drm/i915/guc: add enable_guc_loading parameter

Split the function of "enable_guc_submission" into two separate
options.  The new one ("enable_guc_loading") controls only the
*fetching and loading* of the GuC firmware image. The existing
one is redefined to control only the *use* of the GuC for batch
submission once the firmware is loaded.

In addition, the degree of control has been refined from a simple
bool to an integer key, allowing several options:
-1 (default)     whatever the platform default is
 0  DISABLE      don't load/use the GuC
 1  BEST EFFORT  try to load/use the GuC, fallback if not available
 2  REQUIRE      must load/use the GuC, else leave the GPU wedged

The new platform default (as coded here) will be to attempt to
load the GuC iff the device has a GuC that requires firmware,
but not yet to use it for submission. A later patch will change
to enable it if appropriate.

v4:
    Changed some error-message levels, mostly ERROR->INFO, per
    review comments by Tvrtko Ursulin.

v5:
    Dropped one more error message, disabled GuC submission on
    hypothetical firmware-free devices [Tvrtko Ursulin].

v6:
    Logging tidy by Tvrtko Ursulin:
     * Do not log falling back to execlists when wedging the GPU.
     * Do not log fw load errors when load was disabled by user.
     * Pass down some error code from fw load for log message to
       make more sense.
Signed-off-by: Dave Gordon <david.s.gordon@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> (v5)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Tested-by: Fiedorowicz, Lukasz <lukasz.fiedorowicz@intel.com>
Signed-off-by: Dave Gordon <david.s.gordon@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> (v5)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Nick Hoath <nicholas.hoath@intel.com> (v6)

drivers/gpu/drm/i915/i915_gem.c

@@ -4885,12 +4885,9 @@ i915_gem_init_hw(struct drm_device *dev)
 	/* We can't enable contexts until all firmware is loaded */
 	if (HAS_GUC(dev)) {
 		ret = intel_guc_setup(dev);
-		if (ret) {
-			DRM_ERROR("Failed to initialize GuC, error %d\n", ret);
-			ret = -EIO;
+		if (ret)
 			goto out;
 	}
-	}
 
 	/*
 	 * Increment the next seqno by 0x100 so we have a visible break

drivers/gpu/drm/i915/i915_guc_submission.c

@@ -969,7 +969,7 @@ int intel_guc_suspend(struct drm_device *dev)
 	struct intel_context *ctx;
 	u32 data[3];
 
-	if (!i915.enable_guc_submission)
+	if (guc->guc_fw.guc_fw_load_status != GUC_FIRMWARE_SUCCESS)
 		return 0;
 
 	ctx = dev_priv->kernel_context;
@@ -995,7 +995,7 @@ int intel_guc_resume(struct drm_device *dev)
 	struct intel_context *ctx;
 	u32 data[3];
 
-	if (!i915.enable_guc_submission)
+	if (guc->guc_fw.guc_fw_load_status != GUC_FIRMWARE_SUCCESS)
 		return 0;
 
 	ctx = dev_priv->kernel_context;

drivers/gpu/drm/i915/i915_params.c

@@ -53,7 +53,8 @@ struct i915_params i915 __read_mostly = {
 	.verbose_state_checks = 1,
 	.nuclear_pageflip = 0,
 	.edp_vswing = 0,
-	.enable_guc_submission = false,
+	.enable_guc_loading = -1,
+	.enable_guc_submission = 0,
 	.guc_log_level = -1,
 	.enable_dp_mst = true,
 	.inject_load_failure = 0,
@@ -193,8 +194,15 @@ MODULE_PARM_DESC(edp_vswing,
 		 "(0=use value from vbt [default], 1=low power swing(200mV),"
 		 "2=default swing(400mV))");
 
-module_param_named_unsafe(enable_guc_submission, i915.enable_guc_submission, bool, 0400);
-MODULE_PARM_DESC(enable_guc_submission, "Enable GuC submission (default:false)");
+module_param_named_unsafe(enable_guc_loading, i915.enable_guc_loading, int, 0400);
+MODULE_PARM_DESC(enable_guc_loading,
+		"Enable GuC firmware loading "
+		"(-1=auto [default], 0=never, 1=if available, 2=required)");
+
+module_param_named_unsafe(enable_guc_submission, i915.enable_guc_submission, int, 0400);
+MODULE_PARM_DESC(enable_guc_submission,
+		"Enable GuC submission "
+		"(-1=auto, 0=never [default], 1=if available, 2=required)");
 
