[dpdk-dev] [PATCH v4 3/4] ring: introduce new header file to include common functions

[Jia He <hejianet@gmail.com>]

move the common part of rte_ring.h into rte_ring_generic.h
move the memory barrier part into update_tail()
no functional changes here

Signed-off-by: Jia He <jia.he@hxt-semitech.com>
Suggested-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
Suggested-by: Ananyev, Konstantin <konstantin.ananyev@intel.com>
---
 lib/librte_eventdev/rte_event_ring.h |   6 +-
 lib/librte_ring/Makefile             |   3 +-
 lib/librte_ring/rte_ring.h           | 159 +---------------------------
 lib/librte_ring/rte_ring_generic.h   | 194 +++++++++++++++++++++++++++++++++++
 4 files changed, 202 insertions(+), 160 deletions(-)
 create mode 100644 lib/librte_ring/rte_ring_generic.h

diff --git a/lib/librte_eventdev/rte_event_ring.h b/lib/librte_eventdev/rte_event_ring.h
index ea9b688..3e49458 100644
--- a/lib/librte_eventdev/rte_event_ring.h
+++ b/lib/librte_eventdev/rte_event_ring.h
@@ -126,9 +126,8 @@ rte_event_ring_enqueue_burst(struct rte_event_ring *r,
 		goto end;
 
 	ENQUEUE_PTRS(&r->r, &r[1], prod_head, events, n, struct rte_event);
-	rte_smp_wmb();
 
-	update_tail(&r->r.prod, prod_head, prod_next, 1);
+	update_tail(&r->r.prod, prod_head, prod_next, 1, 1);
 end:
 	if (free_space != NULL)
 		*free_space = free_entries - n;
@@ -168,9 +167,8 @@ rte_event_ring_dequeue_burst(struct rte_event_ring *r,
 		goto end;
 
 	DEQUEUE_PTRS(&r->r, &r[1], cons_head, events, n, struct rte_event);
-	rte_smp_rmb();
 
-	update_tail(&r->r.cons, cons_head, cons_next, 1);
+	update_tail(&r->r.cons, cons_head, cons_next, 1, 0);
 
 end:
 	if (available != NULL)
diff --git a/lib/librte_ring/Makefile b/lib/librte_ring/Makefile
index e34d9d9..c959945 100644
--- a/lib/librte_ring/Makefile
+++ b/lib/librte_ring/Makefile
@@ -45,6 +45,7 @@ LIBABIVER := 1
 SRCS-$(CONFIG_RTE_LIBRTE_RING) := rte_ring.c
 
 # install includes
-SYMLINK-$(CONFIG_RTE_LIBRTE_RING)-include := rte_ring.h
+SYMLINK-$(CONFIG_RTE_LIBRTE_RING)-include := rte_ring.h \
+					rte_ring_generic.h
 
 include $(RTE_SDK)/mk/rte.lib.mk
diff --git a/lib/librte_ring/rte_ring.h b/lib/librte_ring/rte_ring.h
index 3e8085a..519614c 100644
--- a/lib/librte_ring/rte_ring.h
+++ b/lib/librte_ring/rte_ring.h
@@ -356,90 +356,8 @@ void rte_ring_dump(FILE *f, const struct rte_ring *r);
 	} \
 } while (0)
 
-static __rte_always_inline void
-update_tail(struct rte_ring_headtail *ht, uint32_t old_val, uint32_t new_val,
-		uint32_t single)
-{
-	/*
-	 * If there are other enqueues/dequeues in progress that preceded us,
-	 * we need to wait for them to complete
-	 */
-	if (!single)
-		while (unlikely(ht->tail != old_val))
-			rte_pause();
-
-	ht->tail = new_val;
-}
-
-/**
- * @internal This function updates the producer head for enqueue
- *
- * @param r
- *   A pointer to the ring structure
- * @param is_sp
- *   Indicates whether multi-producer path is needed or not
- * @param n
- *   The number of elements we will want to enqueue, i.e. how far should the
- *   head be moved
- * @param behavior
- *   RTE_RING_QUEUE_FIXED:    Enqueue a fixed number of items from a ring
- *   RTE_RING_QUEUE_VARIABLE: Enqueue as many items as possible from ring
- * @param old_head
- *   Returns head value as it was before the move, i.e. where enqueue starts
- * @param new_head
- *   Returns the current/new head value i.e. where enqueue finishes
- * @param free_entries
- *   Returns the amount of free space in the ring BEFORE head was moved
- * @return
- *   Actual number of objects enqueued.
- *   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,
-		unsigned int n, enum rte_ring_queue_behavior behavior,
-		uint32_t *old_head, uint32_t *new_head,
-		uint32_t *free_entries)
-{
-	const uint32_t capacity = r->capacity;
-	unsigned int max = n;
-	int success;
-
-	do {
-		/* Reset n to the initial burst count */
-		n = max;
-
-		*old_head = r->prod.head;
-
-		/* add rmb barrier to avoid load/load reorder in weak
-		 * memory model. It is noop on x86 */
-		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);
-
-		/* check that we have enough room in ring */
-		if (unlikely(n > *free_entries))
-			n = (behavior == RTE_RING_QUEUE_FIXED) ?
-					0 : *free_entries;
-
-		if (n == 0)
-			return 0;
-
-		*new_head = *old_head + n;
-		if (is_sp)
-			r->prod.head = *new_head, success = 1;
-		else
-			success = rte_atomic32_cmpset(&r->prod.head,
-					*old_head, *new_head);
-	} while (unlikely(success == 0));
-	return n;
-}
+/* Move common functions to generic file */
+#include "rte_ring_generic.h"
 
