rcu: add resource reclamation APIs

Add resource reclamation using defer queues to make it simple for
applications and libraries to integrate rte_rcu library.

Signed-off-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Reviewed-by: Ola Liljedahl <ola.liljedahl@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>

lib/Makefile

@@ -117,7 +117,7 @@ DEPDIRS-librte_ipsec := librte_eal librte_mbuf librte_cryptodev librte_security
 DIRS-$(CONFIG_RTE_LIBRTE_TELEMETRY) += librte_telemetry
 DEPDIRS-librte_telemetry := librte_eal librte_metrics librte_ethdev
 DIRS-$(CONFIG_RTE_LIBRTE_RCU) += librte_rcu
-DEPDIRS-librte_rcu := librte_eal
+DEPDIRS-librte_rcu := librte_eal librte_ring
 
 ifeq ($(CONFIG_RTE_EXEC_ENV_LINUX),y)
 DIRS-$(CONFIG_RTE_LIBRTE_KNI) += librte_kni

lib/librte_rcu/Makefile

@@ -7,7 +7,7 @@ include $(RTE_SDK)/mk/rte.vars.mk
 LIB = librte_rcu.a
 
 CFLAGS += $(WERROR_FLAGS) -I$(SRCDIR) -O3
-LDLIBS += -lrte_eal
+LDLIBS += -lrte_eal -lrte_ring
 
 EXPORT_MAP := rte_rcu_version.map
 

lib/librte_rcu/meson.build

@@ -3,3 +3,5 @@
 
 sources = files('rte_rcu_qsbr.c')
 headers = files('rte_rcu_qsbr.h')
+
+deps += ['ring']

lib/librte_rcu/rcu_qsbr_pvt.h

@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright (c) 2020 Arm Limited
+ */
+
+#ifndef _RTE_RCU_QSBR_PVT_H_
+#define _RTE_RCU_QSBR_PVT_H_
+
+/**
+ * This file is private to the RCU library. It should not be included
+ * by the user of this library.
+ */
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include <rte_ring.h>
+#include <rte_ring_elem.h>
+
+#include "rte_rcu_qsbr.h"
+
+/* Defer queue structure.
+ * This structure holds the defer queue. The defer queue is used to
+ * hold the deleted entries from the data structure that are not
+ * yet freed.
+ */
+struct rte_rcu_qsbr_dq {
+	struct rte_rcu_qsbr *v; /**< RCU QSBR variable used by this queue.*/
+	struct rte_ring *r;     /**< RCU QSBR defer queue. */
+	uint32_t size;
+	/**< Number of elements in the defer queue */
+	uint32_t esize;
+	/**< Size (in bytes) of data, including the token, stored on the
+	 *   defer queue.
+	 */
+	uint32_t trigger_reclaim_limit;
+	/**< Trigger automatic reclamation after the defer queue
+	 *   has at least these many resources waiting.
+	 */
+	uint32_t max_reclaim_size;
+	/**< Reclaim at the max these many resources during auto
+	 *   reclamation.
+	 */
+	rte_rcu_qsbr_free_resource_t free_fn;
+	/**< Function to call to free the resource. */
+	void *p;
+	/**< Pointer passed to the free function. Typically, this is the
+	 *   pointer to the data structure to which the resource to free
+	 *   belongs.
+	 */
+};
+
+/* Internal structure to represent the element on the defer queue.
+ * Use alias as a character array is type casted to a variable
+ * of this structure type.
+ */
+typedef struct {
+	uint64_t token;  /**< Token */
+	uint8_t elem[0]; /**< Pointer to user element */
+} __attribute__((__may_alias__)) __rte_rcu_qsbr_dq_elem_t;
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _RTE_RCU_QSBR_PVT_H_ */

lib/librte_rcu/rte_rcu_qsbr.c

@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: BSD-3-Clause
  *
- * Copyright (c) 2018 Arm Limited
+ * Copyright (c) 2018-2020 Arm Limited
  */
 
 #include <stdio.h>
@@ -18,8 +18,10 @@
 #include <rte_per_lcore.h>
 #include <rte_lcore.h>
 #include <rte_errno.h>
+#include <rte_ring_elem.h>
 
 #include "rte_rcu_qsbr.h"
+#include "rcu_qsbr_pvt.h"
 
 /* Get the memory size of QSBR variable */
 size_t
@@ -270,6 +272,229 @@ rte_rcu_qsbr_dump(FILE *f, struct rte_rcu_qsbr *v)
 	return 0;
 }
 
