[PATCH v3 bpf-next 04/14] bpf: add BPF token support to BPF_MAP_CREATE command

[Andrii Nakryiko <andrii@kernel.org>]

Allow providing token_fd for BPF_MAP_CREATE command to allow controlled
BPF map creation from unprivileged process through delegated BPF token.

Further, add a filter of allowed BPF map types to BPF token, specified
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>
---
 include/linux/bpf.h                           |  3 +
 include/uapi/linux/bpf.h                      |  6 ++
 kernel/bpf/syscall.c                          | 56 +++++++++++++++----
 kernel/bpf/token.c                            | 13 +++++
 tools/include/uapi/linux/bpf.h                |  6 ++
 .../selftests/bpf/prog_tests/libbpf_probes.c  |  2 +
 .../selftests/bpf/prog_tests/libbpf_str.c     |  3 +
 7 files changed, 77 insertions(+), 12 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index c4f1684aa138..856a147c8ce8 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -251,6 +251,7 @@ 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
@@ -1538,6 +1539,7 @@ struct bpf_token {
 	struct work_struct work;
 	atomic64_t refcnt;
 	u64 allowed_cmds;
+	u64 allowed_map_types;
 };
 
 struct bpf_struct_ops_value;
@@ -2096,6 +2098,7 @@ 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);
 
 enum bpf_type {
 	BPF_TYPE_UNSPEC	= 0,
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 3c201cfe6d5c..81c88edceac5 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -962,6 +962,7 @@ 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
@@ -1367,6 +1368,7 @@ union bpf_attr {
 		 * to using 5 hash functions).
 		 */
 		__u64	map_extra;
+		__u32	map_token_fd;
 	};
 
 	struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@@ -1657,6 +1659,10 @@ union bpf_attr {
 		 * programs
 		 */
 		__u64		allowed_cmds;
+		/* similarly to allowed_cmds, a bit set of BPF map types that
+		 * are allowed to be created by requested BPF token;
+		 */
+		__u64		allowed_map_types;
 	} token_create;
 
 } __attribute__((aligned(8)));
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index c48e0e829b06..0046bd579f13 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -691,6 +691,7 @@ 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);
@@ -706,6 +707,7 @@ 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)
@@ -1010,7 +1012,7 @@ 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;
 		}
@@ -1092,11 +1094,12 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf,
 	return ret;
 }
 
-#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;
@@ -1147,14 +1150,32 @@ 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) {
@@ -1187,28 +1208,36 @@ 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 (!capable(CAP_NET_ADMIN))
-			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)
@@ -1281,8 +1310,11 @@ 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;
 }
 
@@ -5081,7 +5113,7 @@ static int bpf_prog_bind_map(union bpf_attr *attr)
 	return ret;
 }
 
-#define BPF_TOKEN_CREATE_LAST_FIELD token_create.allowed_cmds
+#define BPF_TOKEN_CREATE_LAST_FIELD token_create.allowed_map_types
 
 static int token_create(union bpf_attr *attr)
 {
diff --git a/kernel/bpf/token.c b/kernel/bpf/token.c
index 1ece52439701..91d8d987faea 100644
--- a/kernel/bpf/token.c
+++ b/kernel/bpf/token.c
@@ -110,6 +110,10 @@ int bpf_token_create(union bpf_attr *attr)
 	/* requested cmds should be a subset of associated token's set */
 	if (token && !is_bit_subset_of(attr->token_create.allowed_cmds, token->allowed_cmds))
 		goto out;
+	/* requested map types should be a subset of associated token's set */
+	if (token && !is_bit_subset_of(attr->token_create.allowed_map_types,
+				       token->allowed_map_types))
+		goto out;
 
 	new_token = bpf_token_alloc();
 	if (!new_token) {
@@ -118,6 +122,7 @@ int bpf_token_create(union bpf_attr *attr)
 	}
 
 	new_token->allowed_cmds = attr->token_create.allowed_cmds;
+	new_token->allowed_map_types = attr->token_create.allowed_map_types;
 
 	ret = bpf_obj_pin_any(attr->token_create.pin_path_fd,
 			      u64_to_user_ptr(attr->token_create.pin_pathname),
@@ -165,3 +170,11 @@ 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_map_types & (1ULL << type);
+}
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 3c201cfe6d5c..81c88edceac5 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -962,6 +962,7 @@ 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
@@ -1367,6 +1368,7 @@ union bpf_attr {
 		 * to using 5 hash functions).
 		 */
 		__u64	map_extra;
+		__u32	map_token_fd;
 	};
 
 	struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@@ -1657,6 +1659,10 @@ union bpf_attr {
 		 * programs
 		 */
 		__u64		allowed_cmds;
+		/* similarly to allowed_cmds, a bit set of BPF map types that
+		 * are allowed to be created by requested BPF token;
+		 */
+		__u64		allowed_map_types;
 	} token_create;
 
 } __attribute__((aligned(8)));
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 efb8bd43653c..e677c0435cec 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