Re: [PATCH] KVM: arm64: Skip CMOs when updating a PTE pointing to non-memory

From: Marc Zyngier <maz@kernel.org>
To: linux-arm-kernel@lists.infradead.org,
	kvmarm@lists.cs.columbia.edu, kvm@vger.kernel.org
Cc: Jean-Philippe Brucker <jean-philippe@linaro.org>,
	Suzuki K Poulose <suzuki.poulose@arm.com>,
	kernel-team@android.com, James Morse <james.morse@arm.com>,
	Sumit Gupta <sumitg@nvidia.com>,
	Alexandru Elisei <alexandru.elisei@arm.com>
Subject: Re: [PATCH] KVM: arm64: Skip CMOs when updating a PTE pointing to non-memory
Date: Mon, 26 Apr 2021 11:41:09 +0100	[thread overview]
Message-ID: <fa71b02d1a7c8be97968be1461749649@kernel.org> (raw)
In-Reply-To: <20210426103605.616908-1-maz@kernel.org>

On 2021-04-26 11:36, Marc Zyngier wrote:
> Sumit Gupta and Krishna Reddy both reported that for MMIO regions
> mapped into userspace using VFIO, a PTE update can trigger a MMU
> notifier reaching kvm_set_spte_hva().
> 
> There is an assumption baked in kvm_set_spte_hva() that it only
> deals with memory pages, and not MMIO. For this purpose, it
> performs a cache cleaning of the potentially newly mapped page.
> However, for a MMIO range, this explodes as there is no linear
> mapping for this range (and doing cache maintenance on it would
> make little sense anyway).
> 
> Check for the validity of the page before performing the CMO
> addresses the problem.
> 
> Reported-by: Krishna Reddy <vdumpa@nvidia.com>
> Reported-by: Sumit Gupta <sumitg@nvidia.com>,
> Tested-by: Sumit Gupta <sumitg@nvidia.com>,
> Signed-off-by: Marc Zyngier <maz@kernel.org>
> Link: 
> https://lore.kernel.org/r/5a8825bc-286e-b316-515f-3bd3c9c70a80@nvidia.com

FWIW, I've locally added:

Fixes: 694556d54f35 ("KVM: arm/arm64: Clean dcache to PoC when changing 
PTE due to CoW")
Cc: stable@vger.kernel.org

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