If we enable RCU for the requests (providing a grace period where we can
inspect a "dead" request before it is freed), we can allow callers to
carefully perform lockless lookup of an active request.
However, by enabling deferred freeing of requests, we can potentially
hog a lot of memory when dealing with tens of thousands of requests per
second - with a quick insertion of the a synchronize_rcu() inside our
shrinker callback, that issue disappears.
Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
---
drivers/gpu/drm/i915/i915_gem.c | 3 ++-
drivers/gpu/drm/i915/i915_gem_request.c | 2 +-
drivers/gpu/drm/i915/i915_gem_request.h | 24 +++++++++++++++++++++++-
drivers/gpu/drm/i915/i915_gem_shrinker.c | 1 +
4 files changed, 27 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index c169574758d5..696ada3891ed 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -4222,7 +4222,8 @@ i915_gem_load(struct drm_device *dev)
dev_priv->requests =
kmem_cache_create("i915_gem_request",
sizeof(struct drm_i915_gem_request), 0,
- SLAB_HWCACHE_ALIGN,
+ SLAB_HWCACHE_ALIGN |
+ SLAB_DESTROY_BY_RCU,
NULL);
INIT_LIST_HEAD(&dev_priv->context_list);
diff --git a/drivers/gpu/drm/i915/i915_gem_request.c b/drivers/gpu/drm/i915/i915_gem_request.c
index 4e087143b1d2..380a5963d957 100644
--- a/drivers/gpu/drm/i915/i915_gem_request.c
+++ b/drivers/gpu/drm/i915/i915_gem_request.c
@@ -335,7 +335,7 @@ static void __i915_gem_request_retire_active(struct drm_i915_gem_request *req)
* and pass along the auxiliary information.
*/
INIT_LIST_HEAD(&active->link);
- active->request = NULL;
+ rcu_assign_pointer(active->request, NULL);
active->retire(active, req);
}
diff --git a/drivers/gpu/drm/i915/i915_gem_request.h b/drivers/gpu/drm/i915/i915_gem_request.h
index 4eb15ed9205e..fae85b111a1e 100644
--- a/drivers/gpu/drm/i915/i915_gem_request.h
+++ b/drivers/gpu/drm/i915/i915_gem_request.h
@@ -139,6 +139,12 @@ i915_gem_request_get(struct drm_i915_gem_request *req)
return to_request(fence_get(&req->fence));
}
+static inline struct drm_i915_gem_request *
+i915_gem_request_get_rcu(struct drm_i915_gem_request *req)
+{
+ return to_request(fence_get_rcu(&req->fence));
+}
+
static inline void
i915_gem_request_put(struct drm_i915_gem_request *req)
{
@@ -243,7 +249,23 @@ i915_gem_request_mark_active(struct drm_i915_gem_request *request,
struct i915_gem_active *active)
{
list_move(&active->link, &request->active_list);
- active->request = request;
+ rcu_assign_pointer(active->request, request);
+}
+
+static inline struct drm_i915_gem_request *
+i915_gem_active_get_request_rcu(struct i915_gem_active *active)
+{
+ do {
+ struct drm_i915_gem_request *request;
+
+ request = rcu_dereference(active->request);
+ if (request == NULL)
+ return NULL;
+
+ request = i915_gem_request_get_rcu(request);
+ if (request)
+ return request;
+ } while (1);
}
#endif /* I915_GEM_REQUEST_H */
diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c
index c561ed2b8287..03a8bbb3e31e 100644
--- a/drivers/gpu/drm/i915/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c
@@ -142,6 +142,7 @@ i915_gem_shrink(struct drm_i915_private *dev_priv,
}
i915_gem_retire_requests(dev_priv->dev);
+ synchronize_rcu(); /* expedite the grace period to free the requests */
return count;
}
--
2.6.4
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
