rte_ring_elem_pvt.h

/* SPDX-License-Identifier: BSD-3-Clause
 *
 * Copyright (c) 2017,2018 HXT-semitech 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_ELEM_PVT_H_
#define _RTE_RING_ELEM_PVT_H_

#if defined(RTE_TOOLCHAIN_GCC) && (GCC_VERSION >= 120000)
#pragma GCC diagnostic push
#pragma GCC diagnostic ignored "-Wstringop-overflow"
#pragma GCC diagnostic ignored "-Wstringop-overread"
#endif

static __rte_always_inline void
__rte_ring_enqueue_elems_32(void *ring_table, const void *obj_table,
    uint32_t size, uint32_t idx, uint32_t n)
{
    unsigned int i;

    uint32_t *ring = (uint32_t *)ring_table;
    const uint32_t *obj = (const uint32_t *)obj_table;

    if (likely(idx + n <= size)) {
        for (i = 0; i < (n & ~0x7); i += 8, idx += 8) {
            ring[idx] = obj[i];
            ring[idx + 1] = obj[i + 1];
            ring[idx + 2] = obj[i + 2];
            ring[idx + 3] = obj[i + 3];
            ring[idx + 4] = obj[i + 4];
            ring[idx + 5] = obj[i + 5];
            ring[idx + 6] = obj[i + 6];
            ring[idx + 7] = obj[i + 7];
        }
        switch (n & 0x7) {
        case 7:
            ring[idx++] = obj[i++]; /* fallthrough */
        case 6:
            ring[idx++] = obj[i++]; /* fallthrough */
        case 5:
            ring[idx++] = obj[i++]; /* fallthrough */
        case 4:
            ring[idx++] = obj[i++]; /* fallthrough */
        case 3:
            ring[idx++] = obj[i++]; /* fallthrough */
        case 2:
            ring[idx++] = obj[i++]; /* fallthrough */
        case 1:
            ring[idx++] = obj[i++]; /* fallthrough */
        }
    } else {
        for (i = 0; idx < size; i++, idx++)
            ring[idx] = obj[i];
        /* Start at the beginning */
        for (idx = 0; i < n; i++, idx++)
            ring[idx] = obj[i];
    }
}

static __rte_always_inline void
__rte_ring_enqueue_elems_64(void *ring_table, const void *obj_table,
    uint32_t size, uint32_t idx, uint32_t n)
{
    unsigned int i;

    uint64_t *ring = (uint64_t *)ring_table;
    const unaligned_uint64_t *obj = (const unaligned_uint64_t *)obj_table;

    if (likely(idx + n <= size)) {
        for (i = 0; i < (n & ~0x3); i += 4, idx += 4) {
            ring[idx] = obj[i];
            ring[idx + 1] = obj[i + 1];
            ring[idx + 2] = obj[i + 2];
            ring[idx + 3] = obj[i + 3];
        }
        switch (n & 0x3) {
        case 3:
            ring[idx++] = obj[i++]; /* fallthrough */
        case 2:
            ring[idx++] = obj[i++]; /* fallthrough */
        case 1:
            ring[idx++] = obj[i++];
        }
    } else {
        for (i = 0; idx < size; i++, idx++)
            ring[idx] = obj[i];
        /* Start at the beginning */
        for (idx = 0; i < n; i++, idx++)
            ring[idx] = obj[i];
    }
}

static __rte_always_inline void
__rte_ring_enqueue_elems_128(void *ring_table, const void *obj_table,
    uint32_t size, uint32_t idx, uint32_t n)
{
    unsigned int i;

    rte_int128_t *ring = (rte_int128_t *)ring_table;
    const rte_int128_t *obj = (const rte_int128_t *)obj_table;

    if (likely(idx + n <= size)) {
        for (i = 0; i < (n & ~0x1); i += 2, idx += 2)
            memcpy((void *)(ring + idx),
                (const void *)(obj + i), 32);
        switch (n & 0x1) {
        case 1:
            memcpy((void *)(ring + idx),
                (const void *)(obj + i), 16);
        }
    } else {
        for (i = 0; idx < size; i++, idx++)
            memcpy((void *)(ring + idx),
                (const void *)(obj + i), 16);
        /* Start at the beginning */
        for (idx = 0; i < n; i++, idx++)
            memcpy((void *)(ring + idx),
                (const void *)(obj + i), 16);
    }
}

/* the actual enqueue of elements on the ring.
 * Placed here since identical code needed in both
 * single and multi producer enqueue functions.
 */
static __rte_always_inline void
__rte_ring_do_enqueue_elems(void *ring_table, const void *obj_table,
    uint32_t size, uint32_t idx, uint32_t esize, uint32_t num)
{
    /* 8B and 16B copies implemented individually to retain
     * the current performance.
     */
    if (esize == 8)
        __rte_ring_enqueue_elems_64(ring_table, obj_table, size,
                idx, num);
    else if (esize == 16)
        __rte_ring_enqueue_elems_128(ring_table, obj_table, size,
                idx, num);
    else {
        uint32_t scale, nr_idx, nr_num, nr_size;

