From: Konrad Rzeszutek Wilk konrad.wilk@oracle.com
If the card is capable of more than 32-bit, then use the default TTM page pool code which allocates from anywhere in the memory.
Note: If the 'ttm.no_dma' parameter is set, the override is ignored and the default TTM pool is used.
V2 use pci_set_consistent_dma_mask
CC: Ben Skeggs bskeggs@redhat.com CC: Francisco Jerez currojerez@riseup.net CC: Dave Airlie airlied@redhat.com Signed-off-by: Konrad Rzeszutek Wilk konrad.wilk@oracle.com Reviewed-by: Jerome Glisse jglisse@redhat.com --- drivers/gpu/drm/nouveau/nouveau_bo.c | 73 ++++++++++++++++++++++++++++- drivers/gpu/drm/nouveau/nouveau_debugfs.c | 1 + drivers/gpu/drm/nouveau/nouveau_mem.c | 6 ++ drivers/gpu/drm/nouveau/nouveau_sgdma.c | 60 +----------------------- 4 files changed, 79 insertions(+), 61 deletions(-)
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 7e5ca3f..36234a7 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -1049,10 +1049,79 @@ 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 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 ((dma_get_mask(dev->dev) <= DMA_BIT_MASK(32)) && swiotlb_nr_tbl()) { + return ttm_dma_populate(ttm, dev->dev); + } +#endif + + r = ttm_page_alloc_ttm_tt_populate(ttm); + if (r) { + return r; + } + + for (i = 0; i < ttm->num_pages; i++) { + ttm->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_address[i])) { + while (--i) { + pci_unmap_page(dev->pdev, ttm->dma_address[i], + PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); + ttm->dma_address[i] = 0; + } + ttm_page_alloc_ttm_tt_unpopulate(ttm); + return -EFAULT; + } + } + return 0; +} + +static void +nouveau_ttm_tt_unpopulate(struct ttm_tt *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 ((dma_get_mask(dev->dev) <= DMA_BIT_MASK(32)) && swiotlb_nr_tbl()) { + ttm_dma_unpopulate(ttm, dev->dev); + return; + } +#endif + + for (i = 0; i < ttm->num_pages; i++) { + if (ttm->dma_address[i]) { + pci_unmap_page(dev->pdev, ttm->dma_address[i], + PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); + } + } + + ttm_page_alloc_ttm_tt_unpopulate(ttm); +} + struct ttm_bo_driver nouveau_bo_driver = { .ttm_tt_create = &nouveau_ttm_tt_create, - .ttm_tt_populate = &ttm_page_alloc_ttm_tt_populate, - .ttm_tt_unpopulate = &ttm_page_alloc_ttm_tt_unpopulate, + .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, diff --git a/drivers/gpu/drm/nouveau/nouveau_debugfs.c b/drivers/gpu/drm/nouveau/nouveau_debugfs.c index 8e15923..f52c2db 100644 --- a/drivers/gpu/drm/nouveau/nouveau_debugfs.c +++ b/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)
diff --git a/drivers/gpu/drm/nouveau/nouveau_mem.c b/drivers/gpu/drm/nouveau/nouveau_mem.c index 36bec48..37fcaa2 100644 --- a/drivers/gpu/drm/nouveau/nouveau_mem.c +++ b/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) diff --git a/drivers/gpu/drm/nouveau/nouveau_sgdma.c b/drivers/gpu/drm/nouveau/nouveau_sgdma.c index bc2ab90..ee1eb7c 100644 --- a/drivers/gpu/drm/nouveau/nouveau_sgdma.c +++ b/drivers/gpu/drm/nouveau/nouveau_sgdma.c @@ -13,41 +13,6 @@ struct nouveau_sgdma_be { u64 offset; };
