Re: drm/radeon spamming alloc_contig_range: [xxx, yyy) PFNs busy busy

From	Michal Nazarewicz <mina86@mina86.com>
Newsgroups	linux.kernel
Subject	Re: drm/radeon spamming alloc_contig_range: [xxx, yyy) PFNs busy busy
Date	2016-12-01 17:10 +0100
Message-ID	<sJC5P-6gw-21@gated-at.bofh.it> (permalink)
References	(5 earlier) <sJjwe-2hE-9@gated-at.bofh.it> <sJtOV-G5-5@gated-at.bofh.it> <sJtYC-Ja-9@gated-at.bofh.it> <sJuhX-PI-23@gated-at.bofh.it> <sJAno-4Xx-17@gated-at.bofh.it>
Organization	http://mina86.com/

Show all headers | View raw

On Thu, Dec 01 2016, Michal Hocko wrote:
> Let's also CC Marek
>
> On Thu 01-12-16 08:43:40, Vlastimil Babka wrote:
>> On 12/01/2016 08:21 AM, Michal Hocko wrote:
>> > Forgot to CC Joonsoo. The email thread starts more or less here
>> > http://lkml.kernel.org/r/20161130092239.GD18437@dhcp22.suse.cz
>> > 
>> > On Thu 01-12-16 08:15:07, Michal Hocko wrote:
>> > > On Wed 30-11-16 20:19:03, Robin H. Johnson wrote:
>> > > [...]
>> > > > alloc_contig_range: [83f2a3, 83f2a4) PFNs busy
>> > > 
>> > > Huh, do I get it right that the request was for a _single_ page? Why do
>> > > we need CMA for that?
>> 
>> Ugh, good point. I assumed that was just the PFNs that it failed to migrate
>> away, but it seems that's indeed the whole requested range. Yeah sounds some
>> part of the dma-cma chain could be smarter and attempt CMA only for e.g.
>> costly orders.
>
> Is there any reason why the DMA api doesn't try the page allocator first
> before falling back to the CMA? I simply have a hard time to see why the
> CMA should be used (and fragment) for small requests size.

There actually may be reasons to always go with CMA even if small
regions are requested.  CMA areas may be defined to map to particular
physical addresses and given device may require allocations from those
addresses.  This may be more than just a matter of DMA address space.
I cannot give you specific examples though and I might be talking
nonsense.

> -- 
> Michal Hocko
> SUSE Labs

-- 
Best regards
ミハウ “𝓶𝓲𝓷𝓪86” ナザレヴイツ
«If at first you don’t succeed, give up skydiving»

Thread

PROBLEM-PERSISTS: dmesg spam: alloc_contig_range: [XX, YY) PFNs busy "Robin H. Johnson" <robbat2@orbis-terrarum.net> - 2016-11-29 23:50 +0100
  Re: PROBLEM-PERSISTS: dmesg spam: alloc_contig_range: [XX, YY) PFNs  busy Michal Hocko <mhocko@kernel.org> - 2016-11-30 10:30 +0100
    Re: PROBLEM-PERSISTS: dmesg spam: alloc_contig_range: [XX, YY) PFNs busy Michal Nazarewicz <mina86@mina86.com> - 2016-11-30 14:10 +0100
      Re: PROBLEM-PERSISTS: dmesg spam: alloc_contig_range: [XX, YY) PFNs  busy Michal Hocko <mhocko@kernel.org> - 2016-11-30 14:30 +0100
        Re: PROBLEM-PERSISTS: dmesg spam: alloc_contig_range: [XX, YY) PFNs  busy "Robin H. Johnson" <robbat2@gentoo.org> - 2016-11-30 21:00 +0100
          drm/radeon spamming alloc_contig_range: [xxx, yyy) PFNs busy busy "Robin H. Johnson" <robbat2@gentoo.org> - 2016-11-30 21:20 +0100
            Re: drm/radeon spamming alloc_contig_range: [xxx, yyy) PFNs busy busy Vlastimil Babka <vbabka@suse.cz> - 2016-11-30 22:30 +0100
              Re: drm/radeon spamming alloc_contig_range: [xxx, yyy) PFNs busy busy "Robin H. Johnson" <robbat2@gentoo.org> - 2016-12-01 07:30 +0100
                Re: drm/radeon spamming alloc_contig_range: [xxx, yyy) PFNs busy busy Vlastimil Babka <vbabka@suse.cz> - 2016-12-01 08:40 +0100
                Re: drm/radeon spamming alloc_contig_range: [xxx, yyy) PFNs busy busy "Robin H. Johnson" <robbat2@gentoo.org> - 2016-12-01 09:00 +0100
            Re: drm/radeon spamming alloc_contig_range: [xxx, yyy) PFNs busy busy Michal Hocko <mhocko@kernel.org> - 2016-12-01 08:20 +0100
              Re: drm/radeon spamming alloc_contig_range: [xxx, yyy) PFNs busy busy Michal Hocko <mhocko@kernel.org> - 2016-12-01 08:30 +0100
                Re: drm/radeon spamming alloc_contig_range: [xxx, yyy) PFNs busy busy Vlastimil Babka <vbabka@suse.cz> - 2016-12-01 08:50 +0100
                Re: drm/radeon spamming alloc_contig_range: [xxx, yyy) PFNs busy busy Michal Hocko <mhocko@kernel.org> - 2016-12-01 15:20 +0100
                Re: drm/radeon spamming alloc_contig_range: [xxx, yyy) PFNs busy busy Michal Nazarewicz <mina86@mina86.com> - 2016-12-01 17:10 +0100
                Re: drm/radeon spamming alloc_contig_range: [xxx, yyy) PFNs busy busy Michal Hocko <mhocko@kernel.org> - 2016-12-01 17:20 +0100
                Re: drm/radeon spamming alloc_contig_range: [xxx, yyy) PFNs busy busy Michal Nazarewicz <mina86@mina86.com> - 2016-12-01 22:10 +0100
                Re: drm/radeon spamming alloc_contig_range: [xxx, yyy) PFNs busy busy Vlastimil Babka <vbabka@suse.cz> - 2016-12-02 07:40 +0100
                Re: drm/radeon spamming alloc_contig_range: [xxx, yyy) PFNs busy  busy Lucas Stach <l.stach@pengutronix.de> - 2016-12-02 11:30 +0100
                Re: drm/radeon spamming alloc_contig_range: [xxx, yyy) PFNs busy busy Jerome Glisse <j.glisse@gmail.com> - 2016-12-02 16:20 +0100
          Re: PROBLEM-PERSISTS: dmesg spam: alloc_contig_range: [XX, YY) PFNs busy Michal Nazarewicz <mina86@mina86.com> - 2016-12-01 02:40 +0100

csiph-web