mptcp: add bpf_setsockopt support
Subsystems (7)
v2 cover mptcp: add bpf_setsockopt support
From: Gang Yan <[email protected]>
Changelog:
v2:
- Patches 1 and 2 are new in this series; they address TCP_MAXSEG handling in the bpf_setsockopt() path [1].
- Patch 4 adds an early return to fix msk->sk_rcvlowat being unexpectedly modified, an issue seen in v1.
- Patch 5 makes the hook safe for the non-tcp master socket: it guards bpf_sock_ops_cb_flags_set() with sk_is_tcp() to prevent out-of-bounds heap reads/writes through tcp_sk(sk)->bpf_sock_ops_cb_flags, and does not set is_locked_tcp_sock for the msk (unlike tcp_call_bpf()). That flag authorizes the verifier's direct tcp_sock-offset field accesses; since the msk is not a tcp_sock, leaving it at the default 0 is safe.
v1:
Gang Yan (7):
mptcp: drop unused @max arg of __mptcp_setsockopt_set_val
mptcp: take TCP_MAXSEG handling into __mptcp_setsockopt_set_val
mptcp: use sockopt_lock/release_sock in sockopt
mptcp: reject sockopt requiring ssks' lock in BPF context
mptcp: enable bpf_setsockopt on the master socket
mptcp: add TCP_CONNECT_CB sock_ops hook
selftests: bpf: verify mptcp bpf_setsockopt from TCP_CONNECT_CB
include/net/mptcp.h | 9 ++ net/core/filter.c | 10 ++ net/ipv4/tcp.c | 1 + net/mptcp/protocol.c | 6 + net/mptcp/protocol.h | 29 ++++ net/mptcp/sockopt.c | 149 +++++++++--------- .../testing/selftests/bpf/prog_tests/mptcp.c | 61 +++++++ .../selftests/bpf/progs/mptcp_setsockopt.c | 32 ++++ 8 files changed, 223 insertions(+), 74 deletions(-) create mode 100644 tools/testing/selftests/bpf/progs/mptcp_setsockopt.c
Signature · 1 line
2.43.0
PATCH v2 1/7 mptcp: drop unused @max arg of __mptcp_setsockopt_set_val
From: Gang Yan <[email protected]>
The @max argument is never read in the function body. Remove it and the MAX_TCP_KEEP* values passed by the TCP_KEEPIDLE/INTVL/KEEPCNT callers.
--- net/mptcp/sockopt.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-)
net/mptcp/sockopt.c +4 -7
@@ -632,7 +632,7 @@ static int mptcp_setsockopt_sol_tcp_congestion(struct mptcp_sock *msk, sockptr_treturn ret; } -static int __mptcp_setsockopt_set_val (struct mptcp_sock *msk,int max, +static int __mptcp_setsockopt_set_val (struct mptcp_sock *msk,int (*set_val)(struct sock *,int ),int *msk_val,int val) {
@@ -876,18 +876,15 @@ static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname, ret =__mptcp_setsockopt_sol_tcp_nodelay (msk, val);break ;case TCP_KEEPIDLE : - ret =__mptcp_setsockopt_set_val (msk,MAX_TCP_KEEPIDLE , - &tcp_sock_set_keepidle_locked, + ret =__mptcp_setsockopt_set_val (msk, &tcp_sock_set_keepidle_locked, &msk->keepalive_idle, val);break ;case TCP_KEEPINTVL : - ret =__mptcp_setsockopt_set_val (msk,MAX_TCP_KEEPINTVL , - &tcp_sock_set_keepintvl, + ret =__mptcp_setsockopt_set_val (msk, &tcp_sock_set_keepintvl, &msk->keepalive_intvl, val);break ;case TCP_KEEPCNT : - ret =__mptcp_setsockopt_set_val (msk,MAX_TCP_KEEPCNT , - &tcp_sock_set_keepcnt, + ret =__mptcp_setsockopt_set_val (msk, &tcp_sock_set_keepcnt, &msk->keepalive_cnt, val);break ;
Signature · 1 line
2.43.0
PATCH v2 2/7 mptcp: take TCP_MAXSEG handling into __mptcp_setsockopt_set_val
In reply to Gang YanFrom: Gang Yan <[email protected]>
mptcp_setsockopt_all_sf is only used in 'TCP_MAXSEG', and it can be replaced with __mptcp_setsockopt_set_val.
