[dpdk-dev] [PATCH 01/27] eventdev: dlb upstream prerequisites

["McDaniel, Timothy" <timothy.mcdaniel@intel.com>]

The DLB hardware does not conform exactly to the eventdev interface.
1) It has a limit on the number of queues that may be linked to a port.
2) Some ports a further restricted to a maximum of 1 linked queue.
3) It does not (currently) have the ability to carry the flow_id as part
of the event (QE) payload.

Due to the above, we would like to propose the following enhancements.

1) Add new fields to the rte_event_dev_info struct. These fields allow
the device to advertize its capabilities so that applications can take
the appropriate actions based on those capabilities.

    struct rte_event_dev_info {
	uint32_t max_event_port_links;
	/**< Maximum number of queues that can be linked to a single event
	 * port by this device.
	 */

	uint8_t max_single_link_event_port_queue_pairs;
	/**< Maximum number of event ports and queues that are optimized for
	 * (and only capable of) single-link configurations supported by this
	 * device. These ports and queues are not accounted for in
	 * max_event_ports or max_event_queues.
	 */
    }

2) Add a new field to the rte_event_dev_config struct. This field allows the
application to specify how many of its ports are limited to a single link,
or will be used in single link mode.

    /** Event device configuration structure */
    struct rte_event_dev_config {
	uint8_t nb_single_link_event_port_queues;
	/**< Number of event ports and queues that will be singly-linked to
	 * each other. These are a subset of the overall event ports and
	 * queues; this value cannot exceed *nb_event_ports* or
	 * *nb_event_queues*. If the device has ports and queues that are
	 * optimized for single-link usage, this field is a hint for how many
	 * to allocate; otherwise, regular event ports and queues can be used.
	 */
    }

3) Replace the dedicated implicit_release_disabled field with a bit field
of explicit port capabilities. The implicit_release_disable functionality
is assiged to one bit, and a port-is-single-link-only  attribute is
assigned to other, with the remaining bits available for future assignment.

	* Event port configuration bitmap flags */
	#define RTE_EVENT_PORT_CFG_DISABLE_IMPL_REL    (1ULL << 0)
	/**< Configure the port not to release outstanding events in
	 * rte_event_dev_dequeue_burst(). If set, all events received through
	 * the port must be explicitly released with RTE_EVENT_OP_RELEASE or
	 * RTE_EVENT_OP_FORWARD. Must be unset if the device is not
	 * RTE_EVENT_DEV_CAP_IMPLICIT_RELEASE_DISABLE capable.
	 */
	#define RTE_EVENT_PORT_CFG_SINGLE_LINK         (1ULL << 1)

	/**< This event port links only to a single event queue.
	 *
	 *  @see rte_event_port_setup(), rte_event_port_link()
	 */

	#define RTE_EVENT_PORT_ATTR_IMPLICIT_RELEASE_DISABLE 3
	/**
	 * The implicit release disable attribute of the port
	 */

	struct rte_event_port_conf {
		uint32_t event_port_cfg; /**< Port cfg flags(EVENT_PORT_CFG_) */
	}

4) Add UMWAIT/UMONITOR bit to rte_cpuflags

5) Added a new API that is useful for probing PCI devices.

	/**
	 * @internal
	 * Wrapper for use by pci drivers as a .probe function to attach to a event
	 * interface.  Same as rte_event_pmd_pci_probe, except caller can specify
	 * the name.
	 */
	static inline int
	rte_event_pmd_pci_probe_named(struct rte_pci_driver *pci_drv,
				    struct rte_pci_device *pci_dev,
				    size_t private_data_size,
				    eventdev_pmd_pci_callback_t devinit,
				    const char *name);

Change-Id: I4cf00015296e2b3feca9886895765554730594be
Signed-off-by: McDaniel, Timothy <timothy.mcdaniel@intel.com>
---
 app/test-eventdev/evt_common.h                     |  1 +
 app/test-eventdev/test_order_atq.c                 |  4 ++
 app/test-eventdev/test_order_common.c              |  6 ++-
 app/test-eventdev/test_order_queue.c               |  4 ++
 app/test-eventdev/test_perf_atq.c                  |  1 +
 app/test-eventdev/test_perf_queue.c                |  1 +
 app/test-eventdev/test_pipeline_atq.c              |  1 +
 app/test-eventdev/test_pipeline_queue.c            |  1 +
 app/test/test_eventdev.c                           |  4 +-
 drivers/event/dpaa2/dpaa2_eventdev.c               |  2 +-
 drivers/event/octeontx/ssovf_evdev.c               |  2 +-
 drivers/event/skeleton/skeleton_eventdev.c         |  2 +-
 drivers/event/sw/sw_evdev.c                        |  5 +-
 drivers/event/sw/sw_evdev_selftest.c               |  9 ++--
 .../eventdev_pipeline/pipeline_worker_generic.c    |  8 ++-
 examples/eventdev_pipeline/pipeline_worker_tx.c    |  3 ++
 examples/l2fwd-event/l2fwd_event_generic.c         |  5 +-
 examples/l2fwd-event/l2fwd_event_internal_port.c   |  5 +-
 examples/l3fwd/l3fwd_event_generic.c               |  5 +-
 examples/l3fwd/l3fwd_event_internal_port.c         |  5 +-
 lib/librte_eal/x86/include/rte_cpuflags.h          |  1 +
 lib/librte_eal/x86/rte_cpuflags.c                  |  1 +
 lib/librte_eventdev/rte_event_eth_tx_adapter.c     |  2 +-
 lib/librte_eventdev/rte_eventdev.c                 | 62 +++++++++++++++++++---
 lib/librte_eventdev/rte_eventdev.h                 | 51 +++++++++++++++---
 lib/librte_eventdev/rte_eventdev_pmd_pci.h         | 54 +++++++++++++++++++
 26 files changed, 208 insertions(+), 37 deletions(-)

