From de1c489b57c11fabc766aeb6777ed5b0038fa3bb Mon Sep 17 00:00:00 2001 From: Jori Koolstra Date: Thu, 13 Aug 2026 12:28:15 -0400 Subject: [PATCH 1/4] net: af_unix: enable custom setsockopt for all socket types unix_setsockopt() and the SOCK_CUSTOM_SOCKOPT flag were only wired up for SOCK_STREAM (introduced along with the stream-only SO_INQ). Consequently custom AF_UNIX options are unreachable on SOCK_DGRAM and SOCK_SEQPACKET: those setsockopt() calls bypass unix_setsockopt() and fall through to the generic sock_setsockopt(), failing with -ENOPROTOOPT. Set SOCK_CUSTOM_SOCKOPT for every AF_UNIX socket type in unix_create(), and also for accepted sockets in unix_accept() (reachable for stream and seqpacket). This is a prerequisite for making SO_RIGHTS_NOTRUNC settable on all AF_UNIX socket types. Signed-off-by: Jori Koolstra Reviewed-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20260813162818.149248-2-jkoolstra@xs4all.nl Signed-off-by: Jakub Kicinski --- net/unix/af_unix.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 10ed9421e43a..51cbf920130d 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -950,7 +950,7 @@ static int unix_setsockopt(struct socket *sock, int level, int optname, switch (optname) { case SO_INQ: if (sk->sk_type != SOCK_STREAM) - return -EINVAL; + return -ENOPROTOOPT; if (val > 1 || val < 0) return -EINVAL; @@ -1006,6 +1006,7 @@ static const struct proto_ops unix_dgram_ops = { #endif .listen = sock_no_listen, .shutdown = unix_shutdown, + .setsockopt = unix_setsockopt, .sendmsg = unix_dgram_sendmsg, .read_skb = unix_read_skb, .recvmsg = unix_dgram_recvmsg, @@ -1030,6 +1031,7 @@ static const struct proto_ops unix_seqpacket_ops = { #endif .listen = unix_listen, .shutdown = unix_shutdown, + .setsockopt = unix_setsockopt, .sendmsg = unix_seqpacket_sendmsg, .recvmsg = unix_seqpacket_recvmsg, .mmap = sock_no_mmap, @@ -1143,9 +1145,10 @@ static int unix_create(struct net *net, struct socket *sock, int protocol, if (protocol && protocol != PF_UNIX) return -EPROTONOSUPPORT; + set_bit(SOCK_CUSTOM_SOCKOPT, &sock->flags); + switch (sock->type) { case SOCK_STREAM: - set_bit(SOCK_CUSTOM_SOCKOPT, &sock->flags); sock->ops = &unix_stream_ops; break; /* @@ -1865,8 +1868,7 @@ static int unix_accept(struct socket *sock, struct socket *newsock, skb_free_datagram(sk, skb); wake_up_interruptible(&unix_sk(sk)->peer_wait); - if (tsk->sk_type == SOCK_STREAM) - set_bit(SOCK_CUSTOM_SOCKOPT, &newsock->flags); + set_bit(SOCK_CUSTOM_SOCKOPT, &newsock->flags); /* attach accepted sock to socket */ unix_state_lock(tsk); From 48b84acc5e18655f2a02fe2a043330d03f939ffe Mon Sep 17 00:00:00 2001 From: Jori Koolstra Date: Thu, 13 Aug 2026 12:28:16 -0400 Subject: [PATCH 2/4] net: scm: move scm_detach_fds() from common path to scm_recv_unix() scm->fp can only be set when using UNIX sockets, therefore we should move it out of the common path __scm_recv_common() into scm_recv_unix(). Reviewed-by: Kuniyuki Iwashima Signed-off-by: Jori Koolstra Link: https://patch.msgid.link/20260813162818.149248-3-jkoolstra@xs4all.nl Signed-off-by: Jakub Kicinski --- net/core/scm.