Re: [RFC PATCH 0/2] iommu: Avoid unnecessary PRI queue flushes - Jean-Philippe Brucker

From: Jean-Philippe Brucker <jean-philippe@linaro.org>
To: Jacob Pan <jacob.jun.pan@linux.intel.com>
Cc: kevin.tian@intel.com, "Raj, Ashok" <ashok.raj@intel.com>,
	arnd@arndb.de, gregkh@linuxfoundation.org,
	iommu@lists.linux-foundation.org, linux-kernel@vger.kernel.org,
	"Lu, Baolu" <baolu.lu@intel.com>,
	Jacon Jun Pan <jacob.jun.pan@intel.com>,
	linux-pci@vger.kernel.org, zhangfei.gao@linaro.org,
	dwmw2@infradead.org, linux-accelerators@lists.ozlabs.org
Subject: Re: [RFC PATCH 0/2] iommu: Avoid unnecessary PRI queue flushes
Date: Fri, 23 Oct 2020 15:30:41 +0200	[thread overview]
Message-ID: <20201023133041.GE2265982@myrica> (raw)
In-Reply-To: <20201019113316.2957c5f0@jacob-builder>

On Mon, Oct 19, 2020 at 11:33:16AM -0700, Jacob Pan wrote:
> Hi Jean-Philippe,
> 
> On Mon, 19 Oct 2020 16:08:24 +0200, Jean-Philippe Brucker
> <jean-philippe@linaro.org> wrote:
> 
> > On Sat, Oct 17, 2020 at 04:25:25AM -0700, Raj, Ashok wrote:
> > > > For devices that *don't* use a stop marker, the PCIe spec says
> > > > (10.4.1.2):
> > > > 
> > > >   To stop [using a PASID] without using a Stop Marker Message, the
> > > >   function shall:
> > > >   1. Stop queueing new Page Request Messages for this PASID.  
> > > 
> > > The device driver would need to tell stop sending any new PR's.
> > >   
> > > >   2. Finish transmitting any multi-page Page Request Messages for this
> > > >      PASID (i.e. send the Page Request Message with the L bit Set).
> > > >   3. Wait for PRG Response Messages associated any outstanding Page
> > > >      Request Messages for the PASID.
> > > > 
> > > > So they have to flush their PR themselves. And since the device driver
> > > > completes this sequence before calling unbind(), then there shouldn't
> > > > be any oustanding PR for the PASID, and unbind() doesn't need to
> > > > flush, right?  
> > > 
> > > I can see how the device can complete #2,3 above. But the device driver
> > > isn't the one managing page-responses right. So in order for the device
> > > to know the above sequence is complete, it would need to get some
> > > assist from IOMMU driver?  
> > 
> > No the device driver just waits for the device to indicate that it has
> > completed the sequence. That's what the magic stop-PASID mechanism
> > described by PCIe does. In 6.20.1 "Managing PASID TLP Prefix Usage" it
> > says:
> > 
> > "A Function must have a mechanism to request that it gracefully stop using
> >  a specific PASID. This mechanism is device specific but must satisfy the
> >  following rules:
> >  [...]
> >  * When the stop request mechanism indicates completion, the Function has:
> >    [...]
> >    * Complied with additional rules described in Address Translation
> >      Services (Chapter 10 [10.4.1.2 quoted above]) if Address Translations
> >      or Page Requests were issued on the behalf of this PASID."
> > 
> > So after the device driver initiates this mechanism in the device, the
> > device must be able to indicate completion of the mechanism, which
> > includes completing all in-flight Page Requests. At that point the device
> > driver can call unbind() knowing there is no pending PR for this PASID.
> > 
> In step #3, I think it is possible that device driver received page response
> as part of the auto page response, so it may not guarantee all the in-flight
> PRQs are completed inside IOMMU. Therefore, drain is _always_ needed to be
> sure?

So I don't think that's a problem, because non-last PR are not handled by
IOPF until the last PR is received. And when the IOMMU driver detects that
the queue has been overflowing and could have auto-responded to last PR,
we discard any pending non-last PR. I couldn't find a leak here.

Thanks,
Jean

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu