bpf: Post-hooks for sys_bind

"Post-hooks" are hooks that are called right before returning from
sys_bind. At this time IP and port are already allocated and no further
changes to `struct sock` can happen before returning from sys_bind but
BPF program has a chance to inspect the socket and change sys_bind
result.

Specifically it can e.g. inspect what port was allocated and if it
doesn't satisfy some policy, BPF program can force sys_bind to fail and
return EPERM to user.

Another example of usage is recording the IP:port pair to some map to
use it in later calls to sys_connect. E.g. if some TCP server inside
cgroup was bound to some IP:port_n, it can be recorded to a map. And
later when some TCP client inside same cgroup is trying to connect to
127.0.0.1:port_n, BPF hook for sys_connect can override the destination
and connect application to IP:port_n instead of 127.0.0.1:port_n. That
helps forcing all applications inside a cgroup to use desired IP and not
break those applications if they e.g. use localhost to communicate
between each other.

== Implementation details ==

Post-hooks are implemented as two new attach types
`BPF_CGROUP_INET4_POST_BIND` and `BPF_CGROUP_INET6_POST_BIND` for
existing prog type `BPF_PROG_TYPE_CGROUP_SOCK`.

Separate attach types for IPv4 and IPv6 are introduced to avoid access
to IPv6 field in `struct sock` from `inet_bind()` and to IPv4 field from
`inet6_bind()` since those fields might not make sense in such cases.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
这个提交包含在:
Andrey Ignatov
2018-03-30 15:08:07 -07:00
提交者 Daniel Borkmann
父节点 622adafb2a
当前提交 aac3fc320d
修改 6 个文件,包含 196 行新增31 行删除

查看文件

@@ -1171,11 +1171,46 @@ struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type,
}
EXPORT_SYMBOL_GPL(bpf_prog_get_type_dev);
/* Initially all BPF programs could be loaded w/o specifying
* expected_attach_type. Later for some of them specifying expected_attach_type
* at load time became required so that program could be validated properly.
* Programs of types that are allowed to be loaded both w/ and w/o (for
* backward compatibility) expected_attach_type, should have the default attach
* type assigned to expected_attach_type for the latter case, so that it can be
* validated later at attach time.
*
* bpf_prog_load_fixup_attach_type() sets expected_attach_type in @attr if
* prog type requires it but has some attach types that have to be backward
* compatible.
*/
static void bpf_prog_load_fixup_attach_type(union bpf_attr *attr)
{
switch (attr->prog_type) {
case BPF_PROG_TYPE_CGROUP_SOCK:
/* Unfortunately BPF_ATTACH_TYPE_UNSPEC enumeration doesn't
* exist so checking for non-zero is the way to go here.
*/
if (!attr->expected_attach_type)
attr->expected_attach_type =
BPF_CGROUP_INET_SOCK_CREATE;
break;
}
}
static int
bpf_prog_load_check_attach_type(enum bpf_prog_type prog_type,
enum bpf_attach_type expected_attach_type)
{
switch (prog_type) {
case BPF_PROG_TYPE_CGROUP_SOCK:
switch (expected_attach_type) {
case BPF_CGROUP_INET_SOCK_CREATE:
case BPF_CGROUP_INET4_POST_BIND:
case BPF_CGROUP_INET6_POST_BIND:
return 0;
default:
return -EINVAL;
}
case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
switch (expected_attach_type) {
case BPF_CGROUP_INET4_BIND:
@@ -1195,6 +1230,7 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
enum bpf_attach_type attach_type)
{
switch (prog->type) {
case BPF_PROG_TYPE_CGROUP_SOCK:
case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
return attach_type == prog->expected_attach_type ? 0 : -EINVAL;
default:
@@ -1240,6 +1276,7 @@ static int bpf_prog_load(union bpf_attr *attr)
!capable(CAP_SYS_ADMIN))
return -EPERM;
bpf_prog_load_fixup_attach_type(attr);
if (bpf_prog_load_check_attach_type(type, attr->expected_attach_type))
return -EINVAL;
@@ -1489,6 +1526,8 @@ static int bpf_prog_attach(const union bpf_attr *attr)
ptype = BPF_PROG_TYPE_CGROUP_SKB;
break;
case BPF_CGROUP_INET_SOCK_CREATE:
case BPF_CGROUP_INET4_POST_BIND:
case BPF_CGROUP_INET6_POST_BIND:
ptype = BPF_PROG_TYPE_CGROUP_SOCK;
break;
case BPF_CGROUP_INET4_BIND:
@@ -1557,6 +1596,8 @@ static int bpf_prog_detach(const union bpf_attr *attr)
ptype = BPF_PROG_TYPE_CGROUP_SKB;
break;
case BPF_CGROUP_INET_SOCK_CREATE:
case BPF_CGROUP_INET4_POST_BIND:
case BPF_CGROUP_INET6_POST_BIND:
ptype = BPF_PROG_TYPE_CGROUP_SOCK;
break;
case BPF_CGROUP_INET4_BIND:
@@ -1616,6 +1657,8 @@ static int bpf_prog_query(const union bpf_attr *attr,
case BPF_CGROUP_INET_SOCK_CREATE:
case BPF_CGROUP_INET4_BIND:
case BPF_CGROUP_INET6_BIND:
case BPF_CGROUP_INET4_POST_BIND:
case BPF_CGROUP_INET6_POST_BIND:
case BPF_CGROUP_INET4_CONNECT:
case BPF_CGROUP_INET6_CONNECT:
case BPF_CGROUP_SOCK_OPS: