linux/kernel/bpf/arraymap.c
Martin KaFai Lau 5dc4c4b7d4 bpf: Introduce BPF_MAP_TYPE_REUSEPORT_SOCKARRAY
This patch introduces a new map type BPF_MAP_TYPE_REUSEPORT_SOCKARRAY.

To unleash the full potential of a bpf prog, it is essential for the
userspace to be capable of directly setting up a bpf map which can then
be consumed by the bpf prog to make decision.  In this case, decide which
SO_REUSEPORT sk to serve the incoming request.

By adding BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, the userspace has total control
and visibility on where a SO_REUSEPORT sk should be located in a bpf map.
The later patch will introduce BPF_PROG_TYPE_SK_REUSEPORT such that
the bpf prog can directly select a sk from the bpf map.  That will
raise the programmability of the bpf prog attached to a reuseport
group (a group of sk serving the same IP:PORT).

For example, in UDP, the bpf prog can peek into the payload (e.g.
through the "data" pointer introduced in the later patch) to learn
the application level's connection information and then decide which sk
to pick from a bpf map.  The userspace can tightly couple the sk's location
in a bpf map with the application logic in generating the UDP payload's
connection information.  This connection info contact/API stays within the
userspace.

Also, when used with map-in-map, the userspace can switch the
old-server-process's inner map to a new-server-process's inner map
in one call "bpf_map_update_elem(outer_map, &index, &new_reuseport_array)".
The bpf prog will then direct incoming requests to the new process instead
of the old process.  The old process can finish draining the pending
requests (e.g. by "accept()") before closing the old-fds.  [Note that
deleting a fd from a bpf map does not necessary mean the fd is closed]

During map_update_elem(),
Only SO_REUSEPORT sk (i.e. which has already been added
to a reuse->socks[]) can be used.  That means a SO_REUSEPORT sk that is
"bind()" for UDP or "bind()+listen()" for TCP.  These conditions are
ensured in "reuseport_array_update_check()".

A SO_REUSEPORT sk can only be added once to a map (i.e. the
same sk cannot be added twice even to the same map).  SO_REUSEPORT
already allows another sk to be created for the same IP:PORT.
There is no need to re-create a similar usage in the BPF side.

When a SO_REUSEPORT is deleted from the "reuse->socks[]" (e.g. "close()"),
it will notify the bpf map to remove it from the map also.  It is
done through "bpf_sk_reuseport_detach()" and it will only be called
if >=1 of the "reuse->sock[]" has ever been added to a bpf map.

The map_update()/map_delete() has to be in-sync with the
"reuse->socks[]".  Hence, the same "reuseport_lock" used
by "reuse->socks[]" has to be used here also. Care has
been taken to ensure the lock is only acquired when the
adding sk passes some strict tests. and
freeing the map does not require the reuseport_lock.

The reuseport_array will also support lookup from the syscall
side.  It will return a sock_gen_cookie().  The sock_gen_cookie()
is on-demand (i.e. a sk's cookie is not generated until the very
first map_lookup_elem()).

The lookup cookie is 64bits but it goes against the logical userspace
expectation on 32bits sizeof(fd) (and as other fd based bpf maps do also).
It may catch user in surprise if we enforce value_size=8 while
userspace still pass a 32bits fd during update.  Supporting different
value_size between lookup and update seems unintuitive also.

We also need to consider what if other existing fd based maps want
to return 64bits value from syscall's lookup in the future.
Hence, reuseport_array supports both value_size 4 and 8, and
assuming user will usually use value_size=4.  The syscall's lookup
will return ENOSPC on value_size=4.  It will will only
return 64bits value from sock_gen_cookie() when user consciously
choose value_size=8 (as a signal that lookup is desired) which then
requires a 64bits value in both lookup and update.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-08-11 01:58:46 +02:00

