linux_dsm_epyc7002/net/core/lwt_bpf.c

399 lines
8.9 KiB
C
Raw Normal View History

/* Copyright (c) 2016 Thomas Graf <tgraf@tgraf.ch>
*
* 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/kernel.h>
#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/types.h>
#include <linux/bpf.h>
#include <net/lwtunnel.h>
struct bpf_lwt_prog {
struct bpf_prog *prog;
char *name;
};
struct bpf_lwt {
struct bpf_lwt_prog in;
struct bpf_lwt_prog out;
struct bpf_lwt_prog xmit;
int family;
};
#define MAX_PROG_NAME 256
static inline struct bpf_lwt *bpf_lwt_lwtunnel(struct lwtunnel_state *lwt)
{
return (struct bpf_lwt *)lwt->data;
}
#define NO_REDIRECT false
#define CAN_REDIRECT true
static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt,
struct dst_entry *dst, bool can_redirect)
{
int ret;
/* Preempt disable is needed to protect per-cpu redirect_info between
* BPF prog and skb_do_redirect(). The call_rcu in bpf_prog_put() and
* access to maps strictly require a rcu_read_lock() for protection,
* mixing with BH RCU lock doesn't work.
*/
preempt_disable();
bpf_compute_data_pointers(skb);
ret = bpf_prog_run_save_cb(lwt->prog, skb);
switch (ret) {
case BPF_OK:
break;
case BPF_REDIRECT:
if (unlikely(!can_redirect)) {
pr_warn_once("Illegal redirect return code in prog %s\n",
lwt->name ? : "<unknown>");
ret = BPF_OK;
} else {
bpf: in __bpf_redirect_no_mac pull mac only if present Syzkaller was able to construct a packet of negative length by redirecting from bpf_prog_test_run_skb with BPF_PROG_TYPE_LWT_XMIT: BUG: KASAN: slab-out-of-bounds in memcpy include/linux/string.h:345 [inline] BUG: KASAN: slab-out-of-bounds in skb_copy_from_linear_data include/linux/skbuff.h:3421 [inline] BUG: KASAN: slab-out-of-bounds in __pskb_copy_fclone+0x2dd/0xeb0 net/core/skbuff.c:1395 Read of size 4294967282 at addr ffff8801d798009c by task syz-executor2/12942 kasan_report.cold.9+0x242/0x309 mm/kasan/report.c:412 check_memory_region_inline mm/kasan/kasan.c:260 [inline] check_memory_region+0x13e/0x1b0 mm/kasan/kasan.c:267 memcpy+0x23/0x50 mm/kasan/kasan.c:302 memcpy include/linux/string.h:345 [inline] skb_copy_from_linear_data include/linux/skbuff.h:3421 [inline] __pskb_copy_fclone+0x2dd/0xeb0 net/core/skbuff.c:1395 __pskb_copy include/linux/skbuff.h:1053 [inline] pskb_copy include/linux/skbuff.h:2904 [inline] skb_realloc_headroom+0xe7/0x120 net/core/skbuff.c:1539 ipip6_tunnel_xmit net/ipv6/sit.c:965 [inline] sit_tunnel_xmit+0xe1b/0x30d0 net/ipv6/sit.c:1029 __netdev_start_xmit include/linux/netdevice.h:4325 [inline] netdev_start_xmit include/linux/netdevice.h:4334 [inline] xmit_one net/core/dev.c:3219 [inline] dev_hard_start_xmit+0x295/0xc90 net/core/dev.c:3235 __dev_queue_xmit+0x2f0d/0x3950 net/core/dev.c:3805 dev_queue_xmit+0x17/0x20 net/core/dev.c:3838 __bpf_tx_skb net/core/filter.c:2016 [inline] __bpf_redirect_common net/core/filter.c:2054 [inline] __bpf_redirect+0x5cf/0xb20 net/core/filter.c:2061 ____bpf_clone_redirect net/core/filter.c:2094 [inline] bpf_clone_redirect+0x2f6/0x490 net/core/filter.c:2066 bpf_prog_41f2bcae09cd4ac3+0xb25/0x1000 The generated test constructs a packet with mac header, network header, skb->data pointing to network header and skb->len 0. Redirecting to a sit0 through __bpf_redirect_no_mac pulls the mac length, even though skb->data already is at