drm/i915: Release i915_gem_context from a worker

The only reason for this really is the i915_gem_engines->fence
callback engines_notify(), which exists purely as a fairly funky
reference counting scheme for that. Otherwise all other callers are
from process context, and generally fairly benign locking context.

Unfortunately untangling that requires some major surgery, and we have
a few i915_gem_context reference counting bugs that need fixing, and
they blow in the current hardirq calling context, so we need a
stop-gap measure.

Put a FIXME comment in when this should be removable again.

v2: Fix mock_context(), noticed by intel-gfx-ci.

Acked-by: Acked-by: Maarten Lankhorst <[email protected]>
Signed-off-by: Daniel Vetter <[email protected]>
Cc: Jon Bloomfield <[email protected]>
Cc: Chris Wilson <[email protected]>
Cc: Maarten Lankhorst <[email protected]>
Cc: Joonas Lahtinen <[email protected]>
Cc: Daniel Vetter <[email protected]>
Cc: "Thomas Hellström" <[email protected]>
Cc: Matthew Auld <[email protected]>
Cc: Lionel Landwerlin <[email protected]>
Cc: Dave Airlie <[email protected]>
Cc: Jason Ekstrand <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

3 files changed, 24 insertions, 2 deletions

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index fd169cf2f75a..051bc357ff65 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -986,9 +986,10 @@ free_engines:
 	return err;
 }
 
-void i915_gem_context_release(struct kref *ref)
+static void i915_gem_context_release_work(struct work_struct *work)
 {
-	struct i915_gem_context *ctx = container_of(ref, typeof(*ctx), ref);
+	struct i915_gem_context *ctx = container_of(work, typeof(*ctx),
+						    release_work);
 
 	trace_i915_context_free(ctx);
 	GEM_BUG_ON(!i915_gem_context_is_closed(ctx));
@@ -1002,6 +1003,13 @@ void i915_gem_context_release(struct kref *ref)
 	kfree_rcu(ctx, rcu);
 }
 
+void i915_gem_context_release(struct kref *ref)
+{
+	struct i915_gem_context *ctx = container_of(ref, typeof(*ctx), ref);
+
+	queue_work(ctx->i915->wq, &ctx->release_work);
+}
+
 static inline struct i915_gem_engines *
 __context_engines_static(const struct i915_gem_context *ctx)
 {
@@ -1303,6 +1311,7 @@ i915_gem_create_context(struct drm_i915_private *i915,
 	ctx->sched = pc->sched;
 	mutex_init(&ctx->mutex);
 	INIT_LIST_HEAD(&ctx->link);
+	INIT_WORK(&ctx->release_work, i915_gem_context_release_work);
 
 	spin_lock_init(&ctx->stale.lock);
 	INIT_LIST_HEAD(&ctx->stale.engines);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
index 94c03a97cb77..0c38789bd4a8 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
@@ -289,6 +289,18 @@ struct i915_gem_context {
 	struct kref ref;
 
 	/**
+	 * @release_work:
+	 *
+	 * Work item for deferred cleanup, since i915_gem_context_put() tends to
+	 * be called from hardirq context.
+	 *
+	 * FIXME: The only real reason for this is &i915_gem_engines.fence, all
+	 * other callers are from process context and need at most some mild
+	 * shuffling to pull the i915_gem_context_put() call out of a spinlock.
+	 */
+	struct work_struct release_work;
+
+	/**
 	 * @rcu: rcu_head for deferred freeing.
 	 */
 	struct rcu_head rcu;
diff --git a/drivers/gpu/drm/i915/gem/selftests/mock_context.c b/drivers/gpu/drm/i915/gem/selftests/mock_context.c
index fee070df1c97..067d68a6fe4c 100644
--- a/drivers/gpu/drm/i915/gem/selftests/mock_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/mock_context.c
@@ -23,6 +23,7 @@ mock_context(struct drm_i915_private *i915,
 	kref_init(&ctx->ref);
 	INIT_LIST_HEAD(&ctx->link);
 	ctx->i915 = i915;
+	INIT_WORK(&ctx->release_work, i915_gem_context_release_work);
 
 	mutex_init(&ctx->mutex);