drm/i915: Snapshot seqno of most recently submitted request.

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.

This fixes a regression introduced in

commit 44cdd6d219bc64f6810b8ed0023a4d4db9e0fe68
Author: John Harrison <John.C.Harrison@Intel.com>
Date:   Mon Nov 24 18:49:40 2014 +0000

    drm/i915: Convert 'ring_idle()' to use requests not seqnos

v2 (Chris Wilson):
- Pass current engine seqno to ring_idle() from i915_hangcheck_elapsed() rather
than compute it over again.
- Remove extra whitespace.

Issue: VIZ-5998
Signed-off-by: Tomas Elf <tomas.elf@intel.com>
Cc: stable@vger.kernel.org
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
[danvet: Add regressing commit citation provided by Chris.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

3 files changed, 11 insertions, 10 deletions

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 248fd1ac7b3a..716e5acc3bb0 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2542,6 +2542,7 @@ int __i915_add_request(struct intel_engine_cs *ring,
 	}
 
 	request->emitted_jiffies = jiffies;
+	ring->last_submitted_seqno = request->seqno;
 	list_add_tail(&request->list, &ring->request_list);
 	request->file_priv = NULL;
 
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index e6bb72dca3ff..984e2fe6688c 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -2706,18 +2706,11 @@ 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)
+ring_idle(struct intel_engine_cs *ring, u32 seqno)
 {
 	return (list_empty(&ring->request_list) ||
-		i915_gem_request_completed(ring_last_request(ring), false));
+		i915_seqno_passed(seqno, ring->last_submitted_seqno));
 }
 
 static bool
@@ -2939,7 +2932,7 @@ static void i915_hangcheck_elapsed(struct work_struct *work)
 		acthd = intel_ring_get_active_head(ring);
 
 		if (ring->hangcheck.seqno == seqno) {
-			if (ring_idle(ring)) {
+			if (ring_idle(ring, seqno)) {
 				ring->hangcheck.action = HANGCHECK_IDLE;
 
 				if (waitqueue_active(&ring->irq_queue)) {
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index e539314ae87e..4be66f60504d 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -275,6 +275,13 @@ struct  intel_engine_cs {
 	 * Do we have some not yet emitted requests outstanding?
 	 */
 	struct drm_i915_gem_request *outstanding_lazy_request;
+	/**
+	 * 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;