Loading...
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 | // SPDX-License-Identifier: GPL-2.0
/*
* queue_stack_maps.c: BPF queue and stack maps
*
* Copyright (c) 2018 Politecnico di Torino
*/
#include <linux/bpf.h>
#include <linux/list.h>
#include <linux/slab.h>
#include <linux/capability.h>
#include "percpu_freelist.h"
#define QUEUE_STACK_CREATE_FLAG_MASK \
(BPF_F_NUMA_NODE | BPF_F_ACCESS_MASK)
struct bpf_queue_stack {
struct bpf_map map;
raw_spinlock_t lock;
u32 head, tail;
u32 size; /* max_entries + 1 */
char elements[] __aligned(8);
};
static struct bpf_queue_stack *bpf_queue_stack(struct bpf_map *map)
{
return container_of(map, struct bpf_queue_stack, map);
}
static bool queue_stack_map_is_empty(struct bpf_queue_stack *qs)
{
return qs->head == qs->tail;
}
static bool queue_stack_map_is_full(struct bpf_queue_stack *qs)
{
u32 head = qs->head + 1;
if (unlikely(head >= qs->size))
head = 0;
return head == qs->tail;
}
/* Called from syscall */
static int queue_stack_map_alloc_check(union bpf_attr *attr)
{
if (!bpf_capable())
return -EPERM;
/* check sanity of attributes */
if (attr->max_entries == 0 || attr->key_size != 0 ||
attr->value_size == 0 ||
attr->map_flags & ~QUEUE_STACK_CREATE_FLAG_MASK ||
!bpf_map_flags_access_ok(attr->map_flags))
return -EINVAL;
if (attr->value_size > KMALLOC_MAX_SIZE)
/* if value_size is bigger, the user space won't be able to
* access the elements.
*/
return -E2BIG;
return 0;
}
static struct bpf_map *queue_stack_map_alloc(union bpf_attr *attr)
{
int ret, numa_node = bpf_map_attr_numa_node(attr);
struct bpf_map_memory mem = {0};
struct bpf_queue_stack *qs;
u64 size, queue_size, cost;
size = (u64) attr->max_entries + 1;
cost = queue_size = sizeof(*qs) + size * attr->value_size;
ret = bpf_map_charge_init(&mem, cost);
if (ret < 0)
return ERR_PTR(ret);
qs = bpf_map_area_alloc(queue_size, numa_node);
if (!qs) {
bpf_map_charge_finish(&mem);
return ERR_PTR(-ENOMEM);
}
memset(qs, 0, sizeof(*qs));
bpf_map_init_from_attr(&qs->map, attr);
bpf_map_charge_move(&qs->map.memory, &mem);
qs->size = size;
raw_spin_lock_init(&qs->lock);
return &qs->map;
}
/* Called when map->refcnt goes to zero, either from workqueue or from syscall */
static void queue_stack_map_free(struct bpf_map *map)
{
struct bpf_queue_stack *qs = bpf_queue_stack(map);
/* at this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0,
* so the programs (can be more than one that used this map) were
* disconnected from events. Wait for outstanding critical sections in
* these programs to complete
*/
synchronize_rcu();
bpf_map_area_free(qs);
}
static int __queue_map_get(struct bpf_map *map, void *value, bool delete)
{
struct bpf_queue_stack *qs = bpf_queue_stack(map);
unsigned long flags;
int err = 0;
void *ptr;
raw_spin_lock_irqsave(&qs->lock, flags);
if (queue_stack_map_is_empty(qs)) {
memset(value, 0, qs->map.value_size);
err = -ENOENT;
goto out;
}
ptr = &qs->elements[qs->tail * qs->map.value_size];
memcpy(value, ptr, qs->map.value_size);
if (delete) {
if (unlikely(++qs->tail >= qs->size))
qs->tail = 0;
}
out:
raw_spin_unlock_irqrestore(&qs->lock, flags);
return err;
}
static int __stack_map_get(struct bpf_map *map, void *value, bool delete)
{
struct bpf_queue_stack *qs = bpf_queue_stack(map);
unsigned long flags;
int err = 0;
void *ptr;
u32 index;
raw_spin_lock_irqsave(&qs->lock, flags);
if (queue_stack_map_is_empty(qs)) {
