drm/dp_mst: Add topology ref history tracking for debugging

For very subtle mistakes with topology refs, it can be rather difficult
to trace them down with the debugging info that we already have. I had
one such issue recently while trying to implement suspend/resume
reprobing for MST, and ended up coming up with this.

Inspired by Chris Wilson's wakeref tracking for i915, this adds a very
similar feature to the DP MST helpers, which allows for partial tracking
of topology refs for both ports and branch devices. This is a lot less
advanced then wakeref tracking: we merely keep a count of all of the
spots where a topology ref has been grabbed or dropped, then dump out
that history in chronological order when a port or branch device's
topology refcount reaches 0. So far, I've found this incredibly useful
for debugging topology refcount errors.

Since this has the potential to be somewhat slow and loud, we add an
expert kernel config option to enable or disable this feature,
CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS.

Changes since v1:
* Don't forget to destroy topology_ref_history_lock
Changes since v4:
* Correct order of kref_put()/topology_ref_history_unlock - we can't
  unlock the history after kref_put() since the memory might have been
  freed by that point
* Don't print message on allocation error failures, the kernel already
  does this for us
Changes since v5:
* Get rid of some leftover usages of %px
* Remove a leftover empty return; statement

Cc: Juston Li <juston.li@intel.com>
Cc: Imre Deak <imre.deak@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Harry Wentland <hwentlan@amd.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Sean Paul <sean@poorly.run>
Signed-off-by: Lyude Paul <lyude@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191022023641.8026-15-lyude@redhat.com

1 files changed, 45 insertions, 0 deletions

diff --git a/include/drm/drm_dp_mst_helper.h b/include/drm/drm_dp_mst_helper.h
index 144027e27464..d5fc90b30487 100644
--- a/include/drm/drm_dp_mst_helper.h
+++ b/include/drm/drm_dp_mst_helper.h
@@ -26,6 +26,26 @@
 #include <drm/drm_dp_helper.h>
 #include <drm/drm_atomic.h>
 
+#if IS_ENABLED(CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS)
+#include <linux/stackdepot.h>
+#include <linux/timekeeping.h>
+
+enum drm_dp_mst_topology_ref_type {
+	DRM_DP_MST_TOPOLOGY_REF_GET,
+	DRM_DP_MST_TOPOLOGY_REF_PUT,
+};
+
+struct drm_dp_mst_topology_ref_history {
+	struct drm_dp_mst_topology_ref_entry {
+		enum drm_dp_mst_topology_ref_type type;
+		int count;
+		ktime_t ts_nsec;
+		depot_stack_handle_t backtrace;
+	} *entries;
+	int len;
+};
+#endif /* IS_ENABLED(CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS) */
+
 struct drm_dp_mst_branch;
 
 /**
@@ -89,6 +109,14 @@ struct drm_dp_mst_port {
 	 */
 	struct kref malloc_kref;
 
+#if IS_ENABLED(CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS)
+	/**
+	 * @topology_ref_history: A history of each topology
+	 * reference/dereference. See CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS.
+	 */
+	struct drm_dp_mst_topology_ref_history topology_ref_history;
+#endif
+
 	u8 port_num;
 	bool input;
 	bool mcs;
@@ -162,6 +190,14 @@ struct drm_dp_mst_branch {
 	 */
 	struct kref malloc_kref;
 
+#if IS_ENABLED(CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS)
+	/**
+	 * @topology_ref_history: A history of each topology
+	 * reference/dereference. See CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS.
+	 */
+	struct drm_dp_mst_topology_ref_history topology_ref_history;
+#endif
+
 	/**
 	 * @destroy_next: linked-list entry used by
 	 * drm_dp_delayed_destroy_work()
@@ -647,6 +683,15 @@ struct drm_dp_mst_topology_mgr {
 	 * transmissions.
 	 */
 	struct work_struct up_req_work;
+
+#if IS_ENABLED(CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS)
+	/**
+	 * @topology_ref_history_lock: protects
+	 * &drm_dp_mst_port.topology_ref_history and
+	 * &drm_dp_mst_branch.topology_ref_history.
+	 */
+	struct mutex topology_ref_history_lock;
+#endif
 };
 
 int drm_dp_mst_topology_mgr_init(struct drm_dp_mst_topology_mgr *mgr,