1================ 2bpftool-map 3================ 4------------------------------------------------------------------------------- 5tool for inspection and simple manipulation of eBPF maps 6------------------------------------------------------------------------------- 7 8:Manual section: 8 9 10SYNOPSIS 11======== 12 13 **bpftool** [*OPTIONS*] **map** *COMMAND* 14 15 *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-f** | **--bpffs** } } 16 17 *COMMANDS* := 18 { **show** | **list** | **create** | **dump** | **update** | **lookup** | **getnext** 19 | **delete** | **pin** | **help** } 20 21MAP COMMANDS 22============= 23 24| **bpftool** **map** { **show** | **list** } [*MAP*] 25| **bpftool** **map create** *FILE* **type** *TYPE* **key** *KEY_SIZE* **value** *VALUE_SIZE* \ 26| **entries** *MAX_ENTRIES* **name** *NAME* [**flags** *FLAGS*] [**inner_map** *MAP*] \ 27| [**dev** *NAME*] 28| **bpftool** **map dump** *MAP* 29| **bpftool** **map update** *MAP* [**key** *DATA*] [**value** *VALUE*] [*UPDATE_FLAGS*] 30| **bpftool** **map lookup** *MAP* [**key** *DATA*] 31| **bpftool** **map getnext** *MAP* [**key** *DATA*] 32| **bpftool** **map delete** *MAP* **key** *DATA* 33| **bpftool** **map pin** *MAP* *FILE* 34| **bpftool** **map event_pipe** *MAP* [**cpu** *N* **index** *M*] 35| **bpftool** **map peek** *MAP* 36| **bpftool** **map push** *MAP* **value** *VALUE* 37| **bpftool** **map pop** *MAP* 38| **bpftool** **map enqueue** *MAP* **value** *VALUE* 39| **bpftool** **map dequeue** *MAP* 40| **bpftool** **map freeze** *MAP* 41| **bpftool** **map help** 42| 43| *MAP* := { **id** *MAP_ID* | **pinned** *FILE* | **name** *MAP_NAME* } 44| *DATA* := { [**hex**] *BYTES* } 45| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* | **name** *PROG_NAME* } 46| *VALUE* := { *DATA* | *MAP* | *PROG* } 47| *UPDATE_FLAGS* := { **any** | **exist** | **noexist** } 48| *TYPE* := { **hash** | **array** | **prog_array** | **perf_event_array** | **percpu_hash** 49| | **percpu_array** | **stack_trace** | **cgroup_array** | **lru_hash** 50| | **lru_percpu_hash** | **lpm_trie** | **array_of_maps** | **hash_of_maps** 51| | **devmap** | **devmap_hash** | **sockmap** | **cpumap** | **xskmap** | **sockhash** 52| | **cgroup_storage** | **reuseport_sockarray** | **percpu_cgroup_storage** 53| | **queue** | **stack** | **sk_storage** | **struct_ops** | **ringbuf** | **inode_storage** 54 | **task_storage** } 55 56DESCRIPTION 57=========== 58 **bpftool map { show | list }** [*MAP*] 59 Show information about loaded maps. If *MAP* is specified 60 show information only about given maps, otherwise list all 61 maps currently loaded on the system. In case of **name**, 62 *MAP* may match several maps which will all be shown. 63 64 Output will start with map ID followed by map type and 65 zero or more named attributes (depending on kernel version). 66 67 Since Linux 5.8 bpftool is able to discover information about 68 processes that hold open file descriptors (FDs) against BPF 69 maps. On such kernels bpftool will automatically emit this 70 information as well. 71 72 **bpftool map create** *FILE* **type** *TYPE* **key** *KEY_SIZE* **value** *VALUE_SIZE* **entries** *MAX_ENTRIES* **name** *NAME* [**flags** *FLAGS*] [**inner_map** *MAP*] [**dev** *NAME*] 73 Create a new map with given parameters and pin it to *bpffs* 74 as *FILE*. 75 76 *FLAGS* should be an integer which is the combination of 77 desired flags, e.g. 1024 for **BPF_F_MMAPABLE** (see bpf.h 78 UAPI header for existing flags). 79 80 To create maps of type array-of-maps or hash-of-maps, the 81 **inner_map** keyword must be used to pass an inner map. The 82 kernel needs it to collect metadata related to the inner maps 83 that the new map will work with. 84 85 Keyword **dev** expects a network interface name, and is used 86 to request hardware offload for the map. 87 88 **bpftool map dump** *MAP* 89 Dump all entries in a given *MAP*. In case of **name**, 90 *MAP* may match several maps which will all be dumped. 91 92 **bpftool map update** *MAP* [**key** *DATA*] [**value** *VALUE*] [*UPDATE_FLAGS*] 93 Update map entry for a given *KEY*. 94 95 *UPDATE_FLAGS* can be one of: **any** update existing entry 96 or add if doesn't exit; **exist** update only if entry already 97 exists; **noexist** update only if entry doesn't exist. 98 99 If the **hex** keyword is provided in front of the bytes 100 sequence, the bytes are parsed as hexadecimal values, even if 101 no "0x" prefix is added. If the keyword is not provided, then 102 the bytes are parsed as decimal values, unless a "0x" prefix 103 (for hexadecimal) or a "0" prefix (for octal) is provided. 104 105 **bpftool map lookup** *MAP* [**key** *DATA*] 106 Lookup **key** in the map. 107 108 **bpftool map getnext** *MAP* [**key** *DATA*] 109 Get next key. If *key* is not specified, get first key. 110 111 **bpftool map delete** *MAP* **key** *DATA* 112 Remove entry from the map. 113 114 **bpftool map pin** *MAP* *FILE* 115 Pin map *MAP* as *FILE*. 