[PATCH 2/2] drm/i915: Return immediately if trylock fails for direct-reclaim

[Chris Wilson]

Ignore trying to shrink from i915 if we fail to acquire the struct_mutex
in the shrinker while performing direct-reclaim. The trade-off being
(much) lower latency for non-i915 clients at an increased risk of being
unable to obtain a page from direct-reclaim without hitting the
oom-notifier. The proviso being that we still keep trying to hard
obtain the lock for oom so that we can reap under heavy memory pressure.

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h          |  7 +++---
 drivers/gpu/drm/i915/i915_gem_gtt.c      |  2 +-
 drivers/gpu/drm/i915/i915_gem_shrinker.c | 29 ++++++++++++------------
 3 files changed, 20 insertions(+), 18 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 7fa2a405c5fe..17a017645c5d 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2899,9 +2899,9 @@ i915_gem_object_unpin_pages(struct drm_i915_gem_object *obj)
 	__i915_gem_object_unpin_pages(obj);
 }
 
-enum i915_mm_subclass { /* lockdep subclass for obj->mm.lock */
+enum i915_mm_subclass { /* lockdep subclass for obj->mm.lock/struct_mutex */
 	I915_MM_NORMAL = 0,
-	I915_MM_SHRINKER
+	I915_MM_SHRINKER /* called "recursively" from direct-reclaim-esque */
 };
 
 void __i915_gem_object_put_pages(struct drm_i915_gem_object *obj,
@@ -3187,7 +3187,8 @@ unsigned long i915_gem_shrink(struct drm_i915_private *i915,
 unsigned long i915_gem_shrink_all(struct drm_i915_private *i915);
 void i915_gem_shrinker_register(struct drm_i915_private *i915);
 void i915_gem_shrinker_unregister(struct drm_i915_private *i915);
-void i915_gem_shrinker_taints_mutex(struct mutex *mutex);
+void i915_gem_shrinker_taints_mutex(struct drm_i915_private *i915,
+				    struct mutex *mutex);
 
 /* i915_gem_tiling.c */
 static inline bool i915_gem_object_needs_bit17_swizzle(struct drm_i915_gem_object *obj)
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index d4c5973ea33d..d1dd538ba1b3 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -483,7 +483,7 @@ static void i915_address_space_init(struct i915_address_space *vm,
 	 * attempt holding the lock is immediately reported by lockdep.
 	 */
 	mutex_init(&vm->mutex);
-	i915_gem_shrinker_taints_mutex(&vm->mutex);
+	i915_gem_shrinker_taints_mutex(vm->i915, &vm->mutex);
 
 	GEM_BUG_ON(!vm->total);
 	drm_mm_init(&vm->mm, 0, vm->total);
diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c
index ea90d3a0d511..ce81c28be295 100644
--- a/drivers/gpu/drm/i915/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c
@@ -36,7 +36,9 @@
 #include "i915_drv.h"
 #include "i915_trace.h"
 
-static bool shrinker_lock(struct drm_i915_private *i915, bool *unlock)
+static bool shrinker_lock(struct drm_i915_private *i915,
+			  unsigned int flags,
+			  bool *unlock)
 {
 	switch (mutex_trylock_recursive(&i915->drm.struct_mutex)) {
 	case MUTEX_TRYLOCK_RECURSIVE:
@@ -45,15 +47,11 @@ static bool shrinker_lock(struct drm_i915_private *i915, bool *unlock)
 
 	case MUTEX_TRYLOCK_FAILED:
 		*unlock = false;
-		preempt_disable();
-		do {
-			cpu_relax();
-			if (mutex_trylock(&i915->drm.struct_mutex)) {
-				*unlock = true;
-				break;
-			}
-		} while (!need_resched());
-		preempt_enable();
+		if (flags & I915_SHRINK_ACTIVE) {
+			mutex_lock_nested(&i915->drm.struct_mutex,
+					  I915_MM_SHRINKER);
+			*unlock = true;
+		}
 		return *unlock;
 
 	case MUTEX_TRYLOCK_SUCCESS:
@@ -160,7 +158,7 @@ i915_gem_shrink(struct drm_i915_private *i915,
 	unsigned long scanned = 0;
 	bool unlock;
 
-	if (!shrinker_lock(i915, &unlock))
+	if (!shrinker_lock(i915, flags, &unlock))
 		return 0;
 
 	/*
@@ -357,7 +355,7 @@ i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc)
 
 	sc->nr_scanned = 0;
 
-	if (!shrinker_lock(i915, &unlock))
+	if (!shrinker_lock(i915, 0, &unlock))
 		return SHRINK_STOP;
 
 	freed = i915_gem_shrink(i915,
@@ -397,7 +395,7 @@ shrinker_lock_uninterruptible(struct drm_i915_private *i915, bool *unlock,
 	do {
 		if (i915_gem_wait_for_idle(i915,
 					   0, MAX_SCHEDULE_TIMEOUT) == 0 &&
-		    shrinker_lock(i915, unlock))
+		    shrinker_lock(i915, 0, unlock))
 			break;
 
 		schedule_timeout_killable(1);
@@ -533,13 +531,16 @@ void i915_gem_shrinker_unregister(struct drm_i915_private *i915)
 	unregister_shrinker(&i915->mm.shrinker);
 }
 
-void i915_gem_shrinker_taints_mutex(struct mutex *mutex)
+void i915_gem_shrinker_taints_mutex(struct drm_i915_private *i915,
+				    struct mutex *mutex)
 {
 	if (!IS_ENABLED(CONFIG_LOCKDEP))
 		return;
 
 	fs_reclaim_acquire(GFP_KERNEL);
+	mutex_lock_nested(&i915->drm.struct_mutex, I915_MM_SHRINKER);
 	mutex_lock(mutex);
 	mutex_unlock(mutex);
+	mutex_unlock(&i915->drm.struct_mutex);
 	fs_reclaim_release(GFP_KERNEL);
 }
-- 
2.20.1