mirror of
https://github.com/torvalds/linux.git
synced 2024-12-29 14:21:47 +00:00
d7ba4cc900
This patch changes the return types of bpf_map_ops functions to long, where previously int was returned. Using long allows for bpf programs to maintain the sign bit in the absence of sign extension during situations where inlined bpf helper funcs make calls to the bpf_map_ops funcs and a negative error is returned. The definitions of the helper funcs are generated from comments in the bpf uapi header at `include/uapi/linux/bpf.h`. The return type of these helpers was previously changed from int to long in commitbdb7b79b4c
. For any case where one of the map helpers call the bpf_map_ops funcs that are still returning 32-bit int, a compiler might not include sign extension instructions to properly convert the 32-bit negative value a 64-bit negative value. For example: bpf assembly excerpt of an inlined helper calling a kernel function and checking for a specific error: ; err = bpf_map_update_elem(&mymap, &key, &val, BPF_NOEXIST); ... 46: call 0xffffffffe103291c ; htab_map_update_elem ; if (err && err != -EEXIST) { 4b: cmp $0xffffffffffffffef,%rax ; cmp -EEXIST,%rax kernel function assembly excerpt of return value from `htab_map_update_elem` returning 32-bit int: movl $0xffffffef, %r9d ... movl %r9d, %eax ...results in the comparison: cmp $0xffffffffffffffef, $0x00000000ffffffef Fixes:bdb7b79b4c
("bpf: Switch most helper return values from 32-bit int to 64-bit long") Tested-by: Eduard Zingerman <eddyz87@gmail.com> Signed-off-by: JP Kobryn <inwardvessel@gmail.com> Link: https://lore.kernel.org/r/20230322194754.185781-3-inwardvessel@gmail.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
289 lines
6.8 KiB
C
289 lines
6.8 KiB
C
// 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 <linux/btf_ids.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 numa_node = bpf_map_attr_numa_node(attr);
|
|
struct bpf_queue_stack *qs;
|
|
u64 size, queue_size;
|
|
|
|
size = (u64) attr->max_entries + 1;
|
|
queue_size = sizeof(*qs) + size * attr->value_size;
|
|
|
|
qs = bpf_map_area_alloc(queue_size, numa_node);
|
|
if (!qs)
|
|
return ERR_PTR(-ENOMEM);
|
|
|
|
bpf_map_init_from_attr(&qs->map, attr);
|
|
|
|
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);
|
|
|
|
bpf_map_area_free(qs);
|
|
}
|
|
|
|
static long __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 long __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 long 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 long 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 long 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 long 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 long 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 long 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 long 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;
|
|
}
|
|
|
|
static u64 queue_stack_map_mem_usage(const struct bpf_map *map)
|
|
{
|
|
u64 usage = sizeof(struct bpf_queue_stack);
|
|
|
|
usage += ((u64)map->max_entries + 1) * map->value_size;
|
|
return usage;
|
|
}
|
|
|
|
BTF_ID_LIST_SINGLE(queue_map_btf_ids, struct, bpf_queue_stack)
|
|
const struct bpf_map_ops queue_map_ops = {
|
|
.map_meta_equal = bpf_map_meta_equal,
|
|
.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,
|
|
.map_mem_usage = queue_stack_map_mem_usage,
|
|
.map_btf_id = &queue_map_btf_ids[0],
|
|
};
|
|
|
|
const struct bpf_map_ops stack_map_ops = {
|
|
.map_meta_equal = bpf_map_meta_equal,
|
|
.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,
|
|
.map_mem_usage = queue_stack_map_mem_usage,
|
|
.map_btf_id = &queue_map_btf_ids[0],
|
|
};
|