_bind,
 	.unbind = vmw_ttm_unbind,
 	.destroy = vmw_ttm_destroy,
 };
 
-struct ttm_backend *vmw_ttm_backend_init(struct ttm_bo_device *bdev)
+struct ttm_tt *vmw_ttm_tt_create(struct ttm_bo_device *bdev,
+				 unsigned long size, uint32_t page_flags,
+				 struct page *dummy_read_page)
 {
-	struct vmw_ttm_backend *vmw_be;
+	struct vmw_ttm_tt *vmw_be;
 
 	vmw_be = kmalloc(sizeof(*vmw_be), GFP_KERNEL);
 	if (!vmw_be)
 		return NULL;
 
-	vmw_be->backend.func = &vmw_ttm_func;
+	vmw_be->ttm.func = &vmw_ttm_func;
 	vmw_be->dev_priv = container_of(bdev, struct vmw_private, bdev);
 
-	return &vmw_be->backend;
+	if (ttm_tt_init(&vmw_be->ttm, bdev, size, page_flags, dummy_read_page)) {
+		kfree(vmw_be);
+		return NULL;
+	}
+
+	return &vmw_be->ttm;
 }
 
 int vmw_invalidate_caches(struct ttm_bo_device *bdev, uint32_t flags)
@@ -357,7 +336,9 @@ static int vmw_sync_obj_wait(void *sync_obj, void *sync_arg,
 }
 
 struct ttm_bo_driver vmw_bo_driver = {
-	.create_ttm_backend_entry = vmw_ttm_backend_init,
+	.ttm_tt_create = &vmw_ttm_tt_create,
+	.ttm_tt_populate = &ttm_pool_populate,
+	.ttm_tt_unpopulate = &ttm_pool_unpopulate,
 	.invalidate_caches = vmw_invalidate_caches,
 	.init_mem_type = vmw_init_mem_type,
 	.evict_flags = vmw_evict_flags,

drivers/gpu/drm/vmwgfx/vmwgfx_resource.c

@@ -1517,29 +1517,10 @@ int vmw_surface_check(struct vmw_private *dev_priv,
 /**
  * Buffer management.
  */
-
-static size_t vmw_dmabuf_acc_size(struct ttm_bo_global *glob,
-				  unsigned long num_pages)
-{
-	static size_t bo_user_size = ~0;
-
-	size_t page_array_size =
-	    (num_pages * sizeof(void *) + PAGE_SIZE - 1) & PAGE_MASK;
-
-	if (unlikely(bo_user_size == ~0)) {
-		bo_user_size = glob->ttm_bo_extra_size +
-		    ttm_round_pot(sizeof(struct vmw_dma_buffer));
-	}
-
-	return bo_user_size + page_array_size;
-}
-
 void vmw_dmabuf_bo_free(struct ttm_buffer_object *bo)
 {
 	struct vmw_dma_buffer *vmw_bo = vmw_dma_buffer(bo);
-	struct ttm_bo_global *glob = bo->glob;
 
-	ttm_mem_global_free(glob->mem_glob, bo->acc_size);
 	kfree(vmw_bo);
 }
 
@@ -1550,24 +1531,12 @@ int vmw_dmabuf_init(struct vmw_private *dev_priv,
 		    void (*bo_free) (struct ttm_buffer_object *bo))
 {
 	struct ttm_bo_device *bdev = &dev_priv->bdev;
-	struct ttm_mem_global *mem_glob = bdev->glob->mem_glob;
 	size_t acc_size;
 	int ret;
 
 	BUG_ON(!bo_free);
 
-	acc_size =
-	    vmw_dmabuf_acc_size(bdev->glob,
-				(size + PAGE_SIZE - 1) >> PAGE_SHIFT);
-
-	ret = ttm_mem_global_alloc(mem_glob, acc_size, false, false);
-	if (unlikely(ret != 0)) {
-		/* we must free the bo here as
-		 * ttm_buffer_object_init does so as well */
-		bo_free(&vmw_bo->base);
-		return ret;
-	}
-
+	acc_size = ttm_bo_acc_size(bdev, size, sizeof(struct vmw_dma_buffer));
 	memset(vmw_bo, 0, sizeof(*vmw_bo));
 