--- net/ipv4/tcp.c | 1 + net/mptcp/sockopt.c | 27 ++------------------------- 2 files changed, 3 insertions(+), 25 deletions(-)
net/ipv4/tcp.c +1 -0
@@ -3830,6 +3830,7 @@ int tcp_sock_set_maxseg(struct sock *sk, int val)WRITE_ONCE (tcp_sk (sk)->rx_opt.user_mss, val);return 0 ; } +EXPORT_SYMBOL (tcp_sock_set_maxseg);/* * Socket option code for TCP.
net/mptcp/sockopt.c +2 -25
@@ -808,28 +808,6 @@ static int mptcp_setsockopt_first_sf_only(struct mptcp_sock *msk, int level, intreturn ret; } -static int mptcp_setsockopt_all_sf (struct mptcp_sock *msk,int level, -int optname,sockptr_t optval, -unsigned int optlen) -{ -struct mptcp_subflow_context *subflow; -int ret =0 ; - -mptcp_for_each_subflow (msk, subflow) { -struct sock *ssk =mptcp_subflow_tcp_sock (subflow); -int err; - - err =tcp_setsockopt (ssk, level, optname, optval, optlen); -if (err <0 && ret ==0 ) - ret = err; - } - -if (!ret) -sockopt_seq_inc (msk); - -return ret; -} -static int mptcp_setsockopt_sol_tcp (struct mptcp_sock *msk,int optname,sockptr_t optval,unsigned int optlen) {
@@ -889,9 +867,8 @@ static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname, val);break ;case TCP_MAXSEG : - msk->maxseg = val; - ret =mptcp_setsockopt_all_sf (msk,SOL_TCP , optname, optval, - optlen); + ret =__mptcp_setsockopt_set_val (msk, &tcp_sock_set_maxseg, + &msk->maxseg, val);break ;default : ret = -ENOPROTOOPT ;
Signature · 1 line
2.43.0
PATCH v2 3/7 mptcp: use sockopt_lock/release_sock in sockopt
In reply to Gang YanFrom: Gang Yan <[email protected]>
TCP and the core socket layer use sockopt_lock_sock() / sockopt_release_sock() in their setsockopt and getsockopt handlers.
Switch the MPTCP socket (msk) level lock_sock()/release_sock() calls to use the BPF-aware wrappers, making the MPTCP sockopt codepaths consistent with the rest of the networking stack.
--- net/mptcp/sockopt.c | 84 ++++++++++++++++++++++----------------------- 1 file changed, 42 insertions(+), 42 deletions(-)
net/mptcp/sockopt.c +42 -42
@@ -78,7 +78,7 @@ static void mptcp_sol_socket_sync_intval(struct mptcp_sock *msk, int optname, instruct mptcp_subflow_context *subflow;struct sock *sk = (struct sock *)msk; -lock_sock (sk); +sockopt_lock_sock (sk);sockopt_seq_inc (msk);mptcp_for_each_subflow (msk, subflow) {
@@ -123,7 +123,7 @@ static void mptcp_sol_socket_sync_intval(struct mptcp_sock *msk, int optname, inunlock_sock_fast (ssk, slow); } -release_sock (sk); +sockopt_release_sock (sk); }static int mptcp_sol_socket_intval (struct mptcp_sock *msk,int optname,int val)
@@ -162,7 +162,7 @@ static int mptcp_setsockopt_sol_socket_tstamp(struct mptcp_sock *msk, int optnamif (ret)return ret; -lock_sock (sk); +sockopt_lock_sock (sk);mptcp_for_each_subflow (msk, subflow) {struct sock *ssk =mptcp_subflow_tcp_sock (subflow);
@@ -171,7 +171,7 @@ static int mptcp_setsockopt_sol_socket_tstamp(struct mptcp_sock *msk, int optnamrelease_sock (ssk); } -release_sock (sk); +sockopt_release_sock (sk);return 0 ; }
@@ -237,7 +237,7 @@ static int mptcp_setsockopt_sol_socket_timestamping(struct mptcp_sock *msk,if (ret)return ret; -lock_sock (sk); +sockopt_lock_sock (sk);mptcp_for_each_subflow (msk, subflow) {struct sock *ssk =mptcp_subflow_tcp_sock (subflow);
@@ -251,7 +251,7 @@ static int mptcp_setsockopt_sol_socket_timestamping(struct mptcp_sock *msk, ret = err; } -release_sock (sk); +sockopt_release_sock (sk);return ret; }
@@ -276,7 +276,7 @@ static int mptcp_setsockopt_sol_socket_linger(struct mptcp_sock *msk, sockptr_tif (ret)return ret; -lock_sock (sk); +sockopt_lock_sock (sk);sockopt_seq_inc (msk);mptcp_for_each_subflow (msk, subflow) {struct sock *ssk =mptcp_subflow_tcp_sock (subflow);
@@ -293,7 +293,7 @@ static int mptcp_setsockopt_sol_socket_linger(struct mptcp_sock *msk, sockptr_tunlock_sock_fast (ssk, slow); } -release_sock (sk); +sockopt_release_sock (sk);return 0 ; }
