From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
To: Chris Wilson <chris@chris-wilson.co.uk>
Cc: intel-gfx@lists.freedesktop.org, Mika Kuoppala <mika.kuoppala@intel.com>
Subject: Re: [PATCH 10/19] drm/i915: Rearrange switch_context to load the aliasing ppgtt on first use
Date: Thu, 21 Apr 2016 10:32:59 +0300 [thread overview]
Message-ID: <1461223979.4381.21.camel@linux.intel.com> (raw)
In-Reply-To: <20160421070137.GD15733@nuc-i3427.alporthouse.com>
On to, 2016-04-21 at 08:01 +0100, Chris Wilson wrote:
> On Thu, Apr 21, 2016 at 09:48:36AM +0300, Joonas Lahtinen wrote:
> >
> > On ke, 2016-04-20 at 19:42 +0100, Chris Wilson wrote:
> > >
> > > The code to switch_mm() is already handled by i915_switch_context(), the
> > > only difference required to setup the aliasing ppgtt is that we need to
> > > emit te switch_mm() on the first context, i.e. when transitioning from
> > > engine->last_context == NULL. This allows us to defer the
> > > initialisation of the GPU from early device initialisation to first use,
> > > which should marginally speed up both. The caveat is that we then defer
> > > the context initialisation until first use - i.e. we cannot assume that
> > > the GPU engines are initialised. For example, this means that power
> > > contexts for rc6 (Ironlake) need to explicitly loaded, as they are.
> > >
> > > Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> > > Cc: Mika Kuoppala <mika.kuoppala@intel.com>
> > Some comments below.
> >
> > Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
> >
> > >
> > > diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> > > index aafcb4942acf..14c9b29294c5 100644
> > > --- a/drivers/gpu/drm/i915/i915_gem.c
> > > +++ b/drivers/gpu/drm/i915/i915_gem.c
> > > @@ -4910,34 +4910,6 @@ i915_gem_init_hw(struct drm_device *dev)
> > > if (ret)
> > > goto out;
> > This whole if (ret) goto out can be removed as out is right after the
> > removed code block.
> Oh, this piece of code is earmarked to be removed and now I even have a
> bugzilla for it!
>
Huh? I was commeting that you just literally removed everything between
"goto out;" and "out:" with this commit. So you can just drop the whole
if (ret) goto out;
> https://bugs.freedesktop.org/show_bug.cgi?id=95023
> is an example where we are doing the wrong thing with the current
> i915_gem_init_seqno.
> -Chris
>
--
Joonas Lahtinen
Open Source Technology Center
Intel Corporation
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
next prev parent reply other threads:[~2016-04-21 7:31 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-04-20 18:42 Premature unpinning at last Chris Wilson
2016-04-20 18:42 ` [PATCH 01/19] drm/i915/overlay: Replace i915_gem_obj_ggtt_offset() with the known flip_addr Chris Wilson
2016-04-20 18:42 ` [PATCH 02/19] io-mapping: Specify mapping size for io_mapping_map_wc() Chris Wilson
2016-04-20 18:58 ` Luis R. Rodriguez
2016-04-20 19:14 ` Chris Wilson
2016-04-20 21:23 ` Luis R. Rodriguez
2016-04-20 18:42 ` [PATCH 03/19] drm/i915: Introduce i915_vm_to_ggtt() Chris Wilson
2016-04-20 18:42 ` [PATCH 04/19] drm/i915: Move ioremap_wc tracking onto VMA Chris Wilson
2016-04-20 18:42 ` [PATCH 05/19] drm/i915: Use i915_vma_pin_iomap on the ringbuffer object Chris Wilson
2016-04-21 7:19 ` Joonas Lahtinen
2016-04-20 18:42 ` [PATCH 06/19] drm/i915: Mark the current context as lost on suspend Chris Wilson
2016-04-20 18:42 ` [PATCH 07/19] drm/i915: L3 cache remapping is part of context switching Chris Wilson
2016-04-20 18:42 ` [PATCH 08/19] drm/i915: Consolidate L3 remapping LRI Chris Wilson
2016-04-20 18:42 ` [PATCH 09/19] drm/i915: Remove early l3-remap Chris Wilson
2016-04-20 18:42 ` [PATCH 10/19] drm/i915: Rearrange switch_context to load the aliasing ppgtt on first use Chris Wilson
2016-04-21 6:48 ` Joonas Lahtinen
2016-04-21 6:58 ` Chris Wilson
2016-04-21 7:01 ` Chris Wilson
2016-04-21 7:24 ` Chris Wilson
2016-04-21 7:32 ` Joonas Lahtinen [this message]
2016-04-20 18:42 ` [PATCH 11/19] drm/i915: Assign every HW context a unique ID Chris Wilson
2016-04-20 18:42 ` [PATCH 12/19] drm/i915: Replace the pinned context address with its " Chris Wilson
2016-04-20 18:42 ` [PATCH 13/19] drm/i915: Refactor execlists default context pinning Chris Wilson
2016-04-20 18:42 ` [PATCH 14/19] drm/i915: Move context initialisation to first-use Chris Wilson
2016-04-21 6:57 ` Joonas Lahtinen
2016-04-21 7:08 ` Chris Wilson
2016-04-21 7:47 ` Joonas Lahtinen
2016-04-21 7:56 ` Chris Wilson
2016-04-21 8:37 ` Joonas Lahtinen
2016-04-20 18:42 ` [PATCH 15/19] drm/i915: Move the magical deferred context allocation into the request Chris Wilson
2016-04-20 18:42 ` [PATCH 16/19] drm/i915: Move releasing of the GEM request from free to retire/cancel Chris Wilson
2016-04-20 18:42 ` [PATCH 17/19] drm/i915: Track the previous pinned context inside the request Chris Wilson
2016-04-21 7:07 ` Joonas Lahtinen
2016-04-21 7:22 ` Chris Wilson
2016-04-21 7:35 ` Joonas Lahtinen
2016-04-20 18:42 ` [PATCH 18/19] drm/i915: Store LRC hardware id in " Chris Wilson
2016-04-21 7:58 ` Tvrtko Ursulin
2016-04-21 9:02 ` Chris Wilson
2016-04-20 18:42 ` [PATCH 19/19] drm/i915: Stop tracking execlists retired requests Chris Wilson
2016-04-21 11:27 ` ✓ Fi.CI.BAT: success for series starting with [01/19] drm/i915/overlay: Replace i915_gem_obj_ggtt_offset() with the known flip_addr Patchwork
2016-04-21 12:05 ` ✗ Fi.CI.BAT: failure " Patchwork
2016-04-23 10:53 ` ✗ Fi.CI.BAT: warning " Patchwork
2016-04-25 6:51 ` Patchwork
-- strict thread matches above, loose matches on Subject: below --
2016-04-21 8:58 [PATCH 01/19] " Chris Wilson
2016-04-21 8:58 ` [PATCH 10/19] drm/i915: Rearrange switch_context to load the aliasing ppgtt on first use Chris Wilson
2016-04-21 14:57 Final CI pass for premature Chris Wilson
2016-04-21 14:57 ` [PATCH 10/19] drm/i915: Rearrange switch_context to load the aliasing ppgtt on first use Chris Wilson
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=1461223979.4381.21.camel@linux.intel.com \
--to=joonas.lahtinen@linux.intel.com \
--cc=chris@chris-wilson.co.uk \
--cc=intel-gfx@lists.freedesktop.org \
--cc=mika.kuoppala@intel.com \
/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