drm/i915/guc: Update to GuC version 69.0.3

Update to the latest GuC release.

The latest GuC firmware introduces a number of interface changes:

GuC may return NO_RESPONSE_RETRY message for requests sent over CTB.
Add support for this reply and try resending the request again as a
new CTB message.

A KLV (key-length-value) mechanism is now used for passing
configuration data such as CTB management.

With the new KLV scheme, the old CTB management actions are no longer
used and are removed.

Register capture on hang is now supported by GuC. Full i915 support
for this will be added by a later patch. A minimum support of
providing capture memory and register lists is required though, so add
that in.

The device id of the current platform needs to be provided at init time.

The 'poll CS' w/a (Wa_22012773006) was blanket enabled by previous
versions of GuC. It must now be explicitly requested by the KMD. So,
add in the code to turn it on when relevant.

The GuC log entry format has changed. This requires adding a new field
to the log header structure to mark the wrap point at the end of the
buffer (as the buffer size is no longer a multiple of the log entry
size).

New CTB notification messages are now sent for some things that were
previously only sent via MMIO notifications.

Of these, the crash dump notification was not really being handled by
i915. It called the log flush code but that only flushed the regular
debug log and then only if relay logging was enabled. So just report
an error message instead.

The 'exception' notification was just being ignored completely. So add
an error message for that as well.

Note that in either the crash dump or the exception case, the GuC is
basically dead. The KMD will detect this via the heartbeat and trigger
both an error log (which will include the crash dump as part of the
GuC log) and a GT reset. So no other processing is really required.

Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220107000622.292081-3-John.C.Harrison@Intel.com

1 files changed, 78 insertions, 63 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 aa6dd6415202..de89d40abd38 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
@@ -112,18 +112,6 @@ void intel_guc_ct_init_early(struct intel_guc_ct *ct)
 	init_waitqueue_head(&ct->wq);
 }
 
-static inline const char *guc_ct_buffer_type_to_str(u32 type)
-{
-	switch (type) {
-	case GUC_CTB_TYPE_HOST2GUC:
-		return "SEND";
-	case GUC_CTB_TYPE_GUC2HOST:
-		return "RECV";
-	default:
-		return "<invalid>";
-	}
-}
-
 static void guc_ct_buffer_desc_init(struct guc_ct_buffer_desc *desc)
 {
 	memset(desc, 0, sizeof(*desc));
@@ -156,71 +144,65 @@ static void guc_ct_buffer_init(struct intel_guc_ct_buffer *ctb,
 	guc_ct_buffer_reset(ctb);
 }
 
-static int guc_action_register_ct_buffer(struct intel_guc *guc, u32 type,
-					 u32 desc_addr, u32 buff_addr, u32 size)
+static int guc_action_control_ctb(struct intel_guc *guc, u32 control)
 {
-	u32 request[HOST2GUC_REGISTER_CTB_REQUEST_MSG_LEN] = {
+	u32 request[HOST2GUC_CONTROL_CTB_REQUEST_MSG_LEN] = {
 		FIELD_PREP(GUC_HXG_MSG_0_ORIGIN, GUC_HXG_ORIGIN_HOST) |
 		FIELD_PREP(GUC_HXG_MSG_0_TYPE, GUC_HXG_TYPE_REQUEST) |
-		FIELD_PREP(GUC_HXG_REQUEST_MSG_0_ACTION, GUC_ACTION_HOST2GUC_REGISTER_CTB),
-		FIELD_PREP(HOST2GUC_REGISTER_CTB_REQUEST_MSG_1_SIZE, size / SZ_4K - 1) |
-		FIELD_PREP(HOST2GUC_REGISTER_CTB_REQUEST_MSG_1_TYPE, type),
-		FIELD_PREP(HOST2GUC_REGISTER_CTB_REQUEST_MSG_2_DESC_ADDR, desc_addr),
-		FIELD_PREP(HOST2GUC_REGISTER_CTB_REQUEST_MSG_3_BUFF_ADDR, buff_addr),
+		FIELD_PREP(GUC_HXG_REQUEST_MSG_0_ACTION, GUC_ACTION_HOST2GUC_CONTROL_CTB),
+		FIELD_PREP(HOST2GUC_CONTROL_CTB_REQUEST_MSG_1_CONTROL, control),
 	};
 	int ret;
 
