From: Dave Gordon <david.s.gordon@intel.com>
To: Michel Thierry <michel.thierry@intel.com>,
Mika Kuoppala <mika.kuoppala@linux.intel.com>,
"Wang, Zhi A" <zhi.a.wang@intel.com>,
"Tian, Kevin" <kevin.tian@intel.com>,
"intel-gfx@lists.freedesktop.org"
<intel-gfx@lists.freedesktop.org>
Subject: Re: [PATCH 02/21] drm/i915/gtt: Workaround for HW preload not flushing pdps
Date: Thu, 13 Aug 2015 12:42:34 +0100 [thread overview]
Message-ID: <55CC82AA.4070507@intel.com> (raw)
In-Reply-To: <55CC6D96.4080902@intel.com>
On 13/08/15 11:12, Michel Thierry wrote:
> On 8/13/2015 5:08 PM, Zhiyuan Lv wrote:
>> Hi Michel,
>>
>> Thanks for the reply!
>>
>> I yet have another question: right now the mark_tlb_dirty() will be
>> called if any level of PPGTT table is changed. But for the EXECLIST
>> context submission, we only need LRI commands if there are L3 PDP root
>> pointer changes right? Thanks!
>
> mark_tlbs_dirty is not only for execlists mode, we re-used it since it
> was already there.
>
> The update is only required when a PDP is allocated.
>
> -Michel
Doesn't that depend on whether the context is running? The LRI reload
has the side effect of flushing all current knowledge of mappings, so
every level of PD gets refreshed from memory.
If we're not updating the top level PDPs, and we know the context isn't
active, then we *assume* that lower-level PDs will be refreshed when the
context is next loaded. (This hasn't been true on all hardware, some of
which cached previously-retrieved PDs across ctx save-and-reload, and
that's one reason why there's a "Force PD Restore" bit, but we've been
told not to use it on current h/w). AFAICT, current chips don't cache
previous PDs and don't need the "Force" bit for this case.
OTOH, if we don't know whether the context is running, then we can't be
sure when (or whether) any PD updates will be seen. As long as the
changes of interest are only ever *from* NULL *to* non-NULL, we *expect*
it to work, because (we *assume*) the GPU won't cache negative results
from PD lookups; so any lookup that previously hit an invalid mapping
will be re-fetched next time it's required (and may now be good).
If we don't reload the PDPs with LRIs, then perhaps to be safe we need
to inject some other instruction that will just force a re-fetch of the
lower-level PDs from memory, without altering any top-level PDPs? In
conjunction with preallocating the top-level entries, that ought to
guarantee that the updates would be seen just before the point where
they're about to be used?
.Dave.
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
next prev parent reply other threads:[~2015-08-13 11:42 UTC|newest]
Thread overview: 86+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-05-22 17:04 [PATCH 00/21] ppgtt cleanups / scratch merge (V2) Mika Kuoppala
2015-05-22 17:04 ` [PATCH 01/21] drm/i915/gtt: Mark TLBS dirty for gen8+ Mika Kuoppala
2015-06-01 14:51 ` Joonas Lahtinen
2015-06-11 17:37 ` Mika Kuoppala
2015-06-23 11:10 ` Joonas Lahtinen
2015-06-01 15:52 ` Michel Thierry
2015-05-22 17:04 ` [PATCH 02/21] drm/i915/gtt: Workaround for HW preload not flushing pdps Mika Kuoppala
2015-05-29 11:05 ` Michel Thierry
2015-05-29 12:53 ` Michel Thierry
2015-06-10 11:42 ` Michel Thierry
2015-06-11 7:31 ` Dave Gordon
2015-06-11 10:46 ` Michel Thierry
2015-06-11 13:57 ` Mika Kuoppala
2015-08-11 5:05 ` Zhiyuan Lv
2015-08-12 7:56 ` Michel Thierry
2015-08-12 15:09 ` Dave Gordon
2015-08-13 9:36 ` Zhiyuan Lv
2015-08-13 9:54 ` Michel Thierry
2015-08-13 9:08 ` Zhiyuan Lv
2015-08-13 10:12 ` Michel Thierry
2015-08-13 11:42 ` Dave Gordon [this message]
2015-08-13 12:03 ` Dave Gordon
2015-08-13 14:56 ` Zhiyuan Lv
