[dpdk-dev] [PATCH v3 2/3] lib/rcu: add resource reclamation APIs

[Ananyev, Konstantin]

> +
> +/* Reclaim resources from the defer queue. */
> +int
> +rte_rcu_qsbr_dq_reclaim(struct rte_rcu_qsbr_dq *dq)
> +{
> +	uint32_t max_cnt;
> +	uint32_t cnt;
> +	void *token;
> +	uint64_t *tmp;
> +	uint32_t i;
> +
> +	if (dq == NULL) {
> +		rte_log(RTE_LOG_ERR, rte_rcu_log_type,
> +			"%s(): Invalid input parameter\n", __func__);
> +		rte_errno = EINVAL;
> +
> +		return 1;
> +	}
> +
> +	/* Anything to reclaim? */
> +	if (rte_ring_count(dq->r) == 0)
> +		return 0;
> +
> +	/* Reclaim at the max 1/16th the total number of entries. */
> +	max_cnt = dq->size >> RTE_RCU_QSBR_MAX_RECLAIM_LIMIT;
> +	max_cnt = (max_cnt == 0) ? dq->size : max_cnt;
> +	cnt = 0;
> +
> +	/* Check reader threads quiescent state and reclaim resources */
> +	while ((cnt < max_cnt) && (rte_ring_peek(dq->r, &token) == 0) &&
> +		(rte_rcu_qsbr_check(dq->v, (uint64_t)((uintptr_t)token), false)

One more thing I forgot to ask - how this construct supposed to work on 32 bit machines?
peek() will return 32-bit value, while  qsbr_check() operates with 64bit tokens...
As I understand in that case you need to peek() 2 elems.
Might work, but still think better to introduce serialize version of ring_dequeue()
See my other mail about re_ring_peek().


