From 4527358b76861dfd64ee34aba45d81648fbc8a61 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Thu, 30 Nov 2023 10:52:15 -0800
Subject: bpf: introduce BPF token object

Add new kind of BPF kernel object, BPF token. BPF token is meant to
allow delegating privileged BPF functionality, like loading a BPF
program or creating a BPF map, from privileged process to a *trusted*
unprivileged process, all while having a good amount of control over which
privileged operations could be performed using provided BPF token.

This is achieved through mounting BPF FS instance with extra delegation
mount options, which determine what operations are delegatable, and also
constraining it to the owning user namespace (as mentioned in the
previous patch).

BPF token itself is just a derivative from BPF FS and can be created
through a new bpf() syscall command, BPF_TOKEN_CREATE, which accepts BPF
FS FD, which can be attained through open() API by opening BPF FS mount
point. Currently, BPF token "inherits" delegated command, map types,
prog type, and attach type bit sets from BPF FS as is. In the future,
having an BPF token as a separate object with its own FD, we can allow
to further restrict BPF token's allowable set of things either at the
creation time or after the fact, allowing the process to guard itself
further from unintentionally trying to load undesired kind of BPF
programs. But for now we keep things simple and just copy bit sets as is.

When BPF token is created from BPF FS mount, we take reference to the
BPF super block's owning user namespace, and then use that namespace for
checking all the {CAP_BPF, CAP_PERFMON, CAP_NET_ADMIN, CAP_SYS_ADMIN}
capabilities that are normally only checked against init userns (using
capable()), but now we check them using ns_capable() instead (if BPF
token is provided). See bpf_token_capable() for details.

Such setup means that BPF token in itself is not sufficient to grant BPF
functionality. User namespaced process has to *also* have necessary
combination of capabilities inside that user namespace. So while
previously CAP_BPF was useless when granted within user namespace, now
it gains a meaning and allows container managers and sys admins to have
a flexible control over which processes can and need to use BPF
functionality within the user namespace (i.e., container in practice).
And BPF FS delegation mount options and derived BPF tokens serve as
a per-container "flag" to grant overall ability to use bpf() (plus further
restrict on which parts of bpf() syscalls are treated as namespaced).

Note also, BPF_TOKEN_CREATE command itself requires ns_capable(CAP_BPF)
within the BPF FS owning user namespace, rounding up the ns_capable()
story of BPF token.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20231130185229.2688956-4-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/include/uapi/linux/bpf.h | 37 +++++++++++++++++++++++++++++++++++++
 1 file changed, 37 insertions(+)

(limited to 'tools')

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index e88746ba7d21..d4a567e5bc3c 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -847,6 +847,36 @@ union bpf_iter_link_info {
  *		Returns zero on success. On error, -1 is returned and *errno*
  *		is set appropriately.
  *
+ * BPF_TOKEN_CREATE
+ *	Description
+ *		Create BPF token with embedded information about what
+ *		BPF-related functionality it allows:
+ *		- a set of allowed bpf() syscall commands;
+ *		- a set of allowed BPF map types to be created with
+ *		BPF_MAP_CREATE command, if BPF_MAP_CREATE itself is allowed;
+ *		- a set of allowed BPF program types and BPF program attach
+ *		types to be loaded with BPF_PROG_LOAD command, if
+ *		BPF_PROG_LOAD itself is allowed.
+ *
+ *		BPF token is created (derived) from an instance of BPF FS,
+ *		assuming it has necessary delegation mount options specified.
+ *		This BPF token can be passed as an extra parameter to various
+ *		bpf() syscall commands to grant BPF subsystem functionality to
+ *		unprivileged processes.
+ *
+ *		When created, BPF token is "associated" with the owning
+ *		user namespace of BPF FS instance (super block) that it was
+ *		derived from, and subsequent BPF operations performed with
+ *		BPF token would be performing capabilities checks (i.e.,
+ *		CAP_BPF, CAP_PERFMON, CAP_NET_ADMIN, CAP_SYS_ADMIN) within
+ *		that user namespace. Without BPF token, such capabilities
+ *		have to be granted in init user namespace, making bpf()
+ *		syscall incompatible with user namespace, for the most part.
+ *
+ *	Return
+ *		A new file descriptor (a nonnegative integer), or -1 if an
+ *		error occurred (in which case, *errno* is set appropriately).
+ *
  * NOTES
  *	eBPF objects (maps and programs) can be shared between processes.
  *
@@ -901,6 +931,8 @@ enum bpf_cmd {
 	BPF_ITER_CREATE,
 	BPF_LINK_DETACH,
 	BPF_PROG_BIND_MAP,
+	BPF_TOKEN_CREATE,
+	__MAX_BPF_CMD,
 };
 
