vfio/type1: Limit DMA mappings per container

Memory backed DMA mappings are accounted against a user's locked
memory limit, including multiple mappings of the same memory.  This
accounting bounds the number of such mappings that a user can create.
However, DMA mappings that are not backed by memory, such as DMA
mappings of device MMIO via mmaps, do not make use of page pinning
and therefore do not count against the user's locked memory limit.
These mappings still consume memory, but the memory is not well
associated to the process for the purpose of oom killing a task.

To add bounding on this use case, we introduce a limit to the total
number of concurrent DMA mappings that a user is allowed to create.
This limit is exposed as a tunable module option where the default
value of 64K is expected to be well in excess of any reasonable use
case (a large virtual machine configuration would typically only make
use of tens of concurrent mappings).

This fixes CVE-2019-3882.
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Tested-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>

CVE-2019-3882

(backported from commit 49285593)
[tyhicks: Backport to 4.4:
 - Minor context differences due to missing blocking notifier from commit
   c086de81 ("vfio iommu: Add blocking notifier to notify DMA_UNMAP")
 - vfio_dma_do_map() doesn't yet have an out_unlock label which was added in
   commit 8f0d5bb9 ("vfio iommu type1: Add task structure to vfio_dma")]
Signed-off-by: Tyler Hicks <tyhicks@canonical.com>
Acked-by: Colin Ian King <colin.king@canonical.com>
Acked-by: Stefan Bader <stefan.bader@canonical.com>
Signed-off-by: Khalid Elmously <khalid.elmously@canonical.com>

drivers/vfio/vfio_iommu_type1.c

@@ -53,10 +53,16 @@ module_param_named(disable_hugepages,
 MODULE_PARM_DESC(disable_hugepages,
 		 "Disable VFIO IOMMU support for IOMMU hugepages.");
 
+static unsigned int dma_entry_limit __read_mostly = U16_MAX;
+module_param_named(dma_entry_limit, dma_entry_limit, uint, 0644);
+MODULE_PARM_DESC(dma_entry_limit,
+		 "Maximum number of user DMA mappings per container (65535).");
+
 struct vfio_iommu {
 	struct list_head	domain_list;
 	struct mutex		lock;
 	struct rb_root		dma_list;
+	unsigned int		dma_avail;
 	bool			v2;
 	bool			nesting;
 };
@@ -382,6 +388,7 @@ static void vfio_remove_dma(struct vfio_iommu *iommu, struct vfio_dma *dma)
 	vfio_unmap_unpin(iommu, dma);
 	vfio_unlink_dma(iommu, dma);
 	kfree(dma);
+	iommu->dma_avail++;
 }
 
 static unsigned long vfio_pgsize_bitmap(struct vfio_iommu *iommu)
@@ -582,12 +589,18 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu,
 		return -EEXIST;
 	}
 
+	if (!iommu->dma_avail) {
+		mutex_unlock(&iommu->lock);
+		return -ENOSPC;
+	}
+
 	dma = kzalloc(sizeof(*dma), GFP_KERNEL);
 	if (!dma) {
 		mutex_unlock(&iommu->lock);
 		return -ENOMEM;
 	}
 
+	iommu->dma_avail--;
 	dma->iova = iova;
 	dma->vaddr = vaddr;
 	dma->prot = prot;
@@ -903,6 +916,7 @@ static void *vfio_iommu_type1_open(unsigned long arg)
 
 	INIT_LIST_HEAD(&iommu->domain_list);
 	iommu->dma_list = RB_ROOT;
+	iommu->dma_avail = dma_entry_limit;
 	mutex_init(&iommu->lock);
 
 	return iommu;