All of lore.kernel.org
 help / color / mirror / Atom feed
From: Matthew Brost <matthew.brost@intel.com>
To: Chris Wilson <chris@chris-wilson.co.uk>
Cc: intel-gfx@lists.freedesktop.org
Subject: Re: [Intel-gfx] [PATCH 19/21] drm/i915/gt: Use indices for writing into relative timelines
Date: Thu, 10 Dec 2020 11:16:44 -0800	[thread overview]
Message-ID: <20201210191644.GA6255@sdutt-i7> (raw)
In-Reply-To: <20201210080240.24529-19-chris@chris-wilson.co.uk>

On Thu, Dec 10, 2020 at 08:02:38AM +0000, Chris Wilson wrote:
> Relative timelines are relative to either the global or per-process
> HWSP, and so we can replace the absolute addressing with store-index
> variants for position invariance.
> 

Can you explain the benifit of relative addressing? Why can't we also
use absolute? If we can always use absolute, I don't see the point
complicating the breadcrumb code.

Matt

> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> ---
>  drivers/gpu/drm/i915/gt/gen8_engine_cs.c | 98 +++++++++++++++++-------
>  drivers/gpu/drm/i915/gt/intel_timeline.h | 12 +++
>  2 files changed, 82 insertions(+), 28 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
> index ed88dc4de72c..386da26816d0 100644
> --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
> +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
> @@ -502,7 +502,19 @@ gen8_emit_fini_breadcrumb_tail(struct i915_request *rq, u32 *cs)
>  
>  static u32 *emit_xcs_breadcrumb(struct i915_request *rq, u32 *cs)
>  {
> -	return gen8_emit_ggtt_write(cs, rq->fence.seqno, hwsp_offset(rq), 0);
> +	struct intel_timeline *tl = rcu_dereference_protected(rq->timeline, 1);
> +	unsigned int flags = MI_FLUSH_DW_OP_STOREDW;
> +	u32 offset = hwsp_offset(rq);
> +
> +	if (intel_timeline_is_relative(tl)) {
> +		offset = offset_in_page(offset);
> +		flags |= MI_FLUSH_DW_STORE_INDEX;
> +	}
> +	GEM_BUG_ON(offset & 7);
> +	if (intel_timeline_is_global(tl))
> +		offset |= MI_FLUSH_DW_USE_GTT;
> +
> +	return __gen8_emit_flush_dw(cs, rq->fence.seqno, offset, flags);
>  }
>  
>  u32 *gen8_emit_fini_breadcrumb_xcs(struct i915_request *rq, u32 *cs)
> @@ -512,6 +524,18 @@ u32 *gen8_emit_fini_breadcrumb_xcs(struct i915_request *rq, u32 *cs)
>  
>  u32 *gen8_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
>  {
> +	struct intel_timeline *tl = rcu_dereference_protected(rq->timeline, 1);
> +	unsigned int flags = PIPE_CONTROL_FLUSH_ENABLE | PIPE_CONTROL_CS_STALL;
> +	u32 offset = hwsp_offset(rq);
> +
> +	if (intel_timeline_is_relative(tl)) {
> +		offset = offset_in_page(offset);
> +		flags |= PIPE_CONTROL_STORE_DATA_INDEX;
> +	}
> +	GEM_BUG_ON(offset & 7);
> +	if (intel_timeline_is_global(tl))
> +		flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
> +
>  	cs = gen8_emit_pipe_control(cs,
>  				    PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
>  				    PIPE_CONTROL_DEPTH_CACHE_FLUSH |
> @@ -519,26 +543,33 @@ u32 *gen8_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
>  				    0);
>  
>  	/* XXX flush+write+CS_STALL all in one upsets gem_concurrent_blt:kbl */
> -	cs = gen8_emit_ggtt_write_rcs(cs,
> -				      rq->fence.seqno,
> -				      hwsp_offset(rq),
> -				      PIPE_CONTROL_FLUSH_ENABLE |
> -				      PIPE_CONTROL_CS_STALL);
> +	cs = __gen8_emit_write_rcs(cs, rq->fence.seqno, offset, 0, flags);
>  
>  	return gen8_emit_fini_breadcrumb_tail(rq, cs);
>  }
>  
>  u32 *gen11_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
>  {
> -	cs = gen8_emit_ggtt_write_rcs(cs,
> -				      rq->fence.seqno,
> -				      hwsp_offset(rq),
> -				      PIPE_CONTROL_CS_STALL |
> -				      PIPE_CONTROL_TILE_CACHE_FLUSH |
