From: "Koenig, Christian" <Christian.Koenig@amd.com>
To: Thomas Hellstrom <thomas@shipmail.org>,
"Kuehling, Felix" <Felix.Kuehling@amd.com>,
"dri-devel@lists.freedesktop.org"
<dri-devel@lists.freedesktop.org>,
"amd-gfx@lists.freedesktop.org" <amd-gfx@lists.freedesktop.org>
Cc: "thellstrom@vmware.com" <thellstrom@vmware.com>
Subject: Re: [PATCH 1/1] [RFC] drm/ttm: Don't init dma32_zone on 64-bit systems
Date: Mon, 18 Feb 2019 09:20:11 +0000 [thread overview]
Message-ID: <254ca765-adc2-5ddf-280f-6cb3643f6e1f@amd.com> (raw)
In-Reply-To: <8538a294-eeab-9c87-ae10-83695149f808@shipmail.org>
Another good question is also why the heck the acc_size counts towards
the DMA32 zone?
In other words why should the internal bookkeeping pages be allocated in
the DMA32 zone?
That doesn't sounds valid to me in any way,
Christian.
Am 18.02.19 um 09:02 schrieb Thomas Hellstrom:
> Hmm,
>
> This zone was intended to stop TTM page allocations from exhausting
> the DMA32 zone. IIRC dma_alloc_coherent() uses DMA32 by default, which
> means if we drop this check, other devices may stop functioning
> unexpectedly?
>
> However, in the end I'd expect the kernel page allocation system to
> make sure there are some pages left in the DMA32 zone, otherwise
> random non-IO page allocations would also potentially exhaust the
> DMA32 zone without anybody caring, which means removing this zone
> wouldn't be any worse than whatever other subsystems may be doing
> already...
>
> /Thomas
>
>
> On 2/16/19 12:02 AM, Kuehling, Felix wrote:
>> This is an RFC. I'm not sure this is the right solution, but it
>> highlights the problem I'm trying to solve.
>>
>> The dma32_zone limits the acc_size of all allocated BOs to 2GB. On a
>> 64-bit system with hundreds of GB of system memory and GPU memory,
>> this can become a bottle neck. We're seeing TTM memory allocation
>> failures not because we're truly out of memory, but because we're
>> out of space in the dma32_zone for the acc_size needed for our BO
>> book-keeping.
>>
>> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
>> CC: thellstrom@vmware.com
>> CC: christian.koenig@amd.com
>> ---
>> drivers/gpu/drm/ttm/ttm_memory.c | 4 ++--
>> 1 file changed, 2 insertions(+), 2 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/ttm/ttm_memory.c
>> b/drivers/gpu/drm/ttm/ttm_memory.c
>> index f1567c3..bb05365 100644
>> --- a/drivers/gpu/drm/ttm/ttm_memory.c
>> +++ b/drivers/gpu/drm/ttm/ttm_memory.c
>> @@ -363,7 +363,7 @@ static int ttm_mem_init_highmem_zone(struct
>> ttm_mem_global *glob,
>> glob->zones[glob->num_zones++] = zone;
>> return 0;
>> }
>> -#else
>> +#elifndef CONFIG_64BIT
>> static int ttm_mem_init_dma32_zone(struct ttm_mem_global *glob,
>> const struct sysinfo *si)
>> {
>> @@ -441,7 +441,7 @@ int ttm_mem_global_init(struct ttm_mem_global *glob)
>> ret = ttm_mem_init_highmem_zone(glob, &si);
>> if (unlikely(ret != 0))
>> goto out_no_zone;
>> -#else
>> +#elifndef CONFIG_64BIT
>> ret = ttm_mem_init_dma32_zone(glob, &si);
>> if (unlikely(ret != 0))
>> goto out_no_zone;
>
>
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel
next prev parent reply other threads:[~2019-02-18 9:20 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-02-15 23:02 [PATCH 1/1] [RFC] drm/ttm: Don't init dma32_zone on 64-bit systems Kuehling, Felix
2019-02-18 8:02 ` Thomas Hellstrom
2019-02-18 9:20 ` Koenig, Christian [this message]
2019-02-18 9:47 ` Thomas Hellstrom
[not found] ` <d90f7ab569b636db0968c80dad9eb16ce7bf1eab.camel-pghWNbHTmq7QT0dZR+AlfA@public.gmane.org>
2019-02-18 17:07 ` Christian König
[not found] ` <89c4b66a-152a-d0f3-4ce0-d89f6ef822bb-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2019-02-18 20:39 ` Thomas Hellstrom
[not found] ` <eaad8f2dc24e98c68036801ccd6a871586033d31.camel-pghWNbHTmq7QT0dZR+AlfA@public.gmane.org>
2019-02-19 17:06 ` Kuehling, Felix
[not found] ` <2be5739a-fe9a-f436-48a2-fb420cb97a13-5C7GfCeVMHo@public.gmane.org>
2019-02-20 6:41 ` Thomas Hellstrom
[not found] ` <19a0abdbd60c251a63975a7ddff31c35a5eb0a31.camel-pghWNbHTmq7QT0dZR+AlfA@public.gmane.org>
2019-02-20 8:07 ` Christian König
2019-02-20 8:14 ` Thomas Hellstrom
[not found] ` <307f2073-7c15-8dac-58fe-3c0170231530-4+hqylr40dJg9hUCZPvPmw@public.gmane.org>
2019-02-20 8:35 ` Koenig, Christian
[not found] ` <66b1fa8a-6449-6fe2-18a0-c7aa2200ac68-5C7GfCeVMHo@public.gmane.org>
2019-02-20 9:01 ` Thomas Hellstrom
2019-02-20 19:23 ` Kuehling, Felix
2019-02-21 6:47 ` Thomas Hellstrom
2019-02-21 7:59 ` Koenig, Christian
[not found] ` <4423e7aa-2153-5305-91c2-8d212ae1786b-5C7GfCeVMHo@public.gmane.org>
2019-02-21 16:57 ` Kuehling, Felix
[not found] ` <2a76cb48-10f1-6df2-5b40-8d5b4c52acc4-5C7GfCeVMHo@public.gmane.org>
2019-02-21 17:34 ` Thomas Hellstrom
[not found] ` <39a4a5534ea3d5fa9ba94714e80f919c5a43aea9.camel-pghWNbHTmq7QT0dZR+AlfA@public.gmane.org>
2019-02-21 20:24 ` Kuehling, Felix
[not found] ` <2b4ea7ed-08e6-6dd3-7b56-e7c1713fc357-5C7GfCeVMHo@public.gmane.org>
2019-02-21 21:02 ` Thomas Hellstrom
[not found] ` <0f1a3b818a4f6b426dff5c641332a456b08136f8.camel-pghWNbHTmq7QT0dZR+AlfA@public.gmane.org>
2019-02-22 7:10 ` Koenig, Christian
2019-02-22 13:45 ` Thomas Hellstrom
[not found] ` <0c5e5ad70e2acbf2efd9fd0878768dcd5e008cd3.camel-pghWNbHTmq7QT0dZR+AlfA@public.gmane.org>
2019-02-22 23:06 ` Kuehling, Felix
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=254ca765-adc2-5ddf-280f-6cb3643f6e1f@amd.com \
--to=christian.koenig@amd.com \
--cc=Felix.Kuehling@amd.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=dri-devel@lists.freedesktop.org \
--cc=thellstrom@vmware.com \
--cc=thomas@shipmail.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox