All of lore.kernel.org
 help / color / mirror / Atom feed
From: John.C.Harrison@Intel.com
To: Intel-GFX@Lists.FreeDesktop.Org
Subject: [RFC 15/39] drm/i915: Keep the reserved space mechanism happy
Date: Fri, 17 Jul 2015 15:33:24 +0100	[thread overview]
Message-ID: <1437143628-6329-16-git-send-email-John.C.Harrison@Intel.com> (raw)
In-Reply-To: <1437143628-6329-1-git-send-email-John.C.Harrison@Intel.com>

From: John Harrison <John.C.Harrison@Intel.com>

Ring space is reserved when constructing a request to ensure that the
subsequent 'add_request()' call cannot fail due to waiting for space
on a busy or broken GPU. However, the scheduler jumps in to the middle
of the execbuffer process between request creation and request
submission. Thus it needs to cancel the reserved space when the
request is simply added to the scheduler's queue and not yet
submitted. Similarly, it needs to re-reserve the space when it finally
does want to send the batch buffer to the hardware.

For: VIZ-1587
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
 drivers/gpu/drm/i915/i915_gem_execbuffer.c |  7 +++++++
 drivers/gpu/drm/i915/i915_scheduler.c      |  4 ++++
 drivers/gpu/drm/i915/intel_lrc.c           | 13 +++++++++++--
 3 files changed, 22 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 364e9cc..75d018d 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1317,6 +1317,10 @@ int i915_gem_ringbuffer_submission_final(struct i915_execbuffer_params *params)
 	/* The mutex must be acquired before calling this function */
 	BUG_ON(!mutex_is_locked(&params->dev->struct_mutex));
 
+	ret = intel_ring_reserve_space(params->request);
+	if (ret)
+		return ret;
+
 	intel_runtime_pm_get(dev_priv);
 
 	/*
@@ -1392,6 +1396,9 @@ error:
 	 */
 	intel_runtime_pm_put(dev_priv);
 
+	if (ret)
+		intel_ring_reserved_space_cancel(params->request->ringbuf);
+
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index 3494fd5..e145829 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -95,6 +95,8 @@ int i915_scheduler_queue_execbuffer(struct i915_scheduler_queue_entry *qe)
 
 		qe->scheduler_index = scheduler->index++;
 
+		intel_ring_reserved_space_cancel(qe->params.request->ringbuf);
+
 		scheduler->flags[qe->params.ring->id] |= i915_sf_submitting;
 		ret = dev_priv->gt.execbuf_final(&qe->params);
 		scheduler->flags[qe->params.ring->id] &= ~i915_sf_submitting;
@@ -126,6 +128,8 @@ int i915_scheduler_queue_execbuffer(struct i915_scheduler_queue_entry *qe)
 	node->stamp  = stamp;
 	i915_gem_request_reference(node->params.request);
 
+	intel_ring_reserved_space_cancel(node->params.request->ringbuf);
+
 	BUG_ON(node->params.request->scheduler_qe);
 	node->params.request->scheduler_qe = node;
 
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index a8c78ec..76d5023 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -908,13 +908,17 @@ int intel_execlists_submission_final(struct i915_execbuffer_params *params)
 	/* The mutex must be acquired before calling this function */
 	BUG_ON(!mutex_is_locked(&params->dev->struct_mutex));
 
+	ret = intel_logical_ring_reserve_space(params->request);
+	if (ret)
+		return ret;
+
 	/*
 	 * Unconditionally invalidate gpu caches and ensure that we do flush
 	 * any residual writes from the previous batch.
 	 */
 	ret = logical_ring_invalidate_all_caches(params->request);
 	if (ret)
-		return ret;
+		goto err;
 
 	if (ring == &dev_priv->ring[RCS] &&
 	    params->instp_mode != dev_priv->relative_constants_mode) {
@@ -938,13 +942,18 @@ int intel_execlists_submission_final(struct i915_execbuffer_params *params)
 
 	ret = ring->emit_bb_start(params->request, exec_start, params->dispatch_flags);
 	if (ret)
-		return ret;
+		goto err;
 
 	trace_i915_gem_ring_dispatch(params->request, params->dispatch_flags);
 
 	i915_gem_execbuffer_retire_commands(params);
 
 	return 0;
+
+err:
+	intel_ring_reserved_space_cancel(params->request->ringbuf);
+
+	return ret;
 }
 
 void intel_execlists_retire_requests(struct intel_engine_cs *ring)
-- 
1.9.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx

  parent reply	other threads:[~2015-07-17 14:34 UTC|newest]

