From: Alexander Mikhalitsyn aleksandr.mikhalitsyn@canonical.com
[ Upstream commit 2598619e012cee5273a2821441b9a051ad931249 ]
Implement ->bpf_bypass_getsockopt proto callback and filter out SCTP_SOCKOPT_PEELOFF, SCTP_SOCKOPT_PEELOFF_FLAGS and SCTP_SOCKOPT_CONNECTX3 socket options from running eBPF hook on them.
SCTP_SOCKOPT_PEELOFF and SCTP_SOCKOPT_PEELOFF_FLAGS options do fd_install(), and if BPF_CGROUP_RUN_PROG_GETSOCKOPT hook returns an error after success of the original handler sctp_getsockopt(...), userspace will receive an error from getsockopt syscall and will be not aware that fd was successfully installed into a fdtable.
As pointed by Marcelo Ricardo Leitner it seems reasonable to skip bpf getsockopt hook for SCTP_SOCKOPT_CONNECTX3 sockopt too. Because internaly, it triggers connect() and if error is masked then userspace will be confused.
This patch was born as a result of discussion around a new SCM_PIDFD interface: https://lore.kernel.org/all/20230413133355.350571-3-aleksandr.mikhalitsyn@ca...
Fixes: 0d01da6afc54 ("bpf: implement getsockopt and setsockopt hooks") Cc: Daniel Borkmann daniel@iogearbox.net Cc: Christian Brauner brauner@kernel.org Cc: Stanislav Fomichev sdf@google.com Cc: Neil Horman nhorman@tuxdriver.com Cc: Marcelo Ricardo Leitner marcelo.leitner@gmail.com Cc: Xin Long lucien.xin@gmail.com Cc: linux-sctp@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: netdev@vger.kernel.org Suggested-by: Stanislav Fomichev sdf@google.com Acked-by: Stanislav Fomichev sdf@google.com Signed-off-by: Alexander Mikhalitsyn aleksandr.mikhalitsyn@canonical.com Acked-by: Xin Long lucien.xin@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/sctp/socket.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+)
diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 35d3eee26ea56..4a7f811abae4e 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -8039,6 +8039,22 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname, return retval; }
+static bool sctp_bpf_bypass_getsockopt(int level, int optname) +{ + if (level == SOL_SCTP) { + switch (optname) { + case SCTP_SOCKOPT_PEELOFF: + case SCTP_SOCKOPT_PEELOFF_FLAGS: + case SCTP_SOCKOPT_CONNECTX3: + return true; + default: + return false; + } + } + + return false; +} + static int sctp_hash(struct sock *sk) { /* STUB */ @@ -9407,6 +9423,7 @@ struct proto sctp_prot = { .shutdown = sctp_shutdown, .setsockopt = sctp_setsockopt, .getsockopt = sctp_getsockopt, + .bpf_bypass_getsockopt = sctp_bpf_bypass_getsockopt, .sendmsg = sctp_sendmsg, .recvmsg = sctp_recvmsg, .bind = sctp_bind, @@ -9459,6 +9476,7 @@ struct proto sctpv6_prot = { .shutdown = sctp_shutdown, .setsockopt = sctp_setsockopt, .getsockopt = sctp_getsockopt, + .bpf_bypass_getsockopt = sctp_bpf_bypass_getsockopt, .sendmsg = sctp_sendmsg, .recvmsg = sctp_recvmsg, .bind = sctp_bind,