X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=lib%2Flibrte_ring%2Frte_ring_c11_mem.h;h=0fb73a33717307c781da38b5a0e8797cabbed141;hb=9135705bb81df0b529821a121004c41f176995ff;hp=cb3f82b1a4230054c40845e7f93136d0f465504c;hpb=e8ed5056c8747cd5d95a41749e48987ad44dc9b3;p=dpdk.git

diff --git a/lib/librte_ring/rte_ring_c11_mem.h b/lib/librte_ring/rte_ring_c11_mem.h
index cb3f82b1a4..0fb73a3371 100644
--- a/lib/librte_ring/rte_ring_c11_mem.h
+++ b/lib/librte_ring/rte_ring_c11_mem.h
@@ -57,18 +57,25 @@ __rte_ring_move_prod_head(struct rte_ring *r, unsigned int is_sp,
 		uint32_t *free_entries)
 {
 	const uint32_t capacity = r->capacity;
+	uint32_t cons_tail;
 	unsigned int max = n;
 	int success;
 
+	*old_head = __atomic_load_n(&r->prod.head, __ATOMIC_RELAXED);
 	do {
 		/* Reset n to the initial burst count */
 		n = max;
 
-		*old_head = __atomic_load_n(&r->prod.head,
+		/* Ensure the head is read before tail */
+		__atomic_thread_fence(__ATOMIC_ACQUIRE);
+
+		/* load-acquire synchronize with store-release of ht->tail
+		 * in update_tail.
+		 */
+		cons_tail = __atomic_load_n(&r->cons.tail,
 					__ATOMIC_ACQUIRE);
-		const uint32_t cons_tail = r->cons.tail;
-		/*
-		 *  The subtraction is done between two unsigned 32bits value
+
+		/* The subtraction is done between two unsigned 32bits value
 		 * (the result is always modulo 32 bits even if we have
 		 * *old_head > cons_tail). So 'free_entries' is always between 0
 		 * and capacity (which is < size).
@@ -87,9 +94,10 @@ __rte_ring_move_prod_head(struct rte_ring *r, unsigned int is_sp,
 		if (is_sp)
 			r->prod.head = *new_head, success = 1;
 		else
+			/* on failure, *old_head is updated */
 			success = __atomic_compare_exchange_n(&r->prod.head,
 					old_head, *new_head,
-					0, __ATOMIC_ACQUIRE,
+					0, __ATOMIC_RELAXED,
 					__ATOMIC_RELAXED);
 	} while (unlikely(success == 0));
 	return n;
@@ -125,15 +133,24 @@ __rte_ring_move_cons_head(struct rte_ring *r, int is_sc,
 		uint32_t *entries)
 {
 	unsigned int max = n;
+	uint32_t prod_tail;
 	int success;
 
 	/* move cons.head atomically */
+	*old_head = __atomic_load_n(&r->cons.head, __ATOMIC_RELAXED);
 	do {
 		/* Restore n as it may change every loop */
 		n = max;
-		*old_head = __atomic_load_n(&r->cons.head,
+
+		/* Ensure the head is read before tail */
+		__atomic_thread_fence(__ATOMIC_ACQUIRE);
+
+		/* this load-acquire synchronize with store-release of ht->tail
+		 * in update_tail.
+		 */
+		prod_tail = __atomic_load_n(&r->prod.tail,
 					__ATOMIC_ACQUIRE);
-		const uint32_t prod_tail = r->prod.tail;
+
 		/* The subtraction is done between two unsigned 32bits value
 		 * (the result is always modulo 32 bits even if we have
 		 * cons_head > prod_tail). So 'entries' is always between 0
@@ -152,9 +169,10 @@ __rte_ring_move_cons_head(struct rte_ring *r, int is_sc,
 		if (is_sc)
 			r->cons.head = *new_head, success = 1;
 		else
+			/* on failure, *old_head will be updated */
 			success = __atomic_compare_exchange_n(&r->cons.head,
 							old_head, *new_head,
-							0, __ATOMIC_ACQUIRE,
+							0, __ATOMIC_RELAXED,
 							__ATOMIC_RELAXED);
 	} while (unlikely(success == 0));
 	return n;