Merge branch 'odp_fixes' into hmm.git

From rdma.git

Jason Gunthorpe says:

====================
This is a collection of general cleanups for ODP to clarify some of the
flows around umem creation and use of the interval tree.
====================

The branch is based on v5.3-rc5 due to dependencies, and is being taken
into hmm.git due to dependencies in the next patches.

* odp_fixes:
  RDMA/mlx5: Use odp instead of mr->umem in pagefault_mr
  RDMA/mlx5: Use ib_umem_start instead of umem.address
  RDMA/core: Make invalidate_range a device operation
  RDMA/odp: Use kvcalloc for the dma_list and page_list
  RDMA/odp: Check for overflow when computing the umem_odp end
  RDMA/odp: Provide ib_umem_odp_release() to undo the allocs
  RDMA/odp: Split creating a umem_odp from ib_umem_get
  RDMA/odp: Make the three ways to create a umem_odp clear
  RMDA/odp: Consolidate umem_odp initialization
  RDMA/odp: Make it clearer when a umem is an implicit ODP umem
  RDMA/odp: Iterate over the whole rbtree directly
  RDMA/odp: Use the common interval tree library instead of generic
  RDMA/mlx5: Fix MR npages calculation for IB_ACCESS_HUGETLB

Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

1 files changed, 42 insertions, 5 deletions

diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 8b78554cfde3..8cf6362e64bf 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -32,6 +32,46 @@ static bool use_pages(struct drm_gem_object *obj)
 	return !msm_obj->vram_node;
 }
 
+/*
+ * Cache sync.. this is a bit over-complicated, to fit dma-mapping
+ * API.  Really GPU cache is out of scope here (handled on cmdstream)
+ * and all we need to do is invalidate newly allocated pages before
+ * mapping to CPU as uncached/writecombine.
+ *
+ * On top of this, we have the added headache, that depending on
+ * display generation, the display's iommu may be wired up to either
+ * the toplevel drm device (mdss), or to the mdp sub-node, meaning
+ * that here we either have dma-direct or iommu ops.
+ *
+ * Let this be a cautionary tail of abstraction gone wrong.
+ */
+
+static void sync_for_device(struct msm_gem_object *msm_obj)
+{
+	struct device *dev = msm_obj->base.dev->dev;
+
+	if (get_dma_ops(dev)) {
+		dma_sync_sg_for_device(dev, msm_obj->sgt->sgl,
+			msm_obj->sgt->nents, DMA_BIDIRECTIONAL);
+	} else {
+		dma_map_sg(dev, msm_obj->sgt->sgl,
+			msm_obj->sgt->nents, DMA_BIDIRECTIONAL);
+	}
+}
+
+static void sync_for_cpu(struct msm_gem_object *msm_obj)
+{
+	struct device *dev = msm_obj->base.dev->dev;
+
+	if (get_dma_ops(dev)) {
+		dma_sync_sg_for_cpu(dev, msm_obj->sgt->sgl,
+			msm_obj->sgt->nents, DMA_BIDIRECTIONAL);
+	} else {
+		dma_unmap_sg(dev, msm_obj->sgt->sgl,
+			msm_obj->sgt->nents, DMA_BIDIRECTIONAL);
+	}
+}
+
 /* allocate pages from VRAM carveout, used when no IOMMU: */
 static struct page **get_pages_vram(struct drm_gem_object *obj, int npages)
 {
@@ -97,8 +137,7 @@ static struct page **get_pages(struct drm_gem_object *obj)
 		 * because display controller, GPU, etc. are not coherent:
 		 */
 		if (msm_obj->flags & (MSM_BO_WC|MSM_BO_UNCACHED))
-			dma_map_sg(dev->dev, msm_obj->sgt->sgl,
-					msm_obj->sgt->nents, DMA_BIDIRECTIONAL);
+			sync_for_device(msm_obj);
 	}
 
 	return msm_obj->pages;
@@ -127,9 +166,7 @@ static void put_pages(struct drm_gem_object *obj)
 			 * GPU, etc. are not coherent:
 			 */
 			if (msm_obj->flags & (MSM_BO_WC|MSM_BO_UNCACHED))
-				dma_unmap_sg(obj->dev->dev, msm_obj->sgt->sgl,
-					     msm_obj->sgt->nents,
-					     DMA_BIDIRECTIONAL);
+				sync_for_cpu(msm_obj);
 
 			sg_free_table(msm_obj->sgt);
 			kfree(msm_obj->sgt);