[Intel-gfx] [PATCH 1/2] drm/i915: Add smp_rmb() to busy ioctl's RCU dance

[Chris Wilson]

In the debate as to whether the second read of active->request is
ordered after the dependent reads of the first read of active->request,
just give in and throw a smp_rmb() in there so that ordering of loads is
assured.

v2: Explain the manual smp_rmb()

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Daniel Vetter <daniel.vetter at ffwll.ch>
Reviewed-by: Daniel Vetter <daniel.vetter at ffwll.ch>
---
 drivers/gpu/drm/i915/i915_gem.c         | 25 ++++++++++++++++++++-----
 drivers/gpu/drm/i915/i915_gem_request.h |  3 +++
 2 files changed, 23 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index f4f8eaa90f2a..654f0b015f97 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3735,7 +3735,7 @@ i915_gem_object_ggtt_unpin_view(struct drm_i915_gem_object *obj,
 	i915_vma_unpin(i915_gem_obj_to_ggtt_view(obj, view));
 }
 
-static __always_inline unsigned __busy_read_flag(unsigned int id)
+static __always_inline unsigned int __busy_read_flag(unsigned int id)
 {
 	/* Note that we could alias engines in the execbuf API, but
 	 * that would be very unwise as it prevents userspace from
@@ -3753,7 +3753,7 @@ static __always_inline unsigned int __busy_write_id(unsigned int id)
 	return id;
 }
 
-static __always_inline unsigned
+static __always_inline unsigned int
 __busy_set_if_active(const struct i915_gem_active *active,
 		     unsigned int (*flag)(unsigned int id))
 {
@@ -3770,19 +3770,34 @@ __busy_set_if_active(const struct i915_gem_active *active,
 
 		id = request->engine->exec_id;
 
-		/* Check that the pointer wasn't reassigned and overwritten. */
+		/* Check that the pointer wasn't reassigned and overwritten.
+		 *
+		 * In __i915_gem_active_get_rcu(), we enforce ordering between
+		 * the first rcu pointer dereference (imposing a
+		 * read-dependency only on access through the pointer) and
+		 * the second lockless access through the memory barrier
+		 * following a successful atomic_inc_not_zero(). Here there
+		 * is no such barrier, and so we must manually insert an
+		 * explicit read barrier to ensure that the following
+		 * access occurs after all the loads through the first
+		 * pointer.
+		 *
+		 * The corresponding write barrier is part of
+		 * rcu_assign_pointer().
+		 */
+		smp_rmb();
 		if (request == rcu_access_pointer(active->request))
 			return flag(id);
 	} while (1);
 }
 
-static inline unsigned
+static __always_inline unsigned int
 busy_check_reader(const struct i915_gem_active *active)
 {
 	return __busy_set_if_active(active, __busy_read_flag);
 }
 
-static inline unsigned
+static __always_inline unsigned int
 busy_check_writer(const struct i915_gem_active *active)
 {
 	return __busy_set_if_active(active, __busy_write_id);
diff --git a/drivers/gpu/drm/i915/i915_gem_request.h b/drivers/gpu/drm/i915/i915_gem_request.h
index 3496e28785e7..b2456dede3ad 100644
--- a/drivers/gpu/drm/i915/i915_gem_request.h
+++ b/drivers/gpu/drm/i915/i915_gem_request.h
@@ -497,6 +497,9 @@ __i915_gem_active_get_rcu(const struct i915_gem_active *active)
 		 * incremented) then the following read for rcu_access_pointer()
 		 * must occur after the atomic operation and so confirm
 		 * that this request is the one currently being tracked.
+		 *
+		 * The corresponding write barrier is part of
+		 * rcu_assign_pointer().
 		 */
 		if (!request || request == rcu_access_pointer(active->request))
 			return rcu_pointer_handoff(request);
-- 
2.8.1