[PATCH 22/22] drm/i915/gt: Protect context lifetime with RCU

[Chris Wilson]

Allow a brief period for continued access to a dead intel_context by
deferring the release of the struct until after an RCU grace period.
As we are using a dedicated slab cache for the contexts, we can defer
the release of the slab pages via RCU, with the caveat that individual
structs may be reused from the freelist within an RCU grace period. To
handle that, we have to avoid clearing members of the zombie struct.

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gt/intel_context.c | 47 ++++++++++++++++++-------
 1 file changed, 34 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index 52db2bde44a3..ba26952a5a53 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -22,7 +22,7 @@ static struct i915_global_context {
 
 static struct intel_context *intel_context_alloc(void)
 {
-	return kmem_cache_zalloc(global.slab_ce, GFP_KERNEL);
+	return kmem_cache_alloc(global.slab_ce, GFP_KERNEL);
 }
 
 void intel_context_free(struct intel_context *ce)
@@ -158,12 +158,12 @@ void intel_context_unpin(struct intel_context *ce)
 	/*
 	 * Once released, we may asynchronously drop the active reference.
 	 * As that may be the only reference keeping the context alive,
-	 * take an extra now so that it is not freed before we finish
+	 * hold onto RCU so that it is not freed before we finish
 	 * dereferencing it.
 	 */
-	intel_context_get(ce);
+	rcu_read_lock();
 	intel_context_active_release(ce);
-	intel_context_put(ce);
+	rcu_read_unlock();
 }
 
 static int __context_pin_state(struct i915_vma *vma)
@@ -279,6 +279,21 @@ static int __intel_context_active(struct i915_active *active)
 	return err;
 }
 
+static void __intel_context_ctor(void *arg)
+{
+	struct intel_context *ce = arg;
+
+	INIT_LIST_HEAD(&ce->signal_link);
+	INIT_LIST_HEAD(&ce->signals);
+
+	atomic_set(&ce->pin_count, 0);
+	mutex_init(&ce->pin_mutex);
+
+	ce->active_count = 0;
+	i915_active_init(&ce->active,
+			 __intel_context_active, __intel_context_retire);
+}
+
 void
 intel_context_init(struct intel_context *ce,
 		   struct intel_engine_cs *engine)
@@ -292,18 +307,18 @@ intel_context_init(struct intel_context *ce,
 	ce->ops = engine->cops;
 	ce->sseu = engine->sseu;
 	ce->ring = __intel_context_ring_size(SZ_4K);
+	ce->flags = 0;
+	ce->tag = 0;
+	ce->wa_bb_page = 0;
 
-	ewma_runtime_init(&ce->runtime.avg);
+	memset(&ce->runtime, 0, sizeof(ce->runtime));
 
 	ce->vm = i915_vm_get(engine->gt->vm);
+	ce->gem_context = NULL;
+	ce->timeline = NULL;
 
-	INIT_LIST_HEAD(&ce->signal_link);
-	INIT_LIST_HEAD(&ce->signals);
-
-	mutex_init(&ce->pin_mutex);
-
-	i915_active_init(&ce->active,
-			 __intel_context_active, __intel_context_retire);
+	GEM_BUG_ON(atomic_read(&ce->pin_count));
+	GEM_BUG_ON(ce->active_count);
 }
 
 void intel_context_fini(struct intel_context *ce)
@@ -333,7 +348,13 @@ static struct i915_global_context global = { {
 
 int __init i915_global_context_init(void)
 {
-	global.slab_ce = KMEM_CACHE(intel_context, SLAB_HWCACHE_ALIGN);
+	global.slab_ce =
+		kmem_cache_create("intel_context",
+				  sizeof(struct intel_context),
+				  __alignof__(struct intel_context),
+				  SLAB_HWCACHE_ALIGN |
+				  SLAB_TYPESAFE_BY_RCU,
+				  __intel_context_ctor);
 	if (!global.slab_ce)
 		return -ENOMEM;
 
-- 
2.20.1