2018-05-02 19:01:28 +08:00
|
|
|
// SPDX-License-Identifier: GPL-2.0
|
|
|
|
/* XSKMAP used for AF_XDP sockets
|
|
|
|
* Copyright(c) 2018 Intel Corporation.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/bpf.h>
|
|
|
|
#include <linux/capability.h>
|
|
|
|
#include <net/xdp_sock.h>
|
|
|
|
#include <linux/slab.h>
|
|
|
|
#include <linux/sched.h>
|
|
|
|
|
2020-05-21 03:20:50 +08:00
|
|
|
#include "xsk.h"
|
|
|
|
|
2019-08-15 17:30:13 +08:00
|
|
|
int xsk_map_inc(struct xsk_map *map)
|
|
|
|
{
|
bpf: Switch bpf_map ref counter to atomic64_t so bpf_map_inc() never fails
92117d8443bc ("bpf: fix refcnt overflow") turned refcounting of bpf_map into
potentially failing operation, when refcount reaches BPF_MAX_REFCNT limit
(32k). Due to using 32-bit counter, it's possible in practice to overflow
refcounter and make it wrap around to 0, causing erroneous map free, while
there are still references to it, causing use-after-free problems.
But having a failing refcounting operations are problematic in some cases. One
example is mmap() interface. After establishing initial memory-mapping, user
is allowed to arbitrarily map/remap/unmap parts of mapped memory, arbitrarily
splitting it into multiple non-contiguous regions. All this happening without
any control from the users of mmap subsystem. Rather mmap subsystem sends
notifications to original creator of memory mapping through open/close
callbacks, which are optionally specified during initial memory mapping
creation. These callbacks are used to maintain accurate refcount for bpf_map
(see next patch in this series). The problem is that open() callback is not
supposed to fail, because memory-mapped resource is set up and properly
referenced. This is posing a problem for using memory-mapping with BPF maps.
One solution to this is to maintain separate refcount for just memory-mappings
and do single bpf_map_inc/bpf_map_put when it goes from/to zero, respectively.
There are similar use cases in current work on tcp-bpf, necessitating extra
counter as well. This seems like a rather unfortunate and ugly solution that
doesn't scale well to various new use cases.
Another approach to solve this is to use non-failing refcount_t type, which
uses 32-bit counter internally, but, once reaching overflow state at UINT_MAX,
stays there. This utlimately causes memory leak, but prevents use after free.
But given refcounting is not the most performance-critical operation with BPF
maps (it's not used from running BPF program code), we can also just switch to
64-bit counter that can't overflow in practice, potentially disadvantaging
32-bit platforms a tiny bit. This simplifies semantics and allows above
described scenarios to not worry about failing refcount increment operation.
In terms of struct bpf_map size, we are still good and use the same amount of
space:
BEFORE (3 cache lines, 8 bytes of padding at the end):
struct bpf_map {
const struct bpf_map_ops * ops __attribute__((__aligned__(64))); /* 0 8 */
struct bpf_map * inner_map_meta; /* 8 8 */
void * security; /* 16 8 */
