drm/radeon/kms: enable the ttm dma pool if swiotlb is on V4

With the exception that we do not handle the AGP case. We only
deal with PCIe cards such as ATI ES1000 or HD3200 that have been
detected to only do DMA up to 32-bits.

V2 force dma32 if we fail to set bigger dma mask
V3 Rebase on top of no memory account changes (where/when is my
   delorean when i need it ?)
V4 add debugfs entry is swiotlb is active not only if we are
   on dma 32bits only gpu

CC: Dave Airlie <airlied@redhat.com>
CC: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Reviewed-by: Jerome Glisse <jglisse@redhat.com>

4 files changed, 84 insertions, 35 deletions

diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index b316b301152..83b2e016a4a 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/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;
 };
 
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index c33bc914d93..7c31321df45 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/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 */
diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c
index ba7ab79e12c..a4d98160858 100644
--- a/drivers/gpu/drm/radeon/radeon_gart.c
+++ b/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);
 }
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index b1768cb971c..f499b2c69de 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -578,11 +578,73 @@ struct ttm_tt *radeon_ttm_tt_create(struct ttm_bo_device *bdev,
 	return &gtt->ttm;
 }
 
+static int radeon_ttm_tt_populate(struct ttm_tt *ttm)
+{
+	struct radeon_device *rdev;
+	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(ttm, rdev->dev);
+	}
+#endif
+
+	r = ttm_pool_populate(ttm);
+	if (r) {
+		return r;
+	}
+
+	for (i = 0; i < ttm->num_pages; i++) {
+		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, ttm->dma_address[i])) {
+			while (--i) {
+				pci_unmap_page(rdev->pdev, ttm->dma_address[i],
+					       PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
+				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;
+	unsigned i;
+
+	rdev = radeon_get_rdev(ttm->bdev);
+
+#ifdef CONFIG_SWIOTLB
+	if (swiotlb_nr_tbl()) {
+		ttm_dma_unpopulate(ttm, rdev->dev);
+		return;
+	}
+#endif
+
+	for (i = 0; i < ttm->num_pages; i++) {
+		if (ttm->dma_address[i]) {
+			pci_unmap_page(rdev->pdev, ttm->dma_address[i],
+				       PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
+		}
+	}
+
+	ttm_pool_unpopulate(ttm);
+}
 
 static struct ttm_bo_driver radeon_bo_driver = {
 	.ttm_tt_create = &radeon_ttm_tt_create,
-	.ttm_tt_populate = &ttm_pool_populate,
-	.ttm_tt_unpopulate = &ttm_pool_unpopulate,
+	.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,
@@ -768,8 +830,8 @@ 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++) {
@@ -791,8 +853,17 @@ 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;