 enum bpf_map_type {
@@ -1712,6 +1744,11 @@ union bpf_attr {
 		__u32		flags;		/* extra flags */
 	} prog_bind_map;
 
+	struct { /* struct used by BPF_TOKEN_CREATE command */
+		__u32		flags;
+		__u32		bpffs_fd;
+	} token_create;
+
 } __attribute__((aligned(8)));
 
 /* The description below is an attempt at providing documentation to eBPF
-- 
cgit v1.2.3


From 688b7270b3cb75e8ac78123d719967db40336e5b Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
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 <andrii@kernel.org>
Link: https://lore.kernel.org/r/20231130185229.2688956-5-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h                                |  2 +
 include/uapi/linux/bpf.h                           |  2 +
 kernel/bpf/inode.c                                 |  3 +-
 kernel/bpf/syscall.c                               | 52 ++++++++++++++++------
 kernel/bpf/token.c                                 | 16 +++++++
 tools/include/uapi/linux/bpf.h                     |  2 +
 .../selftests/bpf/prog_tests/libbpf_probes.c       |  2 +
 .../testing/selftests/bpf/prog_tests/libbpf_str.c  |  3 ++
 8 files changed, 67 insertions(+), 15 deletions(-)

(limited to 'tools')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index aa9cf8e5fab1..e08e8436df38 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1600,6 +1600,7 @@ struct bpf_token {
 	atomic64_t refcnt;
 	struct user_namespace *userns;
 	u64 allowed_cmds;
+	u64 allowed_maps;
 };
 
 struct bpf_struct_ops_value;
@@ -2236,6 +2237,7 @@ int bpf_token_create(union bpf_attr *attr);
 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);
 
 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 d4a567e5bc3c..0bba3392b17a 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -983,6 +983,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_BLOOM_FILTER,
 	BPF_MAP_TYPE_USER_RINGBUF,
 	BPF_MAP_TYPE_CGRP_STORAGE,
+	__MAX_BPF_MAP_TYPE
 };
 
 /* Note that tracing related programs such as
@@ -1433,6 +1434,7 @@ union bpf_attr {
 		 * to using 5 hash functions).
 		 */
 		__u64	map_extra;
+		__u32	map_token_fd;
 	};
 
 	struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 6ce3f9696e72..9c7865d1c53d 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -613,7 +613,8 @@ static int bpf_show_options(struct seq_file *m, struct dentry *root)
 	else if (opts->delegate_cmds)
 		seq_printf(m, ",delegate_cmds=0x%llx", opts->delegate_cmds);
 
-	if (opts->delegate_maps == ~0ULL)
+	mask = (1ULL << __MAX_BPF_MAP_TYPE) - 1;
+	if ((opts->delegate_maps & mask) == mask)
 		seq_printf(m, ",delegate_maps=any");
 	else if (opts->delegate_maps)
 		seq_printf(m, ",delegate_maps=0x%llx", opts->delegate_maps);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index a156d549b356..22e14124cd61 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1009,8 +1009,8 @@ int map_check_no_btf(const struct bpf_map *map,
 	return -ENOTSUPP;
 }
 
