rte_ring.h

Go to the documentation of this file.

/* 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_H_
#define _RTE_RING_H_

#ifdef __cplusplus
extern "C" {
#endif

#include <stdio.h>
#include <stdint.h>
#include <sys/queue.h>
#include <errno.h>
#include <rte_common.h>
#include <rte_config.h>
#include <rte_memory.h>
#include <rte_lcore.h>
#include <rte_atomic.h>
#include <rte_branch_prediction.h>
#include <rte_memzone.h>
#include <rte_pause.h>

#define RTE_TAILQ_RING_NAME "RTE_RING"

enum rte_ring_queue_behavior {
    RTE_RING_QUEUE_FIXED = 0, /* Enq/Deq a fixed number of items from a ring */
    RTE_RING_QUEUE_VARIABLE   /* Enq/Deq as many items as possible from ring */
};

#define RTE_RING_MZ_PREFIX "RG_"

#define RTE_RING_NAMESIZE (RTE_MEMZONE_NAMESIZE - \
               sizeof(RTE_RING_MZ_PREFIX) + 1)

/* structure to hold a pair of head/tail values and other metadata */
struct rte_ring_headtail {
    volatile uint32_t head;  
    volatile uint32_t tail;  
    uint32_t single;         
};

struct rte_ring {
    /*
     * Note: this field kept the RTE_MEMZONE_NAMESIZE size due to ABI
     * compatibility requirements, it could be changed to RTE_RING_NAMESIZE
     * next time the ABI changes
     */
    char name[RTE_MEMZONE_NAMESIZE] __rte_cache_aligned; 
    int flags;               
    const struct rte_memzone *memzone;
    uint32_t size;           
    uint32_t mask;           
    uint32_t capacity;       
    char pad0 __rte_cache_aligned; 
    struct rte_ring_headtail prod __rte_cache_aligned;
    char pad1 __rte_cache_aligned; 
    struct rte_ring_headtail cons __rte_cache_aligned;
    char pad2 __rte_cache_aligned; 
};

#define RING_F_SP_ENQ 0x0001 
#define RING_F_SC_DEQ 0x0002 
#define RING_F_EXACT_SZ 0x0004
#define RTE_RING_SZ_MASK  (0x7fffffffU) 
/* @internal defines for passing to the enqueue dequeue worker functions */
#define __IS_SP 1
#define __IS_MP 0
#define __IS_SC 1
#define __IS_MC 0

ssize_t rte_ring_get_memsize(unsigned count);

int rte_ring_init(struct rte_ring *r, const char *name, unsigned count,
    unsigned flags);

struct rte_ring *rte_ring_create(const char *name, unsigned count,
                 int socket_id, unsigned flags);
void rte_ring_free(struct rte_ring *r);

void rte_ring_dump(FILE *f, const struct rte_ring *r);

/* the actual enqueue of pointers on the ring.
 * Placed here since identical code needed in both
 * single and multi producer enqueue functions */
#define ENQUEUE_PTRS(r, ring_start, prod_head, obj_table, n, obj_type) do { \
    unsigned int i; \
    const uint32_t size = (r)->size; \
    uint32_t idx = prod_head & (r)->mask; \
    obj_type *ring = (obj_type *)ring_start; \
    if (likely(idx + n < size)) { \
        for (i = 0; i < (n & ((~(unsigned)0x3))); i+=4, idx+=4) { \
            ring[idx] = obj_table[i]; \
            ring[idx+1] = obj_table[i+1]; \
            ring[idx+2] = obj_table[i+2]; \
            ring[idx+3] = obj_table[i+3]; \
        } \
        switch (n & 0x3) { \
        case 3: \
            ring[idx++] = obj_table[i++]; /* fallthrough */ \
        case 2: \
            ring[idx++] = obj_table[i++]; /* fallthrough */ \
        case 1: \
            ring[idx++] = obj_table[i++]; \
        } \
    } else { \
        for (i = 0; idx < size; i++, idx++)\
            ring[idx] = obj_table[i]; \
        for (idx = 0; i < n; i++, idx++) \
            ring[idx] = obj_table[i]; \
    } \
} while (0)