-	GEM_BUG_ON(type != GUC_CTB_TYPE_HOST2GUC && type != GUC_CTB_TYPE_GUC2HOST);
-	GEM_BUG_ON(size % SZ_4K);
+	GEM_BUG_ON(control != GUC_CTB_CONTROL_DISABLE && control != GUC_CTB_CONTROL_ENABLE);
 
-	/* CT registration must go over MMIO */
+	/* CT control must go over MMIO */
 	ret = intel_guc_send_mmio(guc, request, ARRAY_SIZE(request), NULL, 0);
 
 	return ret > 0 ? -EPROTO : ret;
 }
 
-static int ct_register_buffer(struct intel_guc_ct *ct, u32 type,
-			      u32 desc_addr, u32 buff_addr, u32 size)
+static int ct_control_enable(struct intel_guc_ct *ct, bool enable)
 {
 	int err;
 
-	err = i915_inject_probe_error(guc_to_gt(ct_to_guc(ct))->i915, -ENXIO);
+	err = guc_action_control_ctb(ct_to_guc(ct), enable ?
+				     GUC_CTB_CONTROL_ENABLE : GUC_CTB_CONTROL_DISABLE);
 	if (unlikely(err))
-		return err;
+		CT_PROBE_ERROR(ct, "Failed to control/%s CTB (%pe)\n",
+			       enabledisable(enable), ERR_PTR(err));
 
-	err = guc_action_register_ct_buffer(ct_to_guc(ct), type,
-					    desc_addr, buff_addr, size);
-	if (unlikely(err))
-		CT_ERROR(ct, "Failed to register %s buffer (%pe)\n",
-			 guc_ct_buffer_type_to_str(type), ERR_PTR(err));
 	return err;
 }
 
-static int guc_action_deregister_ct_buffer(struct intel_guc *guc, u32 type)
+static int ct_register_buffer(struct intel_guc_ct *ct, bool send,
+			      u32 desc_addr, u32 buff_addr, u32 size)
 {
-	u32 request[HOST2GUC_DEREGISTER_CTB_REQUEST_MSG_LEN] = {
-		FIELD_PREP(GUC_HXG_MSG_0_ORIGIN, GUC_HXG_ORIGIN_HOST) |
-		FIELD_PREP(GUC_HXG_MSG_0_TYPE, GUC_HXG_TYPE_REQUEST) |
-		FIELD_PREP(GUC_HXG_REQUEST_MSG_0_ACTION, GUC_ACTION_HOST2GUC_DEREGISTER_CTB),
-		FIELD_PREP(HOST2GUC_DEREGISTER_CTB_REQUEST_MSG_1_TYPE, type),
-	};
-	int ret;
-
-	GEM_BUG_ON(type != GUC_CTB_TYPE_HOST2GUC && type != GUC_CTB_TYPE_GUC2HOST);
-
-	/* CT deregistration must go over MMIO */
-	ret = intel_guc_send_mmio(guc, request, ARRAY_SIZE(request), NULL, 0);
+	int err;
 
-	return ret > 0 ? -EPROTO : ret;
-}
+	err = intel_guc_self_cfg64(ct_to_guc(ct), send ?
+				   GUC_KLV_SELF_CFG_H2G_CTB_DESCRIPTOR_ADDR_KEY :
+				   GUC_KLV_SELF_CFG_G2H_CTB_DESCRIPTOR_ADDR_KEY,
+				   desc_addr);
+	if (unlikely(err))
+		goto failed;
 
