[Intel-gfx] [PATCH] drm/i915: Snapshot seqno of most recently submitted request.

[Tomas Elf]

The hang checker needs to inspect whether or not the ring request list is empty
as well as if the given engine has reached or passed the most recently
submitted request. The problem with this is that the hang checker cannot grab
the struct_mutex, which is required in order to safely inspect requests since
requests might be deallocated during inspection. In the past we've had kernel
panics due to this very unsynchronized access in the hang checker.

One solution to this problem is to not inspect the requests directly since
we're only interested in the seqno of the most recently submitted request - not
the request itself. Instead the seqno of the most recently submitted request is
stored separately, which the hang checker then inspects, circumventing the
issue of synchronization from the hang checker entirely.

Issue: VIZ-5998
Signed-off-by: Tomas Elf <tomas.elf at intel.com>
---
 drivers/gpu/drm/i915/i915_gem.c         |  2 ++
 drivers/gpu/drm/i915/i915_irq.c         | 14 ++++++--------
 drivers/gpu/drm/i915/intel_ringbuffer.h |  7 +++++++
 3 files changed, 15 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index a0bff41..971b439 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2549,6 +2549,7 @@ void __i915_add_request(struct drm_i915_gem_request *request,
 	request->batch_obj = obj;
 
 	request->emitted_jiffies = jiffies;
+	ring->last_submitted_seqno = request->seqno;
 	list_add_tail(&request->list, &ring->request_list);
 
 	trace_i915_gem_request_add(request);
@@ -2784,6 +2785,7 @@ static void i915_gem_reset_ring_cleanup(struct drm_i915_private *dev_priv,
 
 		i915_gem_request_retire(request);
 	}
+
 }
 
 void i915_gem_restore_fences(struct drm_device *dev)
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index a6fbe64..f291bb9 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -2484,18 +2484,16 @@ static void gen8_disable_vblank(struct drm_device *dev, int pipe)
 	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
 }
 
-static struct drm_i915_gem_request *
-ring_last_request(struct intel_engine_cs *ring)
-{
-	return list_entry(ring->request_list.prev,
-			  struct drm_i915_gem_request, list);
-}
-
 static bool
 ring_idle(struct intel_engine_cs *ring)
 {
+	u32 current_seqno;
+
+	current_seqno = ring->get_seqno(ring, false);
+
 	return (list_empty(&ring->request_list) ||
-		i915_gem_request_completed(ring_last_request(ring), false));
+		i915_seqno_passed(current_seqno,
+				  ring->last_submitted_seqno));
 }
 
 static bool
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 0ea89ea..2e85fda 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -292,6 +292,13 @@ struct  intel_engine_cs {
 	 */
 	struct list_head request_list;
 
+	/**
+	 * Seqno of request most recently submitted to request_list.
+	 * Used exclusively by hang checker to avoid grabbing lock while
+	 * inspecting request list.
+	 */
+	u32 last_submitted_seqno;
+
 	bool gpu_caches_dirty;
 
 	wait_queue_head_t irq_queue;
-- 
1.9.1