diff options
Diffstat (limited to 'tools/bpf/bpftool')
28 files changed, 2652 insertions, 429 deletions
diff --git a/tools/bpf/bpftool/.gitignore b/tools/bpf/bpftool/.gitignore index 67167e44b726..b13926432b84 100644 --- a/tools/bpf/bpftool/.gitignore +++ b/tools/bpf/bpftool/.gitignore @@ -1,5 +1,7 @@ *.d -bpftool +/bpftool bpftool*.8 bpf-helpers.* FEATURE-DUMP.bpftool +feature +libbpf diff --git a/tools/bpf/bpftool/Documentation/Makefile b/tools/bpf/bpftool/Documentation/Makefile index f7663a3e60c9..815ac9804aee 100644 --- a/tools/bpf/bpftool/Documentation/Makefile +++ b/tools/bpf/bpftool/Documentation/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only include ../../../scripts/Makefile.include include ../../../scripts/utilities.mak diff --git a/tools/bpf/bpftool/Documentation/bpftool-btf.rst b/tools/bpf/bpftool/Documentation/bpftool-btf.rst new file mode 100644 index 000000000000..39615f8e145b --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-btf.rst @@ -0,0 +1,238 @@ +================ +bpftool-btf +================ +------------------------------------------------------------------------------- +tool for inspection of BTF data +------------------------------------------------------------------------------- + +:Manual section: 8 + +SYNOPSIS +======== + + **bpftool** [*OPTIONS*] **btf** *COMMAND* + + *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] } + + *COMMANDS* := { **dump** | **help** } + +BTF COMMANDS +============= + +| **bpftool** **btf** { **show** | **list** } [**id** *BTF_ID*] +| **bpftool** **btf dump** *BTF_SRC* [**format** *FORMAT*] +| **bpftool** **btf help** +| +| *BTF_SRC* := { **id** *BTF_ID* | **prog** *PROG* | **map** *MAP* [{**key** | **value** | **kv** | **all**}] | **file** *FILE* } +| *FORMAT* := { **raw** | **c** } +| *MAP* := { **id** *MAP_ID* | **pinned** *FILE* } +| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* } + +DESCRIPTION +=========== + **bpftool btf { show | list }** [**id** *BTF_ID*] + Show information about loaded BTF objects. If a BTF ID is + specified, show information only about given BTF object, + otherwise list all BTF objects currently loaded on the + system. + + **bpftool btf dump** *BTF_SRC* + Dump BTF entries from a given *BTF_SRC*. + + When **id** is specified, BTF object with that ID will be + loaded and all its BTF types emitted. + + When **map** is provided, it's expected that map has + associated BTF object with BTF types describing key and + value. It's possible to select whether to dump only BTF + type(s) associated with key (**key**), value (**value**), + both key and value (**kv**), or all BTF types present in + associated BTF object (**all**). If not specified, **kv** + is assumed. + + When **prog** is provided, it's expected that program has + associated BTF object with BTF types. + + When specifying *FILE*, an ELF file is expected, containing + .BTF section with well-defined BTF binary format data, + typically produced by clang or pahole. + + **format** option can be used to override default (raw) + output format. Raw (**raw**) or C-syntax (**c**) output + formats are supported. + + **bpftool btf help** + Print short help message. + +OPTIONS +======= + -h, --help + Print short generic help message (similar to **bpftool help**). + + -V, --version + Print version number (similar to **bpftool version**). + + -j, --json + Generate JSON output. For commands that cannot produce JSON, this + option has no effect. + + -p, --pretty + Generate human-readable JSON output. Implies **-j**. + + -d, --debug + Print all logs available from libbpf, including debug-level + information. + +EXAMPLES +======== +**# bpftool btf dump id 1226** +:: + + [1] PTR '(anon)' type_id=2 + [2] STRUCT 'dummy_tracepoint_args' size=16 vlen=2 + 'pad' type_id=3 bits_offset=0 + 'sock' type_id=4 bits_offset=64 + [3] INT 'long long unsigned int' size=8 bits_offset=0 nr_bits=64 encoding=(none) + [4] PTR '(anon)' type_id=5 + [5] FWD 'sock' fwd_kind=union + +This gives an example of default output for all supported BTF kinds. + +**$ cat prog.c** +:: + + struct fwd_struct; + + enum my_enum { + VAL1 = 3, + VAL2 = 7, + }; + + typedef struct my_struct my_struct_t; + + struct my_struct { + const unsigned int const_int_field; + int bitfield_field: 4; + char arr_field[16]; + const struct fwd_struct *restrict fwd_field; + enum my_enum enum_field; + volatile my_struct_t *typedef_ptr_field; + }; + + union my_union { + int a; + struct my_struct b; + }; + + struct my_struct struct_global_var __attribute__((section("data_sec"))) = { + .bitfield_field = 3, + .enum_field = VAL1, + }; + int