+/* Create a queue used to store the data structure elements that can
+ * be freed later. This queue is referred to as 'defer queue'.
+ */
+struct rte_rcu_qsbr_dq *
+rte_rcu_qsbr_dq_create(const struct rte_rcu_qsbr_dq_parameters *params)
+{
+	struct rte_rcu_qsbr_dq *dq;
+	uint32_t qs_fifo_size;
+	unsigned int flags;
+
+	if (params == NULL || params->free_fn == NULL ||
+		params->v == NULL || params->name == NULL ||
+		params->size == 0 || params->esize == 0 ||
+		(params->esize % 4 != 0)) {
+		rte_log(RTE_LOG_ERR, rte_rcu_log_type,
+			"%s(): Invalid input parameter\n", __func__);
+		rte_errno = EINVAL;
+
+		return NULL;
+	}
+	/* If auto reclamation is configured, reclaim limit
+	 * should be a valid value.
+	 */
+	if ((params->trigger_reclaim_limit <= params->size) &&
+	    (params->max_reclaim_size == 0)) {
+		rte_log(RTE_LOG_ERR, rte_rcu_log_type,
+			"%s(): Invalid input parameter, size = %u, trigger_reclaim_limit = %u, max_reclaim_size = %u\n",
+			__func__, params->size, params->trigger_reclaim_limit,
+			params->max_reclaim_size);
+		rte_errno = EINVAL;
+
+		return NULL;
+	}
+
+	dq = rte_zmalloc(NULL, sizeof(struct rte_rcu_qsbr_dq),
+			 RTE_CACHE_LINE_SIZE);
+	if (dq == NULL) {
+		rte_errno = ENOMEM;
+
+		return NULL;
+	}
+
+	/* Decide the flags for the ring.
+	 * If MT safety is requested, use RTS for ring enqueue as most
+	 * use cases involve dq-enqueue happening on the control plane.
+	 * Ring dequeue is always HTS due to the possibility of revert.
+	 */
+	flags = RING_F_MP_RTS_ENQ;
+	if (params->flags & RTE_RCU_QSBR_DQ_MT_UNSAFE)
+		flags = RING_F_SP_ENQ;
+	flags |= RING_F_MC_HTS_DEQ;
+	/* round up qs_fifo_size to next power of two that is not less than
+	 * max_size.
+	 */
+	qs_fifo_size = rte_align32pow2(params->size + 1);
+	/* Add token size to ring element size */
+	dq->r = rte_ring_create_elem(params->name,
+			__RTE_QSBR_TOKEN_SIZE + params->esize,
+			qs_fifo_size, SOCKET_ID_ANY, flags);
+	if (dq->r == NULL) {
+		rte_log(RTE_LOG_ERR, rte_rcu_log_type,
+			"%s(): defer queue create failed\n", __func__);
+		rte_free(dq);
+		return NULL;
+	}
+
+	dq->v = params->v;
+	dq->size = params->size;
+	dq->esize = __RTE_QSBR_TOKEN_SIZE + params->esize;
+	dq->trigger_reclaim_limit = params->trigger_reclaim_limit;
+	dq->max_reclaim_size = params->max_reclaim_size;
+	dq->free_fn = params->free_fn;
+	dq->p = params->p;
+
+	return dq;
+}
+
+/* Enqueue one resource to the defer queue to free after the grace
+ * period is over.
+ */
+int rte_rcu_qsbr_dq_enqueue(struct rte_rcu_qsbr_dq *dq, void *e)
+{
+	__rte_rcu_qsbr_dq_elem_t *dq_elem;
+	uint32_t cur_size;
+
+	if (dq == NULL || e == NULL) {
+		rte_log(RTE_LOG_ERR, rte_rcu_log_type,
+			"%s(): Invalid input parameter\n", __func__);
+		rte_errno = EINVAL;
+
+		return 1;
+	}
+
+	char data[dq->esize];
+	dq_elem = (__rte_rcu_qsbr_dq_elem_t *)data;
+	/* Start the grace period */
+	dq_elem->token = rte_rcu_qsbr_start(dq->v);
+
+	/* Reclaim resources if the queue size has hit the reclaim
+	 * limit. This helps the queue from growing too large and
+	 * allows time for reader threads to report their quiescent state.
+	 */
+	cur_size = rte_ring_count(dq->r);
