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@xxxxxxxxxx>
---
include/linux/bpf.h | 3 ++
include/uapi/linux/bpf.h | 2 +
kernel/bpf/inode.c | 3 +-
kernel/bpf/syscall.c | 54 +++++++++++++++----
kernel/bpf/token.c | 15 ++++++
tools/include/uapi/linux/bpf.h | 2 +
.../selftests/bpf/prog_tests/libbpf_probes.c | 2 +
.../selftests/bpf/prog_tests/libbpf_str.c | 3 ++
8 files changed, 72 insertions(+), 12 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index ae13538f5465..a4aea5b34290 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -265,6 +265,7 @@ struct bpf_map {
u32 btf_value_type_id;
u32 btf_vmlinux_value_type_id;
struct btf *btf;
+ struct bpf_token *token;
#ifdef CONFIG_MEMCG_KMEM
struct obj_cgroup *objcg;
#endif
@@ -1579,6 +1580,7 @@ struct bpf_token {
atomic64_t refcnt;
struct user_namespace *userns;
u64 allowed_cmds;
+ u64 allowed_maps;
};
struct bpf_struct_ops_value;
@@ -2214,6 +2216,7 @@ int bpf_token_new_fd(struct bpf_token *token);
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 36e98c6f8944..9c399454712e 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -984,6 +984,7 @@ 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
@@ -1423,6 +1424,7 @@ 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 82f11fbffd3e..6e8b4e2bda97 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -614,7 +614,8 @@ 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 93338faa43d5..72fe3b9fa2e4 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -695,6 +695,7 @@ static void bpf_map_free_deferred(struct work_struct *work)
{
struct bpf_map *map = container_of(work, struct bpf_map, work);
struct btf_record *rec = map->record;
+ struct bpf_token *token = map->token;
security_bpf_map_free(map);
bpf_map_release_memcg(map);
@@ -710,6 +711,7 @@ static void bpf_map_free_deferred(struct work_struct *work)
* template bpf_map struct used during verification.
*/
btf_record_free(rec);
+ bpf_token_put(token);
}
static void bpf_map_put_uref(struct bpf_map *map)
@@ -1014,7 +1016,7 @@ 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(map->token, CAP_BPF)) {
ret = -EPERM;
goto free_map_tab;
}
@@ -1102,11 +1104,12 @@ 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;
@@ -1157,14 +1160,32 @@ 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) {
@@ -1197,28 +1218,36 @@ 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;
+ if (token) {
+ /* move token reference into map->token, reuse our refcnt */
+ map->token = token;
+ token = NULL;
+ }
+
err = bpf_obj_name_cpy(map->name, attr->map_name,
sizeof(attr->map_name));
if (err < 0)
@@ -1291,8 +1320,11 @@ static int map_create(union bpf_attr *attr)
free_map_sec:
security_bpf_map_free(map);
free_map:
+ bpf_token_put(map->token);
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 f6ea3eddbee6..bcc170fcf341 100644
--- a/kernel/bpf/token.c
+++ b/kernel/bpf/token.c
@@ -88,6 +88,12 @@ 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);
+
+ 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);
}
static const struct file_operations bpf_token_fops = {
@@ -142,6 +148,7 @@ 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;
ret = bpf_token_new_fd(token);
if (ret < 0)
@@ -187,3 +194,11 @@ 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 36e98c6f8944..9c399454712e 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -984,6 +984,7 @@ 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
@@ -1423,6 +1424,7 @@ 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);
--
2.34.1