diff --git a/app/test-eventdev/evt_common.h b/app/test-eventdev/evt_common.h
index f9d7378d3..120c27b33 100644
--- a/app/test-eventdev/evt_common.h
+++ b/app/test-eventdev/evt_common.h
@@ -169,6 +169,7 @@ evt_configure_eventdev(struct evt_options *opt, uint8_t nb_queues,
 			.dequeue_timeout_ns = opt->deq_tmo_nsec,
 			.nb_event_queues = nb_queues,
 			.nb_event_ports = nb_ports,
+			.nb_single_link_event_port_queues = 0,
 			.nb_events_limit  = info.max_num_events,
 			.nb_event_queue_flows = opt->nb_flows,
 			.nb_event_port_dequeue_depth =
diff --git a/app/test-eventdev/test_order_atq.c b/app/test-eventdev/test_order_atq.c
index 3366cfce9..8246b96f0 100644
--- a/app/test-eventdev/test_order_atq.c
+++ b/app/test-eventdev/test_order_atq.c
@@ -34,6 +34,8 @@ order_atq_worker(void *arg)
 			continue;
 		}
 
+		ev.flow_id = ev.mbuf->udata64;
+
 		if (ev.sub_event_type == 0) { /* stage 0 from producer */
 			order_atq_process_stage_0(&ev);
 			while (rte_event_enqueue_burst(dev_id, port, &ev, 1)
@@ -68,6 +70,8 @@ order_atq_worker_burst(void *arg)
 		}
 
 		for (i = 0; i < nb_rx; i++) {
+			ev[i].flow_id = ev[i].mbuf->udata64;
+
 			if (ev[i].sub_event_type == 0) { /*stage 0 */
 				order_atq_process_stage_0(&ev[i]);
 			} else if (ev[i].sub_event_type == 1) { /* stage 1 */
diff --git a/app/test-eventdev/test_order_common.c b/app/test-eventdev/test_order_common.c
index 4190f9ade..c6fcd0509 100644
--- a/app/test-eventdev/test_order_common.c
+++ b/app/test-eventdev/test_order_common.c
@@ -49,6 +49,7 @@ order_producer(void *arg)
 		const uint32_t flow = (uintptr_t)m % nb_flows;
 		/* Maintain seq number per flow */
 		m->seqn = producer_flow_seq[flow]++;
+		m->udata64 = flow;
 
 		ev.flow_id = flow;
 		ev.mbuf = m;
@@ -318,10 +319,11 @@ order_event_dev_port_setup(struct evt_test *test, struct evt_options *opt,
 		opt->wkr_deq_dep = dev_info.max_event_port_dequeue_depth;
 
 	/* port configuration */
-	const struct rte_event_port_conf p_conf = {
+	struct rte_event_port_conf p_conf = {
 			.dequeue_depth = opt->wkr_deq_dep,
 			.enqueue_depth = dev_info.max_event_port_dequeue_depth,
 			.new_event_threshold = dev_info.max_num_events,
+			.event_port_cfg = 0,
 	};
 
 	/* setup one port per worker, linking to all queues */
@@ -351,6 +353,8 @@ order_event_dev_port_setup(struct evt_test *test, struct evt_options *opt,
 	p->queue_id = 0;
 	p->t = t;
 
+	p_conf.new_event_threshold /= 2;
+
 	ret = rte_event_port_setup(opt->dev_id, port, &p_conf);
 	if (ret) {
 		evt_err("failed to setup producer port %d", port);
diff --git a/app/test-eventdev/test_order_queue.c b/app/test-eventdev/test_order_queue.c
index 495efd92f..a0a2187a2 100644
--- a/app/test-eventdev/test_order_queue.c
+++ b/app/test-eventdev/test_order_queue.c
@@ -34,6 +34,8 @@ order_queue_worker(void *arg)
 			continue;
 		}
 
+		ev.flow_id = ev.mbuf->udata64;
+
 		if (ev.queue_id == 0) { /* from ordered queue */
 			order_queue_process_stage_0(&ev);
 			while (rte_event_enqueue_burst(dev_id, port, &ev, 1)
@@ -68,6 +70,8 @@ order_queue_worker_burst(void *arg)
 		}
 
 		for (i = 0; i < nb_rx; i++) {
+			ev[i].flow_id = ev[i].mbuf->udata64;
+
 			if (ev[i].queue_id == 0) { /* from ordered queue */
 				order_queue_process_stage_0(&ev[i]);
 			} else if (ev[i].queue_id == 1) {/* from atomic queue */
diff --git a/app/test-eventdev/test_perf_atq.c b/app/test-eventdev/test_perf_atq.c
index 8fd51004e..10846f202 100644
--- a/app/test-eventdev/test_perf_atq.c
+++ b/app/test-eventdev/test_perf_atq.c
@@ -204,6 +204,7 @@ perf_atq_eventdev_setup(struct evt_test *test, struct evt_options *opt)
 			.dequeue_depth = opt->wkr_deq_dep,
 			.enqueue_depth = dev_info.max_event_port_dequeue_depth,
 			.new_event_threshold = dev_info.max_num_events,
+			.event_port_cfg = 0,
 	};
 
