[PATCH v4 5/5] mempool/ring: add non-blocking ring handlers

[Gage Eads <gage.eads@intel.com>]

These handlers allow an application to create a mempool based on the
non-blocking ring, with any combination of single/multi producer/consumer.

Also, add a note to the programmer's guide's "known issues" section.

Signed-off-by: Gage Eads <gage.eads@intel.com>
Acked-by: Andrew Rybchenko <arybchenko@solarflare.com>
---
 doc/guides/prog_guide/env_abstraction_layer.rst |  5 +++
 drivers/mempool/ring/Makefile                   |  1 +
 drivers/mempool/ring/meson.build                |  2 +
 drivers/mempool/ring/rte_mempool_ring.c         | 58 +++++++++++++++++++++++--
 4 files changed, 63 insertions(+), 3 deletions(-)

diff --git a/doc/guides/prog_guide/env_abstraction_layer.rst b/doc/guides/prog_guide/env_abstraction_layer.rst
index 929d76dba..fcafd1cff 100644
--- a/doc/guides/prog_guide/env_abstraction_layer.rst
+++ b/doc/guides/prog_guide/env_abstraction_layer.rst
@@ -541,6 +541,11 @@ Known Issues
 
   5. It MUST not be used by multi-producer/consumer pthreads, whose scheduling policies are SCHED_FIFO or SCHED_RR.
 
+  Alternatively, x86_64 applications can use the non-blocking ring mempool handler. When considering it, note that:
+
+  - it is currently limited to the x86_64 platform, because it uses a function (16-byte compare-and-swap) that is not yet available on other platforms.
+  - it has worse average-case performance than the non-preemptive rte_ring, but software caching (e.g. the mempool cache) can mitigate this by reducing the number of handler operations.
+
 + rte_timer
 
   Running  ``rte_timer_manage()`` on a non-EAL pthread is not allowed. However, resetting/stopping the timer from a non-EAL pthread is allowed.
diff --git a/drivers/mempool/ring/Makefile b/drivers/mempool/ring/Makefile
index ddab522fe..012ba6966 100644
--- a/drivers/mempool/ring/Makefile
+++ b/drivers/mempool/ring/Makefile
@@ -10,6 +10,7 @@ LIB = librte_mempool_ring.a
 
 CFLAGS += -O3
 CFLAGS += $(WERROR_FLAGS)
+CFLAGS += -DALLOW_EXPERIMENTAL_API
 LDLIBS += -lrte_eal -lrte_mempool -lrte_ring
 
 EXPORT_MAP := rte_mempool_ring_version.map
diff --git a/drivers/mempool/ring/meson.build b/drivers/mempool/ring/meson.build
index a021e908c..b1cb673cc 100644
--- a/drivers/mempool/ring/meson.build
+++ b/drivers/mempool/ring/meson.build
@@ -1,4 +1,6 @@
 # SPDX-License-Identifier: BSD-3-Clause
 # Copyright(c) 2017 Intel Corporation
 
+allow_experimental_apis = true
+
 sources = files('rte_mempool_ring.c')
diff --git a/drivers/mempool/ring/rte_mempool_ring.c b/drivers/mempool/ring/rte_mempool_ring.c
index bc123fc52..013dac3bc 100644
--- a/drivers/mempool/ring/rte_mempool_ring.c
+++ b/drivers/mempool/ring/rte_mempool_ring.c
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2010-2016 Intel Corporation
+ * Copyright(c) 2010-2019 Intel Corporation
  */
 
 #include <stdio.h>
@@ -47,11 +47,11 @@ common_ring_get_count(const struct rte_mempool *mp)
 
 
 static int
-common_ring_alloc(struct rte_mempool *mp)
+__common_ring_alloc(struct rte_mempool *mp, int rg_flags)
 {
-	int rg_flags = 0, ret;
 	char rg_name[RTE_RING_NAMESIZE];
 	struct rte_ring *r;
+	int ret;
 
 	ret = snprintf(rg_name, sizeof(rg_name),
 		RTE_MEMPOOL_MZ_FORMAT, mp->name);
@@ -82,6 +82,18 @@ common_ring_alloc(struct rte_mempool *mp)
 	return 0;
 }
 
+static int
+common_ring_alloc(struct rte_mempool *mp)
+{
+	return __common_ring_alloc(mp, 0);
+}
+
+static int
+common_ring_alloc_nb(struct rte_mempool *mp)
+{
+	return __common_ring_alloc(mp, RING_F_NB);
+}
+
 static void
 common_ring_free(struct rte_mempool *mp)
 {
@@ -130,7 +142,47 @@ static const struct rte_mempool_ops ops_sp_mc = {
 	.get_count = common_ring_get_count,
 };
 
+static const struct rte_mempool_ops ops_mp_mc_nb = {
+	.name = "ring_mp_mc_nb",
+	.alloc = common_ring_alloc_nb,
+	.free = common_ring_free,
+	.enqueue = common_ring_mp_enqueue,
+	.dequeue = common_ring_mc_dequeue,
+	.get_count = common_ring_get_count,
+};
+
+static const struct rte_mempool_ops ops_sp_sc_nb = {
+	.name = "ring_sp_sc_nb",
+	.alloc = common_ring_alloc_nb,
+	.free = common_ring_free,
+	.enqueue = common_ring_sp_enqueue,
+	.dequeue = common_ring_sc_dequeue,
+	.get_count = common_ring_get_count,
+};
+
+static const struct rte_mempool_ops ops_mp_sc_nb = {
+	.name = "ring_mp_sc_nb",
+	.alloc = common_ring_alloc_nb,
+	.free = common_ring_free,
+	.enqueue = common_ring_mp_enqueue,
+	.dequeue = common_ring_sc_dequeue,
+	.get_count = common_ring_get_count,
+};
+
+static const struct rte_mempool_ops ops_sp_mc_nb = {
+	.name = "ring_sp_mc_nb",
+	.alloc = common_ring_alloc_nb,
+	.free = common_ring_free,
+	.enqueue = common_ring_sp_enqueue,
+	.dequeue = common_ring_mc_dequeue,
+	.get_count = common_ring_get_count,
+};
+
 MEMPOOL_REGISTER_OPS(ops_mp_mc);
 MEMPOOL_REGISTER_OPS(ops_sp_sc);
 MEMPOOL_REGISTER_OPS(ops_mp_sc);
 MEMPOOL_REGISTER_OPS(ops_sp_mc);
+MEMPOOL_REGISTER_OPS(ops_mp_mc_nb);
+MEMPOOL_REGISTER_OPS(ops_sp_sc_nb);
+MEMPOOL_REGISTER_OPS(ops_mp_sc_nb);
+MEMPOOL_REGISTER_OPS(ops_sp_mc_nb);
-- 
2.13.6