UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

bpf: Propagate modified uaddrlen from cgroup sockaddr programs 

[ Upstream commit fefba7d1ae198dcbf8b3b432de46a4e29f8dbd8c ]

As prep for adding unix socket support to the cgroup sockaddr hooks,
let's propagate the sockaddr length back to the caller after running
a bpf cgroup sockaddr hook program. While not important for AF_INET or
AF_INET6, the sockaddr length is important when working with AF_UNIX
sockaddrs as the size of the sockaddr cannot be determined just from the
address family or the sockaddr's contents.

__cgroup_bpf_run_filter_sock_addr() is modified to take the uaddrlen as
an input/output argument. After running the program, the modified sockaddr
length is stored in the uaddrlen pointer.

Signed-off-by: Daan De Meyer <daan.j.demeyer@gmail.com>
Link: https://lore.kernel.org/r/20231011185113.140426-3-daan.j.demeyer@gmail.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Stable-dep-of: c5114710c8ce ("xsk: fix usage of multi-buffer BPF helpers for ZC XDP")
Signed-off-by: Sasha Levin <sashal@kernel.org>
This commit is contained in:
Daan De Meyer 2023-10-11 20:51:04 +02:00 committed by Greg Kroah-Hartman
parent b6e1a1b3b2
commit 6d71331eb0
11 changed files with 76 additions and 54 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

73
include/linux/bpf-cgroup.h
View File

@ -120,6 +120,7 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk,
int __cgroup_bpf_run_filter_sock_addr(struct sock *sk,
struct sockaddr *uaddr,
int *uaddrlen,
enum cgroup_bpf_attach_type atype,
void *t_ctx,
u32 *flags);
@ -230,22 +231,22 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk,
#define BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk) \
BPF_CGROUP_RUN_SK_PROG(sk, CGROUP_INET6_POST_BIND)
#define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, atype) \
#define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, uaddrlen, atype) \
({ \
int __ret = 0; \
if (cgroup_bpf_enabled(atype)) \
__ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, atype, \
NULL, NULL); \
__ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, uaddrlen, \
atype, NULL, NULL); \
__ret; \
})
#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, atype, t_ctx) \
#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, atype, t_ctx) \
({ \
int __ret = 0; \
if (cgroup_bpf_enabled(atype)) { \
lock_sock(sk); \
__ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, atype, \
t_ctx, NULL); \
__ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, uaddrlen, \
atype, t_ctx, NULL); \
release_sock(sk); \
} \
__ret; \
@ -256,14 +257,14 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk,
* (at bit position 0) is to indicate CAP_NET_BIND_SERVICE capability check
* should be bypassed (BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE).
*/
#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, atype, bind_flags) \
#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, uaddrlen, atype, bind_flags) \
({ \
u32 __flags = 0; \
int __ret = 0; \
if (cgroup_bpf_enabled(atype)) { \
lock_sock(sk); \
__ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, atype, \
NULL, &__flags); \
__ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, uaddrlen, \
atype, NULL, &__flags); \
release_sock(sk); \
if (__flags & BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE) \
*bind_flags |= BIND_NO_CAP_NET_BIND_SERVICE; \
@ -276,29 +277,29 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk,
cgroup_bpf_enabled(CGROUP_INET6_CONNECT)) && \
(sk)->sk_prot->pre_connect)
#define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr) \
BPF_CGROUP_RUN_SA_PROG(sk, uaddr, CGROUP_INET4_CONNECT)
#define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr, uaddrlen) \
BPF_CGROUP_RUN_SA_PROG(sk, uaddr, uaddrlen, CGROUP_INET4_CONNECT)
#define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr) \
BPF_CGROUP_RUN_SA_PROG(sk, uaddr, CGROUP_INET6_CONNECT)
#define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr, uaddrlen) \
BPF_CGROUP_RUN_SA_PROG(sk, uaddr, uaddrlen, CGROUP_INET6_CONNECT)
#define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr) \
BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_INET4_CONNECT, NULL)
#define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr, uaddrlen) \
BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_INET4_CONNECT, NULL)
#define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr) \
BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_INET6_CONNECT, NULL)
#define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, uaddrlen) \
BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_INET6_CONNECT, NULL)
#define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, t_ctx) \
BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_UDP4_SENDMSG, t_ctx)
#define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) \
BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, 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, CGROUP_UDP6_SENDMSG, t_ctx)
#define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) \
BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP6_SENDMSG, t_ctx)
#define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr) \
BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_UDP4_RECVMSG, NULL)
#define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr, uaddrlen) \
BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP4_RECVMSG, NULL)
#define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr) \
BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_UDP6_RECVMSG, NULL)
#define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr, uaddrlen) \
BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP6_RECVMSG, NULL)
/* The SOCK_OPS"_SK" macro should be used when sock_ops->sk is not a
* fullsock and its parent fullsock cannot be traced by
@ -477,24 +478,24 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map,
}
#define cgroup_bpf_enabled(atype) (0)
#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, atype, t_ctx) ({ 0; })
#define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, atype) ({ 0; })
#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, atype, t_ctx) ({ 0; })
#define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, uaddrlen, atype) ({ 0; })
#define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0)
#define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; })
#define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; })
#define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; })
#define BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk) ({ 0; })
#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, atype, flags) ({ 0; })
#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, uaddrlen, atype, flags) ({ 0; })
#define BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk) ({ 0; })
#define BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk) ({ 0; })
#define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr) ({ 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_UDP4_RECVMSG_LOCK(sk, uaddr) ({ 0; })
#define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr) ({ 0; })
#define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr, uaddrlen) ({ 0; })
#define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; })
#define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr, uaddrlen) ({ 0; })
#define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; })
#define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; })
#define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; })
#define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; })
#define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; })
#define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; })
#define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(atype, major, minor, access) ({ 0; })
#define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos) ({ 0; })