753 lines
20 KiB
C

/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
* Copyright (c) 2016,2017 Facebook
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*/
#include <linux/bpf.h>
#include <linux/btf.h>
#include <linux/err.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/filter.h>
#include <linux/perf_event.h>
#include <uapi/linux/btf.h>
#include "map_in_map.h"
#define ARRAY_CREATE_FLAG_MASK \
(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
static void bpf_array_free_percpu(struct bpf_array *array)
{
int i;
for (i = 0; i < array->map.max_entries; i++) {
free_percpu(array->pptrs[i]);
cond_resched();
}
}
static int bpf_array_alloc_percpu(struct bpf_array *array)
{
void __percpu *ptr;
int i;
for (i = 0; i < array->map.max_entries; i++) {
ptr = __alloc_percpu_gfp(array->elem_size, 8,
GFP_USER | __GFP_NOWARN);
if (!ptr) {
bpf_array_free_percpu(array);
return -ENOMEM;
}
array->pptrs[i] = ptr;
cond_resched();
}
return 0;
}
/* Called from syscall */
int array_map_alloc_check(union bpf_attr *attr)
{
bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY;
int numa_node = bpf_map_attr_numa_node(attr);
/* check sanity of attributes */
if (attr->max_entries == 0 || attr->key_size != 4 ||
attr->value_size == 0 ||
attr->map_flags & ~ARRAY_CREATE_FLAG_MASK ||
(percpu && numa_node != NUMA_NO_NODE))
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 *array_map_alloc(union bpf_attr *attr)
{
bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY;
int ret, numa_node = bpf_map_attr_numa_node(attr);
u32 elem_size, index_mask, max_entries;
bool unpriv = !capable(CAP_SYS_ADMIN);
u64 cost, array_size, mask64;
struct bpf_array *array;
elem_size = round_up(attr->value_size, 8);
max_entries = attr->max_entries;
/* On 32 bit archs roundup_pow_of_two() with max_entries that has
* upper most bit set in u32 space is undefined behavior due to
* resulting 1U << 32, so do it manually here in u64 space.
*/
mask64 = fls_long(max_entries - 1);
mask64 = 1ULL << mask64;
mask64 -= 1;
index_mask = mask64;
if (unpriv) {
/* round up array size to nearest power of 2,
* since cpu will speculate within index_mask limits
*/
max_entries = index_mask + 1;
/* Check for overflows. */
if (max_entries < attr->max_entries)
return ERR_PTR(-E2BIG);
}
array_size = sizeof(*array);
if (percpu)
array_size += (u64) max_entries * sizeof(void *);
else
array_size += (u64) max_entries * elem_size;
/* make sure there is no u32 overflow later in round_up() */
cost = array_size;
if (cost >= U32_MAX - PAGE_SIZE)
return ERR_PTR(-ENOMEM);
if (percpu) {
cost += (u64)attr->max_entries * elem_size * num_possible_cpus();
if (cost >= U32_MAX - PAGE_SIZE)
return ERR_PTR(-ENOMEM);
}
cost = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
ret = bpf_map_precharge_memlock(cost);
if (ret < 0)
return ERR_PTR(ret);
/* allocate all map elements and zero-initialize them */
array = bpf_map_area_alloc(array_size, numa_node);
if (!array)
return ERR_PTR(-ENOMEM);
array->index_mask = index_mask;
array->map.unpriv_array = unpriv;
/* copy mandatory map attributes */
bpf_map_init_from_attr(&array->map, attr);
array->map.pages = cost;
array->elem_size = elem_size;
if (percpu && bpf_array_alloc_percpu(array)) {
bpf_map_area_free(array);
return ERR_PTR(-ENOMEM);
}
return &array->map;
}
/* Called from syscall or from eBPF program */
static void *array_map_lookup_elem(struct bpf_map *map, void *key)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
u32 index = *(u32 *)key;
if (unlikely(index >= array->map.max_entries))
return NULL;
return array->value + array->elem_size * (index & array->index_mask);
}
