Thread (1 message) flat view 1 message, 1 author, 2017-02-03

Re: [PATCH] Revert "vring: Force use of DMA API for ARM-based systems with legacy devices"

From: Will Deacon <hidden>
Date: 2017-02-03 09:57:26
Also in: lkml, stable

On Fri, Feb 03, 2017 at 05:49:11AM +0200, Michael S. Tsirkin wrote:
This reverts commit c7070619f3408d9a0dffbed9149e6f00479cf43b.

This has been shown to regress on some ARM systems:

by forcing on DMA API usage for ARM systems, we have inadvertently
kicked open a hornets' nest in terms of cache-coherency. Namely that
unless the virtio device is explicitly described as capable of coherent
DMA by firmware, the DMA APIs on ARM and other DT-based platforms will
assume it is non-coherent. This turns out to cause a big problem for the
likes of QEMU and kvmtool, which generate virtio-mmio devices in their
guest DTs but neglect to add the often-overlooked "dma-coherent"
property; as a result, we end up with the guest making non-cacheable
accesses to the vring, the host doing so cacheably, both talking past
each other and things going horribly wrong.

We are working on a safer work-around.

Fixes: c7070619f340 ("vring: Force use of DMA API for ARM-based systems with legacy devices")
Reported-by: Robin Murphy <robin.murphy@arm.com>
Cc: <redacted>
Signed-off-by: Will Deacon <redacted>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Marc Zyngier <redacted>
---

I'll merge this for 4.10. Let's fix it properly for 4.11.
Acked-by: Will Deacon <redacted>

Will
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help