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/core/scm.c b/net/core/scm.c index eec13f50ecaf..a73b1eb30fd2 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -523,9 +523,6 @@ static bool __scm_recv_common(struct sock *sk, struct msghdr *msg, scm_passec(sk, msg, scm); - if (scm->fp) - scm_detach_fds(msg, scm); - return true; } @@ -545,6 +542,9 @@ void scm_recv_unix(struct socket *sock, struct msghdr *msg, if (!__scm_recv_common(sock->sk, msg, scm, flags)) return; + if (scm->fp) + scm_detach_fds(msg, scm); + if (sock->sk->sk_scm_pidfd) scm_pidfd_recv(msg, scm); From fd8756fa1487577535d6294ae7cc67888b19ae2a Mon Sep 17 00:00:00 2001 From: Jori Koolstra Date: Thu, 13 Aug 2026 12:28:17 -0400 Subject: [PATCH 3/4] net: af_unix: useful handling of LSM denials on SCM_RIGHTS Right now if some LSM such as Smack denies an AF_UNIX socket peer to receive an SCM_RIGHTS fd, the SCM_RIGHTS fd array will be cut short at that point, and MSG_CTRUNC is set on return of recvmsg(). This is highly problematic behaviour, because it leaves the receiver wondering what happened. As per man page MSG_CTRUNC is supposed to indicate that the control buffer was sized too short, but suddenly a permission error might result in the exact same flag being set. Moreover, the receiver has no chance to determine how many fds got originally sent and how many were suppressed.[1] Add a SO_RIGHTS_NOTRUNC option to UNIX sockets to enable more useful handling of LSM denials when receiving SCM_RIGHTS messages: instead of truncating the message at the first blocked fd, keep every fd slot and store the LSM errno in the blocked slot. The socket option is inherited by the child accept() socket if set on the listen() socket. [1]: https://github.com/uapi-group/kernel-features#useful-handling-of-lsm-denials-on-scm_rights Reviewed-by: Christian Brauner (Amutable) Signed-off-by: Jori Koolstra Link: https://patch.msgid.link/20260813162818.149248-4-jkoolstra@xs4all.nl Signed-off-by: Jakub Kicinski --- arch/alpha/include/uapi/asm/socket.h | 2 ++ arch/mips/include/uapi/asm/socket.h | 2 ++ arch/parisc/include/uapi/asm/socket.h | 2 ++ arch/sparc/include/uapi/asm/socket.h | 2 ++ include/net/af_unix.h | 1 + include/net/scm.h | 13 +++------ include/uapi/asm-generic/socket.h | 2 ++ net/compat.c | 4 +-- net/core/scm.c | 38 +++++++++++++++++++++++---- net/unix/af_unix.c | 14 ++++++++-- 10 files changed, 62 insertions(+), 18 deletions(-) diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index 5ef57f88df6b..946a5fad2691 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -155,6 +155,8 @@ #define SO_INQ 84 #define SCM_INQ SO_INQ +#define SO_RIGHTS_NOTRUNC 85 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index 72fb1b006da9..f1641dde135f 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -166,6 +166,8 @@ #define SO_INQ 84 #define SCM_INQ SO_INQ +#define SO_RIGHTS_NOTRUNC 85 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index c16ec36dfee6..f3a3815c7dc2 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -147,6 +147,8 @@ #define SO_INQ 0x4052 #define SCM_INQ SO_INQ +#define SO_RIGHTS_NOTRUNC 0x4053 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index 71befa109e1c..7907f3b1f0ee 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -148,6 +148,8 @@ #define SO_INQ 0x005d #define SCM_INQ SO_INQ +#define SO_RIGHTS_NOTRUNC 0x005e + #if !defined(__KERNEL__) diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 34f53dde65ce..bb1b3dee02e8 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -49,6 +49,7 @@ struct unix_sock { struct scm_stat scm_stat; int inq_len; bool recvmsg_inq; + bool scm_rights_notrunc; #if IS_ENABLED(CONFIG_AF_UNIX_OOB) struct sk_buff *oob_skb; #endif diff --git a/include/net/scm.h b/include/net/scm.h index c52519669349..86ae6bc109ec 100644 --- a/include/net/scm.h +++ b/include/net/scm.h @@ -50,8 +50,8 @@ struct scm_cookie { #endif }; -void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm); -void scm_detach_fds_compat(struct msghdr *msg, struct scm_cookie *scm); +void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm, bool notrunc); +void scm_detach_fds_compat(struct msghdr *msg, struct scm_cookie *scm, bool notrunc); int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *scm); void __scm_destroy(struct scm_cookie *scm); struct scm_fp_list *scm_fp_dup(struct scm_fp_list *fpl); @@ -107,13 +107,8 @@ void scm_recv(struct socket *sock, struct msghdr *msg, void scm_recv_unix(struct socket *sock, struct msghdr *msg, struct scm_cookie *scm, int flags); -static inline int scm_recv_one_fd(struct file *f, int __user *ufd, - unsigned int flags) -{ - if (!ufd) - return -EFAULT; - return receive_fd(f, ufd, flags); -} +int scm_recv_one_fd(struct file *f, int __user *ufd, unsigned int flags, + bool notrunc); #endif /* __LINUX_NET_SCM_H */ diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index 53b5a8c002b1..84ea7b92936e 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -150,6 +150,8 @@ #define SO_INQ 84 #define SCM_INQ SO_INQ +#define SO_RIGHTS_NOTRUNC 85 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) diff --git a/net/compat.c b/net/compat.c index d68cf9c3aad5..6bdf4a2c9077 100644 --- a/net/compat.c +++ b/net/compat.c @@ -286,7 +286,7 @@ static int scm_max_fds_compat(struct msghdr *msg) return (msg->msg_controllen - sizeof(struct compat_cmsghdr)) / sizeof(int); } -void scm_detach_fds_compat(struct msghdr *msg, struct scm_cookie *scm) +void scm_detach_fds_compat(struct msghdr *msg, struct scm_cookie *scm, bool notrunc) { struct compat_cmsghdr __user *cm = (struct compat_cmsghdr __user *)msg->msg_control_user; @@ -296,7 +296,7 @@ void scm_detach_fds_compat(struct msghdr *msg, struct scm_cookie *scm) int err = 0, i; for (i = 0; i < fdmax; i++) { - err = scm_recv_one_fd(scm->fp->fp[i], cmsg_data + i, o_flags); + err = scm_recv_one_fd(scm->fp->fp[i], cmsg_data + i, o_flags, notrunc); if (err < 0) break; } diff --git a/net/core/scm.c b/net/core/scm.c index a73b1eb30fd2..f0d44ecdb11f 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -351,7 +351,31 @@ static int scm_max_fds(struct msghdr *msg) return (msg->msg_controllen - sizeof(struct cmsghdr)) / sizeof(int); } -void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm) +int scm_recv_one_fd(struct file *f, int __user *ufd, unsigned int flags, + bool notrunc) +{ + int error; + + if (!ufd) + return -EFAULT; + + error = security_file_receive(f); + if (error) + return notrunc ? put_user(error, ufd) : error; + + FD_PREPARE(fdf, flags, get_file(f)); + if (fdf.err) + return fdf.err; + + error = put_user(fd_prepare_fd(fdf), ufd); + if (error) + return error; + + __receive_sock(fd_prepare_file(fdf)); + return fd_publish(fdf); +} + +void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm, bool notrunc) { struct cmsghdr __user *cm = (__force struct cmsghdr __user *)msg->msg_control_user; @@ -365,12 +389,12 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm) return; if (msg->msg_flags & MSG_CMSG_COMPAT) { - scm_detach_fds_compat(msg, scm); + scm_detach_fds_compat(msg, scm, notrunc); return; } for (i = 0; i < fdmax; i++) { - err = scm_recv_one_fd(scm->fp->fp[i], cmsg_data + i, o_flags); + err = scm_recv_one_fd(scm->fp->fp[i], cmsg_data + i, o_flags, notrunc); if (err < 0) break; } @@ -542,8 +566,12 @@ void scm_recv_unix(struct socket *sock, struct msghdr *msg, if (!__scm_recv_common(sock->sk, msg, scm, flags)) return; - if (scm->fp) - scm_detach_fds(msg, scm); + if (scm->fp) { + struct unix_sock *u; + + u = unix_sk(sock->sk); + scm_detach_fds(msg, scm, READ_ONCE(u->scm_rights_notrunc)); + } if (sock->sk->sk_scm_pidfd) scm_pidfd_recv(msg, scm); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 51cbf920130d..5c0549e6784f 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -922,6 +922,7 @@ static bool unix_custom_sockopt(int optname) { switch (optname) { case SO_INQ: + case SO_RIGHTS_NOTRUNC: return true; default: return false; @@ -957,6 +958,14 @@ static int unix_setsockopt(struct socket *sock, int level, int optname, WRITE_ONCE(u->recvmsg_inq, val); break; + + case SO_RIGHTS_NOTRUNC: + if (val > 1 || val < 0) + return -EINVAL; + + WRITE_ONCE(u->scm_rights_notrunc, val); + break; + default: return -ENOPROTOOPT; } @@ -1746,9 +1755,10 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr_unsized *uad init_peercred(newsk, &peercred); newu = unix_sk(newsk); - newu->listener = other; - RCU_INIT_POINTER(newsk->sk_wq, &newu->peer_wq); otheru = unix_sk(other); + newu->listener = other; + newu->scm_rights_notrunc = READ_ONCE(otheru->scm_rights_notrunc); + RCU_INIT_POINTER(newsk->sk_wq, &newu->peer_wq); /* copy address information from listening to new sock * From 5d513ce19de963c7e36904c98d7b02ecd16a30a1 Mon Sep 17 00:00:00 2001 From: Jori Koolstra Date: Fri, 14 Aug 2026 13:28:06 -0400 Subject: [PATCH 4/4] selftest: Add tests for useful handling of LSM denials on SCM_RIGHTS Tests SCM_RIGHTS fd passing on a socket with the new socket option SO_RIGHTS_NOTRUNC turned on. To hook into the security_file_receive() call, BPF is used. The BPF program shares a hashmap with userspace that lists the inos to be blocked (of the receiver tgid). Signed-off-by: Jori Koolstra Link: https://patch.msgid.link/20260814172806.158954-1-jkoolstra@xs4all.nl Signed-off-by: Jakub Kicinski --- .../testing/selftests/net/af_unix/.gitignore | 2 + tools/testing/selftests/net/af_unix/Makefile | 8 + tools/testing/selftests/net/af_unix/config | 7 + .../net/af_unix/scm_rights_denial_lsm.bpf.c | 36 +++ .../net/af_unix/scm_rights_denial_lsm.c | 292 ++++++++++++++++++ 5 files changed, 345 insertions(+) create