public inbox for intel-gfx@lists.freedesktop.org
 help / color / mirror / Atom feed
From: Damien Lespiau <damien.lespiau@intel.com>
To: "Mateo Lozano, Oscar" <oscar.mateo@intel.com>
Cc: "intel-gfx@lists.freedesktop.org"
	<intel-gfx@lists.freedesktop.org>,
	Ben Widawsky <ben@bwidawsk.net>,
	"Widawsky, Benjamin" <benjamin.widawsky@intel.com>
Subject: Re: [PATCH 17/49] drm/i915/bdw: A bit more advanced context init/fini
Date: Tue, 1 Apr 2014 14:51:27 +0100	[thread overview]
Message-ID: <20140401135127.GD16291@strange.amr.corp.intel.com> (raw)
In-Reply-To: <92648605EABDA246B775AAB04C95A7A3012BE598@IRSMSX103.ger.corp.intel.com>

On Tue, Apr 01, 2014 at 02:47:19PM +0100, Mateo Lozano, Oscar wrote:
> > > --- a/drivers/gpu/drm/i915/i915_lrc.c
> > > +++ b/drivers/gpu/drm/i915/i915_lrc.c
> > > @@ -41,7 +41,45 @@
> > >  #include <drm/i915_drm.h>
> > >  #include "i915_drv.h"
> > >
> > > +#define GEN8_LR_CONTEXT_SIZE (21 * PAGE_SIZE)
> > 
> > I'm a bit puzzled by that number:
> >   - I found a sentence saying: "the Context Image for the rendering
> >     engine consists of 20 4K pages", which seems that it includes the
> >     HWS page (on the same page it says context layout = HWS Page +
> >     register state context).
> >   - When looking at the register state context for the render engine:
> >     18096 dwords -> 18 pages, so in total it'd be 19 pages (need to add
> >     the HWS Page)
> >   - Clearly I must be missing something :)
> >   - That's only for the render engine, other engines have a much smaller
> >     context, smaller enough that it's worth looking at their exact size.
> >   - It'd be nice to work out the real size from the *CXT_*SIZE
> >     registers.
> 
> Hmmmm... I´ll try to get the real context sizes from the registers and
> compare. At least for RCS, VCS and BCS since there doesn´t seem to be
> a register for VECS?

Couldn't find it either. I guess we'll need to ask the help of a friend.
Or the 50/50 joker maybe.

-- 
Damien

  reply	other threads:[~2014-04-01 13:52 UTC|newest]

