static int vfio_dma_do_map()

in vfio_iommu_type1.c [1550:1680]

• 82 lines of code
• 27 McCabe index (conditional complexity)

static int vfio_dma_do_map(struct vfio_iommu *iommu,
			   struct vfio_iommu_type1_dma_map *map)
{
	bool set_vaddr = map->flags & VFIO_DMA_MAP_FLAG_VADDR;
	dma_addr_t iova = map->iova;
	unsigned long vaddr = map->vaddr;
	size_t size = map->size;
	int ret = 0, prot = 0;
	size_t pgsize;
	struct vfio_dma *dma;

	/* Verify that none of our __u64 fields overflow */
	if (map->size != size || map->vaddr != vaddr || map->iova != iova)
		return -EINVAL;

	/* READ/WRITE from device perspective */
	if (map->flags & VFIO_DMA_MAP_FLAG_WRITE)
		prot |= IOMMU_WRITE;
	if (map->flags & VFIO_DMA_MAP_FLAG_READ)
		prot |= IOMMU_READ;

	if ((prot && set_vaddr) || (!prot && !set_vaddr))
		return -EINVAL;

	mutex_lock(&iommu->lock);

	pgsize = (size_t)1 << __ffs(iommu->pgsize_bitmap);

	WARN_ON((pgsize - 1) & PAGE_MASK);

	if (!size || (size | iova | vaddr) & (pgsize - 1)) {
		ret = -EINVAL;
		goto out_unlock;
	}

	/* Don't allow IOVA or virtual address wrap */
	if (iova + size - 1 < iova || vaddr + size - 1 < vaddr) {
		ret = -EINVAL;
		goto out_unlock;
	}

	dma = vfio_find_dma(iommu, iova, size);
	if (set_vaddr) {
		if (!dma) {
			ret = -ENOENT;
		} else if (!dma->vaddr_invalid || dma->iova != iova ||
			   dma->size != size) {
			ret = -EINVAL;
		} else {
			dma->vaddr = vaddr;
			dma->vaddr_invalid = false;
			iommu->vaddr_invalid_count--;
			wake_up_all(&iommu->vaddr_wait);
		}
		goto out_unlock;
	} else if (dma) {
		ret = -EEXIST;
		goto out_unlock;
	}

	if (!iommu->dma_avail) {
		ret = -ENOSPC;
		goto out_unlock;
	}

	if (!vfio_iommu_iova_dma_valid(iommu, iova, iova + size - 1)) {
		ret = -EINVAL;
		goto out_unlock;
	}

	dma = kzalloc(sizeof(*dma), GFP_KERNEL);
	if (!dma) {
		ret = -ENOMEM;
		goto out_unlock;
	}

	iommu->dma_avail--;
	dma->iova = iova;
	dma->vaddr = vaddr;
	dma->prot = prot;

	/*
	 * We need to be able to both add to a task's locked memory and test
	 * against the locked memory limit and we need to be able to do both
	 * outside of this call path as pinning can be asynchronous via the
	 * external interfaces for mdev devices.  RLIMIT_MEMLOCK requires a
	 * task_struct and VM locked pages requires an mm_struct, however
	 * holding an indefinite mm reference is not recommended, therefore we
	 * only hold a reference to a task.  We could hold a reference to
	 * current, however QEMU uses this call path through vCPU threads,
	 * which can be killed resulting in a NULL mm and failure in the unmap
	 * path when called via a different thread.  Avoid this problem by
	 * using the group_leader as threads within the same group require
	 * both CLONE_THREAD and CLONE_VM and will therefore use the same
	 * mm_struct.
	 *
	 * Previously we also used the task for testing CAP_IPC_LOCK at the
	 * time of pinning and accounting, however has_capability() makes use
	 * of real_cred, a copy-on-write field, so we can't guarantee that it
	 * matches group_leader, or in fact that it might not change by the
	 * time it's evaluated.  If a process were to call MAP_DMA with
	 * CAP_IPC_LOCK but later drop it, it doesn't make sense that they
	 * possibly see different results for an iommu_mapped vfio_dma vs
	 * externally mapped.  Therefore track CAP_IPC_LOCK in vfio_dma at the
	 * time of calling MAP_DMA.
	 */
	get_task_struct(current->group_leader);
	dma->task = current->group_leader;
	dma->lock_cap = capable(CAP_IPC_LOCK);

	dma->pfn_list = RB_ROOT;

	/* Insert zero-sized and grow as we map chunks of it */
	vfio_link_dma(iommu, dma);

	/* Don't pin and map if container doesn't contain IOMMU capable domain*/
	if (list_empty(&iommu->domain_list))
		dma->size = size;
	else
		ret = vfio_pin_map_dma(iommu, dma, size);

	if (!ret && iommu->dirty_page_tracking) {
		ret = vfio_dma_bitmap_alloc(dma, pgsize);
		if (ret)
			vfio_remove_dma(iommu, dma);
	}

out_unlock:
	mutex_unlock(&iommu->lock);
	return ret;
}