[Intel-gfx] [PATCH 3/4] drm/i915: After reset on sanitization, reset the engine backends

[Chris Wilson]

As we reset the GPU on suspend/resume, we also do need to reset the
engine state tracking so call into the engine backends. This is
especially important so that we can also sanitize the state tracking
across resume.

References: https://bugs.freedesktop.org/show_bug.cgi?id=106702
Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala at intel.com>
---
 drivers/gpu/drm/i915/i915_gem.c  | 24 ++++++++++++++++++++++++
 drivers/gpu/drm/i915/intel_lrc.c |  8 +++++---
 2 files changed, 29 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index b312ac006d24..9b8fa1866cc9 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -4959,7 +4959,22 @@ static void assert_kernel_context_is_current(struct drm_i915_private *i915)
 
 void i915_gem_sanitize(struct drm_i915_private *i915)
 {
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	GEM_TRACE("\n");
+
 	mutex_lock(&i915->drm.struct_mutex);
+
+	intel_runtime_pm_get(i915);
+	intel_uncore_forcewake_get(i915, FORCEWAKE_ALL);
+
+	/*
+	 * As we have just resumed the machine and woken the device up from
+	 * deep PCI sleep (presumably D3_cold), assume the HW has been reset
+	 * back to defaults, recovering from whatever wedged state we left it
+	 * in and so worth trying to use the device once more.
+	 */
 	if (i915_terminally_wedged(&i915->gpu_error))
 		i915_gem_unset_wedged(i915);
 
@@ -4974,6 +4989,15 @@ void i915_gem_sanitize(struct drm_i915_private *i915)
 	if (INTEL_GEN(i915) >= 5 && intel_has_gpu_reset(i915))
 		WARN_ON(intel_gpu_reset(i915, ALL_ENGINES));
 
+	/* Reset the submission backend after resume as well as the GPU reset */
+	for_each_engine(engine, i915, id) {
+		if (engine->reset.reset)
+			engine->reset.reset(engine, NULL);
+	}
+
+	intel_uncore_forcewake_put(i915, FORCEWAKE_ALL);
+	intel_runtime_pm_put(i915);
+
 	i915_gem_contexts_lost(i915);
 	mutex_unlock(&i915->drm.struct_mutex);
 }
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 8a6058b4102f..517e92c6a70b 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1787,9 +1787,6 @@ static void enable_execlists(struct intel_engine_cs *engine)
 	I915_WRITE(RING_HWS_PGA(engine->mmio_base),
 		   engine->status_page.ggtt_offset);
 	POSTING_READ(RING_HWS_PGA(engine->mmio_base));
-
-	/* Following the reset, we need to reload the CSB read/write pointers */
-	engine->execlists.csb_head = -1;
 }
 
 static bool unexpected_starting_state(struct intel_engine_cs *engine)
@@ -1961,6 +1958,9 @@ static void execlists_reset(struct intel_engine_cs *engine,
 	__unwind_incomplete_requests(engine);
 	spin_unlock(&engine->timeline.lock);
 
+	/* Following the reset, we need to reload the CSB read/write pointers */
+	engine->execlists.csb_head = -1;
+
 	local_irq_restore(flags);
 
 	/*
@@ -2460,6 +2460,8 @@ static int logical_ring_init(struct intel_engine_cs *engine)
 			upper_32_bits(ce->lrc_desc);
 	}
 
+	engine->execlists.csb_head = -1;
+
 	return 0;
 
 error:
-- 
2.17.0