drm/i915: Try harder to finish the idle-worker

If a worker requeues itself, it may switch to a different kworker pool,
which flush_work() considers as complete. To be strict, we then need to
keep flushing the work until it is no longer pending.

References: https://bugs.freedesktop.org/show_bug.cgi?id=102456
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171006104038.22337-1-chris@chris-wilson.co.uk

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 44aae25..84ab77c 100644 (file)
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -4259,8 +4259,7 @@ fault_irq_set(struct drm_i915_private *i915,
        mutex_unlock(&i915->drm.struct_mutex);
 
        /* Flush idle worker to disarm irq */
-       while (flush_delayed_work(&i915->gt.idle_work))
-               ;
+       drain_delayed_work(&i915->gt.idle_work);
 
        return 0;
 

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index ab8c694..c48700f 100644 (file)
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -4547,8 +4547,7 @@ int i915_gem_suspend(struct drm_i915_private *dev_priv)
        /* As the idle_work is rearming if it detects a race, play safe and
         * repeat the flush until it is definitely idle.
         */
-       while (flush_delayed_work(&dev_priv->gt.idle_work))
-               ;
+       drain_delayed_work(&dev_priv->gt.idle_work);
 
        /* Assert that we sucessfully flushed all the work and
         * reset the GPU back to its idle, low power state.

diff --git a/drivers/gpu/drm/i915/i915_utils.h b/drivers/gpu/drm/i915/i915_utils.h
index c242327..af3d7cc 100644 (file)
--- a/drivers/gpu/drm/i915/i915_utils.h
+++ b/drivers/gpu/drm/i915/i915_utils.h
@@ -124,4 +124,17 @@ static inline void __list_del_many(struct list_head *head,
        WRITE_ONCE(head->next, first);
 }
 
+/*
+ * Wait until the work is finally complete, even if it tries to postpone
+ * by requeueing itself. Note, that if the worker never cancels itself,
+ * we will spin forever.
+ */
+static inline void drain_delayed_work(struct delayed_work *dw)
+{
+       do {
+               while (flush_delayed_work(dw))
+                       ;
+       } while (delayed_work_pending(dw));
+}
+
 #endif /* !__I915_UTILS_H */