-static int map_check_btf(struct bpf_map *map, const struct btf *btf,
-			 u32 btf_key_id, u32 btf_value_id)
+static int map_check_btf(struct bpf_map *map, struct bpf_token *token,
+			 const struct btf *btf, u32 btf_key_id, u32 btf_value_id)
 {
 	const struct btf_type *key_type, *value_type;
 	u32 key_size, value_size;
@@ -1038,7 +1038,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf,
 	if (!IS_ERR_OR_NULL(map->record)) {
 		int i;
 
-		if (!bpf_capable()) {
+		if (!bpf_token_capable(token, CAP_BPF)) {
 			ret = -EPERM;
 			goto free_map_tab;
 		}
@@ -1126,11 +1126,12 @@ static bool bpf_net_capable(void)
 	return capable(CAP_NET_ADMIN) || capable(CAP_SYS_ADMIN);
 }
 
-#define BPF_MAP_CREATE_LAST_FIELD map_extra
+#define BPF_MAP_CREATE_LAST_FIELD map_token_fd
 /* called via syscall */
 static int map_create(union bpf_attr *attr)
 {
 	const struct bpf_map_ops *ops;
+	struct bpf_token *token = NULL;
 	int numa_node = bpf_map_attr_numa_node(attr);
 	u32 map_type = attr->map_type;
 	struct bpf_map *map;
@@ -1181,14 +1182,32 @@ static int map_create(union bpf_attr *attr)
 	if (!ops->map_mem_usage)
 		return -EINVAL;
 
+	if (attr->map_token_fd) {
+		token = bpf_token_get_from_fd(attr->map_token_fd);
+		if (IS_ERR(token))
+			return PTR_ERR(token);
+
+		/* if current token doesn't grant map creation 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_MAP_CREATE) ||
+		    !bpf_token_allow_map_type(token, attr->map_type)) {
+			bpf_token_put(token);
+			token = NULL;
+		}
+	}
+
+	err = -EPERM;
+
 	/* Intent here is for unprivileged_bpf_disabled to block BPF map
 	 * creation for unprivileged users; other actions depend
 	 * on fd availability and access to bpffs, so are dependent on
 	 * object creation success. Even with unprivileged BPF disabled,
 	 * capability checks are still carried out.
 	 */
-	if (sysctl_unprivileged_bpf_disabled && !bpf_capable())
-		return -EPERM;
+	if (sysctl_unprivileged_bpf_disabled && !bpf_token_capable(token, CAP_BPF))
+		goto put_token;
 
 	/* check privileged map type permissions */
 	switch (map_type) {
@@ -1221,25 +1240,27 @@ static int map_create(union bpf_attr *attr)
 	case BPF_MAP_TYPE_LRU_PERCPU_HASH:
 	case BPF_MAP_TYPE_STRUCT_OPS:
 	case BPF_MAP_TYPE_CPUMAP:
-		if (!bpf_capable())
-			return -EPERM;
+		if (!bpf_token_capable(token, CAP_BPF))
+			goto put_token;
 		break;
 	case BPF_MAP_TYPE_SOCKMAP:
 	case BPF_MAP_TYPE_SOCKHASH:
 	case BPF_MAP_TYPE_DEVMAP:
 	case BPF_MAP_TYPE_DEVMAP_HASH:
 	case BPF_MAP_TYPE_XSKMAP:
-		if (!bpf_net_capable())
-			return -EPERM;
+		if (!bpf_token_capable(token, CAP_NET_ADMIN))
+			goto put_token;
 		break;
 	default:
 		WARN(1, "unsupported map type %d", map_type);
-		return -EPERM;
+		goto put_token;
 	}
 
 	map = ops->map_alloc(attr);
-	if (IS_ERR(map))
-		return PTR_ERR(map);
+	if (IS_ERR(map)) {
+		err = PTR_ERR(map);
+		goto put_token;
+	}
 	map->ops = ops;
 	map->map_type = map_type;
 