mode 100644 tools/testing/selftests/net/af_unix/scm_rights_denial_lsm.bpf.c create mode 100644 tools/testing/selftests/net/af_unix/scm_rights_denial_lsm.c diff --git a/tools/testing/selftests/net/af_unix/.gitignore b/tools/testing/selftests/net/af_unix/.gitignore index 973176644103..954f0958dd03 100644 --- a/tools/testing/selftests/net/af_unix/.gitignore +++ b/tools/testing/selftests/net/af_unix/.gitignore @@ -3,6 +3,8 @@ msg_oob scm_inq scm_pidfd scm_rights +scm_rights_denial_lsm +scm_rights_denial_lsm.bpf.o so_peek_off unix_connect unix_connreset diff --git a/tools/testing/selftests/net/af_unix/Makefile b/tools/testing/selftests/net/af_unix/Makefile index 57d159803a3a..a66f10fb0c23 100644 --- a/tools/testing/selftests/net/af_unix/Makefile +++ b/tools/testing/selftests/net/af_unix/Makefile @@ -11,10 +11,18 @@ TEST_GEN_PROGS := \ scm_inq \ scm_pidfd \ scm_rights \ + scm_rights_denial_lsm \ so_peek_off \ unix_connect \ unix_connreset \ unix_listen \ # end of TEST_GEN_PROGS +TEST_GEN_FILES := scm_rights_denial_lsm.bpf.o + include ../../lib.mk +include ../bpf.mk + +$(OUTPUT)/scm_rights_denial_lsm: $(BPFOBJ) +$(OUTPUT)/scm_rights_denial_lsm: CFLAGS += -I$(SCRATCH_DIR)/include +$(OUTPUT)/scm_rights_denial_lsm: LDLIBS += -lelf -lz diff --git a/tools/testing/selftests/net/af_unix/config b/tools/testing/selftests/net/af_unix/config index 41dbb03c747e..46450fea8407 100644 --- a/tools/testing/selftests/net/af_unix/config +++ b/tools/testing/selftests/net/af_unix/config @@ -1,4 +1,11 @@ CONFIG_AF_UNIX_OOB=y +CONFIG_BPF=y +CONFIG_BPF_EVENTS=y +CONFIG_BPF_JIT=y +CONFIG_BPF_LSM=y +CONFIG_BPF_SYSCALL=y +CONFIG_DEBUG_INFO_BTF=y +CONFIG_SECURITY=y CONFIG_UNIX=y CONFIG_UNIX_DIAG=m CONFIG_USER_NS=y diff --git a/tools/testing/selftests/net/af_unix/scm_rights_denial_lsm.bpf.c b/tools/testing/selftests/net/af_unix/scm_rights_denial_lsm.bpf.c new file mode 100644 index 000000000000..4f2414465bfd --- /dev/null +++ b/tools/testing/selftests/net/af_unix/scm_rights_denial_lsm.bpf.c @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include + +char _license[] SEC("license") = "GPL"; + +struct inode { + unsigned long i_ino; +} __attribute__((preserve_access_index)); + +struct file { + struct inode *f_inode; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 16); + __type(key, __u64); /* inode number */ + __type(value, __u32); /* tgid of the receiver being tested */ +} denied_inodes SEC(".maps"); + +SEC("lsm/file_receive") +int BPF_PROG(scm_rights_deny, struct file *file) +{ + __u32 tgid = bpf_get_current_pid_tgid() >> 32; + __u64 ino = file->f_inode->i_ino; + __u32 *owner; + + owner = bpf_map_lookup_elem(&denied_inodes, &ino); + if (owner && *owner == tgid) + return -EPERM; + + return 0; +} diff --git a/tools/testing/selftests/net/af_unix/scm_rights_denial_lsm.c b/tools/testing/selftests/net/af_unix/scm_rights_denial_lsm.c new file mode 100644 index 000000000000..55c7ecdbb5fe --- /dev/null +++ b/tools/testing/selftests/net/af_unix/scm_rights_denial_lsm.c @@ -0,0 +1,292 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#include "kselftest_harness.h" + +#ifndef SO_RIGHTS_NOTRUNC +#define SO_RIGHTS_NOTRUNC 85 +#endif + +#define NR_FILES 