 /**
  * @internal Enqueue several objects on the ring
@@ -475,9 +393,8 @@ __rte_ring_do_enqueue(struct rte_ring *r, void * const *obj_table,
 		goto end;
 
 	ENQUEUE_PTRS(r, &r[1], prod_head, obj_table, n, void *);
-	rte_smp_wmb();
 
-	update_tail(&r->prod, prod_head, prod_next, is_sp);
+	update_tail(&r->prod, prod_head, prod_next, is_sp, 1);
 end:
 	if (free_space != NULL)
 		*free_space = free_entries - n;
@@ -485,73 +402,6 @@ __rte_ring_do_enqueue(struct rte_ring *r, void * const *obj_table,
 }
 
 /**
- * @internal This function updates the consumer head for dequeue
- *
- * @param r
- *   A pointer to the ring structure
- * @param is_sc
- *   Indicates whether multi-consumer path is needed or not
- * @param n
- *   The number of elements we will want to enqueue, i.e. how far should the
- *   head be moved
- * @param behavior
- *   RTE_RING_QUEUE_FIXED:    Dequeue a fixed number of items from a ring
- *   RTE_RING_QUEUE_VARIABLE: Dequeue as many items as possible from ring
- * @param old_head
- *   Returns head value as it was before the move, i.e. where dequeue starts
- * @param new_head
- *   Returns the current/new head value i.e. where dequeue finishes
- * @param entries
- *   Returns the number of entries in the ring BEFORE head was moved
- * @return
- *   - Actual number of objects dequeued.
- *     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,
-		unsigned int n, enum rte_ring_queue_behavior behavior,
-		uint32_t *old_head, uint32_t *new_head,
-		uint32_t *entries)
-{
-	unsigned int max = n;
-	int success;
-
-	/* move cons.head atomically */
-	do {
-		/* Restore n as it may change every loop */
-		n = max;
-
-		*old_head = r->cons.head;
-
-		/* add rmb barrier to avoid load/load reorder in weak
-		 * memory model. It is noop on x86 */
-		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);
-
-		/* Set the actual entries for dequeue */
-		if (n > *entries)
-			n = (behavior == RTE_RING_QUEUE_FIXED) ? 0 : *entries;
-
-		if (unlikely(n == 0))
-			return 0;
-
-		*new_head = *old_head + n;
-		if (is_sc)
-			r->cons.head = *new_head, success = 1;
-		else
-			success = rte_atomic32_cmpset(&r->cons.head, *old_head,
-					*new_head);
-	} while (unlikely(success == 0));
-	return n;
-}
-
-/**
  * @internal Dequeue several objects from the ring
  *
  * @param r
@@ -585,9 +435,8 @@ __rte_ring_do_dequeue(struct rte_ring *r, void **obj_table,
 		goto end;
 
 	DEQUEUE_PTRS(r, &r[1], cons_head, obj_table, n, void *);
-	rte_smp_rmb();
 
-	update_tail(&r->cons, cons_head, cons_next, is_sc);
+	update_tail(&r->cons, cons_head, cons_next, is_sc, 0);
 