1
include/linux/filter.h
View File

@ -1285,6 +1285,7 @@ struct bpf_sock_addr_kern {
*/
u64 tmp_reg;
void *t_ctx; /* Attach type specific context. */
u32 uaddrlen;
};
struct bpf_sock_ops_kern {

17
kernel/bpf/cgroup.c
View File

@ -1450,6 +1450,9 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk);
* provided by user sockaddr
* @sk: sock struct that will use sockaddr
* @uaddr: sockaddr struct provided by user
* @uaddrlen: Pointer to the size of the sockaddr struct provided by user. It is
* read-only for AF_INET[6] uaddr but can be modified for AF_UNIX
* uaddr.
* @atype: The type of program to be executed
* @t_ctx: Pointer to attach type specific context
* @flags: Pointer to u32 which contains higher bits of BPF program
@ -1462,6 +1465,7 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk);
*/
int __cgroup_bpf_run_filter_sock_addr(struct sock *sk,
struct sockaddr *uaddr,
int *uaddrlen,
enum cgroup_bpf_attach_type atype,
void *t_ctx,
u32 *flags)
@ -1473,6 +1477,7 @@ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk,
};
struct sockaddr_storage unspec;
struct cgroup *cgrp;
int ret;
/* Check socket family since not all sockets represent network
* endpoint (e.g. AF_UNIX).
@ -1483,11 +1488,19 @@ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk,
if (!ctx.uaddr) {
memset(&unspec, 0, sizeof(unspec));
ctx.uaddr = (struct sockaddr *)&unspec;
ctx.uaddrlen = 0;
} else {
ctx.uaddrlen = *uaddrlen;
}
cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
return bpf_prog_run_array_cg(&cgrp->bpf, atype, &ctx, bpf_prog_run,
0, flags);
ret = bpf_prog_run_array_cg(&cgrp->bpf, atype, &ctx, bpf_prog_run,
0, flags);
if (!ret && uaddr)
*uaddrlen = ctx.uaddrlen;
return ret;
}
EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_addr);

7
net/ipv4/af_inet.c
View File

@ -455,7 +455,7 @@ int inet_bind_sk(struct sock *sk, struct sockaddr *uaddr, int addr_len)
/* BPF prog is run before any checks are done so that if the prog
* changes context in a wrong way it will be caught.
*/
err = BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr,
err = BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, &addr_len,
CGROUP_INET4_BIND, &flags);
if (err)
return err;
@ -797,6 +797,7 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr,
struct sock *sk = sock->sk;
struct inet_sock *inet = inet_sk(sk);
DECLARE_SOCKADDR(struct sockaddr_in *, sin, uaddr);
int sin_addr_len = sizeof(*sin);
sin->sin_family = AF_INET;
lock_sock(sk);
@ -809,7 +810,7 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr,
}
sin->sin_port = inet->inet_dport;
sin->sin_addr.s_addr = inet->inet_daddr;
BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin,
BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, &sin_addr_len,
CGROUP_INET4_GETPEERNAME);
} else {
__be32 addr = inet->inet_rcv_saddr;
@ -817,7 +818,7 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr,
addr = inet->inet_saddr;
sin->sin_port = inet->inet_sport;
sin->sin_addr.s_addr = addr;
BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin,
BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, &sin_addr_len,
CGROUP_INET4_GETSOCKNAME);
}
release_sock(sk);