enum bpf_map_type map_type; /* 24 4 */
u32 key_size; /* 28 4 */
u32 value_size; /* 32 4 */
u32 max_entries; /* 36 4 */
u32 map_flags; /* 40 4 */
int spin_lock_off; /* 44 4 */
u32 id; /* 48 4 */
int numa_node; /* 52 4 */
u32 btf_key_type_id; /* 56 4 */
u32 btf_value_type_id; /* 60 4 */
/* --- cacheline 1 boundary (64 bytes) --- */
struct btf * btf; /* 64 8 */
struct bpf_map_memory memory; /* 72 16 */
bool unpriv_array; /* 88 1 */
bool frozen; /* 89 1 */
/* XXX 38 bytes hole, try to pack */
/* --- cacheline 2 boundary (128 bytes) --- */
atomic_t refcnt __attribute__((__aligned__(64))); /* 128 4 */
atomic_t usercnt; /* 132 4 */
struct work_struct work; /* 136 32 */
char name[16]; /* 168 16 */
/* size: 192, cachelines: 3, members: 21 */
/* sum members: 146, holes: 1, sum holes: 38 */
/* padding: 8 */
/* forced alignments: 2, forced holes: 1, sum forced holes: 38 */
} __attribute__((__aligned__(64)));
AFTER (same 3 cache lines, no extra padding now):
struct bpf_map {
const struct bpf_map_ops * ops __attribute__((__aligned__(64))); /* 0 8 */
struct bpf_map * inner_map_meta; /* 8 8 */
void * security; /* 16 8 */
enum bpf_map_type map_type; /* 24 4 */
u32 key_size; /* 28 4 */
u32 value_size; /* 32 4 */
u32 max_entries; /* 36 4 */
u32 map_flags; /* 40 4 */
int spin_lock_off; /* 44 4 */
u32 id; /* 48 4 */
int numa_node; /* 52 4 */
u32 btf_key_type_id; /* 56 4 */
u32 btf_value_type_id; /* 60 4 */
/* --- cacheline 1 boundary (64 bytes) --- */
struct btf * btf; /* 64 8 */
struct bpf_map_memory memory; /* 72 16 */
bool unpriv_array; /* 88 1 */
bool frozen; /* 89 1 */
/* XXX 38 bytes hole, try to pack */
/* --- cacheline 2 boundary (128 bytes) --- */
atomic64_t refcnt __attribute__((__aligned__(64))); /* 128 8 */
atomic64_t usercnt; /* 136 8 */
struct work_struct work; /* 144 32 */
char name[16]; /* 176 16 */
/* size: 192, cachelines: 3, members: 21 */
/* sum members: 154, holes: 1, sum holes: 38 */
/* forced alignments: 2, forced holes: 1, sum forced holes: 38 */
} __attribute__((__aligned__(64)));
This patch, while modifying all users of bpf_map_inc, also cleans up its
interface to match bpf_map_put with separate operations for bpf_map_inc and
bpf_map_inc_with_uref (to match bpf_map_put and bpf_map_put_with_uref,
respectively). Also, given there are no users of bpf_map_inc_not_zero
specifying uref=true, remove uref flag and default to uref=false internally.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20191117172806.2195367-2-andriin@fb.com
2019-11-18 01:28:02 +08:00
|
|
|
bpf_map_inc(&map->map);
|
|
|
|
return 0;
|
2019-08-15 17:30:13 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
void xsk_map_put(struct xsk_map *map)
|
|
|
|
{
|
|
|
|
bpf_map_put(&map->map);
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct xsk_map_node *xsk_map_node_alloc(struct xsk_map *map,
|
|
|
|
struct xdp_sock **map_entry)
|
|
|
|
{
|
|
|
|
struct xsk_map_node *node;
|
|
|
|
int err;
|
|
|
|
|
|
|
|
node = kzalloc(sizeof(*node), GFP_ATOMIC | __GFP_NOWARN);
|
|
|
|
if (!node)
|
2019-09-25 00:25:21 +08:00
|
|
|
