bpf: introduce cgroup storage maps

This commit introduces BPF_MAP_TYPE_CGROUP_STORAGE maps:
a special type of maps which are implementing the cgroup storage.

>From the userspace point of view it's almost a generic
hash map with the (cgroup inode id, attachment type) pair
used as a key.

The only difference is that some operations are restricted:
  1) a user can't create new entries,
  2) a user can't remove existing entries.

The lookup from userspace is o(log(n)).

Signed-off-by: Roman Gushchin <[email protected]>
Cc: Alexei Starovoitov <[email protected]>
Cc: Daniel Borkmann <[email protected]>
Acked-by: Martin KaFai Lau <[email protected]>
Signed-off-by: Daniel Borkmann <[email protected]>

Author: rgushchin

include/linux/bpf-cgroup.h

@@ -4,19 +4,39 @@
 
 #include <linux/errno.h>
 #include <linux/jump_label.h>
+#include <linux/rbtree.h>
 #include <uapi/linux/bpf.h>
 
 struct sock;
 struct sockaddr;
 struct cgroup;
 struct sk_buff;
+struct bpf_map;
+struct bpf_prog;
 struct bpf_sock_ops_kern;
+struct bpf_cgroup_storage;
 
 #ifdef CONFIG_CGROUP_BPF
 
 extern struct static_key_false cgroup_bpf_enabled_key;
 #define cgroup_bpf_enabled static_branch_unlikely(&cgroup_bpf_enabled_key)
 
+struct bpf_cgroup_storage_map;
+
+struct bpf_storage_buffer {
+	struct rcu_head rcu;
+	char data[0];
+};
+
+struct bpf_cgroup_storage {
+	struct bpf_storage_buffer *buf;
+	struct bpf_cgroup_storage_map *map;
+	struct bpf_cgroup_storage_key key;
+	struct list_head list;
+	struct rb_node node;
+	struct rcu_head rcu;
+};
+
 struct bpf_prog_list {
 	struct list_head node;
 	struct bpf_prog *prog;
@@ -77,6 +97,15 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk,
 int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
 				      short access, enum bpf_attach_type type);
 
+struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog);
+void bpf_cgroup_storage_free(struct bpf_cgroup_storage *storage);
+void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage,
+			     struct cgroup *cgroup,
+			     enum bpf_attach_type type);
+void bpf_cgroup_storage_unlink(struct bpf_cgroup_storage *storage);
+int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *map);
+void bpf_cgroup_storage_release(struct bpf_prog *prog, struct bpf_map *map);
+
 /* Wrappers for __cgroup_bpf_run_filter_skb() guarded by cgroup_bpf_enabled. */
 #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb)			      \
 ({									      \
@@ -221,6 +250,15 @@ static inline int cgroup_bpf_prog_query(const union bpf_attr *attr,
 	return -EINVAL;
 }
 
+static inline int bpf_cgroup_storage_assign(struct bpf_prog *prog,
+					    struct bpf_map *map) { return 0; }
+static inline void bpf_cgroup_storage_release(struct bpf_prog *prog,
+					      struct bpf_map *map) {}
+static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(
+	struct bpf_prog *prog) { return 0; }
+static inline void bpf_cgroup_storage_free(
+	struct bpf_cgroup_storage *storage) {}
+
 #define cgroup_bpf_enabled (0)
 #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0)
 #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; })

include/linux/bpf.h

@@ -282,6 +282,7 @@ struct bpf_prog_aux {
 	struct bpf_prog *prog;
 	struct user_struct *user;
 	u64 load_time; /* ns since boottime */
+	struct bpf_map *cgroup_storage;
 	char name[BPF_OBJ_NAME_LEN];
 #ifdef CONFIG_SECURITY
 	void *security;

include/linux/bpf_types.h

@@ -37,6 +37,9 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_PERF_EVENT_ARRAY, perf_event_array_map_ops)
 #ifdef CONFIG_CGROUPS
 BPF_MAP_TYPE(BPF_MAP_TYPE_CGROUP_ARRAY, cgroup_array_map_ops)
 #endif
+#ifdef CONFIG_CGROUP_BPF
+BPF_MAP_TYPE(BPF_MAP_TYPE_CGROUP_STORAGE, cgroup_storage_map_ops)
+#endif
 BPF_MAP_TYPE(BPF_MAP_TYPE_HASH, htab_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_HASH, htab_percpu_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_LRU_HASH, htab_lru_map_ops)

include/uapi/linux/bpf.h

@@ -75,6 +75,11 @@ struct bpf_lpm_trie_key {
 	__u8	data[0];	/* Arbitrary size */
 };
 
+struct bpf_cgroup_storage_key {
+	__u64	cgroup_inode_id;	/* cgroup inode id */
+	__u32	attach_type;		/* program attach type */
+};
+
 /* BPF syscall commands, see bpf(2) man-page for details. */
 enum bpf_cmd {
 	BPF_MAP_CREATE,
@@ -120,6 +125,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_CPUMAP,
 	BPF_MAP_TYPE_XSKMAP,
 	BPF_MAP_TYPE_SOCKHASH,
+	BPF_MAP_TYPE_CGROUP_STORAGE,
 };
 
 enum bpf_prog_type {

kernel/bpf/Makefile

@@ -3,6 +3,7 @@ obj-y := core.o
 
 obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o
 obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
+obj-$(CONFIG_BPF_SYSCALL) += local_storage.o
 obj-$(CONFIG_BPF_SYSCALL) += disasm.o
 obj-$(CONFIG_BPF_SYSCALL) += btf.o
 ifeq ($(CONFIG_NET),y)