> -				      PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
> -				      PIPE_CONTROL_DEPTH_CACHE_FLUSH |
> -				      PIPE_CONTROL_DC_FLUSH_ENABLE |
> -				      PIPE_CONTROL_FLUSH_ENABLE);
> +	struct intel_timeline *tl = rcu_dereference_protected(rq->timeline, 1);
> +	u32 offset = hwsp_offset(rq);
> +	unsigned int flags;
> +
> +	flags = (PIPE_CONTROL_CS_STALL |
> +		 PIPE_CONTROL_TILE_CACHE_FLUSH |
> +		 PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
> +		 PIPE_CONTROL_DEPTH_CACHE_FLUSH |
> +		 PIPE_CONTROL_DC_FLUSH_ENABLE |
> +		 PIPE_CONTROL_FLUSH_ENABLE);
> +
> +	if (intel_timeline_is_relative(tl)) {
> +		offset = offset_in_page(offset);
> +		flags |= PIPE_CONTROL_STORE_DATA_INDEX;
> +	}
> +	GEM_BUG_ON(offset & 7);
> +	if (intel_timeline_is_global(tl))
> +		flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
> +
> +	cs = __gen8_emit_write_rcs(cs, rq->fence.seqno, offset, 0, flags);
>  
>  	return gen8_emit_fini_breadcrumb_tail(rq, cs);
>  }
> @@ -601,19 +632,30 @@ u32 *gen12_emit_fini_breadcrumb_xcs(struct i915_request *rq, u32 *cs)
>  
>  u32 *gen12_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
>  {
> -	cs = gen12_emit_ggtt_write_rcs(cs,
> -				       rq->fence.seqno,
> -				       hwsp_offset(rq),
> -				       PIPE_CONTROL0_HDC_PIPELINE_FLUSH,
> -				       PIPE_CONTROL_CS_STALL |
> -				       PIPE_CONTROL_TILE_CACHE_FLUSH |
> -				       PIPE_CONTROL_FLUSH_L3 |
> -				       PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
> -				       PIPE_CONTROL_DEPTH_CACHE_FLUSH |
> -				       /* Wa_1409600907:tgl */
> -				       PIPE_CONTROL_DEPTH_STALL |
> -				       PIPE_CONTROL_DC_FLUSH_ENABLE |
> -				       PIPE_CONTROL_FLUSH_ENABLE);
> +	struct intel_timeline *tl = rcu_dereference_protected(rq->timeline, 1);
> +	u32 offset = hwsp_offset(rq);
> +	unsigned int flags;
> +
> +	flags = (PIPE_CONTROL_CS_STALL |
> +		 PIPE_CONTROL_TILE_CACHE_FLUSH |
> +		 PIPE_CONTROL_FLUSH_L3 |
> +		 PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
> +		 PIPE_CONTROL_DEPTH_CACHE_FLUSH |
> +		 /* Wa_1409600907:tgl */
> +		 PIPE_CONTROL_DEPTH_STALL |
> +		 PIPE_CONTROL_DC_FLUSH_ENABLE |
> +		 PIPE_CONTROL_FLUSH_ENABLE);
> +
> +	if (intel_timeline_is_relative(tl)) {
> +		offset = offset_in_page(offset);
> +		flags |= PIPE_CONTROL_STORE_DATA_INDEX;
> +	}
> +	GEM_BUG_ON(offset & 7);
> +	if (intel_timeline_is_global(tl))
> +		flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
> +
> +	cs = __gen8_emit_write_rcs(cs, rq->fence.seqno, offset,
> +				   PIPE_CONTROL0_HDC_PIPELINE_FLUSH, flags);
>  
>  	return gen12_emit_fini_breadcrumb_tail(rq, cs);
>  }
> diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.h b/drivers/gpu/drm/i915/gt/intel_timeline.h
> index 69250de3a814..a3bdbff62e96 100644
> --- a/drivers/gpu/drm/i915/gt/intel_timeline.h
> +++ b/drivers/gpu/drm/i915/gt/intel_timeline.h
> @@ -79,6 +79,18 @@ intel_timeline_has_initial_breadcrumb(const struct intel_timeline *tl)
>  	return tl->mode == INTEL_TIMELINE_ABSOLUTE;
>  }
>  
> +static inline bool
> +intel_timeline_is_relative(const struct intel_timeline *tl)
> +{
> +	return tl->mode != INTEL_TIMELINE_ABSOLUTE;
> +}
> +
> +static inline bool
> +intel_timeline_is_global(const struct intel_timeline *tl)
> +{
> +	return tl->mode != INTEL_TIMELINE_CONTEXT;
> +}
> +
>  static inline int __intel_timeline_sync_set(struct intel_timeline *tl,
>  					    u64 context, u32 seqno)
>  {
> -- 
> 2.20.1
> 
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/intel-gfx
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

  reply	other threads:[~2020-12-10 19:22 UTC|newest]

