From: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@xxxxxxxxxxxxx> [ 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@xxxxxxxxxxxxx/ Fixes: 0d01da6afc54 ("bpf: implement getsockopt and setsockopt hooks") Cc: Daniel Borkmann <daniel@xxxxxxxxxxxxx> Cc: Christian Brauner <brauner@xxxxxxxxxx> Cc: Stanislav Fomichev <sdf@xxxxxxxxxx> Cc: Neil Horman <nhorman@xxxxxxxxxxxxx> Cc: Marcelo Ricardo Leitner <marcelo.leitner@xxxxxxxxx> Cc: Xin Long <lucien.xin@xxxxxxxxx> Cc: linux-sctp@xxxxxxxxxxxxxxx Cc: linux-kernel@xxxxxxxxxxxxxxx Cc: netdev@xxxxxxxxxxxxxxx Suggested-by: Stanislav Fomichev <sdf@xxxxxxxxxx> Acked-by: Stanislav Fomichev <sdf@xxxxxxxxxx> Signed-off-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@xxxxxxxxxxxxx> Acked-by: Xin Long <lucien.xin@xxxxxxxxx> Signed-off-by: David S. Miller <davem@xxxxxxxxxxxxx> Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx> --- net/sctp/socket.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 218e0982c3707..0932cbf568ee9 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -8280,6 +8280,22 @@ 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 */ @@ -9649,6 +9665,7 @@ 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, @@ -9704,6 +9721,7 @@ 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, -- 2.39.2