2 + +/* Per-file content, so a received fd can be matched to the file sent */ +#define SECRET(n) "secret %d", (n) + +/* Indices into the socketpair */ +#define SK_SENDER 0 +#define SK_RECEIVER 1 + +FIXTURE(scm_rights_denial_bpf) +{ + struct bpf_object *obj; + struct bpf_link *link; + int map_fd; + int sk[2]; + int files[NR_FILES]; + __u64 inos[NR_FILES]; + char paths[NR_FILES][64]; +}; + +FIXTURE_VARIANT(scm_rights_denial_bpf) +{ + int sock_type; +}; + +FIXTURE_VARIANT_ADD(scm_rights_denial_bpf, stream) +{ + .sock_type = SOCK_STREAM, +}; + +FIXTURE_VARIANT_ADD(scm_rights_denial_bpf, dgram) +{ + .sock_type = SOCK_DGRAM, +}; + +FIXTURE_VARIANT_ADD(scm_rights_denial_bpf, seqpacket) +{ + .sock_type = SOCK_SEQPACKET, +}; + +FIXTURE_SETUP(scm_rights_denial_bpf) +{ + struct bpf_program *prog; + char lsms[256] = {}; + int i, fd; + + if (geteuid() != 0) + SKIP(return, "requires root"); + + fd = open("/sys/kernel/security/lsm", O_RDONLY); + ASSERT_GE(fd, 0); + ASSERT_LT(0, read(fd, lsms, sizeof(lsms) - 1)); + close(fd); + + if (!strstr(lsms, "bpf")) + SKIP(return, "BPF LSM not active (boot with lsm=...,bpf)"); + + self->obj = bpf_object__open_file("scm_rights_denial_lsm.bpf.o", NULL); + ASSERT_NE(NULL, self->obj); + ASSERT_EQ(0, bpf_object__load(self->obj)); + + prog = bpf_object__find_program_by_name(self->obj, "scm_rights_deny"); + ASSERT_NE(NULL, prog); + + self->link = bpf_program__attach_lsm(prog); + ASSERT_NE(NULL, self->link); + + self->map_fd = bpf_object__find_map_fd_by_name(self->obj, + "denied_inodes"); + ASSERT_GE(self->map_fd, 0); + + ASSERT_EQ(0, socketpair(AF_UNIX, variant->sock_type, 0, self->sk)); + + for (i = 0; i < NR_FILES; i++) { + struct stat st; + + snprintf(self->paths[i], sizeof(self->paths[i]), + "/tmp/scm_rights_denial_bpf.%d.XXXXXX", i); + self->files[i] = mkstemp(self->paths[i]); + ASSERT_GE(self->files[i], 0); + + ASSERT_LT(0, dprintf(self->files[i], SECRET(i))); + + ASSERT_EQ(0, fstat(self->files[i], &st)); + self->inos[i] = st.st_ino; + } +} + +FIXTURE_TEARDOWN(scm_rights_denial_bpf) +{ + bpf_link__destroy(self->link); + bpf_object__close(self->obj); + + for (int i = 0; i < NR_FILES; i++) { + if (self->files[i] >= 0) { + close(self->files[i]); + unlink(self->paths[i]); + } + } + + close(self->sk[SK_SENDER]); + close(self->sk[SK_RECEIVER]); +} + +static int deny_inode(int map_fd, __u64 ino) +{ + __u32 tgid = getpid(); + + return bpf_map_update_elem(map_fd, &ino, &tgid, BPF_ANY); +} + +static int set_notrunc(int sk) +{ + int one = 1; + + return setsockopt(sk, SOL_SOCKET, SO_RIGHTS_NOTRUNC, + &one, sizeof(one)); +} + +static int send_fds(int sk, int *fds, int n) +{ + char ctrl[CMSG_SPACE(NR_FILES * sizeof(int))] = {}; + char data = 'x'; + struct iovec iov = { + .iov_base = &data, + .iov_len = sizeof(data), + }; + struct msghdr msg = { + .msg_iov = &iov, + .msg_iovlen = 1, + .msg_control = ctrl, + .msg_controllen = CMSG_SPACE(n * sizeof(int)), + }; + struct cmsghdr *cmsg = CMSG_FIRSTHDR(&msg); + int ret; + + cmsg->cmsg_level = SOL_SOCKET; + cmsg->cmsg_type = SCM_RIGHTS; + cmsg->cmsg_len = CMSG_LEN(n * sizeof(int)); + memcpy(CMSG_DATA(cmsg), fds, n * sizeof(int)); + + ret = sendmsg(sk, &msg, 