Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1476249 > unrolled thread

Re: io_page_fault seen in normal kernel boot log

Started byJoerg Roedel <joro@8bytes.org>
First post2016-09-05 12:00 +0200
Last post2016-09-09 10:50 +0200
Articles 6 — 2 participants

Back to article view | Back to linux.kernel

This discussion starts older than the indexed window; earlier articles aren't shown. The article labeled Started by below is the oldest one visible, not the original post.


Contents

  Re: io_page_fault seen in normal kernel boot log Joerg Roedel <joro@8bytes.org> - 2016-09-05 12:00 +0200
    Re: io_page_fault seen in normal kernel boot log Baoquan He <bhe@redhat.com> - 2016-09-05 12:20 +0200
      Re: io_page_fault seen in normal kernel boot log Joerg Roedel <joro@8bytes.org> - 2016-09-06 11:20 +0200
        Re: io_page_fault seen in normal kernel boot log Baoquan He <bhe@redhat.com> - 2016-09-09 10:10 +0200
          Re: io_page_fault seen in normal kernel boot log Joerg Roedel <joro@8bytes.org> - 2016-09-09 10:40 +0200
            Re: io_page_fault seen in normal kernel boot log Baoquan He <bhe@redhat.com> - 2016-09-09 10:50 +0200

#1476249 — Re: io_page_fault seen in normal kernel boot log

FromJoerg Roedel <joro@8bytes.org>
Date2016-09-05 12:00 +0200
SubjectRe: io_page_fault seen in normal kernel boot log
Message-ID<sdYR6-209-59@gated-at.bofh.it>
Hi Baoquan

On Mon, Sep 05, 2016 at 01:38:05PM +0800, Baoquan He wrote:
> This happened on 4.8.0-rc5
> 
> [  +0.006771] AMD-Vi: Event logged [IO_PAGE_FAULT device=00:14.4 domain=0x0009 address=0x0000000000001000 flags=0x0000]
> [  +0.010593] AMD-Vi: Event logged [IO_PAGE_FAULT device=00:14.4 domain=0x0009 address=0x0000000000001040 flags=0x0000]
> [  +0.010596] AMD-Vi: Event logged [IO_PAGE_FAULT device=00:14.4 domain=0x0009 address=0x0000000000001080 flags=0x0000]
> [  +0.010597] AMD-Vi: Event logged [IO_PAGE_FAULT device=00:14.4 domain=0x0009 address=0x00000000000010c0 flags=0x0000]
> [  +0.010592] AMD-Vi: Event logged [IO_PAGE_FAULT device=00:14.4 domain=0x0009 address=0x0000000000001100 flags=0x0000]
> [  +0.010592] AMD-Vi: Event logged [IO_PAGE_FAULT device=00:14.4 domain=0x0009 address=0x0000000000001140 flags=0x0000]

This is probably a radeon driver issue, the address looks like its
handed out by the IOMMU driver, so probably a use-after-free bug. I also
see those GPU related faults from time to time. The system usually boots
fine anyway. Does boot complete on that system?


Regards,

	Joerg

[toc] | [next] | [standalone]


#1476276

FromBaoquan He <bhe@redhat.com>
Date2016-09-05 12:20 +0200
Message-ID<sdZap-2o0-5@gated-at.bofh.it>
In reply to#1476249
On 09/05/16 at 11:59am, Joerg Roedel wrote:
> Hi Baoquan
> 
> On Mon, Sep 05, 2016 at 01:38:05PM +0800, Baoquan He wrote:
> > This happened on 4.8.0-rc5
> > 
> > [  +0.006771] AMD-Vi: Event logged [IO_PAGE_FAULT device=00:14.4 domain=0x0009 address=0x0000000000001000 flags=0x0000]
> > [  +0.010593] AMD-Vi: Event logged [IO_PAGE_FAULT device=00:14.4 domain=0x0009 address=0x0000000000001040 flags=0x0000]
> > [  +0.010596] AMD-Vi: Event logged [IO_PAGE_FAULT device=00:14.4 domain=0x0009 address=0x0000000000001080 flags=0x0000]
> > [  +0.010597] AMD-Vi: Event logged [IO_PAGE_FAULT device=00:14.4 domain=0x0009 address=0x00000000000010c0 flags=0x0000]
> > [  +0.010592] AMD-Vi: Event logged [IO_PAGE_FAULT device=00:14.4 domain=0x0009 address=0x0000000000001100 flags=0x0000]
> > [  +0.010592] AMD-Vi: Event logged [IO_PAGE_FAULT device=00:14.4 domain=0x0009 address=0x0000000000001140 flags=0x0000]
> 
> This is probably a radeon driver issue, the address looks like its
> handed out by the IOMMU driver, so probably a use-after-free bug. I also
> see those GPU related faults from time to time. The system usually boots
> fine anyway. Does boot complete on that system?

Yes, except for this message, system is not impacted.