 	ret = perf_event_dev_port_setup(test, opt, 1 /* stride */, nb_queues,
diff --git a/app/test-eventdev/test_perf_queue.c b/app/test-eventdev/test_perf_queue.c
index f4ea3a795..a0119da60 100644
--- a/app/test-eventdev/test_perf_queue.c
+++ b/app/test-eventdev/test_perf_queue.c
@@ -219,6 +219,7 @@ perf_queue_eventdev_setup(struct evt_test *test, struct evt_options *opt)
 			.dequeue_depth = opt->wkr_deq_dep,
 			.enqueue_depth = dev_info.max_event_port_dequeue_depth,
 			.new_event_threshold = dev_info.max_num_events,
+			.event_port_cfg = 0,
 	};
 
 	ret = perf_event_dev_port_setup(test, opt, nb_stages /* stride */,
diff --git a/app/test-eventdev/test_pipeline_atq.c b/app/test-eventdev/test_pipeline_atq.c
index 8e8686c14..a95ec0aa5 100644
--- a/app/test-eventdev/test_pipeline_atq.c
+++ b/app/test-eventdev/test_pipeline_atq.c
@@ -356,6 +356,7 @@ pipeline_atq_eventdev_setup(struct evt_test *test, struct evt_options *opt)
 		.dequeue_depth = opt->wkr_deq_dep,
 		.enqueue_depth = info.max_event_port_dequeue_depth,
 		.new_event_threshold = info.max_num_events,
+		.event_port_cfg = 0,
 	};
 
 	if (!t->internal_port)
diff --git a/app/test-eventdev/test_pipeline_queue.c b/app/test-eventdev/test_pipeline_queue.c
index 7bebac34f..30817dc78 100644
--- a/app/test-eventdev/test_pipeline_queue.c
+++ b/app/test-eventdev/test_pipeline_queue.c
@@ -379,6 +379,7 @@ pipeline_queue_eventdev_setup(struct evt_test *test, struct evt_options *opt)
 			.dequeue_depth = opt->wkr_deq_dep,
 			.enqueue_depth = info.max_event_port_dequeue_depth,
 			.new_event_threshold = info.max_num_events,
+			.event_port_cfg = 0,
 	};
 
 	if (!t->internal_port) {
diff --git a/app/test/test_eventdev.c b/app/test/test_eventdev.c
index 43ccb1ce9..62019c185 100644
--- a/app/test/test_eventdev.c
+++ b/app/test/test_eventdev.c
@@ -559,10 +559,10 @@ test_eventdev_port_setup(void)
 	if (!(info.event_dev_cap &
 	      RTE_EVENT_DEV_CAP_IMPLICIT_RELEASE_DISABLE)) {
 		pconf.enqueue_depth = info.max_event_port_enqueue_depth;
-		pconf.disable_implicit_release = 1;
+		pconf.event_port_cfg = RTE_EVENT_PORT_CFG_DISABLE_IMPL_REL;
 		ret = rte_event_port_setup(TEST_DEV_ID, 0, &pconf);
 		TEST_ASSERT(ret == -EINVAL, "Expected -EINVAL, %d", ret);
-		pconf.disable_implicit_release = 0;
+		pconf.event_port_cfg = 0;
 	}
 
 	ret = rte_event_port_setup(TEST_DEV_ID, info.max_event_ports,
diff --git a/drivers/event/dpaa2/dpaa2_eventdev.c b/drivers/event/dpaa2/dpaa2_eventdev.c
index a196ad4c6..8568bfcfc 100644
--- a/drivers/event/dpaa2/dpaa2_eventdev.c
+++ b/drivers/event/dpaa2/dpaa2_eventdev.c
@@ -537,7 +537,7 @@ dpaa2_eventdev_port_def_conf(struct rte_eventdev *dev, uint8_t port_id,
 		DPAA2_EVENT_MAX_PORT_DEQUEUE_DEPTH;
 	port_conf->enqueue_depth =
 		DPAA2_EVENT_MAX_PORT_ENQUEUE_DEPTH;
-	port_conf->disable_implicit_release = 0;
+	port_conf->event_port_cfg = 0;
 }
 
 static int
diff --git a/drivers/event/octeontx/ssovf_evdev.c b/drivers/event/octeontx/ssovf_evdev.c
index 1b1a5d939..99c0b2efb 100644
--- a/drivers/event/octeontx/ssovf_evdev.c
+++ b/drivers/event/octeontx/ssovf_evdev.c
@@ -224,7 +224,7 @@ ssovf_port_def_conf(struct rte_eventdev *dev, uint8_t port_id,
 	port_conf->new_event_threshold = edev->max_num_events;
 	port_conf->dequeue_depth = 1;
 	port_conf->enqueue_depth = 1;
-	port_conf->disable_implicit_release = 0;
+	port_conf->event_port_cfg = 0;
 }
 
 static void
diff --git a/drivers/event/skeleton/skeleton_eventdev.c b/drivers/event/skeleton/skeleton_eventdev.c
index c889220e0..37d569b8c 100644
--- a/drivers/event/skeleton/skeleton_eventdev.c
+++ b/drivers/event/skeleton/skeleton_eventdev.c
@@ -209,7 +209,7 @@ skeleton_eventdev_port_def_conf(struct rte_eventdev *dev, uint8_t port_id,
 	port_conf->new_event_threshold = 32 * 1024;
 	port_conf->dequeue_depth = 16;
 	port_conf->enqueue_depth = 16;
-	port_conf->disable_implicit_release = 0;
+	port_conf->event_port_cfg = 0;
 }
 
 static void
diff --git a/drivers/event/sw/sw_evdev.c b/drivers/event/sw/sw_evdev.c
index fb8e8bebb..0b3dd9c1c 100644
--- a/drivers/event/sw/sw_evdev.c
+++ b/drivers/event/sw/sw_evdev.c
@@ -175,7 +175,8 @@ sw_port_setup(struct rte_eventdev *dev, uint8_t port_id,
 	}
 
 	p->inflight_max = conf->new_event_threshold;
-	p->implicit_release = !conf->disable_implicit_release;
+	p->implicit_release = !(conf->event_port_cfg &
+				RTE_EVENT_PORT_CFG_DISABLE_IMPL_REL);
 