return ERR_PTR(-ENOMEM);
|
2019-08-15 17:30:13 +08:00
|
|
|
|
|
|
|
err = xsk_map_inc(map);
|
|
|
|
if (err) {
|
|
|
|
kfree(node);
|
|
|
|
return ERR_PTR(err);
|
|
|
|
}
|
|
|
|
|
|
|
|
node->map = map;
|
|
|
|
node->map_entry = map_entry;
|
|
|
|
return node;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void xsk_map_node_free(struct xsk_map_node *node)
|
|
|
|
{
|
|
|
|
xsk_map_put(node->map);
|
|
|
|
kfree(node);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void xsk_map_sock_add(struct xdp_sock *xs, struct xsk_map_node *node)
|
|
|
|
{
|
|
|
|
spin_lock_bh(&xs->map_list_lock);
|
|
|
|
list_add_tail(&node->node, &xs->map_list);
|
|
|
|
spin_unlock_bh(&xs->map_list_lock);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void xsk_map_sock_delete(struct xdp_sock *xs,
|
|
|
|
struct xdp_sock **map_entry)
|
|
|
|
{
|
|
|
|
struct xsk_map_node *n, *tmp;
|
|
|
|
|
|
|
|
spin_lock_bh(&xs->map_list_lock);
|
|
|
|
list_for_each_entry_safe(n, tmp, &xs->map_list, node) {
|
|
|
|
if (map_entry == n->map_entry) {
|
|
|
|
list_del(&n->node);
|
|
|
|
xsk_map_node_free(n);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
spin_unlock_bh(&xs->map_list_lock);
|
|
|
|
}
|
|
|
|
|
2018-05-02 19:01:28 +08:00
|
|
|
static struct bpf_map *xsk_map_alloc(union bpf_attr *attr)
|
|
|
|
{
|
2019-11-01 19:03:44 +08:00
|
|
|
struct bpf_map_memory mem;
|
2019-12-19 14:10:02 +08:00
|
|
|
int err, numa_node;
|
2018-05-02 19:01:28 +08:00
|
|
|
struct xsk_map *m;
|
2019-12-19 14:10:02 +08:00
|
|
|
u64 size;
|
2018-05-02 19:01:28 +08:00
|
|
|
|
|
|
|
if (!capable(CAP_NET_ADMIN))
|
|
|
|
return ERR_PTR(-EPERM);
|
|
|
|
|
|
|
|
if (attr->max_entries == 0 || attr->key_size != 4 ||
|
|
|
|
attr->value_size != 4 ||
|
|
|
|
attr->map_flags & ~(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY))
|
|
|
|
return ERR_PTR(-EINVAL);
|
|
|
|
|
2019-11-01 19:03:44 +08:00
|
|
|
numa_node = bpf_map_attr_numa_node(attr);
|
|
|
|
size = struct_size(m, xsk_map, attr->max_entries);
|
|
|
|
|
2019-12-19 14:10:02 +08:00
|
|
|
err = bpf_map_charge_init(&mem, size);
|
2019-11-01 19:03:44 +08:00
|
|
|
if (err < 0)
|
|
|
|
return ERR_PTR(err);
|
|
|
|
|
|
|
|
m = bpf_map_area_alloc(size, numa_node);
|
|
|
|
if (!m) {
|
|
|
|
bpf_map_charge_finish(&mem);
|
2018-05-02 19:01:28 +08:00
|
|
|
return ERR_PTR(-ENOMEM);
|
2019-11-01 19:03:44 +08:00
|
|
|
}
|
2018-05-02 19:01:28 +08:00
|
|
|
|
|
|
|
bpf_map_init_from_attr(&m->map, attr);
|
2019-11-01 19:03:44 +08:00
|
|
|
bpf_map_charge_move(&m->map.memory, &mem);
|
2019-08-15 17:30:13 +08:00
|
|
|
spin_lock_init(&m->lock);
|
2018-05-02 19:01:28 +08:00
|
|
|
|
|
|
|
return &m->map;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void xsk_map_free(struct bpf_map *map)
|
|
|
|
{
|
|
|
|
struct xsk_map *m = container_of(map, struct xsk_map, map);
|
|
|
|
|
2018-08-18 05:26:14 +08:00
|
|
|
bpf_clear_redirect_map(map);
|
2018-05-02 19:01:28 +08:00
|
|
|
synchronize_net();
|
2019-11-01 19:03:44 +08:00
|
|
|
bpf_map_area_free(m);
|
