tmakin/ack-tegra
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'net: bpf: handle return value of post_bind{4,6} and add selftests for it'

Browse Source 
Menglong Dong says:

====================

From: Menglong Dong <imagedong@tencent.com>

The return value of BPF_CGROUP_RUN_PROG_INET{4,6}_POST_BIND() in
__inet_bind() is not handled properly. While the return value
is non-zero, it will set inet_saddr and inet_rcv_saddr to 0 and
exit:

        err = BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk);
        if (err) {
                inet->inet_saddr = inet->inet_rcv_saddr = 0;
                goto out_release_sock;
        }

Let's take UDP for example and see what will happen. For UDP
socket, it will be added to 'udp_prot.h.udp_table->hash' and
'udp_prot.h.udp_table->hash2' after the sk->sk_prot->get_port()
called success. If 'inet->inet_rcv_saddr' is specified here,
then 'sk' will be in the 'hslot2' of 'hash2' that it don't belong
to (because inet_saddr is changed to 0), and UDP packet received
will not be passed to this sock. If 'inet->inet_rcv_saddr' is not
specified here, the sock will work fine, as it can receive packet
properly, which is wired, as the 'bind()' is already failed.

To undo the get_port() operation, introduce the 'put_port' field
for 'struct proto'. For TCP proto, it is inet_put_port(); For UDP
proto, it is udp_lib_unhash(); For icmp proto, it is
ping_unhash().

Therefore, after sys_bind() fail caused by
BPF_CGROUP_RUN_PROG_INET4_POST_BIND(), it will be unbinded, which
means that it can try to be binded to another port.

The second patch use C99 initializers in test_sock.c

The third patch is the selftests for this modification.

Changes since v4:
- use C99 initializers in test_sock.c before adding the test case

Changes since v3:
- add the third patch which use C99 initializers in test_sock.c

Changes since v2:
- NULL check for sk->sk_prot->put_port

Changes since v1:
- introduce 'put_port' field for 'struct proto'
- add selftests for it
====================