@@ -1276,7 +1297,7 @@ static int map_create(union bpf_attr *attr)
 		map->btf = btf;
 
 		if (attr->btf_value_type_id) {
-			err = map_check_btf(map, btf, attr->btf_key_type_id,
+			err = map_check_btf(map, token, btf, attr->btf_key_type_id,
 					    attr->btf_value_type_id);
 			if (err)
 				goto free_map;
@@ -1297,6 +1318,7 @@ static int map_create(union bpf_attr *attr)
 		goto free_map_sec;
 
 	bpf_map_save_memcg(map);
+	bpf_token_put(token);
 
 	err = bpf_map_new_fd(map, f_flags);
 	if (err < 0) {
@@ -1317,6 +1339,8 @@ free_map_sec:
 free_map:
 	btf_put(map->btf);
 	map->ops->map_free(map);
+put_token:
+	bpf_token_put(token);
 	return err;
 }
 
diff --git a/kernel/bpf/token.c b/kernel/bpf/token.c
index e18aaecc67e9..06c34dae658e 100644
--- a/kernel/bpf/token.c
+++ b/kernel/bpf/token.c
@@ -72,6 +72,13 @@ static void bpf_token_show_fdinfo(struct seq_file *m, struct file *filp)
 		seq_printf(m, "allowed_cmds:\tany\n");
 	else
 		seq_printf(m, "allowed_cmds:\t0x%llx\n", token->allowed_cmds);
+
+	BUILD_BUG_ON(__MAX_BPF_MAP_TYPE >= 64);
+	mask = (1ULL << __MAX_BPF_MAP_TYPE) - 1;
+	if ((token->allowed_maps & mask) == mask)
+		seq_printf(m, "allowed_maps:\tany\n");
+	else
+		seq_printf(m, "allowed_maps:\t0x%llx\n", token->allowed_maps);
 }
 
 #define BPF_TOKEN_INODE_NAME "bpf-token"
@@ -161,6 +168,7 @@ 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;
 
 	fd = get_unused_fd_flags(O_CLOEXEC);
 	if (fd < 0) {
@@ -212,3 +220,11 @@ bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd)
 
 	return token->allowed_cmds & (1ULL << cmd);
 }
+
+bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type)
+{
+	if (!token || type >= __MAX_BPF_MAP_TYPE)
+		return false;
+
+	return token->allowed_maps & (1ULL << type);
+}
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index d4a567e5bc3c..0bba3392b17a 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -983,6 +983,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_BLOOM_FILTER,
 	BPF_MAP_TYPE_USER_RINGBUF,
 	BPF_MAP_TYPE_CGRP_STORAGE,
+	__MAX_BPF_MAP_TYPE
 };
 
 /* Note that tracing related programs such as
@@ -1433,6 +1434,7 @@ union bpf_attr {
 		 * to using 5 hash functions).
 		 */
 		__u64	map_extra;
+		__u32	map_token_fd;
 	};
 
 	struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
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 ee54b1a910e4d49c9a104f31ae3f5b979131adf8 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Thu, 30 Nov 2023 10:52:17 -0800
Subject: bpf: add BPF token support to BPF_BTF_LOAD command

Accept BPF token FD in BPF_BTF_LOAD command to allow BTF data loading
through delegated BPF token. BTF loading is a pretty straightforward
operation, so as long as BPF token is created with allow_cmds granting
BPF_BTF_LOAD command, kernel proceeds to parsing BTF data and creating
BTF object.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20231130185229.2688956-6-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/bpf.h       |  1 +
 kernel/bpf/syscall.c           | 20 ++++++++++++++++++--
 tools/include/uapi/linux/bpf.h |  1 +
 3 files changed, 20 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 0bba3392b17a..9f9989e0d062 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1616,6 +1616,7 @@ union bpf_attr {
 		 * truncated), or smaller (if log buffer wasn't filled completely).
 		 */
 		__u32		btf_log_true_size;
+		__u32		btf_token_fd;
 	};
 
 	struct {
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 22e14124cd61..d87c5c27cde3 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -4777,15 +4777,31 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr,
 	return err;
 }
 
