From 688b7270b3cb75e8ac78123d719967db40336e5b Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 30 Nov 2023 10:52:16 -0800 Subject: bpf: add BPF token support to BPF_MAP_CREATE command Allow providing token_fd for BPF_MAP_CREATE command to allow controlled BPF map creation from unprivileged process through delegated BPF token. Wire through a set of allowed BPF map types to BPF token, derived from BPF FS at BPF token creation time. This, in combination with allowed_cmds allows to create a narrowly-focused BPF token (controlled by privileged agent) with a restrictive set of BPF maps that application can attempt to create. Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20231130185229.2688956-5-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/prog_tests/libbpf_probes.c | 2 ++ tools/testing/selftests/bpf/prog_tests/libbpf_str.c | 3 +++ 2 files changed, 5 insertions(+) (limited to 'tools/testing') diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c index 9f766ddd946a..573249a2814d 100644 --- a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c +++ b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c @@ -68,6 +68,8 @@ void test_libbpf_probe_map_types(void) if (map_type == BPF_MAP_TYPE_UNSPEC) continue; + if (strcmp(map_type_name, "__MAX_BPF_MAP_TYPE") == 0) + continue; if (!test__start_subtest(map_type_name)) continue; diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c index c440ea3311ed..2a0633f43c73 100644 --- a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c +++ b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c @@ -132,6 +132,9 @@ static void test_libbpf_bpf_map_type_str(void) const char *map_type_str; char buf[256]; + if (map_type == __MAX_BPF_MAP_TYPE) + continue; + map_type_name = btf__str_by_offset(btf, e->name_off); map_type_str = libbpf_bpf_map_type_str(map_type); ASSERT_OK_PTR(map_type_str, map_type_name); -- cgit v1.2.3 From e1cef620f598853a90f17701fcb1057a6768f7b8 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 30 Nov 2023 10:52:18 -0800 Subject: bpf: add BPF token support to BPF_PROG_LOAD command Add basic support of BPF token to BPF_PROG_LOAD. Wire through a set of allowed BPF program types and attach types, derived from BPF FS at BPF token creation time. Then make sure we perform bpf_token_capable() checks everywhere where it's relevant. Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20231130185229.2688956-7-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 6 ++ include/uapi/linux/bpf.h | 2 + kernel/bpf/core.c | 1 + kernel/bpf/inode.c | 6 +- kernel/bpf/syscall.c | 87 ++++++++++++++++------ kernel/bpf/token.c | 27 +++++++ tools/include/uapi/linux/bpf.h | 2 + .../selftests/bpf/prog_tests/libbpf_probes.c | 2 + .../testing/selftests/bpf/prog_tests/libbpf_str.c | 3 + 9 files changed, 110 insertions(+), 26 deletions(-) (limited to 'tools/testing') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e08e8436df38..20af87b59d70 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1461,6 +1461,7 @@ struct bpf_prog_aux { #ifdef CONFIG_SECURITY void *security; #endif + struct bpf_token *token; struct bpf_prog_offload *offload; struct btf *btf; struct bpf_func_info *func_info; @@ -1601,6 +1602,8 @@ struct bpf_token { struct user_namespace *userns; u64 allowed_cmds; u64 allowed_maps; + u64 allowed_progs; + u64 allowed_attachs; }; struct bpf_struct_ops_value; @@ -2238,6 +2241,9 @@ struct bpf_token *bpf_token_get_from_fd(u32 ufd); bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd); bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type); +bool bpf_token_allow_prog_type(const struct bpf_token *token, + enum bpf_prog_type prog_type, + enum bpf_attach_type attach_type); int bpf_obj_pin_user(u32 ufd, int path_fd, const char __user *pathname); int bpf_obj_get_user(int path_fd, const char __user *pathname, int flags); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 9f9989e0d062..4df2d025c784 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1028,6 +1028,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_SK_LOOKUP, BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */ BPF_PROG_TYPE_NETFILTER, + __MAX_BPF_PROG_TYPE }; enum bpf_attach_type { @@ -1504,6 +1505,7 @@ union bpf_attr { * truncated), or smaller (if log buffer wasn't filled completely). */ __u32 log_true_size; + __u32 prog_token_fd; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 4b813da8d6c0..47085839af8d 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2751,6 +2751,7 @@ void bpf_prog_free(struct bpf_prog *fp) if (aux->dst_prog) bpf_prog_put(aux->dst_prog); + bpf_token_put(aux->token); INIT_WORK(&aux->work, bpf_prog_free_deferred); schedule_work(&aux->work); } diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 9c7865d1c53d..5359a0929c35 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -619,12 +619,14 @@ static int bpf_show_options(struct seq_file *m, struct dentry *root) else if (opts->delegate_maps) seq_printf(m, ",delegate_maps=0x%llx", opts->delegate_maps); - if (opts->delegate_progs == ~0ULL) + mask = (1ULL << __MAX_BPF_PROG_TYPE) - 1; + if ((opts->delegate_progs & mask) == mask) seq_printf(m, ",delegate_progs=any"); else if (opts->delegate_progs) seq_printf(m, ",delegate_progs=0x%llx", opts->delegate_progs); - if (opts->delegate_attachs == ~0ULL) + mask = (1ULL << __MAX_BPF_ATTACH_TYPE) - 1; + if ((opts->delegate_attachs & mask) == mask) seq_printf(m, ",delegate_attachs=any"); else if (opts->delegate_attachs) seq_printf(m, ",delegate_attachs=0x%llx", opts->delegate_attachs); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index d87c5c27cde3..2c8393c21b8c 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2608,13 +2608,15 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type) } /* last field in 'union bpf_attr' used by this command */ -#define BPF_PROG_LOAD_LAST_FIELD log_true_size +#define BPF_PROG_LOAD_LAST_FIELD prog_token_fd static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) { enum bpf_prog_type type = attr->prog_type; struct bpf_prog *prog, *dst_prog = NULL; struct btf *attach_btf = NULL; + struct bpf_token *token = NULL; + bool bpf_cap; int err; char license[128]; @@ -2631,10 +2633,31 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) BPF_F_TEST_REG_INVARIANTS)) return -EINVAL; + bpf_prog_load_fixup_attach_type(attr); + + if (attr->prog_token_fd) { + token = bpf_token_get_from_fd(attr->prog_token_fd); + if (IS_ERR(token)) + return PTR_ERR(token); + /* if current token doesn't grant prog loading permissions, + * then we can't use this token, so ignore it and rely on + * system-wide capabilities checks + */ + if (!bpf_token_allow_cmd(token, BPF_PROG_LOAD) || + !bpf_token_allow_prog_type(token, attr->prog_type, + attr->expected_attach_type)) { + bpf_token_put(token); + token = NULL; + } + } + + bpf_cap = bpf_token_capable(token, CAP_BPF); + err = -EPERM; + if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && (attr->prog_flags & BPF_F_ANY_ALIGNMENT) && - !bpf_capable()) - return -EPERM; + !bpf_cap) + goto put_token; /* Intent here is for unprivileged_bpf_disabled to block BPF program * creation for unprivileged users; other actions depend @@ -2643,21 +2666,23 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) * capability checks are still carried out for these * and other operations. */ - if (sysctl_unprivileged_bpf_disabled && !bpf_capable()) - return -EPERM; + if (sysctl_unprivileged_bpf_disabled && !bpf_cap) + goto put_token; if (attr->insn_cnt == 0 || - attr->insn_cnt > (bpf_capable() ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS)) - return -E2BIG; + attr->insn_cnt > (bpf_cap ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS)) { + err = -E2BIG; + goto put_token; + } if (type != BPF_PROG_TYPE_SOCKET_FILTER && type != BPF_PROG_TYPE_CGROUP_SKB && - !bpf_capable()) - return -EPERM; + !bpf_cap) + goto put_token; - if (is_net_admin_prog_type(type) && !bpf_net_capable()) - return -EPERM; - if (is_perfmon_prog_type(type) && !perfmon_capable()) - return -EPERM; + if (is_net_admin_prog_type(type) && !bpf_token_capable(token, CAP_NET_ADMIN)) + goto put_token; + if (is_perfmon_prog_type(type) && !bpf_token_capable(token, CAP_PERFMON)) + goto