rte_graph_worker.h

Go to the documentation of this file.

/* SPDX-License-Identifier: BSD-3-Clause
 * Copyright(C) 2020 Marvell International Ltd.
 */

#ifndef _RTE_GRAPH_WORKER_H_
#define _RTE_GRAPH_WORKER_H_

#include <rte_common.h>
#include <rte_cycles.h>
#include <rte_prefetch.h>
#include <rte_memcpy.h>
#include <rte_memory.h>

#include "rte_graph.h"

#ifdef __cplusplus
extern "C" {
#endif

struct rte_graph {
    uint32_t tail;           
    uint32_t head;           
    uint32_t cir_mask;       
    rte_node_t nb_nodes;         
    rte_graph_off_t *cir_start;  
    rte_graph_off_t nodes_start; 
    rte_graph_t id; 
    int socket; 
    char name[RTE_GRAPH_NAMESIZE];  
    uint64_t fence;         
} __rte_cache_aligned;

struct rte_node {
    /* Slow path area  */
    uint64_t fence;     
    rte_graph_off_t next;   
    rte_node_t id;      
    rte_node_t parent_id;   
    rte_edge_t nb_edges;    
    uint32_t realloc_count; 
    char parent[RTE_NODE_NAMESIZE]; 
    char name[RTE_NODE_NAMESIZE];   
    /* Fast path area  */
#define RTE_NODE_CTX_SZ 16
    uint8_t ctx[RTE_NODE_CTX_SZ] __rte_cache_aligned; 
    uint16_t size;      
    uint16_t idx;       
    rte_graph_off_t off;    
    uint64_t total_cycles;  
    uint64_t total_calls;   
    uint64_t total_objs;    
    RTE_STD_C11
        union {
            void **objs;       
            uint64_t objs_u64;
        };
    RTE_STD_C11
        union {
            rte_node_process_t process; 
            uint64_t process_u64;
        };
    struct rte_node *nodes[] __rte_cache_min_aligned; 
} __rte_cache_aligned;

__rte_experimental
void __rte_node_stream_alloc(struct rte_graph *graph, struct rte_node *node);

__rte_experimental
void __rte_node_stream_alloc_size(struct rte_graph *graph,
                  struct rte_node *node, uint16_t req_size);

__rte_experimental
static inline void
rte_graph_walk(struct rte_graph *graph)
{
    const rte_graph_off_t *cir_start = graph->cir_start;
    const rte_node_t mask = graph->cir_mask;
    uint32_t head = graph->head;
    struct rte_node *node;
    uint64_t start;
    uint16_t rc;
    void **objs;

    /*
     * Walk on the source node(s) ((cir_start - head) -> cir_start) and then
     * on the pending streams (cir_start -> (cir_start + mask) -> cir_start)
     * in a circular buffer fashion.
     *
     *  +-----+ <= cir_start - head [number of source nodes]
     *  |     |
     *  | ... | <= source nodes
     *  |     |
     *  +-----+ <= cir_start [head = 0] [tail = 0]
     *  |     |
     *  | ... | <= pending streams
     *  |     |
     *  +-----+ <= cir_start + mask
     */
    while (likely(head != graph->tail)) {
        node = (struct rte_node *)RTE_PTR_ADD(graph, cir_start[(int32_t)head++]);
        RTE_ASSERT(node->fence == RTE_GRAPH_FENCE);
        objs = node->objs;
        rte_prefetch0(objs);

        if (rte_graph_has_stats_feature()) {
            start = rte_rdtsc();
            rc = node->process(graph, node, objs, node->idx);
            node->total_cycles += rte_rdtsc() - start;
            node->total_calls++;
            node->total_objs += rc;
        } else {
            node->process(graph, node, objs, node->idx);
        }
        node->idx = 0;
        head = likely((int32_t)head > 0) ? head & mask : head;
    }
    graph->tail = 0;
}

/* Fast path helper functions */

static __rte_always_inline void
__rte_node_enqueue_tail_update(struct rte_graph *graph, struct rte_node *node)
{
    uint32_t tail;

    tail = graph->tail;
    graph->cir_start[tail++] = node->off;
    graph->tail = tail & graph->cir_mask;
}

static __rte_always_inline void
__rte_node_enqueue_prologue(struct rte_graph *graph, struct rte_node *node,
                const uint16_t idx, const uint16_t space)
{