-#define BPF_BTF_LOAD_LAST_FIELD btf_log_true_size
+#define BPF_BTF_LOAD_LAST_FIELD btf_token_fd
 
 static int bpf_btf_load(const union bpf_attr *attr, bpfptr_t uattr, __u32 uattr_size)
 {
+	struct bpf_token *token = NULL;
+
 	if (CHECK_ATTR(BPF_BTF_LOAD))
 		return -EINVAL;
 
-	if (!bpf_capable())
+	if (attr->btf_token_fd) {
+		token = bpf_token_get_from_fd(attr->btf_token_fd);
+		if (IS_ERR(token))
+			return PTR_ERR(token);
+		if (!bpf_token_allow_cmd(token, BPF_BTF_LOAD)) {
+			bpf_token_put(token);
+			token = NULL;
+		}
+	}
+
+	if (!bpf_token_capable(token, CAP_BPF)) {
+		bpf_token_put(token);
 		return -EPERM;
+	}
+
+	bpf_token_put(token);
 
 	return btf_new_fd(attr, uattr, uattr_size);
 }
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 0bba3392b17a..9f9989e0d062 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1616,6 +1616,7 @@ union bpf_attr {
 		 * truncated), or smaller (if log buffer wasn't filled completely).
 		 */
 		__u32		btf_log_true_size;
+		__u32		btf_token_fd;
 	};
 
 	struct {
-- 
cgit v1.2.3


From e1cef620f598853a90f17701fcb1057a6768f7b8 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
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 <andrii@kernel.org>
Link: https://lore.kernel.org/r/20231130185229.2688956-7-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 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')

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 ecd435143eb03611e25694141bf59d1c04ad5b9e Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Thu, 30 Nov 2023 10:52:24 -0800
Subject: libbpf: add bpf_token_create() API

Add low-level wrapper API for BPF_TOKEN_CREATE command in bpf() syscall.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20231130185229.2688956-13-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/bpf.c      | 17 +++++++++++++++++
 tools/lib/bpf/bpf.h      | 24 ++++++++++++++++++++++++
 tools/lib/bpf/libbpf.map |  1 +
 3 files changed, 42 insertions(+)

(limited to 'tools')

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 9dc9625651dc..d4019928a864 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -1287,3 +1287,20 @@ int bpf_prog_bind_map(int prog_fd, int map_fd,
 	ret = sys_bpf(BPF_PROG_BIND_MAP, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
+
+int bpf_token_create(int bpffs_fd, struct bpf_token_create_opts *opts)
+{
+	const size_t attr_sz = offsetofend(union bpf_attr, token_create);
+	union bpf_attr attr;
+	int fd;
+
+	if (!OPTS_VALID(opts, bpf_token_create_opts))
+		return libbpf_err(-EINVAL);
+
+	memset(&attr, 0, attr_sz);
+	attr.token_create.bpffs_fd = bpffs_fd;
+	attr.token_create.flags = OPTS_GET(opts, flags, 0);
+
+	fd = sys_bpf_fd(BPF_TOKEN_CREATE, &attr, attr_sz);
+	return libbpf_err_errno(fd);
+}
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index d0f53772bdc0..e49254c9f68f 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -640,6 +640,30 @@ struct bpf_test_run_opts {
 LIBBPF_API int bpf_prog_test_run_opts(int prog_fd,
 				      struct bpf_test_run_opts *opts);
 