        /* Normalize to uint32_t */
        scale = esize / sizeof(uint32_t);
        nr_num = num * scale;
        nr_idx = idx * scale;
        nr_size = size * scale;
        __rte_ring_enqueue_elems_32(ring_table, obj_table, nr_size,
                nr_idx, nr_num);
    }
}

static __rte_always_inline void
__rte_ring_enqueue_elems(struct rte_ring *r, uint32_t prod_head,
        const void *obj_table, uint32_t esize, uint32_t num)
{
    __rte_ring_do_enqueue_elems(&r[1], obj_table, r->size,
            prod_head & r->mask, esize, num);
}

static __rte_always_inline void
__rte_ring_dequeue_elems_32(void *obj_table, const void *ring_table,
    uint32_t size, uint32_t idx, uint32_t n)
{
    unsigned int i;
    uint32_t *obj = (uint32_t *)obj_table;
    const uint32_t *ring = (const uint32_t *)ring_table;

    if (likely(idx + n <= size)) {
        for (i = 0; i < (n & ~0x7); i += 8, idx += 8) {
            obj[i] = ring[idx];
            obj[i + 1] = ring[idx + 1];
            obj[i + 2] = ring[idx + 2];
            obj[i + 3] = ring[idx + 3];
            obj[i + 4] = ring[idx + 4];
            obj[i + 5] = ring[idx + 5];
            obj[i + 6] = ring[idx + 6];
            obj[i + 7] = ring[idx + 7];
        }
        switch (n & 0x7) {
        case 7:
            obj[i++] = ring[idx++]; /* fallthrough */
        case 6:
            obj[i++] = ring[idx++]; /* fallthrough */
        case 5:
            obj[i++] = ring[idx++]; /* fallthrough */
        case 4:
            obj[i++] = ring[idx++]; /* fallthrough */
        case 3:
            obj[i++] = ring[idx++]; /* fallthrough */
        case 2:
            obj[i++] = ring[idx++]; /* fallthrough */
        case 1:
            obj[i++] = ring[idx++]; /* fallthrough */
        }
    } else {
        for (i = 0; idx < size; i++, idx++)
            obj[i] = ring[idx];
        /* Start at the beginning */
        for (idx = 0; i < n; i++, idx++)
            obj[i] = ring[idx];
    }
}

static __rte_always_inline void
__rte_ring_dequeue_elems_64(void *obj_table, const void *ring_table,
    uint32_t size, uint32_t idx, uint32_t n)
{
    unsigned int i;
    unaligned_uint64_t *obj = (unaligned_uint64_t *)obj_table;
    const uint64_t *ring = (const uint64_t *)ring_table;

    if (likely(idx + n <= size)) {
        for (i = 0; i < (n & ~0x3); i += 4, idx += 4) {
            obj[i] = ring[idx];
            obj[i + 1] = ring[idx + 1];
            obj[i + 2] = ring[idx + 2];
            obj[i + 3] = ring[idx + 3];
        }
        switch (n & 0x3) {
        case 3:
            obj[i++] = ring[idx++]; /* fallthrough */
        case 2:
            obj[i++] = ring[idx++]; /* fallthrough */
        case 1:
            obj[i++] = ring[idx++]; /* fallthrough */
        }
    } else {
        for (i = 0; idx < size; i++, idx++)
            obj[i] = ring[idx];
        /* Start at the beginning */
        for (idx = 0; i < n; i++, idx++)
            obj[i] = ring[idx];
    }
}

static __rte_always_inline void
__rte_ring_dequeue_elems_128(void *obj_table, const void *ring_table,
    uint32_t size, uint32_t idx, uint32_t n)
{
    unsigned int i;
    rte_int128_t *obj = (rte_int128_t *)obj_table;
    const rte_int128_t *ring = (const rte_int128_t *)ring_table;

    if (likely(idx + n <= size)) {
        for (i = 0; i < (n & ~0x1); i += 2, idx += 2)
            memcpy((obj + i), (const void *)(ring + idx), 32);
        switch (n & 0x1) {
        case 1:
            memcpy((obj + i), (const void *)(ring + idx), 16);
        }
    } else {
        for (i = 0; idx < size; i++, idx++)
            memcpy((obj + i), (const void *)(ring + idx), 16);
        /* Start at the beginning */
        for (idx = 0; i < n; i++, idx++)
            memcpy((obj + i), (const void *)(ring + idx), 16);
    }
}