2018-05-02 19:01:28 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static int xsk_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
|
|
|
|
{
|
|
|
|
struct xsk_map *m = container_of(map, struct xsk_map, map);
|
|
|
|
u32 index = key ? *(u32 *)key : U32_MAX;
|
|
|
|
u32 *next = next_key;
|
|
|
|
|
|
|
|
if (index >= m->map.max_entries) {
|
|
|
|
*next = 0;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (index == m->map.max_entries - 1)
|
|
|
|
return -ENOENT;
|
|
|
|
*next = index + 1;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2019-11-01 19:03:45 +08:00
|
|
|
static u32 xsk_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
|
|
|
|
{
|
|
|
|
const int ret = BPF_REG_0, mp = BPF_REG_1, index = BPF_REG_2;
|
|
|
|
struct bpf_insn *insn = insn_buf;
|
|
|
|
|
|
|
|
*insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0);
|
|
|
|
*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 5);
|
|
|
|
*insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(sizeof(struct xsk_sock *)));
|
|
|
|
*insn++ = BPF_ALU64_IMM(BPF_ADD, mp, offsetof(struct xsk_map, xsk_map));
|
|
|
|
*insn++ = BPF_ALU64_REG(BPF_ADD, ret, mp);
|
|
|
|
*insn++ = BPF_LDX_MEM(BPF_SIZEOF(struct xsk_sock *), ret, ret, 0);
|
|
|
|
*insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1);
|
|
|
|
*insn++ = BPF_MOV64_IMM(ret, 0);
|
|
|
|
return insn - insn_buf;
|
|
|
|
}
|
|
|
|
|
2018-05-02 19:01:28 +08:00
|
|
|
static void *xsk_map_lookup_elem(struct bpf_map *map, void *key)
|
2019-06-07 04:59:40 +08:00
|
|
|
{
|
|
|
|
WARN_ON_ONCE(!rcu_read_lock_held());
|
|
|
|
return __xsk_map_lookup_elem(map, *(u32 *)key);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void *xsk_map_lookup_elem_sys_only(struct bpf_map *map, void *key)
|
2018-05-02 19:01:28 +08:00
|
|
|
{
|
2018-10-09 09:04:50 +08:00
|
|
|
return ERR_PTR(-EOPNOTSUPP);
|
2018-05-02 19:01:28 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value,
|
|
|
|
u64 map_flags)
|
|
|
|
{
|
|
|
|
struct xsk_map *m = container_of(map, struct xsk_map, map);
|
2019-08-15 17:30:13 +08:00
|
|
|
struct xdp_sock *xs, *old_xs, **map_entry;
|
2018-05-02 19:01:28 +08:00
|
|
|
u32 i = *(u32 *)key, fd = *(u32 *)value;
|
2019-08-15 17:30:13 +08:00
|
|
|
struct xsk_map_node *node;
|
2018-05-02 19:01:28 +08:00
|
|
|
struct socket *sock;
|
|
|
|
int err;
|
|
|
|
|
|
|
|
if (unlikely(map_flags > BPF_EXIST))
|
|
|
|
return -EINVAL;
|
|
|
|
if (unlikely(i >= m->map.max_entries))
|
|
|
|
return -E2BIG;
|
|
|
|
|
|
|
|
sock = sockfd_lookup(fd, &err);
|
|
|
|
if (!sock)
|
|
|
|
return err;
|
|
|
|
|
|
|
|
if (sock->sk->sk_family != PF_XDP) {
|
|
|
|
sockfd_put(sock);
|
|
|
|
return -EOPNOTSUPP;
|
|
|
|
}
|
|
|
|
|
|
|
|
xs = (struct xdp_sock *)sock->sk;
|
|
|
|
|
2019-08-15 17:30:13 +08:00
|
|
|
map_entry = &m->xsk_map[i];
|
|
|
|
node = xsk_map_node_alloc(m, map_entry);
|
|
|
|
if (IS_ERR(node)) {
|
|
|
|
sockfd_put(sock);
|
|
|
|
return PTR_ERR(node);
|
|
|
|
}
|
2018-05-02 19:01:28 +08:00
|
|
|
|
2019-08-15 17:30:13 +08:00
|
|
|
spin_lock_bh(&m->lock);
|
|
|
|
old_xs = READ_ONCE(*map_entry);
|
|
|
|
if (old_xs == xs) {
|
|
|
|
err = 0;
|
|
|