Thread overview: 85+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-03-27 17:59 [PATCH 00/49] Execlists oscar.mateo
2014-03-27 17:59 ` [PATCH 01/49] drm/i915/bdw: Macro to distinguish LRCs (Logical Ring Contexts) oscar.mateo
2014-03-27 17:59 ` [PATCH 02/49] drm/i915: s/for_each_ring/for_each_active_ring oscar.mateo
2014-03-27 17:59 ` [PATCH 03/49] drm/i915: for_each_ring oscar.mateo
2014-03-27 17:59 ` [PATCH 04/49] drm/i915: Simplify a couple of functions thanks to for_each_ring oscar.mateo
2014-03-27 17:59 ` [PATCH 05/49] drm/i915: Extract trivial parts of ring init (early init) oscar.mateo
2014-03-27 17:59 ` [PATCH 06/49] drm/i915/bdw: New file for logical ring contexts and execlists oscar.mateo
2014-03-27 17:59 ` [PATCH 07/49] drm/i915/bdw: Rework init code for gen8 contexts oscar.mateo
2014-03-27 17:59 ` [PATCH 08/49] drm/i915: Make i915_gem_create_context outside accessible oscar.mateo
2014-03-27 17:59 ` [PATCH 09/49] drm/i915: Extract ringbuffer obj alloc & destroy oscar.mateo
2014-03-27 17:59 ` [PATCH 10/49] drm/i915: s/intel_ring_buffer/intel_engine oscar.mateo
2014-03-27 17:59 ` [PATCH 11/49] drm/i915: Split the ringbuffers and the rings oscar.mateo
2014-03-27 17:59 ` [PATCH 12/49] drm/i915: Rename functions that mention ringbuffers (meaning rings) oscar.mateo
2014-03-27 17:59 ` [PATCH 13/49] drm/i915/bdw: Execlists ring tail writing oscar.mateo
2014-03-27 17:13   ` Mateo Lozano, Oscar
2014-03-27 17:59 ` [PATCH 14/49] drm/i915/bdw: LR context ring init oscar.mateo
2014-03-27 17:59 ` [PATCH 15/49] drm/i915/bdw: GEN8 semaphoreless ring add request oscar.mateo
2014-03-27 17:59 ` [PATCH 16/49] drm/i915/bdw: GEN8 new ring flush oscar.mateo
2014-03-27 17:59 ` [PATCH 17/49] drm/i915/bdw: A bit more advanced context init/fini oscar.mateo
2014-04-01  0:38   ` Damien Lespiau
2014-04-01 13:47     ` Mateo Lozano, Oscar
2014-04-01 13:51       ` Damien Lespiau [this message]
2014-04-01 19:18         ` Ben Widawsky
2014-04-01 21:05           ` Damien Lespiau
2014-04-02  4:07             ` Ben Widawsky
2014-03-27 17:59 ` [PATCH 18/49] drm/i915/bdw: Allocate ringbuffer for LR contexts oscar.mateo
2014-03-27 17:59 ` [PATCH 19/49] drm/i915/bdw: Populate LR contexts (somewhat) oscar.mateo
2014-04-01  0:00   ` Damien Lespiau
2014-04-01 13:33     ` Mateo Lozano, Oscar
2014-04-15 16:00   ` Jeff McGee
2014-04-15 16:10     ` Jeff McGee
2014-04-15 19:51       ` Daniel Vetter
2014-04-15 20:43       ` Jeff McGee
2014-04-15 21:08         ` Daniel Vetter
2014-04-15 22:32           ` Jeff McGee
2014-04-16  6:04             ` Daniel Vetter
2014-03-27 17:59 ` [PATCH 20/49] drm/i915/bdw: Status page for LR contexts oscar.mateo
2014-03-27 17:59 ` [PATCH 21/49] drm/i915/bdw: Enable execlists in the hardware oscar.mateo
2014-03-27 17:59 ` [PATCH 22/49] drm/i915/bdw: Plumbing for user LR context switching oscar.mateo
2014-03-27 17:59 ` [PATCH 23/49] drm/i915: s/__intel_ring_advance/intel_ringbuffer_advance_and_submit oscar.mateo
2014-03-27 17:59 ` [PATCH 24/49] drm/i915/bdw: Write a new set of context-aware ringbuffer management functions oscar.mateo
2014-03-27 17:59 ` [PATCH 25/49] drm/i915: Final touches to LR contexts plumbing and refactoring oscar.mateo
2014-03-27 17:59 ` [PATCH 26/49] drm/i915/bdw: Set the request context information correctly in the LRC case oscar.mateo
2014-03-27 17:59 ` [PATCH 27/49] drm/i915/bdw: Prepare for user-created LR contexts oscar.mateo
2014-03-27 17:59 ` [PATCH 28/49] drm/i915/bdw: Start creating & destroying user " oscar.mateo
2014-03-27 17:59 ` [PATCH 29/49] drm/i915/bdw: Pin context pages at context create time oscar.mateo
2014-03-27 17:59 ` [PATCH 30/49] drm/i915/bdw: Extract LR context object populating oscar.mateo
2014-03-27 18:00 ` [PATCH 31/49] drm/i915/bdw: Introduce dependent contexts oscar.mateo
2014-03-27 17:21   ` Mateo Lozano, Oscar
2014-04-09 16:54     ` Mateo Lozano, Oscar
2014-03-27 18:00 ` [PATCH 32/49] drm/i915/bdw: Create stand-alone and " oscar.mateo
2014-03-27 18:00 ` [PATCH 33/49] drm/i915/bdw: Allow non-default, non-render user LR contexts oscar.mateo
2014-03-27 18:00 ` [PATCH 34/49] drm/i915/bdw: Fix reset stats ioctl with " oscar.mateo
2014-03-27 18:00 ` [PATCH 35/49] drm/i915: Allocate an integer ID for each new file descriptor oscar.mateo
2014-03-27 18:00 ` [PATCH 36/49] drm/i915/bdw: Prepare for a 20-bits globally unique submission ID oscar.mateo
2014-03-27 18:00 ` [PATCH 37/49] drm/i915/bdw: Implement context switching (somewhat) oscar.mateo
2014-03-27 18:00 ` [PATCH 38/49] drm/i915/bdw: Add forcewake lock around ELSP writes oscar.mateo
2014-03-27 18:00 ` [PATCH 39/49] drm/i915/bdw: Swap the PPGTT PDPs, LRC style oscar.mateo
2014-03-31 16:42   ` Damien Lespiau
2014-04-01 13:42     ` Mateo Lozano, Oscar
2014-04-02 13:47   ` Damien Lespiau
2014-04-09  7:56     ` Mateo Lozano, Oscar
2014-03-27 18:00 ` [PATCH 40/49] drm/i915/bdw: Write the tail pointer, " oscar.mateo
2014-03-27 18:00 ` [PATCH 41/49] drm/i915/bdw: LR context switch interrupts oscar.mateo
2014-04-02 11:42   ` Damien Lespiau
2014-04-02 11:49     ` Daniel Vetter
2014-04-02 12:56       ` Damien Lespiau
2014-03-27 18:00 ` [PATCH 42/49] drm/i915/bdw: Get prepared for a two-stage execlist submit process oscar.mateo
2014-04-04 11:12   ` Damien Lespiau
2014-04-04 13:24     ` Damien Lespiau
2014-04-09  7:57       ` Mateo Lozano, Oscar
2014-03-27 18:00 ` [PATCH 43/49] drm/i915/bdw: Handle context switch events oscar.mateo
2014-04-03 14:24   ` Damien Lespiau
2014-04-09  8:15     ` Mateo Lozano, Oscar
2014-04-26  0:53   ` Robert Beckett
2014-04-28 14:43     ` Mateo Lozano, Oscar
2014-03-27 18:00 ` [PATCH 44/49] drm/i915/bdw: Display execlists info in debugfs oscar.mateo
2014-04-07 19:19   ` Damien Lespiau
2014-03-27 18:00 ` [PATCH 45/49] drm/i915/bdw: Display context ringbuffer " oscar.mateo
2014-03-27 18:00 ` [PATCH 46/49] drm/i915/bdw: Start queueing contexts to be submitted oscar.mateo
2014-03-27 18:00 ` [PATCH 47/49] drm/i915/bdw: Always write seqno to default context oscar.mateo
2014-03-27 18:00 ` [PATCH 48/49] drm/i915/bdw: Enable logical ring contexts oscar.mateo
2014-03-27 18:00 ` [PATCH 49/49] drm/i915/bdw: Document execlists and " oscar.mateo
2014-04-07 18:12 ` [PATCH 00/49] Execlists Damien Lespiau
2014-04-07 21:32   ` Daniel Vetter

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=20140401135127.GD16291@strange.amr.corp.intel.com \
    --to=damien.lespiau@intel.com \
    --cc=ben@bwidawsk.net \
    --cc=benjamin.widawsky@intel.com \
    --cc=intel-gfx@lists.freedesktop.org \
    --cc=oscar.mateo@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