@@ -309,10 +309,10 @@ static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname,case SO_REUSEADDR :case SO_BINDTODEVICE :case SO_BINDTOIFINDEX : -lock_sock (sk); +sockopt_lock_sock (sk); ssk =__mptcp_nmpc_sk (msk);if (IS_ERR (ssk)) { -release_sock (sk); +sockopt_release_sock (sk);return PTR_ERR (ssk); }
@@ -327,7 +327,7 @@ static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname,else if (optname ==SO_BINDTOIFINDEX ) sk->sk_bound_dev_if = ssk->sk_bound_dev_if; } -release_sock (sk); +sockopt_release_sock (sk);return ret;case SO_KEEPALIVE :case SO_PRIORITY :
@@ -405,16 +405,16 @@ static int mptcp_setsockopt_v6(struct mptcp_sock *msk, int optname,case IPV6_V6ONLY :case IPV6_TRANSPARENT :case IPV6_FREEBIND : -lock_sock (sk); +sockopt_lock_sock (sk); ssk =__mptcp_nmpc_sk (msk);if (IS_ERR (ssk)) { -release_sock (sk); +sockopt_release_sock (sk);return PTR_ERR (ssk); } ret =tcp_setsockopt (ssk,SOL_IPV6 , optname, optval, optlen);if (ret !=0 ) { -release_sock (sk); +sockopt_release_sock (sk);return ret; }
@@ -434,7 +434,7 @@ static int mptcp_setsockopt_v6(struct mptcp_sock *msk, int optname,break ; } -release_sock (sk); +sockopt_release_sock (sk);break ; }
@@ -611,7 +611,7 @@ static int mptcp_setsockopt_sol_tcp_congestion(struct mptcp_sock *msk, sockptr_t cap_net_admin =ns_capable (sock_net (sk)->user_ns,CAP_NET_ADMIN ); ret =0 ; -lock_sock (sk); +sockopt_lock_sock (sk);sockopt_seq_inc (msk);mptcp_for_each_subflow (msk, subflow) {struct sock *ssk =mptcp_subflow_tcp_sock (subflow);
@@ -628,7 +628,7 @@ static int mptcp_setsockopt_sol_tcp_congestion(struct mptcp_sock *msk, sockptr_tif (ret ==0 )strscpy (msk->ca_name, name,sizeof (msk->ca_name)); -release_sock (sk); +sockopt_release_sock (sk);return ret; }
@@ -707,11 +707,11 @@ static int mptcp_setsockopt_sol_ip_set(struct mptcp_sock *msk, int optname,if (err !=0 )return err; -lock_sock (sk); +sockopt_lock_sock (sk); ssk =__mptcp_nmpc_sk (msk);if (IS_ERR (ssk)) { -release_sock (sk); +sockopt_release_sock (sk);return PTR_ERR (ssk); }
@@ -732,13 +732,13 @@ static int mptcp_setsockopt_sol_ip_set(struct mptcp_sock *msk, int optname, READ_ONCE(inet_sk(sk)->local_port_range));break ;default : -release_sock (sk); +sockopt_release_sock (sk);WARN_ON_ONCE (1 );return -EOPNOTSUPP ; }sockopt_seq_inc (msk); -release_sock (sk); +sockopt_release_sock (sk);return 0 ; }
@@ -754,7 +754,7 @@ static int mptcp_setsockopt_v4_set_tos(struct mptcp_sock *msk, int optname,if (err !=0 )return err; -lock_sock (sk); +sockopt_lock_sock (sk);sockopt_seq_inc (msk); val =READ_ONCE (inet_sk (sk)->tos);mptcp_for_each_subflow (msk, subflow) {
@@ -765,7 +765,7 @@ static int mptcp_setsockopt_v4_set_tos(struct mptcp_sock *msk, int optname,__ip_sock_set_tos (ssk, val);unlock_sock_fast (ssk, slow); } -release_sock (sk); +sockopt_release_sock (sk);return 0 ; }
@@ -794,7 +794,7 @@ static int mptcp_setsockopt_first_sf_only(struct mptcp_sock *msk, int level, intint ret;/* Limit to first subflow, before the connection establishment */ -lock_sock (sk); +sockopt_lock_sock (sk); ssk =__mptcp_nmpc_sk (msk);if (IS_ERR (ssk)) { ret =PTR_ERR (ssk);
@@ -804,7 +804,7 @@ static int mptcp_setsockopt_first_sf_only(struct mptcp_sock *msk, int level, int ret =tcp_setsockopt (ssk, level, optname, optval, optlen); unlock: -release_sock (sk); +sockopt_release_sock (sk);return ret; }
@@ -835,7 +835,7 @@ static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname,if (ret)return ret; -lock_sock (sk); +sockopt_lock_sock (sk);switch (optname) {case TCP_INQ :if (val <0 || val >1 )
@@ -874,7 +874,7 @@ static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname, ret = -ENOPROTOOPT ; } -release_sock (sk); +sockopt_release_sock (sk);return ret; }