0); + if (ret != 1) + return -1; + + return 0; +} + +static int recv_fd_slots(int sk, int *slots, int *msg_flags) +{ + int nr_slots; + char ctrl[CMSG_SPACE(NR_FILES * sizeof(int))]; + char data; + struct iovec iov = { + .iov_base = &data, + .iov_len = sizeof(data), + }; + struct msghdr msg = { + .msg_iov = &iov, + .msg_iovlen = 1, + .msg_control = ctrl, + .msg_controllen = sizeof(ctrl), + }; + struct cmsghdr *cmsg; + + if (recvmsg(sk, &msg, 0) < 0) + return -1; + + *msg_flags = msg.msg_flags; + + cmsg = CMSG_FIRSTHDR(&msg); + if (!cmsg) + return 0; + + nr_slots = (cmsg->cmsg_len - CMSG_LEN(0)) / sizeof(int); + memcpy(slots, CMSG_DATA(cmsg), nr_slots * sizeof(int)); + + return nr_slots; +} + +/* Prove a received fd works by reading back the file's content. */ +static int check_secret(int fd, int idx) +{ + char want[32], got[32] = {}; + + snprintf(want, sizeof(want), SECRET(idx)); + if (pread(fd, got, sizeof(got) - 1, 0) < 0) + return -1; + + return strcmp(want, got); +} + +TEST_F(scm_rights_denial_bpf, all_allowed) +{ + int slots[NR_FILES], nr_slots, flags; + + ASSERT_EQ(0, set_notrunc(self->sk[SK_RECEIVER])); + ASSERT_EQ(0, send_fds(self->sk[SK_SENDER], self->files, NR_FILES)); + nr_slots = recv_fd_slots(self->sk[SK_RECEIVER], slots, &flags); + + ASSERT_EQ(NR_FILES, nr_slots); + EXPECT_EQ(0, flags & MSG_CTRUNC); + + for (int i = 0; i < nr_slots; i++) { + ASSERT_GE(slots[i], 0); + EXPECT_EQ(0, check_secret(slots[i], i)); + close(slots[i]); + } +} + +TEST_F(scm_rights_denial_bpf, first_denied) +{ + int slots[NR_FILES], nr_slots, flags; + + ASSERT_EQ(0, deny_inode(self->map_fd, self->inos[0])); + + ASSERT_EQ(0, set_notrunc(self->sk[SK_RECEIVER])); + ASSERT_EQ(0, send_fds(self->sk[SK_SENDER], self->files, NR_FILES)); + nr_slots = recv_fd_slots(self->sk[SK_RECEIVER], slots, &flags); + + ASSERT_EQ(NR_FILES, nr_slots); + EXPECT_EQ(0, flags & MSG_CTRUNC); + + EXPECT_EQ(-EPERM, slots[0]); + for (int i = 1; i < nr_slots; i++) { + ASSERT_GE(slots[i], 0); + EXPECT_EQ(0, check_secret(slots[i], i)); + close(slots[i]); + } +} + +TEST_F(scm_rights_denial_bpf, all_denied) +{ + int slots[NR_FILES], nr_slots, flags, i; + + for (i = 0; i < NR_FILES; i++) + ASSERT_EQ(0, deny_inode(self->map_fd, self->inos[i])); + + ASSERT_EQ(0, set_notrunc(self->sk[SK_RECEIVER])); + ASSERT_EQ(0, send_fds(self->sk[SK_SENDER], self->files, NR_FILES)); + nr_slots = recv_fd_slots(self->sk[SK_RECEIVER], slots, &flags); + + ASSERT_EQ(NR_FILES, nr_slots); + EXPECT_EQ(0, flags & MSG_CTRUNC); + + for (i = 0; i < nr_slots; i++) + EXPECT_EQ(-EPERM, slots[i]); +} + +TEST_F(scm_rights_denial_bpf, denied_without_notrunc) +{ + int slots[NR_FILES], nr_slots, flags; + + /* + * Baseline behaviour without SO_RIGHTS_NOTRUNC: the fd array is + * truncated at the first denied fd and MSG_CTRUNC is set. + */ + ASSERT_EQ(0, deny_inode(self->map_fd, self->inos[1])); + + ASSERT_EQ(0, send_fds(self->sk[SK_SENDER], self->files, NR_FILES)); + nr_slots = recv_fd_slots(self->sk[SK_RECEIVER], slots, &flags); + + ASSERT_EQ(1, nr_slots); + EXPECT_NE(0, flags & MSG_CTRUNC); + + ASSERT_GE(slots[0], 0); + EXPECT_EQ(0, check_secret(slots[0], 0)); + close(slots[0]); +} + +TEST_HARNESS_MAIN