 	/* check if ring exists, same as rx_worker above */
 	snprintf(buf, sizeof(buf), "sw%d_p%u, %s", dev->data->dev_id,
@@ -508,7 +509,7 @@ sw_port_def_conf(struct rte_eventdev *dev, uint8_t port_id,
 	port_conf->new_event_threshold = 1024;
 	port_conf->dequeue_depth = 16;
 	port_conf->enqueue_depth = 16;
-	port_conf->disable_implicit_release = 0;
+	port_conf->event_port_cfg = 0;
 }
 
 static int
diff --git a/drivers/event/sw/sw_evdev_selftest.c b/drivers/event/sw/sw_evdev_selftest.c
index 38c21fa0f..a78d6cd0d 100644
--- a/drivers/event/sw/sw_evdev_selftest.c
+++ b/drivers/event/sw/sw_evdev_selftest.c
@@ -172,7 +172,7 @@ create_ports(struct test *t, int num_ports)
 			.new_event_threshold = 1024,
 			.dequeue_depth = 32,
 			.enqueue_depth = 64,
-			.disable_implicit_release = 0,
+			.event_port_cfg = 0,
 	};
 	if (num_ports > MAX_PORTS)
 		return -1;
@@ -1227,7 +1227,7 @@ port_reconfig_credits(struct test *t)
 				.new_event_threshold = 128,
 				.dequeue_depth = 32,
 				.enqueue_depth = 64,
-				.disable_implicit_release = 0,
+				.event_port_cfg = 0,
 		};
 		if (rte_event_port_setup(evdev, 0, &port_conf) < 0) {
 			printf("%d Error setting up port\n", __LINE__);
@@ -1317,7 +1317,7 @@ port_single_lb_reconfig(struct test *t)
 		.new_event_threshold = 128,
 		.dequeue_depth = 32,
 		.enqueue_depth = 64,
-		.disable_implicit_release = 0,
+		.event_port_cfg = 0,
 	};
 	if (rte_event_port_setup(evdev, 0, &port_conf) < 0) {
 		printf("%d Error setting up port\n", __LINE__);
@@ -3079,7 +3079,8 @@ worker_loopback(struct test *t, uint8_t disable_implicit_release)
 	 * only be initialized once - and this needs to be set for multiple runs
 	 */
 	conf.new_event_threshold = 512;
-	conf.disable_implicit_release = disable_implicit_release;
+	conf.event_port_cfg = disable_implicit_release ?
+		RTE_EVENT_PORT_CFG_DISABLE_IMPL_REL : 0;
 
 	if (rte_event_port_setup(evdev, 0, &conf) < 0) {
 		printf("Error setting up RX port\n");
diff --git a/examples/eventdev_pipeline/pipeline_worker_generic.c b/examples/eventdev_pipeline/pipeline_worker_generic.c
index 42ff4eeb9..a091da3ba 100644
--- a/examples/eventdev_pipeline/pipeline_worker_generic.c
+++ b/examples/eventdev_pipeline/pipeline_worker_generic.c
@@ -129,6 +129,7 @@ setup_eventdev_generic(struct worker_data *worker_data)
 	struct rte_event_dev_config config = {
 			.nb_event_queues = nb_queues,
 			.nb_event_ports = nb_ports,
+			.nb_single_link_event_port_queues = 1,
 			.nb_events_limit  = 4096,
 			.nb_event_queue_flows = 1024,
 			.nb_event_port_dequeue_depth = 128,
@@ -138,12 +139,13 @@ setup_eventdev_generic(struct worker_data *worker_data)
 			.dequeue_depth = cdata.worker_cq_depth,
 			.enqueue_depth = 64,
 			.new_event_threshold = 4096,
+			.event_port_cfg = 0,
 	};
 	struct rte_event_queue_conf wkr_q_conf = {
 			.schedule_type = cdata.queue_type,
 			.priority = RTE_EVENT_DEV_PRIORITY_NORMAL,
 			.nb_atomic_flows = 1024,
-		.nb_atomic_order_sequences = 1024,
+			.nb_atomic_order_sequences = 1024,
 	};
 	struct rte_event_queue_conf tx_q_conf = {
 			.priority = RTE_EVENT_DEV_PRIORITY_HIGHEST,
@@ -167,7 +169,8 @@ setup_eventdev_generic(struct worker_data *worker_data)
 	disable_implicit_release = (dev_info.event_dev_cap &
 			RTE_EVENT_DEV_CAP_IMPLICIT_RELEASE_DISABLE);
 