@@ -898,9 +898,9 @@ int mptcp_setsockopt(struct sock *sk, int level, int optname,* is in TCP fallback, when TCP socket options are passed through * to the one remaining subflow. */ -lock_sock (sk); +sockopt_lock_sock (sk); ssk =__mptcp_tcp_fallback (msk); -release_sock (sk); +sockopt_release_sock (sk);if (ssk)return tcp_setsockopt (ssk, level, optname, optval, optlen);
@@ -923,7 +923,7 @@ static int mptcp_getsockopt_first_sf_only(struct mptcp_sock *msk, int level, intstruct sock *ssk;int ret; -lock_sock (sk); +sockopt_lock_sock (sk); ssk = msk->first;if (ssk) goto get;
@@ -938,7 +938,7 @@ static int mptcp_getsockopt_first_sf_only(struct mptcp_sock *msk, int level, int ret =tcp_getsockopt (ssk, level, optname, optval, optlen); out: -release_sock (sk); +sockopt_release_sock (sk);return ret; }
@@ -1109,7 +1109,7 @@ static int mptcp_getsockopt_tcpinfo(struct mptcp_sock *msk, char __user *optval, infoptr = optval + sfd.size_subflow_data; -lock_sock (sk); +sockopt_lock_sock (sk);mptcp_for_each_subflow (msk, subflow) {struct sock *ssk =mptcp_subflow_tcp_sock (subflow);
@@ -1122,7 +1122,7 @@ static int mptcp_getsockopt_tcpinfo(struct mptcp_sock *msk, char __user *optval,tcp_get_info (ssk, &info);if (copy_to_user (infoptr, &info, sfd.size_user)) { -release_sock (sk); +sockopt_release_sock (sk);return -EFAULT ; }
@@ -1132,7 +1132,7 @@ static int mptcp_getsockopt_tcpinfo(struct mptcp_sock *msk, char __user *optval, } } -release_sock (sk); +sockopt_release_sock (sk); sfd.num_subflows = sfcount;
@@ -1201,7 +1201,7 @@ static int mptcp_getsockopt_subflow_addrs(struct mptcp_sock *msk, char __user *o addrptr = optval + sfd.size_subflow_data; -lock_sock (sk); +sockopt_lock_sock (sk);mptcp_for_each_subflow (msk, subflow) {struct sock *ssk =mptcp_subflow_tcp_sock (subflow);
@@ -1214,7 +1214,7 @@ static int mptcp_getsockopt_subflow_addrs(struct mptcp_sock *msk, char __user *omptcp_get_sub_addrs (ssk, &a);if (copy_to_user (addrptr, &a, sfd.size_user)) { -release_sock (sk); +sockopt_release_sock (sk);return -EFAULT ; }
@@ -1224,7 +1224,7 @@ static int mptcp_getsockopt_subflow_addrs(struct mptcp_sock *msk, char __user *o } } -release_sock (sk); +sockopt_release_sock (sk); sfd.num_subflows = sfcount;
@@ -1310,7 +1310,7 @@ static int mptcp_getsockopt_full_info(struct mptcp_sock *msk, char __user *optva sizeof(struct mptcp_subflow_info)); tcpinfoptr =u64_to_user_ptr (mfi.tcp_info); -lock_sock (sk); +sockopt_lock_sock (sk);mptcp_for_each_subflow (msk, subflow) {struct sock *ssk =mptcp_subflow_tcp_sock (subflow);struct mptcp_subflow_info sfinfo;
@@ -1340,7 +1340,7 @@ static int mptcp_getsockopt_full_info(struct mptcp_sock *msk, char __user *optva tcpinfoptr += mfi.size_tcpinfo_user; sfinfoptr += mfi.size_sfinfo_user; } -release_sock (sk); +sockopt_release_sock (sk); mfi.num_subflows = sfcount;if (mptcp_put_full_info (&mfi, optval, copylen, optlen))
@@ -1349,7 +1349,7 @@ static int mptcp_getsockopt_full_info(struct mptcp_sock *msk, char __user *optvareturn 0 ; fail_release: -release_sock (sk); +sockopt_release_sock (sk);return -EFAULT ; }
@@ -1504,9 +1504,9 @@ int mptcp_getsockopt(struct sock *sk, int level, int optname,* is in TCP fallback, when socket options are passed through * to the one remaining subflow. */ -lock_sock (sk); +sockopt_lock_sock (sk); ssk =__mptcp_tcp_fallback (msk); -release_sock (sk); +sockopt_release_sock (sk);if (ssk)return tcp_getsockopt (ssk, level, optname, optval, option);
Signature · 1 line
2.43.0
PATCH v2 4/7 mptcp: reject sockopt requiring ssks' lock in BPF context
In reply to Gang YanFrom: Gang Yan <[email protected]>
Several MPTCP setsockopt handlers need to acquire the subflow lock via lock_sock(ssk) to propagate settings to each subflow. This lock can sleep and is therefore not usable in BPF context where sleeping is forbidden.
The short-term solution is to make any sockopt operation that requires subflow-level lock fail with -EOPNOTSUPP when called from BPF context.