|
goto out;
|
2019-08-15 17:30:14 +08:00
|
|
|
} else if (old_xs && map_flags == BPF_NOEXIST) {
|
|
|
|
err = -EEXIST;
|
|
|
|
goto out;
|
|
|
|
} else if (!old_xs && map_flags == BPF_EXIST) {
|
|
|
|
err = -ENOENT;
|
|
|
|
goto out;
|
2019-08-15 17:30:13 +08:00
|
|
|
}
|
|
|
|
xsk_map_sock_add(xs, node);
|
|
|
|
WRITE_ONCE(*map_entry, xs);
|
2018-10-09 01:40:16 +08:00
|
|
|
if (old_xs)
|
2019-08-15 17:30:13 +08:00
|
|
|
xsk_map_sock_delete(old_xs, map_entry);
|
|
|
|
spin_unlock_bh(&m->lock);
|
2018-05-02 19:01:28 +08:00
|
|
|
sockfd_put(sock);
|
|
|
|
return 0;
|
2019-08-15 17:30:13 +08:00
|
|
|
|
|
|
|
out:
|
|
|
|
spin_unlock_bh(&m->lock);
|
|
|
|
sockfd_put(sock);
|
|
|
|
xsk_map_node_free(node);
|
|
|
|
return err;
|
2018-05-02 19:01:28 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static int xsk_map_delete_elem(struct bpf_map *map, void *key)
|
|
|
|
{
|
|
|
|
struct xsk_map *m = container_of(map, struct xsk_map, map);
|
2019-08-15 17:30:13 +08:00
|
|
|
struct xdp_sock *old_xs, **map_entry;
|
2018-05-02 19:01:28 +08:00
|
|
|
int k = *(u32 *)key;
|
|
|
|
|
|
|
|
if (k >= map->max_entries)
|
|
|
|
return -EINVAL;
|
|
|
|
|
2019-08-15 17:30:13 +08:00
|
|
|
spin_lock_bh(&m->lock);
|
|
|
|
map_entry = &m->xsk_map[k];
|
|
|
|
old_xs = xchg(map_entry, NULL);
|
2018-10-09 01:40:16 +08:00
|
|
|
if (old_xs)
|
2019-08-15 17:30:13 +08:00
|
|
|
xsk_map_sock_delete(old_xs, map_entry);
|
|
|
|
spin_unlock_bh(&m->lock);
|
2018-05-02 19:01:28 +08:00
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2019-08-15 17:30:13 +08:00
|
|
|
void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs,
|
|
|
|
struct xdp_sock **map_entry)
|
|
|
|
{
|
|
|
|
spin_lock_bh(&map->lock);
|
|
|
|
if (READ_ONCE(*map_entry) == xs) {
|
|
|
|
WRITE_ONCE(*map_entry, NULL);
|
|
|
|
xsk_map_sock_delete(xs, map_entry);
|
|
|
|
}
|
|
|
|
spin_unlock_bh(&map->lock);
|
|
|
|
}
|
|
|
|
|
2020-08-28 09:18:13 +08:00
|
|
|
static bool xsk_map_meta_equal(const struct bpf_map *meta0,
|
|
|
|
const struct bpf_map *meta1)
|
|
|
|
{
|
|
|
|
return meta0->max_entries == meta1->max_entries &&
|
|
|
|
bpf_map_meta_equal(meta0, meta1);
|
|
|
|
}
|
|
|
|
|
2020-06-20 05:11:44 +08:00
|
|
|
static int xsk_map_btf_id;
|
2018-05-02 19:01:28 +08:00
|
|
|
const struct bpf_map_ops xsk_map_ops = {
|
2020-08-28 09:18:13 +08:00
|
|
|
.map_meta_equal = xsk_map_meta_equal,
|
2018-05-02 19:01:28 +08:00
|
|
|
.map_alloc = xsk_map_alloc,
|
|
|
|
.map_free = xsk_map_free,
|
|
|
|
.map_get_next_key = xsk_map_get_next_key,
|
|
|
|
.map_lookup_elem = xsk_map_lookup_elem,
|
2019-11-01 19:03:45 +08:00
|
|
|
.map_gen_lookup = xsk_map_gen_lookup,
|
2019-06-07 04:59:40 +08:00
|
|
|
.map_lookup_elem_sys_only = xsk_map_lookup_elem_sys_only,
|
2018-05-02 19:01:28 +08:00
|
|
|
.map_update_elem = xsk_map_update_elem,
|
|
|
|
.map_delete_elem = xsk_map_delete_elem,
|
2018-08-12 07:59:17 +08:00
|
|
|
.map_check_btf = map_check_no_btf,
|
2020-06-20 05:11:44 +08:00
|
|
|
.map_btf_name = "xsk_map",
|
|
|
|
.map_btf_id = &xsk_map_btf_id,
|
2018-05-02 19:01:28 +08:00
|
|
|
};
|