-	wkr_p_conf.disable_implicit_release = disable_implicit_release;
+	wkr_p_conf.event_port_cfg = disable_implicit_release ?
+		RTE_EVENT_PORT_CFG_DISABLE_IMPL_REL : 0;
 
 	if (dev_info.max_num_events < config.nb_events_limit)
 		config.nb_events_limit = dev_info.max_num_events;
@@ -417,6 +420,7 @@ init_adapters(uint16_t nb_ports)
 		.dequeue_depth = cdata.worker_cq_depth,
 		.enqueue_depth = 64,
 		.new_event_threshold = 4096,
+		.event_port_cfg = 0,
 	};
 
 	if (adptr_p_conf.new_event_threshold > dev_info.max_num_events)
diff --git a/examples/eventdev_pipeline/pipeline_worker_tx.c b/examples/eventdev_pipeline/pipeline_worker_tx.c
index 55bb2f762..e8a9652aa 100644
--- a/examples/eventdev_pipeline/pipeline_worker_tx.c
+++ b/examples/eventdev_pipeline/pipeline_worker_tx.c
@@ -436,6 +436,7 @@ setup_eventdev_worker_tx_enq(struct worker_data *worker_data)
 	struct rte_event_dev_config config = {
 			.nb_event_queues = nb_queues,
 			.nb_event_ports = nb_ports,
+			.nb_single_link_event_port_queues = 0,
 			.nb_events_limit  = 4096,
 			.nb_event_queue_flows = 1024,
 			.nb_event_port_dequeue_depth = 128,
@@ -445,6 +446,7 @@ setup_eventdev_worker_tx_enq(struct worker_data *worker_data)
 			.dequeue_depth = cdata.worker_cq_depth,
 			.enqueue_depth = 64,
 			.new_event_threshold = 4096,
+			.event_port_cfg = 0,
 	};
 	struct rte_event_queue_conf wkr_q_conf = {
 			.schedule_type = cdata.queue_type,
@@ -746,6 +748,7 @@ init_adapters(uint16_t nb_ports)
 		.dequeue_depth = cdata.worker_cq_depth,
 		.enqueue_depth = 64,
 		.new_event_threshold = 4096,
+		.event_port_cfg = 0,
 	};
 
 	init_ports(nb_ports);
diff --git a/examples/l2fwd-event/l2fwd_event_generic.c b/examples/l2fwd-event/l2fwd_event_generic.c
index 2dc95e5f7..e01df0435 100644
--- a/examples/l2fwd-event/l2fwd_event_generic.c
+++ b/examples/l2fwd-event/l2fwd_event_generic.c
@@ -126,8 +126,9 @@ l2fwd_event_port_setup_generic(struct l2fwd_resources *rsrc)
 	if (def_p_conf.enqueue_depth < event_p_conf.enqueue_depth)
 		event_p_conf.enqueue_depth = def_p_conf.enqueue_depth;
 
-	event_p_conf.disable_implicit_release =
-		evt_rsrc->disable_implicit_release;
+	event_p_conf.event_port_cfg = 0;
+	if (evt_rsrc->disable_implicit_release)
+		event_p_conf.event_port_cfg |= RTE_EVENT_PORT_CFG_DISABLE_IMPL_REL;
 	evt_rsrc->deq_depth = def_p_conf.dequeue_depth;
 
 	for (event_p_id = 0; event_p_id < evt_rsrc->evp.nb_ports;
diff --git a/examples/l2fwd-event/l2fwd_event_internal_port.c b/examples/l2fwd-event/l2fwd_event_internal_port.c
index 63d57b46c..f54327b4f 100644
--- a/examples/l2fwd-event/l2fwd_event_internal_port.c
+++ b/examples/l2fwd-event/l2fwd_event_internal_port.c
@@ -123,8 +123,9 @@ l2fwd_event_port_setup_internal_port(struct l2fwd_resources *rsrc)
 	if (def_p_conf.enqueue_depth < event_p_conf.enqueue_depth)
 		event_p_conf.enqueue_depth = def_p_conf.enqueue_depth;
 
-	event_p_conf.disable_implicit_release =
-		evt_rsrc->disable_implicit_release;
+	event_p_conf.event_port_cfg = 0;
+	if (evt_rsrc->disable_implicit_release)
+		event_p_conf.event_port_cfg |= RTE_EVENT_PORT_CFG_DISABLE_IMPL_REL;
 
 	for (event_p_id = 0; event_p_id < evt_rsrc->evp.nb_ports;
 								event_p_id++) {
diff --git a/examples/l3fwd/l3fwd_event_generic.c b/examples/l3fwd/l3fwd_event_generic.c
index f8c98435d..409a4107e 100644
--- a/examples/l3fwd/l3fwd_event_generic.c
+++ b/examples/l3fwd/l3fwd_event_generic.c
@@ -115,8 +115,9 @@ l3fwd_event_port_setup_generic(void)
 	if (def_p_conf.enqueue_depth < event_p_conf.enqueue_depth)
 		event_p_conf.enqueue_depth = def_p_conf.enqueue_depth;
 
-	event_p_conf.disable_implicit_release =
-		evt_rsrc->disable_implicit_release;
+	event_p_conf.event_port_cfg = 0;
+	if (evt_rsrc->disable_implicit_release)
+		event_p_conf.event_port_cfg |= RTE_EVENT_PORT_CFG_DISABLE_IMPL_REL;
 	evt_rsrc->deq_depth = def_p_conf.dequeue_depth;
 
 	for (event_p_id = 0; event_p_id < evt_rsrc->evp.nb_ports;
diff --git a/examples/l3fwd/l3fwd_event_internal_port.c b/examples/l3fwd/l3fwd_event_internal_port.c
index 03ac581d6..df410f10f 100644
--- a/examples/l3fwd/l3fwd_event_internal_port.c
+++ b/examples/l3fwd/l3fwd_event_internal_port.c
@@ -113,8 +113,9 @@ l3fwd_event_port_setup_internal_port(void)
 	if (def_p_conf.enqueue_depth < event_p_conf.enqueue_depth)
 		event_p_conf.enqueue_depth = def_p_conf.enqueue_depth;
 