--- net/mptcp/sockopt.c | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+)
net/mptcp/sockopt.c +27 -0
@@ -185,6 +185,9 @@ static int mptcp_setsockopt_sol_socket_int(struct mptcp_sock *msk, int optname,if (ret)return ret; +if (has_current_bpf_ctx ()) +return -EOPNOTSUPP ; +switch (optname) {case SO_KEEPALIVE :case SO_DEBUG :
@@ -218,6 +221,9 @@ static int mptcp_setsockopt_sol_socket_timestamping(struct mptcp_sock *msk,struct so_timestamping timestamping;int ret; +if (has_current_bpf_ctx ()) +return -EOPNOTSUPP ; +if (optlen ==sizeof (timestamping)) {if (copy_from_sockptr (×tamping, optval,sizeof (timestamping)))
@@ -265,6 +271,9 @@ static int mptcp_setsockopt_sol_socket_linger(struct mptcp_sock *msk, sockptr_tsockptr_t kopt;int ret; +if (has_current_bpf_ctx ()) +return -EOPNOTSUPP ; +if (optlen <sizeof (ling))return -EINVAL ;
@@ -598,6 +607,9 @@ static int mptcp_setsockopt_sol_tcp_congestion(struct mptcp_sock *msk, sockptr_tbool cap_net_admin;int ret; +if (has_current_bpf_ctx ()) +return -EOPNOTSUPP ; +if (optlen <1 )return -EINVAL ;
@@ -639,6 +651,9 @@ static int __mptcp_setsockopt_set_val(struct mptcp_sock *msk,struct mptcp_subflow_context *subflow;int err =0 ; +if (has_current_bpf_ctx ()) +return -EOPNOTSUPP ; +mptcp_for_each_subflow (msk, subflow) {struct sock *ssk =mptcp_subflow_tcp_sock (subflow);int ret;
@@ -662,6 +677,9 @@ static int __mptcp_setsockopt_sol_tcp_cork(struct mptcp_sock *msk, int val)struct mptcp_subflow_context *subflow;struct sock *sk = (struct sock *)msk; +if (has_current_bpf_ctx ()) +return -EOPNOTSUPP ; +sockopt_seq_inc (msk); msk->cork = !!val;mptcp_for_each_subflow (msk, subflow) {
@@ -682,6 +700,9 @@ static int __mptcp_setsockopt_sol_tcp_nodelay(struct mptcp_sock *msk, int val)struct mptcp_subflow_context *subflow;struct sock *sk = (struct sock *)msk; +if (has_current_bpf_ctx ()) +return -EOPNOTSUPP ; +sockopt_seq_inc (msk); msk->nodelay = !!val;mptcp_for_each_subflow (msk, subflow) {
@@ -749,6 +770,9 @@ static int mptcp_setsockopt_v4_set_tos(struct mptcp_sock *msk, int optname,struct sock *sk = (struct sock *)msk;int err, val; +if (has_current_bpf_ctx ()) +return -EOPNOTSUPP ; + err =ip_setsockopt (sk,SOL_IP , optname, optval, optlen);if (err !=0 )
@@ -1610,6 +1634,9 @@ int mptcp_set_rcvlowat(struct sock *sk, int val)if (sk->sk_protocol ==IPPROTO_TCP )return -EINVAL ; +if (has_current_bpf_ctx ()) +return -EOPNOTSUPP ; +if (sk->sk_userlocks &SOCK_RCVBUF_LOCK ) cap = sk->sk_rcvbuf >>1 ;else
Signature · 1 line
2.43.0
PATCH v2 5/7 mptcp: enable bpf_setsockopt on the master socket
In reply to Gang YanFrom: Gang Yan <[email protected]>
bpf_setsockopt() currently cannot be used on mptcp master sockets:__bpf_setsockopt() dispatches by level to the protocol-agnostic sol_*_sockopt() helpers, which either reject the msk (sk_protocol == IPPROTO_MPTCP) and the ssk (sk_is_tcp() is false) or bypass mptcp's own dispatch (e.g. SOL_IP going straight to do_ip_setsockopt()).
This patch routes any level to mptcp_setsockopt(), which already handles all levels.
