[PATCH-for-6.1 v3] block/nvme: Fix VFIO_MAP_DMA failed: No space left on device

[PATCH-for-6.1 v3] block/nvme: Fix VFIO_MAP_DMA failed: No space left on device

[Philippe Mathieu-Daudé]

When the NVMe block driver was introduced (see commit bdd6a90a9e5,
January 2018), Linux VFIO_IOMMU_MAP_DMA ioctl was only returning
-ENOMEM in case of error. The driver was correctly handling the
error path to recycle its volatile IOVA mappings.

To fix CVE-2019-3882, Linux commit 492855939bdb ("vfio/type1: Limit
DMA mappings per container", April 2019) added the -ENOSPC error to
signal the user exhausted the DMA mappings available for a container.

The block driver started to mis-behave:

  qemu-system-x86_64: VFIO_MAP_DMA failed: No space left on device
  (qemu)
  (qemu) info status
  VM status: paused (io-error)
  (qemu) c
  VFIO_MAP_DMA failed: No space left on device
  (qemu) c
  VFIO_MAP_DMA failed: No space left on device

(The VM is not resumable from here, hence stuck.)

Fix by handling the new -ENOSPC error (when DMA mappings are
exhausted) without any distinction to the current -ENOMEM error,
so we don't change the behavior on old kernels where the CVE-2019-3882
fix is not present.

An easy way to reproduce this bug is to restrict the DMA mapping
limit (65535 by default) when loading the VFIO IOMMU module:

  # modprobe vfio_iommu_type1 dma_entry_limit=666

Cc: qemu-stable@nongnu.org
Cc: Fam Zheng <fam@euphon.net>
Cc: Maxim Levitsky <mlevitsk@redhat.com>
Cc: Alex Williamson <alex.williamson@redhat.com>
Reported-by: Michal Prívozník <mprivozn@redhat.com>
Fixes: bdd6a90a9e5 ("block: Add VFIO based NVMe driver")
Buglink: https://bugs.launchpad.net/qemu/+bug/1863333
Resolves: https://gitlab.com/qemu-project/qemu/-/issues/65
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
---
v3: Reworded (Fam)
v2: KISS checking both errors undistinguishedly (Maxim)
---
 block/nvme.c | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/block/nvme.c b/block/nvme.c
index 2b5421e7aa6..e8dbbc23177 100644
--- a/block/nvme.c
+++ b/block/nvme.c
@@ -1030,7 +1030,29 @@ try_map:
         r = qemu_vfio_dma_map(s->vfio,
                               qiov->iov[i].iov_base,
                               len, true, &iova);
+        if (r == -ENOSPC) {
+            /*
+             * In addition to the -ENOMEM error, the VFIO_IOMMU_MAP_DMA
+             * ioctl returns -ENOSPC to signal the user exhausted the DMA
+             * mappings available for a container since Linux kernel commit
+             * 492855939bdb ("vfio/type1: Limit DMA mappings per container",
+             * April 2019, see CVE-2019-3882).
+             *
+             * This block driver already handles this error path by checking
+             * for the -ENOMEM error, so we directly replace -ENOSPC by
+             * -ENOMEM. Beside, -ENOSPC has a specific meaning for blockdev
+             * coroutines: it triggers BLOCKDEV_ON_ERROR_ENOSPC and
+             * BLOCK_ERROR_ACTION_STOP which stops the VM, asking the operator
+             * to add more storage to the blockdev. Not something we can do
+             * easily with an IOMMU :)
+             */
+            r = -ENOMEM;
+        }
         if (r == -ENOMEM && retry) {
+            /*
+             * We exhausted the DMA mappings available for our container:
+             * recycle the volatile IOVA mappings.
+             */
             retry = false;
             trace_nvme_dma_flush_queue_wait(s);
             if (s->dma_map_count) {
-- 
2.31.1

Re: [PATCH-for-6.1 v3] block/nvme: Fix VFIO_MAP_DMA failed: No space left on device

[Stefan Hajnoczi]

[-- Attachment #1: Type: text/plain, Size: 2083 bytes --]

On Fri, Jul 23, 2021 at 09:58:43PM +0200, Philippe Mathieu-Daudé wrote:
> When the NVMe block driver was introduced (see commit bdd6a90a9e5,
> January 2018), Linux VFIO_IOMMU_MAP_DMA ioctl was only returning
> -ENOMEM in case of error. The driver was correctly handling the
> error path to recycle its volatile IOVA mappings.
> 
> To fix CVE-2019-3882, Linux commit 492855939bdb ("vfio/type1: Limit
> DMA mappings per container", April 2019) added the -ENOSPC error to
> signal the user exhausted the DMA mappings available for a container.
> 
> The block driver started to mis-behave:
> 
>   qemu-system-x86_64: VFIO_MAP_DMA failed: No space left on device
>   (qemu)
>   (qemu) info status
>   VM status: paused (io-error)
>   (qemu) c
>   VFIO_MAP_DMA failed: No space left on device
>   (qemu) c
>   VFIO_MAP_DMA failed: No space left on device
> 
> (The VM is not resumable from here, hence stuck.)
> 
> Fix by handling the new -ENOSPC error (when DMA mappings are
> exhausted) without any distinction to the current -ENOMEM error,
> so we don't change the behavior on old kernels where the CVE-2019-3882
> fix is not present.
> 
> An easy way to reproduce this bug is to restrict the DMA mapping
> limit (65535 by default) when loading the VFIO IOMMU module:
> 
>   # modprobe vfio_iommu_type1 dma_entry_limit=666
> 
> Cc: qemu-stable@nongnu.org
> Cc: Fam Zheng <fam@euphon.net>
> Cc: Maxim Levitsky <mlevitsk@redhat.com>
> Cc: Alex Williamson <alex.williamson@redhat.com>
> Reported-by: Michal Prívozník <mprivozn@redhat.com>
> Fixes: bdd6a90a9e5 ("block: Add VFIO based NVMe driver")
> Buglink: https://bugs.launchpad.net/qemu/+bug/1863333
> Resolves: https://gitlab.com/qemu-project/qemu/-/issues/65
> Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
> ---
> v3: Reworded (Fam)
> v2: KISS checking both errors undistinguishedly (Maxim)
> ---
>  block/nvme.c | 22 ++++++++++++++++++++++
>  1 file changed, 22 insertions(+)

Thanks, applied to my block tree:
https://gitlab.com/stefanha/qemu/commits/block

Stefan

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]