New upstream version 18.08upstream/18.08

Change-Id: I32fdf5e5016556d9c0a6d88ddaf1fc468961790a
Signed-off-by: Luca Boccassi <luca.boccassi@gmail.com>

4 files changed, 22 insertions, 27 deletions

diff --git a/lib/librte_ring/Makefile b/lib/librte_ring/Makefile
index bde8907d..21a36770 100644
--- a/lib/librte_ring/Makefile
+++ b/lib/librte_ring/Makefile
@@ -11,7 +11,7 @@ LDLIBS += -lrte_eal
 
 EXPORT_MAP := rte_ring_version.map
 
-LIBABIVER := 1
+LIBABIVER := 2
 
 # all source are stored in SRCS-y
 SRCS-$(CONFIG_RTE_LIBRTE_RING) := rte_ring.c
diff --git a/lib/librte_ring/rte_ring.h b/lib/librte_ring/rte_ring.h
index 253cdc96..7a731d07 100644
--- a/lib/librte_ring/rte_ring.h
+++ b/lib/librte_ring/rte_ring.h
@@ -26,8 +26,9 @@
  * - Bulk dequeue.
  * - Bulk enqueue.
  *
- * Note: the ring implementation is not preemptable. A lcore must not
- * be interrupted by another task that uses the same ring.
+ * Note: the ring implementation is not preemptible. Refer to Programmer's
+ * guide/Environment Abstraction Layer/Multiple pthread/Known Issues/rte_ring
+ * for more information.
  *
  */
 
@@ -62,14 +63,6 @@ enum rte_ring_queue_behavior {
 
 struct rte_memzone; /* forward declaration, so as not to require memzone.h */
 
-#if RTE_CACHE_LINE_SIZE < 128
-#define PROD_ALIGN (RTE_CACHE_LINE_SIZE * 2)
-#define CONS_ALIGN (RTE_CACHE_LINE_SIZE * 2)
-#else
-#define PROD_ALIGN RTE_CACHE_LINE_SIZE
-#define CONS_ALIGN RTE_CACHE_LINE_SIZE
-#endif
-
 /* structure to hold a pair of head/tail values and other metadata */
 struct rte_ring_headtail {
 	volatile uint32_t head;  /**< Prod/consumer head. */
@@ -101,11 +94,15 @@ struct rte_ring {
 	uint32_t mask;           /**< Mask (size-1) of ring. */
 	uint32_t capacity;       /**< Usable size of ring */
 
+	char pad0 __rte_cache_aligned; /**< empty cache line */
+
 	/** Ring producer status. */
-	struct rte_ring_headtail prod __rte_aligned(PROD_ALIGN);
+	struct rte_ring_headtail prod __rte_cache_aligned;
+	char pad1 __rte_cache_aligned; /**< empty cache line */
 
 	/** Ring consumer status. */
-	struct rte_ring_headtail cons __rte_aligned(CONS_ALIGN);
+	struct rte_ring_headtail cons __rte_cache_aligned;
+	char pad2 __rte_cache_aligned; /**< empty cache line */
 };
 
 #define RING_F_SP_ENQ 0x0001 /**< The default enqueue is "single-producer". */
@@ -339,7 +336,7 @@ void rte_ring_dump(FILE *f, const struct rte_ring *r);
 static __rte_always_inline unsigned int
 __rte_ring_do_enqueue(struct rte_ring *r, void * const *obj_table,
 		 unsigned int n, enum rte_ring_queue_behavior behavior,
-		 int is_sp, unsigned int *free_space)
+		 unsigned int is_sp, unsigned int *free_space)
 {
 	uint32_t prod_head, prod_next;
 	uint32_t free_entries;
@@ -381,12 +378,12 @@ end:
 static __rte_always_inline unsigned int
 __rte_ring_do_dequeue(struct rte_ring *r, void **obj_table,
 		 unsigned int n, enum rte_ring_queue_behavior behavior,
-		 int is_sc, unsigned int *available)
+		 unsigned int is_sc, unsigned int *available)
 {
 	uint32_t cons_head, cons_next;
 	uint32_t entries;
 
