External/cloud-hypervisor
1
0
Fork 0
mirror of https://github.com/cloud-hypervisor/cloud-hypervisor.git synced 2025-02-01 17:35:19 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: Describe about virtio-iommu with FDT

Browse Source 
Added a section in "Usage" chapter of "iommu.md" to introduce the
special behavior when virtio-iommu is working with FDT on AArch64.

Signed-off-by: Michael Zhao <michael.zhao@arm.com>
This commit is contained in:
Michael Zhao 2021-09-17 17:04:23 +08:00 committed by Sebastien Boeuf
parent 9dc9e224b9
commit da8eecc797
1 changed files with 23 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
docs/iommu.md
View File

@ -121,6 +121,29 @@ lspci
00:04.0 Unassigned class [ffff]: Red Hat, Inc. Virtio RNG 00:04.0 Unassigned class [ffff]: Red Hat, Inc. Virtio RNG
``` ```
### Work with FDT on AArch64
On AArch64 architecture, the virtual IOMMU can still be used even if ACPI is not
enabled. But the effect is different with what the aforementioned test showed.
When ACPI is disabled, virtual IOMMU is supported through Flattened Device Tree
(FDT). In this case, the guest kernel can not tell which device should be
IOMMU-attached and which should not. No matter how many devices you attached to
the virtual IOMMU by setting `iommu=on` option, all the devices on the PCI bus
will be attached to the virtual IOMMU (except the IOMMU itself). Each of the
devices will be added into a IOMMU group.
As a result, the directory content of `/sys/kernel/iommu_groups` would be:
```bash
ls /sys/kernel/iommu_groups/0/devices/
0000:00:02.0
ls /sys/kernel/iommu_groups/1/devices/
0000:00:03.0
ls /sys/kernel/iommu_groups/2/devices/
0000:00:04.0
```
## Faster mappings ## Faster mappings
By default, the guest memory is mapped with 4k pages and no huge pages, which By default, the guest memory is mapped with 4k pages and no huge pages, which