-	event_p_conf.disable_implicit_release =
-		evt_rsrc->disable_implicit_release;
+	event_p_conf.event_port_cfg = 0;
+	if (evt_rsrc->disable_implicit_release)
+		event_p_conf.event_port_cfg |= RTE_EVENT_PORT_CFG_DISABLE_IMPL_REL;
 
 	for (event_p_id = 0; event_p_id < evt_rsrc->evp.nb_ports;
 								event_p_id++) {
diff --git a/lib/librte_eal/x86/include/rte_cpuflags.h b/lib/librte_eal/x86/include/rte_cpuflags.h
index c1d20364d..ab2c3b379 100644
--- a/lib/librte_eal/x86/include/rte_cpuflags.h
+++ b/lib/librte_eal/x86/include/rte_cpuflags.h
@@ -130,6 +130,7 @@ enum rte_cpu_flag_t {
 	RTE_CPUFLAG_CLDEMOTE,               /**< Cache Line Demote */
 	RTE_CPUFLAG_MOVDIRI,                /**< Direct Store Instructions */
 	RTE_CPUFLAG_MOVDIR64B,              /**< Direct Store Instructions 64B */
+	RTE_CPUFLAG_UMWAIT,                 /**< UMONITOR/UMWAIT */
 	RTE_CPUFLAG_AVX512VP2INTERSECT,     /**< AVX512 Two Register Intersection */
 
 	/* The last item */
diff --git a/lib/librte_eal/x86/rte_cpuflags.c b/lib/librte_eal/x86/rte_cpuflags.c
index 30439e795..69ac0dbce 100644
--- a/lib/librte_eal/x86/rte_cpuflags.c
+++ b/lib/librte_eal/x86/rte_cpuflags.c
@@ -137,6 +137,7 @@ const struct feature_entry rte_cpu_feature_table[] = {
 	FEAT_DEF(CLDEMOTE, 0x00000007, 0, RTE_REG_ECX, 25)
 	FEAT_DEF(MOVDIRI, 0x00000007, 0, RTE_REG_ECX, 27)
 	FEAT_DEF(MOVDIR64B, 0x00000007, 0, RTE_REG_ECX, 28)
+        FEAT_DEF(UMWAIT, 0x00000007, 0, RTE_REG_ECX, 5)
 	FEAT_DEF(AVX512VP2INTERSECT, 0x00000007, 0, RTE_REG_EDX, 8)
 };
 
diff --git a/lib/librte_eventdev/rte_event_eth_tx_adapter.c b/lib/librte_eventdev/rte_event_eth_tx_adapter.c
index bb21dc407..8a72256de 100644
--- a/lib/librte_eventdev/rte_event_eth_tx_adapter.c
+++ b/lib/librte_eventdev/rte_event_eth_tx_adapter.c
@@ -286,7 +286,7 @@ txa_service_conf_cb(uint8_t __rte_unused id, uint8_t dev_id,
 		return ret;
 	}
 
-	pc->disable_implicit_release = 0;
+	pc->event_port_cfg = 0;
 	ret = rte_event_port_setup(dev_id, port_id, pc);
 	if (ret) {
 		RTE_EDEV_LOG_ERR("failed to setup event port %u\n",
diff --git a/lib/librte_eventdev/rte_eventdev.c b/lib/librte_eventdev/rte_eventdev.c
index 82c177c73..4955ab1a0 100644
--- a/lib/librte_eventdev/rte_eventdev.c
+++ b/lib/librte_eventdev/rte_eventdev.c
@@ -437,9 +437,29 @@ rte_event_dev_configure(uint8_t dev_id,
 					dev_id);
 		return -EINVAL;
 	}
-	if (dev_conf->nb_event_queues > info.max_event_queues) {
-		RTE_EDEV_LOG_ERR("%d nb_event_queues=%d > max_event_queues=%d",
-		dev_id, dev_conf->nb_event_queues, info.max_event_queues);
+	if (dev_conf->nb_event_queues > info.max_event_queues +
+			info.max_single_link_event_port_queue_pairs) {
+		RTE_EDEV_LOG_ERR("%d nb_event_queues=%d > max_event_queues=%d + max_single_link_event_port_queue_pairs=%d",
+				 dev_id, dev_conf->nb_event_queues,
+				 info.max_event_queues,
+				 info.max_single_link_event_port_queue_pairs);
+		return -EINVAL;
+	}
+	if (dev_conf->nb_event_queues -
+			dev_conf->nb_single_link_event_port_queues >
+			info.max_event_queues) {
+		RTE_EDEV_LOG_ERR("id%d nb_event_queues=%d - nb_single_link_event_port_queues=%d > max_event_queues=%d",
+				 dev_id, dev_conf->nb_event_queues,
+				 dev_conf->nb_single_link_event_port_queues,
+				 info.max_event_queues);
+		return -EINVAL;
+	}
+	if (dev_conf->nb_single_link_event_port_queues >
+			dev_conf->nb_event_queues) {
+		RTE_EDEV_LOG_ERR("dev%d nb_single_link_event_port_queues=%d > nb_event_queues=%d",
+				 dev_id,
+				 dev_conf->nb_single_link_event_port_queues,
+				 dev_conf->nb_event_queues);
 		return -EINVAL;
 	}
 