 module_param_named(guc_log_level, i915.guc_log_level, int, 0400);
 MODULE_PARM_DESC(guc_log_level,

drivers/gpu/drm/i915/i915_params.h

@@ -45,6 +45,8 @@ struct i915_params {
 	int enable_ips;
 	int invert_brightness;
 	int enable_cmd_parser;
+	int enable_guc_loading;
+	int enable_guc_submission;
 	int guc_log_level;
 	int mmio_debug;
 	int edp_vswing;
@@ -56,7 +58,6 @@ struct i915_params {
 	bool load_detect_test;
 	bool reset;
 	bool disable_display;
-	bool enable_guc_submission;
 	bool verbose_state_checks;
 	bool nuclear_pageflip;
 	bool enable_dp_mst;

drivers/gpu/drm/i915/intel_guc_loader.c

@@ -402,49 +402,41 @@ int intel_guc_setup(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_guc_fw *guc_fw = &dev_priv->guc.guc_fw;
-	int retries, err = 0;
+	const char *fw_path = guc_fw->guc_fw_path;
+	int retries, ret, err;
 
-	if (!i915.enable_guc_submission)
-		return 0;
-
-	DRM_DEBUG_DRIVER("GuC fw status: fetch %s, load %s\n",
+	DRM_DEBUG_DRIVER("GuC fw status: path %s, fetch %s, load %s\n",
+		fw_path,
 		intel_guc_fw_status_repr(guc_fw->guc_fw_fetch_status),
 		intel_guc_fw_status_repr(guc_fw->guc_fw_load_status));
 
-	direct_interrupts_to_host(dev_priv);
+	/* Loading forbidden, or no firmware to load? */
+	if (!i915.enable_guc_loading) {
+		err = 0;
+		goto fail;
+	} else if (fw_path == NULL || *fw_path == '\0') {
+		if (*fw_path == '\0')
+			DRM_INFO("No GuC firmware known for this platform\n");
+		err = -ENODEV;
+		goto fail;
+	}
 
-	if (guc_fw->guc_fw_fetch_status == GUC_FIRMWARE_NONE)
-		return 0;
+	/* Fetch failed, or already fetched but failed to load? */
+	if (guc_fw->guc_fw_fetch_status != GUC_FIRMWARE_SUCCESS) {
+		err = -EIO;
+		goto fail;
+	} else if (guc_fw->guc_fw_load_status == GUC_FIRMWARE_FAIL) {
+		err = -ENOEXEC;
+		goto fail;
+	}
 
-	if (guc_fw->guc_fw_fetch_status == GUC_FIRMWARE_SUCCESS &&
-	    guc_fw->guc_fw_load_status == GUC_FIRMWARE_FAIL)
-		return -ENOEXEC;
+	direct_interrupts_to_host(dev_priv);
 
 	guc_fw->guc_fw_load_status = GUC_FIRMWARE_PENDING;
 
-	DRM_DEBUG_DRIVER("GuC fw fetch status %s\n",
-		intel_guc_fw_status_repr(guc_fw->guc_fw_fetch_status));
-
-	switch (guc_fw->guc_fw_fetch_status) {
-	case GUC_FIRMWARE_FAIL:
-		/* something went wrong :( */
-		err = -EIO;
-		goto fail;
-
-	case GUC_FIRMWARE_NONE:
-	case GUC_FIRMWARE_PENDING:
-	default:
-		/* "can't happen" */
-		WARN_ONCE(1, "GuC fw %s invalid guc_fw_fetch_status %s [%d]\n",
-			guc_fw->guc_fw_path,
+	DRM_DEBUG_DRIVER("GuC fw status: fetch %s, load %s\n",
 		intel_guc_fw_status_repr(guc_fw->guc_fw_fetch_status),
-			guc_fw->guc_fw_fetch_status);
-		err = -ENXIO;
-		goto fail;
-
-	case GUC_FIRMWARE_SUCCESS:
-		break;
-	}
+		intel_guc_fw_status_repr(guc_fw->guc_fw_load_status));
 
 	err = i915_guc_submission_init(dev);
 	if (err)
@@ -463,7 +455,7 @@ int intel_guc_setup(struct drm_device *dev)
 		 */
 		err = i915_reset_guc(dev_priv);
 		if (err) {
-			DRM_ERROR("GuC reset failed, err %d\n", err);
+			DRM_ERROR("GuC reset failed: %d\n", err);
 			goto fail;
 		}
 