-static int -nouveau_sgdma_dma_map(struct ttm_tt *ttm) -{ - struct nouveau_sgdma_be *nvbe = (struct nouveau_sgdma_be *)ttm; - struct drm_device *dev = nvbe->dev; - int i; - - for (i = 0; i < ttm->num_pages; i++) { - ttm->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_address[i])) { - return -EFAULT; - } - } - - return 0; -} - -static void -nouveau_sgdma_dma_unmap(struct ttm_tt *ttm) -{ - struct nouveau_sgdma_be *nvbe = (struct nouveau_sgdma_be *)ttm; - struct drm_device *dev = nvbe->dev; - int i; - - for (i = 0; i < ttm->num_pages; i++) { - if (ttm->dma_address[i]) { - pci_unmap_page(dev->pdev, ttm->dma_address[i], - PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); - } - ttm->dma_address[i] = 0; - } -} - static void nouveau_sgdma_destroy(struct ttm_tt *ttm) { @@ -67,13 +32,8 @@ nv04_sgdma_bind(struct ttm_tt *ttm, struct ttm_mem_reg *mem) struct drm_nouveau_private *dev_priv = dev->dev_private; struct nouveau_gpuobj *gpuobj = dev_priv->gart_info.sg_ctxdma; unsigned i, j, pte; - int r;
NV_DEBUG(dev, "pg=0x%lx\n", mem->start); - r = nouveau_sgdma_dma_map(ttm); - if (r) { - return r; - }
nvbe->offset = mem->start << PAGE_SHIFT; pte = (nvbe->offset >> NV_CTXDMA_PAGE_SHIFT) + 2; @@ -110,7 +70,6 @@ nv04_sgdma_unbind(struct ttm_tt *ttm) nv_wo32(gpuobj, (pte * 4) + 0, 0x00000000); }
- nouveau_sgdma_dma_unmap(ttm); return 0; }
@@ -141,13 +100,8 @@ nv41_sgdma_bind(struct ttm_tt *ttm, struct ttm_mem_reg *mem) dma_addr_t *list = ttm->dma_address; u32 pte = mem->start << 2; u32 cnt = ttm->num_pages; - int r;
nvbe->offset = mem->start << PAGE_SHIFT; - r = nouveau_sgdma_dma_map(ttm); - if (r) { - return r; - }
while (cnt--) { nv_wo32(pgt, pte, (*list++ >> 7) | 1); @@ -173,7 +127,6 @@ nv41_sgdma_unbind(struct ttm_tt *ttm) }
nv41_sgdma_flush(nvbe); - nouveau_sgdma_dma_unmap(ttm); return 0; }
@@ -256,13 +209,9 @@ nv44_sgdma_bind(struct ttm_tt *ttm, struct ttm_mem_reg *mem) dma_addr_t *list = ttm->dma_address; u32 pte = mem->start << 2, tmp[4]; u32 cnt = ttm->num_pages; - int i, r; + int i;
nvbe->offset = mem->start << PAGE_SHIFT; - r = nouveau_sgdma_dma_map(ttm); - if (r) { - return r; - }
if (pte & 0x0000000c) { u32 max = 4 - ((pte >> 2) & 0x3); @@ -321,7 +270,6 @@ nv44_sgdma_unbind(struct ttm_tt *ttm) nv44_sgdma_fill(pgt, NULL, pte, cnt);
nv44_sgdma_flush(ttm); - nouveau_sgdma_dma_unmap(ttm); return 0; }
@@ -335,13 +283,8 @@ static int nv50_sgdma_bind(struct ttm_tt *ttm, struct ttm_mem_reg *mem) { struct nouveau_mem *node = mem->mm_node; - int r;
/* noop: bound in move_notify() */ - r = nouveau_sgdma_dma_map(ttm); - if (r) { - return r; - } node->pages = ttm->dma_address; return 0; } @@ -350,7 +293,6 @@ static int nv50_sgdma_unbind(struct ttm_tt *ttm) { /* noop: unbound in move_notify() */ - nouveau_sgdma_dma_unmap(ttm); return 0; }