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-12-10  8:02 [Intel-gfx] [PATCH 01/21] drm/i915/gt: Mark legacy ring context as lost Chris Wilson
2020-12-10  8:02 ` [Intel-gfx] [PATCH 02/21] drm/i915/gt: Wean workaround selftests off GEM context Chris Wilson
2020-12-10 17:04   ` Mika Kuoppala
2020-12-10  8:02 ` [Intel-gfx] [PATCH 03/21] drm/i915/gt: Replace direct submit with direct call to tasklet Chris Wilson
2020-12-10  8:02 ` [Intel-gfx] [PATCH 04/21] drm/i915/gt: Use virtual_engine during execlists_dequeue Chris Wilson
2020-12-10  8:02 ` [Intel-gfx] [PATCH 05/21] drm/i915/gt: Decouple inflight virtual engines Chris Wilson
2020-12-10  8:02 ` [Intel-gfx] [PATCH 06/21] drm/i915/gt: Defer schedule_out until after the next dequeue Chris Wilson
2020-12-10  8:02 ` [Intel-gfx] [PATCH 07/21] drm/i915/gt: Remove virtual breadcrumb before transfer Chris Wilson
2020-12-10  8:02 ` [Intel-gfx] [PATCH 08/21] drm/i915/gt: Shrink the critical section for irq signaling Chris Wilson
2020-12-10  8:02 ` [Intel-gfx] [PATCH 09/21] drm/i915/gt: Resubmit the virtual engine on schedule-out Chris Wilson
2020-12-10  8:02 ` [Intel-gfx] [PATCH 10/21] drm/i915/gt: Simplify virtual engine handling for execlists_hold() Chris Wilson
2020-12-10  8:02 ` [Intel-gfx] [PATCH 11/21] drm/i915/gt: ce->inflight updates are now serialised Chris Wilson
2020-12-10  8:02 ` [Intel-gfx] [PATCH 12/21] drm/i915/gem: Drop free_work for GEM contexts Chris Wilson
2020-12-10 18:50   ` Matthew Brost
2020-12-10  8:02 ` [Intel-gfx] [PATCH 13/21] drm/i915/gt: Track the overall awake/busy time Chris Wilson
2020-12-10  8:02 ` [Intel-gfx] [PATCH 14/21] drm/i915: Encode fence specific waitqueue behaviour into the wait.flags Chris Wilson
2020-12-10  8:02 ` [Intel-gfx] [PATCH 15/21] drm/i915/gt: Track all timelines created using the HWSP Chris Wilson
2020-12-10 18:28   ` Matthew Brost
2020-12-10  8:02 ` [Intel-gfx] [PATCH 16/21] drm/i915/gt: Wrap intel_timeline.has_initial_breadcrumb Chris Wilson
2020-12-10  8:02 ` [Intel-gfx] [PATCH 17/21] drm/i915/gt: Track timeline GGTT offset separately from subpage offset Chris Wilson
2020-12-10 21:37   ` Matthew Brost
2020-12-10  8:02 ` [Intel-gfx] [PATCH 18/21] drm/i915/gt: Add timeline "mode" Chris Wilson
2020-12-10 19:28   ` Matthew Brost
2020-12-10 21:00     ` Chris Wilson
2020-12-10 21:18       ` Matthew Brost
2020-12-10  8:02 ` [Intel-gfx] [PATCH 19/21] drm/i915/gt: Use indices for writing into relative timelines Chris Wilson
2020-12-10 19:16   ` Matthew Brost [this message]
2020-12-10 21:05     ` Chris Wilson
2020-12-10 21:51       ` Matthew Brost
2020-12-10  8:02 ` [Intel-gfx] [PATCH 20/21] drm/i915/selftests: Exercise relative timeline modes Chris Wilson
2020-12-10  8:02 ` [Intel-gfx] [PATCH 21/21] drm/i915/gt: Use ppHWSP for unshared non-semaphore related timelines Chris Wilson
2020-12-10 21:28   ` Matthew Brost
2020-12-10  8:31 ` [Intel-gfx] ✗ Fi.CI.SPARSE: warning for series starting with [01/21] drm/i915/gt: Mark legacy ring context as lost Patchwork
2020-12-10  8:34 ` [Intel-gfx] ✗ Fi.CI.DOCS: " Patchwork
2020-12-10  8:59 ` [Intel-gfx] ✓ Fi.CI.BAT: success " Patchwork
2020-12-10 12:18 ` [Intel-gfx] ✗ Fi.CI.IGT: failure " Patchwork
2020-12-10 16:39 ` [Intel-gfx] [PATCH 01/21] " Mika Kuoppala
2020-12-10 17:04 ` Matthew Brost

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=20201210191644.GA6255@sdutt-i7 \
    --to=matthew.brost@intel.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.