272 lines · plain
1.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)2 3================4bpftool-map5================6-------------------------------------------------------------------------------7tool for inspection and simple manipulation of eBPF maps8-------------------------------------------------------------------------------9 10:Manual section: 811 12.. include:: substitutions.rst13 14SYNOPSIS15========16 17**bpftool** [*OPTIONS*] **map** *COMMAND*18 19*OPTIONS* := { |COMMON_OPTIONS| | { **-f** | **--bpffs** } | { **-n** | **--nomount** } }20 21*COMMANDS* :=22{ **show** | **list** | **create** | **dump** | **update** | **lookup** | **getnext** |23**delete** | **pin** | **help** }24 25MAP COMMANDS26=============27 28| **bpftool** **map** { **show** | **list** } [*MAP*]29| **bpftool** **map create** *FILE* **type** *TYPE* **key** *KEY_SIZE* **value** *VALUE_SIZE* \30| **entries** *MAX_ENTRIES* **name** *NAME* [**flags** *FLAGS*] [**inner_map** *MAP*] \31| [**offload_dev** *NAME*]32| **bpftool** **map dump** *MAP*33| **bpftool** **map update** *MAP* [**key** *DATA*] [**value** *VALUE*] [*UPDATE_FLAGS*]34| **bpftool** **map lookup** *MAP* [**key** *DATA*]35| **bpftool** **map getnext** *MAP* [**key** *DATA*]36| **bpftool** **map delete** *MAP* **key** *DATA*37| **bpftool** **map pin** *MAP* *FILE*38| **bpftool** **map event_pipe** *MAP* [**cpu** *N* **index** *M*]39| **bpftool** **map peek** *MAP*40| **bpftool** **map push** *MAP* **value** *VALUE*41| **bpftool** **map pop** *MAP*42| **bpftool** **map enqueue** *MAP* **value** *VALUE*43| **bpftool** **map dequeue** *MAP*44| **bpftool** **map freeze** *MAP*45| **bpftool** **map help**46|47| *MAP* := { **id** *MAP_ID* | **pinned** *FILE* | **name** *MAP_NAME* }48| *DATA* := { [**hex**] *BYTES* }49| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* | **name** *PROG_NAME* }50| *VALUE* := { *DATA* | *MAP* | *PROG* }51| *UPDATE_FLAGS* := { **any** | **exist** | **noexist** }52| *TYPE* := { **hash** | **array** | **prog_array** | **perf_event_array** | **percpu_hash**53| | **percpu_array** | **stack_trace** | **cgroup_array** | **lru_hash**54| | **lru_percpu_hash** | **lpm_trie** | **array_of_maps** | **hash_of_maps**55| | **devmap** | **devmap_hash** | **sockmap** | **cpumap** | **xskmap** | **sockhash**56| | **cgroup_storage** | **reuseport_sockarray** | **percpu_cgroup_storage**57| | **queue** | **stack** | **sk_storage** | **struct_ops** | **ringbuf** | **inode_storage**58| | **task_storage** | **bloom_filter** | **user_ringbuf** | **cgrp_storage** | **arena** }59 60DESCRIPTION61===========62bpftool map { show | list } [*MAP*]63 Show information about loaded maps. If *MAP* is specified show information64 only about given maps, otherwise list all maps currently loaded on the65 system. In case of **name**, *MAP* may match several maps which will all66 be shown.67 68 Output will start with map ID followed by map type and zero or more named69 attributes (depending on kernel version).70 71 Since Linux 5.8 bpftool is able to discover information about processes72 that hold open file descriptors (FDs) against BPF maps. On such kernels73 bpftool will automatically emit this information as well.74 75bpftool map create *FILE* type *TYPE* key *KEY_SIZE* value *VALUE_SIZE* entries *MAX_ENTRIES* name *NAME* [flags *FLAGS*] [inner_map *MAP*] [offload_dev *NAME*]76 Create a new map with given parameters and pin it to *bpffs* as *FILE*.77 78 *FLAGS* should be an integer which is the combination of desired flags,79 e.g. 1024 for **BPF_F_MMAPABLE** (see bpf.h UAPI header for existing80 flags).81 82 To create maps of type array-of-maps or hash-of-maps, the **inner_map**83 keyword must be used to pass an inner map. The kernel needs it to collect84 metadata related to the inner maps that the new map will work with.85 86 Keyword **offload_dev** expects a network interface name, and is used to87 request hardware offload for the map.88 89bpftool map dump *MAP*90 Dump all entries in a given *MAP*. In case of **name**, *MAP* may match91 several maps which will all be dumped.92 93bpftool map update *MAP* [key *DATA*] [value *VALUE*] [*UPDATE_FLAGS*]94 Update map entry for a given *KEY*.95 96 *UPDATE_FLAGS* can be one of: **any** update existing entry or add if97 doesn't exit; **exist** update only if entry already exists; **noexist**98 update only if entry doesn't exist.99 100 If the **hex** keyword is provided in front of the bytes sequence, the101 bytes are parsed as hexadecimal values, even if no "0x" prefix is added. If102 the keyword is not provided, then the bytes are parsed as decimal values,103 unless a "0x" prefix (for hexadecimal) or a "0" prefix (for octal) is104 provided.105 106bpftool map lookup *MAP* [key *DATA*]107 Lookup **key** in the map.108 109bpftool map getnext *MAP* [key *DATA*]110 Get next key. If *key* is not specified, get first key.111 112bpftool map delete *MAP* key *DATA*113 Remove entry from the map.114 115bpftool map pin *MAP* *FILE*116 Pin map *MAP* as *FILE*.117 118 Note: *FILE* must be located in *bpffs* mount. It must not contain a dot119 character ('.'), which is reserved for future extensions of *bpffs*.120 121bpftool 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 output of any125 **bpf_perf_event_output**\ () call in the kernel. By default read the126 number of CPUs on the system and install perf ring for each CPU in the127 corresponding index in the array.128 129 If **cpu** and **index** are specified, install perf ring for given **cpu**130 at **index** in the array (single ring).131 132 Note that installing a perf ring into an array will silently replace any133 existing ring. Any other application will stop receiving events if it134 installed its rings earlier.135 136bpftool map peek *MAP*137 Peek next value in the queue or stack.138 139bpftool map push *MAP* value *VALUE*140 Push *VALUE* onto the stack.141 142bpftool map pop *MAP*143 Pop and print value from the stack.144 145bpftool map enqueue *MAP* value *VALUE*146 Enqueue *VALUE* into the queue.147 148bpftool map dequeue *MAP*149 Dequeue and print value from the queue.150 151bpftool map freeze *MAP*152 Freeze the map as read-only from user space. Entries from a frozen map can153 not longer be updated or deleted with the **bpf**\ () system call. This154 operation is not reversible, and the map remains immutable from user space155 until its destruction. However, read and write permissions for BPF programs156 to the map remain unchanged.157 158bpftool map help159 Print short help message.160 161OPTIONS162=======163.. include:: common_options.rst164 165-f, --bpffs166 Show file names of pinned maps.167 168-n, --nomount169 Do not automatically attempt to mount any virtual file system (such as170 tracefs or BPF virtual file system) when necessary.171 172EXAMPLES173========174**# bpftool map show**175 176::177 178 10: hash name some_map flags 0x0179 key 4B value 8B max_entries 2048 memlock 167936B180 pids systemd(1)181 182The following three commands are equivalent:183 184|185| **# bpftool map update id 10 key hex 20 c4 b7 00 value hex 0f ff ff ab 01 02 03 4c**186| **# bpftool map update id 10 key 0x20 0xc4 0xb7 0x00 value 0x0f 0xff 0xff 0xab 0x01 0x02 0x03 0x4c**187| **# bpftool map update id 10 key 32 196 183 0 value 15 255 255 171 1 2 3 76**188 189**# bpftool map lookup id 10 key 0 1 2 3**190 191::192 193 key: 00 01 02 03 value: 00 01 02 03 04 05 06 07194 195 196**# bpftool map dump id 10**197 198::199 200 key: 00 01 02 03 value: 00 01 02 03 04 05 06 07201 key: 0d 00 07 00 value: 02 00 00 00 01 02 03 04202 Found 2 elements203 204**# bpftool map getnext id 10 key 0 1 2 3**205 206::207 208 key:209 00 01 02 03210 next key:211 0d 00 07 00212 213|214| **# mount -t bpf none /sys/fs/bpf/**215| **# bpftool map pin id 10 /sys/fs/bpf/map**216| **# bpftool map del pinned /sys/fs/bpf/map key 13 00 07 00**217 218Note that map update can also be used in order to change the program references219hold by a program array map. This can be used, for example, to change the220programs used for tail-call jumps at runtime, without having to reload the221entry-point program. Below is an example for this use case: we load a program222defining a prog array map, and with a main function that contains a tail call223to other programs that can be used either to "process" packets or to "debug"224processing. Note that the prog array map MUST be pinned into the BPF virtual225file system for the map update to work successfully, as kernel flushes prog226array maps when they have no more references from user space (and the update227would be lost as soon as bpftool exits).228 229|230| **# bpftool prog loadall tail_calls.o /sys/fs/bpf/foo type xdp**231| **# bpftool prog --bpffs**232 233::234 235 545: xdp name main_func tag 674b4b5597193dc3 gpl236 loaded_at 2018-12-12T15:02:58+0000 uid 0237 xlated 240B jited 257B memlock 4096B map_ids 294238 pinned /sys/fs/bpf/foo/xdp239 546: xdp name bpf_func_process tag e369a529024751fc gpl240 loaded_at 2018-12-12T15:02:58+0000 uid 0241 xlated 200B jited 164B memlock 4096B242 pinned /sys/fs/bpf/foo/process243 547: xdp name bpf_func_debug tag 0b597868bc7f0976 gpl244 loaded_at 2018-12-12T15:02:58+0000 uid 0245 xlated 200B jited 164B memlock 4096B246 pinned /sys/fs/bpf/foo/debug247 248**# bpftool map**249 250::251 252 294: prog_array name jmp_table flags 0x0253 key 4B value 4B max_entries 1 memlock 4096B254 owner_prog_type xdp owner jited255 256|257| **# bpftool map pin id 294 /sys/fs/bpf/bar**258| **# bpftool map dump pinned /sys/fs/bpf/bar**259 260::261 262 Found 0 elements263 264|265| **# bpftool map update pinned /sys/fs/bpf/bar key 0 0 0 0 value pinned /sys/fs/bpf/foo/debug**266| **# bpftool map dump pinned /sys/fs/bpf/bar**267 268::269 270 key: 00 00 00 00 value: 22 02 00 00271 Found 1 element272