@@ -448,9 +468,31 @@ rte_event_dev_configure(uint8_t dev_id,
 		RTE_EDEV_LOG_ERR("dev%d nb_event_ports cannot be zero", dev_id);
 		return -EINVAL;
 	}
-	if (dev_conf->nb_event_ports > info.max_event_ports) {
-		RTE_EDEV_LOG_ERR("id%d nb_event_ports=%d > max_event_ports= %d",
-		dev_id, dev_conf->nb_event_ports, info.max_event_ports);
+	if (dev_conf->nb_event_ports > info.max_event_ports +
+			info.max_single_link_event_port_queue_pairs) {
+		RTE_EDEV_LOG_ERR("id%d nb_event_ports=%d > max_event_ports=%d + max_single_link_event_port_queue_pairs=%d",
+				 dev_id, dev_conf->nb_event_ports,
+				 info.max_event_ports,
+				 info.max_single_link_event_port_queue_pairs);
+		return -EINVAL;
+	}
+	if (dev_conf->nb_event_ports -
+			dev_conf->nb_single_link_event_port_queues
+			> info.max_event_ports) {
+		RTE_EDEV_LOG_ERR("id%d nb_event_ports=%d - nb_single_link_event_port_queues=%d > max_event_ports=%d",
+				 dev_id, dev_conf->nb_event_ports,
+				 dev_conf->nb_single_link_event_port_queues,
+				 info.max_event_ports);
+		return -EINVAL;
+	}
+
+	if (dev_conf->nb_single_link_event_port_queues >
+	    dev_conf->nb_event_ports) {
+		RTE_EDEV_LOG_ERR(
+				 "dev%d nb_single_link_event_port_queues=%d > nb_event_ports=%d",
+				 dev_id,
+				 dev_conf->nb_single_link_event_port_queues,
+				 dev_conf->nb_event_ports);
 		return -EINVAL;
 	}
 
@@ -737,7 +779,8 @@ rte_event_port_setup(uint8_t dev_id, uint8_t port_id,
 		return -EINVAL;
 	}
 
-	if (port_conf && port_conf->disable_implicit_release &&
+	if (port_conf &&
+	    (port_conf->event_port_cfg & RTE_EVENT_PORT_CFG_DISABLE_IMPL_REL) &&
 	    !(dev->data->event_dev_cap &
 	      RTE_EVENT_DEV_CAP_IMPLICIT_RELEASE_DISABLE)) {
 		RTE_EDEV_LOG_ERR(
@@ -809,6 +852,7 @@ rte_event_port_attr_get(uint8_t dev_id, uint8_t port_id, uint32_t attr_id,
 			uint32_t *attr_value)
 {
 	struct rte_eventdev *dev;
+	uint32_t config;
 
 	if (!attr_value)
 		return -EINVAL;
@@ -830,6 +874,10 @@ rte_event_port_attr_get(uint8_t dev_id, uint8_t port_id, uint32_t attr_id,
 	case RTE_EVENT_PORT_ATTR_NEW_EVENT_THRESHOLD:
 		*attr_value = dev->data->ports_cfg[port_id].new_event_threshold;
 		break;
+	case RTE_EVENT_PORT_ATTR_IMPLICIT_RELEASE_DISABLE:
+		config = dev->data->ports_cfg[port_id].event_port_cfg;
+		*attr_value = !!(config & RTE_EVENT_PORT_CFG_DISABLE_IMPL_REL);
+		break;
 	default:
 		return -EINVAL;
 	};
diff --git a/lib/librte_eventdev/rte_eventdev.h b/lib/librte_eventdev/rte_eventdev.h
index 7dc832353..7f7a8a275 100644
--- a/lib/librte_eventdev/rte_eventdev.h
+++ b/lib/librte_eventdev/rte_eventdev.h
@@ -291,6 +291,13 @@ struct rte_event;
  * single queue to each port or map a single queue to many port.
  */
 
+#define RTE_EVENT_DEV_CAP_CARRY_FLOW_ID (1ULL << 9)
+/**< Event device is capable of carrying the flow ID from the enqueued
+ * event to the dequeued event. If the flag is set, the dequeued event's flow
+ * ID matches the corresponding enqueued event's flow ID. If the flag is not
+ * set, the dequeued event's flow ID field is uninitialized.
+ */
+
 /* Event device priority levels */
 #define RTE_EVENT_DEV_PRIORITY_HIGHEST   0
 /**< Highest priority expressed across eventdev subsystem
@@ -380,6 +387,10 @@ struct rte_event_dev_info {
 	 * event port by this device.
 	 * A device that does not support bulk enqueue will set this as 1.
 	 */
+	uint32_t max_event_port_links;
+	/**< Maximum number of queues that can be linked to a single event
+	 * port by this device.
+	 */
 	int32_t max_num_events;
 	/**< A *closed system* event dev has a limit on the number of events it
 	 * can manage at a time. An *open system* event dev does not have a
@@ -387,6 +398,12 @@ struct rte_event_dev_info {
 	 */
 	uint32_t event_dev_cap;
 	/**< Event device capabilities(RTE_EVENT_DEV_CAP_)*/
+	uint8_t max_single_link_event_port_queue_pairs;
+	/**< Maximum number of event ports and queues that are optimized for
+	 * (and only capable of) single-link configurations supported by this
+	 * device. These ports and queues are not accounted for in
+	 * max_event_ports or max_event_queues.
+	 */
 };
 
