IB/mlx5: Fix device memory flows

Fix device memory flows so that only once there will be no live mmaped
VA to a given allocation the matching object will be destroyed.

This prevents a potential scenario that existing VA that was mmaped by
one process might still be used post its deallocation despite that it's
owned now by other process.

The above is achieved by integrating with IB core APIs to manage
mmap/munmap. Only once the refcount will become 0 the DM object and its
underlay area will be freed.

Fixes: 3b113a1ec3d4 ("IB/mlx5: Support device memory type attribute")
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Link: https://lore.kernel.org/r/20191212100237.330654-3-leon@kernel.org
Signed-off-by: Doug Ledford <dledford@redhat.com>

1 files changed, 79 insertions, 41 deletions

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 2f5a159cbe1c..997cbfe4b90c 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -2074,6 +2074,24 @@ static int mlx5_ib_mmap_clock_info_page(struct mlx5_ib_dev *dev,
 			      virt_to_page(dev->mdev->clock_info));
 }
 
+static void mlx5_ib_mmap_free(struct rdma_user_mmap_entry *entry)
+{
+	struct mlx5_user_mmap_entry *mentry = to_mmmap(entry);
+	struct mlx5_ib_dev *dev = to_mdev(entry->ucontext->device);
+	struct mlx5_ib_dm *mdm;
+
+	switch (mentry->mmap_flag) {
+	case MLX5_IB_MMAP_TYPE_MEMIC:
+		mdm = container_of(mentry, struct mlx5_ib_dm, mentry);
+		mlx5_cmd_dealloc_memic(&dev->dm, mdm->dev_addr,
+				       mdm->size);
+		kfree(mdm);
+		break;
+	default:
+		WARN_ON(true);
+	}
+}
+
 static int uar_mmap(struct mlx5_ib_dev *dev, enum mlx5_ib_mmap_cmd cmd,
 		    struct vm_area_struct *vma,
 		    struct mlx5_ib_ucontext *context)
@@ -2186,26 +2204,55 @@ free_bfreg:
 	return err;
 }
 
-static int dm_mmap(struct ib_ucontext *context, struct vm_area_struct *vma)
+static int add_dm_mmap_entry(struct ib_ucontext *context,
+			     struct mlx5_ib_dm *mdm,
+			     u64 address)
+{
+	mdm->mentry.mmap_flag = MLX5_IB_MMAP_TYPE_MEMIC;
+	mdm->mentry.address = address;
+	return rdma_user_mmap_entry_insert_range(
+			context, &mdm->mentry.rdma_entry,
+			mdm->size,
+			MLX5_IB_MMAP_DEVICE_MEM << 16,
+			(MLX5_IB_MMAP_DEVICE_MEM << 16) + (1UL << 16) - 1);
+}
+
+static unsigned long mlx5_vma_to_pgoff(struct vm_area_struct *vma)
+{
+	unsigned long idx;
+	u8 command;
+
+	command = get_command(vma->vm_pgoff);
+	idx = get_extended_index(vma->vm_pgoff);
+
+	return (command << 16 | idx);
+}
+
+static int mlx5_ib_mmap_offset(struct mlx5_ib_dev *dev,
+			       struct vm_area_struct *vma,
+			       struct ib_ucontext *ucontext)
 {
-	struct mlx5_ib_ucontext *mctx = to_mucontext(context);
-	struct mlx5_ib_dev *dev = to_mdev(context->device);
-	u16 page_idx = get_extended_index(vma->vm_pgoff);
-	size_t map_size = vma->vm_end - vma->vm_start;
-	u32 npages = map_size >> PAGE_SHIFT;
+	struct mlx5_user_mmap_entry *mentry;
+	struct rdma_user_mmap_entry *entry;
+	unsigned long pgoff;
+	pgprot_t prot;
 	phys_addr_t pfn;
+	int ret;
 
-	if (find_next_zero_bit(mctx->dm_pages, page_idx + npages, page_idx) !=
-	    page_idx + npages)
+	pgoff = mlx5_vma_to_pgoff(vma);
+	entry = rdma_user_mmap_entry_get_pgoff(ucontext, pgoff);
+	if (!entry)
 		return -EINVAL;
 
-	pfn = ((dev->mdev->bar_addr +
-	      MLX5_CAP64_DEV_MEM(dev->mdev, memic_bar_start_addr)) >>
-	      PAGE_SHIFT) +
-	      page_idx;
-	return rdma_user_mmap_io(context, vma, pfn, map_size,
-				 pgprot_writecombine(vma->vm_page_prot),
-				 NULL);
+	mentry = to_mmmap(entry);
+	pfn = (mentry->address >> PAGE_SHIFT);
+	prot = pgprot_writecombine(vma->vm_page_prot);
+	ret = rdma_user_mmap_io(ucontext, vma, pfn,
+				entry->npages * PAGE_SIZE,
+				prot,
+				entry);
+	rdma_user_mmap_entry_put(&mentry->rdma_entry);
+	return ret;
 }
 
 static int mlx5_ib_mmap(struct ib_ucontext *ibcontext, struct vm_area_struct *vma)
@@ -2248,11 +2295,8 @@ static int mlx5_ib_mmap(struct ib_ucontext *ibcontext, struct vm_area_struct *vm
 	case MLX5_IB_MMAP_CLOCK_INFO:
 		return mlx5_ib_mmap_clock_info_page(dev, vma, context);
 
