From e4d8e8aa342ae676093f8b5bb17401ce44a24ea8 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 19 Dec 2019 12:43:52 +0000
Subject: drm/i915/gt: Schedule request retirement when signaler idles
Git-commit: dc93c9b69315167f5678b94aa911dc8e7c299fe5
Patch-mainline: v5.6-rc1
References: jsc#SLE-12680, jsc#SLE-12880, jsc#SLE-12882, jsc#SLE-12883, jsc#SLE-13496, jsc#SLE-15322

Very similar to commit 4f88f8747fa4 ("drm/i915/gt: Schedule request
retirement when timeline idles"), but this time instead of coupling into
the execlists CS event interrupt, we couple into the breadcrumb
interrupt and queue a timeline's retirement when the last signaler is
completed. This should allow us to more rapidly park ringbuffer
submission, and so help reduce power consumption on older systems.

v2: Fixup intel_engine_add_retire() to handle concurrent callers

References: 4f88f8747fa4 ("drm/i915/gt: Schedule request retirement when timeline idles")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191219124353.8607-1-chris@chris-wilson.co.uk
Signed-off-by: Patrik Jakobsson <pjakobsson@suse.de>
---
 drivers/gpu/drm/i915/gt/intel_breadcrumbs.c | 6 +++++-
 drivers/gpu/drm/i915/gt/intel_gt_requests.c | 7 ++-----
 drivers/gpu/drm/i915/gt/intel_lrc.c         | 2 +-
 3 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
index 5fa4d621528e..4f491791b4ba 100644
--- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
@@ -29,6 +29,7 @@
 #include "i915_drv.h"
 #include "i915_trace.h"
 #include "intel_gt_pm.h"
+#include "intel_gt_requests.h"
 
 static void irq_enable(struct intel_engine_cs *engine)
 {
@@ -179,8 +180,11 @@ static void signal_irq_work(struct irq_work *work)
 		if (!list_is_first(pos, &ce->signals)) {
 			/* Advance the list to the first incomplete request */
 			__list_del_many(&ce->signals, pos);
-			if (&ce->signals == pos) /* now empty */
+			if (&ce->signals == pos) { /* now empty */
 				list_del_init(&ce->signal_link);
+				intel_engine_add_retire(ce->engine,
+							ce->timeline);
+			}
 		}
 	}
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.c b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
index 8cb5421e5f0e..0d1bca787288 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_requests.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
@@ -62,19 +62,16 @@ static void engine_retire(struct work_struct *work)
 static bool add_retire(struct intel_engine_cs *engine,
 		       struct intel_timeline *tl)
 {
+#define STUB ((struct intel_timeline *)1)
 	struct intel_timeline *first;
 
 	/*
 	 * We open-code a llist here to include the additional tag [BIT(0)]
 	 * so that we know when the timeline is already on a
 	 * retirement queue: either this engine or another.
-	 *
-	 * However, we rely on that a timeline can only be active on a single
-	 * engine at any one time and that add_retire() is called before the
-	 * engine releases the timeline and transferred to another to retire.
 	 */
 
-	if (READ_ONCE(tl->retire)) /* already queued */
+	if (cmpxchg(&tl->retire, NULL, STUB)) /* already queued */
 		return false;
 
 	intel_timeline_get(tl);
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 31c82581a351..e53b6c45b0cd 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -4521,8 +4521,8 @@ intel_execlists_create_virtual(struct i915_gem_context *ctx,
 
 	intel_engine_init_active(&ve->base, ENGINE_VIRTUAL);
 	intel_engine_init_breadcrumbs(&ve->base);
-
 	intel_engine_init_execlists(&ve->base);
+	intel_engine_init_retire(&ve->base);
 
 	ve->base.cops = &virtual_context_ops;
 	ve->base.request_alloc = execlists_request_alloc;
-- 
2.28.0