2015-05-22 17:04 ` [PATCH 03/21] drm/i915/gtt: Check va range against vm size Mika Kuoppala
2015-06-01 15:33 ` Joonas Lahtinen
2015-06-11 14:23 ` Mika Kuoppala
2015-06-24 14:48 ` Michel Thierry
2015-05-22 17:04 ` [PATCH 04/21] drm/i915/gtt: Allow >= 4GB sizes for vm Mika Kuoppala
2015-05-26 7:15 ` Daniel Vetter
2015-06-11 17:38 ` Mika Kuoppala
2015-05-22 17:04 ` [PATCH 05/21] drm/i915/gtt: Don't leak scratch page on mapping error Mika Kuoppala
2015-06-01 15:02 ` Joonas Lahtinen
2015-06-15 10:13 ` Daniel Vetter
2015-05-22 17:04 ` [PATCH 06/21] drm/i915/gtt: Remove _single from page table allocator Mika Kuoppala
2015-06-02 9:53 ` Joonas Lahtinen
2015-06-02 9:56 ` Michel Thierry
2015-06-15 10:14 ` Daniel Vetter
2015-05-22 17:05 ` [PATCH 07/21] drm/i915/gtt: Introduce i915_page_dir_dma_addr Mika Kuoppala
2015-06-02 10:11 ` Michel Thierry
2015-05-22 17:05 ` [PATCH 08/21] drm/i915/gtt: Introduce struct i915_page_dma Mika Kuoppala
2015-06-02 12:39 ` Michel Thierry
2015-06-11 17:48 ` Mika Kuoppala
2015-06-22 14:05 ` Michel Thierry
2015-05-22 17:05 ` [PATCH 09/21] drm/i915/gtt: Rename unmap_and_free_px to free_px Mika Kuoppala
2015-06-02 13:08 ` Michel Thierry
2015-06-11 17:48 ` Mika Kuoppala
2015-06-22 14:09 ` Michel Thierry
2015-06-22 14:43 ` Daniel Vetter
2015-05-22 17:05 ` [PATCH 10/21] drm/i915/gtt: Remove superfluous free_pd with gen6/7 Mika Kuoppala
2015-06-02 14:07 ` Michel Thierry
2015-05-22 17:05 ` [PATCH 11/21] drm/i915/gtt: Introduce fill_page_dma() Mika Kuoppala
2015-06-02 14:51 ` Michel Thierry
2015-06-02 15:01 ` Ville Syrjälä
2015-06-15 10:16 ` Daniel Vetter
2015-06-11 17:50 ` Mika Kuoppala
2015-06-24 15:05 ` Michel Thierry
2015-05-22 17:05 ` [PATCH 12/21] drm/i915/gtt: Introduce kmap|kunmap for dma page Mika Kuoppala
2015-06-03 10:55 ` Michel Thierry
2015-06-11 17:50 ` Mika Kuoppala
2015-06-24 15:06 ` Michel Thierry
2015-05-22 17:05 ` [PATCH 13/21] drm/i915/gtt: Use macros to access dma mapped pages Mika Kuoppala
2015-06-03 10:57 ` Michel Thierry
2015-05-22 17:05 ` [PATCH 14/21] drm/i915/gtt: Make scratch page i915_page_dma compatible Mika Kuoppala
2015-06-03 13:44 ` Michel Thierry
2015-06-11 16:30 ` Mika Kuoppala
2015-06-24 14:59 ` Michel Thierry
2015-05-22 17:05 ` [PATCH 15/21] drm/i915/gtt: Fill scratch page Mika Kuoppala
2015-05-27 18:12 ` Tomas Elf
2015-06-01 15:53 ` Chris Wilson
2015-06-04 11:08 ` Tomas Elf
2015-06-04 11:24 ` Chris Wilson
2015-06-11 16:37 ` Mika Kuoppala
2015-06-03 14:03 ` Michel Thierry
2015-05-22 17:05 ` [PATCH 16/21] drm/i915/gtt: Pin vma during virtual address allocation Mika Kuoppala
2015-06-03 14:27 ` Michel Thierry
2015-05-22 17:05 ` [PATCH 17/21] drm/i915/gtt: Cleanup page directory encoding Mika Kuoppala
2015-06-03 14:58 ` Michel Thierry
2015-05-22 17:05 ` [PATCH 18/21] drm/i915/gtt: Move scratch_pd and scratch_pt into vm area Mika Kuoppala
2015-06-03 16:46 ` Michel Thierry
2015-05-22 17:05 ` [PATCH 19/21] drm/i915/gtt: One instance of scratch page table/directory Mika Kuoppala
2015-06-03 16:57 ` Michel Thierry
2015-05-22 17:05 ` [PATCH 20/21] drm/i915/gtt: Use nonatomic bitmap ops Mika Kuoppala
2015-06-03 17:07 ` Michel Thierry
2015-05-22 17:05 ` [PATCH 21/21] drm/i915/gtt: Reorder page alloc/free/init functions Mika Kuoppala
2015-06-03 17:14 ` Michel Thierry
2015-06-11 17:52 ` Mika Kuoppala
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=55CC82AA.4070507@intel.com \
--to=david.s.gordon@intel.com \
--cc=intel-gfx@lists.freedesktop.org \
--cc=kevin.tian@intel.com \
--cc=michel.thierry@intel.com \
--cc=mika.kuoppala@linux.intel.com \
--cc=zhi.a.wang@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 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.