--- include/net/mptcp.h | 9 +++++++++ net/core/filter.c | 7 +++++++ 2 files changed, 16 insertions(+)
include/net/mptcp.h +9 -0
@@ -237,6 +237,9 @@ static inline __be32 mptcp_reset_option(const struct sk_buff *skb) }void mptcp_active_detect_blackhole (struct sock *sk,bool expired); + +int mptcp_setsockopt (struct sock *sk,int level,int optname, +sockptr_t optval,unsigned int optlen);#else static inline void mptcp_init (void )
@@ -314,6 +317,12 @@ static inline struct request_sock *mptcp_subflow_reqsk_alloc(const struct requesstatic inline __be32 mptcp_reset_option (const struct sk_buff *skb) {return htonl (0u ); }static inline void mptcp_active_detect_blackhole (struct sock *sk,bool expired) { } + +static inline int mptcp_setsockopt (struct sock *sk,int level,int optname, +sockptr_t optval,unsigned int optlen) +{ +return -EINVAL ; +}#endif /* CONFIG_MPTCP */ #if IS_ENABLED (CONFIG_MPTCP_IPV6 )
net/core/filter.c +7 -0
@@ -5683,6 +5683,13 @@ static int __bpf_setsockopt(struct sock *sk, int level, int optname,if (!sk_fullsock (sk))return -EINVAL ; +/* Route any bpf_setsockopt on the mptcp socket to mptcp_setsockopt, +* which handles all levels. +*/ +if (IS_ENABLED (CONFIG_MPTCP ) && sk->sk_protocol ==IPPROTO_MPTCP ) +return mptcp_setsockopt (sk, level, optname, +KERNEL_SOCKPTR (optval), optlen); +if (level ==SOL_SOCKET )return sol_socket_sockopt (sk, optname, optval, &optlen, false);else if (IS_ENABLED (CONFIG_INET ) && level ==SOL_IP )
Signature · 1 line
2.43.0
PATCH v2 6/7 mptcp: add TCP_CONNECT_CB sock_ops hook
In reply to Gang YanFrom: Gang Yan <[email protected]>
This patch adds a helper named 'mptcp_call_bpf' like tcp_call_bpf. Invoke the new helper from mptcp_connect() with BPF_SOCK_OPS_TCP_CONNECT_CB, placed after the subflow lock is acquired and before tcp_connect(). At this point the msk lock is held by __inet_stream_connect(), mirroring the placement of TCP_CONNECT_CB in tcp_v4_connect()/tcp_v6_connect().
'bpf_sock_ops_cb_flags_set' can be called via msk, so using sk_is_tcp() to avoid this issue.
---
Note:
I'm using CONFIG_BPF_JIT here because it is used in bpf.c for conditional compilation. However, maybe the macro in bpf.c should be changed to CONFIG_BPF instead?
WDYT?
--- net/core/filter.c | 3 +++ net/mptcp/protocol.c | 6 ++++++ net/mptcp/protocol.h | 29 +++++++++++++++++++++++++++++ 3 files changed, 38 insertions(+)
net/core/filter.c +3 -0
@@ -6097,6 +6097,9 @@ BPF_CALL_2(bpf_sock_ops_cb_flags_set, struct bpf_sock_ops_kern *, bpf_sock,if (!IS_ENABLED (CONFIG_INET ) || !sk_fullsock (sk))return -EINVAL ; +if (!sk_is_tcp (sk)) +return -EOPNOTSUPP ; +tcp_sk (sk)->bpf_sock_ops_cb_flags = val;return argval & (~BPF_SOCK_OPS_ALL_CB_FLAGS );
net/mptcp/protocol.c +6 -0
@@ -4149,6 +4149,12 @@ static int mptcp_connect(struct sock *sk, struct sockaddr_unsized *uaddr,if (!msk->fastopening)lock_sock (ssk); +/* Notify cgroup BPF on the msk before initiating the subflow connect. +* Mirrors BPF_SOCK_OPS_TCP_CONNECT_CB; msk lock is held by the +* caller (__inet_stream_connect) and ssk is held before. +*/ +mptcp_call_bpf (sk,BPF_SOCK_OPS_TCP_CONNECT_CB ,0 ,NULL ); +/* the following mirrors closely a very small chunk of code from * __inet_stream_connect() */
net/mptcp/protocol.h +29 -0
@@ -1374,4 +1374,33 @@ mptcp_token_join_cookie_init_state(struct mptcp_subflow_request_sock *subflow_restatic inline void mptcp_join_cookie_init (void ) {}#endif +#ifdef CONFIG_BPF_JIT +static inline int mptcp_call_bpf (struct sock *sk,int op,u32 nargs,u32 *args) +{ +struct bpf_sock_ops_kern sock_ops; +int ret; + +memset (&sock_ops,0 , offsetof(struct bpf_sock_ops_kern , temp)); + +if (sk_fullsock (sk)) { + sock_ops.is_fullsock =1 ; +sock_owned_by_me (sk); + } + + sock_ops.sk = sk; + sock_ops.op = op; + +if (nargs >0 ) +memcpy (sock_ops.args, args, nargs *sizeof (*args)); + + ret =BPF_CGROUP_RUN_PROG_SOCK_OPS (&sock_ops); +return ret ==0 ? sock_ops.reply :-1 ; +} +#else +static inline int mptcp_call_bpf (struct sock *sk,int op,u32 nargs,u32 *args) +{ +return -1 ; +} +#endif +#endif /* __MPTCP_PROTOCOL_H */
Signature · 1 line
2.43.0
PATCH v2 7/7 selftests: bpf: verify mptcp bpf_setsockopt from TCP_CONNECT_CB
In reply to Gang YanFrom: Gang Yan <[email protected]>
Add a BPF sockops program attached to BPF_CGROUP_SOCK_OPS that fires on BPF_SOCK_OPS_TCP_CONNECT_CB and exercises bpf_setsockopt() on the mptcp master socket (msk).
