[Intel-gfx] [PATCH v2] drm/i915: Clean up associated VMAs on context destruction

[Tvrtko Ursulin]

From: Tvrtko Ursulin <tvrtko.ursulin at intel.com>

Prevent leaking VMAs and PPGTT VMs when objects are imported
via flink.

Scenario is that any VMAs created by the importer will be left
dangling after the importer exits, or destroys the PPGTT context
with which they are associated.

This is caused by object destruction not running when the
importer closes the buffer object handle due the reference held
by the exporter. This also leaks the VM since the VMA has a
reference on it.

In practice these leaks can be observed by stopping and starting
the X server on a kernel with fbcon compiled in. Every time
X server exits another VMA will be leaked against the fbcon's
frame buffer object.

Also on systems where flink buffer sharing is used extensively,
like Android, this leak has even more serious consequences.

This version is takes a general approach from the  earlier work
by Rafael Barabalho (drm/i915: Clean-up PPGTT on context
destruction) and tries to incorporate the subsequent discussion
between Chris Wilson and Daniel Vetter.

On context destruction a worker thread is scheduled to unbind
all inactive VMAs for this VM.

v2:

Removed immediate cleanup on object retire - it was causing a
recursive VMA unbind via i915_gem_object_wait_rendering. And
it is in fact not even needed since by definition context
cleanup worker runs only after the last context reference has
been dropped, hence all VMAs against the VM belonging to the
context are already on the inactive list.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
Testcase: igt/gem_ppgtt.c/flink-and-exit-vma-leak
Cc: Daniel Vetter <daniel.vetter at ffwll.ch>
Cc: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Rafael Barbalho <rafael.barbalho at intel.com>
Cc: Michel Thierry <michel.thierry at intel.com>
---
 drivers/gpu/drm/i915/i915_gem_context.c | 50 +++++++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/i915_gem_gtt.h     |  2 ++
 2 files changed, 52 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 74aa0c9929ba..714d71bae572 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -133,6 +133,49 @@ static int get_context_size(struct drm_device *dev)
 	return ret;
 }
 
+static void
+i915_gem_context_cleanup_worker(struct work_struct *work)
+{
+	struct i915_hw_ppgtt *ppgtt = container_of(work, typeof(*ppgtt),
+						   cleanup_work);
+	struct drm_device *dev = ppgtt->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct i915_vma *vma, *next;
+	bool was_interruptible;
+
+	mutex_lock(&dev->struct_mutex);
+	was_interruptible = dev_priv->mm.interruptible;
+
+	WARN_ON(!list_empty(&ppgtt->base.active_list));
+
+	list_for_each_entry_safe(vma, next, &ppgtt->base.inactive_list,
+				 mm_list) {
+		dev_priv->mm.interruptible = false;
+		if (WARN_ON(i915_vma_unbind(vma)))
+			break;
+	}
+
+	i915_ppgtt_put(ppgtt);
+
+	dev_priv->mm.interruptible = was_interruptible;
+	mutex_unlock(&dev->struct_mutex);
+}
+
+static void i915_gem_context_clean(struct intel_context *ctx)
+{
+	struct i915_hw_ppgtt *ppgtt = ctx->ppgtt;
+
+	if (!ppgtt)
+		return;
+
+	/*
+	 * Unbind all inactive VMAs for this VM, but do it asynchronously.
+	 */
+	INIT_WORK(&ppgtt->cleanup_work, i915_gem_context_cleanup_worker);
+	i915_ppgtt_get(ppgtt);
+	schedule_work(&ppgtt->cleanup_work);
+}
+
 void i915_gem_context_free(struct kref *ctx_ref)
 {
 	struct intel_context *ctx = container_of(ctx_ref, typeof(*ctx), ref);
@@ -142,6 +185,13 @@ void i915_gem_context_free(struct kref *ctx_ref)
 	if (i915.enable_execlists)
 		intel_lr_context_free(ctx);
 
+	/*
+	 * This context is going away and we need to remove all VMAs still
+	 * around. This is to handle imported shared objects for which
+	 * destructor did not run when their handles were closed.
+	 */
+	i915_gem_context_clean(ctx);
+
 	i915_ppgtt_put(ctx->ppgtt);
 
 	if (ctx->legacy_hw_ctx.rcs_state)
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 430cc283d3c9..c7426b76cd1d 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -375,6 +375,8 @@ struct i915_hw_ppgtt {
 
 	struct drm_i915_file_private *file_priv;
 
+	struct work_struct cleanup_work;
+
 	gen6_pte_t __iomem *pd_addr;
 
 	int (*enable)(struct i915_hw_ppgtt *ppgtt);
-- 
2.5.1