    /* Add to the pending stream list if the node is new */
    if (idx == 0)
        __rte_node_enqueue_tail_update(graph, node);

    if (unlikely(node->size < (idx + space)))
        __rte_node_stream_alloc_size(graph, node, node->size + space);
}

static __rte_always_inline struct rte_node *
__rte_node_next_node_get(struct rte_node *node, rte_edge_t next)
{
    RTE_ASSERT(next < node->nb_edges);
    RTE_ASSERT(node->fence == RTE_GRAPH_FENCE);
    node = node->nodes[next];
    RTE_ASSERT(node->fence == RTE_GRAPH_FENCE);

    return node;
}

__rte_experimental
static inline void
rte_node_enqueue(struct rte_graph *graph, struct rte_node *node,
         rte_edge_t next, void **objs, uint16_t nb_objs)
{
    node = __rte_node_next_node_get(node, next);
    const uint16_t idx = node->idx;

    __rte_node_enqueue_prologue(graph, node, idx, nb_objs);

    rte_memcpy(&node->objs[idx], objs, nb_objs * sizeof(void *));
    node->idx = idx + nb_objs;
}

__rte_experimental
static inline void
rte_node_enqueue_x1(struct rte_graph *graph, struct rte_node *node,
            rte_edge_t next, void *obj)
{
    node = __rte_node_next_node_get(node, next);
    uint16_t idx = node->idx;

    __rte_node_enqueue_prologue(graph, node, idx, 1);

    node->objs[idx++] = obj;
    node->idx = idx;
}

__rte_experimental
static inline void
rte_node_enqueue_x2(struct rte_graph *graph, struct rte_node *node,
            rte_edge_t next, void *obj0, void *obj1)
{
    node = __rte_node_next_node_get(node, next);
    uint16_t idx = node->idx;

    __rte_node_enqueue_prologue(graph, node, idx, 2);

    node->objs[idx++] = obj0;
    node->objs[idx++] = obj1;
    node->idx = idx;
}

__rte_experimental
static inline void
rte_node_enqueue_x4(struct rte_graph *graph, struct rte_node *node,
            rte_edge_t next, void *obj0, void *obj1, void *obj2,
            void *obj3)
{
    node = __rte_node_next_node_get(node, next);
    uint16_t idx = node->idx;

    __rte_node_enqueue_prologue(graph, node, idx, 4);

    node->objs[idx++] = obj0;
    node->objs[idx++] = obj1;
    node->objs[idx++] = obj2;
    node->objs[idx++] = obj3;
    node->idx = idx;
}

__rte_experimental
static inline void
rte_node_enqueue_next(struct rte_graph *graph, struct rte_node *node,
              rte_edge_t *nexts, void **objs, uint16_t nb_objs)
{
    uint16_t i;

    for (i = 0; i < nb_objs; i++)
        rte_node_enqueue_x1(graph, node, nexts[i], objs[i]);
}

__rte_experimental
static inline void **
rte_node_next_stream_get(struct rte_graph *graph, struct rte_node *node,
             rte_edge_t next, uint16_t nb_objs)
{
    node = __rte_node_next_node_get(node, next);
    const uint16_t idx = node->idx;
    uint16_t free_space = node->size - idx;

    if (unlikely(free_space < nb_objs))
        __rte_node_stream_alloc_size(graph, node, node->size + nb_objs);

    return &node->objs[idx];
}

__rte_experimental
static inline void
rte_node_next_stream_put(struct rte_graph *graph, struct rte_node *node,
             rte_edge_t next, uint16_t idx)
{
    if (unlikely(!idx))
        return;

    node = __rte_node_next_node_get(node, next);
    if (node->idx == 0)
        __rte_node_enqueue_tail_update(graph, node);

    node->idx += idx;
}

__rte_experimental
static inline void
rte_node_next_stream_move(struct rte_graph *graph, struct rte_node *src,
              rte_edge_t next)
{
    struct rte_node *dst = __rte_node_next_node_get(src, next);

    /* Let swap the pointers if dst don't have valid objs */
    if (likely(dst->idx == 0)) {
        void **dobjs = dst->objs;
        uint16_t dsz = dst->size;
        dst->objs = src->objs;
        dst->size = src->size;
        src->objs = dobjs;
        src->size = dsz;
        dst->idx = src->idx;
        __rte_node_enqueue_tail_update(graph, dst);
    } else { /* Move the objects from src node to dst node */
        rte_node_enqueue(graph, src, next, src->objs, src->idx);
    }
}

#ifdef __cplusplus
}
#endif

#endif /* _RTE_GRAPH_WORKER_H_ */