Received-SPF: pass (google.com: domain of linux-kernel+bounces-140564-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45e3:2400::1 as permitted sender) client-ip=2604:1380:45e3:2400::1;
Message-ID: <57d2fe8c-b438-42ae-a1ff-0ba0ee226c37@linux.intel.com>
Date: Thu, 11 Apr 2024 21:48:41 +0800
Precedence: bulk
MIME-Version: 1.0
User-Agent: Mozilla Thunderbird
Cc: baolu.lu@linux.intel.com, Kevin Tian <kevin.tian@intel.com>,
 Yi Liu <yi.l.liu@intel.com>, Jacob Pan <jacob.jun.pan@linux.intel.com>,
 Joerg Roedel <joro@8bytes.org>, Will Deacon <will@kernel.org>,
 linux-kernel@vger.kernel.org
Subject: Re: [PATCH v2 1/1] iommu/vt-d: Remove caching mode check before
 device TLB flush
To: Robin Murphy <robin.murphy@arm.com>, iommu@lists.linux.dev
References: <20240410055823.264501-1-baolu.lu@linux.intel.com>
 <51055d13-4a72-4000-9a22-b403d8c5b2ff@arm.com>
Content-Language: en-US
From: Baolu Lu <baolu.lu@linux.intel.com>
In-Reply-To: <51055d13-4a72-4000-9a22-b403d8c5b2ff@arm.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 8bit

On 2024/4/11 21:13, Robin Murphy wrote:
> On 10/04/2024 6:58 am, Lu Baolu wrote:
>> The Caching Mode (CM) of the Intel IOMMU indicates if the hardware
>> implementation caches not-present or erroneous translation-structure
>> entries except the first-stage translation. The caching mode is
>> irrelevant to the device TLB , therefore there is no need to check
>> it before a device TLB invalidation operation.
>>
>> iommu_flush_iotlb_psi() is called in map and unmap paths. The caching
>> mode check before device TLB invalidation will cause device TLB
>> invalidation always issued if IOMMU is not running in caching mode.
>> This is wrong and causes unnecessary performance overhead.
>>
>> The removal of caching mode check in intel_flush_iotlb_all() doesn't
>> impact anything no matter the IOMMU is working in caching mode or not.
>> Commit <29b32839725f> ("iommu/vt-d: Do not use flush-queue when
>> caching-mode is on") has already disabled flush-queue for caching mode,
>> hence caching mode will never call intel_flush_iotlb_all().
> 
> Well, technically it might still, at domain creation via 
> iommu_create_device_direct_mappings(), but domain->has_iotlb_device 
> should definitely be false at that point ????

Oh! I overlooked that path. :-)

Yes. iommu_create_device_direct_mappings() is called before setting the
domain to device for intel iommu driver, hence in practice the
domain->has_iotlb_device is always false.

Best regards,
baolu