diff options
author | Michael S. Tsirkin <mst@redhat.com> | 2018-11-20 22:01:18 -0500 |
---|---|---|
committer | Michael S. Tsirkin <mst@redhat.com> | 2018-12-12 17:21:29 -0500 |
commit | 3c19f4b6bf7dcfdac96ade31c459c4288966600c (patch) | |
tree | aa3f11c500d77e8d47465b4c12ba5f9876ba9260 /notifications-be.c | |
parent | 66631dae1cceabd82d3fec3c0a99dacbfa3668ca (diff) | |
download | virtio-spec-3c19f4b6bf7dcfdac96ade31c459c4288966600c.tar.gz |
ACCESS_PLATFORM/ORDER_PLATFORM
This is an attempt to clarify the intent behind
VIRTIO_F_IOMMU_PLATFORM and VIRTIO_F_IO_BARRIER
which based on recent discussions appear to be hard to understand.
- rename VIRTIO_F_IOMMU_PLATFORM to ACCESS_PLATFORM
It is already the fact that the DMA API that Linux
uses does more than just IOMMUs - it includes
cache flushing, bounce buffers for limited
addressing, etc.
Update spec to match this reality.
- rename VIRTIO_F_IO_BARRIER to VIRTIO_F_ORDER_PLATFORM
this is after all what device is telling driver:
its memory accesses are only ordered weakly,
this is why a stronger barrier is required.
- As no one yet implemented IO_BARRIER yet, add a recommendation
to have a software fallback so that existing drivers
aren't broken.
Fixes: https://github.com/oasis-tcs/virtio-spec/issues/25
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Diffstat (limited to 'notifications-be.c')
0 files changed, 0 insertions, 0 deletions