+	if (cur_size > dq->trigger_reclaim_limit) {
+		rte_log(RTE_LOG_INFO, rte_rcu_log_type,
+			"%s(): Triggering reclamation\n", __func__);
+		rte_rcu_qsbr_dq_reclaim(dq, dq->max_reclaim_size,
+						NULL, NULL, NULL);
+	}
+
+	/* Enqueue the token and resource. Generating the token and
+	 * enqueuing (token + resource) on the queue is not an
+	 * atomic operation. When the defer queue is shared by multiple
+	 * writers, this might result in tokens enqueued out of order
+	 * on the queue. So, some tokens might wait longer than they
+	 * are required to be reclaimed.
+	 */
+	memcpy(dq_elem->elem, e, dq->esize - __RTE_QSBR_TOKEN_SIZE);
+	/* Check the status as enqueue might fail since the other threads
+	 * might have used up the freed space.
+	 * Enqueue uses the configured flags when the DQ was created.
+	 */
+	if (rte_ring_enqueue_elem(dq->r, data, dq->esize) != 0) {
+		rte_log(RTE_LOG_ERR, rte_rcu_log_type,
+			"%s(): Enqueue failed\n", __func__);
+		/* Note that the token generated above is not used.
+		 * Other than wasting tokens, it should not cause any
+		 * other issues.
+		 */
+		rte_log(RTE_LOG_INFO, rte_rcu_log_type,
+			"%s(): Skipped enqueuing token = %"PRIu64"\n",
+			__func__, dq_elem->token);
+
+		rte_errno = ENOSPC;
+		return 1;
+	}
+
+	rte_log(RTE_LOG_INFO, rte_rcu_log_type,
+		"%s(): Enqueued token = %"PRIu64"\n", __func__, dq_elem->token);
+
+	return 0;
+}
+
+/* Reclaim resources from the defer queue. */
+int
+rte_rcu_qsbr_dq_reclaim(struct rte_rcu_qsbr_dq *dq, unsigned int n,
+			unsigned int *freed, unsigned int *pending,
+			unsigned int *available)
+{
+	uint32_t cnt;
+	__rte_rcu_qsbr_dq_elem_t *dq_elem;
+
+	if (dq == NULL || n == 0) {
+		rte_log(RTE_LOG_ERR, rte_rcu_log_type,
+			"%s(): Invalid input parameter\n", __func__);
+		rte_errno = EINVAL;
+
+		return 1;
+	}
+
+	cnt = 0;
+
+	char data[dq->esize];
+	/* Check reader threads quiescent state and reclaim resources */
+	while (cnt < n &&
+		rte_ring_dequeue_bulk_elem_start(dq->r, &data,
+					dq->esize, 1, available) != 0) {
+		dq_elem = (__rte_rcu_qsbr_dq_elem_t *)data;
+
+		/* Reclaim the resource */
+		if (rte_rcu_qsbr_check(dq->v, dq_elem->token, false) != 1) {
+			rte_ring_dequeue_elem_finish(dq->r, 0);
+			break;
+		}
+		rte_ring_dequeue_elem_finish(dq->r, 1);
+
+		rte_log(RTE_LOG_INFO, rte_rcu_log_type,
+			"%s(): Reclaimed token = %"PRIu64"\n",
+			__func__, dq_elem->token);
+
+		dq->free_fn(dq->p, dq_elem->elem, 1);
+
+		cnt++;
+	}
+
+	rte_log(RTE_LOG_INFO, rte_rcu_log_type,
+		"%s(): Reclaimed %u resources\n", __func__, cnt);
+
+	if (freed != NULL)
+		*freed = cnt;
+	if (pending != NULL)
+		*pending = rte_ring_count(dq->r);
+
+	return 0;
+}
+
+/* Delete a defer queue. */
+int
+rte_rcu_qsbr_dq_delete(struct rte_rcu_qsbr_dq *dq)
+{
+	unsigned int pending;
+
+	if (dq == NULL) {
+		rte_log(RTE_LOG_DEBUG, rte_rcu_log_type,
+			"%s(): Invalid input parameter\n", __func__);
+
+		return 0;
+	}
+
+	/* Reclaim all the resources */
+	rte_rcu_qsbr_dq_reclaim(dq, ~0, NULL, &pending, NULL);
+	if (pending != 0) {
+		rte_errno = EAGAIN;
+
+		return 1;
+	}
+
+	rte_ring_free(dq->r);
+	rte_free(dq);
+
+	return 0;
+}
+
 int rte_rcu_log_type;
 
