nagai/kernel
3
0
Fork 0
forked from mirrors/linux
Code Pull requests Activity

bpf: Hooks for sys_sendmsg

Browse source 
In addition to already existing BPF hooks for sys_bind and sys_connect,
the patch provides new hooks for sys_sendmsg.

It leverages existing BPF program type `BPF_PROG_TYPE_CGROUP_SOCK_ADDR`
that provides access to socket itlself (properties like family, type,
protocol) and user-passed `struct sockaddr *` so that BPF program can
override destination IP and port for system calls such as sendto(2) or
sendmsg(2) and/or assign source IP to the socket.

The hooks are implemented as two new attach types:
`BPF_CGROUP_UDP4_SENDMSG` and `BPF_CGROUP_UDP6_SENDMSG` for UDPv4 and
UDPv6 correspondingly.

UDPv4 and UDPv6 separate attach types for same reason as sys_bind and
sys_connect hooks, i.e. to prevent reading from / writing to e.g.
user_ip6 fields when user passes sockaddr_in since it'd be out-of-bound.

The difference with already existing hooks is sys_sendmsg are
implemented only for unconnected UDP.

For TCP it doesn't make sense to change user-provided `struct sockaddr *`
at sendto(2)/sendmsg(2) time since socket either was already connected
and has source/destination set or wasn't connected and call to
sendto(2)/sendmsg(2) would lead to ENOTCONN anyway.

Connected UDP is already handled by sys_connect hooks that can override
source/destination at connect time and use fast-path later, i.e. these
hooks don't affect UDP fast-path.

Rewriting source IP is implemented differently than that in sys_connect
hooks. When sys_sendmsg is used with unconnected UDP it doesn't work to
just bind socket to desired local IP address since source IP can be set
on per-packet basis by using ancillary data (cmsg(3)). So no matter if
socket is bound or not, source IP has to be rewritten on every call to
sys_sendmsg.

To do so two new fields are added to UAPI `struct bpf_sock_addr`;
* `msg_src_ip4` to set source IPv4 for UDPv4;
* `msg_src_ip6` to set source IPv6 for UDPv6.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
This commit is contained in:
Andrey Ignatov 2018-05-25 08:55:23 -07:00 committed by Daniel Borkmann
parent 13193b0f39
commit 1cedee13d2
8 changed files with 125 additions and 9 deletions
repo.diff.show_diff_stats Download patch file Download diff file Expand all files Collapse all files

23
include/linux/bpf-cgroup.h
View file

@ -66,7 +66,8 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk,
int __cgroup_bpf_run_filter_sock_addr(struct sock *sk,
struct sockaddr *uaddr,
enum bpf_attach_type type);
enum bpf_attach_type type,
void *t_ctx);
int __cgroup_bpf_run_filter_sock_ops(struct sock *sk,
struct bpf_sock_ops_kern *sock_ops,
@ -120,16 +121,18 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
({ \
int __ret = 0; \
if (cgroup_bpf_enabled) \
__ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type); \
__ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type, \
NULL); \
__ret; \
})
#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, type) \
#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, type, t_ctx) \
({ \
int __ret = 0; \
if (cgroup_bpf_enabled) { \
lock_sock(sk); \
__ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type); \
__ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type, \
t_ctx); \
release_sock(sk); \
} \
__ret; \
@ -151,10 +154,16 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
BPF_CGROUP_RUN_SA_PROG(sk, uaddr, BPF_CGROUP_INET6_CONNECT)
#define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr) \
BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET4_CONNECT)
BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET4_CONNECT, NULL)
#define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr) \
BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET6_CONNECT)
BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET6_CONNECT, NULL)
#define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, t_ctx) \
BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_UDP4_SENDMSG, t_ctx)
#define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, t_ctx) \
BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_UDP6_SENDMSG, t_ctx)
#define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) \
({ \
@ -198,6 +207,8 @@ static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; }
#define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr) ({ 0; })
#define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr) ({ 0; })
#define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr) ({ 0; })
#define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, t_ctx) ({ 0; })
#define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, t_ctx) ({ 0; })
#define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; })
#define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; })

1
include/linux/filter.h
View file

@ -1010,6 +1010,7 @@ struct bpf_sock_addr_kern {
* only two (src and dst) are available at convert_ctx_access time
*/
u64 tmp_reg;
void *t_ctx; /* Attach type specific context. */
};
struct bpf_sock_ops_kern {