-static int ct_deregister_buffer(struct intel_guc_ct *ct, u32 type)
-{
-	int err = guc_action_deregister_ct_buffer(ct_to_guc(ct), type);
+	err = intel_guc_self_cfg64(ct_to_guc(ct), send ?
+				   GUC_KLV_SELF_CFG_H2G_CTB_ADDR_KEY :
+				   GUC_KLV_SELF_CFG_G2H_CTB_ADDR_KEY,
+				   buff_addr);
+	if (unlikely(err))
+		goto failed;
 
+	err = intel_guc_self_cfg32(ct_to_guc(ct), send ?
+				   GUC_KLV_SELF_CFG_H2G_CTB_SIZE_KEY :
+				   GUC_KLV_SELF_CFG_G2H_CTB_SIZE_KEY,
+				   size);
 	if (unlikely(err))
-		CT_ERROR(ct, "Failed to deregister %s buffer (%pe)\n",
-			 guc_ct_buffer_type_to_str(type), ERR_PTR(err));
+failed:
+		CT_PROBE_ERROR(ct, "Failed to register %s buffer (%pe)\n",
+			       send ? "SEND" : "RECV", ERR_PTR(err));
+
 	return err;
 }
 
@@ -308,7 +290,7 @@ void intel_guc_ct_fini(struct intel_guc_ct *ct)
 int intel_guc_ct_enable(struct intel_guc_ct *ct)
 {
 	struct intel_guc *guc = ct_to_guc(ct);
-	u32 base, desc, cmds;
+	u32 base, desc, cmds, size;
 	void *blob;
 	int err;
 
@@ -333,27 +315,27 @@ int intel_guc_ct_enable(struct intel_guc_ct *ct)
 	 */
 	desc = base + ptrdiff(ct->ctbs.recv.desc, blob);
 	cmds = base + ptrdiff(ct->ctbs.recv.cmds, blob);
-	err = ct_register_buffer(ct, GUC_CTB_TYPE_GUC2HOST,
-				 desc, cmds, ct->ctbs.recv.size * 4);
-
+	size = ct->ctbs.recv.size * 4;
+	err = ct_register_buffer(ct, false, desc, cmds, size);
 	if (unlikely(err))
 		goto err_out;
 
 	desc = base + ptrdiff(ct->ctbs.send.desc, blob);
 	cmds = base + ptrdiff(ct->ctbs.send.cmds, blob);
-	err = ct_register_buffer(ct, GUC_CTB_TYPE_HOST2GUC,
-				 desc, cmds, ct->ctbs.send.size * 4);
+	size = ct->ctbs.send.size * 4;
+	err = ct_register_buffer(ct, true, desc, cmds, size);
+	if (unlikely(err))
+		goto err_out;
 
+	err = ct_control_enable(ct, true);
 	if (unlikely(err))
-		goto err_deregister;
+		goto err_out;
 
 	ct->enabled = true;
 	ct->stall_time = KTIME_MAX;
 
 	return 0;
 
-err_deregister:
-	ct_deregister_buffer(ct, GUC_CTB_TYPE_GUC2HOST);
 err_out:
 	CT_PROBE_ERROR(ct, "Failed to enable CTB (%pe)\n", ERR_PTR(err));
 	return err;
@@ -372,8 +354,7 @@ void intel_guc_ct_disable(struct intel_guc_ct *ct)
 	ct->enabled = false;
 
 	if (intel_guc_is_fw_running(guc)) {
-		ct_deregister_buffer(ct, GUC_CTB_TYPE_HOST2GUC);
-		ct_deregister_buffer(ct, GUC_CTB_TYPE_GUC2HOST);
+		ct_control_enable(ct, false);
 	}
 }
 
@@ -662,6 +643,7 @@ static int ct_send(struct intel_guc_ct *ct,
 	struct ct_request request;
 	unsigned long flags;
 	unsigned int sleep_period_ms = 1;
+	bool send_again;
 	u32 fence;
 	int err;
 
@@ -671,6 +653,9 @@ static int ct_send(struct intel_guc_ct *ct,
 	GEM_BUG_ON(!response_buf && response_buf_size);
 	might_sleep();
 