skb->network_header. bpf_prog_test_run_skb has already pulled it as LWT_XMIT !is_l2. Update the offset calculation to pull only if skb->data differs from skb->network_header, which is not true in this case. The test itself can be run only from commit 1cf1cae963c2 ("bpf: introduce BPF_PROG_TEST_RUN command"), but the same type of packets with skb at network header could already be built from lwt xmit hooks, so this fix is more relevant to that commit. Also set the mac header on redirect from LWT_XMIT, as even after this change to __bpf_redirect_no_mac that field is expected to be set, but is not yet in ip_finish_output2. Fixes: 3a0af8fd61f9 ("bpf: BPF for lightweight tunnel infrastructure") Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: Willem de Bruijn <willemb@google.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-01-16 08:19:22 +07:00
skb_reset_mac_header(skb);
ret = skb_do_redirect(skb);
if (ret == 0)
ret = BPF_REDIRECT;
}
break;
case BPF_DROP:
kfree_skb(skb);
ret = -EPERM;
break;
default:
pr_warn_once("bpf-lwt: Illegal return value %u, expect packet loss\n", ret);
kfree_skb(skb);
ret = -EINVAL;
break;
}
preempt_enable();
return ret;
}
static int bpf_input(struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
struct bpf_lwt *bpf;
int ret;
bpf = bpf_lwt_lwtunnel(dst->lwtstate);
if (bpf->in.prog) {
ret = run_lwt_bpf(skb, &bpf->in, dst, NO_REDIRECT);
if (ret < 0)
return ret;
}
if (unlikely(!dst->lwtstate->orig_input)) {
pr_warn_once("orig_input not set on dst for prog %s\n",
bpf->out.name);
kfree_skb(skb);
return -EINVAL;
}
return dst->lwtstate->orig_input(skb);
}
static int bpf_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
struct bpf_lwt *bpf;
int ret;
bpf = bpf_lwt_lwtunnel(dst->lwtstate);
if (bpf->out.prog) {
ret = run_lwt_bpf(skb, &bpf->out, dst, NO_REDIRECT);
if (ret < 0)
return ret;
}
if (unlikely(!dst->lwtstate->orig_output)) {
pr_warn_once("orig_output not set on dst for prog %s\n",
bpf->out.name);
kfree_skb(skb);
return -EINVAL;
}
return dst->lwtstate->orig_output(net, sk, skb);
}
static int xmit_check_hhlen(struct sk_buff *skb)
{
int hh_len = skb_dst(skb)->dev->hard_header_len;
if (skb_headroom(skb) < hh_len) {
int nhead = HH_DATA_ALIGN(hh_len - skb_headroom(skb));
if (pskb_expand_head(skb, nhead, 0, GFP_ATOMIC))
return -ENOMEM;
}
return 0;
}
static int bpf_xmit(struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
struct bpf_lwt *bpf;
bpf = bpf_lwt_lwtunnel(dst->lwtstate);
if (bpf->xmit.prog) {
int ret;
ret = run_lwt_bpf(skb, &bpf->xmit, dst, CAN_REDIRECT);
switch (ret) {
case BPF_OK:
/* If the header was expanded, headroom might be too
* small for L2 header to come, expand as needed.
*/
ret = xmit_check_hhlen(skb);
if (unlikely(ret))
return ret;
return LWTUNNEL_XMIT_CONTINUE;
case BPF_REDIRECT:
return LWTUNNEL_XMIT_DONE;
default:
return ret;
}
}
return LWTUNNEL_XMIT_CONTINUE;
}
static void bpf_lwt_prog_destroy(struct bpf_lwt_prog *prog)
{
if (prog->prog)
bpf_prog_put(prog->prog);
kfree(prog->name);
}
static void bpf_destroy_state(struct lwtunnel_state *lwt)
{
struct bpf_lwt *bpf = bpf_lwt_lwtunnel(lwt);
bpf_lwt_prog_destroy(&bpf->in);
bpf_lwt_prog_destroy(&bpf->out);
bpf_lwt_prog_destroy(&bpf->xmit);
}
static const struct nla_policy bpf_prog_policy[LWT_BPF_PROG_MAX + 1] = {
[LWT_BPF_PROG_FD] = { .type = NLA_U32, },