8
include/uapi/linux/bpf.h
View file

@ -160,6 +160,8 @@ enum bpf_attach_type {
BPF_CGROUP_INET6_CONNECT,
BPF_CGROUP_INET4_POST_BIND,
BPF_CGROUP_INET6_POST_BIND,
BPF_CGROUP_UDP4_SENDMSG,
BPF_CGROUP_UDP6_SENDMSG,
__MAX_BPF_ATTACH_TYPE
};
@ -2363,6 +2365,12 @@ struct bpf_sock_addr {
__u32 family; /* Allows 4-byte read, but no write */
__u32 type; /* Allows 4-byte read, but no write */
__u32 protocol; /* Allows 4-byte read, but no write */
__u32 msg_src_ip4; /* Allows 1,2,4-byte read an 4-byte write.
* Stored in network byte order.
*/
__u32 msg_src_ip6[4]; /* Allows 1,2,4-byte read an 4-byte write.
* Stored in network byte order.
*/
};
/* User bpf_sock_ops struct to access socket values and specify request ops

11
kernel/bpf/cgroup.c
View file

@ -500,6 +500,7 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk);
* @sk: sock struct that will use sockaddr
* @uaddr: sockaddr struct provided by user
* @type: The type of program to be exectuted
* @t_ctx: Pointer to attach type specific context
*
* socket is expected to be of type INET or INET6.
*
@ -508,12 +509,15 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk);
*/
int __cgroup_bpf_run_filter_sock_addr(struct sock *sk,
struct sockaddr *uaddr,
enum bpf_attach_type type)
enum bpf_attach_type type,
void *t_ctx)
{
struct bpf_sock_addr_kern ctx = {
.sk = sk,
.uaddr = uaddr,
.t_ctx = t_ctx,
};
struct sockaddr_storage unspec;
struct cgroup *cgrp;
int ret;
@ -523,6 +527,11 @@ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk,
if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6)
return 0;
if (!ctx.uaddr) {
memset(&unspec, 0, sizeof(unspec));
ctx.uaddr = (struct sockaddr *)&unspec;
}
cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], &ctx, BPF_PROG_RUN);

8
kernel/bpf/syscall.c
View file

@ -1249,6 +1249,8 @@ bpf_prog_load_check_attach_type(enum bpf_prog_type prog_type,
case BPF_CGROUP_INET6_BIND:
case BPF_CGROUP_INET4_CONNECT:
case BPF_CGROUP_INET6_CONNECT:
case BPF_CGROUP_UDP4_SENDMSG:
case BPF_CGROUP_UDP6_SENDMSG:
return 0;
default:
return -EINVAL;
@ -1565,6 +1567,8 @@ static int bpf_prog_attach(const union bpf_attr *attr)
case BPF_CGROUP_INET6_BIND:
case BPF_CGROUP_INET4_CONNECT:
case BPF_CGROUP_INET6_CONNECT:
case BPF_CGROUP_UDP4_SENDMSG:
case BPF_CGROUP_UDP6_SENDMSG:
ptype = BPF_PROG_TYPE_CGROUP_SOCK_ADDR;
break;
case BPF_CGROUP_SOCK_OPS:
@ -1635,6 +1639,8 @@ static int bpf_prog_detach(const union bpf_attr *attr)
case BPF_CGROUP_INET6_BIND:
case BPF_CGROUP_INET4_CONNECT:
case BPF_CGROUP_INET6_CONNECT:
case BPF_CGROUP_UDP4_SENDMSG:
case BPF_CGROUP_UDP6_SENDMSG:
ptype = BPF_PROG_TYPE_CGROUP_SOCK_ADDR;
break;
case BPF_CGROUP_SOCK_OPS:
@ -1692,6 +1698,8 @@ static int bpf_prog_query(const union bpf_attr *attr,
case BPF_CGROUP_INET6_POST_BIND:
case BPF_CGROUP_INET4_CONNECT:
case BPF_CGROUP_INET6_CONNECT:
case BPF_CGROUP_UDP4_SENDMSG:
case BPF_CGROUP_UDP6_SENDMSG:
case BPF_CGROUP_SOCK_OPS:
case BPF_CGROUP_DEVICE:
break;