put_token; /* attach_prog_fd/attach_btf_obj_fd can specify fd of either bpf_prog * or btf, we need to check which one it is @@ -2667,27 +2692,33 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) if (IS_ERR(dst_prog)) { dst_prog = NULL; attach_btf = btf_get_by_fd(attr->attach_btf_obj_fd); - if (IS_ERR(attach_btf)) - return -EINVAL; + if (IS_ERR(attach_btf)) { + err = -EINVAL; + goto put_token; + } if (!btf_is_kernel(attach_btf)) { /* attaching through specifying bpf_prog's BTF * objects directly might be supported eventually */ btf_put(attach_btf); - return -ENOTSUPP; + err = -ENOTSUPP; + goto put_token; } } } else if (attr->attach_btf_id) { /* fall back to vmlinux BTF, if BTF type ID is specified */ attach_btf = bpf_get_btf_vmlinux(); - if (IS_ERR(attach_btf)) - return PTR_ERR(attach_btf); - if (!attach_btf) - return -EINVAL; + if (IS_ERR(attach_btf)) { + err = PTR_ERR(attach_btf); + goto put_token; + } + if (!attach_btf) { + err = -EINVAL; + goto put_token; + } btf_get(attach_btf); } - bpf_prog_load_fixup_attach_type(attr); if (bpf_prog_load_check_attach(type, attr->expected_attach_type, attach_btf, attr->attach_btf_id, dst_prog)) { @@ -2695,7 +2726,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) bpf_prog_put(dst_prog); if (attach_btf) btf_put(attach_btf); - return -EINVAL; + err = -EINVAL; + goto put_token; } /* plain bpf_prog allocation */ @@ -2705,7 +2737,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) bpf_prog_put(dst_prog); if (attach_btf) btf_put(attach_btf); - return -ENOMEM; + err = -EINVAL; + goto put_token; } prog->expected_attach_type = attr->expected_attach_type; @@ -2716,6 +2749,10 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE; prog->aux->xdp_has_frags = attr->prog_flags & BPF_F_XDP_HAS_FRAGS; + /* move token into prog->aux, reuse taken refcnt */ + prog->aux->token = token; + token = NULL; + err = security_bpf_prog_alloc(prog->aux); if (err) goto free_prog; @@ -2817,6 +2854,8 @@ free_prog: if (prog->aux->attach_btf) btf_put(prog->aux->attach_btf); bpf_prog_free(prog); +put_token: + bpf_token_put(token); return err; } @@ -3806,7 +3845,7 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, case BPF_PROG_TYPE_SK_LOOKUP: return attach_type == prog->expected_attach_type ? 0 : -EINVAL; case BPF_PROG_TYPE_CGROUP_SKB: - if (!bpf_net_capable()) + if (!bpf_token_capable(prog->aux->token, CAP_NET_ADMIN)) /* cg-skb progs can be loaded by unpriv user. * check permissions at attach time. */ diff --git a/kernel/bpf/token.c b/kernel/bpf/token.c index 06c34dae658e..5a51e6b8f6bf 100644 --- a/kernel/bpf/token.c +++ b/kernel/bpf/token.c @@ -79,6 +79,20 @@ static void bpf_token_show_fdinfo(struct seq_file *m, struct file *filp) seq_printf(m, "allowed_maps:\tany\n"); else seq_printf(m, "allowed_maps:\t0x%llx\n", token->allowed_maps); + + BUILD_BUG_ON(__MAX_BPF_PROG_TYPE >= 64); + mask = (1ULL << __MAX_BPF_PROG_TYPE) - 1; + if ((token->allowed_progs & mask) == mask) + seq_printf(m, "allowed_progs:\tany\n"); + else + seq_printf(m, "allowed_progs:\t0x%llx\n", token->allowed_progs); + + BUILD_BUG_ON(__MAX_BPF_ATTACH_TYPE >= 64); + mask = (1ULL << __MAX_BPF_ATTACH_TYPE) - 1; + if ((token->allowed_attachs & mask) == mask) + seq_printf(m, "allowed_attachs:\tany\n"); + else + seq_printf(m, "allowed_attachs:\t0x%llx\n", token->allowed_attachs); } #define BPF_TOKEN_INODE_NAME "bpf-token" @@ -169,6 +183,8 @@ int bpf_token_create(union bpf_attr *attr) mnt_opts = path.dentry->d_sb->s_fs_info; token->allowed_cmds = mnt_opts->delegate_cmds; token->allowed_maps = mnt_opts->delegate_maps; + token->allowed_progs = mnt_opts->delegate_progs; + token->allowed_attachs = mnt_opts->delegate_attachs; fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) { @@ -228,3 +244,14 @@ bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type t return token->allowed_maps & (1ULL << type); } + +bool bpf_token_allow_prog_type(const struct bpf_token *token, + enum bpf_prog_type prog_type, + enum bpf_attach_type attach_type) +{ + if (!token || prog_type >= __MAX_BPF_PROG_TYPE || attach_type >= __MAX_BPF_ATTACH_TYPE) + return