[LWT_BPF_PROG_NAME] = { .type = NLA_NUL_STRING,
.len = MAX_PROG_NAME },
};
static int bpf_parse_prog(struct nlattr *attr, struct bpf_lwt_prog *prog,
enum bpf_prog_type type)
{
struct nlattr *tb[LWT_BPF_PROG_MAX + 1];
struct bpf_prog *p;
int ret;
u32 fd;
ret = nla_parse_nested(tb, LWT_BPF_PROG_MAX, attr, bpf_prog_policy,
NULL);
if (ret < 0)
return ret;
if (!tb[LWT_BPF_PROG_FD] || !tb[LWT_BPF_PROG_NAME])
return -EINVAL;
bpf: use GFP_ATOMIC instead of GFP_KERNEL in bpf_parse_prog() bpf_parse_prog() is protected by rcu_read_lock(). so that GFP_KERNEL is not allowed in the bpf_parse_prog(). [51015.579396] ============================= [51015.579418] WARNING: suspicious RCU usage [51015.579444] 4.18.0-rc6+ #208 Not tainted [51015.579464] ----------------------------- [51015.579488] ./include/linux/rcupdate.h:303 Illegal context switch in RCU read-side critical section! [51015.579510] other info that might help us debug this: [51015.579532] rcu_scheduler_active = 2, debug_locks = 1 [51015.579556] 2 locks held by ip/1861: [51015.579577] #0: 00000000a8c12fd1 (rtnl_mutex){+.+.}, at: rtnetlink_rcv_msg+0x2e0/0x910 [51015.579711] #1: 00000000bf815f8e (rcu_read_lock){....}, at: lwtunnel_build_state+0x96/0x390 [51015.579842] stack backtrace: [51015.579869] CPU: 0 PID: 1861 Comm: ip Not tainted 4.18.0-rc6+ #208 [51015.579891] Hardware name: To be filled by O.E.M. To be filled by O.E.M./Aptio CRB, BIOS 5.6.5 07/08/2015 [51015.579911] Call Trace: [51015.579950] dump_stack+0x74/0xbb [51015.580000] ___might_sleep+0x16b/0x3a0 [51015.580047] __kmalloc_track_caller+0x220/0x380 [51015.580077] kmemdup+0x1c/0x40 [51015.580077] bpf_parse_prog+0x10e/0x230 [51015.580164] ? kasan_kmalloc+0xa0/0xd0 [51015.580164] ? bpf_destroy_state+0x30/0x30 [51015.580164] ? bpf_build_state+0xe2/0x3e0 [51015.580164] bpf_build_state+0x1bb/0x3e0 [51015.580164] ? bpf_parse_prog+0x230/0x230 [51015.580164] ? lock_is_held_type+0x123/0x1a0 [51015.580164] lwtunnel_build_state+0x1aa/0x390 [51015.580164] fib_create_info+0x1579/0x33d0 [51015.580164] ? sched_clock_local+0xe2/0x150 [51015.580164] ? fib_info_update_nh_saddr+0x1f0/0x1f0 [51015.580164] ? sched_clock_local+0xe2/0x150 [51015.580164] fib_table_insert+0x201/0x1990 [51015.580164] ? lock_downgrade+0x610/0x610 [51015.580164] ? fib_table_lookup+0x1920/0x1920 [51015.580164] ? lwtunnel_valid_encap_type.part.6+0xcb/0x3a0 [51015.580164] ? rtm_to_fib_config+0x637/0xbd0 [51015.580164] inet_rtm_newroute+0xed/0x1b0 [51015.580164] ? rtm_to_fib_config+0xbd0/0xbd0 [51015.580164] rtnetlink_rcv_msg+0x331/0x910 [ ... ] Fixes: 3a0af8fd61f9 ("bpf: BPF for lightweight tunnel infrastructure") Signed-off-by: Taehee Yoo <ap420073@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-07-28 22:28:31 +07:00
prog->name = nla_memdup(tb[LWT_BPF_PROG_NAME], GFP_ATOMIC);
if (!prog->name)
return -ENOMEM;
fd = nla_get_u32(tb[LWT_BPF_PROG_FD]);
p = bpf_prog_get_type(fd, type);
if (IS_ERR(p))
return PTR_ERR(p);
prog->prog = p;
return 0;
}
static const struct nla_policy bpf_nl_policy[LWT_BPF_MAX + 1] = {
[LWT_BPF_IN] = { .type = NLA_NESTED, },
[LWT_BPF_OUT] = { .type = NLA_NESTED, },
[LWT_BPF_XMIT] = { .type = NLA_NESTED, },
[LWT_BPF_XMIT_HEADROOM] = { .type = NLA_U32 },
};
static int bpf_build_state(struct nlattr *nla,
unsigned int family, const void *cfg,
struct lwtunnel_state **ts,
