[lkml]   [2019]   [Apr]   [27]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
Patch in this message
Subject[PATCH 3.16 189/202] vfio/type1: Limit DMA mappings per container
3.16.66-rc1 review patch.  If anyone has any objections, please let me know.


From: Alex Williamson <>

commit 492855939bdb59c6f947b0b5b44af9ad82b7e38c upstream.

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 <>
Tested-by: Eric Auger <>
Reviewed-by: Peter Xu <>
Reviewed-by: Cornelia Huck <>
Signed-off-by: Alex Williamson <>
[bwh: Backported to 3.16:
- Add the out_unlock label in vfio_dma_do_map()
- Adjust context]
Signed-off-by: Ben Hutchings <>
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -53,10 +53,16 @@ module_param_named(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);
+ "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;

@@ -364,6 +370,7 @@ static void vfio_remove_dma(struct vfio_
vfio_unmap_unpin(iommu, dma);
vfio_unlink_dma(iommu, dma);
+ iommu->dma_avail++;

static unsigned long vfio_pgsize_bitmap(struct vfio_iommu *iommu)
@@ -549,12 +556,18 @@ static int vfio_dma_do_map(struct vfio_i
return -EEXIST;

+ if (!iommu->dma_avail) {
+ ret = -ENOSPC;
+ goto out_unlock;
+ }
dma = kzalloc(sizeof(*dma), GFP_KERNEL);
if (!dma) {
return -ENOMEM;

+ iommu->dma_avail--;
dma->iova = iova;
dma->vaddr = vaddr;
dma->prot = prot;
@@ -586,6 +599,7 @@ static int vfio_dma_do_map(struct vfio_i
if (ret)
vfio_remove_dma(iommu, dma);

return ret;
@@ -816,6 +830,7 @@ static void *vfio_iommu_type1_open(unsig

iommu->dma_list = RB_ROOT;
+ iommu->dma_avail = dma_entry_limit;
iommu->v2 = (arg == VFIO_TYPE1v2_IOMMU);

 \ /
  Last update: 2019-04-27 17:16    [W:0.475 / U:0.360 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site