false; + + return (token->allowed_progs & (1ULL << prog_type)) && + (token->allowed_attachs & (1ULL << attach_type)); +} diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 9f9989e0d062..4df2d025c784 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1028,6 +1028,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_SK_LOOKUP, BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */ BPF_PROG_TYPE_NETFILTER, + __MAX_BPF_PROG_TYPE }; enum bpf_attach_type { @@ -1504,6 +1505,7 @@ union bpf_attr { * truncated), or smaller (if log buffer wasn't filled completely). */ __u32 log_true_size; + __u32 prog_token_fd; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c index 573249a2814d..4ed46ed58a7b 100644 --- a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c +++ b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c @@ -30,6 +30,8 @@ void test_libbpf_probe_prog_types(void) if (prog_type == BPF_PROG_TYPE_UNSPEC) continue; + if (strcmp(prog_type_name, "__MAX_BPF_PROG_TYPE") == 0) + continue; if (!test__start_subtest(prog_type_name)) continue; diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c index 2a0633f43c73..384bc1f7a65e 100644 --- a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c +++ b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c @@ -189,6 +189,9 @@ static void test_libbpf_bpf_prog_type_str(void) const char *prog_type_str; char buf[256]; + if (prog_type == __MAX_BPF_PROG_TYPE) + continue; + prog_type_name = btf__str_by_offset(btf, e->name_off); prog_type_str = libbpf_bpf_prog_type_str(prog_type); ASSERT_OK_PTR(prog_type_str, prog_type_name); -- cgit v1.2.3 From dc5196fac40c2cb96330bcb98eef868a7fd225b3 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 30 Nov 2023 10:52:28 -0800 Subject: selftests/bpf: add BPF token-enabled tests Add a selftest that attempts to conceptually replicate intended BPF token use cases inside user namespaced container. Child process is forked. It is then put into its own userns and mountns. Child creates BPF FS context object. This ensures child userns is captured as the owning userns for this instance of BPF FS. Given setting delegation mount options is privileged operation, we ensure that child cannot set them. This context is passed back to privileged parent process through Unix socket, where parent sets up delegation options, creates, and mounts it as a detached mount. This mount FD is passed back to the child to be used for BPF token creation, which allows otherwise privileged BPF operations to succeed inside userns. We validate that all of token-enabled privileged commands (BPF_BTF_LOAD, BPF_MAP_CREATE, and BPF_PROG_LOAD) work as intended. They should only succeed inside the userns if a) BPF token is provided with proper allowed sets of commands and types; and b) namespaces CAP_BPF and other privileges are set. Lacking a) or b) should lead to -EPERM failures. Based on suggested workflow by Christian Brauner ([0]). [0] https://lore.kernel.org/bpf/20230704-hochverdient-lehne-eeb9eeef785e@brauner/ Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20231130185229.2688956-17-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/prog_tests/token.c | 672 +++++++++++++++++++++++++ 1 file changed, 672 insertions(+) create mode 100644 tools/testing/selftests/bpf/prog_tests/token.c (limited to 'tools/testing') diff --git a/tools/testing/selftests/bpf/prog_tests/token.c b/tools/testing/selftests/bpf/prog_tests/token.c new file mode 100644 index 000000000000..dc03790c6272 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/token.c @@ -0,0 +1,672 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ +#define _GNU_SOURCE +#include +#include +#include "cap_helpers.h" +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static inline int sys_mount(const char *dev_name, const char *dir_name, + const char *type, unsigned long flags, + const void *data) +{ + return syscall(__NR_mount, dev_name, dir_name, type, flags, data); +} + +static inline int sys_fsopen(const char *fsname, unsigned flags) +{ + return syscall(__NR_fsopen, fsname, flags); +} + +static