/* the actual copy of pointers on the ring to obj_table.
 * Placed here since identical code needed in both
 * single and multi consumer dequeue functions */
#define DEQUEUE_PTRS(r, ring_start, cons_head, obj_table, n, obj_type) do { \
    unsigned int i; \
    uint32_t idx = cons_head & (r)->mask; \
    const uint32_t size = (r)->size; \
    obj_type *ring = (obj_type *)ring_start; \
    if (likely(idx + n < size)) { \
        for (i = 0; i < (n & (~(unsigned)0x3)); i+=4, idx+=4) {\
            obj_table[i] = ring[idx]; \
            obj_table[i+1] = ring[idx+1]; \
            obj_table[i+2] = ring[idx+2]; \
            obj_table[i+3] = ring[idx+3]; \
        } \
        switch (n & 0x3) { \
        case 3: \
            obj_table[i++] = ring[idx++]; /* fallthrough */ \
        case 2: \
            obj_table[i++] = ring[idx++]; /* fallthrough */ \
        case 1: \
            obj_table[i++] = ring[idx++]; \
        } \
    } else { \
        for (i = 0; idx < size; i++, idx++) \
            obj_table[i] = ring[idx]; \
        for (idx = 0; i < n; i++, idx++) \
            obj_table[i] = ring[idx]; \
    } \
} while (0)

/* Between load and load. there might be cpu reorder in weak model
 * (powerpc/arm).
 * There are 2 choices for the users
 * 1.use rmb() memory barrier
 * 2.use one-direction load_acquire/store_release barrier,defined by
 * CONFIG_RTE_USE_C11_MEM_MODEL=y
 * It depends on performance test results.
 * By default, move common functions to rte_ring_generic.h
 */
#ifdef RTE_USE_C11_MEM_MODEL
#include "rte_ring_c11_mem.h"
#else
#include "rte_ring_generic.h"
#endif

static __rte_always_inline unsigned int
__rte_ring_do_enqueue(struct rte_ring *r, void * const *obj_table,
         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;

    ENQUEUE_PTRS(r, &r[1], prod_head, obj_table, n, void *);

    update_tail(&r->prod, prod_head, prod_next, is_sp, 1);
end:
    if (free_space != NULL)
        *free_space = free_entries - n;
    return n;
}

static __rte_always_inline unsigned int
__rte_ring_do_dequeue(struct rte_ring *r, void **obj_table,
         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;

    DEQUEUE_PTRS(r, &r[1], cons_head, obj_table, n, void *);

    update_tail(&r->cons, cons_head, cons_next, is_sc, 0);

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

static __rte_always_inline unsigned int
rte_ring_mp_enqueue_bulk(struct rte_ring *r, void * const *obj_table,
             unsigned int n, unsigned int *free_space)
{
    return __rte_ring_do_enqueue(r, obj_table, n, RTE_RING_QUEUE_FIXED,
            __IS_MP, free_space);
}

static __rte_always_inline unsigned int
rte_ring_sp_enqueue_bulk(struct rte_ring *r, void * const *obj_table,
             unsigned int n, unsigned int *free_space)
{
    return __rte_ring_do_enqueue(r, obj_table, n, RTE_RING_QUEUE_FIXED,
            __IS_SP, free_space);
}

static __rte_always_inline unsigned int
rte_ring_enqueue_bulk(struct rte_ring *r, void * const *obj_table,
              unsigned int n, unsigned int *free_space)
{
    return __rte_ring_do_enqueue(r, obj_table, n, RTE_RING_QUEUE_FIXED,
            r->prod.single, free_space);
}

static __rte_always_inline int
rte_ring_mp_enqueue(struct rte_ring *r, void *obj)
{
    return rte_ring_mp_enqueue_bulk(r, &obj, 1, NULL) ? 0 : -ENOBUFS;
}

static __rte_always_inline int
rte_ring_sp_enqueue(struct rte_ring *r, void *obj)
{
    return rte_ring_sp_enqueue_bulk(r, &obj, 1, NULL) ? 0 : -ENOBUFS;
}

static __rte_always_inline int
rte_ring_enqueue(struct rte_ring *r, void *obj)
{
    return rte_ring_enqueue_bulk(r, &obj, 1, NULL) ? 0 : -ENOBUFS;
}

static __rte_always_inline unsigned int
rte_ring_mc_dequeue_bulk(struct rte_ring *r, void **obj_table,
        unsigned int n, unsigned int *available)
{
    return __rte_ring_do_dequeue(r, obj_table, n, RTE_RING_QUEUE_FIXED,
            __IS_MC, available);
}