/* emit BPF instructions equivalent to C code of array_map_lookup_elem() */
static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
struct bpf_insn *insn = insn_buf;
u32 elem_size = round_up(map->value_size, 8);
const int ret = BPF_REG_0;
const int map_ptr = BPF_REG_1;
const int index = BPF_REG_2;
*insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value));
*insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0);
if (map->unpriv_array) {
*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 4);
*insn++ = BPF_ALU32_IMM(BPF_AND, ret, array->index_mask);
} else {
*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 3);
}
if (is_power_of_2(elem_size)) {
*insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(elem_size));
} else {
*insn++ = BPF_ALU64_IMM(BPF_MUL, ret, elem_size);
}
*insn++ = BPF_ALU64_REG(BPF_ADD, ret, map_ptr);
*insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1);
*insn++ = BPF_MOV64_IMM(ret, 0);
return insn - insn_buf;
}
/* Called from eBPF program */
static void *percpu_array_map_lookup_elem(struct bpf_map *map, void *key)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
u32 index = *(u32 *)key;
if (unlikely(index >= array->map.max_entries))
return NULL;
return this_cpu_ptr(array->pptrs[index & array->index_mask]);
}
int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
u32 index = *(u32 *)key;
void __percpu *pptr;
int cpu, off = 0;
u32 size;
if (unlikely(index >= array->map.max_entries))
return -ENOENT;
/* per_cpu areas are zero-filled and bpf programs can only
* access 'value_size' of them, so copying rounded areas
* will not leak any kernel data
*/
size = round_up(map->value_size, 8);
rcu_read_lock();
pptr = array->pptrs[index & array->index_mask];
for_each_possible_cpu(cpu) {
bpf_long_memcpy(value + off, per_cpu_ptr(pptr, cpu), size);
off += size;
}
rcu_read_unlock();
return 0;
}
/* Called from syscall */
static int array_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
u32 index = key ? *(u32 *)key : U32_MAX;
u32 *next = (u32 *)next_key;
if (index >= array->map.max_entries) {
*next = 0;
return 0;
}
if (index == array->map.max_entries - 1)
return -ENOENT;
*next = index + 1;
return 0;
}
/* Called from syscall or from eBPF program */
static int array_map_update_elem(struct bpf_map *map, void *key, void *value,
u64 map_flags)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
u32 index = *(u32 *)key;
if (unlikely(map_flags > BPF_EXIST))
/* unknown flags */
return -EINVAL;
if (unlikely(index >= array->map.max_entries))
/* all elements were pre-allocated, cannot insert a new one */
return -E2BIG;
if (unlikely(map_flags == BPF_NOEXIST))
/* all elements already exist */
return -EEXIST;
if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
memcpy(this_cpu_ptr(array->pptrs[index & array->index_mask]),
value, map->value_size);
else
memcpy(array->value +
array->elem_size * (index & array->index_mask),
value, map->value_size);
return 0;
}
int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value,
u64 map_flags)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
u32 index = *(u32 *)key;
void __percpu *pptr;
int cpu, off = 0;
u32 size;
if (unlikely(map_flags > BPF_EXIST))
/* unknown flags */
return -EINVAL;
if (unlikely(index >= array->map.max_entries))
/* all elements were pre-allocated, cannot insert a new one */
return -E2BIG;
if (unlikely(map_flags == BPF_NOEXIST))
/* all elements already exist */
return -EEXIST;
/* the user space will provide round_up(value_size, 8) bytes that
* will be copied into per-cpu area. bpf programs can only access
* value_size of it. During lookup the same extra bytes will be
* returned or zeros which were zero-filled by percpu_alloc,
