[Intel-gfx] [PATCH 09/15] drm/i915: Stop parking the signaler around reset

[Chris Wilson]

We cannot call kthread_park() from softirq context, so let's avoid it
entirely during the reset. We wanted to suspend the signaler so that it
would not mark a request as complete at the same time as we marked it as
being in error. Instead of parking the signaling, stop the engine from
advancing so that the GPU doesn't emit the breadcrumb for our choosen
"guilty" request.

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala at linux.intel.com>
Cc: Michał Winiarski <michal.winiarski at intel.com>
CC: Michel Thierry <michel.thierry at intel.com>
Cc: Jeff McGee <jeff.mcgee at intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
---
 drivers/gpu/drm/i915/i915_gem.c         | 14 --------------
 drivers/gpu/drm/i915/intel_lrc.c        | 29 +++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/intel_ringbuffer.c | 30 ++++++++++++++++++++++++++++++
 3 files changed, 59 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 038867c96809..8a6acb1d5ad3 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2928,18 +2928,6 @@ i915_gem_reset_prepare_engine(struct intel_engine_cs *engine)
 	 */
 	intel_uncore_forcewake_get(engine->i915, FORCEWAKE_ALL);
 
-	/*
-	 * Prevent the signaler thread from updating the request
-	 * state (by calling dma_fence_signal) as we are processing
-	 * the reset. The write from the GPU of the seqno is
-	 * asynchronous and the signaler thread may see a different
-	 * value to us and declare the request complete, even though
-	 * the reset routine have picked that request as the active
-	 * (incomplete) request. This conflict is not handled
-	 * gracefully!
-	 */
-	kthread_park(engine->breadcrumbs.signaler);
-
 	request = engine->reset.prepare(engine);
 	if (request && request->fence.error == -EIO)
 		request = ERR_PTR(-EIO); /* Previous reset failed! */
@@ -3136,8 +3124,6 @@ void i915_gem_reset_finish_engine(struct intel_engine_cs *engine)
 {
 	engine->reset.finish(engine);
 
-	kthread_unpark(engine->breadcrumbs.signaler);
-
 	intel_uncore_forcewake_put(engine->i915, FORCEWAKE_ALL);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index be1737d42d43..36f8490de178 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1732,6 +1732,29 @@ static void tasklet_kill_and_disable(struct tasklet_struct *t)
 	smp_mb();
 }
 
+static void set_stop_engine(struct intel_engine_cs *engine)
+{
+	struct drm_i915_private *dev_priv = engine->i915;
+	const u32 base = engine->mmio_base;
+	const i915_reg_t mode = RING_MI_MODE(base);
+
+	I915_WRITE_FW(mode, _MASKED_BIT_ENABLE(STOP_RING));
+	if (__intel_wait_for_register_fw(dev_priv,
+					 mode, MODE_IDLE, MODE_IDLE,
+					 1000, 0,
+					 NULL))
+		DRM_DEBUG_DRIVER("%s: timed out on STOP_RING\n",
+				 engine->name);
+}
+
+static void clear_stop_engine(struct intel_engine_cs *engine)
+{
+	struct drm_i915_private *dev_priv = engine->i915;
+
+	I915_WRITE_FW(RING_MI_MODE(engine->mmio_base),
+		      _MASKED_BIT_DISABLE(STOP_RING));
+}
+
 static struct i915_request *
 execlists_reset_prepare(struct intel_engine_cs *engine)
 {
@@ -1768,6 +1791,9 @@ execlists_reset_prepare(struct intel_engine_cs *engine)
 	if (test_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted))
 		process_csb(engine);
 
+	intel_uncore_forcewake_get(engine->i915, FORCEWAKE_ALL);
+	set_stop_engine(engine);
+
 	/*
 	 * The last active request can then be no later than the last request
 	 * now in ELSP[0]. So search backwards from there, so that if the GPU
@@ -1869,6 +1895,9 @@ static void execlists_reset(struct intel_engine_cs *engine,
 
 static void execlists_reset_finish(struct intel_engine_cs *engine)
 {
+	clear_stop_engine(engine);
+	intel_uncore_forcewake_get(engine->i915, FORCEWAKE_ALL);
+
 	tasklet_enable(&engine->execlists.tasklet);
 
 	GEM_TRACE("%s\n", engine->name);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 5dadbc435c0e..03b84cd45314 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -530,8 +530,35 @@ static int init_ring_common(struct intel_engine_cs *engine)
 	return ret;
 }
 
+static void set_stop_engine(struct intel_engine_cs *engine)
+{
+	struct drm_i915_private *dev_priv = engine->i915;
+	const u32 base = engine->mmio_base;
+	const i915_reg_t mode = RING_MI_MODE(base);
+
+	I915_WRITE_FW(mode, _MASKED_BIT_ENABLE(STOP_RING));
+	if (__intel_wait_for_register_fw(dev_priv,
+					 mode, MODE_IDLE, MODE_IDLE,
+					 1000, 0,
+					 NULL))
+		DRM_DEBUG_DRIVER("%s: timed out on STOP_RING\n",
+				 engine->name);
+}
+
+static void clear_stop_engine(struct intel_engine_cs *engine)
+{
+	struct drm_i915_private *dev_priv = engine->i915;
+
+	I915_WRITE_FW(RING_MI_MODE(engine->mmio_base),
+		      _MASKED_BIT_DISABLE(STOP_RING));
+}
+
 static struct i915_request *reset_prepare(struct intel_engine_cs *engine)
 {
+	intel_uncore_forcewake_get(engine->i915, FORCEWAKE_ALL);
+	if (INTEL_GEN(engine->i915) >= 3)
+		set_stop_engine(engine);
+
 	if (engine->irq_seqno_barrier)
 		engine->irq_seqno_barrier(engine);
 
@@ -608,6 +635,9 @@ static void reset_ring(struct intel_engine_cs *engine,
 
 static void reset_finish(struct intel_engine_cs *engine)
 {
+	if (INTEL_GEN(engine->i915) >= 3)
+		clear_stop_engine(engine);
+	intel_uncore_forcewake_get(engine->i915, FORCEWAKE_ALL);
 }
 
 static int intel_rcs_ctx_init(struct i915_request *rq)
-- 
2.16.3