summaryrefslogtreecommitdiffstats
path: root/kernel/bpf/syscall.c
diff options
context:
space:
mode:
authorAndrey Ignatov <rdna@fb.com>2018-03-30 15:08:02 -0700
committerDaniel Borkmann <daniel@iogearbox.net>2018-03-31 02:15:18 +0200
commit4fbac77d2d092b475dda9eea66da674369665427 (patch)
treee565018845653a1d55241ffbc8f40cc30ae1e19a /kernel/bpf/syscall.c
parentd7be143b67c2cf99bf93279217b1cf93a1e8a6b1 (diff)
downloadlinux-4fbac77d2d092b475dda9eea66da674369665427.tar.bz2
bpf: Hooks for sys_bind
== The problem == There is a use-case when all processes inside a cgroup should use one single IP address on a host that has multiple IP configured. Those processes should use the IP for both ingress and egress, for TCP and UDP traffic. So TCP/UDP servers should be bound to that IP to accept incoming connections on it, and TCP/UDP clients should make outgoing connections from that IP. It should not require changing application code since it's often not possible. Currently it's solved by intercepting glibc wrappers around syscalls such as `bind(2)` and `connect(2)`. It's done by a shared library that is preloaded for every process in a cgroup so that whenever TCP/UDP server calls `bind(2)`, the library replaces IP in sockaddr before passing arguments to syscall. When application calls `connect(2)` the library transparently binds the local end of connection to that IP (`bind(2)` with `IP_BIND_ADDRESS_NO_PORT` to avoid performance penalty). Shared library approach is fragile though, e.g.: * some applications clear env vars (incl. `LD_PRELOAD`); * `/etc/ld.so.preload` doesn't help since some applications are linked with option `-z nodefaultlib`; * other applications don't use glibc and there is nothing to intercept. == The solution == The patch provides much more reliable in-kernel solution for the 1st part of the problem: binding TCP/UDP servers on desired IP. It does not depend on application environment and implementation details (whether glibc is used or not). It adds new eBPF program type `BPF_PROG_TYPE_CGROUP_SOCK_ADDR` and attach types `BPF_CGROUP_INET4_BIND` and `BPF_CGROUP_INET6_BIND` (similar to already existing `BPF_CGROUP_INET_SOCK_CREATE`). The new program type is intended to be used with sockets (`struct sock`) in a cgroup and provided by user `struct sockaddr`. Pointers to both of them are parts of the context passed to programs of newly added types. The new attach types provides hooks in `bind(2)` system call for both IPv4 and IPv6 so that one can write a program to override IP addresses and ports user program tries to bind to and apply such a program for whole cgroup. == Implementation notes == [1] Separate attach types for `AF_INET` and `AF_INET6` are added intentionally to prevent reading/writing to offsets that don't make sense for corresponding socket family. E.g. if user passes `sockaddr_in` it doesn't make sense to read from / write to `user_ip6[]` context fields. [2] The write access to `struct bpf_sock_addr_kern` is implemented using special field as an additional "register". There are just two registers in `sock_addr_convert_ctx_access`: `src` with value to write and `dst` with pointer to context that can't be changed not to break later instructions. But the fields, allowed to write to, are not available directly and to access them address of corresponding pointer has to be loaded first. To get additional register the 1st not used by `src` and `dst` one is taken, its content is saved to `bpf_sock_addr_kern.tmp_reg`, then the register is used to load address of pointer field, and finally the register's content is restored from the temporary field after writing `src` value. Signed-off-by: Andrey Ignatov <rdna@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Diffstat (limited to 'kernel/bpf/syscall.c')
-rw-r--r--kernel/bpf/syscall.c36
1 files changed, 28 insertions, 8 deletions
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 9d3b572d4dec..2cad66a4cacb 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1175,19 +1175,29 @@ static int
bpf_prog_load_check_attach_type(enum bpf_prog_type prog_type,
enum bpf_attach_type expected_attach_type)
{
- /* There are currently no prog types that require specifying
- * attach_type at load time.
- */
- return 0;
+ switch (prog_type) {
+ case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
+ switch (expected_attach_type) {
+ case BPF_CGROUP_INET4_BIND:
+ case BPF_CGROUP_INET6_BIND:
+ return 0;
+ default:
+ return -EINVAL;
+ }
+ default:
+ return 0;
+ }
}
static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
enum bpf_attach_type attach_type)
{
- /* There are currently no prog types that require specifying
- * attach_type at load time.
- */
- return 0;
+ switch (prog->type) {
+ case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
+ return attach_type == prog->expected_attach_type ? 0 : -EINVAL;
+ default:
+ return 0;
+ }
}
/* last field in 'union bpf_attr' used by this command */
@@ -1479,6 +1489,10 @@ static int bpf_prog_attach(const union bpf_attr *attr)
case BPF_CGROUP_INET_SOCK_CREATE:
ptype = BPF_PROG_TYPE_CGROUP_SOCK;
break;
+ case BPF_CGROUP_INET4_BIND:
+ case BPF_CGROUP_INET6_BIND:
+ ptype = BPF_PROG_TYPE_CGROUP_SOCK_ADDR;
+ break;
case BPF_CGROUP_SOCK_OPS:
ptype = BPF_PROG_TYPE_SOCK_OPS;
break;
@@ -1541,6 +1555,10 @@ static int bpf_prog_detach(const union bpf_attr *attr)
case BPF_CGROUP_INET_SOCK_CREATE:
ptype = BPF_PROG_TYPE_CGROUP_SOCK;
break;
+ case BPF_CGROUP_INET4_BIND:
+ case BPF_CGROUP_INET6_BIND:
+ ptype = BPF_PROG_TYPE_CGROUP_SOCK_ADDR;
+ break;
case BPF_CGROUP_SOCK_OPS:
ptype = BPF_PROG_TYPE_SOCK_OPS;
break;
@@ -1590,6 +1608,8 @@ static int bpf_prog_query(const union bpf_attr *attr,
case BPF_CGROUP_INET_INGRESS:
case BPF_CGROUP_INET_EGRESS:
case BPF_CGROUP_INET_SOCK_CREATE:
+ case BPF_CGROUP_INET4_BIND:
+ case BPF_CGROUP_INET6_BIND:
case BPF_CGROUP_SOCK_OPS:
case BPF_CGROUP_DEVICE:
break;