> 
> 
> Regards,
> 
> 	Joerg
> 

[toc] | [prev] | [next] | [standalone]


#1477202

FromJoerg Roedel <joro@8bytes.org>
Date2016-09-06 11:20 +0200
Message-ID<sekHT-8tW-17@gated-at.bofh.it>
In reply to#1476276
On Mon, Sep 05, 2016 at 06:11:58PM +0800, Baoquan He wrote:
> On 09/05/16 at 11:59am, Joerg Roedel wrote:
> > > This happened on 4.8.0-rc5
> > > 
> > > [  +0.006771] AMD-Vi: Event logged [IO_PAGE_FAULT device=00:14.4 domain=0x0009 address=0x0000000000001000 flags=0x0000]
> > > [  +0.010593] AMD-Vi: Event logged [IO_PAGE_FAULT device=00:14.4 domain=0x0009 address=0x0000000000001040 flags=0x0000]
> > > [  +0.010596] AMD-Vi: Event logged [IO_PAGE_FAULT device=00:14.4 domain=0x0009 address=0x0000000000001080 flags=0x0000]
> > > [  +0.010597] AMD-Vi: Event logged [IO_PAGE_FAULT device=00:14.4 domain=0x0009 address=0x00000000000010c0 flags=0x0000]
> > > [  +0.010592] AMD-Vi: Event logged [IO_PAGE_FAULT device=00:14.4 domain=0x0009 address=0x0000000000001100 flags=0x0000]
> > > [  +0.010592] AMD-Vi: Event logged [IO_PAGE_FAULT device=00:14.4 domain=0x0009 address=0x0000000000001140 flags=0x0000]
> > 
> > This is probably a radeon driver issue, the address looks like its
> > handed out by the IOMMU driver, so probably a use-after-free bug. I also
> > see those GPU related faults from time to time. The system usually boots
> > fine anyway. Does boot complete on that system?
> 
> Yes, except for this message, system is not impacted.

Hmm, on the other hand, the AMD-Vi driver in 4.8 uses the generic IOVA
allocator, so the addresses it hands out should be closer to 4GB.
Anyway, this is probably a bug/problem in the GPU driver.



	Joerg

[toc] | [prev] | [next] | [standalone]


#1479721

FromBaoquan He <bhe@redhat.com>
Date2016-09-09 10:10 +0200
Message-ID<sfp2N-ne-5@gated-at.bofh.it>
In reply to#1477202
On 09/06/16 at 11:13am, Joerg Roedel wrote:
> On Mon, Sep 05, 2016 at 06:11:58PM +0800, Baoquan He wrote:
> > On 09/05/16 at 11:59am, Joerg Roedel wrote:
> > > > This happened on 4.8.0-rc5
> > > > 
> > > > [  +0.006771] AMD-Vi: Event logged [IO_PAGE_FAULT device=00:14.4 domain=0x0009 address=0x0000000000001000 flags=0x0000]
> > > > [  +0.010593] AMD-Vi: Event logged [IO_PAGE_FAULT device=00:14.4 domain=0x0009 address=0x0000000000001040 flags=0x0000]
> > > > [  +0.010596] AMD-Vi: Event logged [IO_PAGE_FAULT device=00:14.4 domain=0x0009 address=0x0000000000001080 flags=0x0000]
> > > > [  +0.010597] AMD-Vi: Event logged [IO_PAGE_FAULT device=00:14.4 domain=0x0009 address=0x00000000000010c0 flags=0x0000]
> > > > [  +0.010592] AMD-Vi: Event logged [IO_PAGE_FAULT device=00:14.4 domain=0x0009 address=0x0000000000001100 flags=0x0000]
> > > > [  +0.010592] AMD-Vi: Event logged [IO_PAGE_FAULT device=00:14.4 domain=0x0009 address=0x0000000000001140 flags=0x0000]
> > > 
> > > This is probably a radeon driver issue, the address looks like its
> > > handed out by the IOMMU driver, so probably a use-after-free bug. I also
> > > see those GPU related faults from time to time. The system usually boots
> > > fine anyway. Does boot complete on that system?
> > 
> > Yes, except for this message, system is not impacted.
> 
> Hmm, on the other hand, the AMD-Vi driver in 4.8 uses the generic IOVA
> allocator, so the addresses it hands out should be closer to 4GB.
> Anyway, this is probably a bug/problem in the GPU driver.

Thanks for telling. So should I raise this issue to radeon driver
mailist list? They probably they have some clues.

Thanks
Baoquan

[toc] | [prev] | [next] | [standalone]


#1479742

FromJoerg Roedel <joro@8bytes.org>
Date2016-09-09 10:40 +0200
Message-ID<sfpvQ-wL-13@gated-at.bofh.it>
In reply to#1479721
On Fri, Sep 09, 2016 at 04:05:50PM +0800, Baoquan He wrote:
> On 09/06/16 at 11:13am, Joerg Roedel wrote:
> > Hmm, on the other hand, the AMD-Vi driver in 4.8 uses the generic IOVA
> > allocator, so the addresses it hands out should be closer to 4GB.
> > Anyway, this is probably a bug/problem in the GPU driver.
> 
> Thanks for telling. So should I raise this issue to radeon driver
> mailist list? They probably they have some clues.

I tried that before and seldom got a response, but maybe you have more
luck :)


	Joerg

[toc] | [prev] | [next] | [standalone]


#1479757

FromBaoquan He <bhe@redhat.com>
Date2016-09-09 10:50 +0200
Message-ID<sfpFv-zV-13@gated-at.bofh.it>
In reply to#1479742
On 09/09/16 at 10:30am, Joerg Roedel wrote:
> On Fri, Sep 09, 2016 at 04:05:50PM +0800, Baoquan He wrote:
> > On 09/06/16 at 11:13am, Joerg Roedel wrote:
> > > Hmm, on the other hand, the AMD-Vi driver in 4.8 uses the generic IOVA
> > > allocator, so the addresses it hands out should be closer to 4GB.
> > > Anyway, this is probably a bug/problem in the GPU driver.
> > 
> > Thanks for telling. So should I raise this issue to radeon driver
> > mailist list? They probably they have some clues.
> 
> I tried that before and seldom got a response, but maybe you have more
> luck :)

OK, got it. I will resend it to their mailing list. Thanks.

[toc] | [prev] | [standalone]


Back to top | Article view | linux.kernel


csiph-web