Re: [PATCH v2 03/16] iommu: introduce iommu invalidate API function

[Jean-Philippe Brucker <jean-philippe.brucker@arm.com>]

On 12/10/17 11:07, Bob Liu wrote:
> On 2017/10/12 17:50, Liu, Yi L wrote:
>>
>>
>>> -----Original Message-----
>>> From: Bob Liu [mailto:liubo95@huawei.com]
>>> Sent: Thursday, October 12, 2017 5:39 PM
>>> To: Jean-Philippe Brucker <jean-philippe.brucker@arm.com>; Joerg Roedel
>>> <joro@8bytes.org>; Liu, Yi L <yi.l.liu@intel.com>
>>> Cc: Lan, Tianyu <tianyu.lan@intel.com>; Liu, Yi L <yi.l.liu@linux.intel.com>; Greg
>>> Kroah-Hartman <gregkh@linuxfoundation.org>; Wysocki, Rafael J
>>> <rafael.j.wysocki@intel.com>; LKML <linux-kernel@vger.kernel.org>;
>>> iommu@lists.linux-foundation.org; David Woodhouse <dwmw2@infradead.org>
>>> Subject: Re: [PATCH v2 03/16] iommu: introduce iommu invalidate API function
>>>
>>> On 2017/10/11 20:48, Jean-Philippe Brucker wrote:
>>>> On 11/10/17 13:15, Joerg Roedel wrote:
>>>>> On Wed, Oct 11, 2017 at 11:54:52AM +0000, Liu, Yi L wrote:
>>>>>> I didn't quite get 'iovm' mean. Can you explain a bit about the idea?
>>>>>
>>>>> It's short for IO Virtual Memory, basically a replacement term for 'svm'
>>>>> that is not ambiguous (afaik) and not specific to Intel.
>>>>
>>>> I wonder if SVM originated in OpenCL first, rather than intel? That's
>>>> why I'm using it, but it is ambiguous. I'm not sure IOVM is precise
>>>> enough though, since the name could as well be used without shared
>>>> tables, for classical map/unmap and IOVAs. Kevin Tian suggested SVA
>>>> "Shared Virtual Addressing" last time, which is a little more clear
>>>> than SVM and isn't used elsewhere in the kernel either.
>>>>
>>>
>>> The process "vaddr" can be the same as "IOVA" by using the classical map/unmap
>>> way.
>>> This is also a kind of share virtual memory/address(except have to pin physical
>>> memory).
>>> How to distinguish these two different implementation of "share virtual
>>> memory/address"?
>>>
>> [Liu, Yi L] Not sure if I get your idea well. Process "vaddr" is owned by process and
>> maintained by mmu, while "IOVA" is maintained by iommu. So they are different in the
>> way they are maintained. Since process "vaddr" is maintained by mmu and then used by
>> iommu, so we call it shared virtual memory/address. This is how "shared" term comes.
> 
> I think from the view of application, the share virtual memory/address(or Nvidia-CUDA unify virtual address) is like this:
> 
> 1. vaddr = malloc(); e.g vaddr=0x10000
> 2. device can get the same data(accessing the same physical memory) through same address e.g 0x10000, and don't care about it's a vaddr or IOVA..
> (actually in Nvidia-cuda case, the data will be migrated between system-ddr and gpu-memory, but the vaddr is always the same for CPU and GPU).
> 
> So there are two ways(beside Nvidia way) to implement this requirement:
> 1)
> get the physical memory of vaddr;
> dma_map the paddr to iova;
> If we appoint iova = vaddr (e.g iova can be controlled by the user space driver through vfio DMA_MAP), 
> This can also be called share virtual address between CPU process and device..

This could probably be implemented by augmenting the iommu_map/unmap API
to take a PASID, as the mm subsystem isn't really involved and there isn't
any need for bind/unbind.

Maybe we should continue the conversation on the other thread though,
since this one is about sharing PASID tables with a guest.

Thanks,
Jean

> 2) 
> The second way is what this RFC did.