drm/i915: Take runtime pm reference on hangcheck_info88910

We read the coherent current seqno and actual head from ring.
For hardware access we need to take runtime_pm reference, which brings in
locking. As this debugfs entry is for debugging hangcheck behaviour,
including locking problems, we need to be flexible on taking them.

Try to see if we get a lock and if so, get seqno and actual head
from hardware. If we don't have exclusive access, get lazy coherent
seqno and print token acthd for which the user can see that the
seqno is of different nature.

Testcase: igt/pm_rpm/debugfs-read
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=88910
Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>

1 files changed, 23 insertions, 3 deletions

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 211d4949a675..04ae72b66dc7 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -1223,8 +1223,11 @@ out:
 static int i915_hangcheck_info(struct seq_file *m, void *unused)
 {
 	struct drm_info_node *node = m->private;
-	struct drm_i915_private *dev_priv = to_i915(node->minor->dev);
+	struct drm_device *dev = node->minor->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_engine_cs *ring;
+	u64 acthd[I915_NUM_RINGS];
+	u32 seqno[I915_NUM_RINGS];
 	int i;
 
 	if (!i915.enable_hangcheck) {
@@ -1232,6 +1235,23 @@ static int i915_hangcheck_info(struct seq_file *m, void *unused)
 		return 0;
 	}
 
+	if (mutex_trylock(&dev->struct_mutex)) {
+		intel_runtime_pm_get(dev_priv);
+
+		for_each_ring(ring, dev_priv, i) {
+			seqno[i] = ring->get_seqno(ring, false);
+			acthd[i] = intel_ring_get_active_head(ring);
+		}
+
+		intel_runtime_pm_put(dev_priv);
+		mutex_unlock(&dev->struct_mutex);
+	} else {
+		for_each_ring(ring, dev_priv, i) {
+			seqno[i] = ring->get_seqno(ring, true);
+			acthd[i] = -1;
+		}
+	}
+
 	if (delayed_work_pending(&dev_priv->gpu_error.hangcheck_work)) {
 		seq_printf(m, "Hangcheck active, fires in %dms\n",
 			   jiffies_to_msecs(dev_priv->gpu_error.hangcheck_work.timer.expires -
@@ -1242,12 +1262,12 @@ static int i915_hangcheck_info(struct seq_file *m, void *unused)
 	for_each_ring(ring, dev_priv, i) {
 		seq_printf(m, "%s:\n", ring->name);
 		seq_printf(m, "\tseqno = %x [current %x]\n",
-			   ring->hangcheck.seqno, ring->get_seqno(ring, false));
+			   ring->hangcheck.seqno, seqno[i]);
 		seq_printf(m, "\taction = %d\n", ring->hangcheck.action);
 		seq_printf(m, "\tscore = %d\n", ring->hangcheck.score);
 		seq_printf(m, "\tACTHD = 0x%08llx [current 0x%08llx]\n",
 			   (long long)ring->hangcheck.acthd,
-			   (long long)intel_ring_get_active_head(ring));
+			   (long long)acthd[i]);
 		seq_printf(m, "\tmax ACTHD = 0x%08llx\n",
 			   (long long)ring->hangcheck.max_acthd);
 	}