 	INIT_LIST_HEAD(&vmw_bo->validate_list);
@@ -1582,9 +1551,7 @@ int vmw_dmabuf_init(struct vmw_private *dev_priv,
 static void vmw_user_dmabuf_destroy(struct ttm_buffer_object *bo)
 {
 	struct vmw_user_dma_buffer *vmw_user_bo = vmw_user_dma_buffer(bo);
-	struct ttm_bo_global *glob = bo->glob;
 
-	ttm_mem_global_free(glob->mem_glob, bo->acc_size);
 	kfree(vmw_user_bo);
 }
 

drivers/xen/swiotlb-xen.c

@@ -153,7 +153,7 @@ void __init xen_swiotlb_init(int verbose)
 	char *m = NULL;
 	unsigned int repeat = 3;
 
-	nr_tbl = swioltb_nr_tbl();
+	nr_tbl = swiotlb_nr_tbl();
 	if (nr_tbl)
 		xen_io_tlb_nslabs = nr_tbl;
 	else {

include/drm/ttm/ttm_bo_api.h

@@ -122,17 +122,12 @@ struct ttm_mem_reg {
  * be mmapped by user space. Each of these bos occupy a slot in the
  * device address space, that can be used for normal vm operations.
  *
- * @ttm_bo_type_user: These are user-space memory areas that are made
- * available to the GPU by mapping the buffer pages into the GPU aperture
- * space. These buffers cannot be mmaped from the device address space.
- *
  * @ttm_bo_type_kernel: These buffers are like ttm_bo_type_device buffers,
  * but they cannot be accessed from user-space. For kernel-only use.
  */
 
 enum ttm_bo_type {
 	ttm_bo_type_device,
-	ttm_bo_type_user,
 	ttm_bo_type_kernel
 };
 
@@ -434,9 +429,9 @@ extern void ttm_bo_unlock_delayed_workqueue(struct ttm_bo_device *bdev,
  * -EBUSY if the buffer is busy and no_wait is true.
  * -ERESTARTSYS if interrupted by a signal.
  */
-
 extern int
 ttm_bo_synccpu_write_grab(struct ttm_buffer_object *bo, bool no_wait);
+
 /**
  * ttm_bo_synccpu_write_release:
  *
@@ -446,6 +441,22 @@ ttm_bo_synccpu_write_grab(struct ttm_buffer_object *bo, bool no_wait);
  */
 extern void ttm_bo_synccpu_write_release(struct ttm_buffer_object *bo);
 
+/**
+ * ttm_bo_acc_size
+ *
+ * @bdev: Pointer to a ttm_bo_device struct.
+ * @bo_size: size of the buffer object in byte.
+ * @struct_size: size of the structure holding buffer object datas
+ *
+ * Returns size to account for a buffer object
+ */
+size_t ttm_bo_acc_size(struct ttm_bo_device *bdev,
+		       unsigned long bo_size,
+		       unsigned struct_size);
+size_t ttm_bo_dma_acc_size(struct ttm_bo_device *bdev,
+			   unsigned long bo_size,
+			   unsigned struct_size);
+
 /**
  * ttm_bo_init
  *
@@ -493,6 +504,7 @@ extern int ttm_bo_init(struct ttm_bo_device *bdev,
 			struct file *persistent_swap_storage,
 			size_t acc_size,
 			void (*destroy) (struct ttm_buffer_object *));
+
 /**
  * ttm_bo_synccpu_object_init
  *

include/drm/ttm/ttm_page_alloc.h

@@ -30,45 +30,70 @@
 #include "ttm_memory.h"
 