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
This commit is contained in:
Alexei Starovoitov
2022-01-06 17:08:35 -08:00
parent 44bab87d8c f734248174
commit eff14fcd03
10 changed files with 233 additions and 148 deletions
Download Patch File Download Diff File Expand all files Collapse all files
include/net/sock.h
+1
View File
@@ -1209,6 +1209,7 @@ struct proto {
void (*unhash)(struct sock *sk);
void (*rehash)(struct sock *sk);
int (*get_port)(struct sock *sk, unsigned short snum);
void (*put_port)(struct sock *sk);
#ifdef CONFIG_BPF_SYSCALL
int (*psock_update_sk_prot)(struct sock *sk,
struct sk_psock *psock,
net/ipv4/af_inet.c
+2
View File
@@ -531,6 +531,8 @@ int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
err = BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk);
if (err) {
inet->inet_saddr = inet->inet_rcv_saddr = 0;
if (sk->sk_prot->put_port)
sk->sk_prot->put_port(sk);
goto out_release_sock;
}
}
net/ipv4/ping.c
+1
View File
@@ -994,6 +994,7 @@ struct proto ping_prot = {
.hash = ping_hash,
.unhash = ping_unhash,
.get_port = ping_get_port,
.put_port = ping_unhash,
.obj_size = sizeof(struct inet_sock),
};
EXPORT_SYMBOL(ping_prot);
net/ipv4/tcp_ipv4.c
+1
View File
@@ -3076,6 +3076,7 @@ struct proto tcp_prot = {
.hash = inet_hash,
.unhash = inet_unhash,
.get_port = inet_csk_get_port,
.put_port = inet_put_port,
#ifdef CONFIG_BPF_SYSCALL
.psock_update_sk_prot = tcp_bpf_update_proto,
#endif
net/ipv4/udp.c
+1
View File
@@ -2927,6 +2927,7 @@ struct proto udp_prot = {
.unhash = udp_lib_unhash,
.rehash = udp_v4_rehash,
.get_port = udp_v4_get_port,
.put_port = udp_lib_unhash,
#ifdef CONFIG_BPF_SYSCALL
.psock_update_sk_prot = udp_bpf_update_proto,
#endif
net/ipv6/af_inet6.c
+2
View File
@@ -413,6 +413,8 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
if (err) {
sk->sk_ipv6only = saved_ipv6only;
inet_reset_saddr(sk);
if (sk->sk_prot->put_port)
sk->sk_prot->put_port(sk);
goto out;
}
}
net/ipv6/ping.c
+1
View File
@@ -177,6 +177,7 @@ struct proto pingv6_prot = {
.hash = ping_hash,
.unhash = ping_unhash,
.get_port = ping_get_port,
.put_port = ping_unhash,
.obj_size = sizeof(struct raw6_sock),
};
EXPORT_SYMBOL_GPL(pingv6_prot);
net/ipv6/tcp_ipv6.c
+1
View File
@@ -2181,6 +2181,7 @@ struct proto tcpv6_prot = {
.hash = inet6_hash,
.unhash = inet_unhash,
.get_port = inet_csk_get_port,
.put_port = inet_put_port,
#ifdef CONFIG_BPF_SYSCALL
.psock_update_sk_prot = tcp_bpf_update_proto,
#endif
net/ipv6/udp.c
+1
View File
@@ -1732,6 +1732,7 @@ struct proto udpv6_prot = {
.unhash = udp_lib_unhash,
.rehash = udp_v6_rehash,
.get_port = udp_v6_get_port,
.put_port = udp_lib_unhash,
#ifdef CONFIG_BPF_SYSCALL
.psock_update_sk_prot = udp_bpf_update_proto,
#endif
tools/testing/selftests/bpf/test_sock.c
+222 -148
View File
@@ -35,18 +35,21 @@ struct sock_test {
/* Endpoint to bind() to */
const char *ip;
unsigned short port;
unsigned short port_retry;
/* Expected test result */
enum {
LOAD_REJECT,
ATTACH_REJECT,
BIND_REJECT,
SUCCESS,
RETRY_SUCCESS,
RETRY_REJECT
} result;
};
static struct sock_test tests[] = {
{
"bind4 load with invalid access: src_ip6",
.descr = "bind4 load with invalid access: src_ip6",
.insns = {
BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
@@ -54,16 +57,12 @@ static struct sock_test tests[] = {
BPF_MOV64_IMM(BPF_REG_0, 1),
BPF_EXIT_INSN(),
},
BPF_CGROUP_INET4_POST_BIND,
BPF_CGROUP_INET4_POST_BIND,
0,
0,
NULL,
0,
LOAD_REJECT,
.expected_attach_type = BPF_CGROUP_INET4_POST_BIND,
.attach_type = BPF_CGROUP_INET4_POST_BIND,
.result = LOAD_REJECT,
},
{
"bind4 load with invalid access: mark",
.descr = "bind4 load with invalid access: mark",
.insns = {
BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
@@ -71,16 +70,12 @@ static struct sock_test tests[] = {
BPF_MOV64_IMM(BPF_REG_0, 1),
BPF_EXIT_INSN(),
},
BPF_CGROUP_INET4_POST_BIND,
BPF_CGROUP_INET4_POST_BIND,
0,
0,
NULL,
0,
LOAD_REJECT,
.expected_attach_type = BPF_CGROUP_INET4_POST_BIND,
.attach_type = BPF_CGROUP_INET4_POST_BIND,
.result = LOAD_REJECT,
},
{
"bind6 load with invalid access: src_ip4",
.descr = "bind6 load with invalid access: src_ip4",
.insns = {
BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
@@ -88,16 +83,12 @@ static struct sock_test tests[] = {
BPF_MOV64_IMM(BPF_REG_0, 1),
BPF_EXIT_INSN(),
},
BPF_CGROUP_INET6_POST_BIND,
BPF_CGROUP_INET6_POST_BIND,
0,
0,
NULL,
0,
LOAD_REJECT,
.expected_attach_type = BPF_CGROUP_INET6_POST_BIND,
.attach_type = BPF_CGROUP_INET6_POST_BIND,
.result = LOAD_REJECT,
},
{
"sock_create load with invalid access: src_port",
.descr = "sock_create load with invalid access: src_port",
.insns = {
BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
@@ -105,128 +96,106 @@ static struct sock_test tests[] = {
BPF_MOV64_IMM(BPF_REG_0, 1),
BPF_EXIT_INSN(),
},
BPF_CGROUP_INET_SOCK_CREATE,
BPF_CGROUP_INET_SOCK_CREATE,
0,
0,
NULL,
0,
LOAD_REJECT,
.expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE,
.attach_type = BPF_CGROUP_INET_SOCK_CREATE,
.result = LOAD_REJECT,
},
{
"sock_create load w/o expected_attach_type (compat mode)",
.descr = "sock_create load w/o expected_attach_type (compat mode)",
.insns = {
BPF_MOV64_IMM(BPF_REG_0, 1),
BPF_EXIT_INSN(),
},
0,
BPF_CGROUP_INET_SOCK_CREATE,
AF_INET,
SOCK_STREAM,
"127.0.0.1",
8097,
SUCCESS,
.expected_attach_type = 0,
.attach_type = BPF_CGROUP_INET_SOCK_CREATE,
.domain = AF_INET,
.type = SOCK_STREAM,
.ip = "127.0.0.1",
.port = 8097,
.result = SUCCESS,
},
{
"sock_create load w/ expected_attach_type",
.descr = "sock_create load w/ expected_attach_type",
.insns = {
BPF_MOV64_IMM(BPF_REG_0, 1),
BPF_EXIT_INSN(),
},
BPF_CGROUP_INET_SOCK_CREATE,
BPF_CGROUP_INET_SOCK_CREATE,
AF_INET,
SOCK_STREAM,
"127.0.0.1",
8097,
SUCCESS,
.expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE,
.attach_type = BPF_CGROUP_INET_SOCK_CREATE,
.domain = AF_INET,
.type = SOCK_STREAM,
.ip = "127.0.0.1",
.port = 8097,
.result = SUCCESS,
},
{
"attach type mismatch bind4 vs bind6",
.descr = "attach type mismatch bind4 vs bind6",
.insns = {
BPF_MOV64_IMM(BPF_REG_0, 1),
BPF_EXIT_INSN(),
},
BPF_CGROUP_INET4_POST_BIND,
BPF_CGROUP_INET6_POST_BIND,
0,
0,
NULL,
0,
ATTACH_REJECT,
.expected_attach_type = BPF_CGROUP_INET4_POST_BIND,
.attach_type = BPF_CGROUP_INET6_POST_BIND,
.result = ATTACH_REJECT,
},
{
"attach type mismatch bind6 vs bind4",
.descr = "attach type mismatch bind6 vs bind4",
.insns = {
BPF_MOV64_IMM(BPF_REG_0, 1),
BPF_EXIT_INSN(),
},
BPF_CGROUP_INET6_POST_BIND,
BPF_CGROUP_INET4_POST_BIND,
0,
0,
NULL,
0,
ATTACH_REJECT,
.expected_attach_type = BPF_CGROUP_INET6_POST_BIND,
.attach_type = BPF_CGROUP_INET4_POST_BIND,
.result = ATTACH_REJECT,
},
{
"attach type mismatch default vs bind4",
.descr = "attach type mismatch default vs bind4",
.insns = {
BPF_MOV64_IMM(BPF_REG_0, 1),
BPF_EXIT_INSN(),
},
0,
BPF_CGROUP_INET4_POST_BIND,
0,
0,
NULL,
0,
ATTACH_REJECT,
.expected_attach_type = 0,
.attach_type = BPF_CGROUP_INET4_POST_BIND,
.result = ATTACH_REJECT,
},
{
"attach type mismatch bind6 vs sock_create",
.descr = "attach type mismatch bind6 vs sock_create",
.insns = {
BPF_MOV64_IMM(BPF_REG_0, 1),
BPF_EXIT_INSN(),
},
BPF_CGROUP_INET6_POST_BIND,
BPF_CGROUP_INET_SOCK_CREATE,
0,
0,
NULL,
0,
ATTACH_REJECT,
.expected_attach_type = BPF_CGROUP_INET6_POST_BIND,
.attach_type = BPF_CGROUP_INET_SOCK_CREATE,
.result = ATTACH_REJECT,
},
{
"bind4 reject all",
.descr = "bind4 reject all",
