From 6ca9a2beb54a385c8cc5e39a9d2ef49945896c64 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 13 Dec 2017 13:43:47 +0000
Subject: [PATCH] drm/i915: Unwind i915_gem_init() failure
Mime-version: 1.0
Content-type: text/plain; charset=UTF-8
Content-transfer-encoding: 8bit
Git-commit: 6ca9a2beb54a385c8cc5e39a9d2ef49945896c64
Patch-mainline: v4.16-rc1
References: FATE#322643 bsc#1055900

Since Michal introduced new user controllable errors other than -EIO
during i915_gem_init(), we need to actually unwind on the error path as
we have to abort the module load (and we expect to do so cleanly!).

As we now teardown key state and then mark the driver as wedged (on
EIO), we have to be careful to not allow ourselves to resume and
unwedge, thus attempting to use the uninitialised driver.

V2: Try not to free driver state for the suppressed EIO
V3: Use load-fault-injection to test both error/recovery paths.

References: 8620eb1dbbf2 ("drm/i915/uc: Don't use -EIO to report missing firmware")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Sagar Arun Kamble <sagar.a.kamble@intel.com>
Reviewed-by: Michał Winiarski <michal.winiarski@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171213134347.4608-1-chris@chris-wilson.co.uk
Acked-by: Takashi Iwai <tiwai@suse.de>

---
 drivers/gpu/drm/i915/i915_gem.c |   80 +++++++++++++++++++++++++++++++++-------
 1 file changed, 66 insertions(+), 14 deletions(-)

--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -4865,7 +4865,8 @@ void i915_gem_resume(struct drm_i915_pri
 	i915_gem_restore_gtt_mappings(i915);
 	i915_gem_restore_fences(i915);
 
-	/* As we didn't flush the kernel context before suspend, we cannot
+	/*
+	 * As we didn't flush the kernel context before suspend, we cannot
 	 * guarantee that the context image is complete. So let's just reset
 	 * it and start again.
 	 */
@@ -4886,8 +4887,10 @@ out_unlock:
 	return;
 
 err_wedged:
-	DRM_ERROR("failed to re-initialize GPU, declaring wedged!\n");
-	i915_gem_set_wedged(i915);
+	if (!i915_terminally_wedged(&i915->gpu_error)) {
+		DRM_ERROR("failed to re-initialize GPU, declaring wedged!\n");
+		i915_gem_set_wedged(i915);
+	}
 	goto out_unlock;
 }
 
@@ -5170,22 +5173,28 @@ int i915_gem_init(struct drm_i915_privat
 	intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
 
 	ret = i915_gem_init_ggtt(dev_priv);
-	if (ret)
-		goto out_unlock;
+	if (ret) {
+		GEM_BUG_ON(ret == -EIO);
+		goto err_unlock;
+	}
 
 	ret = i915_gem_contexts_init(dev_priv);
-	if (ret)
-		goto out_unlock;
+	if (ret) {
+		GEM_BUG_ON(ret == -EIO);
+		goto err_ggtt;
+	}
 
 	ret = intel_engines_init(dev_priv);
-	if (ret)
-		goto out_unlock;
+	if (ret) {
+		GEM_BUG_ON(ret == -EIO);
+		goto err_context;
+	}
 
 	intel_init_gt_powersave(dev_priv);
 
 	ret = i915_gem_init_hw(dev_priv);
 	if (ret)
-		goto out_unlock;
+		goto err_pm;
 
 	/*
 	 * Despite its name intel_init_clock_gating applies both display
@@ -5199,9 +5208,53 @@ int i915_gem_init(struct drm_i915_privat
 	intel_init_clock_gating(dev_priv);
 
 	ret = __intel_engines_record_defaults(dev_priv);
-out_unlock:
+	if (ret)
+		goto err_init_hw;
+
+	if (i915_inject_load_failure()) {
+		ret = -ENODEV;
+		goto err_init_hw;
+	}
+
+	if (i915_inject_load_failure()) {
+		ret = -EIO;
+		goto err_init_hw;
+	}
+
+	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
+	mutex_unlock(&dev_priv->drm.struct_mutex);
+
+	return 0;
+
+	/*
+	 * Unwinding is complicated by that we want to handle -EIO to mean
+	 * disable GPU submission but keep KMS alive. We want to mark the
+	 * HW as irrevisibly wedged, but keep enough state around that the
+	 * driver doesn't explode during runtime.
+	 */
+err_init_hw:
+	i915_gem_wait_for_idle(dev_priv, I915_WAIT_LOCKED);
+	i915_gem_contexts_lost(dev_priv);
+	intel_uc_fini_hw(dev_priv);
+err_pm:
+	if (ret != -EIO) {
+		intel_cleanup_gt_powersave(dev_priv);
+		i915_gem_cleanup_engines(dev_priv);
+	}
+err_context:
+	if (ret != -EIO)
+		i915_gem_contexts_fini(dev_priv);
+err_ggtt:
+err_unlock:
+	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
+	mutex_unlock(&dev_priv->drm.struct_mutex);
+
+	if (ret != -EIO)
+		i915_gem_cleanup_userptr(dev_priv);
+
 	if (ret == -EIO) {
-		/* Allow engine initialisation to fail by marking the GPU as
+		/*
+		 * Allow engine initialisation to fail by marking the GPU as
 		 * wedged. But we only want to do this where the GPU is angry,
 		 * for all other failure, such as an allocation failure, bail.
 		 */
@@ -5211,9 +5264,8 @@ out_unlock:
 		}
 		ret = 0;
 	}
-	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
-	mutex_unlock(&dev_priv->drm.struct_mutex);
 
+	i915_gem_drain_freed_objects(dev_priv);
 	return ret;
 }