 RTE_INIT(rte_rcu_register)

lib/librte_rcu/rte_rcu_qsbr.h

@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: BSD-3-Clause
- * Copyright (c) 2018 Arm Limited
+ * Copyright (c) 2018-2020 Arm Limited
  */
 
 #ifndef _RTE_RCU_QSBR_H_
@@ -34,6 +34,7 @@ extern "C" {
 #include <rte_lcore.h>
 #include <rte_debug.h>
 #include <rte_atomic.h>
+#include <rte_ring.h>
 
 extern int rte_rcu_log_type;
 
@@ -84,6 +85,7 @@ struct rte_rcu_qsbr_cnt {
 #define __RTE_QSBR_CNT_THR_OFFLINE 0
 #define __RTE_QSBR_CNT_INIT 1
 #define __RTE_QSBR_CNT_MAX ((uint64_t)~0)
+#define __RTE_QSBR_TOKEN_SIZE sizeof(uint64_t)
 
 /* RTE Quiescent State variable structure.
  * This structure has two elements that vary in size based on the
@@ -114,6 +116,86 @@ struct rte_rcu_qsbr {
 	 */
 } __rte_cache_aligned;
 
+/**
+ * Call back function called to free the resources.
+ *
+ * @param p
+ *   Pointer provided while creating the defer queue
+ * @param e
+ *   Pointer to the resource data stored on the defer queue
+ * @param n
+ *   Number of resources to free. Currently, this is set to 1.
+ *
+ * @return
+ *   None
+ */
+typedef void (*rte_rcu_qsbr_free_resource_t)(void *p, void *e, unsigned int n);
+
+#define RTE_RCU_QSBR_DQ_NAMESIZE RTE_RING_NAMESIZE
+
+/**
+ * Various flags supported.
+ */
+/**< Enqueue and reclaim operations are multi-thread safe by default.
+ *   The call back functions registered to free the resources are
+ *   assumed to be multi-thread safe.
+ *   Set this flag if multi-thread safety is not required.
+ */
+#define RTE_RCU_QSBR_DQ_MT_UNSAFE 1
+
+/**
+ * Parameters used when creating the defer queue.
+ */
+struct rte_rcu_qsbr_dq_parameters {
+	const char *name;
+	/**< Name of the queue. */
+	uint32_t flags;
+	/**< Flags to control API behaviors */
+	uint32_t size;
+	/**< Number of entries in queue. Typically, this will be
+	 *   the same as the maximum number of entries supported in the
+	 *   lock free data structure.
+	 *   Data structures with unbounded number of entries is not
+	 *   supported currently.
+	 */
+	uint32_t esize;
+	/**< Size (in bytes) of each element in the defer queue.
+	 *   This has to be multiple of 4B.
+	 */
+	uint32_t trigger_reclaim_limit;
+	/**< Trigger automatic reclamation after the defer queue
+	 *   has at least these many resources waiting. This auto
+	 *   reclamation is triggered in rte_rcu_qsbr_dq_enqueue API
+	 *   call.
+	 *   If this is greater than 'size', auto reclamation is
+	 *   not triggered.
+	 *   If this is set to 0, auto reclamation is triggered
+	 *   in every call to rte_rcu_qsbr_dq_enqueue API.
+	 */
+	uint32_t max_reclaim_size;
+	/**< When automatic reclamation is enabled, reclaim at the max
+	 *   these many resources. This should contain a valid value, if
+	 *   auto reclamation is on. Setting this to 'size' or greater will
+	 *   reclaim all possible resources currently on the defer queue.
+	 */
+	rte_rcu_qsbr_free_resource_t free_fn;
+	/**< Function to call to free the resource. */
+	void *p;
+	/**< Pointer passed to the free function. Typically, this is the
+	 *   pointer to the data structure to which the resource to free
+	 *   belongs. This can be NULL.
+	 */
+	struct rte_rcu_qsbr *v;
+	/**< RCU QSBR variable to use for this defer queue */
+};
+
+/* RTE defer queue structure.
+ * This structure holds the defer queue. The defer queue is used to
+ * hold the deleted entries from the data structure that are not
+ * yet freed.
+ */
+struct rte_rcu_qsbr_dq;
+
 /**
  * @warning
  * @b EXPERIMENTAL: this API may change without prior notice
@@ -692,6 +774,116 @@ __rte_experimental
 int
 rte_rcu_qsbr_dump(FILE *f, struct rte_rcu_qsbr *v);
 
