For 64-bit architectures, doubling the head and tail index widths greatly
increases the time it takes for them to wrap-around (with current CPU
speeds, it won't happen within the author's lifetime). This is important in
avoiding the ABA problem -- in which a thread mistakes reading the same
tail index in two accesses to mean that the ring was not modified in the
intervening time -- in the upcoming non-blocking ring implementation. Using
a 64-bit index makes the possibility of this occurring effectively zero.

I tested this commit's performance impact with an x86_64 build on a
dual-socket Xeon E5-2699 v4 using ring_perf_autotest, and the change made
no significant difference -- the few differences appear to be system noise.
(The test ran on isolcpus cores using a tickless scheduler, but some
variation was stll observed.) Each test was run three times and the results
were averaged:

                                  | 64b head/tail cycle cost minus
             Test                 |     32b head/tail cycle cost
------------------------------------------------------------------
SP/SC single enq/dequeue          | 0.33
MP/MC single enq/dequeue          | 0.00
SP/SC burst enq/dequeue (size 8)  | 0.00
MP/MC burst enq/dequeue (size 8)  | 1.00
SP/SC burst enq/dequeue (size 32) | 0.00
MP/MC burst enq/dequeue (size 32) | -1.00
SC empty dequeue                  | 0.01
MC empty dequeue                  | 0.00

Single lcore:
SP/SC bulk enq/dequeue (size 8)   | -0.36
MP/MC bulk enq/dequeue (size 8)   | 0.99
SP/SC bulk enq/dequeue (size 32)  | -0.40
MP/MC bulk enq/dequeue (size 32)  | -0.57

Two physical cores:
SP/SC bulk enq/dequeue (size 8)   | -0.49
MP/MC bulk enq/dequeue (size 8)   | 0.19
SP/SC bulk enq/dequeue (size 32)  | -0.28
MP/MC bulk enq/dequeue (size 32)  | -0.62

Two NUMA nodes:
SP/SC bulk enq/dequeue (size 8)   | 3.25
MP/MC bulk enq/dequeue (size 8)   | 1.87
SP/SC bulk enq/dequeue (size 32)  | -0.44
MP/MC bulk enq/dequeue (size 32)  | -1.10

An earlier version of this patch changed the head and tail indexes to
uint64_t, but that caused a performance drop on 32-bit builds. With
uintptr_t, no performance difference is observed on an i686 build.

Signed-off-by: Gage Eads <redacted>
---
 lib/librte_eventdev/rte_event_ring.h |  6 +++---
 lib/librte_ring/rte_ring.c           | 10 +++++-----
 lib/librte_ring/rte_ring.h           | 20 ++++++++++----------
 lib/librte_ring/rte_ring_generic.h   | 16 +++++++++-------
 4 files changed, 27 insertions(+), 25 deletions(-)

diff --git a/lib/librte_eventdev/rte_event_ring.h b/lib/librte_eventdev/rte_event_ring.h
index 827a3209e..eae70f904 100644
--- a/lib/librte_eventdev/rte_event_ring.h
+++ b/lib/librte_eventdev/rte_event_ring.h

@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2016-2017 Intel Corporation
+ * Copyright(c) 2016-2019 Intel Corporation
  */
 
 /**

@@ -88,7 +88,7 @@ rte_event_ring_enqueue_burst(struct rte_event_ring *r,
 		const struct rte_event *events,
 		unsigned int n, uint16_t *free_space)
 {
-	uint32_t prod_head, prod_next;
+	uintptr_t prod_head, prod_next;
 	uint32_t free_entries;
 
 	n = __rte_ring_move_prod_head(&r->r, r->r.prod.single, n,

@@ -129,7 +129,7 @@ rte_event_ring_dequeue_burst(struct rte_event_ring *r,
 		struct rte_event *events,
 		unsigned int n, uint16_t *available)
 {
-	uint32_t cons_head, cons_next;
+	uintptr_t cons_head, cons_next;
 	uint32_t entries;
 
 	n = __rte_ring_move_cons_head(&r->r, r->r.cons.single, n,

diff --git a/lib/librte_ring/rte_ring.c b/lib/librte_ring/rte_ring.c
index d215acecc..b15ee0eb3 100644
--- a/lib/librte_ring/rte_ring.c
+++ b/lib/librte_ring/rte_ring.c

@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: BSD-3-Clause
  *
- * Copyright (c) 2010-2015 Intel Corporation
+ * Copyright (c) 2010-2019 Intel Corporation
  * Copyright (c) 2007,2008 Kip Macy kmacy@freebsd.org
  * All rights reserved.
  * Derived from FreeBSD's bufring.h

@@ -227,10 +227,10 @@ rte_ring_dump(FILE *f, const struct rte_ring *r)
 	fprintf(f, "  flags=%x\n", r->flags);
 	fprintf(f, "  size=%"PRIu32"\n", r->size);
 	fprintf(f, "  capacity=%"PRIu32"\n", r->capacity);
-	fprintf(f, "  ct=%"PRIu32"\n", r->cons.tail);
-	fprintf(f, "  ch=%"PRIu32"\n", r->cons.head);
-	fprintf(f, "  pt=%"PRIu32"\n", r->prod.tail);
-	fprintf(f, "  ph=%"PRIu32"\n", r->prod.head);
+	fprintf(f, "  ct=%"PRIuPTR"\n", r->cons.tail);
+	fprintf(f, "  ch=%"PRIuPTR"\n", r->cons.head);
+	fprintf(f, "  pt=%"PRIuPTR"\n", r->prod.tail);
+	fprintf(f, "  ph=%"PRIuPTR"\n", r->prod.head);
 	fprintf(f, "  used=%u\n", rte_ring_count(r));
 	fprintf(f, "  avail=%u\n", rte_ring_free_count(r));
 }

diff --git a/lib/librte_ring/rte_ring.h b/lib/librte_ring/rte_ring.h
index af5444a9f..12af64e13 100644
--- a/lib/librte_ring/rte_ring.h
+++ b/lib/librte_ring/rte_ring.h

@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: BSD-3-Clause
  *
- * Copyright (c) 2010-2017 Intel Corporation
+ * Copyright (c) 2010-2019 Intel Corporation
  * Copyright (c) 2007-2009 Kip Macy kmacy@freebsd.org
  * All rights reserved.
  * Derived from FreeBSD's bufring.h

@@ -65,8 +65,8 @@ struct rte_memzone; /* forward declaration, so as not to require memzone.h */
 
 /* structure to hold a pair of head/tail values and other metadata */
 struct rte_ring_headtail {
-	volatile uint32_t head;  /**< Prod/consumer head. */
-	volatile uint32_t tail;  /**< Prod/consumer tail. */
+	volatile uintptr_t head;  /**< Prod/consumer head. */
+	volatile uintptr_t tail;  /**< Prod/consumer tail. */
 	uint32_t single;         /**< True if single prod/cons */
 };