ODP Fixes

index 048f4e974a61..b90a3649e7d1 100644
@@ -101,18 +101,6 @@ void mlx5_ib_cont_pages(struct ib_umem *umem, u64 addr,
 	*count = i;
 }
 
-static u64 umem_dma_to_mtt(dma_addr_t umem_dma)
-{
-	u64 mtt_entry = umem_dma & ODP_DMA_ADDR_MASK;
-
-	if (umem_dma & ODP_READ_ALLOWED_BIT)
-		mtt_entry |= MLX5_IB_MTT_READ;
-	if (umem_dma & ODP_WRITE_ALLOWED_BIT)
-		mtt_entry |= MLX5_IB_MTT_WRITE;
-
-	return mtt_entry;
-}
-
 /*
  * Populate the given array with bus addresses from the umem.
  *

@@ -139,19 +127,6 @@ void __mlx5_ib_populate_pas(struct mlx5_ib_dev *dev, struct ib_umem *umem,
 	struct scatterlist *sg;
 	int entry;
 
-	if (umem->is_odp) {
-		WARN_ON(shift != 0);
-		WARN_ON(access_flags != (MLX5_IB_MTT_READ | MLX5_IB_MTT_WRITE));
-
-		for (i = 0; i < num_pages; ++i) {
-			dma_addr_t pa =
-				to_ib_umem_odp(umem)->dma_list[offset + i];
-
-			pas[i] = cpu_to_be64(umem_dma_to_mtt(pa));
-		}
-		return;
-	}
-
 	i = 0;
 	for_each_sg(umem->sg_head.sgl, sg, umem->nmap, entry) {
 		len = sg_dma_len(sg) >> PAGE_SHIFT;

index b06f32ff5748..927948328184 100644
@@ -1276,8 +1276,8 @@ void mlx5_ib_odp_cleanup_one(struct mlx5_ib_dev *ibdev);
 int __init mlx5_ib_odp_init(void);
 void mlx5_ib_odp_cleanup(void);
 void mlx5_odp_init_mr_cache_entry(struct mlx5_cache_ent *ent);
-void mlx5_odp_populate_klm(struct mlx5_klm *pklm, size_t offset,
-			   size_t nentries, struct mlx5_ib_mr *mr, int flags);
+void mlx5_odp_populate_xlt(void *xlt, size_t idx, size_t nentries,
+			   struct mlx5_ib_mr *mr, int flags);
 
 int mlx5_ib_advise_mr_prefetch(struct ib_pd *pd,
 			       enum ib_uverbs_advise_mr_advice advice,

@@ -1293,9 +1293,8 @@ static inline void mlx5_ib_odp_cleanup_one(struct mlx5_ib_dev *ibdev) {}
 static inline int mlx5_ib_odp_init(void) { return 0; }
 static inline void mlx5_ib_odp_cleanup(void)				    {}
 static inline void mlx5_odp_init_mr_cache_entry(struct mlx5_cache_ent *ent) {}
-static inline void mlx5_odp_populate_klm(struct mlx5_klm *pklm, size_t offset,
-					 size_t nentries, struct mlx5_ib_mr *mr,
-					 int flags) {}
+static inline void mlx5_odp_populate_xlt(void *xlt, size_t idx, size_t nentries,
+					 struct mlx5_ib_mr *mr, int flags) {}
 
 static inline int
 mlx5_ib_advise_mr_prefetch(struct ib_pd *pd,

85 lines not on this page · raw message

54 lines not on this page · raw message

index e42d44e501fd..2e9ee7adab13 100644
@@ -440,7 +440,7 @@ int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 user_virt,
 
 	while (bcnt > 0) {
 		const size_t gup_num_pages = min_t(size_t,
-				(bcnt + BIT(page_shift) - 1) >> page_shift,
+				ALIGN(bcnt, PAGE_SIZE) / PAGE_SIZE,
 				PAGE_SIZE / sizeof(struct page *));
 
 		down_read(&owning_mm->mmap_sem);

index 2e9ee7adab13..533271897908 100644
@@ -241,22 +241,10 @@ struct ib_umem_odp *ib_umem_odp_get(struct ib_udata *udata, unsigned long addr,
 	umem_odp->umem.owning_mm = mm = current->mm;
 	umem_odp->notifier.ops = ops;
 
-	umem_odp->page_shift = PAGE_SHIFT;
-	if (access & IB_ACCESS_HUGETLB) {
-		struct vm_area_struct *vma;
-		struct hstate *h;
-
-		down_read(&mm->mmap_sem);
-		vma = find_vma(mm, ib_umem_start(umem_odp));
-		if (!vma || !is_vm_hugetlb_page(vma)) {
-			up_read(&mm->mmap_sem);
-			ret = -EINVAL;
-			goto err_free;
-		}
-		h = hstate_vma(vma);
-		umem_odp->page_shift = huge_page_shift(h);
-		up_read(&mm->mmap_sem);
-	}
+	if (access & IB_ACCESS_HUGETLB)
+		umem_odp->page_shift = HPAGE_SHIFT;
+	else
+		umem_odp->page_shift = PAGE_SHIFT;
 
 	umem_odp->tgid = get_task_pid(current->group_leader, PIDTYPE_PID);
 	ret = ib_init_umem_odp(umem_odp, ops);

@@ -266,7 +254,6 @@ struct ib_umem_odp *ib_umem_odp_get(struct ib_udata *udata, unsigned long addr,
 
 err_put_pid:
 	put_pid(umem_odp->tgid);
-err_free:
 	kfree(umem_odp);
 	return ERR_PTR(ret);
 }

@@ -403,6 +390,7 @@ int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 user_virt,
 	int j, k, ret = 0, start_idx, npages = 0;
 	unsigned int flags = 0, page_shift;
 	phys_addr_t p = 0;
+	struct vm_area_struct **vmas;
 
 	if (access_mask == 0)
 		return -EINVAL;

@@ -415,6 +403,12 @@ int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 user_virt,
 	if (!local_page_list)
 		return -ENOMEM;
 
+	vmas = (struct vm_area_struct **)__get_free_page(GFP_KERNEL);
+	if (!vmas) {
+		ret = -ENOMEM;
+		goto out_free_page_list;
+	}
+
 	page_shift = umem_odp->page_shift;
 	page_mask = ~(BIT(page_shift) - 1);
 	off = user_virt & (~page_mask);

@@ -453,7 +447,7 @@ int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 user_virt,
 		 */
 		npages = get_user_pages_remote(owning_process, owning_mm,
 				user_virt, gup_num_pages,
-				flags, local_page_list, NULL, NULL);
+				flags, local_page_list, vmas, NULL);
 		up_read(&owning_mm->mmap_sem);
 
 		if (npages < 0) {

@@ -477,6 +471,11 @@ int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 user_virt,
 				continue;
 			}
 
+			if ((1 << page_shift) > vma_kernel_pagesize(vmas[j])) {
+				ret = -EFAULT;
+				break;
+			}
+
 			ret = ib_umem_odp_map_dma_single_page(
 					umem_odp, k, local_page_list[j],
 					access_mask, current_seq);

@@ -517,6 +516,8 @@ int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 user_virt,
 out_put_task:
 	if (owning_process)
 		put_task_struct(owning_process);
+	free_page((unsigned long)vmas);
+out_free_page_list:
 	free_page((unsigned long)local_page_list);
 	return ret;
 }