-	n = __rte_ring_move_cons_head(r, is_sc, n, behavior,
+	n = __rte_ring_move_cons_head(r, (int)is_sc, n, behavior,
 			&cons_head, &cons_next, &entries);
 	if (n == 0)
 		goto end;
diff --git a/lib/librte_ring/rte_ring_c11_mem.h b/lib/librte_ring/rte_ring_c11_mem.h
index 08825ea5..94df3c4a 100644
--- a/lib/librte_ring/rte_ring_c11_mem.h
+++ b/lib/librte_ring/rte_ring_c11_mem.h
@@ -51,7 +51,7 @@ update_tail(struct rte_ring_headtail *ht, uint32_t old_val, uint32_t new_val,
  *   If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
  */
 static __rte_always_inline unsigned int
-__rte_ring_move_prod_head(struct rte_ring *r, int is_sp,
+__rte_ring_move_prod_head(struct rte_ring *r, unsigned int is_sp,
 		unsigned int n, enum rte_ring_queue_behavior behavior,
 		uint32_t *old_head, uint32_t *new_head,
 		uint32_t *free_entries)
@@ -66,14 +66,14 @@ __rte_ring_move_prod_head(struct rte_ring *r, int is_sp,
 
 		*old_head = __atomic_load_n(&r->prod.head,
 					__ATOMIC_ACQUIRE);
-		const uint32_t cons_tail = r->cons.tail;
+
 		/*
 		 *  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).
 		 */
-		*free_entries = (capacity + cons_tail - *old_head);
+		*free_entries = (capacity + r->cons.tail - *old_head);
 
 		/* check that we have enough room in ring */
 		if (unlikely(n > *free_entries))
@@ -133,13 +133,13 @@ __rte_ring_move_cons_head(struct rte_ring *r, int is_sc,
 		n = max;
 		*old_head = __atomic_load_n(&r->cons.head,
 					__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
 		 * and size(ring)-1.
 		 */
-		*entries = (prod_tail - *old_head);
+		*entries = (r->prod.tail - *old_head);
 
 		/* Set the actual entries for dequeue */
 		if (n > *entries)
diff --git a/lib/librte_ring/rte_ring_generic.h b/lib/librte_ring/rte_ring_generic.h
index 5b110425..ea7dbe5b 100644
--- a/lib/librte_ring/rte_ring_generic.h
+++ b/lib/librte_ring/rte_ring_generic.h
@@ -53,7 +53,7 @@ update_tail(struct rte_ring_headtail *ht, uint32_t old_val, uint32_t new_val,
  *   If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
  */
 static __rte_always_inline unsigned int
-__rte_ring_move_prod_head(struct rte_ring *r, int is_sp,
+__rte_ring_move_prod_head(struct rte_ring *r, unsigned int is_sp,
 		unsigned int n, enum rte_ring_queue_behavior behavior,
 		uint32_t *old_head, uint32_t *new_head,
 		uint32_t *free_entries)
@@ -73,14 +73,13 @@ __rte_ring_move_prod_head(struct rte_ring *r, int is_sp,
 		 */
 		rte_smp_rmb();
 
-		const uint32_t cons_tail = r->cons.tail;
 		/*
 		 *  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).
 		 */
-		*free_entries = (capacity + cons_tail - *old_head);
+		*free_entries = (capacity + r->cons.tail - *old_head);
 
 		/* check that we have enough room in ring */
 		if (unlikely(n > *free_entries))
@@ -124,7 +123,7 @@ __rte_ring_move_prod_head(struct rte_ring *r, int is_sp,
  *     If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
  */
 static __rte_always_inline unsigned int
-__rte_ring_move_cons_head(struct rte_ring *r, int is_sc,
+__rte_ring_move_cons_head(struct rte_ring *r, unsigned int is_sc,
 		unsigned int n, enum rte_ring_queue_behavior behavior,
 		uint32_t *old_head, uint32_t *new_head,
 		uint32_t *entries)
@@ -144,13 +143,12 @@ __rte_ring_move_cons_head(struct rte_ring *r, int is_sc,
 		 */
 		rte_smp_rmb();
 
-		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
 		 * and size(ring)-1.
 		 */
-		*entries = (prod_tail - *old_head);
+		*entries = (r->prod.tail - *old_head);
 
 		/* Set the actual entries for dequeue */
 		if (n > *entries)