-	case MLX5_IB_MMAP_DEVICE_MEM:
-		return dm_mmap(ibcontext, vma);
-
 	default:
-		return -EINVAL;
+		return mlx5_ib_mmap_offset(dev, vma, ibcontext);
 	}
 
 	return 0;
@@ -2288,8 +2332,9 @@ static int handle_alloc_dm_memic(struct ib_ucontext *ctx,
 {
 	struct mlx5_dm *dm_db = &to_mdev(ctx->device)->dm;
 	u64 start_offset;
-	u32 page_idx;
+	u16 page_idx;
 	int err;
+	u64 address;
 
 	dm->size = roundup(attr->length, MLX5_MEMIC_BASE_SIZE);
 
@@ -2298,28 +2343,30 @@ static int handle_alloc_dm_memic(struct ib_ucontext *ctx,
 	if (err)
 		return err;
 
-	page_idx = (dm->dev_addr - pci_resource_start(dm_db->dev->pdev, 0) -
-		    MLX5_CAP64_DEV_MEM(dm_db->dev, memic_bar_start_addr)) >>
-		    PAGE_SHIFT;
+	address = dm->dev_addr & PAGE_MASK;
+	err = add_dm_mmap_entry(ctx, dm, address);
+	if (err)
+		goto err_dealloc;
 
+	page_idx = dm->mentry.rdma_entry.start_pgoff & 0xFFFF;
 	err = uverbs_copy_to(attrs,
 			     MLX5_IB_ATTR_ALLOC_DM_RESP_PAGE_INDEX,
-			     &page_idx, sizeof(page_idx));
+			     &page_idx,
+			     sizeof(page_idx));
 	if (err)
-		goto err_dealloc;
+		goto err_copy;
 
 	start_offset = dm->dev_addr & ~PAGE_MASK;
 	err = uverbs_copy_to(attrs,
 			     MLX5_IB_ATTR_ALLOC_DM_RESP_START_OFFSET,
 			     &start_offset, sizeof(start_offset));
 	if (err)
-		goto err_dealloc;
-
-	bitmap_set(to_mucontext(ctx)->dm_pages, page_idx,
-		   DIV_ROUND_UP(dm->size, PAGE_SIZE));
+		goto err_copy;
 
 	return 0;
 
+err_copy:
+	rdma_user_mmap_entry_remove(&dm->mentry.rdma_entry);
 err_dealloc:
 	mlx5_cmd_dealloc_memic(dm_db, dm->dev_addr, dm->size);
 
@@ -2423,23 +2470,13 @@ int mlx5_ib_dealloc_dm(struct ib_dm *ibdm, struct uverbs_attr_bundle *attrs)
 	struct mlx5_ib_ucontext *ctx = rdma_udata_to_drv_context(
 		&attrs->driver_udata, struct mlx5_ib_ucontext, ibucontext);
 	struct mlx5_core_dev *dev = to_mdev(ibdm->device)->mdev;
-	struct mlx5_dm *dm_db = &to_mdev(ibdm->device)->dm;
 	struct mlx5_ib_dm *dm = to_mdm(ibdm);
-	u32 page_idx;
 	int ret;
 
 	switch (dm->type) {
 	case MLX5_IB_UAPI_DM_TYPE_MEMIC:
-		ret = mlx5_cmd_dealloc_memic(dm_db, dm->dev_addr, dm->size);
-		if (ret)
-			return ret;
-
-		page_idx = (dm->dev_addr - pci_resource_start(dev->pdev, 0) -
-			    MLX5_CAP64_DEV_MEM(dev, memic_bar_start_addr)) >>
-			    PAGE_SHIFT;
-		bitmap_clear(ctx->dm_pages, page_idx,
-			     DIV_ROUND_UP(dm->size, PAGE_SIZE));
-		break;
+		rdma_user_mmap_entry_remove(&dm->mentry.rdma_entry);
+		return 0;
 	case MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM:
 		ret = mlx5_dm_sw_icm_dealloc(dev, MLX5_SW_ICM_TYPE_STEERING,
 					     dm->size, ctx->devx_uid, dm->dev_addr,
@@ -6235,6 +6272,7 @@ static const struct ib_device_ops mlx5_ib_dev_ops = {
 	.map_mr_sg = mlx5_ib_map_mr_sg,
 	.map_mr_sg_pi = mlx5_ib_map_mr_sg_pi,
 	.mmap = mlx5_ib_mmap,
+	.mmap_free = mlx5_ib_mmap_free,
 	.modify_cq = mlx5_ib_modify_cq,
 	.modify_device = mlx5_ib_modify_device,
 	.modify_port = mlx5_ib_modify_port,