Thread overview: 48+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-07-17 14:33 [RFC 00/39] GPU scheduler for i915 driver John.C.Harrison
2015-07-17 14:33 ` [RFC 01/39] drm/i915: Add total count to context status debugfs output John.C.Harrison
2015-07-17 14:33 ` [RFC 02/39] drm/i915: Updating assorted register and status page definitions John.C.Harrison
2015-07-17 14:33 ` [RFC 03/39] drm/i915: Explicit power enable during deferred context initialisation John.C.Harrison
2015-07-21  7:54   ` Daniel Vetter
2015-07-17 14:33 ` [RFC 04/39] drm/i915: Prelude to splitting i915_gem_do_execbuffer in two John.C.Harrison
2015-07-21  8:06   ` Daniel Vetter
2015-07-17 14:33 ` [RFC 05/39] drm/i915: Split i915_dem_do_execbuffer() in half John.C.Harrison
2015-07-21  8:00   ` Daniel Vetter
2015-07-17 14:33 ` [RFC 06/39] drm/i915: Re-instate request->uniq because it is extremely useful John.C.Harrison
2015-07-17 14:33 ` [RFC 07/39] drm/i915: Start of GPU scheduler John.C.Harrison
2015-07-21  9:40   ` Daniel Vetter
2015-07-17 14:33 ` [RFC 08/39] drm/i915: Prepare retire_requests to handle out-of-order seqnos John.C.Harrison
2015-07-17 14:33 ` [RFC 09/39] drm/i915: Added scheduler hook into i915_gem_complete_requests_ring() John.C.Harrison
2015-07-17 14:33 ` [RFC 10/39] drm/i915: Disable hardware semaphores when GPU scheduler is enabled John.C.Harrison
2015-07-17 14:33 ` [RFC 11/39] drm/i915: Force MMIO flips when scheduler enabled John.C.Harrison
2015-07-17 14:33 ` [RFC 12/39] drm/i915: Added scheduler hook when closing DRM file handles John.C.Harrison
2015-07-17 14:33 ` [RFC 13/39] drm/i915: Added deferred work handler for scheduler John.C.Harrison
2015-07-17 14:33 ` [RFC 14/39] drm/i915: Redirect execbuffer_final() via scheduler John.C.Harrison
2015-07-17 14:33 ` John.C.Harrison [this message]
2015-07-17 14:33 ` [RFC 16/39] drm/i915: Added tracking/locking of batch buffer objects John.C.Harrison
2015-07-17 14:33 ` [RFC 17/39] drm/i915: Hook scheduler node clean up into retire requests John.C.Harrison
2015-07-17 14:33 ` [RFC 18/39] drm/i915: Added scheduler interrupt handler hook John.C.Harrison
2015-07-17 14:33 ` [RFC 19/39] drm/i915: Added scheduler support to __wait_request() calls John.C.Harrison
2015-07-21  9:27   ` Daniel Vetter
2015-07-17 14:33 ` [RFC 20/39] drm/i915: Added scheduler support to page fault handler John.C.Harrison
2015-07-17 14:33 ` [RFC 21/39] drm/i915: Added scheduler flush calls to ring throttle and idle functions John.C.Harrison
2015-07-17 14:33 ` [RFC 22/39] drm/i915: Add scheduler hook to GPU reset John.C.Harrison
2015-07-17 14:33 ` [RFC 23/39] drm/i915: Added a module parameter for allowing scheduler overrides John.C.Harrison
2015-07-17 14:33 ` [RFC 24/39] drm/i915: Support for 'unflushed' ring idle John.C.Harrison
2015-07-21  8:50   ` Daniel Vetter
2015-07-17 14:33 ` [RFC 25/39] drm/i915: Defer seqno allocation until actual hardware submission time John.C.Harrison
2015-07-17 14:33 ` [RFC 26/39] drm/i915: Added immediate submission override to scheduler John.C.Harrison
2015-07-17 14:33 ` [RFC 27/39] drm/i915: Add sync wait support " John.C.Harrison
2015-07-21  9:59   ` Daniel Vetter
2015-07-17 14:33 ` [RFC 28/39] drm/i915: Connecting execbuff fences " John.C.Harrison
2015-07-17 14:33 ` [RFC 29/39] drm/i915: Added trace points " John.C.Harrison
2015-07-17 14:33 ` [RFC 30/39] drm/i915: Added scheduler queue throttling by DRM file handle John.C.Harrison
2015-07-17 14:33 ` [RFC 31/39] drm/i915: Added debugfs interface to scheduler tuning parameters John.C.Harrison
2015-07-17 14:33 ` [RFC 32/39] drm/i915: Added debug state dump facilities to scheduler John.C.Harrison
2015-07-17 14:33 ` [RFC 33/39] drm/i915: Add early exit to execbuff_final() if insufficient ring space John.C.Harrison
2015-07-17 14:33 ` [RFC 34/39] drm/i915: Added scheduler statistic reporting to debugfs John.C.Harrison
2015-07-17 14:33 ` [RFC 35/39] drm/i915: Added seqno values to scheduler status dump John.C.Harrison
2015-07-17 14:33 ` [RFC 36/39] drm/i915: Add scheduler support functions for TDR John.C.Harrison
2015-07-17 14:33 ` [RFC 37/39] drm/i915: GPU priority bumping to prevent starvation John.C.Harrison
2015-07-17 14:33 ` [RFC 38/39] drm/i915: Enable GPU scheduler by default John.C.Harrison
2015-07-17 14:33 ` [RFC 39/39] drm/i915: Allow scheduler to manage inter-ring object synchronisation John.C.Harrison
2015-07-21 13:33 ` [RFC 00/39] GPU scheduler for i915 driver 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=1437143628-6329-16-git-send-email-John.C.Harrison@Intel.com \
    --to=john.c.harrison@intel.com \
    --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.