drm/i915/guc: Don't abort on CTB_UNUSED status

When the KMD sends a CLIENT_RESET request to GuC (as part of the
suspend sequence), GuC will mark the CTB buffer as 'UNUSED'. If the
KMD then checked the CTB queue, it would see a non-zero status value
and report the buffer as corrupted.

Technically, no G2H messages should be received once the CLIENT_RESET
has been sent. However, if a context was outstanding on an engine then
it would get reset and a reset notification would be sent. So, don't
actually treat UNUSED as a catastrophic error. Just flag it up as
unexpected and keep going.
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220728024225.2363663-7-John.C.Harrison@Intel.com

drivers/gpu/drm/i915/gt/uc/abi/guc_communication_ctb_abi.h

@@ -37,6 +37,7 @@
  *  |   |       |   - _`GUC_CTB_STATUS_OVERFLOW` = 1 (head/tail too large)     |
  *  |   |       |   - _`GUC_CTB_STATUS_UNDERFLOW` = 2 (truncated message)      |
  *  |   |       |   - _`GUC_CTB_STATUS_MISMATCH` = 4 (head/tail modified)      |
+ *  |   |       |   - _`GUC_CTB_STATUS_UNUSED` = 8 (CTB is not in use)         |
  *  +---+-------+--------------------------------------------------------------+
  *  |...|       | RESERVED = MBZ                                               |
  *  +---+-------+--------------------------------------------------------------+
@@ -49,9 +50,10 @@ struct guc_ct_buffer_desc {
 	u32 tail;
 	u32 status;
 #define GUC_CTB_STATUS_NO_ERROR				0
-#define GUC_CTB_STATUS_OVERFLOW				(1 << 0)
-#define GUC_CTB_STATUS_UNDERFLOW			(1 << 1)
-#define GUC_CTB_STATUS_MISMATCH				(1 << 2)
+#define GUC_CTB_STATUS_OVERFLOW				BIT(0)
+#define GUC_CTB_STATUS_UNDERFLOW			BIT(1)
+#define GUC_CTB_STATUS_MISMATCH				BIT(2)
+#define GUC_CTB_STATUS_UNUSED				BIT(3)
 	u32 reserved[13];
 } __packed;
 static_assert(sizeof(struct guc_ct_buffer_desc) == 64);

drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c

@@ -829,8 +829,22 @@ static int ct_read(struct intel_guc_ct *ct, struct ct_incoming_msg **msg)
 	if (unlikely(ctb->broken))
 		return -EPIPE;
 
-	if (unlikely(desc->status))
-		goto corrupted;
+	if (unlikely(desc->status)) {
+		u32 status = desc->status;
+
+		if (status & GUC_CTB_STATUS_UNUSED) {
+			/*
+			 * Potentially valid if a CLIENT_RESET request resulted in
+			 * contexts/engines being reset. But should never happen as
+			 * no contexts should be active when CLIENT_RESET is sent.
+			 */
+			CT_ERROR(ct, "Unexpected G2H after GuC has stopped!\n");
+			status &= ~GUC_CTB_STATUS_UNUSED;
+		}
+
+		if (status)
+			goto corrupted;
+	}
 
 	GEM_BUG_ON(head > size);