39
net/core/filter.c
View file

@ -5299,6 +5299,7 @@ static bool sock_addr_is_valid_access(int off, int size,
switch (prog->expected_attach_type) {
case BPF_CGROUP_INET4_BIND:
case BPF_CGROUP_INET4_CONNECT:
case BPF_CGROUP_UDP4_SENDMSG:
break;
default:
return false;
@ -5308,6 +5309,24 @@ static bool sock_addr_is_valid_access(int off, int size,
switch (prog->expected_attach_type) {
case BPF_CGROUP_INET6_BIND:
case BPF_CGROUP_INET6_CONNECT:
case BPF_CGROUP_UDP6_SENDMSG:
break;
default:
return false;
}
break;
case bpf_ctx_range(struct bpf_sock_addr, msg_src_ip4):
switch (prog->expected_attach_type) {
case BPF_CGROUP_UDP4_SENDMSG:
break;
default:
return false;
}
break;
case bpf_ctx_range_till(struct bpf_sock_addr, msg_src_ip6[0],
msg_src_ip6[3]):
switch (prog->expected_attach_type) {
case BPF_CGROUP_UDP6_SENDMSG:
break;
default:
return false;
@ -5318,6 +5337,9 @@ static bool sock_addr_is_valid_access(int off, int size,
switch (off) {
case bpf_ctx_range(struct bpf_sock_addr, user_ip4):
case bpf_ctx_range_till(struct bpf_sock_addr, user_ip6[0], user_ip6[3]):
case bpf_ctx_range(struct bpf_sock_addr, msg_src_ip4):
case bpf_ctx_range_till(struct bpf_sock_addr, msg_src_ip6[0],
msg_src_ip6[3]):
/* Only narrow read access allowed for now. */
if (type == BPF_READ) {
bpf_ctx_record_field_size(info, size_default);
@ -6072,6 +6094,23 @@ static u32 sock_addr_convert_ctx_access(enum bpf_access_type type,
*insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg,
SK_FL_PROTO_SHIFT);
break;
case offsetof(struct bpf_sock_addr, msg_src_ip4):
/* Treat t_ctx as struct in_addr for msg_src_ip4. */
SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF(
struct bpf_sock_addr_kern, struct in_addr, t_ctx,
s_addr, BPF_SIZE(si->code), 0, tmp_reg);
break;
case bpf_ctx_range_till(struct bpf_sock_addr, msg_src_ip6[0],
msg_src_ip6[3]):
off = si->off;
off -= offsetof(struct bpf_sock_addr, msg_src_ip6[0]);
/* Treat t_ctx as struct in6_addr for msg_src_ip6. */
SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF(
struct bpf_sock_addr_kern, struct in6_addr, t_ctx,
s6_addr32[0], BPF_SIZE(si->code), off, tmp_reg);
break;
}
return insn - insn_buf;

20
net/ipv4/udp.c
View file

@ -901,6 +901,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
{
struct inet_sock *inet = inet_sk(sk);
struct udp_sock *up = udp_sk(sk);
DECLARE_SOCKADDR(struct sockaddr_in *, usin, msg->msg_name);
struct flowi4 fl4_stack;
struct flowi4 *fl4;
int ulen = len;
@ -955,8 +956,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
/*
* Get and verify the address.
*/
if (msg->msg_name) {
DECLARE_SOCKADDR(struct sockaddr_in *, usin, msg->msg_name);
if (usin) {
if (msg->msg_namelen < sizeof(*usin))
return -EINVAL;
if (usin->sin_family != AF_INET) {
@ -1010,6 +1010,22 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
rcu_read_unlock();
}
if (cgroup_bpf_enabled && !connected) {
err = BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk,
(struct sockaddr *)usin, &ipc.addr);
if (err)
goto out_free;
if (usin) {
if (usin->sin_port == 0) {
/* BPF program set invalid port. Reject it. */
err = -EINVAL;
goto out_free;
}
daddr = usin->sin_addr.s_addr;
dport = usin->sin_port;
}
}
saddr = ipc.addr;
ipc.addr = faddr = daddr;

24
net/ipv6/udp.c
View file

@ -1316,6 +1316,29 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
fl6.saddr = np->saddr;
fl6.fl6_sport = inet->inet_sport;
if (cgroup_bpf_enabled && !connected) {
err = BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk,
(struct sockaddr *)sin6, &fl6.saddr);
if (err)
goto out_no_dst;
if (sin6) {
if (ipv6_addr_v4mapped(&sin6->sin6_addr)) {
/* BPF program rewrote IPv6-only by IPv4-mapped
* IPv6. It's currently unsupported.
*/
err = -ENOTSUPP;
goto out_no_dst;
}
if (sin6->sin6_port == 0) {
/* BPF program set invalid port. Reject it. */
err = -EINVAL;
goto out_no_dst;
}
fl6.fl6_dport = sin6->sin6_port;
fl6.daddr = sin6->sin6_addr;
}
}
final_p = fl6_update_dst(&fl6, opt, &final);
if (final_p)
connected = false;
@ -1395,6 +1418,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
out:
dst_release(dst);
out_no_dst:
fl6_sock_release(flowlabel);
txopt_put(opt_to_free);
if (!err)