170 lines · plain
1.. SPDX-License-Identifier: GPL-2.0-only2.. Copyright (C) 2020 Google LLC.3 4===========================5BPF_MAP_TYPE_CGROUP_STORAGE6===========================7 8The ``BPF_MAP_TYPE_CGROUP_STORAGE`` map type represents a local fix-sized9storage. It is only available with ``CONFIG_CGROUP_BPF``, and to programs that10attach to cgroups; the programs are made available by the same Kconfig. The11storage is identified by the cgroup the program is attached to.12 13The map provide a local storage at the cgroup that the BPF program is attached14to. It provides a faster and simpler access than the general purpose hash15table, which performs a hash table lookups, and requires user to track live16cgroups on their own.17 18This document describes the usage and semantics of the19``BPF_MAP_TYPE_CGROUP_STORAGE`` map type. Some of its behaviors was changed in20Linux 5.9 and this document will describe the differences.21 22Usage23=====24 25The map uses key of type of either ``__u64 cgroup_inode_id`` or26``struct bpf_cgroup_storage_key``, declared in ``linux/bpf.h``::27 28 struct bpf_cgroup_storage_key {29 __u64 cgroup_inode_id;30 __u32 attach_type;31 };32 33``cgroup_inode_id`` is the inode id of the cgroup directory.34``attach_type`` is the program's attach type.35 36Linux 5.9 added support for type ``__u64 cgroup_inode_id`` as the key type.37When this key type is used, then all attach types of the particular cgroup and38map will share the same storage. Otherwise, if the type is39``struct bpf_cgroup_storage_key``, then programs of different attach types40be isolated and see different storages.41 42To access the storage in a program, use ``bpf_get_local_storage``::43 44 void *bpf_get_local_storage(void *map, u64 flags)45 46``flags`` is reserved for future use and must be 0.47 48There is no implicit synchronization. Storages of ``BPF_MAP_TYPE_CGROUP_STORAGE``49can be accessed by multiple programs across different CPUs, and user should50take care of synchronization by themselves. The bpf infrastructure provides51``struct bpf_spin_lock`` to synchronize the storage. See52``tools/testing/selftests/bpf/progs/test_spin_lock.c``.53 54Examples55========56 57Usage with key type as ``struct bpf_cgroup_storage_key``::58 59 #include <bpf/bpf.h>60 61 struct {62 __uint(type, BPF_MAP_TYPE_CGROUP_STORAGE);63 __type(key, struct bpf_cgroup_storage_key);64 __type(value, __u32);65 } cgroup_storage SEC(".maps");66 67 int program(struct __sk_buff *skb)68 {69 __u32 *ptr = bpf_get_local_storage(&cgroup_storage, 0);70 __sync_fetch_and_add(ptr, 1);71 72 return 0;73 }74 75Userspace accessing map declared above::76 77 #include <linux/bpf.h>78 #include <linux/libbpf.h>79 80 __u32 map_lookup(struct bpf_map *map, __u64 cgrp, enum bpf_attach_type type)81 {82 struct bpf_cgroup_storage_key = {83 .cgroup_inode_id = cgrp,84 .attach_type = type,85 };86 __u32 value;87 bpf_map_lookup_elem(bpf_map__fd(map), &key, &value);88 // error checking omitted89 return value;90 }91 92Alternatively, using just ``__u64 cgroup_inode_id`` as key type::93 94 #include <bpf/bpf.h>95 96 struct {97 __uint(type, BPF_MAP_TYPE_CGROUP_STORAGE);98 __type(key, __u64);99 __type(value, __u32);100 } cgroup_storage SEC(".maps");101 102 int program(struct __sk_buff *skb)103 {104 __u32 *ptr = bpf_get_local_storage(&cgroup_storage, 0);105 __sync_fetch_and_add(ptr, 1);106 107 return 0;108 }109 110And userspace::111 112 #include <linux/bpf.h>113 #include <linux/libbpf.h>114 115 __u32 map_lookup(struct bpf_map *map, __u64 cgrp, enum bpf_attach_type type)116 {117 __u32 value;118 bpf_map_lookup_elem(bpf_map__fd(map), &cgrp, &value);119 // error checking omitted120 return value;121 }122 123Semantics124=========125 126``BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE`` is a variant of this map type. This127per-CPU variant will have different memory regions for each CPU for each128storage. The non-per-CPU will have the same memory region for each storage.129 130Prior to Linux 5.9, the lifetime of a storage is precisely per-attachment, and131for a single ``CGROUP_STORAGE`` map, there can be at most one program loaded132that uses the map. A program may be attached to multiple cgroups or have133multiple attach types, and each attach creates a fresh zeroed storage. The134storage is freed upon detach.135 136There is a one-to-one association between the map of each type (per-CPU and137non-per-CPU) and the BPF program during load verification time. As a result,138each map can only be used by one BPF program and each BPF program can only use139one storage map of each type. Because of map can only be used by one BPF140program, sharing of this cgroup's storage with other BPF programs were141impossible.142 143Since Linux 5.9, storage can be shared by multiple programs. When a program is144attached to a cgroup, the kernel would create a new storage only if the map145does not already contain an entry for the cgroup and attach type pair, or else146the old storage is reused for the new attachment. If the map is attach type147shared, then attach type is simply ignored during comparison. Storage is freed148only when either the map or the cgroup attached to is being freed. Detaching149will not directly free the storage, but it may cause the reference to the map150to reach zero and indirectly freeing all storage in the map.151 152The map is not associated with any BPF program, thus making sharing possible.153However, the BPF program can still only associate with one map of each type154(per-CPU and non-per-CPU). A BPF program cannot use more than one155``BPF_MAP_TYPE_CGROUP_STORAGE`` or more than one156``BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE``.157 158In all versions, userspace may use the attach parameters of cgroup and159attach type pair in ``struct bpf_cgroup_storage_key`` as the key to the BPF map160APIs to read or update the storage for a given attachment. For Linux 5.9161attach type shared storages, only the first value in the struct, cgroup inode162id, is used during comparison, so userspace may just specify a ``__u64``163directly.164 165The storage is bound at attach time. Even if the program is attached to parent166and triggers in child, the storage still belongs to the parent.167 168Userspace cannot create a new entry in the map or delete an existing entry.169Program test runs always use a temporary storage.170