Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Message-ID: <22b659c7-e972-7a56-2bd7-8df3b4820d4e@intel.com>
Date:   Mon, 25 Apr 2022 08:55:46 -0700
MIME-Version: 1.0
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:91.0) Gecko/20100101
 Thunderbird/91.7.0
Subject: Re: [PATCH v4 05/11] iommu/sva: Assign a PASID to mm on PASID
 allocation and free it on mm exit
Content-Language: en-US
To:     Jean-Philippe Brucker <jean-philippe@linaro.org>
Cc:     "zhangfei.gao@foxmail.com" <zhangfei.gao@foxmail.com>,
        Fenghua Yu <fenghua.yu@intel.com>,
        Joerg Roedel <joro@8bytes.org>,
        Ravi V Shankar <ravi.v.shankar@intel.com>,
        Tony Luck <tony.luck@intel.com>,
        Ashok Raj <ashok.raj@intel.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Dave Hansen <dave.hansen@linux.intel.com>,
        x86 <x86@kernel.org>,
        linux-kernel <linux-kernel@vger.kernel.org>,
        iommu <iommu@lists.linux-foundation.org>,
        Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
        Andy Lutomirski <luto@kernel.org>,
        Josh Poimboeuf <jpoimboe@redhat.com>,
        Thomas Gleixner <tglx@linutronix.de>, will@kernel.org,
        robin.murphy@arm.com, zhangfei.gao@linaro.org
References: <YllADL6uMoLllzQo@fyu1.sc.intel.com> <YmA4pbgevqln/jSO@myrica>
 <tencent_76E043C4D1B6A21A5253579A61034107EB06@qq.com>
 <tencent_7477100F8A445C6CAFA8F13601A55134480A@qq.com>
 <YmJ/WA6KAQU/xJjA@myrica>
 <tencent_A4E83BA6071B2204B6F5D4E69A50D21C1A09@qq.com>
 <YmLOznyBF0f7COYT@myrica>
 <tencent_2922DAB6F3D5789A1CD3A21A843B4007ED09@qq.com>
 <Yman5hLomw9/c+bi@myrica> <76ec6342-0d7c-7c7b-c132-2892e4048fa1@intel.com>
 <YmavoKkVu+hd+x0M@myrica>
From:   Dave Hansen <dave.hansen@intel.com>
In-Reply-To: <YmavoKkVu+hd+x0M@myrica>
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 7bit
Precedence: bulk

On 4/25/22 07:26, Jean-Philippe Brucker wrote:
>>
>> How does the IOMMU hardware know that all activity to a given PASID is
>> finished?  That activity should, today, be independent of an mm or a
>> fd's lifetime.
> In the case of uacce, it's tied to the fd lifetime: opening an accelerator
> queue calls iommu_sva_bind_device(), which sets up the PASID context in
> the IOMMU. Closing the queue calls iommu_sva_unbind_device() which
> destroys the PASID context (after the device driver stopped all DMA for
> this PASID).

Could this PASID context destruction move from being "fd-based" to
happening under mm_pasid_drop()?  Logically, it seems like that should
work because mm_pasid_drop() happens after exit_mmap() where the VMAs
(which hold references to 'struct file' via vma->vm_file) are torn down.