Two scenarios are covered by the new "setsockopt" subtest:
- TCP_INQ must succeed and the value (1) must be observable from userspace via getsockopt() on the mptcp socket.
- TCP_CONGESTION needs the subflow lock and is therefore rejected in bpf context with -EOPNOTSUPP.
--- .../testing/selftests/bpf/prog_tests/mptcp.c | 61 +++++++++++++++++++ .../selftests/bpf/progs/mptcp_setsockopt.c | 32 ++++++++++ 2 files changed, 93 insertions(+) create mode 100644 tools/testing/selftests/bpf/progs/mptcp_setsockopt.c
tools/testing/selftests/bpf/prog_tests/mptcp.c +61 -0
@@ -18,6 +18,7 @@#include "mptcp_bpf_rr.skel.h" #include "mptcp_bpf_red.skel.h" #include "mptcp_bpf_burst.skel.h" +#include "mptcp_setsockopt.skel.h" #define NS_TEST "mptcp_ns"#define ADDR_1 "10.0.1.1"
@@ -813,6 +814,64 @@ static void test_burst(void)mptcp_bpf_burst__destroy (skel); } +static void test_setsockopt (void ) +{ +struct mptcp_setsockopt *skel; +struct netns_obj *netns; +int cgroup_fd, server_fd, client_fd; +int err; +int inq; +socklen_t len; + + cgroup_fd =test__join_cgroup ("/mptcp_setsockopt" ); +if (!ASSERT_OK_FD (cgroup_fd,"join_cgroup" )) +return ; + + skel =mptcp_setsockopt__open_and_load (); +if (!ASSERT_OK_PTR (skel,"skel_open_load" )) + goto close_cgroup; + + skel->links.mptcp_connect_cb = +bpf_program__attach_cgroup (skel->progs.mptcp_connect_cb, + cgroup_fd); +if (!ASSERT_OK_PTR (skel->links.mptcp_connect_cb,"attach connect_cb" )) + goto skel_destroy; + + netns =netns_new (NS_TEST , true); +if (!ASSERT_OK_PTR (netns,"netns_new" )) + goto skel_destroy; + + server_fd =start_mptcp_server (AF_INET ,NULL ,0 ,0 ); +if (!ASSERT_OK_FD (server_fd,"start_mptcp_server" )) + goto close_netns; + + client_fd =connect_to_fd (server_fd,0 ); +if (!ASSERT_OK_FD (client_fd,"connect_to_fd" )) + goto close_server; + +/* TCP_INQ should be set successfullly */ +ASSERT_EQ (skel->bss->connect_cb_inq_ret,0 ,"connect_cb TCP_INQ ret" ); + + len =sizeof (inq); + err =getsockopt (client_fd,SOL_TCP ,TCP_INQ , &inq, &len); +if (ASSERT_OK (err,"getsockopt TCP_INQ" )) +ASSERT_EQ (inq,1 ,"TCP_INQ value" ); + +/* TCP_CONGESTION should be -EOPNOTSUPP */ +ASSERT_EQ (skel->bss->connect_cb_cc_ret, -EOPNOTSUPP , +"connect_cb TCP_CONGESTION ret" ); + +close (client_fd); +close_server: +close (server_fd); +close_netns: +netns_free (netns); +skel_destroy: +mptcp_setsockopt__destroy (skel); +close_cgroup: +close (cgroup_fd); +} +void test_mptcp (void ) {if (test__start_subtest ("base" ))
@@ -835,4 +894,6 @@ void test_mptcp(void)test_red ();if (test__start_subtest ("burst" ))test_burst (); +if (test__start_subtest ("setsockopt" )) +test_setsockopt (); }
tools/testing/selftests/bpf/progs/mptcp_setsockopt.c new file +32 -0
@@ -0,0 +1,32 @@ +#include "bpf_tracing_net.h" +#include "mptcp_bpf.h" + +#ifndef TCP_INQ +#define TCP_INQ 36 +#endif + +int connect_cb_inq_ret; +int connect_cb_cc_ret; + +char cc_reno[TCP_CA_NAME_MAX ] ="reno" ; + +SEC("sockops") +int mptcp_connect_cb (struct bpf_sock_ops *skops) +{ +struct bpf_sock *sk = skops->sk; +int one =1 ; + +if (skops->op !=BPF_SOCK_OPS_TCP_CONNECT_CB ) +return 1 ; + +if (!sk || sk->protocol !=IPPROTO_MPTCP ) +return 1 ; + + connect_cb_inq_ret = +bpf_setsockopt (skops,SOL_TCP ,TCP_INQ , &one,sizeof (one)); + connect_cb_cc_ret = +bpf_setsockopt (skops,SOL_TCP ,TCP_CONGESTION , + cc_reno,sizeof (cc_reno)); + +return 1 ; +}
Signature · 1 line
2.43.0
Hi Gang,
Thank you for your modifications, that's great!
