All of lore.kernel.org
 help / color / mirror / Atom feed
From: John.C.Harrison@Intel.com
To: Intel-GFX@Lists.FreeDesktop.Org
Subject: [RFC 24/39] drm/i915: Support for 'unflushed' ring idle
Date: Fri, 17 Jul 2015 15:33:33 +0100	[thread overview]
Message-ID: <1437143628-6329-25-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>

When the seqno wraps around zero, the entire GPU is forced to be idle
for some reason (possibly only to work around issues with hardware
semaphores but no-one seems too sure!). This causes a problem if the
force idle occurs at an inopportune moment such as in the middle of
submitting a batch buffer. Specifically, it would lead to recursive
submits - submitting work requires a new seqno, the new seqno requires
idling the ring, idling the ring requires submitting work, submitting
work requires a new seqno...

This change adds a 'flush' parameter to the idle function call which
specifies whether the scheduler queues should be flushed out. I.e. is
the call intended to just idle the ring as it is right now (no flush)
or is it intended to force all outstanding work out of the system
(with flush).

In the seqno wrap case, pending work is not an issue because the next
operation will be to submit it. However, in other cases, the intention
is to make sure everything that could be done has been done.

Change-Id: I182e9a5853666c64ecc9e84d8a8b820a7f8e8836
For: VIZ-1587
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
 drivers/gpu/drm/i915/i915_gem.c         |  4 ++--
 drivers/gpu/drm/i915/intel_lrc.c        |  2 +-
 drivers/gpu/drm/i915/intel_ringbuffer.c | 17 +++++++++++++++--
 drivers/gpu/drm/i915/intel_ringbuffer.h |  2 +-
 4 files changed, 19 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 6d72caa..20c696f 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2474,7 +2474,7 @@ i915_gem_init_seqno(struct drm_device *dev, u32 seqno)
 
 	/* Carefully retire all requests without writing to the rings */
 	for_each_ring(ring, dev_priv, i) {
-		ret = intel_ring_idle(ring);
+		ret = intel_ring_idle(ring, false);
 		if (ret)
 			return ret;
 	}
@@ -3732,7 +3732,7 @@ int i915_gpu_idle(struct drm_device *dev)
 			i915_add_request_no_flush(req);
 		}
 
-		ret = intel_ring_idle(ring);
+		ret = intel_ring_idle(ring, true);
 		if (ret)
 			return ret;
 	}
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 76d5023..a811d0b 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -990,7 +990,7 @@ void intel_logical_ring_stop(struct intel_engine_cs *ring)
 	if (!intel_ring_initialized(ring))
 		return;
 
-	ret = intel_ring_idle(ring);
+	ret = intel_ring_idle(ring, true);
 	if (ret && !i915_reset_in_progress(&to_i915(ring->dev)->gpu_error))
 		DRM_ERROR("failed to quiesce %s whilst cleaning up: %d\n",
 			  ring->name, ret);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index e0992b7..afb04de 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -2177,9 +2177,22 @@ static void __wrap_ring_buffer(struct intel_ringbuffer *ringbuf)
 	intel_ring_update_space(ringbuf);
 }
 
-int intel_ring_idle(struct intel_engine_cs *ring)
+int intel_ring_idle(struct intel_engine_cs *ring, bool flush)
 {
 	struct drm_i915_gem_request *req;
+	int ret;
+
+	/*
+	 * NB: Must not flush the scheduler if this idle request is from
+	 * within an execbuff submission (i.e. due to 'get_seqno' calling
+	 * 'wrap_seqno' calling 'idle'). As that would lead to recursive
+	 * flushes!
+	 */
+	if (flush) {
+		ret = i915_scheduler_flush(ring, true);
+		if (ret)
+			return ret;
+	}
 
 	/* Wait upon the last request to be completed */
 	if (list_empty(&ring->request_list))
@@ -2983,7 +2996,7 @@ intel_stop_ring_buffer(struct intel_engine_cs *ring)
 	if (!intel_ring_initialized(ring))
 		return;
 
-	ret = intel_ring_idle(ring);
+	ret = intel_ring_idle(ring, true);
 	if (ret && !i915_reset_in_progress(&to_i915(ring->dev)->gpu_error))
 		DRM_ERROR("failed to quiesce %s whilst cleaning up: %d\n",
 			  ring->name, ret);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 9457774..2f30900 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -487,7 +487,7 @@ void intel_ring_update_space(struct intel_ringbuffer *ringbuf);
 int intel_ring_space(struct intel_ringbuffer *ringbuf);
 bool intel_ring_stopped(struct intel_engine_cs *ring);
 
-int __must_check intel_ring_idle(struct intel_engine_cs *ring);
+int __must_check intel_ring_idle(struct intel_engine_cs *ring, bool flush);
 void intel_ring_init_seqno(struct intel_engine_cs *ring, u32 seqno);
 int intel_ring_flush_all_caches(struct drm_i915_gem_request *req);
 int intel_ring_invalidate_all_caches(struct drm_i915_gem_request *req);
-- 
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 ` [RFC 15/39] drm/i915: Keep the reserved space mechanism happy John.C.Harrison
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 ` John.C.Harrison [this message]
2015-07-21  8:50   ` [RFC 24/39] drm/i915: Support for 'unflushed' ring idle 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=1437143628-6329-25-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.