[Intel-gfx] [PATCH v2 4/5] drm/i915: Spin for struct_mutex inside shrinker

[Chris Wilson]

Having resolved whether or not we would deadlock upon a call to
mutex_lock(&dev->struct_mutex), we can then spin for the contended
struct_mutex if we are not the owner. We cannot afford to simply block
and wait for the mutex, as the owner may itself be waiting for the
allocator -- i.e. a cyclic deadlock. This should significantly improve
the chance of running the shrinker for other processes whilst the GPU is
busy.

A more balanced approach would be to optimistically spin whilst the
mutex owner was on the cpu and there was an opportunity to acquire the
mutex for ourselves quickly. However, that requires support from
kernel/locking/ and a new mutex_spin_trylock() primitive.

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala at linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen at linux.intel.com>
---
 drivers/gpu/drm/i915/i915_gem_shrinker.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c
index 58f27369183c..1032f98add11 100644
--- a/drivers/gpu/drm/i915/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c
@@ -38,16 +38,21 @@
 static bool shrinker_lock(struct drm_i915_private *dev_priv, bool *unlock)
 {
 	switch (mutex_trylock_recursive(&dev_priv->drm.struct_mutex)) {
-	case MUTEX_TRYLOCK_FAILED:
-		return false;
-
-	case MUTEX_TRYLOCK_SUCCESS:
-		*unlock = true;
-		return true;
-
 	case MUTEX_TRYLOCK_RECURSIVE:
 		*unlock = false;
 		return true;
+
+	case MUTEX_TRYLOCK_FAILED:
+		do {
+			cpu_relax();
+			if (mutex_trylock(&dev_priv->drm.struct_mutex)) {
+	case MUTEX_TRYLOCK_SUCCESS:
+				*unlock = true;
+				return true;
+			}
+		} while (!need_resched());
+
+		return false;
 	}
 
 	BUG();
-- 
2.11.0