 /**
@@ -494,6 +511,14 @@ struct rte_event_dev_config {
 	 */
 	uint32_t event_dev_cfg;
 	/**< Event device config flags(RTE_EVENT_DEV_CFG_)*/
+	uint8_t nb_single_link_event_port_queues;
+	/**< Number of event ports and queues that will be singly-linked to
+	 * each other. These are a subset of the overall event ports and
+	 * queues; this value cannot exceed *nb_event_ports* or
+	 * *nb_event_queues*. If the device has ports and queues that are
+	 * optimized for single-link usage, this field is a hint for how many
+	 * to allocate; otherwise, regular event ports and queues can be used.
+	 */
 };
 
 /**
@@ -671,6 +696,20 @@ rte_event_queue_attr_get(uint8_t dev_id, uint8_t queue_id, uint32_t attr_id,
 
 /* Event port specific APIs */
 
+/* Event port configuration bitmap flags */
+#define RTE_EVENT_PORT_CFG_DISABLE_IMPL_REL    (1ULL << 0)
+/**< Configure the port not to release outstanding events in
+ * rte_event_dev_dequeue_burst(). If set, all events received through
+ * the port must be explicitly released with RTE_EVENT_OP_RELEASE or
+ * RTE_EVENT_OP_FORWARD. Must be unset if the device is not
+ * RTE_EVENT_DEV_CAP_IMPLICIT_RELEASE_DISABLE capable.
+ */
+#define RTE_EVENT_PORT_CFG_SINGLE_LINK         (1ULL << 1)
+/**< This event port links only to a single event queue.
+ *
+ *  @see rte_event_port_setup(), rte_event_port_link()
+ */
+
 /** Event port configuration structure */
 struct rte_event_port_conf {
 	int32_t new_event_threshold;
@@ -698,13 +737,7 @@ struct rte_event_port_conf {
 	 * which previously supplied to rte_event_dev_configure().
 	 * Ignored when device is not RTE_EVENT_DEV_CAP_BURST_MODE capable.
 	 */
-	uint8_t disable_implicit_release;
-	/**< Configure the port not to release outstanding events in
-	 * rte_event_dev_dequeue_burst(). If true, all events received through
-	 * the port must be explicitly released with RTE_EVENT_OP_RELEASE or
-	 * RTE_EVENT_OP_FORWARD. Must be false when the device is not
-	 * RTE_EVENT_DEV_CAP_IMPLICIT_RELEASE_DISABLE capable.
-	 */
+	uint32_t event_port_cfg; /**< Port cfg flags(EVENT_PORT_CFG_) */
 };
 
 /**
@@ -769,6 +802,10 @@ rte_event_port_setup(uint8_t dev_id, uint8_t port_id,
  * The new event threshold of the port
  */
 #define RTE_EVENT_PORT_ATTR_NEW_EVENT_THRESHOLD 2
+/**
+ * The implicit release disable attribute of the port
+ */
+#define RTE_EVENT_PORT_ATTR_IMPLICIT_RELEASE_DISABLE 3
 
 /**
  * Get an attribute from a port.
diff --git a/lib/librte_eventdev/rte_eventdev_pmd_pci.h b/lib/librte_eventdev/rte_eventdev_pmd_pci.h
index 443cd38c2..157299983 100644
--- a/lib/librte_eventdev/rte_eventdev_pmd_pci.h
+++ b/lib/librte_eventdev/rte_eventdev_pmd_pci.h
@@ -88,6 +88,60 @@ rte_event_pmd_pci_probe(struct rte_pci_driver *pci_drv,
 	return -ENXIO;
 }
 
+/**
+ * @internal
+ * Wrapper for use by pci drivers as a .probe function to attach to a event
+ * interface.  Same as rte_event_pmd_pci_probe, except caller can specify
+ * the name.
+ */
+static inline int
+rte_event_pmd_pci_probe_named(struct rte_pci_driver *pci_drv,
+			    struct rte_pci_device *pci_dev,
+			    size_t private_data_size,
+			    eventdev_pmd_pci_callback_t devinit,
+			    const char *name)
+{
+	struct rte_eventdev *eventdev;
+
+	int retval;
+
+	if (devinit == NULL)
+		return -EINVAL;
+
+	eventdev = rte_event_pmd_allocate(name,
+			 pci_dev->device.numa_node);
+	if (eventdev == NULL)
+		return -ENOMEM;
+
+	if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
+		eventdev->data->dev_private =
+				rte_zmalloc_socket(
+						"eventdev private structure",
+						private_data_size,
+						RTE_CACHE_LINE_SIZE,
+						rte_socket_id());
+
+		if (eventdev->data->dev_private == NULL)
+			rte_panic("Cannot allocate memzone for private "
+					"device data");
+	}
+
+	eventdev->dev = &pci_dev->device;
+
+	/* Invoke PMD device initialization function */
+	retval = devinit(eventdev);
+	if (retval == 0)
+		return 0;
+
+	RTE_EDEV_LOG_ERR("driver %s: (vendor_id=0x%x device_id=0x%x)"
+			" failed", pci_drv->driver.name,
+			(unsigned int) pci_dev->id.vendor_id,
+			(unsigned int) pci_dev->id.device_id);
+
+	rte_event_pmd_release(eventdev);
+
+	return -ENXIO;
+}
 
 /**
  * @internal
-- 
2.13.6