struct netlink_ext_ack *extack)
{
struct nlattr *tb[LWT_BPF_MAX + 1];
struct lwtunnel_state *newts;
struct bpf_lwt *bpf;
int ret;
if (family != AF_INET && family != AF_INET6)
return -EAFNOSUPPORT;
ret = nla_parse_nested(tb, LWT_BPF_MAX, nla, bpf_nl_policy, extack);
if (ret < 0)
return ret;
if (!tb[LWT_BPF_IN] && !tb[LWT_BPF_OUT] && !tb[LWT_BPF_XMIT])
return -EINVAL;
newts = lwtunnel_state_alloc(sizeof(*bpf));
if (!newts)
return -ENOMEM;
newts->type = LWTUNNEL_ENCAP_BPF;
bpf = bpf_lwt_lwtunnel(newts);
if (tb[LWT_BPF_IN]) {
newts->flags |= LWTUNNEL_STATE_INPUT_REDIRECT;
ret = bpf_parse_prog(tb[LWT_BPF_IN], &bpf->in,
BPF_PROG_TYPE_LWT_IN);
if (ret < 0)
goto errout;
}
if (tb[LWT_BPF_OUT]) {
newts->flags |= LWTUNNEL_STATE_OUTPUT_REDIRECT;
ret = bpf_parse_prog(tb[LWT_BPF_OUT], &bpf->out,
BPF_PROG_TYPE_LWT_OUT);
if (ret < 0)
goto errout;
}
if (tb[LWT_BPF_XMIT]) {
newts->flags |= LWTUNNEL_STATE_XMIT_REDIRECT;
ret = bpf_parse_prog(tb[LWT_BPF_XMIT], &bpf->xmit,
BPF_PROG_TYPE_LWT_XMIT);
if (ret < 0)
goto errout;
}
if (tb[LWT_BPF_XMIT_HEADROOM]) {
u32 headroom = nla_get_u32(tb[LWT_BPF_XMIT_HEADROOM]);
if (headroom > LWT_BPF_MAX_HEADROOM) {
ret = -ERANGE;
goto errout;
}
newts->headroom = headroom;
}
bpf->family = family;
*ts = newts;
return 0;
errout:
bpf_destroy_state(newts);
kfree(newts);
return ret;
}
static int bpf_fill_lwt_prog(struct sk_buff *skb, int attr,
struct bpf_lwt_prog *prog)
{
struct nlattr *nest;
if (!prog->prog)
return 0;
nest = nla_nest_start(skb, attr);
if (!nest)
return -EMSGSIZE;
if (prog->name &&
nla_put_string(skb, LWT_BPF_PROG_NAME, prog->name))
return -EMSGSIZE;
return nla_nest_end(skb, nest);
}
static int bpf_fill_encap_info(struct sk_buff *skb, struct lwtunnel_state *lwt)
{
struct bpf_lwt *bpf = bpf_lwt_lwtunnel(lwt);
if (bpf_fill_lwt_prog(skb, LWT_BPF_IN, &bpf->in) < 0 ||
bpf_fill_lwt_prog(skb, LWT_BPF_OUT, &bpf->out) < 0 ||
bpf_fill_lwt_prog(skb, LWT_BPF_XMIT, &bpf->xmit) < 0)
return -EMSGSIZE;
return 0;
}
static int bpf_encap_nlsize(struct lwtunnel_state *lwtstate)
{
int nest_len = nla_total_size(sizeof(struct nlattr)) +
nla_total_size(MAX_PROG_NAME) + /* LWT_BPF_PROG_NAME */
0;
return nest_len + /* LWT_BPF_IN */
nest_len + /* LWT_BPF_OUT */
nest_len + /* LWT_BPF_XMIT */
0;
}
static int bpf_lwt_prog_cmp(struct bpf_lwt_prog *a, struct bpf_lwt_prog *b)
{
/* FIXME:
* The LWT state is currently rebuilt for delete requests which
* results in a new bpf_prog instance. Comparing names for now.
*/
if (!a->name && !b->name)
return 0;
if (!a->name || !b->name)
return 1;
return strcmp(a->name, b->name);
}
static int bpf_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b)
{
struct bpf_lwt *a_bpf = bpf_lwt_lwtunnel(a);
struct bpf_lwt *b_bpf = bpf_lwt_lwtunnel(b);
return bpf_lwt_prog_cmp(&a_bpf->in, &b_bpf->in) ||
bpf_lwt_prog_cmp(&a_bpf->out, &b_bpf->out) ||
bpf_lwt_prog_cmp(&a_bpf->xmit, &b_bpf->xmit);
}
static const struct lwtunnel_encap_ops bpf_encap_ops = {
.build_state = bpf_build_state,
.destroy_state = bpf_destroy_state,
.input = bpf_input,
.output = bpf_output,
.xmit = bpf_xmit,
.fill_encap = bpf_fill_encap_info,
.get_encap_size = bpf_encap_nlsize,
.cmp_encap = bpf_encap_cmp,
.owner = THIS_MODULE,
};
static int __init bpf_lwt_init(void)
{
return lwtunnel_encap_add_ops(&bpf_encap_ops, LWTUNNEL_ENCAP_BPF);
}
subsys_initcall(bpf_lwt_init)