drm/i915/guc: capture GuC logs if FW fails to load

We're currently deleting the GuC logs if the FW fails to load, but those
are still useful to understand why the loading failed. Keeping the
object around allows us to access them after driver load is completed.

v2: keep the object around instead of using kernel memory (chris)
    don't store the logs in the gpu_error struct (Chris)
    add a check on guc_log_level to avoid snapshotting empty logs

v3: use separate debugfs for error log (Chris)

v4: rebased

v5: clean up obj selection, move err_load inside guc_log, move err_load
    cleanup, rename functions (Michal)

v6: move obj back to intel_guc, move functions to intel_uc.c, don't
    clear obj on new GuC load, free object only if enable_guc_loading
    is set (Michal)

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Oscar Mateo <oscar.mateo@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1495475428-19295-1-git-send-email-daniele.ceraolospurio@intel.com
Reviewed-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Tested-by: Michel Thierry <michel.thierry@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>

3 files changed, 51 insertions, 16 deletions

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index c51c56af0013..0615237d1cea 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -2586,27 +2586,37 @@ static int i915_guc_stage_pool(struct seq_file *m, void *data)
 
 static int i915_guc_log_dump(struct seq_file *m, void *data)
 {
-	struct drm_i915_private *dev_priv = node_to_i915(m->private);
-	struct drm_i915_gem_object *obj;
-	int i = 0, pg;
-
-	if (!dev_priv->guc.log.vma)
-		return 0;
+	struct drm_info_node *node = m->private;
+	struct drm_i915_private *dev_priv = node_to_i915(node);
+	bool dump_load_err = !!node->info_ent->data;
+	struct drm_i915_gem_object *obj = NULL;
+	u32 *log;
+	int i = 0;
 
-	obj = dev_priv->guc.log.vma->obj;
-	for (pg = 0; pg < obj->base.size / PAGE_SIZE; pg++) {
-		u32 *log = kmap_atomic(i915_gem_object_get_page(obj, pg));
+	if (dump_load_err)
+		obj = dev_priv->guc.load_err_log;
+	else if (dev_priv->guc.log.vma)
+		obj = dev_priv->guc.log.vma->obj;
 
-		for (i = 0; i < PAGE_SIZE / sizeof(u32); i += 4)
-			seq_printf(m, "0x%08x 0x%08x 0x%08x 0x%08x\n",
-				   *(log + i), *(log + i + 1),
-				   *(log + i + 2), *(log + i + 3));
+	if (!obj)
+		return 0;
 
-		kunmap_atomic(log);
+	log = i915_gem_object_pin_map(obj, I915_MAP_WC);
+	if (IS_ERR(log)) {
+		DRM_DEBUG("Failed to pin object\n");
+		seq_puts(m, "(log data unaccessible)\n");
+		return PTR_ERR(log);
 	}
 
+	for (i = 0; i < obj->base.size / sizeof(u32); i += 4)
+		seq_printf(m, "0x%08x 0x%08x 0x%08x 0x%08x\n",
+			   *(log + i), *(log + i + 1),
+			   *(log + i + 2), *(log + i + 3));
+
 	seq_putc(m, '\n');
 
+	i915_gem_object_unpin_map(obj);
+
 	return 0;
 }
 
@@ -4791,6 +4801,7 @@ static const struct drm_info_list i915_debugfs_list[] = {
 	{"i915_guc_info", i915_guc_info, 0},
 	{"i915_guc_load_status", i915_guc_load_status_info, 0},
 	{"i915_guc_log_dump", i915_guc_log_dump, 0},
+	{"i915_guc_load_err_log_dump", i915_guc_log_dump, 0, (void *)1},
 	{"i915_guc_stage_pool", i915_guc_stage_pool, 0},
 	{"i915_huc_load_status", i915_huc_load_status_info, 0},
 	{"i915_frequency_info", i915_frequency_info, 0},
diff --git a/drivers/gpu/drm/i915/intel_uc.c b/drivers/gpu/drm/i915/intel_uc.c
index d17029c57433..7a7b07de28a3 100644
--- a/drivers/gpu/drm/i915/intel_uc.c
+++ b/drivers/gpu/drm/i915/intel_uc.c
@@ -288,6 +288,23 @@ static void guc_init_send_regs(struct intel_guc *guc)
 	guc->send_regs.fw_domains = fw_domains;
 }
 
+static void guc_capture_load_err_log(struct intel_guc *guc)
+{
+	if (!guc->log.vma || i915.guc_log_level < 0)
+		return;
+
+	if (!guc->load_err_log)
+		guc->load_err_log = i915_gem_object_get(guc->log.vma->obj);
+
+	return;
+}
+
+static void guc_free_load_err_log(struct intel_guc *guc)
+{
+	if (guc->load_err_log)
+		i915_gem_object_put(guc->load_err_log);
+}
+
 static int guc_enable_communication(struct intel_guc *guc)
 {
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
@@ -367,11 +384,11 @@ int intel_uc_init_hw(struct drm_i915_private *dev_priv)
 
 	/* Did we succeded or run out of retries? */
 	if (ret)
-		goto err_submission;
+		goto err_log_capture;
 
 	ret = guc_enable_communication(guc);
 	if (ret)
-		goto err_submission;
+		goto err_log_capture;
 
 	intel_guc_auth_huc(dev_priv);
 	if (i915.enable_guc_submission) {
@@ -397,6 +414,8 @@ int intel_uc_init_hw(struct drm_i915_private *dev_priv)
 err_interrupts:
 	guc_disable_communication(guc);
 	gen9_disable_guc_interrupts(dev_priv);
+err_log_capture:
+	guc_capture_load_err_log(guc);
 err_submission:
 	if (i915.enable_guc_submission)
 		i915_guc_submission_fini(dev_priv);
@@ -422,6 +441,8 @@ void intel_uc_fini_hw(struct drm_i915_private *dev_priv)
 	if (!i915.enable_guc_loading)
 		return;
 
+	guc_free_load_err_log(&dev_priv->guc);
+
 	if (i915.enable_guc_submission)
 		i915_guc_submission_disable(dev_priv);
 
diff --git a/drivers/gpu/drm/i915/intel_uc.h b/drivers/gpu/drm/i915/intel_uc.h
index fb1d640a1b04..69daf4c01cd0 100644
--- a/drivers/gpu/drm/i915/intel_uc.h
+++ b/drivers/gpu/drm/i915/intel_uc.h
@@ -175,6 +175,9 @@ struct intel_guc {
 	struct intel_guc_log log;
 	struct intel_guc_ct ct;
 
+	/* Log snapshot if GuC errors during load */
+	struct drm_i915_gem_object *load_err_log;
+
 	/* intel_guc_recv interrupt related state */
 	bool interrupts_enabled;