* so no kernel data leaks possible
*/
size = round_up(map->value_size, 8);
rcu_read_lock();
pptr = array->pptrs[index & array->index_mask];
for_each_possible_cpu(cpu) {
bpf_long_memcpy(per_cpu_ptr(pptr, cpu), value + off, size);
off += size;
}
rcu_read_unlock();
return 0;
}
/* Called from syscall or from eBPF program */
static int array_map_delete_elem(struct bpf_map *map, void *key)
{
return -EINVAL;
}
/* Called when map->refcnt goes to zero, either from workqueue or from syscall */
static void array_map_free(struct bpf_map *map)
{
struct bpf_array *array = container_of(map, struct bpf_array, 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 programs to complete
* and free the array
*/
synchronize_rcu();
if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
bpf_array_free_percpu(array);
bpf_map_area_free(array);
}
static void array_map_seq_show_elem(struct bpf_map *map, void *key,
struct seq_file *m)
{
void *value;
rcu_read_lock();
value = array_map_lookup_elem(map, key);
if (!value) {
rcu_read_unlock();
return;
}
seq_printf(m, "%u: ", *(u32 *)key);
btf_type_seq_show(map->btf, map->btf_value_type_id, value, m);
seq_puts(m, "\n");
rcu_read_unlock();
}
static int array_map_check_btf(const struct bpf_map *map, const struct btf *btf,
u32 btf_key_id, u32 btf_value_id)
{
const struct btf_type *key_type, *value_type;
u32 key_size, value_size;
u32 int_data;
key_type = btf_type_id_size(btf, &btf_key_id, &key_size);
if (!key_type || BTF_INFO_KIND(key_type->info) != BTF_KIND_INT)
return -EINVAL;
int_data = *(u32 *)(key_type + 1);
/* bpf array can only take a u32 key. This check makes
* sure that the btf matches the attr used during map_create.
*/
if (BTF_INT_BITS(int_data) != 32 || key_size != 4 ||
BTF_INT_OFFSET(int_data))
return -EINVAL;
value_type = btf_type_id_size(btf, &btf_value_id, &value_size);
if (!value_type || value_size != map->value_size)
return -EINVAL;
return 0;
}
const struct bpf_map_ops array_map_ops = {
.map_alloc_check = array_map_alloc_check,
.map_alloc = array_map_alloc,
.map_free = array_map_free,
.map_get_next_key = array_map_get_next_key,
.map_lookup_elem = array_map_lookup_elem,
.map_update_elem = array_map_update_elem,
.map_delete_elem = array_map_delete_elem,
.map_gen_lookup = array_map_gen_lookup,
.map_seq_show_elem = array_map_seq_show_elem,
.map_check_btf = array_map_check_btf,
};
const struct bpf_map_ops percpu_array_map_ops = {
.map_alloc_check = array_map_alloc_check,
.map_alloc = array_map_alloc,
.map_free = array_map_free,
.map_get_next_key = array_map_get_next_key,
.map_lookup_elem = percpu_array_map_lookup_elem,
.map_update_elem = array_map_update_elem,
.map_delete_elem = array_map_delete_elem,
};
static int fd_array_map_alloc_check(union bpf_attr *attr)
{
/* only file descriptors can be stored in this type of map */
if (attr->value_size != sizeof(u32))
return -EINVAL;
return array_map_alloc_check(attr);
}
static void fd_array_map_free(struct bpf_map *map)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
int i;
synchronize_rcu();
/* make sure it's empty */
for (i = 0; i < array->map.max_entries; i++)
BUG_ON(array->ptrs[i] != NULL);
bpf_map_area_free(array);
}
static void *fd_array_map_lookup_elem(struct bpf_map *map, void *key)
{
return NULL;
}
/* only called from syscall */
int bpf_fd_array_map_lookup_elem(struct bpf_map *map, void *key, u32 *value)
{
void **elem, *ptr;
int ret = 0;
if (!map->ops->map_fd_sys_lookup_elem)
return -ENOTSUPP;
rcu_read_lock();
elem = array_map_lookup_elem(map, key);
if (elem && (ptr = READ_ONCE(*elem)))
*value = map->ops->map_fd_sys_lookup_elem(ptr);
else
ret = -ENOENT;
