On 02/02/17 18:18, Will Deacon wrote:

On Wed, Feb 01, 2017 at 04:29:50PM +0000, Marc Zyngier wrote:

quoted

On 27/01/17 18:07, Will Deacon wrote:

quoted

The SPE buffer is virtually addressed, using the page tables of the CPU
MMU. Unusually, this means that the EL0/1 page table may be live whilst
we're executing at EL2 on non-VHE configurations. When VHE is in use,
we can use the same property to profile the guest behind its back.

This patch adds the relevant disabling and flushing code to KVM so that
the host can make use of SPE without corrupting guest memory, and any
attempts by a guest to use SPE will result in a trap.

Cc: Marc Zyngier <redacted>
Cc: Alex Benn?e <redacted>
Cc: Christoffer Dall <redacted>
Signed-off-by: Will Deacon <redacted>
---
 arch/arm64/include/asm/kvm_arm.h  |  3 ++
 arch/arm64/include/asm/kvm_host.h |  7 ++++-
 arch/arm64/kvm/debug.c            |  6 ++++
 arch/arm64/kvm/hyp/debug-sr.c     | 66 +++++++++++++++++++++++++++++++++++++--
 arch/arm64/kvm/hyp/switch.c       | 17 +++++++++-
 5 files changed, 95 insertions(+), 4 deletions(-)

[...]

quoted

Acked-by: Marc Zyngier <redacted>

Thanks! Given that this patch depends on an earlier one in the series
(already queued via arm64) and the rest of the series depends on this
patch, do you mind if I take this via arm64 for 4.11? It applies cleanly
against current -next.

Sure, that's fine by me. I don't foresee anything clashing with this
patch that we may queue for 4.11.

Thanks,

	M.
-- 
Jazz is not dead. It just smells funny...