Received-SPF: pass (google.com: domain of linux-kernel+bounces-58154-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:4601:e00::3 as permitted sender) client-ip=2604:1380:4601:e00::3;
Date: Thu, 8 Feb 2024 13:26:52 +0000
From: Oliver Upton <oliver.upton@linux.dev>
To: ankita@nvidia.com
Cc: jgg@nvidia.com, maz@kernel.org, james.morse@arm.com,
	suzuki.poulose@arm.com, yuzenghui@huawei.com,
	reinette.chatre@intel.com, surenb@google.com, stefanha@redhat.com,
	brauner@kernel.org, catalin.marinas@arm.com, will@kernel.org,
	mark.rutland@arm.com, alex.williamson@redhat.com,
	kevin.tian@intel.com, yi.l.liu@intel.com, ardb@kernel.org,
	akpm@linux-foundation.org, andreyknvl@gmail.com,
	wangjinchao@xfusion.com, gshan@redhat.com, ricarkol@google.com,
	linux-mm@kvack.org, lpieralisi@kernel.org, rananta@google.com,
	ryan.roberts@arm.com, aniketa@nvidia.com, cjia@nvidia.com,
	kwankhede@nvidia.com, targupta@nvidia.com, vsethi@nvidia.com,
	acurrid@nvidia.com, apopple@nvidia.com, jhubbard@nvidia.com,
	danw@nvidia.com, kvmarm@lists.linux.dev, mochs@nvidia.com,
	zhiw@nvidia.com, kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-arm-kernel@lists.infradead.org
Subject: Re: [PATCH v6 3/4] kvm: arm64: set io memory s2 pte as normalnc for
 vfio pci device
Message-ID: <ZcTWnDBfAtMriXqp@linux.dev>
References: <20240207204652.22954-1-ankita@nvidia.com>
 <20240207204652.22954-4-ankita@nvidia.com>
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20240207204652.22954-4-ankita@nvidia.com>

On Thu, Feb 08, 2024 at 02:16:51AM +0530, ankita@nvidia.com wrote:
> @@ -1557,10 +1559,18 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
>  	if (exec_fault)
>  		prot |= KVM_PGTABLE_PROT_X;
>  
> -	if (device)
> -		prot |= KVM_PGTABLE_PROT_DEVICE;
> -	else if (cpus_have_final_cap(ARM64_HAS_CACHE_DIC))
> +	if (device) {
> +		/*
> +		 * To provide VM with the ability to get device IO memory
> +		 * with NormalNC property, map device MMIO as NormalNC in S2.
> +		 */

nit: the comment doesn't provide anything of value, the logic is rather
straightforward here.

> +		if (vfio_allow_wc)
> +			prot |= KVM_PGTABLE_PROT_NORMAL_NC;
> +		else
> +			prot |= KVM_PGTABLE_PROT_DEVICE;
> +	} else if (cpus_have_final_cap(ARM64_HAS_CACHE_DIC)) {
>  		prot |= KVM_PGTABLE_PROT_X;
> +	}
>  
>  	/*
>  	 * Under the premise of getting a FSC_PERM fault, we just need to relax
> -- 
> 2.34.1
>

-- 
Thanks,
Oliver