[PATCH 3/5] ring: use C11 for update_tail

[Stephen Hemminger]

The GCC builtin atomic special case is not needed for updating tail.
The performance is the same with C11 memory model.

Signed-off-by: Stephen Hemminger <stephen at networkplumber.org>
---
 lib/ring/rte_ring_c11_pvt.h  | 24 ------------------------
 lib/ring/rte_ring_elem_pvt.h | 22 ++++++++++++++++++++++
 lib/ring/rte_ring_gcc_pvt.h  | 25 -------------------------
 3 files changed, 22 insertions(+), 49 deletions(-)

diff --git a/lib/ring/rte_ring_c11_pvt.h b/lib/ring/rte_ring_c11_pvt.h
index 8358b0f21f..3258829696 100644
--- a/lib/ring/rte_ring_c11_pvt.h
+++ b/lib/ring/rte_ring_c11_pvt.h
@@ -19,30 +19,6 @@
  * For more information please refer to <rte_ring.h>.
  */
 
-/**
- * @internal This function updates tail values.
- */
-static __rte_always_inline void
-__rte_ring_update_tail(struct rte_ring_headtail *ht, uint32_t old_val,
-		uint32_t new_val, uint32_t single, uint32_t enqueue)
-{
-	RTE_SET_USED(enqueue);
-
-	/*
-	 * If there are other enqueues/dequeues in progress that preceded us,
-	 * we need to wait for them to complete
-	 */
-	if (!single)
-		rte_wait_until_equal_32((uint32_t *)(uintptr_t)&ht->tail, old_val,
-			rte_memory_order_relaxed);
-
-	/*
-	 * R0: Establishes a synchronizing edge with load-acquire of tail at A1.
-	 * Ensures that memory effects by this thread on ring elements array
-	 * is observed by a different thread of the other type.
-	 */
-	rte_atomic_store_explicit(&ht->tail, new_val, rte_memory_order_release);
-}
 /**
  * @internal This is a helper function that moves the producer/consumer head
  *    optimized for single threaded case
diff --git a/lib/ring/rte_ring_elem_pvt.h b/lib/ring/rte_ring_elem_pvt.h
index 9a0170c4f0..a7ff76931b 100644
--- a/lib/ring/rte_ring_elem_pvt.h
+++ b/lib/ring/rte_ring_elem_pvt.h
@@ -299,6 +299,28 @@ __rte_ring_dequeue_elems(struct rte_ring *r, uint32_t cons_head,
 			cons_head & r->mask, esize, num);
 }
 
+static __rte_always_inline void
+__rte_ring_update_tail(struct rte_ring_headtail *ht, uint32_t old_val,
+		uint32_t new_val, uint32_t single, uint32_t enqueue)
+{
+	RTE_SET_USED(enqueue);
+
+	/*
+	 * If there are other enqueues/dequeues in progress that preceded us,
+	 * we need to wait for them to complete
+	 */
+	if (!single)
+		rte_wait_until_equal_32((uint32_t *)(uintptr_t)&ht->tail, old_val,
+			rte_memory_order_relaxed);
+
+	/*
+	 * R0: Establishes a synchronizing edge with load-acquire of tail at A1.
+	 * Ensures that memory effects by this thread on ring elements array
+	 * is observed by a different thread of the other type.
+	 */
+	rte_atomic_store_explicit(&ht->tail, new_val, rte_memory_order_release);
+}
+
 /* Between load and load. there might be cpu reorder in weak model
  * (powerpc/arm).
  * There are 2 choices for the users
diff --git a/lib/ring/rte_ring_gcc_pvt.h b/lib/ring/rte_ring_gcc_pvt.h
index 9033a15647..6b14c1c822 100644
--- a/lib/ring/rte_ring_gcc_pvt.h
+++ b/lib/ring/rte_ring_gcc_pvt.h
@@ -18,31 +18,6 @@
  * For more information please refer to <rte_ring.h>.
  */
 
-/**
- * @internal This function updates tail values.
- */
-static __rte_always_inline void
-__rte_ring_update_tail(struct rte_ring_headtail *ht, uint32_t old_val,
-		uint32_t new_val, uint32_t single, uint32_t enqueue)
-{
-	RTE_SET_USED(enqueue);
-
-	/*
-	 * If there are other enqueues/dequeues in progress that preceded us,
-	 * we need to wait for them to complete
-	 */
-	if (!single)
-		rte_wait_until_equal_32((volatile uint32_t *)(uintptr_t)&ht->tail, old_val,
-			rte_memory_order_relaxed);
-
-	/*
-	 * R0: Establishes a synchronizing edge with load-acquire of tail at A1.
-	 * Ensures that memory effects by this thread on ring elements array
-	 * is observed by a different thread of the other type.
-	 */
-	__atomic_store_n(&ht->tail, new_val, __ATOMIC_RELEASE);
-}
-
 /**
  * @internal This is a helper function that moves the producer/consumer head
  *    for use in multi-thread safe path
-- 
2.53.0