1 files changed, 130 insertions, 10 deletions

diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
index 1803a633ed64..f28a3a83742d 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
@@ -13,6 +13,30 @@
 #include "intel_guc_ct.h"
 #include "intel_guc_print.h"
 
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GUC)
+enum {
+	CT_DEAD_ALIVE = 0,
+	CT_DEAD_SETUP,
+	CT_DEAD_WRITE,
+	CT_DEAD_DEADLOCK,
+	CT_DEAD_H2G_HAS_ROOM,
+	CT_DEAD_READ,
+	CT_DEAD_PROCESS_FAILED,
+};
+
+static void ct_dead_ct_worker_func(struct work_struct *w);
+
+#define CT_DEAD(ct, reason)	\
+	do { \
+		if (!(ct)->dead_ct_reported) { \
+			(ct)->dead_ct_reason |= 1 << CT_DEAD_##reason; \
+			queue_work(system_unbound_wq, &(ct)->dead_ct_worker); \
+		} \
+	} while (0)
+#else
+#define CT_DEAD(ct, reason)	do { } while (0)
+#endif
+
 static inline struct intel_guc *ct_to_guc(struct intel_guc_ct *ct)
 {
 	return container_of(ct, struct intel_guc, ct);
@@ -93,6 +117,9 @@ void intel_guc_ct_init_early(struct intel_guc_ct *ct)
 	spin_lock_init(&ct->requests.lock);
 	INIT_LIST_HEAD(&ct->requests.pending);
 	INIT_LIST_HEAD(&ct->requests.incoming);
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GUC)
+	INIT_WORK(&ct->dead_ct_worker, ct_dead_ct_worker_func);
+#endif
 	INIT_WORK(&ct->requests.worker, ct_incoming_request_worker_func);
 	tasklet_setup(&ct->receive_tasklet, ct_receive_tasklet_func);
 	init_waitqueue_head(&ct->wq);
@@ -319,11 +346,16 @@ int intel_guc_ct_enable(struct intel_guc_ct *ct)
 
 	ct->enabled = true;
 	ct->stall_time = KTIME_MAX;
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GUC)
+	ct->dead_ct_reported = false;
+	ct->dead_ct_reason = CT_DEAD_ALIVE;
+#endif
 
 	return 0;
 
 err_out:
 	CT_PROBE_ERROR(ct, "Failed to enable CTB (%pe)\n", ERR_PTR(err));
+	CT_DEAD(ct, SETUP);
 	return err;
 }
 
@@ -344,6 +376,24 @@ void intel_guc_ct_disable(struct intel_guc_ct *ct)
 	}
 }
 
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
+static void ct_track_lost_and_found(struct intel_guc_ct *ct, u32 fence, u32 action)
+{
+	unsigned int lost = fence % ARRAY_SIZE(ct->requests.lost_and_found);
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GUC)
+	unsigned long entries[SZ_32];
+	unsigned int n;
+
+	n = stack_trace_save(entries, ARRAY_SIZE(entries), 1);
+
+	/* May be called under spinlock, so avoid sleeping */
+	ct->requests.lost_and_found[lost].stack = stack_depot_save(entries, n, GFP_NOWAIT);
+#endif
+	ct->requests.lost_and_found[lost].fence = fence;
+	ct->requests.lost_and_found[lost].action = action;
+}
+#endif
+
 static u32 ct_get_next_fence(struct intel_guc_ct *ct)
 {
 	/* For now it's trivial */
@@ -394,11 +444,11 @@ static int ct_write(struct intel_guc_ct *ct,
 		 FIELD_PREP(GUC_CTB_MSG_0_NUM_DWORDS, len) |
 		 FIELD_PREP(GUC_CTB_MSG_0_FENCE, fence);
 
-	type = (flags & INTEL_GUC_CT_SEND_NB) ? GUC_HXG_TYPE_EVENT :
+	type = (flags & INTEL_GUC_CT_SEND_NB) ? GUC_HXG_TYPE_FAST_REQUEST :
 		GUC_HXG_TYPE_REQUEST;
 	hxg = FIELD_PREP(GUC_HXG_MSG_0_TYPE, type) |
-		FIELD_PREP(GUC_HXG_EVENT_MSG_0_ACTION |
-			   GUC_HXG_EVENT_MSG_0_DATA0, action[0]);
+		FIELD_PREP(GUC_HXG_REQUEST_MSG_0_ACTION |
+			   GUC_HXG_REQUEST_MSG_0_DATA0, action[0]);
 
 	CT_DEBUG(ct, "writing (tail %u) %*ph %*ph %*ph\n",
 		 tail, 4, &header, 4, &hxg, 4 * (len - 1), &action[1]);
@@ -415,6 +465,11 @@ static int ct_write(struct intel_guc_ct *ct,
 	}
 	GEM_BUG_ON(tail > size);
 
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
+	ct_track_lost_and_found(ct, fence,
+				FIELD_GET(GUC_HXG_EVENT_MSG_0_ACTION, action[0]));
+#endif
+
 	/*
 	 * make sure H2G buffer update and LRC tail update (if this triggering a
 	 * submission) are visible before updating the descriptor tail
@@ -434,6 +489,7 @@ static int ct_write(struct intel_guc_ct *ct,
 corrupted:
 	CT_ERROR(ct, "Corrupted descriptor head=%u tail=%u status=%#x\n",
 		 desc->head, desc->tail, desc->status);
+	CT_DEAD(ct, WRITE);
 	ctb->broken = true;
 	return -EPIPE;
 }
@@ -504,6 +560,7 @@ static inline bool ct_deadlocked(struct intel_guc_ct *ct)
 		CT_ERROR(ct, "Head: %u\n (Dwords)", ct->ctbs.recv.desc->head);
 		CT_ERROR(ct, "Tail: %u\n (Dwords)", ct->ctbs.recv.desc->tail);
 