Our CI did some validations and here is its report:
- KVM Validation: normal (except selftest_mptcp_join): Success! ✅
- KVM Validation: normal (only selftest_mptcp_join): Success! ✅
- KVM Validation: debug (except selftest_mptcp_join): Success! ✅
- KVM Validation: debug (only selftest_mptcp_join): Success! ✅
- KVM Validation: btf-normal (only bpftest_all): Success! ✅
- KVM Validation: btf-debug (only bpftest_all): Success! ✅
- Task: https://github.com/multipath-tcp/mptcp_net-next/actions/runs/29797149050
Initiator: Patchew Applier
Commits: https://github.com/multipath-tcp/mptcp_net-next/commits/6e51b04fa682
Patchwork: https://patchwork.kernel.org/project/mptcp/list/?series=1131261
If there are some issues, you can reproduce them using the same environment as the one used by the CI thanks to a docker image, e.g.:
$ cd [kernel source code]
$ docker run -v "${PWD}:${PWD}:rw" -w "${PWD}" --privileged --rm -it \
--pull always mptcp/mptcp-upstream-virtme-docker:latest \
auto-normalFor more details:
https://github.com/multipath-tcp/mptcp-upstream-virtme-docker
Please note that despite all the efforts that have been already done to have a stable tests suite when executed on a public CI like here, it is possible some reported issues are not due to your modifications. Still, do not hesitate to help us improve that ;-)
Cheers,
MPTCP GH Action bot
Bot operated by Matthieu Baerts (NGI0 Core)
Geliang Tang
reviewerRe: [PATCH mptcp-next v2 2/7] mptcp: take TCP_MAXSEG handling into __mptcp_setsockopt_set_val
In reply to Gang YanHi Gang,
Quoted 47 lines · Gang Yan
From: Gang Yan <[email protected]>
mptcp_setsockopt_all_sfis only used in 'TCP_MAXSEG', and it can be replaced with__mptcp_setsockopt_set_val.Signed-off-by Gang Yan <[email protected]>---
net/ipv4/tcp.c | 1 +net/mptcp/sockopt.c| 27 ++-------------------------2 files changed, 3 insertions(+), 25 deletions(-)net/ipv4/tcp.c +1
-0@@ -3830,6 +3830,7 @@ int tcp_sock_set_maxseg(struct sock *sk, int val) WRITE_ONCE(tcp_sk(sk)->rx_opt.user_mss, val); return 0; } +EXPORT_SYMBOL (tcp_sock_set_maxseg);
/*
* Socket option code for TCP.net/mptcp/sockopt.c +0
-0@@ -808,28 +808,6 @@ static int mptcp_setsockopt_first_sf_only(struct
mptcp_sock*msk, int level, int
return ret;
}
-static int mptcp_setsockopt_all_sf(structmptcp_sock*msk, int level,net/mptcp/sockopt.c +0
-11- int optname, sockptr_t optval, - unsigned int optlen) -{ -struct mptcp_subflow_context *subflow; -int ret =0 ; - -mptcp_for_each_subflow (msk, subflow) { -struct sock *ssk =mptcp_subflow_tcp_sock (subflow); -int err; - - err = tcp_setsockopt(ssk, level, optname, optval,optlen);
net/mptcp/sockopt.c static int mptcp_setsockopt_first_sf_only(struct mptcp_sock *msk, int level, int · line 831
Quoted 9 lines
net/mptcp/sockopt.c +0
-9-if (err <0 && ret ==0 ) - ret = err; - } - -if (!ret) -sockopt_seq_inc (msk); - -return ret; -}
This helper will also be used when implementing IPV6_TCLASS [1], so don't delete it for now. Let's wait until IPV6_TCLASS is merged before posting this patch.
Thanks,
-Geliang
Quoted 21 lines
-
static int mptcp_setsockopt_sol_tcp(structmptcp_sock*msk, int optname,
sockptr_toptval, unsigned int optlen)
{net/mptcp/sockopt.c +0
-0@@ -889,9 +867,8 @@ static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname, val); break;case
TCP_MAXSEG:net/mptcp/sockopt.c +0
-2- msk->maxseg = val; - ret = mptcp_setsockopt_all_sf(msk, SOL_TCP, optname,optval,
net/mptcp/sockopt.c +1
-1- optlen); + ret = __mptcp_setsockopt_set_val(msk,
&tcp_sock_set_maxseg,net/mptcp/sockopt.c +1
-0+ &msk->maxseg, val);break;
default:
ret =-ENOPROTOOPT;