@@ -474,7 +466,7 @@ int intel_guc_setup(struct drm_device *dev)
 		if (--retries == 0)
 			goto fail;
 
-		DRM_INFO("GuC fw load failed, err %d; will reset and "
+		DRM_INFO("GuC fw load failed: %d; will reset and "
 			 "retry %d more time(s)\n", err, retries);
 	}
 
@@ -497,7 +489,6 @@ int intel_guc_setup(struct drm_device *dev)
 	return 0;
 
 fail:
-	DRM_ERROR("GuC firmware load failed, err %d\n", err);
 	if (guc_fw->guc_fw_load_status == GUC_FIRMWARE_PENDING)
 		guc_fw->guc_fw_load_status = GUC_FIRMWARE_FAIL;
 
@@ -505,7 +496,41 @@ int intel_guc_setup(struct drm_device *dev)
 	i915_guc_submission_disable(dev);
 	i915_guc_submission_fini(dev);
 
-	return err;
+	/*
+	 * We've failed to load the firmware :(
+	 *
+	 * Decide whether to disable GuC submission and fall back to
+	 * execlist mode, and whether to hide the error by returning
+	 * zero or to return -EIO, which the caller will treat as a
+	 * nonfatal error (i.e. it doesn't prevent driver load, but
+	 * marks the GPU as wedged until reset).
+	 */
+	if (i915.enable_guc_loading > 1) {
+		ret = -EIO;
+	} else if (i915.enable_guc_submission > 1) {
+		ret = -EIO;
+	} else {
+		ret = 0;
+	}
+
+	if (err == 0)
+		DRM_INFO("GuC firmware load skipped\n");
+	else if (ret == -EIO)
+		DRM_ERROR("GuC firmware load failed: %d\n", err);
+	else
+		DRM_INFO("GuC firmware load failed: %d\n", err);
+
+	if (i915.enable_guc_submission) {
+		if (fw_path == NULL)
+			DRM_INFO("GuC submission without firmware not supported\n");
+		if (ret == 0)
+			DRM_INFO("Falling back to execlist mode\n");
+		else
+			DRM_ERROR("GuC init failed: %d\n", ret);
+	}
+	i915.enable_guc_submission = 0;
+
+	return ret;
 }
 
 static void guc_fw_fetch(struct drm_device *dev, struct intel_guc_fw *guc_fw)
@@ -644,8 +669,11 @@ void intel_guc_init(struct drm_device *dev)
 	struct intel_guc_fw *guc_fw = &dev_priv->guc.guc_fw;
 	const char *fw_path;
 
-	if (!HAS_GUC_SCHED(dev))
-		i915.enable_guc_submission = false;
+	/* A negative value means "use platform default" */
+	if (i915.enable_guc_loading < 0)
+		i915.enable_guc_loading = HAS_GUC_UCODE(dev);
+	if (i915.enable_guc_submission < 0)
+		i915.enable_guc_submission = HAS_GUC_SCHED(dev);
 
 	if (!HAS_GUC_UCODE(dev)) {
 		fw_path = NULL;
@@ -658,26 +686,21 @@ void intel_guc_init(struct drm_device *dev)
 		guc_fw->guc_fw_major_wanted = 8;
 		guc_fw->guc_fw_minor_wanted = 7;
 	} else {
-		i915.enable_guc_submission = false;
 		fw_path = "";	/* unknown device */
 	}
 
-	if (!i915.enable_guc_submission)
-		return;
-
 	guc_fw->guc_dev = dev;
 	guc_fw->guc_fw_path = fw_path;
 	guc_fw->guc_fw_fetch_status = GUC_FIRMWARE_NONE;
 	guc_fw->guc_fw_load_status = GUC_FIRMWARE_NONE;
 
+	/* Early (and silent) return if GuC loading is disabled */
+	if (!i915.enable_guc_loading)
+		return;
 	if (fw_path == NULL)
 		return;
-
-	if (*fw_path == '\0') {
-		DRM_ERROR("No GuC firmware known for this platform\n");
-		guc_fw->guc_fw_fetch_status = GUC_FIRMWARE_FAIL;
+	if (*fw_path == '\0')
 		return;
-	}
 
 	guc_fw->guc_fw_fetch_status = GUC_FIRMWARE_PENDING;
 	DRM_DEBUG_DRIVER("GuC firmware pending, path %s\n", fw_path);