+struct bpf_token_create_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+	__u32 flags;
+	size_t :0;
+};
+#define bpf_token_create_opts__last_field flags
+
+/**
+ * @brief **bpf_token_create()** creates a new instance of BPF token derived
+ * from specified BPF FS mount point.
+ *
+ * BPF token created with this API can be passed to bpf() syscall for
+ * commands like BPF_PROG_LOAD, BPF_MAP_CREATE, etc.
+ *
+ * @param bpffs_fd FD for BPF FS instance from which to derive a BPF token
+ * instance.
+ * @param opts optional BPF token creation options, can be NULL
+ *
+ * @return BPF token FD > 0, on success; negative error code, otherwise (errno
+ * is also set to the error code)
+ */
+LIBBPF_API int bpf_token_create(int bpffs_fd,
+				struct bpf_token_create_opts *opts);
+
 #ifdef __cplusplus
 } /* extern "C" */
 #endif
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 91c5aef7dae7..df7657b65c47 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -401,6 +401,7 @@ LIBBPF_1.3.0 {
 		bpf_program__attach_netkit;
 		bpf_program__attach_tcx;
 		bpf_program__attach_uprobe_multi;
+		bpf_token_create;
 		ring__avail_data_size;
 		ring__consume;
 		ring__consumer_pos;
-- 
cgit v1.2.3


From 37891cea6699200fb83eae464ebe1c0f73040474 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Thu, 30 Nov 2023 10:52:25 -0800
Subject: libbpf: add BPF token support to bpf_map_create() API

Add ability to provide token_fd for BPF_MAP_CREATE command through
bpf_map_create() API.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20231130185229.2688956-14-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/bpf.c | 4 +++-
 tools/lib/bpf/bpf.h | 5 ++++-
 2 files changed, 7 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index d4019928a864..1653b64b7015 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -169,7 +169,7 @@ int bpf_map_create(enum bpf_map_type map_type,
 		   __u32 max_entries,
 		   const struct bpf_map_create_opts *opts)
 {
-	const size_t attr_sz = offsetofend(union bpf_attr, map_extra);
+	const size_t attr_sz = offsetofend(union bpf_attr, map_token_fd);
 	union bpf_attr attr;
 	int fd;
 
@@ -198,6 +198,8 @@ int bpf_map_create(enum bpf_map_type map_type,
 	attr.numa_node = OPTS_GET(opts, numa_node, 0);
 	attr.map_ifindex = OPTS_GET(opts, map_ifindex, 0);
 
+	attr.map_token_fd = OPTS_GET(opts, token_fd, 0);
+
 	fd = sys_bpf_fd(BPF_MAP_CREATE, &attr, attr_sz);
 	return libbpf_err_errno(fd);
 }
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index e49254c9f68f..ae2136f596b4 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -51,8 +51,11 @@ struct bpf_map_create_opts {
 
 	__u32 numa_node;
 	__u32 map_ifindex;
+
+	__u32 token_fd;
+	size_t :0;
 };
-#define bpf_map_create_opts__last_field map_ifindex
+#define bpf_map_create_opts__last_field token_fd
 
 LIBBPF_API int bpf_map_create(enum bpf_map_type map_type,
 			      const char *map_name,
-- 
cgit v1.2.3


From 1a8df7fa00aac35aff9ef1941c5334b3a01d09e4 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Thu, 30 Nov 2023 10:52:26 -0800
Subject: libbpf: add BPF token support to bpf_btf_load() API

Allow user to specify token_fd for bpf_btf_load() API that wraps
kernel's BPF_BTF_LOAD command. This allows loading BTF from unprivileged
process as long as it has BPF token allowing BPF_BTF_LOAD command, which
can be created and delegated by privileged process.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20231130185229.2688956-15-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/bpf.c | 4 +++-
 tools/lib/bpf/bpf.h | 3 ++-
 2 files changed, 5 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 1653b64b7015..544ae2376b6b 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -1184,7 +1184,7 @@ int bpf_raw_tracepoint_open(const char *name, int prog_fd)
 