+		CT_DEAD(ct, DEADLOCK);
 		ct->ctbs.send.broken = true;
 	}
 
@@ -552,6 +609,7 @@ static inline bool h2g_has_room(struct intel_guc_ct *ct, u32 len_dw)
 			 head, ctb->size);
 		desc->status |= GUC_CTB_STATUS_OVERFLOW;
 		ctb->broken = true;
+		CT_DEAD(ct, H2G_HAS_ROOM);
 		return false;
 	}
 
@@ -640,7 +698,7 @@ static int ct_send(struct intel_guc_ct *ct,
 
 	GEM_BUG_ON(!ct->enabled);
 	GEM_BUG_ON(!len);
-	GEM_BUG_ON(len & ~GUC_CT_MSG_LEN_MASK);
+	GEM_BUG_ON(len > GUC_CTB_HXG_MSG_MAX_LEN - GUC_CTB_HDR_LEN);
 	GEM_BUG_ON(!response_buf && response_buf_size);
 	might_sleep();
 
@@ -902,15 +960,59 @@ static int ct_read(struct intel_guc_ct *ct, struct ct_incoming_msg **msg)
 	/* now update descriptor */
 	WRITE_ONCE(desc->head, head);
 
+	/*
+	 * Wa_22016122933: Making sure the head update is
+	 * visible to GuC right away
+	 */
+	intel_guc_write_barrier(ct_to_guc(ct));
+
 	return available - len;
 
 corrupted:
 	CT_ERROR(ct, "Corrupted descriptor head=%u tail=%u status=%#x\n",
 		 desc->head, desc->tail, desc->status);
 	ctb->broken = true;
+	CT_DEAD(ct, READ);
 	return -EPIPE;
 }
 
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
+static bool ct_check_lost_and_found(struct intel_guc_ct *ct, u32 fence)
+{
+	unsigned int n;
+	char *buf = NULL;
+	bool found = false;
+
+	lockdep_assert_held(&ct->requests.lock);
+
+	for (n = 0; n < ARRAY_SIZE(ct->requests.lost_and_found); n++) {
+		if (ct->requests.lost_and_found[n].fence != fence)
+			continue;
+		found = true;
+
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GUC)
+		buf = kmalloc(SZ_4K, GFP_NOWAIT);
+		if (buf && stack_depot_snprint(ct->requests.lost_and_found[n].stack,
+					       buf, SZ_4K, 0)) {
+			CT_ERROR(ct, "Fence %u was used by action %#04x sent at\n%s",
+				 fence, ct->requests.lost_and_found[n].action, buf);
+			break;
+		}
+#endif
+		CT_ERROR(ct, "Fence %u was used by action %#04x\n",
+			 fence, ct->requests.lost_and_found[n].action);
+		break;
+	}
+	kfree(buf);
+	return found;
+}
+#else
+static bool ct_check_lost_and_found(struct intel_guc_ct *ct, u32 fence)
+{
+	return false;
+}
+#endif
+
 static int ct_handle_response(struct intel_guc_ct *ct, struct ct_incoming_msg *response)
 {
 	u32 len = FIELD_GET(GUC_CTB_MSG_0_NUM_DWORDS, response->msg[0]);
@@ -952,12 +1054,13 @@ static int ct_handle_response(struct intel_guc_ct *ct, struct ct_incoming_msg *r
 		break;
 	}
 	if (!found) {
-		CT_ERROR(ct, "Unsolicited response (fence %u)\n", fence);
-		CT_ERROR(ct, "Could not find fence=%u, last_fence=%u\n", fence,
-			 ct->requests.last_fence);
-		list_for_each_entry(req, &ct->requests.pending, link)
-			CT_ERROR(ct, "request %u awaits response\n",
-				 req->fence);
+		CT_ERROR(ct, "Unsolicited response message: len %u, data %#x (fence %u, last %u)\n",
+			 len, hxg[0], fence, ct->requests.last_fence);
+		if (!ct_check_lost_and_found(ct, fence)) {
+			list_for_each_entry(req, &ct->requests.pending, link)
+				CT_ERROR(ct, "request %u awaits response\n",
+					 req->fence);
+		}
 		err = -ENOKEY;
 	}
 	spin_unlock_irqrestore(&ct->requests.lock, flags);
@@ -1057,6 +1160,7 @@ static bool ct_process_incoming_requests(struct intel_guc_ct *ct)
 	if (unlikely(err)) {
 		CT_ERROR(ct, "Failed to process CT message (%pe) %*ph\n",
 			 ERR_PTR(err), 4 * request->size, request->msg);
+		CT_DEAD(ct, PROCESS_FAILED);
 		ct_free_msg(request);
 	}
 
@@ -1233,3 +1337,19 @@ void intel_guc_ct_print_info(struct intel_guc_ct *ct,
 	drm_printf(p, "Tail: %u\n",
 		   ct->ctbs.recv.desc->tail);
 }
+
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GUC)
+static void ct_dead_ct_worker_func(struct work_struct *w)
+{
+	struct intel_guc_ct *ct = container_of(w, struct intel_guc_ct, dead_ct_worker);
+	struct intel_guc *guc = ct_to_guc(ct);
+
+	if (ct->dead_ct_reported)
+		return;
+
+	ct->dead_ct_reported = true;
+
+	guc_info(guc, "CTB is dead - reason=0x%X\n", ct->dead_ct_reason);
+	intel_klog_error_capture(guc_to_gt(guc), (intel_engine_mask_t)~0U);
+}
+#endif