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>

1 files changed, 41 insertions, 0 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index d3c9acc593ea..aa9cf8e5fab1 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -51,6 +51,10 @@ struct module;
 struct bpf_func_state;
 struct ftrace_ops;
 struct cgroup;
+struct bpf_token;
+struct user_namespace;
+struct super_block;
+struct inode;
 
 extern struct idr btf_idr;
 extern spinlock_t btf_idr_lock;
@@ -1591,6 +1595,13 @@ struct bpf_mount_opts {
 	u64 delegate_attachs;
 };
 
+struct bpf_token {
+	struct work_struct work;
+	atomic64_t refcnt;
+	struct user_namespace *userns;
+	u64 allowed_cmds;
+};
+
 struct bpf_struct_ops_value;
 struct btf_member;
 
@@ -2048,6 +2059,7 @@ static inline void bpf_enable_instrumentation(void)
 	migrate_enable();
 }
 
+extern const struct super_operations bpf_super_ops;
 extern const struct file_operations bpf_map_fops;
 extern const struct file_operations bpf_prog_fops;
 extern const struct file_operations bpf_iter_fops;
@@ -2182,6 +2194,8 @@ static inline void bpf_map_dec_elem_count(struct bpf_map *map)
 
 extern int sysctl_unprivileged_bpf_disabled;
 
+bool bpf_token_capable(const struct bpf_token *token, int cap);
+
 static inline bool bpf_allow_ptr_leaks(void)
 {
 	return perfmon_capable();
@@ -2216,8 +2230,17 @@ int bpf_link_new_fd(struct bpf_link *link);
 struct bpf_link *bpf_link_get_from_fd(u32 ufd);
 struct bpf_link *bpf_link_get_curr_or_next(u32 *id);
 
+void bpf_token_inc(struct bpf_token *token);
+void bpf_token_put(struct bpf_token *token);
+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);
+
 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);
+struct inode *bpf_get_inode(struct super_block *sb, const struct inode *dir,
+			    umode_t mode);
 
 #define BPF_ITER_FUNC_PREFIX "bpf_iter_"
 #define DEFINE_BPF_ITER_FUNC(target, args...)			\
@@ -2580,6 +2603,24 @@ static inline int bpf_obj_get_user(const char __user *pathname, int flags)
 	return -EOPNOTSUPP;
 }
 
+static inline bool bpf_token_capable(const struct bpf_token *token, int cap)
+{
+	return capable(cap) || (cap != CAP_SYS_ADMIN && capable(CAP_SYS_ADMIN));
+}
+
+static inline void bpf_token_inc(struct bpf_token *token)
+{
+}
+
+static inline void bpf_token_put(struct bpf_token *token)
+{
+}
+
+static inline struct bpf_token *bpf_token_get_from_fd(u32 ufd)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
 static inline void __dev_flush(void)
 {
 }