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice
+ *
+ * Create a queue used to store the data structure elements that can
+ * be freed later. This queue is referred to as 'defer queue'.
+ *
+ * @param params
+ *   Parameters to create a defer queue.
+ * @return
+ *   On success - Valid pointer to defer queue
+ *   On error - NULL
+ *   Possible rte_errno codes are:
+ *   - EINVAL - NULL parameters are passed
+ *   - ENOMEM - Not enough memory
+ */
+__rte_experimental
+struct rte_rcu_qsbr_dq *
+rte_rcu_qsbr_dq_create(const struct rte_rcu_qsbr_dq_parameters *params);
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice
+ *
+ * Enqueue one resource to the defer queue and start the grace period.
+ * The resource will be freed later after at least one grace period
+ * is over.
+ *
+ * If the defer queue is full, it will attempt to reclaim resources.
+ * It will also reclaim resources at regular intervals to avoid
+ * the defer queue from growing too big.
+ *
+ * Multi-thread safety is provided as the defer queue configuration.
+ * When multi-thread safety is requested, it is possible that the
+ * resources are not stored in their order of deletion. This results
+ * in resources being held in the defer queue longer than they should.
+ *
+ * @param dq
+ *   Defer queue to allocate an entry from.
+ * @param e
+ *   Pointer to resource data to copy to the defer queue. The size of
+ *   the data to copy is equal to the element size provided when the
+ *   defer queue was created.
+ * @return
+ *   On success - 0
+ *   On error - 1 with rte_errno set to
+ *   - EINVAL - NULL parameters are passed
+ *   - ENOSPC - Defer queue is full. This condition can not happen
+ *		if the defer queue size is equal (or larger) than the
+ *		number of elements in the data structure.
+ */
+__rte_experimental
+int
+rte_rcu_qsbr_dq_enqueue(struct rte_rcu_qsbr_dq *dq, void *e);
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice
+ *
+ * Free resources from the defer queue.
+ *
+ * This API is multi-thread safe.
+ *
+ * @param dq
+ *   Defer queue to free an entry from.
+ * @param n
+ *   Maximum number of resources to free.
+ * @param freed
+ *   Number of resources that were freed.
+ * @param pending
+ *   Number of resources pending on the defer queue. This number might not
+ *   be accurate if multi-thread safety is configured.
+ * @param available
+ *   Number of resources that can be added to the defer queue.
+ *   This number might not be accurate if multi-thread safety is configured.
+ * @return
+ *   On successful reclamation of at least 1 resource - 0
+ *   On error - 1 with rte_errno set to
+ *   - EINVAL - NULL parameters are passed
+ */
+__rte_experimental
+int
+rte_rcu_qsbr_dq_reclaim(struct rte_rcu_qsbr_dq *dq, unsigned int n,
+	unsigned int *freed, unsigned int *pending, unsigned int *available);
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice
+ *
+ * Delete a defer queue.
+ *
+ * It tries to reclaim all the resources on the defer queue.
+ * If any of the resources have not completed the grace period
+ * the reclamation stops and returns immediately. The rest of
+ * the resources are not reclaimed and the defer queue is not
+ * freed.
+ *
+ * @param dq
+ *   Defer queue to delete.
+ * @return
+ *   On success - 0
+ *   On error - 1
+ *   Possible rte_errno codes are:
+ *   - EAGAIN - Some of the resources have not completed at least 1 grace
+ *		period, try again.
+ */
+__rte_experimental
+int
+rte_rcu_qsbr_dq_delete(struct rte_rcu_qsbr_dq *dq);
+
 #ifdef __cplusplus
 }
 #endif

lib/librte_rcu/rte_rcu_version.map

@@ -8,6 +8,10 @@ EXPERIMENTAL {
 	rte_rcu_qsbr_synchronize;
 	rte_rcu_qsbr_thread_register;
 	rte_rcu_qsbr_thread_unregister;
+	rte_rcu_qsbr_dq_create;
+	rte_rcu_qsbr_dq_enqueue;
+	rte_rcu_qsbr_dq_reclaim;
+	rte_rcu_qsbr_dq_delete;
 
 	local: *;
 };

lib/meson.build

@@ -11,7 +11,9 @@
 libraries = [
 	'kvargs', # eal depends on kvargs
 	'eal', # everything depends on eal
-	'ring', 'mempool', 'mbuf', 'net', 'meter', 'ethdev', 'pci', # core
+	'ring',
+	'rcu', # rcu depends on ring
+	'mempool', 'mbuf', 'net', 'meter', 'ethdev', 'pci', # core
 	'cmdline',
 	'metrics', # bitrate/latency stats depends on this
 	'hash',    # efd depends on this
@@ -22,7 +24,7 @@ libraries = [
 	'gro', 'gso', 'ip_frag', 'jobstats',
 	'kni', 'latencystats', 'lpm', 'member',
 	'power', 'pdump', 'rawdev',
-	'rcu', 'rib', 'reorder', 'sched', 'security', 'stack', 'vhost',
+	'rib', 'reorder', 'sched', 'security', 'stack', 'vhost',
 	# ipsec lib depends on net, crypto and security
 	'ipsec',
 	#fib lib depends on rib