 end:
 	if (available != NULL)
diff --git a/lib/librte_ring/rte_ring_generic.h b/lib/librte_ring/rte_ring_generic.h
new file mode 100644
index 0000000..3f49ac1
--- /dev/null
+++ b/lib/librte_ring/rte_ring_generic.h
@@ -0,0 +1,194 @@
+/*-
+ *   BSD LICENSE
+ *
+ *   Copyright(c) 2017 hxt-semitech. All rights reserved.
+ *
+ *   Redistribution and use in source and binary forms, with or without
+ *   modification, are permitted provided that the following conditions
+ *   are met:
+ *
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in
+ *       the documentation and/or other materials provided with the
+ *       distribution.
+ *     * Neither the name of hxt-semitech nor the names of its
+ *       contributors may be used to endorse or promote products derived
+ *       from this software without specific prior written permission.
+ *
+ *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _RTE_RING_GENERIC_H_
+#define _RTE_RING_GENERIC_H_
+
+static __rte_always_inline void
+update_tail(struct rte_ring_headtail *ht, uint32_t old_val, uint32_t new_val,
+		uint32_t single, uint32_t enqueue)
+{
+	if (enqueue)
+		rte_smp_wmb();
+	else
+		rte_smp_rmb();
+	/*
+	 * If there are other enqueues/dequeues in progress that preceded us,
+	 * we need to wait for them to complete
+	 */
+	if (!single)
+		while (unlikely(ht->tail != old_val))
+			rte_pause();
+
+	ht->tail = new_val;
+}
+
+/**
+ * @internal This function updates the producer head for enqueue
+ *
+ * @param r
+ *   A pointer to the ring structure
+ * @param is_sp
+ *   Indicates whether multi-producer path is needed or not
+ * @param n
+ *   The number of elements we will want to enqueue, i.e. how far should the
+ *   head be moved
+ * @param behavior
+ *   RTE_RING_QUEUE_FIXED:    Enqueue a fixed number of items from a ring
+ *   RTE_RING_QUEUE_VARIABLE: Enqueue as many items as possible from ring
+ * @param old_head
+ *   Returns head value as it was before the move, i.e. where enqueue starts
+ * @param new_head
+ *   Returns the current/new head value i.e. where enqueue finishes
+ * @param free_entries
+ *   Returns the amount of free space in the ring BEFORE head was moved
+ * @return
+ *   Actual number of objects enqueued.
+ *   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,
+		unsigned int n, enum rte_ring_queue_behavior behavior,
+		uint32_t *old_head, uint32_t *new_head,
+		uint32_t *free_entries)
+{
+	const uint32_t capacity = r->capacity;
+	unsigned int max = n;
+	int success;
+
+	do {
+		/* Reset n to the initial burst count */
+		n = max;
+
+		*old_head = r->prod.head;
+
+		/* add rmb barrier to avoid load/load reorder in weak
+		 * memory model. It is noop on x86
+		 */
+		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);
+
+		/* check that we have enough room in ring */
+		if (unlikely(n > *free_entries))
+			n = (behavior == RTE_RING_QUEUE_FIXED) ?
+					0 : *free_entries;
+
+		if (n == 0)
+			return 0;
+
+		*new_head = *old_head + n;
+		if (is_sp)
+			r->prod.head = *new_head, success = 1;
+		else
+			success = rte_atomic32_cmpset(&r->prod.head,
+					*old_head, *new_head);
+	} while (unlikely(success == 0));
+	return n;
+}
+
+/**
+ * @internal This function updates the consumer head for dequeue
+ *
+ * @param r
+ *   A pointer to the ring structure
+ * @param is_sc
+ *   Indicates whether multi-consumer path is needed or not
+ * @param n
+ *   The number of elements we will want to enqueue, i.e. how far should the
+ *   head be moved
+ * @param behavior
+ *   RTE_RING_QUEUE_FIXED:    Dequeue a fixed number of items from a ring
+ *   RTE_RING_QUEUE_VARIABLE: Dequeue as many items as possible from ring
+ * @param old_head
+ *   Returns head value as it was before the move, i.e. where dequeue starts
+ * @param new_head
+ *   Returns the current/new head value i.e. where dequeue finishes
+ * @param entries
+ *   Returns the number of entries in the ring BEFORE head was moved
+ * @return
+ *   - Actual number of objects dequeued.
+ *     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,
+		unsigned int n, enum rte_ring_queue_behavior behavior,
+		uint32_t *old_head, uint32_t *new_head,
+		uint32_t *entries)
+{
+	unsigned int max = n;
+	int success;
+
+	/* move cons.head atomically */
+	do {
+		/* Restore n as it may change every loop */
+		n = max;
+
+		*old_head = r->cons.head;
+
+		/* add rmb barrier to avoid load/load reorder in weak
+		 * memory model. It is noop on x86
+		 */
+		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);
+
+		/* Set the actual entries for dequeue */
+		if (n > *entries)
+			n = (behavior == RTE_RING_QUEUE_FIXED) ? 0 : *entries;
+
+		if (unlikely(n == 0))
+			return 0;
+
+		*new_head = *old_head + n;
+		if (is_sc)
+			r->cons.head = *new_head, success = 1;
+		else
+			success = rte_atomic32_cmpset(&r->cons.head, *old_head,
+					*new_head);
+	} while (unlikely(success == 0));
+	return n;
+}
+
+#endif /* _RTE_RING_GENERIC_H_ */
-- 
2.7.4