[Intel-gfx] [PATCH v5 0/7] Command parser batch buffer copy

Michael H. Nguyen michael.h.nguyen at intel.com
Mon Dec 1 14:39:51 PST 2014



On 11/26/2014 11:44 PM, Chris Wilson wrote:
> On Wed, Nov 26, 2014 at 01:53:34PM -0800, michael.h.nguyen at intel.com wrote:
>> From: "Michael H. Nguyen" <michael.h.nguyen at intel.com>
>>
>> This is v5 of the series sent here:
>> http://lists.freedesktop.org/archives/intel-gfx/2014-November/055141.html
>>
>> This version incorporates the following feedback from v4.
>>
>> - 0/7 Move 'pending_read_domains |= I915_GEM_DOMAIN_COMMAND' after the
>>    parser (danvet)
>> - 1/7 Move purged check inside the loop (danvet)
>> - 6/7 Move 'shadow_batch_obj->madv = I915_MADV_WILLNEED' inside _get
>>    fnc (danvet)
>> - 7/7 Move pin/unpin calls inside i915_parse_cmds() (Chris W)
>>
>> Issue: VIZ-4719
>> Brad Volkin (7):
>>    drm/i915: Implement a framework for batch buffer pools
>>    drm/i915: Use batch pools with the command parser
>>    drm/i915: Add a batch pool debugfs file
>>    drm/i915: Add batch pool details to i915_gem_objects debugfs
>>    drm/i915: Use batch length instead of object size in command parser
>>    drm/i915: Mark shadow batch buffers as purgeable
>>    drm/i915: Tidy up execbuffer command parsing code
>
> This still does not incorporate the feedback from the last N cycles.
>
> Chiefly: A single cache list, madvise on creation, and squash the
> framework and debugging patches into one.

Re: single cache list

OK. Found the feedback in an old rev.

Re: madvise on creation

Were you referring to this?

from 
http://lists.freedesktop.org/archives/intel-gfx/2014-November/055060.htm

	obj = i915_gem_obj_alloc();
	i915_gem_object_get_pages(obj);
	obj->madv = I915_MADV_DONTNEED;

If so, I don't understand . _get is returning obj and it'll be needed so 
would expect to set 'obj->madv = I915_MADV_WILLNEED' which is the case now.

For this feedback, would appreciate it if you could provide comments or 
proposed solutions in line w/ source. That would be helpful for me to 
get whatever context I'm missing.

Re: Squash

OK. I didn't see this feedback. Will do.

Thanks,
-Mike

> -Chris
>



More information about the Intel-gfx mailing list