/* the actual dequeue of elements from the ring.
 * Placed here since identical code needed in both
 * single and multi producer enqueue functions.
 */
static __rte_always_inline void
__rte_ring_do_dequeue_elems(void *obj_table, const void *ring_table,
    uint32_t size, uint32_t idx, uint32_t esize, uint32_t num)
{
    /* 8B and 16B copies implemented individually to retain
     * the current performance.
     */
    if (esize == 8)
        __rte_ring_dequeue_elems_64(obj_table, ring_table, size,
                idx, num);
    else if (esize == 16)
        __rte_ring_dequeue_elems_128(obj_table, ring_table, size,
                idx, num);
    else {
        uint32_t scale, nr_idx, nr_num, nr_size;

        /* Normalize to uint32_t */
        scale = esize / sizeof(uint32_t);
        nr_num = num * scale;
        nr_idx = idx * scale;
        nr_size = size * scale;
        __rte_ring_dequeue_elems_32(obj_table, ring_table, nr_size,
                nr_idx, nr_num);
    }
}

static __rte_always_inline void
__rte_ring_dequeue_elems(struct rte_ring *r, uint32_t cons_head,
        void *obj_table, uint32_t esize, uint32_t num)
{
    __rte_ring_do_dequeue_elems(obj_table, &r[1], r->size,
            cons_head & r->mask, esize, num);
}

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)
{
    /*
     * If there are other enqueues/dequeues in progress that preceded us,
     * we need to wait for them to complete
     */
    if (!single)
        rte_wait_until_equal_32((uint32_t *)(uintptr_t)&ht->tail, old_val,
            rte_memory_order_relaxed);

    /*
     * R0: Establishes a synchronizing edge with load-acquire of tail at A1.
     * Ensures that memory effects by this thread on ring elements array
     * is observed by a different thread of the other type.
     */
    rte_atomic_store_explicit(&ht->tail, new_val, rte_memory_order_release);
}

/*
 * The function __rte_ring_headtail_move_head_mt,st has two versions
 * based on what is most efficient on a given architecture.
 *
 * The C11 is preferred but on x86 GCC has 10% performance drop.
 */
#ifdef RTE_USE_C11_MEM_MODEL
#include "rte_ring_c11_pvt.h"
#else
#include "rte_ring_gcc_pvt.h"
#endif

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)
{
    if (is_sp)
        return __rte_ring_headtail_move_head_st(&r->prod, &r->cons, r->capacity,
                n, behavior, old_head, new_head, free_entries);
    else
        return __rte_ring_headtail_move_head_mt(&r->prod, &r->cons, r->capacity,
                n, behavior, old_head, new_head, free_entries);
}

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)
{
    if (is_sc)
        return __rte_ring_headtail_move_head_st(&r->cons, &r->prod, 0,
                n, behavior, old_head, new_head, entries);
    else
        return __rte_ring_headtail_move_head_mt(&r->cons, &r->prod, 0,
                n, behavior, old_head, new_head, entries);
}

static __rte_always_inline unsigned int
__rte_ring_do_enqueue_elem(struct rte_ring *r, const void *obj_table,
        unsigned int esize, unsigned int n,
        enum rte_ring_queue_behavior behavior, unsigned int is_sp,
        unsigned int *free_space)
{
    uint32_t prod_head, prod_next;
    uint32_t free_entries;

    n = __rte_ring_move_prod_head(r, is_sp, n, behavior,
            &prod_head, &prod_next, &free_entries);
    if (n == 0)
        goto end;

    __rte_ring_enqueue_elems(r, prod_head, obj_table, esize, n);

    __rte_ring_update_tail(&r->prod, prod_head, prod_next, is_sp);
end:
    if (free_space != NULL)
        *free_space = free_entries - n;
    return n;
}

static __rte_always_inline unsigned int
__rte_ring_do_dequeue_elem(struct rte_ring *r, void *obj_table,
        unsigned int esize, unsigned int n,
        enum rte_ring_queue_behavior behavior, unsigned int is_sc,
        unsigned int *available)
{
    uint32_t cons_head, cons_next;
    uint32_t entries;

    n = __rte_ring_move_cons_head(r, (int)is_sc, n, behavior,
            &cons_head, &cons_next, &entries);
    if (n == 0)
        goto end;

    __rte_ring_dequeue_elems(r, cons_head, obj_table, esize, n);

    __rte_ring_update_tail(&r->cons, cons_head, cons_next, is_sc);

end:
    if (available != NULL)
        *available = entries - n;
    return n;
}

#if defined(RTE_TOOLCHAIN_GCC) && (GCC_VERSION >= 120000)
#pragma GCC diagnostic pop
#endif

#endif /* _RTE_RING_ELEM_PVT_H_ */