1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
|
/* SPDX-License-Identifier: BSD-3-Clause
* Copyright(C) 2023 Intel Corporation
*/
#include "graph_private.h"
#include <eal_export.h>
#include "rte_graph_model_mcore_dispatch.h"
int
graph_sched_wq_create(struct graph *_graph, struct graph *_parent_graph,
struct rte_graph_param *prm)
{
struct rte_graph *parent_graph = _parent_graph->graph;
struct rte_graph *graph = _graph->graph;
unsigned int wq_size;
unsigned int flags = RING_F_SC_DEQ;
wq_size = RTE_GRAPH_SCHED_WQ_SIZE(graph->nb_nodes);
wq_size = rte_align32pow2(wq_size + 1);
if (prm->dispatch.wq_size_max > 0)
wq_size = wq_size <= (prm->dispatch.wq_size_max) ? wq_size :
prm->dispatch.wq_size_max;
if (!rte_is_power_of_2(wq_size))
flags |= RING_F_EXACT_SZ;
graph->dispatch.wq = rte_ring_create(graph->name, wq_size, graph->socket,
flags);
if (graph->dispatch.wq == NULL)
SET_ERR_JMP(EIO, fail, "Failed to allocate graph WQ");
if (prm->dispatch.mp_capacity > 0)
wq_size = (wq_size <= prm->dispatch.mp_capacity) ? wq_size :
prm->dispatch.mp_capacity;
graph->dispatch.mp = rte_mempool_create(graph->name, wq_size,
sizeof(struct graph_mcore_dispatch_wq_node),
0, 0, NULL, NULL, NULL, NULL,
graph->socket, MEMPOOL_F_SP_PUT);
if (graph->dispatch.mp == NULL)
SET_ERR_JMP(EIO, fail_mp,
"Failed to allocate graph WQ schedule entry");
graph->dispatch.lcore_id = _graph->lcore_id;
if (parent_graph->dispatch.rq == NULL) {
parent_graph->dispatch.rq = &parent_graph->dispatch.rq_head;
SLIST_INIT(parent_graph->dispatch.rq);
}
graph->dispatch.rq = parent_graph->dispatch.rq;
SLIST_INSERT_HEAD(graph->dispatch.rq, graph, next);
return 0;
fail_mp:
rte_ring_free(graph->dispatch.wq);
graph->dispatch.wq = NULL;
fail:
return -rte_errno;
}
void
graph_sched_wq_destroy(struct graph *_graph)
{
struct rte_graph *graph = _graph->graph;
if (graph == NULL)
return;
rte_ring_free(graph->dispatch.wq);
graph->dispatch.wq = NULL;
rte_mempool_free(graph->dispatch.mp);
graph->dispatch.mp = NULL;
}
static __rte_always_inline bool
__graph_sched_node_enqueue(struct rte_node *node, struct rte_graph *graph)
{
struct graph_mcore_dispatch_wq_node *wq_node;
uint16_t off = 0;
uint16_t size;
submit_again:
if (rte_mempool_get(graph->dispatch.mp, (void **)&wq_node) < 0)
goto fallback;
size = RTE_MIN(node->idx, RTE_DIM(wq_node->objs));
wq_node->node_off = node->off;
wq_node->nb_objs = size;
rte_memcpy(wq_node->objs, &node->objs[off], size * sizeof(void *));
while (rte_ring_mp_enqueue_bulk_elem(graph->dispatch.wq, (void *)&wq_node,
sizeof(wq_node), 1, NULL) == 0)
rte_pause();
off += size;
node->dispatch.total_sched_objs += size;
node->idx -= size;
if (node->idx > 0)
goto submit_again;
if (graph->dispatch.notify_cb)
graph->dispatch.notify_cb(graph, graph->dispatch.cb_priv);
return true;
fallback:
if (off != 0)
memmove(&node->objs[0], &node->objs[off],
node->idx * sizeof(void *));
node->dispatch.total_sched_fail += node->idx;
return false;
}
RTE_EXPORT_SYMBOL(__rte_graph_mcore_dispatch_sched_node_enqueue)
bool __rte_noinline
__rte_graph_mcore_dispatch_sched_node_enqueue(struct rte_node *node,
struct rte_graph_rq_head *rq)
{
const unsigned int lcore_id = node->dispatch.lcore_id;
struct rte_graph *graph = node->dispatch.graph;
if (unlikely((!graph) || (graph->dispatch.lcore_id != lcore_id))) {
SLIST_FOREACH(graph, rq, next)
if (graph->dispatch.lcore_id == lcore_id)
break;
node->dispatch.graph = graph;
}
return graph != NULL ? __graph_sched_node_enqueue(node, graph) : false;
}
RTE_EXPORT_SYMBOL(__rte_graph_mcore_dispatch_sched_wq_process)
void
__rte_graph_mcore_dispatch_sched_wq_process(struct rte_graph *graph)
{
#define WQ_SZ 32
struct graph_mcore_dispatch_wq_node *wq_node;
struct rte_mempool *mp = graph->dispatch.mp;
struct rte_ring *wq = graph->dispatch.wq;
uint16_t idx, free_space;
struct rte_node *node;
unsigned int i, n;
struct graph_mcore_dispatch_wq_node *wq_nodes[WQ_SZ];
n = rte_ring_sc_dequeue_burst_elem(wq, wq_nodes, sizeof(wq_nodes[0]),
RTE_DIM(wq_nodes), NULL);
if (n == 0)
return;
for (i = 0; i < n; i++) {
wq_node = wq_nodes[i];
node = RTE_PTR_ADD(graph, wq_node->node_off);
RTE_ASSERT(node->fence == RTE_GRAPH_FENCE);
idx = node->idx;
free_space = node->size - idx;
if (unlikely(free_space < wq_node->nb_objs))
__rte_node_stream_alloc_size(graph, node, node->size + wq_node->nb_objs);
memmove(&node->objs[idx], wq_node->objs, wq_node->nb_objs * sizeof(void *));
node->idx = idx + wq_node->nb_objs;
__rte_node_process(graph, node);
wq_node->nb_objs = 0;
node->idx = 0;
}
rte_mempool_put_bulk(mp, (void **)wq_nodes, n);
}
RTE_EXPORT_SYMBOL(rte_graph_model_mcore_dispatch_node_lcore_affinity_set)
int
rte_graph_model_mcore_dispatch_node_lcore_affinity_set(const char *name, unsigned int lcore_id)
{
struct node *node;
int ret = -EINVAL;
if (lcore_id >= RTE_MAX_LCORE)
return ret;
graph_spinlock_lock();
STAILQ_FOREACH(node, node_list_head_get(), next) {
if (strncmp(node->name, name, RTE_NODE_NAMESIZE) == 0) {
node->lcore_id = lcore_id;
ret = 0;
break;
}
}
graph_spinlock_unlock();
return ret;
}
|
