drm/i915: Prevent machine hang from Broxton's vtd w/a and error capture

Since capturing the error state requires fiddling around with the GGTT
to read arbitrary buffers and is itself run under stop_machine(), it
deadlocks the machine (effectively a hard hang) when run in conjunction
with Broxton's VTd workaround to serialize GGTT access.

v2: Store the ERR_PTR in first_error so that the error can be reported
to the user via sysfs.
v3: Mention the quirk in dmesg (using info as per usual)

Fixes: 0ef34ad6222a ("drm/i915: Serialize GTT/Aperture accesses on BXT")
Signed-off-by: Chris Wilson <[e-mail]>
Cc: Jon Bloomfield <[e-mail]>
Cc: John Harrison <[e-mail]>
Cc: Tvrtko Ursulin <[e-mail]>
Cc: Joonas Lahtinen <[e-mail]>
Cc: Daniel Vetter <[e-mail]>
Reviewed-by: Joonas Lahtinen <[e-mail]>
Link: https://patchwork.freedesktop.org/patch/msgid/[e-mail]
(cherry picked from commit fb6f0b64e455b207a636346588e65bf9598d30eb)
Signed-off-by: Joonas Lahtinen <[e-mail]>

drivers/gpu/drm/i915/i915_gem_gtt.c

···
 		ggtt->vm.insert_page    = bxt_vtd_ggtt_insert_page__BKL;
 		if (ggtt->vm.clear_range != nop_clear_range)
 			ggtt->vm.clear_range = bxt_vtd_ggtt_clear_range__BKL;
+
+		/* Prevent recursively calling stop_machine() and deadlocks. */
+		dev_info(dev_priv->drm.dev,
+			 "Disabling error capture for VT-d workaround\n");
+		i915_disable_error_state(dev_priv, -ENODEV);
 	}
 
 	ggtt->invalidate = gen6_ggtt_invalidate;

drivers/gpu/drm/i915/i915_gpu_error.c

···
 		return 0;
 	}
 
+	if (IS_ERR(error))
+		return PTR_ERR(error);
+
 	if (*error->error_msg)
 		err_printf(m, "%s\n", error->error_msg);
 	err_printf(m, "Kernel: " UTS_RELEASE "\n");
···
 	error = i915_capture_gpu_state(i915);
 	if (!error) {
 		DRM_DEBUG_DRIVER("out of memory, not capturing error state\n");
+		i915_disable_error_state(i915, -ENOMEM);
 		return;
 	}
 
···
 	i915->gpu_error.first_error = NULL;
 	spin_unlock_irq(&i915->gpu_error.lock);
 
-	i915_gpu_state_put(error);
+	if (!IS_ERR(error))
+		i915_gpu_state_put(error);
+}
+
+void i915_disable_error_state(struct drm_i915_private *i915, int err)
+{
+	spin_lock_irq(&i915->gpu_error.lock);
+	if (!i915->gpu_error.first_error)
+		i915->gpu_error.first_error = ERR_PTR(err);
+	spin_unlock_irq(&i915->gpu_error.lock);
 }

drivers/gpu/drm/i915/i915_gpu_error.h

···
 
 struct i915_gpu_state *i915_first_error_state(struct drm_i915_private *i915);
 void i915_reset_error_state(struct drm_i915_private *i915);
+void i915_disable_error_state(struct drm_i915_private *i915, int err);
 
 #else
 
···
 static inline struct i915_gpu_state *
 i915_first_error_state(struct drm_i915_private *i915)
 {
-	return NULL;
+	return ERR_PTR(-ENODEV);
 }
 
 static inline void i915_reset_error_state(struct drm_i915_private *i915)
+{
+}
+
+static inline void i915_disable_error_state(struct drm_i915_private *i915,
+					    int err)
 {
 }