Message-ID: <e37f4226-b4ee-9a80-187c-ac13733d353c@linux.intel.com>
Date:   Wed, 8 Mar 2023 10:23:48 +0800
MIME-Version: 1.0
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:102.0) Gecko/20100101
 Thunderbird/102.7.1
Cc:     baolu.lu@linux.intel.com, dmaengine@vger.kernel.org,
        linux-kernel <linux-kernel@vger.kernel.org>,
        Alistair Popple <apopple@nvidia.com>,
        Joerg Roedel <joro@8bytes.org>, Will Deacon <will@kernel.org>,
        Robin Murphy <robin.murphy@arm.com>,
        Lorenzo Stoakes <lstoakes@gmail.com>,
        Christoph Hellwig <hch@infradead.org>, iommu@lists.linux.dev
Subject: Re: [PATCH v2 08/16] iommu: define and export
 iommu_access_remote_vm()
Content-Language: en-US
To:     Fenghua Yu <fenghua.yu@intel.com>, Vinod Koul <vkoul@kernel.org>,
        Dave Jiang <dave.jiang@intel.com>
References: <20230306163138.587484-1-fenghua.yu@intel.com>
 <20230306163138.587484-9-fenghua.yu@intel.com>
 <f7b0cbef-3d7d-e5aa-1971-fe230d0c80e1@linux.intel.com>
 <932aebd3-c655-3266-1acb-e41e8cbfb771@intel.com>
From:   Baolu Lu <baolu.lu@linux.intel.com>
In-Reply-To: <932aebd3-c655-3266-1acb-e41e8cbfb771@intel.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit
Precedence: bulk

On 3/8/23 1:55 AM, Fenghua Yu wrote:
> Hi, Baolu,
> 
> On 3/6/23 17:41, Baolu Lu wrote:
>> On 3/7/23 12:31 AM, Fenghua Yu wrote:
>>> Define and export iommu_access_remote_vm() to allow IOMMU related
>>> drivers to access user address space by PASID.
>>>
>>> The IDXD driver would like to use it to write the user's completion
>>> record that the hardware device is not able to write to due to user
>>> page fault.
>>
>> I don't quite follow here. Isn't I/O page fault already supported?
> 
> The following patch 9 in this series explains in details why IDXD device 
> cannot use page fault to write to user memory: 
> https://lore.kernel.org/dmaengine/20230306163138.587484-10-fenghua.yu@intel.com/
> 
> "DSA supports page fault handling through PRS. However, the DMA engine
> that's processing the descriptor is blocked until the PRS response is
> received. Other workqueues sharing the engine are also blocked.
> Page fault handing by the driver with PRS disabled can be used to
> mitigate the stalling.

Ah! Get your point now. Thanks for the explanation.

> 
> With PRS disabled while ATS remain enabled, DSA handles page faults on
> a completion record by reporting an event in the event log. In this
> instance, the descriptor is completed and the event log contains the
> completion record address and the contents of the completion record."
> 
> That's why IDXD driver needs this IOMMU's helper 
> iommu_access_remote_vm() to copy the completion record from event log 
> buffer to user space.
> 
> Thanks.
> 
> -Fenghua

Best regards,
baolu