116 117 Note: *FILE* must be located in *bpffs* mount. It must not 118 contain a dot character ('.'), which is reserved for future 119 extensions of *bpffs*. 120 121 **bpftool** **map event_pipe** *MAP* [**cpu** *N* **index** *M*] 122 Read events from a **BPF_MAP_TYPE_PERF_EVENT_ARRAY** map. 123 124 Install perf rings into a perf event array map and dump 125 output of any **bpf_perf_event_output**\ () call in the kernel. 126 By default read the number of CPUs on the system and 127 install perf ring for each CPU in the corresponding index 128 in the array. 129 130 If **cpu** and **index** are specified, install perf ring 131 for given **cpu** at **index** in the array (single ring). 132 133 Note that installing a perf ring into an array will silently 134 replace any existing ring. Any other application will stop 135 receiving events if it installed its rings earlier. 136 137 **bpftool map peek** *MAP* 138 Peek next value in the queue or stack. 139 140 **bpftool map push** *MAP* **value** *VALUE* 141 Push *VALUE* onto the stack. 142 143 **bpftool map pop** *MAP* 144 Pop and print value from the stack. 145 146 **bpftool map enqueue** *MAP* **value** *VALUE* 147 Enqueue *VALUE* into the queue. 148 149 **bpftool map dequeue** *MAP* 150 Dequeue and print value from the queue. 151 152 **bpftool map freeze** *MAP* 153 Freeze the map as read-only from user space. Entries from a 154 frozen map can not longer be updated or deleted with the 155 **bpf**\ () system call. This operation is not reversible, 156 and the map remains immutable from user space until its 157 destruction. However, read and write permissions for BPF 158 programs to the map remain unchanged. 159 160 **bpftool map help** 161 Print short help message. 162 163OPTIONS 164======= 165 .. include:: common_options.rst 166 167 -f, --bpffs 168 Show file names of pinned maps. 169 170 -n, --nomount 171 Do not automatically attempt to mount any virtual file system 172 (such as tracefs or BPF virtual file system) when necessary. 173 174EXAMPLES 175======== 176**# bpftool map show** 177 178:: 179 180 10: hash name some_map flags 0x0 181 key 4B value 8B max_entries 2048 memlock 167936B 182 pids systemd(1) 183 184The following three commands are equivalent: 185 186| 187| **# bpftool map update id 10 key hex 20 c4 b7 00 value hex 0f ff ff ab 01 02 03 4c** 188| **# bpftool map update id 10 key 0x20 0xc4 0xb7 0x00 value 0x0f 0xff 0xff 0xab 0x01 0x02 0x03 0x4c** 189| **# bpftool map update id 10 key 32 196 183 0 value 15 255 255 171 1 2 3 76** 190 191**# bpftool map lookup id 10 key 0 1 2 3** 192 193:: 194 195 key: 00 01 02 03 value: 00 01 02 03 04 05 06 07 196 197 198**# bpftool map dump id 10** 199 200:: 201 202 key: 00 01 02 03 value: 00 01 02 03 04 05 06 07 203 key: 0d 00 07 00 value: 02 00 00 00 01 02 03 04 204 Found 2 elements 205 206**# bpftool map getnext id 10 key 0 1 2 3** 207 208:: 209 210 key: 211 00 01 02 03 212 next key: 213 0d 00 07 00 214 215| 216| **# mount -t bpf none /sys/fs/bpf/** 217| **# bpftool map pin id 10 /sys/fs/bpf/map** 218| **# bpftool map del pinned /sys/fs/bpf/map key 13 00 07 00** 219 220Note that map update can also be used in order to change the program references 221hold by a program array map. This can be used, for example, to change the 222programs used for tail-call jumps at runtime, without having to reload the 223entry-point program. Below is an example for this use case: we load a program 224defining a prog array map, and with a main function that contains a tail call 225to other programs that can be used either to "process" packets or to "debug" 226processing. Note that the prog array map MUST be pinned into the BPF virtual 227file system for the map update to work successfully, as kernel flushes prog 228array maps when they have no more references from user space (and the update 229would be lost as soon as bpftool exits). 230 231| 232| **# bpftool prog loadall tail_calls.o /sys/fs/bpf/foo type xdp** 233| **# bpftool prog --bpffs** 234 235:: 236 237 545: xdp name main_func tag 674b4b5597193dc3 gpl 238 loaded_at 2018-12-12T15:02:58+0000 uid 0 239 xlated 240B jited 257B memlock 4096B map_ids 294 240 pinned /sys/fs/bpf/foo/xdp 241 546: xdp name bpf_func_process tag e369a529024751fc gpl 242 loaded_at 2018-12-12T15:02:58+0000 uid 0 243 xlated 200B jited 164B memlock 4096B 244 pinned /sys/fs/bpf/foo/process 245 547: xdp name bpf_func_debug tag 0b597868bc7f0976 gpl 246 loaded_at 2018-12-12T15:02:58+0000 uid 0 247 xlated 200B jited 164B memlock 4096B 248 pinned /sys/fs/bpf/foo/debug 249 250**# bpftool map** 251 252:: 253 254 294: prog_array name jmp_table flags 0x0 255 key 4B value 4B max_entries 1 memlock 4096B 256 owner_prog_type xdp owner jited 257 258| 259| **# bpftool map pin id 294 /sys/fs/bpf/bar** 260| **# bpftool map dump pinned /sys/fs/bpf/bar** 261 262:: 263 264 Found 0 elements 265 266| 267| **# bpftool map update pinned /sys/fs/bpf/bar key 0 0 0 0 value pinned /sys/fs/bpf/foo/debug** 268| **# bpftool map dump pinned /sys/fs/bpf/bar** 269 270:: 271 272 key: 00 00 00 00 value: 22 02 00 00 273 Found 1 element 274