bpf: Implement exclusive map creation

Exclusive maps allow maps to only be accessed by program with a
program with a matching hash which is specified in the excl_prog_hash
attr.

For the signing use-case, this allows the trusted loader program
to load the map and verify the integrity

Signed-off-by: KP Singh <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Alexei Starovoitov <[email protected]>

Author: sinkap

include/linux/bpf.h

@@ -329,6 +329,7 @@ struct bpf_map {
 	atomic64_t sleepable_refcnt;
 	s64 __percpu *elem_count;
 	u64 cookie; /* write-once */
+	char *excl_prog_sha;
 };
 
 static inline const char *btf_field_type_name(enum btf_field_type type)

include/uapi/linux/bpf.h

@@ -1522,6 +1522,12 @@ union bpf_attr {
 		 * If provided, map_flags should have BPF_F_TOKEN_FD flag set.
 		 */
 		__s32	map_token_fd;
+
+		/* Hash of the program that has exclusive access to the map.
+		 */
+		__aligned_u64 excl_prog_hash;
+		/* Size of the passed excl_prog_hash. */
+		__u32 excl_prog_hash_size;
 	};
 
 	struct { /* anonymous struct used by BPF_MAP_*_ELEM and BPF_MAP_FREEZE commands */

kernel/bpf/syscall.c

@@ -860,6 +860,7 @@ static void bpf_map_free(struct bpf_map *map)
 	 * the free of values or special fields allocated from bpf memory
 	 * allocator.
 	 */
+	kfree(map->excl_prog_sha);
 	migrate_disable();
 	map->ops->map_free(map);
 	migrate_enable();
@@ -1338,9 +1339,9 @@ static bool bpf_net_capable(void)
 	return capable(CAP_NET_ADMIN) || capable(CAP_SYS_ADMIN);
 }
 
-#define BPF_MAP_CREATE_LAST_FIELD map_token_fd
+#define BPF_MAP_CREATE_LAST_FIELD excl_prog_hash_size
 /* called via syscall */
-static int map_create(union bpf_attr *attr, bool kernel)
+static int map_create(union bpf_attr *attr, bpfptr_t uattr)
 {
 	const struct bpf_map_ops *ops;
 	struct bpf_token *token = NULL;
@@ -1534,7 +1535,29 @@ static int map_create(union bpf_attr *attr, bool kernel)
 			attr->btf_vmlinux_value_type_id;
 	}
 
-	err = security_bpf_map_create(map, attr, token, kernel);
+	if (attr->excl_prog_hash) {
+		bpfptr_t uprog_hash = make_bpfptr(attr->excl_prog_hash, uattr.is_kernel);
+
+		if (attr->excl_prog_hash_size != SHA256_DIGEST_SIZE) {
+			err = -EINVAL;
+			goto free_map;
+		}
+
+		map->excl_prog_sha = kzalloc(SHA256_DIGEST_SIZE, GFP_KERNEL);
+		if (!map->excl_prog_sha) {
+			err = -ENOMEM;
+			goto free_map;
+		}
+
+		if (copy_from_bpfptr(map->excl_prog_sha, uprog_hash, SHA256_DIGEST_SIZE)) {
+			err = -EFAULT;
+			goto free_map;
+		}
+	} else if (attr->excl_prog_hash_size) {
+		return -EINVAL;
+	}
+
+	err = security_bpf_map_create(map, attr, token, uattr.is_kernel);
 	if (err)
 		goto free_map_sec;
 
@@ -6008,7 +6031,7 @@ static int __sys_bpf(enum bpf_cmd cmd, bpfptr_t uattr, unsigned int size)
 
 	switch (cmd) {
 	case BPF_MAP_CREATE:
-		err = map_create(&attr, uattr.is_kernel);
+		err = map_create(&attr, uattr);
 		break;
 	case BPF_MAP_LOOKUP_ELEM:
 		err = map_lookup_elem(&attr);

kernel/bpf/verifier.c

@@ -20407,6 +20407,12 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env,
 {
 	enum bpf_prog_type prog_type = resolve_prog_type(prog);
 
+	if (map->excl_prog_sha &&
+	    memcmp(map->excl_prog_sha, prog->digest, SHA256_DIGEST_SIZE)) {
+		verbose(env, "program's hash doesn't match map's excl_prog_hash\n");
+		return -EACCES;
+	}
+
 	if (btf_record_has_field(map->record, BPF_LIST_HEAD) ||
 	    btf_record_has_field(map->record, BPF_RB_ROOT)) {
 		if (is_tracing_prog_type(prog_type)) {

tools/include/uapi/linux/bpf.h

@@ -1522,6 +1522,12 @@ union bpf_attr {
 		 * If provided, map_flags should have BPF_F_TOKEN_FD flag set.
 		 */
 		__s32	map_token_fd;
+
+		/* Hash of the program that has exclusive access to the map.
+		 */
+		__aligned_u64 excl_prog_hash;
+		/* Size of the passed excl_prog_hash. */
+		__u32 excl_prog_hash_size;
 	};
 
 	struct { /* anonymous struct used by BPF_MAP_*_ELEM and BPF_MAP_FREEZE commands */