.insns = {
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
BPF_CGROUP_INET4_POST_BIND,
BPF_CGROUP_INET4_POST_BIND,
AF_INET,
SOCK_STREAM,
"0.0.0.0",
0,
BIND_REJECT,
.expected_attach_type = BPF_CGROUP_INET4_POST_BIND,
.attach_type = BPF_CGROUP_INET4_POST_BIND,
.domain = AF_INET,
.type = SOCK_STREAM,
.ip = "0.0.0.0",
.result = BIND_REJECT,
},
{
"bind6 reject all",
.descr = "bind6 reject all",
.insns = {
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
BPF_CGROUP_INET6_POST_BIND,
BPF_CGROUP_INET6_POST_BIND,
AF_INET6,
SOCK_STREAM,
"::",
0,
BIND_REJECT,
.expected_attach_type = BPF_CGROUP_INET6_POST_BIND,
.attach_type = BPF_CGROUP_INET6_POST_BIND,
.domain = AF_INET6,
.type = SOCK_STREAM,
.ip = "::",
.result = BIND_REJECT,
},
{
"bind6 deny specific IP & port",
.descr = "bind6 deny specific IP & port",
.insns = {
BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
@@ -247,16 +216,16 @@ static struct sock_test tests[] = {
BPF_MOV64_IMM(BPF_REG_0, 1),
BPF_EXIT_INSN(),
},
BPF_CGROUP_INET6_POST_BIND,
BPF_CGROUP_INET6_POST_BIND,
AF_INET6,
SOCK_STREAM,
"::1",
8193,
BIND_REJECT,
.expected_attach_type = BPF_CGROUP_INET6_POST_BIND,
.attach_type = BPF_CGROUP_INET6_POST_BIND,
.domain = AF_INET6,
.type = SOCK_STREAM,
.ip = "::1",
.port = 8193,
.result = BIND_REJECT,
},
{
"bind4 allow specific IP & port",
.descr = "bind4 allow specific IP & port",
.insns = {
BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
@@ -277,41 +246,132 @@ static struct sock_test tests[] = {
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
BPF_CGROUP_INET4_POST_BIND,
BPF_CGROUP_INET4_POST_BIND,
AF_INET,
SOCK_STREAM,
"127.0.0.1",
4098,
SUCCESS,
.expected_attach_type = BPF_CGROUP_INET4_POST_BIND,
.attach_type = BPF_CGROUP_INET4_POST_BIND,
.domain = AF_INET,
.type = SOCK_STREAM,
.ip = "127.0.0.1",
.port = 4098,
.result = SUCCESS,
},
{
"bind4 allow all",
.descr = "bind4 deny specific IP & port of TCP, and retry",
.insns = {
BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
/* if (ip == expected && port == expected) */
BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
offsetof(struct bpf_sock, src_ip4)),
BPF_JMP_IMM(BPF_JNE, BPF_REG_7,
__bpf_constant_ntohl(0x7F000001), 4),
BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
offsetof(struct bpf_sock, src_port)),
BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0x1002, 2),
/* return DENY; */
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_JMP_A(1),
/* else return ALLOW; */
BPF_MOV64_IMM(BPF_REG_0, 1),
BPF_EXIT_INSN(),
},
.expected_attach_type = BPF_CGROUP_INET4_POST_BIND,
.attach_type = BPF_CGROUP_INET4_POST_BIND,
.domain = AF_INET,
.type = SOCK_STREAM,
.ip = "127.0.0.1",
.port = 4098,
.port_retry = 5000,
.result = RETRY_SUCCESS,
},
{
.descr = "bind4 deny specific IP & port of UDP, and retry",
.insns = {
BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
/* if (ip == expected && port == expected) */
BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
offsetof(struct bpf_sock, src_ip4)),
BPF_JMP_IMM(BPF_JNE, BPF_REG_7,
__bpf_constant_ntohl(0x7F000001), 4),
BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
offsetof(struct bpf_sock, src_port)),
BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0x1002, 2),
/* return DENY; */
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_JMP_A(1),
/* else return ALLOW; */
BPF_MOV64_IMM(BPF_REG_0, 1),
BPF_EXIT_INSN(),
},
.expected_attach_type = BPF_CGROUP_INET4_POST_BIND,
.attach_type = BPF_CGROUP_INET4_POST_BIND,
.domain = AF_INET,
.type = SOCK_DGRAM,
.ip = "127.0.0.1",
.port = 4098,
.port_retry = 5000,
.result = RETRY_SUCCESS,
},
{
.descr = "bind6 deny specific IP & port, and retry",
