rte_ring_generic_pvt.h

/* SPDX-License-Identifier: BSD-3-Clause
 *
 * Copyright (c) 2010-2017 Intel Corporation
 * Copyright (c) 2007-2009 Kip Macy kmacy@freebsd.org
 * All rights reserved.
 * Derived from FreeBSD's bufring.h
 * Used as BSD-3 Licensed with permission from Kip Macy.
 */

#ifndef _RTE_RING_GENERIC_PVT_H_
#define _RTE_RING_GENERIC_PVT_H_

static __rte_always_inline void
__rte_ring_update_tail(struct rte_ring_headtail *ht, uint32_t old_val,
        uint32_t new_val, uint32_t single, uint32_t enqueue)
{
    if (enqueue)
        rte_smp_wmb();
    else
        rte_smp_rmb();
    /*
     * If there are other enqueues/dequeues in progress that preceded us,
     * we need to wait for them to complete
     */
    if (!single)
        while (unlikely(ht->tail != old_val))
            rte_pause();

    ht->tail = new_val;
}

static __rte_always_inline unsigned int
__rte_ring_move_prod_head(struct rte_ring *r, unsigned int is_sp,
        unsigned int n, enum rte_ring_queue_behavior behavior,
        uint32_t *old_head, uint32_t *new_head,
        uint32_t *free_entries)
{
    const uint32_t capacity = r->capacity;
    unsigned int max = n;
    int success;

    do {
        /* Reset n to the initial burst count */
        n = max;

        *old_head = r->prod.head;

        /* add rmb barrier to avoid load/load reorder in weak
         * memory model. It is noop on x86
         */
        rte_smp_rmb();

        /*
         *  The subtraction is done between two unsigned 32bits value
         * (the result is always modulo 32 bits even if we have
         * *old_head > cons_tail). So 'free_entries' is always between 0
         * and capacity (which is < size).
         */
        *free_entries = (capacity + r->cons.tail - *old_head);

        /* check that we have enough room in ring */
        if (unlikely(n > *free_entries))
            n = (behavior == RTE_RING_QUEUE_FIXED) ?
                    0 : *free_entries;

        if (n == 0)
            return 0;

        *new_head = *old_head + n;
        if (is_sp)
            r->prod.head = *new_head, success = 1;
        else
            success = rte_atomic32_cmpset(&r->prod.head,
                    *old_head, *new_head);
    } while (unlikely(success == 0));
    return n;
}

static __rte_always_inline unsigned int
__rte_ring_move_cons_head(struct rte_ring *r, unsigned int is_sc,
        unsigned int n, enum rte_ring_queue_behavior behavior,
        uint32_t *old_head, uint32_t *new_head,
        uint32_t *entries)
{
    unsigned int max = n;
    int success;

    /* move cons.head atomically */
    do {
        /* Restore n as it may change every loop */
        n = max;

        *old_head = r->cons.head;

        /* add rmb barrier to avoid load/load reorder in weak
         * memory model. It is noop on x86
         */
        rte_smp_rmb();

        /* The subtraction is done between two unsigned 32bits value
         * (the result is always modulo 32 bits even if we have
         * cons_head > prod_tail). So 'entries' is always between 0
         * and size(ring)-1.
         */
        *entries = (r->prod.tail - *old_head);

        /* Set the actual entries for dequeue */
        if (n > *entries)
            n = (behavior == RTE_RING_QUEUE_FIXED) ? 0 : *entries;

        if (unlikely(n == 0))
            return 0;

        *new_head = *old_head + n;
        if (is_sc) {
            r->cons.head = *new_head;
            rte_smp_rmb();
            success = 1;
        } else {
            success = rte_atomic32_cmpset(&r->cons.head, *old_head,
                    *new_head);
        }
    } while (unlikely(success == 0));
    return n;
}

#endif /* _RTE_RING_GENERIC_PVT_H_ */