 int bpf_btf_load(const void *btf_data, size_t btf_size, struct bpf_btf_load_opts *opts)
 {
-	const size_t attr_sz = offsetofend(union bpf_attr, btf_log_true_size);
+	const size_t attr_sz = offsetofend(union bpf_attr, btf_token_fd);
 	union bpf_attr attr;
 	char *log_buf;
 	size_t log_size;
@@ -1209,6 +1209,8 @@ int bpf_btf_load(const void *btf_data, size_t btf_size, struct bpf_btf_load_opts
 
 	attr.btf = ptr_to_u64(btf_data);
 	attr.btf_size = btf_size;
+	attr.btf_token_fd = OPTS_GET(opts, token_fd, 0);
+
 	/* log_level == 0 and log_buf != NULL means "try loading without
 	 * log_buf, but retry with log_buf and log_level=1 on error", which is
 	 * consistent across low-level and high-level BTF and program loading
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index ae2136f596b4..4b0f25e97b0d 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -133,9 +133,10 @@ struct bpf_btf_load_opts {
 	 * If kernel doesn't support this feature, log_size is left unchanged.
 	 */
 	__u32 log_true_size;
+	__u32 token_fd;
 	size_t :0;
 };
-#define bpf_btf_load_opts__last_field log_true_size
+#define bpf_btf_load_opts__last_field token_fd
 
 LIBBPF_API int bpf_btf_load(const void *btf_data, size_t btf_size,
 			    struct bpf_btf_load_opts *opts);
-- 
cgit v1.2.3


From 1571740a9ba036f26cc5211a86021199987219e8 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Thu, 30 Nov 2023 10:52:27 -0800
Subject: libbpf: add BPF token support to bpf_prog_load() API

Wire through token_fd into bpf_prog_load().

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20231130185229.2688956-16-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/bpf.c | 3 ++-
 tools/lib/bpf/bpf.h | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 544ae2376b6b..f4e1da3c6d5f 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -234,7 +234,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type,
 		  const struct bpf_insn *insns, size_t insn_cnt,
 		  struct bpf_prog_load_opts *opts)
 {
-	const size_t attr_sz = offsetofend(union bpf_attr, log_true_size);
+	const size_t attr_sz = offsetofend(union bpf_attr, prog_token_fd);
 	void *finfo = NULL, *linfo = NULL;
 	const char *func_info, *line_info;
 	__u32 log_size, log_level, attach_prog_fd, attach_btf_obj_fd;
@@ -263,6 +263,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type,
 	attr.prog_flags = OPTS_GET(opts, prog_flags, 0);
 	attr.prog_ifindex = OPTS_GET(opts, prog_ifindex, 0);
 	attr.kern_version = OPTS_GET(opts, kern_version, 0);
+	attr.prog_token_fd = OPTS_GET(opts, token_fd, 0);
 
 	if (prog_name && kernel_supports(NULL, FEAT_PROG_NAME))
 		libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name));
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 4b0f25e97b0d..991b86bfe7e4 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -105,9 +105,10 @@ struct bpf_prog_load_opts {
 	 * If kernel doesn't support this feature, log_size is left unchanged.
 	 */
 	__u32 log_true_size;
+	__u32 token_fd;
 	size_t :0;
 };
-#define bpf_prog_load_opts__last_field log_true_size
+#define bpf_prog_load_opts__last_field token_fd
 
 LIBBPF_API int bpf_prog_load(enum bpf_prog_type prog_type,
 			     const char *prog_name, const char *license,
-- 
cgit v1.2.3


From dc5196fac40c2cb96330bcb98eef868a7fd225b3 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
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 <andrii@kernel.org>
Link: https://lore.kernel.org/r/20231130185229.2688956-17-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 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')

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 <test_progs.h>
+#include <bpf/btf.h>
+#include "cap_helpers.h"
+#include <fcntl.h>
+#include <sched.h>
+#include <signal.h>
+#include <unistd.h>
+#include <linux/filter.h>
+#include <linux/unistd.h>
+#include <linux/mount.h>
+#include <sys/socket.h>
+#include <sys/syscall.h>
+#include <sys/un.h>
+
+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