2017-11-01 08:08:43 -06:00
|
|
|
/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
|
2013-01-18 00:17:30 -07:00
|
|
|
#ifndef _XT_BPF_H
|
|
|
|
#define _XT_BPF_H
|
|
|
|
|
|
|
|
#include <linux/filter.h>
|
2016-12-06 14:25:02 -07:00
|
|
|
#include <linux/limits.h>
|
2013-01-18 00:17:30 -07:00
|
|
|
#include <linux/types.h>
|
|
|
|
|
|
|
|
#define XT_BPF_MAX_NUM_INSTR 64
|
2016-12-06 14:25:02 -07:00
|
|
|
#define XT_BPF_PATH_MAX (XT_BPF_MAX_NUM_INSTR * sizeof(struct sock_filter))
|
2013-01-18 00:17:30 -07:00
|
|
|
|
net: filter: split 'struct sk_filter' into socket and bpf parts
clean up names related to socket filtering and bpf in the following way:
- everything that deals with sockets keeps 'sk_*' prefix
- everything that is pure BPF is changed to 'bpf_*' prefix
split 'struct sk_filter' into
struct sk_filter {
atomic_t refcnt;
struct rcu_head rcu;
struct bpf_prog *prog;
};
and
struct bpf_prog {
u32 jited:1,
len:31;
struct sock_fprog_kern *orig_prog;
unsigned int (*bpf_func)(const struct sk_buff *skb,
const struct bpf_insn *filter);
union {
struct sock_filter insns[0];
struct bpf_insn insnsi[0];
struct work_struct work;
};
};
so that 'struct bpf_prog' can be used independent of sockets and cleans up
'unattached' bpf use cases
split SK_RUN_FILTER macro into:
SK_RUN_FILTER to be used with 'struct sk_filter *' and
BPF_PROG_RUN to be used with 'struct bpf_prog *'
__sk_filter_release(struct sk_filter *) gains
__bpf_prog_release(struct bpf_prog *) helper function
also perform related renames for the functions that work
with 'struct bpf_prog *', since they're on the same lines:
sk_filter_size -> bpf_prog_size
sk_filter_select_runtime -> bpf_prog_select_runtime
sk_filter_free -> bpf_prog_free
sk_unattached_filter_create -> bpf_prog_create
sk_unattached_filter_destroy -> bpf_prog_destroy
sk_store_orig_filter -> bpf_prog_store_orig_filter
sk_release_orig_filter -> bpf_release_orig_filter
__sk_migrate_filter -> bpf_migrate_filter
__sk_prepare_filter -> bpf_prepare_filter
API for attaching classic BPF to a socket stays the same:
sk_attach_filter(prog, struct sock *)/sk_detach_filter(struct sock *)
and SK_RUN_FILTER(struct sk_filter *, ctx) to execute a program
which is used by sockets, tun, af_packet
API for 'unattached' BPF programs becomes:
bpf_prog_create(struct bpf_prog **)/bpf_prog_destroy(struct bpf_prog *)
and BPF_PROG_RUN(struct bpf_prog *, ctx) to execute a program
which is used by isdn, ppp, team, seccomp, ptp, xt_bpf, cls_bpf, test_bpf
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-30 21:34:16 -06:00
|
|
|
struct bpf_prog;
|
2014-07-29 10:12:15 -06:00
|
|
|
|
2013-01-18 00:17:30 -07:00
|
|
|
struct xt_bpf_info {
|
|
|
|
__u16 bpf_program_num_elem;
|
|
|
|
struct sock_filter bpf_program[XT_BPF_MAX_NUM_INSTR];
|
|
|
|
|
|
|
|
/* only used in the kernel */
|
net: filter: split 'struct sk_filter' into socket and bpf parts
clean up names related to socket filtering and bpf in the following way:
- everything that deals with sockets keeps 'sk_*' prefix
- everything that is pure BPF is changed to 'bpf_*' prefix
split 'struct sk_filter' into
struct sk_filter {
atomic_t refcnt;
struct rcu_head rcu;
struct bpf_prog *prog;
};
and
struct bpf_prog {
u32 jited:1,
len:31;
struct sock_fprog_kern *orig_prog;
unsigned int (*bpf_func)(const struct sk_buff *skb,
const struct bpf_insn *filter);
union {
struct sock_filter insns[0];
struct bpf_insn insnsi[0];
struct work_struct work;
};
};
so that 'struct bpf_prog' can be used independent of sockets and cleans up
'unattached' bpf use cases
split SK_RUN_FILTER macro into:
SK_RUN_FILTER to be used with 'struct sk_filter *' and
BPF_PROG_RUN to be used with 'struct bpf_prog *'
__sk_filter_release(struct sk_filter *) gains
__bpf_prog_release(struct bpf_prog *) helper function
also perform related renames for the functions that work