inline int sys_fspick(int dfd, const char *path, unsigned flags) +{ + return syscall(__NR_fspick, dfd, path, flags); +} + +static inline int sys_fsconfig(int fs_fd, unsigned cmd, const char *key, const void *val, int aux) +{ + return syscall(__NR_fsconfig, fs_fd, cmd, key, val, aux); +} + +static inline int sys_fsmount(int fs_fd, unsigned flags, unsigned ms_flags) +{ + return syscall(__NR_fsmount, fs_fd, flags, ms_flags); +} + +static int drop_priv_caps(__u64 *old_caps) +{ + return cap_disable_effective((1ULL << CAP_BPF) | + (1ULL << CAP_PERFMON) | + (1ULL << CAP_NET_ADMIN) | + (1ULL << CAP_SYS_ADMIN), old_caps); +} + +static int restore_priv_caps(__u64 old_caps) +{ + return cap_enable_effective(old_caps, NULL); +} + +static int set_delegate_mask(int fs_fd, const char *key, __u64 mask) +{ + char buf[32]; + int err; + + snprintf(buf, sizeof(buf), "0x%llx", (unsigned long long)mask); + err = sys_fsconfig(fs_fd, FSCONFIG_SET_STRING, key, + mask == ~0ULL ? "any" : buf, 0); + if (err < 0) + err = -errno; + return err; +} + +#define zclose(fd) do { if (fd >= 0) close(fd); fd = -1; } while (0) + +struct bpffs_opts { + __u64 cmds; + __u64 maps; + __u64 progs; + __u64 attachs; +}; + +static int create_bpffs_fd(void) +{ + int fs_fd; + + /* create VFS context */ + fs_fd = sys_fsopen("bpf", 0); + ASSERT_GE(fs_fd, 0, "fs_fd"); + + return fs_fd; +} + +static int materialize_bpffs_fd(int fs_fd, struct bpffs_opts *opts) +{ + int mnt_fd, err; + + /* set up token delegation mount options */ + err = set_delegate_mask(fs_fd, "delegate_cmds", opts->cmds); + if (!ASSERT_OK(err, "fs_cfg_cmds")) + return err; + err = set_delegate_mask(fs_fd, "delegate_maps", opts->maps); + if (!ASSERT_OK(err, "fs_cfg_maps")) + return err; + err = set_delegate_mask(fs_fd, "delegate_progs", opts->progs); + if (!ASSERT_OK(err, "fs_cfg_progs")) + return err; + err = set_delegate_mask(fs_fd, "delegate_attachs", opts->attachs); + if (!ASSERT_OK(err, "fs_cfg_attachs")) + return err; + + /* instantiate FS object */ + err = sys_fsconfig(fs_fd, FSCONFIG_CMD_CREATE, NULL, NULL, 0); + if (err < 0) + return -errno; + + /* create O_PATH fd for detached mount */ + mnt_fd = sys_fsmount(fs_fd, 0, 0); + if (err < 0) + return -errno; + + return mnt_fd; +} + +/* send FD over Unix domain (AF_UNIX) socket */ +static int sendfd(int sockfd, int fd) +{ + struct msghdr msg = {}; + struct cmsghdr *cmsg; + int fds[1] = { fd }, err; + char iobuf[1]; + struct iovec io = { + .iov_base = iobuf, + .iov_len = sizeof(iobuf), + }; + union { + char buf[CMSG_SPACE(sizeof(fds))]; + struct cmsghdr align; + } u; + + msg.msg_iov = &io; + msg.msg_iovlen = 1; + msg.msg_control = u.buf; + msg.msg_controllen = sizeof(u.buf); + cmsg = CMSG_FIRSTHDR(&msg); + cmsg->cmsg_level = SOL_SOCKET; + cmsg->cmsg_type = SCM_RIGHTS; + cmsg->cmsg_len = CMSG_LEN(sizeof(fds)); + memcpy(CMSG_DATA(cmsg), fds, sizeof(fds)); + + err = sendmsg(sockfd, &msg, 0); + if (err < 0) + err = -errno; + if (!ASSERT_EQ(err, 1, "sendmsg")) + return -EINVAL; + + return 0; +} + +/* receive FD over Unix domain (AF_UNIX) socket */ +static int recvfd(int sockfd, int *fd) +{ + struct msghdr msg = {}; + struct cmsghdr *cmsg; + int fds[1], err; + char iobuf[1]; + struct iovec io = { + .iov_base = iobuf, + .iov_len = sizeof(iobuf), + }; + union { + char buf[CMSG_SPACE(sizeof(fds))]; + struct cmsghdr align; + } u; + + msg.msg_iov = &io; + msg.msg_iovlen = 1; + msg.msg_control = u.buf; + msg.msg_controllen = sizeof(u.buf); + + err = recvmsg(sockfd, &msg, 0); + if (err < 0) + err = -errno; + if (!ASSERT_EQ(err, 1, "recvmsg")) + return -EINVAL; + + cmsg = CMSG_FIRSTHDR(&msg); + if (!ASSERT_OK_PTR(cmsg, "cmsg_null") || + !ASSERT_EQ(cmsg->cmsg_len, CMSG_LEN(sizeof(fds)), "cmsg_len") || + !ASSERT_EQ(cmsg->cmsg_level, SOL_SOCKET, "cmsg_level") || + !ASSERT_EQ(cmsg->cmsg_type, SCM_RIGHTS, "cmsg_type")) + return -EINVAL; + + memcpy(fds, CMSG_DATA(cmsg), sizeof(fds)); + *fd = fds[0]; + + return 0; +} + +static ssize_t write_nointr(int fd, const void *buf, size_t count) +{ + ssize_t ret; + + do { + ret = write(fd, buf, count); + } while (ret < 0 && errno == EINTR); + + return ret; +} + +static int write_file(const char *path, const void *buf, size_t count) +{ + int fd; + ssize_t ret; + + fd = open(path, O_WRONLY | O_CLOEXEC | O_NOCTTY | O_NOFOLLOW); + if (fd < 0) + return -1; + + ret = write_nointr(fd, buf, count); + close(fd); + if (ret < 0 || (size_t)ret != count) + return -1; + + return 0; +} + +static int create_and_enter_userns(void) +{ + uid_t uid; + gid_t gid; + char map[100]; + + uid = getuid(); + gid = getgid(); + + if (unshare(CLONE_NEWUSER)) + return -1; + + if (write_file("/proc/self/setgroups", "deny", sizeof("deny") - 1) && + errno != ENOENT) + return -1; + + snprintf(map, sizeof(map), "0 %d 1", uid); + if (write_file("/proc/self/uid_map", map, strlen(map))) + return -1; + + + snprintf(map, sizeof(map), "0 %d 1", gid); + if (write_file("/proc/self/gid_map", map, strlen(map))) + return -1; + + if (setgid(0)) + return -1; + + if (setuid(0)) + return -1; + + return 0; +} + +typedef int (*child_callback_fn)(int); + +static void child(int sock_fd, struct bpffs_opts *opts, child_callback_fn callback) +{ + LIBBPF_OPTS(bpf_map_create_opts, map_opts); + int mnt_fd = -1, fs_fd = -1, err = 0, bpffs_fd = -1; + + /* setup userns with root mappings */ + err = create_and_enter_userns(); + if (!ASSERT_OK(err, "create_and_enter_userns")) + goto cleanup; + + /* setup mountns to allow creating BPF FS (fsopen("bpf")) from unpriv process */ + err = unshare(CLONE_NEWNS); + if (!ASSERT_OK(err, "create_mountns")) + goto cleanup; + + err = sys_mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, 0); + if (!ASSERT_OK(err, "remount_root")) + goto cleanup; + + fs_fd = create_bpffs_fd(); + if (!ASSERT_GE(fs_fd, 0, "create_bpffs_fd")) { + err = -EINVAL; + goto cleanup; + } + + /* ensure unprivileged child cannot set delegation options */ + err = set_delegate_mask(fs_fd, "delegate_cmds", 0x1); + ASSERT_EQ(err, -EPERM, "delegate_cmd_eperm"); + err = set_delegate_mask(fs_fd, "delegate_maps", 0x1); + ASSERT_EQ(err, -EPERM, "delegate_maps_eperm"); + err = set_delegate_mask(fs_fd, "delegate_progs", 0x1); + ASSERT_EQ(err, -EPERM, "delegate_progs_eperm"); + err = set_delegate_mask(fs_fd, "delegate_attachs", 0x1); + ASSERT_EQ(err, -EPERM, "delegate_attachs_eperm"); + + /* pass BPF FS context object to parent */ + err = sendfd(sock_fd, fs_fd); + if (!ASSERT_OK(err, "send_fs_fd")) + goto cleanup; + zclose(fs_fd); + + /* avoid mucking around with mount namespaces and mounting at + * well-known path, just get detach-mounted BPF FS fd back from parent + */ + err = recvfd(sock_fd, &mnt_fd); + if (!ASSERT_OK(err, "recv_mnt_fd")) + goto cleanup; + + /* try to fspick() BPF FS and try to add some delegation options */ + fs_fd = sys_fspick(mnt_fd, "", FSPICK_EMPTY_PATH); + if (!ASSERT_GE(fs_fd, 0, "bpffs_fspick")) { + err = -EINVAL; + goto cleanup; + } + + /* ensure unprivileged child cannot reconfigure to set delegation options */ + err = set_delegate_mask(fs_fd, "delegate_cmds", ~0ULL); + if (!ASSERT_EQ(err, -EPERM, "delegate_cmd_eperm_reconfig")) { + err = -EINVAL; + goto cleanup; + } + err = set_delegate_mask(fs_fd, "delegate_maps", ~0ULL); + if (!ASSERT_EQ(err, -EPERM, "delegate_maps_eperm_reconfig")) { + err = -EINVAL; + goto cleanup; + } + err = set_delegate_mask(fs_fd, "delegate_progs", ~0ULL); + if (!ASSERT_EQ(err, -EPERM, "delegate_progs_eperm_reconfig")) { + err = -EINVAL; + goto cleanup; + } + err = set_delegate_mask(fs_fd, "delegate_attachs", ~0ULL); + if (!ASSERT_EQ(err, -EPERM, "delegate_attachs_eperm_reconfig")) { + err = -EINVAL; + goto cleanup; + } + zclose(fs_fd); + + bpffs_fd = openat(mnt_fd, ".", 0, O_RDWR); + if (!ASSERT_GE(bpffs_fd, 0, "bpffs_open")) { + err = -EINVAL; + goto cleanup; + } + + /* do custom test logic with customly set up BPF FS instance */ + err = callback(bpffs_fd); + if (!ASSERT_OK(err, "test_callback")) + goto cleanup; + + err = 0; +cleanup: + zclose(sock_fd); + zclose(mnt_fd); + zclose(fs_fd); + zclose(bpffs_fd); + + exit(-err); +} + +static int wait_for_pid(pid_t pid) +{ + int status, ret; + +again: + ret = waitpid(pid, &status, 0); + if (ret == -1) { + if (errno == EINTR) + goto again; + + return -1; + } + + if (!WIFEXITED(status)) + return -1; + + return WEXITSTATUS(status); +} + +static void parent(int child_pid, struct bpffs_opts *bpffs_opts, int sock_fd) +{ + int fs_fd = -1, mnt_fd = -1, err; + + err = recvfd(sock_fd, &fs_fd); + if (!ASSERT_OK(err, "recv_bpffs_fd")) + goto cleanup; + + mnt_fd = materialize_bpffs_fd(fs_fd, bpffs_opts); + if (!ASSERT_GE(mnt_fd, 0, "materialize_bpffs_fd")) { + err = -EINVAL; + goto cleanup; + } + zclose(fs_fd); + + /* pass BPF FS context object to parent */ + err = sendfd(sock_fd, mnt_fd); + if (!ASSERT_OK(err, "send_mnt_fd")) + goto cleanup; + zclose(mnt_fd); + + err = wait_for_pid(child_pid); + ASSERT_OK(err, "waitpid_child"); + +cleanup: + zclose(sock_fd); + zclose(fs_fd); + zclose(mnt_fd); + + if (child_pid > 0) + (void)kill(child_pid, SIGKILL); +} + +static void subtest_userns(struct bpffs_opts *bpffs_opts, child_callback_fn cb) +{ + int sock_fds[2] = { -1, -1 }; + int child_pid = 0, err; + + err = socketpair(AF_UNIX, SOCK_STREAM, 0, sock_fds); + if (!ASSERT_OK(err, "socketpair")) + goto cleanup; + + child_pid = fork(); + if (!ASSERT_GE(child_pid, 0, "fork")) + goto cleanup; + + if (child_pid == 0) { + zclose(sock_fds[0]); + return child(sock_fds[1], bpffs_opts, cb); + + } else { + zclose(sock_fds[1]); + return parent(child_pid, bpffs_opts, sock_fds[0]); + } + +cleanup: + zclose(sock_fds[0]); + zclose(sock_fds[1]); + if (child_pid > 0) + (void)kill(child_pid, SIGKILL); +} + +static int userns_map_create(int mnt_fd) +{ + LIBBPF_OPTS(bpf_map_create_opts, map_opts); + int err, token_fd = -1, map_fd = -1; + __u64 old_caps = 0; + + /* create BPF token from BPF FS mount */ + token_fd = bpf_token_create(mnt_fd, NULL); + if (!ASSERT_GT(token_fd, 0, "token_create")) { + err = -EINVAL; + goto cleanup; + } + + /* while inside non-init userns, we need both a BPF token *and* + * CAP_BPF inside current userns to create privileged map; let's test + * that neither BPF token alone nor namespaced CAP_BPF is sufficient + */ + err = drop_priv_caps(&old_caps); + if (!ASSERT_OK(err, "drop_caps")) + goto cleanup; + + /* no token, no CAP_BPF -> fail */ + map_opts.token_fd = 0; + map_fd = bpf_map_create(BPF_MAP_TYPE_STACK, "wo_token_wo_bpf", 0, 8, 1, &map_opts); + if (!ASSERT_LT(map_fd, 0, "stack_map_wo_token_wo_cap_bpf_should_fail")) { + err = -EINVAL; + goto cleanup; + } + + /* token without CAP_BPF -> fail */ + map_opts.token_fd = token_fd; + map_fd = bpf_map_create(BPF_MAP_TYPE_STACK, "w_token_wo_bpf", 0, 8, 1, &map_opts); + if (!ASSERT_LT(map_fd, 0, "stack_map_w_token_wo_cap_bpf_should_fail")) { + err = -EINVAL; + goto cleanup; + } + + /* get back effective local CAP_BPF (and CAP_SYS_ADMIN) */ + err = restore_priv_caps(old_caps); + if (!ASSERT_OK(err, "restore_caps")) + goto cleanup; + + /* CAP_BPF without token -> fail */ + map_opts.token_fd = 0; + map_fd = bpf_map_create(BPF_MAP_TYPE_STACK, "wo_token_w_bpf", 0, 8, 1, &map_opts); + if (!ASSERT_LT(map_fd, 0, "stack_map_wo_token_w_cap_bpf_should_fail")) { + err = -EINVAL; + goto cleanup; + } + + /* finally, namespaced CAP_BPF + token -> success */ + map_opts.token_fd = token_fd; + map_fd = bpf_map_create(BPF_MAP_TYPE_STACK, "w_token_w_bpf", 0, 8, 1, &map_opts); + if (!ASSERT_GT(map_fd, 0, "stack_map_w_token_w_cap_bpf")) { + err = -EINVAL; + goto cleanup; + } + +cleanup: + zclose(token_fd); + zclose(map_fd); + return err; +} + +static int userns_btf_load(int mnt_fd) +{ + LIBBPF_OPTS(bpf_btf_load_opts, btf_opts); + int err, token_fd = -1, btf_fd = -1; + const void *raw_btf_data; + struct btf *btf = NULL; + __u32 raw_btf_size; + __u64 old_caps = 0; + + /* create BPF token from BPF FS mount */ + token_fd = bpf_token_create(mnt_fd, NULL); + if (!ASSERT_GT(token_fd, 0, "token_create")) { + err = -EINVAL; + goto cleanup; + } + + /* while inside non-init userns, we need both a BPF token *and* + * CAP_BPF inside current userns to create privileged map; let's test + * that neither BPF token alone nor namespaced CAP_BPF is sufficient + */ + err = drop_priv_caps(&old_caps); + if (!ASSERT_OK(err, "drop_caps")) + goto cleanup; + + /* setup a trivial BTF data to load to the kernel */ + btf = btf__new_empty(); + if (!ASSERT_OK_PTR(btf, "empty_btf")) + goto cleanup; + + ASSERT_GT(btf__add_int(btf, "int", 4, 0), 0, "int_type"); + + raw_btf_data = btf__raw_data(btf, &raw_btf_size); + if (!ASSERT_OK_PTR(raw_btf_data, "raw_btf_data")) + goto cleanup; + + /* no token + no CAP_BPF -> failure */ + btf_opts.token_fd = 0; + btf_fd = bpf_btf_load(raw_btf_data, raw_btf_size, &btf_opts); + if (!ASSERT_LT(btf_fd, 0, "no_token_no_cap_should_fail")) + goto cleanup; + + /* token + no CAP_BPF -> failure */ + btf_opts.token_fd = token_fd; + btf_fd = bpf_btf_load(raw_btf_data, raw_btf_size, &btf_opts); + if (!ASSERT_LT(btf_fd, 0, "token_no_cap_should_fail")) + goto cleanup; + + /* get back effective local CAP_BPF (and CAP_SYS_ADMIN) */ + err = restore_priv_caps(old_caps); + if (!ASSERT_OK(err, "restore_caps")) + goto cleanup; + + /* token + CAP_BPF -> success */ + btf_opts.token_fd = token_fd; + btf_fd = bpf_btf_load(raw_btf_data, raw_btf_size, &btf_opts); + if (!ASSERT_GT(btf_fd, 0, "token_and_cap_success")) + goto cleanup; + + err = 0; +cleanup: + btf__free(btf); + zclose(btf_fd); + zclose(token_fd); + return err; +} + +static int userns_prog_load(int mnt_fd) +{ + LIBBPF_OPTS(bpf_prog_load_opts, prog_opts); + int err, token_fd = -1, prog_fd = -1; + struct bpf_insn insns[] = { + /* bpf_jiffies64() requires CAP_BPF */ + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_jiffies64), + /* bpf_get_current_task() requires CAP_PERFMON */ + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_current_task), + /* r0 = 0; exit; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + size_t insn_cnt = ARRAY_SIZE(insns); + __u64 old_caps = 0; + + /* create BPF token from BPF FS mount */ + token_fd = bpf_token_create(mnt_fd, NULL); + if (!ASSERT_GT(token_fd, 0, "token_create")) { + err = -EINVAL; + goto cleanup; + } + + /* validate we can successfully load BPF program with token; this + * being XDP program (CAP_NET_ADMIN) using bpf_jiffies64() (CAP_BPF) + * and bpf_get_current_task() (CAP_PERFMON) helpers validates we have + * BPF token wired properly in a bunch of places in the kernel + */ + prog_opts.token_fd = token_fd; + prog_opts.expected_attach_type = BPF_XDP; + prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, "token_prog", "GPL", + insns, insn_cnt, &prog_opts); + if (!ASSERT_GT(prog_fd, 0, "prog_fd")) { + err = -EPERM; + goto cleanup; + } + + /* no token + caps -> failure */ + prog_opts.token_fd = 0; + prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, "token_prog", "GPL", + insns, insn_cnt, &prog_opts); + if (!ASSERT_EQ(prog_fd, -EPERM, "prog_fd_eperm")) { + err = -EPERM; + goto cleanup; + } + + err = drop_priv_caps(&old_caps); + if (!ASSERT_OK(err, "drop_caps")) + goto cleanup; + + /* no caps + token -> failure */ + prog_opts.token_fd = token_fd; + prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, "token_prog", "GPL", + insns, insn_cnt, &prog_opts); + if (!ASSERT_EQ(prog_fd, -EPERM, "prog_fd_eperm")) { + err = -EPERM; + goto cleanup; + } + + /* no caps + no token -> definitely a failure */ + prog_opts.token_fd = 0; + prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, "token_prog", "GPL", + insns, insn_cnt, &prog_opts); + if (!ASSERT_EQ(prog_fd, -EPERM, "prog_fd_eperm")) { + err = -EPERM; + goto cleanup; + } + + err = 0; +cleanup: + zclose(prog_fd); + zclose(token_fd); + return err; +} + +void test_token(void) +{ + if (test__start_subtest("map_token")) { + struct bpffs_opts opts = { + .cmds = 1ULL << BPF_MAP_CREATE, + .maps = 1ULL << BPF_MAP_TYPE_STACK, + }; + + subtest_userns(&opts, userns_map_create); + } + if (test__start_subtest("btf_token")) { + struct bpffs_opts opts = { + .cmds = 1ULL << BPF_BTF_LOAD, + }; + + subtest_userns(&opts, userns_btf_load); + } + if (test__start_subtest("prog_token")) { + struct bpffs_opts opts = { + .cmds = 1ULL << BPF_PROG_LOAD, + .progs = 1ULL << BPF_PROG_TYPE_XDP, + .attachs = 1ULL << BPF_XDP, + }; + + subtest_userns(&opts, userns_prog_load); + } +} -- cgit v1.2.3