[PATCH 7/7] drm/i915: Stop parking the signaler around reset

[Chris Wilson <chris@chris-wilson.co.uk>]

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 chosen
"guilty" request.

v2: Refactor setting STOP_RING so that we don't have the same code thrice

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Michałt Winiarski <michal.winiarski@intel.com>
CC: Michel Thierry <michel.thierry@intel.com>
Cc: Jeff McGee <jeff.mcgee@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
 drivers/gpu/drm/i915/i915_gem.c         | 14 ------------
 drivers/gpu/drm/i915/intel_engine_cs.c  | 29 +++++++++++++++++++++++++
 drivers/gpu/drm/i915/intel_lrc.c        |  6 +++++
 drivers/gpu/drm/i915/intel_ringbuffer.c |  2 ++
 drivers/gpu/drm/i915/intel_ringbuffer.h |  2 ++
 drivers/gpu/drm/i915/intel_uncore.c     | 12 +++-------
 6 files changed, 42 insertions(+), 23 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index abf661d40641..b0fe452ce17c 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3015,18 +3015,6 @@ 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! */
@@ -3229,8 +3217,6 @@ 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_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 6bfd7e3ed152..d4e159ae65a6 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -769,6 +769,35 @@ u64 intel_engine_get_last_batch_head(const struct intel_engine_cs *engine)
 	return bbaddr;
 }
 
+int intel_engine_stop_cs(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);
+	int err;
+
+	if (INTEL_GEN(dev_priv) < 3)
+		return -ENODEV;
+
+	GEM_TRACE("%s\n", engine->name);
+
+	I915_WRITE_FW(mode, _MASKED_BIT_ENABLE(STOP_RING));
+
+	err = 0;
+	if (__intel_wait_for_register_fw(dev_priv,
+					 mode, MODE_IDLE, MODE_IDLE,
+					 1000, 0,
+					 NULL)) {
+		GEM_TRACE("%s: timed out on STOP_RING -> IDLE\n", engine->name);
+		err = -ETIMEDOUT;
+	}
+
+	/* A final mmio read to let GPU writes be hopefully flushed to memory */
+	POSTING_READ_FW(mode);
+
+	return err;
+}
+
 const char *i915_cache_level_str(struct drm_i915_private *i915, int type)
 {
 	switch (type) {
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 3b889bb4352a..646ecf267411 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1878,6 +1878,12 @@ execlists_reset_prepare(struct intel_engine_cs *engine)
 	if (request) {
 		unsigned long flags;
 
+		/*
+		 * Prevent the breadcrumb from advancing before we decide
+		 * which request is currently active.
+		 */
+		intel_engine_stop_cs(engine);
+
 		spin_lock_irqsave(&engine->timeline.lock, flags);
 		list_for_each_entry_from_reverse(request,
 						 &engine->timeline.requests,
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index af5a178366ed..6f200a747176 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -533,6 +533,8 @@ static int init_ring_common(struct intel_engine_cs *engine)
 
 static struct i915_request *reset_prepare(struct intel_engine_cs *engine)
 {
+	intel_engine_stop_cs(engine);
+
 	if (engine->irq_seqno_barrier)
 		engine->irq_seqno_barrier(engine);
 
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 1e8bacba7754..61f385a92484 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -878,6 +878,8 @@ int intel_init_bsd_ring_buffer(struct intel_engine_cs *engine);
 int intel_init_blt_ring_buffer(struct intel_engine_cs *engine);
 int intel_init_vebox_ring_buffer(struct intel_engine_cs *engine);
 
+int intel_engine_stop_cs(struct intel_engine_cs *engine);
+
 u64 intel_engine_get_active_head(const struct intel_engine_cs *engine);
 u64 intel_engine_get_last_batch_head(const struct intel_engine_cs *engine);
 
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 448293eb638d..b36a3b5736a0 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -1702,15 +1702,9 @@ static void gen3_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,
-					 500, 0,
-					 NULL))
-		DRM_DEBUG_DRIVER("%s: timed out on STOP_RING\n",
-				 engine->name);
+
+	if (intel_engine_stop_cs(engine))
+		DRM_DEBUG_DRIVER("%s: timed out on STOP_RING\n", engine->name);
 
 	I915_WRITE_FW(RING_HEAD(base), I915_READ_FW(RING_TAIL(base)));
 	POSTING_READ_FW(RING_HEAD(base)); /* paranoia */
-- 
2.17.0

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