with 'struct bpf_prog *', since they're on the same lines:
sk_filter_size -> bpf_prog_size
sk_filter_select_runtime -> bpf_prog_select_runtime
sk_filter_free -> bpf_prog_free
sk_unattached_filter_create -> bpf_prog_create
sk_unattached_filter_destroy -> bpf_prog_destroy
sk_store_orig_filter -> bpf_prog_store_orig_filter
sk_release_orig_filter -> bpf_release_orig_filter
__sk_migrate_filter -> bpf_migrate_filter
__sk_prepare_filter -> bpf_prepare_filter
API for attaching classic BPF to a socket stays the same:
sk_attach_filter(prog, struct sock *)/sk_detach_filter(struct sock *)
and SK_RUN_FILTER(struct sk_filter *, ctx) to execute a program
which is used by sockets, tun, af_packet
API for 'unattached' BPF programs becomes:
bpf_prog_create(struct bpf_prog **)/bpf_prog_destroy(struct bpf_prog *)
and BPF_PROG_RUN(struct bpf_prog *, ctx) to execute a program
which is used by isdn, ppp, team, seccomp, ptp, xt_bpf, cls_bpf, test_bpf
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-30 21:34:16 -06:00
|
|
|
struct bpf_prog *filter __attribute__((aligned(8)));
|
2013-01-18 00:17:30 -07:00
|
|
|
};
|
|
|
|
|
2016-12-06 14:25:02 -07:00
|
|
|
enum xt_bpf_modes {
|
|
|
|
XT_BPF_MODE_BYTECODE,
|
|
|
|
XT_BPF_MODE_FD_PINNED,
|
|
|
|
XT_BPF_MODE_FD_ELF,
|
|
|
|
};
|
netfilter: xt_bpf: Fix XT_BPF_MODE_FD_PINNED mode of 'xt_bpf_info_v1'
Commit 2c16d6033264 ("netfilter: xt_bpf: support ebpf") introduced
support for attaching an eBPF object by an fd, with the
'bpf_mt_check_v1' ABI expecting the '.fd' to be specified upon each
IPT_SO_SET_REPLACE call.
However this breaks subsequent iptables calls:
# iptables -A INPUT -m bpf --object-pinned /sys/fs/bpf/xxx -j ACCEPT
# iptables -A INPUT -s 5.6.7.8 -j ACCEPT
iptables: Invalid argument. Run `dmesg' for more information.
That's because iptables works by loading existing rules using
IPT_SO_GET_ENTRIES to userspace, then issuing IPT_SO_SET_REPLACE with
the replacement set.
However, the loaded 'xt_bpf_info_v1' has an arbitrary '.fd' number
(from the initial "iptables -m bpf" invocation) - so when 2nd invocation
occurs, userspace passes a bogus fd number, which leads to
'bpf_mt_check_v1' to fail.
One suggested solution [1] was to hack iptables userspace, to perform a
"entries fixup" immediatley after IPT_SO_GET_ENTRIES, by opening a new,
process-local fd per every 'xt_bpf_info_v1' entry seen.
However, in [2] both Pablo Neira Ayuso and Willem de Bruijn suggested to
depricate the xt_bpf_info_v1 ABI dealing with pinned ebpf objects.
This fix changes the XT_BPF_MODE_FD_PINNED behavior to ignore the given
'.fd' and instead perform an in-kernel lookup for the bpf object given
the provided '.path'.
It also defines an alias for the XT_BPF_MODE_FD_PINNED mode, named
XT_BPF_MODE_PATH_PINNED, to better reflect the fact that the user is
expected to provide the path of the pinned object.
Existing XT_BPF_MODE_FD_ELF behavior (non-pinned fd mode) is preserved.
References: [1] https://marc.info/?l=netfilter-devel&m=150564724607440&w=2
[2] https://marc.info/?l=netfilter-devel&m=150575727129880&w=2
Reported-by: Rafael Buchbinder <rafi@rbk.ms>
Signed-off-by: Shmulik Ladkani <shmulik.ladkani@gmail.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2017-10-09 06:27:15 -06:00
|
|
|
#define XT_BPF_MODE_PATH_PINNED XT_BPF_MODE_FD_PINNED
|
2016-12-06 14:25:02 -07:00
|
|
|
|
|
|
|
struct xt_bpf_info_v1 {
|
|
|
|
__u16 mode;
|
|
|
|
__u16 bpf_program_num_elem;
|
|
|
|
__s32 fd;
|
|
|
|
union {
|
|
|
|
struct sock_filter bpf_program[XT_BPF_MAX_NUM_INSTR];
|
|
|
|
char path[XT_BPF_PATH_MAX];
|
|
|
|
};
|
|
|
|
|
|
|
|
/* only used in the kernel */
|
|
|
|
struct bpf_prog *filter __attribute__((aligned(8)));
|
|
|
|
};
|
|
|
|
|
2013-01-18 00:17:30 -07:00
|
|
|
#endif /*_XT_BPF_H */
|