static __rte_always_inline unsigned int
rte_ring_sc_dequeue_bulk(struct rte_ring *r, void **obj_table,
        unsigned int n, unsigned int *available)
{
    return __rte_ring_do_dequeue(r, obj_table, n, RTE_RING_QUEUE_FIXED,
            __IS_SC, available);
}

static __rte_always_inline unsigned int
rte_ring_dequeue_bulk(struct rte_ring *r, void **obj_table, unsigned int n,
        unsigned int *available)
{
    return __rte_ring_do_dequeue(r, obj_table, n, RTE_RING_QUEUE_FIXED,
                r->cons.single, available);
}

static __rte_always_inline int
rte_ring_mc_dequeue(struct rte_ring *r, void **obj_p)
{
    return rte_ring_mc_dequeue_bulk(r, obj_p, 1, NULL)  ? 0 : -ENOENT;
}

static __rte_always_inline int
rte_ring_sc_dequeue(struct rte_ring *r, void **obj_p)
{
    return rte_ring_sc_dequeue_bulk(r, obj_p, 1, NULL) ? 0 : -ENOENT;
}

static __rte_always_inline int
rte_ring_dequeue(struct rte_ring *r, void **obj_p)
{
    return rte_ring_dequeue_bulk(r, obj_p, 1, NULL) ? 0 : -ENOENT;
}

__rte_experimental
void
rte_ring_reset(struct rte_ring *r);

static inline unsigned
rte_ring_count(const struct rte_ring *r)
{
    uint32_t prod_tail = r->prod.tail;
    uint32_t cons_tail = r->cons.tail;
    uint32_t count = (prod_tail - cons_tail) & r->mask;
    return (count > r->capacity) ? r->capacity : count;
}

static inline unsigned
rte_ring_free_count(const struct rte_ring *r)
{
    return r->capacity - rte_ring_count(r);
}

static inline int
rte_ring_full(const struct rte_ring *r)
{
    return rte_ring_free_count(r) == 0;
}

static inline int
rte_ring_empty(const struct rte_ring *r)
{
    return rte_ring_count(r) == 0;
}

static inline unsigned int
rte_ring_get_size(const struct rte_ring *r)
{
    return r->size;
}

static inline unsigned int
rte_ring_get_capacity(const struct rte_ring *r)
{
    return r->capacity;
}

void rte_ring_list_dump(FILE *f);

struct rte_ring *rte_ring_lookup(const char *name);

static __rte_always_inline unsigned
rte_ring_mp_enqueue_burst(struct rte_ring *r, void * const *obj_table,
             unsigned int n, unsigned int *free_space)
{
    return __rte_ring_do_enqueue(r, obj_table, n,
            RTE_RING_QUEUE_VARIABLE, __IS_MP, free_space);
}

static __rte_always_inline unsigned
rte_ring_sp_enqueue_burst(struct rte_ring *r, void * const *obj_table,
             unsigned int n, unsigned int *free_space)
{
    return __rte_ring_do_enqueue(r, obj_table, n,
            RTE_RING_QUEUE_VARIABLE, __IS_SP, free_space);
}

static __rte_always_inline unsigned
rte_ring_enqueue_burst(struct rte_ring *r, void * const *obj_table,
              unsigned int n, unsigned int *free_space)
{
    return __rte_ring_do_enqueue(r, obj_table, n, RTE_RING_QUEUE_VARIABLE,
            r->prod.single, free_space);
}

static __rte_always_inline unsigned
rte_ring_mc_dequeue_burst(struct rte_ring *r, void **obj_table,
        unsigned int n, unsigned int *available)
{
    return __rte_ring_do_dequeue(r, obj_table, n,
            RTE_RING_QUEUE_VARIABLE, __IS_MC, available);
}

static __rte_always_inline unsigned
rte_ring_sc_dequeue_burst(struct rte_ring *r, void **obj_table,
        unsigned int n, unsigned int *available)
{
    return __rte_ring_do_dequeue(r, obj_table, n,
            RTE_RING_QUEUE_VARIABLE, __IS_SC, available);
}

static __rte_always_inline unsigned
rte_ring_dequeue_burst(struct rte_ring *r, void **obj_table,
        unsigned int n, unsigned int *available)
{
    return __rte_ring_do_dequeue(r, obj_table, n,
                RTE_RING_QUEUE_VARIABLE,
                r->cons.single, available);
}

#ifdef __cplusplus
}
#endif

#endif /* _RTE_RING_H_ */