.insns = {
BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
/* if (ip == expected && port == expected) */
BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
offsetof(struct bpf_sock, src_ip6[3])),
BPF_JMP_IMM(BPF_JNE, BPF_REG_7,
__bpf_constant_ntohl(0x00000001), 4),
BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
offsetof(struct bpf_sock, src_port)),
BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0x2001, 2),
/* return DENY; */
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_JMP_A(1),
/* else return ALLOW; */
BPF_MOV64_IMM(BPF_REG_0, 1),
BPF_EXIT_INSN(),
},
.expected_attach_type = BPF_CGROUP_INET6_POST_BIND,
.attach_type = BPF_CGROUP_INET6_POST_BIND,
.domain = AF_INET6,
.type = SOCK_STREAM,
.ip = "::1",
.port = 8193,
.port_retry = 9000,
.result = RETRY_SUCCESS,
},
{
.descr = "bind4 allow all",
.insns = {
BPF_MOV64_IMM(BPF_REG_0, 1),
BPF_EXIT_INSN(),
},
BPF_CGROUP_INET4_POST_BIND,
BPF_CGROUP_INET4_POST_BIND,
AF_INET,
SOCK_STREAM,
"0.0.0.0",
0,
SUCCESS,
.expected_attach_type = BPF_CGROUP_INET4_POST_BIND,
.attach_type = BPF_CGROUP_INET4_POST_BIND,
.domain = AF_INET,
.type = SOCK_STREAM,
.ip = "0.0.0.0",
.result = SUCCESS,
},
{
"bind6 allow all",
.descr = "bind6 allow all",
.insns = {
BPF_MOV64_IMM(BPF_REG_0, 1),
BPF_EXIT_INSN(),
},
BPF_CGROUP_INET6_POST_BIND,
BPF_CGROUP_INET6_POST_BIND,
AF_INET6,
SOCK_STREAM,
"::",
0,
SUCCESS,
.expected_attach_type = BPF_CGROUP_INET6_POST_BIND,
.attach_type = BPF_CGROUP_INET6_POST_BIND,
.domain = AF_INET6,
.type = SOCK_STREAM,
.ip = "::",
.result = SUCCESS,
},
};
@@ -351,14 +411,15 @@ static int attach_sock_prog(int cgfd, int progfd,
return bpf_prog_attach(progfd, cgfd, attach_type, BPF_F_ALLOW_OVERRIDE);
}
static int bind_sock(int domain, int type, const char *ip, unsigned short port)
static int bind_sock(int domain, int type, const char *ip,
unsigned short port, unsigned short port_retry)
{
struct sockaddr_storage addr;
struct sockaddr_in6 *addr6;
struct sockaddr_in *addr4;
int sockfd = -1;
socklen_t len;
int err = 0;
int res = SUCCESS;
sockfd = socket(domain, type, 0);
if (sockfd < 0)
@@ -384,21 +445,44 @@ static int bind_sock(int domain, int type, const char *ip, unsigned short port)
goto err;
}
if (bind(sockfd, (const struct sockaddr *)&addr, len) == -1)
goto err;
if (bind(sockfd, (const struct sockaddr *)&addr, len) == -1) {
/* sys_bind() may fail for different reasons, errno has to be
* checked to confirm that BPF program rejected it.
*/
if (errno != EPERM)
goto err;
if (port_retry)
goto retry;
res = BIND_REJECT;
goto out;
}
goto out;
retry:
if (domain == AF_INET)
addr4->sin_port = htons(port_retry);
else
addr6->sin6_port = htons(port_retry);
if (bind(sockfd, (const struct sockaddr *)&addr, len) == -1) {
if (errno != EPERM)
goto err;
res = RETRY_REJECT;
} else {
res = RETRY_SUCCESS;
}
goto out;
err:
err = -1;
res = -1;
out:
close(sockfd);
return err;
return res;
}
static int run_test_case(int cgfd, const struct sock_test *test)
{
int progfd = -1;
int err = 0;
int res;
printf("Test case: %s .. ", test->descr);
progfd = load_sock_prog(test->insns, test->expected_attach_type);
@@ -416,21 +500,11 @@ static int run_test_case(int cgfd, const struct sock_test *test)
goto err;
}
if (bind_sock(test->domain, test->type, test->ip, test->port) == -1) {
/* sys_bind() may fail for different reasons, errno has to be
* checked to confirm that BPF program rejected it.
*/
if (test->result == BIND_REJECT && errno == EPERM)
goto out;
else
goto err;
}
res = bind_sock(test->domain, test->type, test->ip, test->port,
test->port_retry);
if (res > 0 && test->result == res)
goto out;
if (test->result != SUCCESS)
goto err;
goto out;
err:
err = -1;
out: