From: Matthew Auld <matthew.william.auld@gmail.com>
To: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Intel Graphics Development <intel-gfx@lists.freedesktop.org>
Subject: Re: [Intel-gfx] [PATCH 14/22] drm/i915/gem: Async GPU relocations only
Date: Thu, 4 Jun 2020 14:37:40 +0100 [thread overview]
Message-ID: <CAM0jSHM=qwi9h20Lu9JCz8KXPNJHo7ToUv63t9eADM-U9MZm9A@mail.gmail.com> (raw)
In-Reply-To: <20200604103751.18816-14-chris@chris-wilson.co.uk>
On Thu, 4 Jun 2020 at 11:38, Chris Wilson <chris@chris-wilson.co.uk> wrote:
>
> Reduce the 3 relocation patches down to the single path that accommodates
> all. The primary motivation for this is to guard the relocations with a
> natural fence (derived from the i915_request used to write the
> relocation from the GPU).
>
> The tradeoff in using async gpu relocations is that it increases latency
> over using direct CPU relocations, for the cases where the target is
> idle and accessible by the CPU. The benefit is greatly reduced lock
> contention and improved concurrency by pipelining.
>
> Note that forcing the async gpu relocations does reveal a few issues
> they have. Firstly, is that they are visible as writes to gem_busy,
> causing to mark some buffers are being to written to by the GPU even
> though userspace only reads. Secondly is that, in combination with the
> cmdparser, they can cause priority inversions. This should be the case
> where the work is being put into a common workqueue losing our priority
> information and so being executed in FIFO from the worker, denying us
> the opportunity to reorder the requests afterwards.
>
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
next prev parent reply other threads:[~2020-06-04 13:38 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-06-04 10:37 [Intel-gfx] [PATCH 01/22] drm/i915/gem: Mark the buffer pool as active for the cmdparser Chris Wilson
2020-06-04 10:37 ` [Intel-gfx] [PATCH 02/22] drm/i915: Trim set_timer_ms() intervals Chris Wilson
2020-06-04 12:54 ` Matthew Auld
2020-06-04 10:37 ` [Intel-gfx] [PATCH 03/22] drm/i915/gt: Set timeslicing priority from queue Chris Wilson
2020-06-04 10:37 ` [Intel-gfx] [PATCH 04/22] drm/i915/gt: Always check to enable timeslicing if not submitting Chris Wilson
2020-06-04 10:37 ` [Intel-gfx] [PATCH 05/22] Restore "drm/i915: drop engine_pin/unpin_breadcrumbs_irq" Chris Wilson
2020-06-04 10:37 ` [Intel-gfx] [PATCH 06/22] drm/i915/gt: Couple tasklet scheduling for all CS interrupts Chris Wilson
2020-06-04 10:37 ` [Intel-gfx] [PATCH 07/22] drm/i915/gt: Support creation of 'internal' rings Chris Wilson
2020-06-04 10:37 ` [Intel-gfx] [PATCH 08/22] drm/i915/gt: Use client timeline address for seqno writes Chris Wilson
2020-06-04 10:37 ` [Intel-gfx] [PATCH 09/22] drm/i915/gt: Infrastructure for ring scheduling Chris Wilson
2020-06-04 10:37 ` [Intel-gfx] [PATCH 10/22] drm/i915/gt: Enable busy-stats for ring-scheduler Chris Wilson
2020-06-04 10:37 ` [Intel-gfx] [PATCH 11/22] drm/i915/gt: Track if an engine requires forcewake w/a Chris Wilson
2020-06-04 10:37 ` [Intel-gfx] [PATCH 12/22] drm/i915/gt: Implement ring scheduler for gen6/7 Chris Wilson
2020-06-04 10:37 ` [Intel-gfx] [PATCH 13/22] drm/i915/gt: Enable ring scheduling " Chris Wilson
2020-06-04 10:37 ` [Intel-gfx] [PATCH 14/22] drm/i915/gem: Async GPU relocations only Chris Wilson
2020-06-04 13:37 ` Matthew Auld [this message]
2020-06-04 13:44 ` Chris Wilson
2020-06-04 10:37 ` [Intel-gfx] [PATCH 15/22] drm/i915: Add list_for_each_entry_safe_continue_reverse Chris Wilson
2020-06-04 10:37 ` [Intel-gfx] [PATCH 16/22] drm/i915/gem: Separate reloc validation into an earlier step Chris Wilson
2020-06-04 10:37 ` [Intel-gfx] [PATCH 17/22] drm/i915/gem: Lift GPU relocation allocation Chris Wilson
2020-06-04 10:37 ` [Intel-gfx] [PATCH 18/22] drm/i915/gem: Build the reloc request first Chris Wilson
2020-06-04 10:37 ` [Intel-gfx] [PATCH 19/22] drm/i915/gem: Add all GPU reloc awaits/signals en masse Chris Wilson
2020-06-04 10:37 ` [Intel-gfx] [PATCH 20/22] dma-buf: Proxy fence, an unsignaled fence placeholder Chris Wilson
2020-06-04 10:37 ` [Intel-gfx] [PATCH 21/22] drm/i915: Unpeel awaits on a proxy fence Chris Wilson
2020-06-04 10:37 ` [Intel-gfx] [PATCH 22/22] drm/i915/gem: Make relocations atomic within execbuf Chris Wilson
2020-06-04 11:36 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for series starting with [01/22] drm/i915/gem: Mark the buffer pool as active for the cmdparser Patchwork
2020-06-04 11:37 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2020-06-04 12:06 ` [Intel-gfx] ✗ Fi.CI.BAT: failure " Patchwork
2020-06-04 12:49 ` [Intel-gfx] [PATCH 01/22] " Matthew Auld
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='CAM0jSHM=qwi9h20Lu9JCz8KXPNJHo7ToUv63t9eADM-U9MZm9A@mail.gmail.com' \
--to=matthew.william.auld@gmail.com \
--cc=chris@chris-wilson.co.uk \
--cc=intel-gfx@lists.freedesktop.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.