2
net/ipv4/ping.c
View File

@ -301,7 +301,7 @@ static int ping_pre_connect(struct sock *sk, struct sockaddr *uaddr,
if (addr_len < sizeof(struct sockaddr_in))
return -EINVAL;
return BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr);
return BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr, &addr_len);
}
/* Checks the bind address and possibly modifies sk->sk_bound_dev_if. */

2
net/ipv4/tcp_ipv4.c
View File

@ -194,7 +194,7 @@ static int tcp_v4_pre_connect(struct sock *sk, struct sockaddr *uaddr,
sock_owned_by_me(sk);
return BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr);
return BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr, &addr_len);
}
/* This will initiate an outgoing connection. */

9
net/ipv4/udp.c
View File

@ -1143,7 +1143,9 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
if (cgroup_bpf_enabled(CGROUP_UDP4_SENDMSG) && !connected) {
err = BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk,
(struct sockaddr *)usin, &ipc.addr);
(struct sockaddr *)usin,
&msg->msg_namelen,
&ipc.addr);
if (err)
goto out_free;
if (usin) {
@ -1865,7 +1867,8 @@ try_again:
*addr_len = sizeof(*sin);
BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk,
(struct sockaddr *)sin);
(struct sockaddr *)sin,
addr_len);
}
if (udp_test_bit(GRO_ENABLED, sk))
@ -1904,7 +1907,7 @@ int udp_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
if (addr_len < sizeof(struct sockaddr_in))
return -EINVAL;
return BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr);
return BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr, &addr_len);
}
EXPORT_SYMBOL(udp_pre_connect);

9
net/ipv6/af_inet6.c
View File

@ -456,7 +456,7 @@ int inet6_bind_sk(struct sock *sk, struct sockaddr *uaddr, int addr_len)
/* BPF prog is run before any checks are done so that if the prog
* changes context in a wrong way it will be caught.
*/
err = BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr,
err = BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, &addr_len,
CGROUP_INET6_BIND, &flags);
if (err)
return err;
@ -522,6 +522,7 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr,
int peer)
{
struct sockaddr_in6 *sin = (struct sockaddr_in6 *)uaddr;
int sin_addr_len = sizeof(*sin);
struct sock *sk = sock->sk;
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
@ -541,7 +542,7 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr,
sin->sin6_addr = sk->sk_v6_daddr;
if (np->sndflow)
sin->sin6_flowinfo = np->flow_label;
BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin,
BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, &sin_addr_len,
CGROUP_INET6_GETPEERNAME);
} else {
if (ipv6_addr_any(&sk->sk_v6_rcv_saddr))
@ -549,13 +550,13 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr,
else
sin->sin6_addr = sk->sk_v6_rcv_saddr;
sin->sin6_port = inet->inet_sport;
BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin,
BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, &sin_addr_len,
CGROUP_INET6_GETSOCKNAME);
}
sin->sin6_scope_id = ipv6_iface_scope_id(&sin->sin6_addr,
sk->sk_bound_dev_if);
release_sock(sk);
return sizeof(*sin);
return sin_addr_len;
}
EXPORT_SYMBOL(inet6_getname);

2
net/ipv6/ping.c
View File

@ -56,7 +56,7 @@ static int ping_v6_pre_connect(struct sock *sk, struct sockaddr *uaddr,
if (addr_len < SIN6_LEN_RFC2133)
return -EINVAL;
return BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr);
return BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, &addr_len);
}
static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)

2
net/ipv6/tcp_ipv6.c
View File

@ -135,7 +135,7 @@ static int tcp_v6_pre_connect(struct sock *sk, struct sockaddr *uaddr,
sock_owned_by_me(sk);
return BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr);
return BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr, &addr_len);
}
static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,

6
net/ipv6/udp.c
View File

@ -410,7 +410,8 @@ try_again:
*addr_len = sizeof(*sin6);
BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk,
(struct sockaddr *)sin6);
(struct sockaddr *)sin6,
addr_len);
}
if (udp_test_bit(GRO_ENABLED, sk))
@ -1157,7 +1158,7 @@ static int udpv6_pre_connect(struct sock *sk, struct sockaddr *uaddr,
if (addr_len < SIN6_LEN_RFC2133)
return -EINVAL;
return BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr);
return BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, &addr_len);
}
/**
@ -1510,6 +1511,7 @@ do_udp_sendmsg:
if (cgroup_bpf_enabled(CGROUP_UDP6_SENDMSG) && !connected) {
err = BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk,
(struct sockaddr *)sin6,
&addr_len,
&fl6->saddr);
if (err)
goto out_no_dst;