 /**
- * Get count number of pages from pool to pages list.
+ * Initialize pool allocator.
+ */
+int ttm_page_alloc_init(struct ttm_mem_global *glob, unsigned max_pages);
+/**
+ * Free pool allocator.
+ */
+void ttm_page_alloc_fini(void);
+
+/**
+ * ttm_pool_populate:
+ *
+ * @ttm: The struct ttm_tt to contain the backing pages.
  *
- * @pages: head of empty linked list where pages are filled.
- * @flags: ttm flags for page allocation.
- * @cstate: ttm caching state for the page.
- * @count: number of pages to allocate.
- * @dma_address: The DMA (bus) address of pages (if TTM_PAGE_FLAG_DMA32 set).
+ * Add backing pages to all of @ttm
  */
-int ttm_get_pages(struct list_head *pages,
-		  int flags,
-		  enum ttm_caching_state cstate,
-		  unsigned count,
-		  dma_addr_t *dma_address);
+extern int ttm_pool_populate(struct ttm_tt *ttm);
+
 /**
- * Put linked list of pages to pool.
+ * ttm_pool_unpopulate:
+ *
+ * @ttm: The struct ttm_tt which to free backing pages.
  *
- * @pages: list of pages to free.
- * @page_count: number of pages in the list. Zero can be passed for unknown
- * count.
- * @flags: ttm flags for page allocation.
- * @cstate: ttm caching state.
- * @dma_address: The DMA (bus) address of pages (if TTM_PAGE_FLAG_DMA32 set).
+ * Free all pages of @ttm
  */
-void ttm_put_pages(struct list_head *pages,
-		   unsigned page_count,
-		   int flags,
-		   enum ttm_caching_state cstate,
-		   dma_addr_t *dma_address);
+extern void ttm_pool_unpopulate(struct ttm_tt *ttm);
+
+/**
+ * Output the state of pools to debugfs file
+ */
+extern int ttm_page_alloc_debugfs(struct seq_file *m, void *data);
+
+
+#ifdef CONFIG_SWIOTLB
 /**
  * Initialize pool allocator.
  */
-int ttm_page_alloc_init(struct ttm_mem_global *glob, unsigned max_pages);
+int ttm_dma_page_alloc_init(struct ttm_mem_global *glob, unsigned max_pages);
+
 /**
  * Free pool allocator.
  */
-void ttm_page_alloc_fini(void);
+void ttm_dma_page_alloc_fini(void);
 
 /**
  * Output the state of pools to debugfs file
  */
-extern int ttm_page_alloc_debugfs(struct seq_file *m, void *data);
+extern int ttm_dma_page_alloc_debugfs(struct seq_file *m, void *data);
+
+extern int ttm_dma_populate(struct ttm_dma_tt *ttm_dma, struct device *dev);
+extern void ttm_dma_unpopulate(struct ttm_dma_tt *ttm_dma, struct device *dev);
+
+#else
+static inline int ttm_dma_page_alloc_init(struct ttm_mem_global *glob,
+					  unsigned max_pages)
+{
+	return -ENODEV;
+}
+
+static inline void ttm_dma_page_alloc_fini(void) { return; }
+
+static inline int ttm_dma_page_alloc_debugfs(struct seq_file *m, void *data)
+{
+	return 0;
+}
+#endif
+
 #endif

include/linux/swiotlb.h

@@ -24,7 +24,7 @@ extern int swiotlb_force;
 
 extern void swiotlb_init(int verbose);
 extern void swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose);
-extern unsigned long swioltb_nr_tbl(void);
+extern unsigned long swiotlb_nr_tbl(void);
 
 /*
  * Enumeration for sync targets

lib/swiotlb.c

@@ -110,11 +110,11 @@ setup_io_tlb_npages(char *str)
 __setup("swiotlb=", setup_io_tlb_npages);
 /* make io_tlb_overflow tunable too? */
 
-unsigned long swioltb_nr_tbl(void)
+unsigned long swiotlb_nr_tbl(void)
 {
 	return io_tlb_nslabs;
 }
-
+EXPORT_SYMBOL_GPL(swiotlb_nr_tbl);
 /* Note that this doesn't work with highmem page */
 static dma_addr_t swiotlb_virt_to_bus(struct device *hwdev,
 				      volatile void *address)
@@ -321,6 +321,7 @@ void __init swiotlb_free(void)
 		free_bootmem_late(__pa(io_tlb_start),
 				  PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
 	}
+	io_tlb_nslabs = 0;
 }
 
 static int is_swiotlb_buffer(phys_addr_t paddr)