Re: [Qemu-devel] [PATCH 2/6] PCI DMA API

[Anthony Liguori <aliguori@us.ibm.com>]

Paul Brook wrote:
> On Saturday 29 March 2008, Anthony Liguori wrote:
>   
>> This patch introduces a PCI DMA API and some generic code to support other
>> DMA APIs.  Two types are introduced: PhysIOVector and IOVector.  A DMA API
>> maps a PhysIOVector, which is composed of target_phys_addr_t, into an
>> IOVector, which is composed of void *.
>>     
>
> Devices should not be using IOVector. They should either use the DMA copy 
> routines to copy from a PhysIOVector into a local buffer, or they should pass 
> a PhysIOVector to a block/network read/write routine. The DMA API should 
> allow devices to be agnostic about how DMA is implemented. They should not be 
> trying to manually implement zero copy.
>   

Someone has to do the translation of PhysIOVector => IOVector.  It 
doesn't seem logical to me to do it in the IO backend level because the 
block subsystem doesn't know how to do that translation.  You would have 
to pass the PhysIOVector although with a translation function and an 
opaque pointer.

What could work is if the DMA API functions mapped PhysIOVector => 
PhysIOVector and then the network and block subsystems could operate on 
a PhysIOVector.  I have patches that implement vector IO for net and 
block but didn't want to include them in this series to keep things simple.

>> This enables zero-copy IO to be preformed without introducing assumptions
>> of phys_ram_base.  This API is at the PCI device level to enable support of
>> per-device IOMMU remapping.
>>     
>
> By my reading it *requires* bridges be zero-copy.  For big-endian targets we 
> need to ability to byteswap accesses.
>   

You mean via ld/st_phys?  I can add a set of ld/st_vec functions (and 
even use them in hw/virtio.c).  I think operating on a translated vec is 
the right thing to do as it avoids the translation to be cached.  To 
make ld/st_phys just work, we would have to have some sort of global DMA 
context.  That gets tricky for drivers that use timer callbacks.

> Some description (in the form of source comments) of how it's meant to be used 
> would also be helpful.
>   

Will do for the next round.

Thanks,

Anthony Liguori

> Paul
>