+resend:
+	send_again = false;
+
 	/*
 	 * We use a lazy spin wait loop here as we believe that if the CT
 	 * buffers are sized correctly the flow control condition should be
@@ -725,6 +710,13 @@ retry:
 		goto unlink;
 	}
 
+	if (FIELD_GET(GUC_HXG_MSG_0_TYPE, *status) == GUC_HXG_TYPE_NO_RESPONSE_RETRY) {
+		CT_DEBUG(ct, "retrying request %#x (%u)\n", *action,
+			 FIELD_GET(GUC_HXG_RETRY_MSG_0_REASON, *status));
+		send_again = true;
+		goto unlink;
+	}
+
 	if (FIELD_GET(GUC_HXG_MSG_0_TYPE, *status) != GUC_HXG_TYPE_RESPONSE_SUCCESS) {
 		err = -EIO;
 		goto unlink;
@@ -747,6 +739,9 @@ unlink:
 	list_del(&request.link);
 	spin_unlock_irqrestore(&ct->requests.lock, flags);
 
+	if (unlikely(send_again))
+		goto resend;
+
 	return err;
 }
 
@@ -918,6 +913,7 @@ static int ct_handle_response(struct intel_guc_ct *ct, struct ct_incoming_msg *r
 	GEM_BUG_ON(len < GUC_HXG_MSG_MIN_LEN);
 	GEM_BUG_ON(FIELD_GET(GUC_HXG_MSG_0_ORIGIN, hxg[0]) != GUC_HXG_ORIGIN_GUC);
 	GEM_BUG_ON(FIELD_GET(GUC_HXG_MSG_0_TYPE, hxg[0]) != GUC_HXG_TYPE_RESPONSE_SUCCESS &&
+		   FIELD_GET(GUC_HXG_MSG_0_TYPE, hxg[0]) != GUC_HXG_TYPE_NO_RESPONSE_RETRY &&
 		   FIELD_GET(GUC_HXG_MSG_0_TYPE, hxg[0]) != GUC_HXG_TYPE_RESPONSE_FAILURE);
 
 	CT_DEBUG(ct, "response fence %u status %#x\n", fence, hxg[0]);
@@ -990,9 +986,27 @@ static int ct_process_request(struct intel_guc_ct *ct, struct ct_incoming_msg *r
 	case INTEL_GUC_ACTION_CONTEXT_RESET_NOTIFICATION:
 		ret = intel_guc_context_reset_process_msg(guc, payload, len);
 		break;
+	case INTEL_GUC_ACTION_STATE_CAPTURE_NOTIFICATION:
+		ret = intel_guc_error_capture_process_msg(guc, payload, len);
+		if (unlikely(ret))
+			CT_ERROR(ct, "error capture notification failed %x %*ph\n",
+				 action, 4 * len, payload);
+		break;
 	case INTEL_GUC_ACTION_ENGINE_FAILURE_NOTIFICATION:
 		ret = intel_guc_engine_failure_process_msg(guc, payload, len);
 		break;
+	case INTEL_GUC_ACTION_NOTIFY_FLUSH_LOG_BUFFER_TO_FILE:
+		intel_guc_log_handle_flush_event(&guc->log);
+		ret = 0;
+		break;
+	case INTEL_GUC_ACTION_NOTIFY_CRASH_DUMP_POSTED:
+		CT_ERROR(ct, "Received GuC crash dump notification!\n");
+		ret = 0;
+		break;
+	case INTEL_GUC_ACTION_NOTIFY_EXCEPTION:
+		CT_ERROR(ct, "Received GuC exception notification!\n");
+		ret = 0;
+		break;
 	default:
 		ret = -EOPNOTSUPP;
 		break;
@@ -1098,6 +1112,7 @@ static int ct_handle_hxg(struct intel_guc_ct *ct, struct ct_incoming_msg *msg)
 		break;
 	case GUC_HXG_TYPE_RESPONSE_SUCCESS:
 	case GUC_HXG_TYPE_RESPONSE_FAILURE:
+	case GUC_HXG_TYPE_NO_RESPONSE_RETRY:
 		err = ct_handle_response(ct, msg);
 		break;
 	default: