On 2022-01-22 11:14, Ard Biesheuvel wrote:
On Sat, 22 Jan 2022 at 11:39, Marc Zyngier wrote:
Contrary to what df652bcf1136 ("KVM: arm64: vgic-v3: Work around GICv3
locally generated SErrors") was asserting, there is at least one other
system out there (Cavium ThunderX2) implementing SEIS, and
On Sat, 22 Jan 2022 at 11:39, Marc Zyngier wrote:
>
> Contrary to what df652bcf1136 ("KVM: arm64: vgic-v3: Work around GICv3
> locally generated SErrors") was asserting, there is at least one other
> system out there (Cavium ThunderX2) implementing SEIS, and not in
> an obviously broken way.
>
>
Contrary to what df652bcf1136 ("KVM: arm64: vgic-v3: Work around GICv3
locally generated SErrors") was asserting, there is at least one other
system out there (Cavium ThunderX2) implementing SEIS, and not in
an obviously broken way.
So instead of imposing the M1 workaround on an innocent