memset(value, 0, qs->map.value_size);
err = -ENOENT;
goto out;
}
index = qs->head - 1;
if (unlikely(index >= qs->size))
index = qs->size - 1;
ptr = &qs->elements[index * qs->map.value_size];
memcpy(value, ptr, qs->map.value_size);
if (delete)
qs->head = index;
out:
raw_spin_unlock_irqrestore(&qs->lock, flags);
return err;
}
/* Called from syscall or from eBPF program */
static int queue_map_peek_elem(struct bpf_map *map, void *value)
{
return __queue_map_get(map, value, false);
}
/* Called from syscall or from eBPF program */
static int stack_map_peek_elem(struct bpf_map *map, void *value)
{
return __stack_map_get(map, value, false);
}
/* Called from syscall or from eBPF program */
static int queue_map_pop_elem(struct bpf_map *map, void *value)
{
return __queue_map_get(map, value, true);
}
/* Called from syscall or from eBPF program */
static int stack_map_pop_elem(struct bpf_map *map, void *value)
{
return __stack_map_get(map, value, true);
}
/* Called from syscall or from eBPF program */
static int queue_stack_map_push_elem(struct bpf_map *map, void *value,
u64 flags)
{
struct bpf_queue_stack *qs = bpf_queue_stack(map);
unsigned long irq_flags;
int err = 0;
void *dst;
/* BPF_EXIST is used to force making room for a new element in case the
* map is full
*/
bool replace = (flags & BPF_EXIST);
/* Check supported flags for queue and stack maps */
if (flags & BPF_NOEXIST || flags > BPF_EXIST)
return -EINVAL;
raw_spin_lock_irqsave(&qs->lock, irq_flags);
if (queue_stack_map_is_full(qs)) {
if (!replace) {
err = -E2BIG;
goto out;
}
/* advance tail pointer to overwrite oldest element */
if (unlikely(++qs->tail >= qs->size))
qs->tail = 0;
}
dst = &qs->elements[qs->head * qs->map.value_size];
memcpy(dst, value, qs->map.value_size);
if (unlikely(++qs->head >= qs->size))
qs->head = 0;
out:
raw_spin_unlock_irqrestore(&qs->lock, irq_flags);
return err;
}
/* Called from syscall or from eBPF program */
static void *queue_stack_map_lookup_elem(struct bpf_map *map, void *key)
{
return NULL;
}
/* Called from syscall or from eBPF program */
static int queue_stack_map_update_elem(struct bpf_map *map, void *key,
void *value, u64 flags)
{
return -EINVAL;
}
/* Called from syscall or from eBPF program */
static int queue_stack_map_delete_elem(struct bpf_map *map, void *key)
{
return -EINVAL;
}
/* Called from syscall */
static int queue_stack_map_get_next_key(struct bpf_map *map, void *key,
void *next_key)
{
return -EINVAL;
}
const struct bpf_map_ops queue_map_ops = {
.map_alloc_check = queue_stack_map_alloc_check,
.map_alloc = queue_stack_map_alloc,
.map_free = queue_stack_map_free,
.map_lookup_elem = queue_stack_map_lookup_elem,
.map_update_elem = queue_stack_map_update_elem,
.map_delete_elem = queue_stack_map_delete_elem,
.map_push_elem = queue_stack_map_push_elem,
.map_pop_elem = queue_map_pop_elem,
.map_peek_elem = queue_map_peek_elem,
.map_get_next_key = queue_stack_map_get_next_key,
};
const struct bpf_map_ops stack_map_ops = {
.map_alloc_check = queue_stack_map_alloc_check,
.map_alloc = queue_stack_map_alloc,
.map_free = queue_stack_map_free,
.map_lookup_elem = queue_stack_map_lookup_elem,
.map_update_elem = queue_stack_map_update_elem,
.map_delete_elem = queue_stack_map_delete_elem,
.map_push_elem = queue_stack_map_push_elem,
.map_pop_elem = stack_map_pop_elem,
.map_peek_elem = stack_map_peek_elem,
.map_get_next_key = queue_stack_map_get_next_key,
};
|