rcu_read_unlock();
return ret;
}
/* only called from syscall */
int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file,
void *key, void *value, u64 map_flags)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
void *new_ptr, *old_ptr;
u32 index = *(u32 *)key, ufd;
if (map_flags != BPF_ANY)
return -EINVAL;
if (index >= array->map.max_entries)
return -E2BIG;
ufd = *(u32 *)value;
new_ptr = map->ops->map_fd_get_ptr(map, map_file, ufd);
if (IS_ERR(new_ptr))
return PTR_ERR(new_ptr);
old_ptr = xchg(array->ptrs + index, new_ptr);
if (old_ptr)
map->ops->map_fd_put_ptr(old_ptr);
return 0;
}
static int fd_array_map_delete_elem(struct bpf_map *map, void *key)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
void *old_ptr;
u32 index = *(u32 *)key;
if (index >= array->map.max_entries)
return -E2BIG;
old_ptr = xchg(array->ptrs + index, NULL);
if (old_ptr) {
map->ops->map_fd_put_ptr(old_ptr);
return 0;
} else {
return -ENOENT;
}
}
static void *prog_fd_array_get_ptr(struct bpf_map *map,
struct file *map_file, int fd)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
struct bpf_prog *prog = bpf_prog_get(fd);
if (IS_ERR(prog))
return prog;
if (!bpf_prog_array_compatible(array, prog)) {
bpf_prog_put(prog);
return ERR_PTR(-EINVAL);
}
return prog;
}
static void prog_fd_array_put_ptr(void *ptr)
{
bpf_prog_put(ptr);
}
static u32 prog_fd_array_sys_lookup_elem(void *ptr)
{
return ((struct bpf_prog *)ptr)->aux->id;
}
/* decrement refcnt of all bpf_progs that are stored in this map */
static void bpf_fd_array_map_clear(struct bpf_map *map)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
int i;
for (i = 0; i < array->map.max_entries; i++)
fd_array_map_delete_elem(map, &i);
}
const struct bpf_map_ops prog_array_map_ops = {
.map_alloc_check = fd_array_map_alloc_check,
.map_alloc = array_map_alloc,
.map_free = fd_array_map_free,
.map_get_next_key = array_map_get_next_key,
.map_lookup_elem = fd_array_map_lookup_elem,
.map_delete_elem = fd_array_map_delete_elem,
.map_fd_get_ptr = prog_fd_array_get_ptr,
.map_fd_put_ptr = prog_fd_array_put_ptr,
.map_fd_sys_lookup_elem = prog_fd_array_sys_lookup_elem,
.map_release_uref = bpf_fd_array_map_clear,
};
static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file,
struct file *map_file)
{
struct bpf_event_entry *ee;
ee = kzalloc(sizeof(*ee), GFP_ATOMIC);
if (ee) {
ee->event = perf_file->private_data;
ee->perf_file = perf_file;
ee->map_file = map_file;
}
return ee;
}
static void __bpf_event_entry_free(struct rcu_head *rcu)
{
struct bpf_event_entry *ee;
ee = container_of(rcu, struct bpf_event_entry, rcu);
fput(ee->perf_file);
kfree(ee);
}
static void bpf_event_entry_free_rcu(struct bpf_event_entry *ee)
{
call_rcu(&ee->rcu, __bpf_event_entry_free);
}
static void *perf_event_fd_array_get_ptr(struct bpf_map *map,
struct file *map_file, int fd)
{
struct bpf_event_entry *ee;
struct perf_event *event;
struct file *perf_file;
u64 value;
perf_file = perf_event_get(fd);
if (IS_ERR(perf_file))
return perf_file;
ee = ERR_PTR(-EOPNOTSUPP);
event = perf_file->private_data;
if (perf_event_read_local(event, &value, NULL, NULL) == -EOPNOTSUPP)
goto err_out;
ee = bpf_event_entry_gen(perf_file, map_file);
if (ee)
return ee;
ee = ERR_PTR(-ENOMEM);
err_out:
fput(perf_file);
return ee;
}
static void perf_event_fd_array_put_ptr(void *ptr)
{
bpf_event_entry_free_rcu(ptr);
}
static void perf_event_fd_array_release(struct bpf_map *map,
struct file *map_file)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
struct bpf_event_entry *ee;
int i;
rcu_read_lock();
for (i = 0; i < array->map.max_entries; i++) {
ee = READ_ONCE(array->ptrs[i]);