> +			== 1)) {
> +		(void)rte_ring_sc_dequeue(dq->r, &token);
> +		/* The resource to dequeue needs to be a multiple of 64b
> +		 * due to the limitation of the rte_ring implementation.
> +		 */
> +		for (i = 0, tmp = (uint64_t *)dq->e; i < dq->esize/8;
> +			i++, tmp++)
> +			(void)rte_ring_sc_dequeue(dq->r,
> +					(void *)(uintptr_t)tmp);
> +		dq->f(dq->p, dq->e);
> +
> +		cnt++;
> +	}
> +
> +	rte_log(RTE_LOG_INFO, rte_rcu_log_type,
> +		"%s(): Reclaimed %u resources\n", __func__, cnt);
> +
> +	if (cnt == 0) {
> +		/* No resources were reclaimed */
> +		rte_errno = EAGAIN;
> +		return 1;
> +	}
> +
> +	return 0;
> +}
> +
> +/* Delete a defer queue. */
> +int
> +rte_rcu_qsbr_dq_delete(struct rte_rcu_qsbr_dq *dq)
> +{
> +	if (dq == NULL) {
> +		rte_log(RTE_LOG_ERR, rte_rcu_log_type,
> +			"%s(): Invalid input parameter\n", __func__);
> +		rte_errno = EINVAL;
> +
> +		return 1;
> +	}
> +
> +	/* Reclaim all the resources */
> +	if (rte_rcu_qsbr_dq_reclaim(dq) != 0)
> +		/* Error number is already set by the reclaim API */
> +		return 1;
> +
> +	rte_ring_free(dq->r);
> +	rte_free(dq);
> +
> +	return 0;
> +}
> +
>  int rte_rcu_log_type;
> 
>  RTE_INIT(rte_rcu_register)
> diff --git a/lib/librte_rcu/rte_rcu_qsbr.h b/lib/librte_rcu/rte_rcu_qsbr.h
> index c80f15c00..185d4b50a 100644
> --- a/lib/librte_rcu/rte_rcu_qsbr.h
> +++ b/lib/librte_rcu/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;
> 
> @@ -109,6 +110,67 @@ 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
> + *
> + * @return
> + *   None
> + */
> +typedef void (*rte_rcu_qsbr_free_resource)(void *p, void *e);
> +
> +#define RTE_RCU_QSBR_DQ_NAMESIZE RTE_RING_NAMESIZE
> +
> +/**
> + *  Trigger automatic reclamation after 1/8th the defer queue is full.
> + */
> +#define RTE_RCU_QSBR_AUTO_RECLAIM_LIMIT 3
> +
> +/**
> + *  Reclaim at the max 1/16th the total number of resources.
> + */
> +#define RTE_RCU_QSBR_MAX_RECLAIM_LIMIT 4
> +
> +/**
> + * Parameters used when creating the defer queue.
> + */
> +struct rte_rcu_qsbr_dq_parameters {
> +	const char *name;
> +	/**< Name of the queue. */
> +	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 8B as the rte_ring APIs
> +	 *   support 8B element sizes only.
> +	 */
> +	rte_rcu_qsbr_free_resource f;
> +	/**< 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
> @@ -648,6 +710,113 @@ __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.
> + *
> + * This API is not multi-thread safe. It is expected that the caller
> + * provides multi-thread safety by locking a mutex or some other means.
> + *
> + * A lock free multi-thread writer algorithm could achieve multi-thread
> + * safety by creating and using one defer queue per thread.
> + *
> + * @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
> + *
> + * Reclaim resources from the defer queue.
> + *
> + * This API is not multi-thread safe. It is expected that the caller
> + * provides multi-thread safety by locking a mutex or some other means.
> + *
> + * A lock free multi-thread writer algorithm could achieve multi-thread
> + * safety by creating and using one defer queue per thread.
> + *
> + * @param dq
> + *   Defer queue to reclaim an entry from.
> + * @return
> + *   On successful reclamation of at least 1 resource - 0
> + *   On error - 1 with rte_errno set to
> + *   - EINVAL - NULL parameters are passed
> + *   - EAGAIN - None of the resources have completed at least 1 grace period,
> + *		try again.
> + */
> +__rte_experimental
> +int
> +rte_rcu_qsbr_dq_reclaim(struct rte_rcu_qsbr_dq *dq);
> +
> +/**
> + * @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:
> + *   - EINVAL - NULL parameters are passed
> + *   - 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
> diff --git a/lib/librte_rcu/rte_rcu_qsbr_pvt.h b/lib/librte_rcu/rte_rcu_qsbr_pvt.h
> new file mode 100644
> index 000000000..2122bc36a
> --- /dev/null
> +++ b/lib/librte_rcu/rte_rcu_qsbr_pvt.h
> @@ -0,0 +1,46 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright (c) 2019 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_rcu_qsbr.h"
> +
> +/* 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 {
> +	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 stored on the defer queue */
> +	rte_rcu_qsbr_free_resource f;
> +	/**< 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.
> +	 */
> +	char e[0];
> +	/**< Temporary storage to copy the defer queue element. */
> +};
> +
> +#ifdef __cplusplus
> +}
> +#endif
> +
> +#endif /* _RTE_RCU_QSBR_PVT_H_ */
> diff --git a/lib/librte_rcu/rte_rcu_version.map b/lib/librte_rcu/rte_rcu_version.map
> index f8b9ef2ab..dfac88a37 100644
> --- a/lib/librte_rcu/rte_rcu_version.map
> +++ b/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: *;
>  };
> diff --git a/lib/meson.build b/lib/meson.build
> index e5ff83893..0e1be8407 100644
> --- a/lib/meson.build
> +++ b/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', 'reorder', 'sched', 'security', 'stack', 'vhost',
> +	'reorder', 'sched', 'security', 'stack', 'vhost',
>  	# ipsec lib depends on net, crypto and security
>  	'ipsec',
>  	# add pkt framework libs which use other libs from above
> --
> 2.17.1