if (ee && ee->map_file == map_file)
fd_array_map_delete_elem(map, &i);
}
rcu_read_unlock();
}
const struct bpf_map_ops perf_event_array_map_ops = {
.map_alloc_check = fd_array_map_alloc_check,
.map_alloc = array_map_alloc,
.map_free = fd_array_map_free,
.map_get_next_key = array_map_get_next_key,
.map_lookup_elem = fd_array_map_lookup_elem,
.map_delete_elem = fd_array_map_delete_elem,
.map_fd_get_ptr = perf_event_fd_array_get_ptr,
.map_fd_put_ptr = perf_event_fd_array_put_ptr,
.map_release = perf_event_fd_array_release,
};
#ifdef CONFIG_CGROUPS
static void *cgroup_fd_array_get_ptr(struct bpf_map *map,
struct file *map_file /* not used */,
int fd)
{
return cgroup_get_from_fd(fd);
}
static void cgroup_fd_array_put_ptr(void *ptr)
{
/* cgroup_put free cgrp after a rcu grace period */
cgroup_put(ptr);
}
static void cgroup_fd_array_free(struct bpf_map *map)
{
bpf_fd_array_map_clear(map);
fd_array_map_free(map);
}
const struct bpf_map_ops cgroup_array_map_ops = {
.map_alloc_check = fd_array_map_alloc_check,
.map_alloc = array_map_alloc,
.map_free = cgroup_fd_array_free,
.map_get_next_key = array_map_get_next_key,
.map_lookup_elem = fd_array_map_lookup_elem,
.map_delete_elem = fd_array_map_delete_elem,
.map_fd_get_ptr = cgroup_fd_array_get_ptr,
.map_fd_put_ptr = cgroup_fd_array_put_ptr,
};
#endif
static struct bpf_map *array_of_map_alloc(union bpf_attr *attr)
{
struct bpf_map *map, *inner_map_meta;
inner_map_meta = bpf_map_meta_alloc(attr->inner_map_fd);
if (IS_ERR(inner_map_meta))
return inner_map_meta;
map = array_map_alloc(attr);
if (IS_ERR(map)) {
bpf_map_meta_free(inner_map_meta);
return map;
}
map->inner_map_meta = inner_map_meta;
return map;
}
static void array_of_map_free(struct bpf_map *map)
{
/* map->inner_map_meta is only accessed by syscall which
* is protected by fdget/fdput.
*/
bpf_map_meta_free(map->inner_map_meta);
bpf_fd_array_map_clear(map);
fd_array_map_free(map);
}
static void *array_of_map_lookup_elem(struct bpf_map *map, void *key)
{
struct bpf_map **inner_map = array_map_lookup_elem(map, key);
if (!inner_map)
return NULL;
return READ_ONCE(*inner_map);
}
static u32 array_of_map_gen_lookup(struct bpf_map *map,
struct bpf_insn *insn_buf)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
u32 elem_size = round_up(map->value_size, 8);
struct bpf_insn *insn = insn_buf;
const int ret = BPF_REG_0;
const int map_ptr = BPF_REG_1;
const int index = BPF_REG_2;
*insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value));
*insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0);
if (map->unpriv_array) {
*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 6);
*insn++ = BPF_ALU32_IMM(BPF_AND, ret, array->index_mask);
} else {
*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 5);
}
if (is_power_of_2(elem_size))
*insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(elem_size));
else
*insn++ = BPF_ALU64_IMM(BPF_MUL, ret, elem_size);
*insn++ = BPF_ALU64_REG(BPF_ADD, ret, map_ptr);
*insn++ = BPF_LDX_MEM(BPF_DW, ret, ret, 0);
*insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 1);
*insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1);
*insn++ = BPF_MOV64_IMM(ret, 0);
return insn - insn_buf;
}
const struct bpf_map_ops array_of_maps_map_ops = {
.map_alloc_check = fd_array_map_alloc_check,
.map_alloc = array_of_map_alloc,
.map_free = array_of_map_free,
.map_get_next_key = array_map_get_next_key,
.map_lookup_elem = array_of_map_lookup_elem,
.map_delete_elem = fd_array_map_delete_elem,
.map_fd_get_ptr = bpf_map_fd_get_ptr,
.map_fd_put_ptr = bpf_map_fd_put_ptr,
.map_fd_sys_lookup_elem = bpf_map_fd_sys_lookup_elem,
.map_gen_lookup = array_of_map_gen_lookup,
};