global_var __attribute__((section("data_sec"))) = 7; + + __attribute__((noinline)) + int my_func(union my_union *arg1, int arg2) + { + static int static_var __attribute__((section("data_sec"))) = 123; + static_var++; + return static_var; + } + +**$ bpftool btf dump file prog.o** +:: + + [1] PTR '(anon)' type_id=2 + [2] UNION 'my_union' size=48 vlen=2 + 'a' type_id=3 bits_offset=0 + 'b' type_id=4 bits_offset=0 + [3] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED + [4] STRUCT 'my_struct' size=48 vlen=6 + 'const_int_field' type_id=5 bits_offset=0 + 'bitfield_field' type_id=3 bits_offset=32 bitfield_size=4 + 'arr_field' type_id=8 bits_offset=40 + 'fwd_field' type_id=10 bits_offset=192 + 'enum_field' type_id=14 bits_offset=256 + 'typedef_ptr_field' type_id=15 bits_offset=320 + [5] CONST '(anon)' type_id=6 + [6] INT 'unsigned int' size=4 bits_offset=0 nr_bits=32 encoding=(none) + [7] INT 'char' size=1 bits_offset=0 nr_bits=8 encoding=SIGNED + [8] ARRAY '(anon)' type_id=7 index_type_id=9 nr_elems=16 + [9] INT '__ARRAY_SIZE_TYPE__' size=4 bits_offset=0 nr_bits=32 encoding=(none) + [10] RESTRICT '(anon)' type_id=11 + [11] PTR '(anon)' type_id=12 + [12] CONST '(anon)' type_id=13 + [13] FWD 'fwd_struct' fwd_kind=union + [14] ENUM 'my_enum' size=4 vlen=2 + 'VAL1' val=3 + 'VAL2' val=7 + [15] PTR '(anon)' type_id=16 + [16] VOLATILE '(anon)' type_id=17 + [17] TYPEDEF 'my_struct_t' type_id=4 + [18] FUNC_PROTO '(anon)' ret_type_id=3 vlen=2 + 'arg1' type_id=1 + 'arg2' type_id=3 + [19] FUNC 'my_func' type_id=18 + [20] VAR 'struct_global_var' type_id=4, linkage=global-alloc + [21] VAR 'global_var' type_id=3, linkage=global-alloc + [22] VAR 'my_func.static_var' type_id=3, linkage=static + [23] DATASEC 'data_sec' size=0 vlen=3 + type_id=20 offset=0 size=48 + type_id=21 offset=0 size=4 + type_id=22 offset=52 size=4 + +The following commands print BTF types associated with specified map's key, +value, both key and value, and all BTF types, respectively. By default, both +key and value types will be printed. + +**# bpftool btf dump map id 123 key** + +:: + + [39] TYPEDEF 'u32' type_id=37 + +**# bpftool btf dump map id 123 value** + +:: + + [86] PTR '(anon)' type_id=87 + +**# bpftool btf dump map id 123 kv** + +:: + + [39] TYPEDEF 'u32' type_id=37 + [86] PTR '(anon)' type_id=87 + +**# bpftool btf dump map id 123 all** + +:: + + [1] PTR '(anon)' type_id=0 + . + . + . + [2866] ARRAY '(anon)' type_id=52 index_type_id=51 nr_elems=4 + +All the standard ways to specify map or program are supported: + +**# bpftool btf dump map id 123** + +**# bpftool btf dump map pinned /sys/fs/bpf/map_name** + +**# bpftool btf dump prog id 456** + +**# bpftool btf dump prog tag b88e0a09b1d9759d** + +**# bpftool btf dump prog pinned /sys/fs/bpf/prog_name** + +SEE ALSO +======== + **bpf**\ (2), + **bpf-helpers**\ (7), + **bpftool**\ (8), + **bpftool-map**\ (8), + **bpftool-prog**\ (8), + **bpftool-cgroup**\ (8), + **bpftool-feature**\ (8), + **bpftool-net**\ (8), + **bpftool-perf**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst index 9bb9ace54ba8..06a28b07787d 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst @@ -20,8 +20,8 @@ SYNOPSIS CGROUP COMMANDS =============== -| **bpftool** **cgroup { show | list }** *CGROUP* -| **bpftool** **cgroup tree** [*CGROUP_ROOT*] +| **bpftool** **cgroup { show | list }** *CGROUP* [**effective**] +| **bpftool** **cgroup tree** [*CGROUP_ROOT*] [**effective**] | **bpftool** **cgroup attach** *CGROUP* *ATTACH_TYPE* *PROG* [*ATTACH_FLAGS*] | **bpftool** **cgroup detach** *CGROUP* *ATTACH_TYPE* *PROG* | **bpftool** **cgroup help** @@ -29,18 +29,23 @@ CGROUP COMMANDS | *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* } | *ATTACH_TYPE* := { **ingress** | **egress** | **sock_create** | **sock_ops** | **device** | | **bind4** | **bind6** | **post_bind4** | **post_bind6** | **connect4** | **connect6** | -| **sendmsg4** | **sendmsg6** } +| **sendmsg4** | **sendmsg6** | **recvmsg4** | **recvmsg6** | **sysctl** | +| **getsockopt** | **setsockopt** } | *ATTACH_FLAGS* := { **multi** | **override** } DESCRIPTION =========== - **bpftool cgroup { show | list }** *CGROUP* + **bpftool cgroup { show | list }** *CGROUP* [**effective**] List all programs attached to the cgroup *CGROUP*. Output will start with program ID followed by attach type, attach flags and program name. - **bpftool cgroup tree** [*CGROUP_ROOT*] + If **effective** is specified retrieve effective programs that + will execute for events within a cgroup. This includes + inherited along with attached ones. + + **bpftool cgroup tree** [*CGROUP_ROOT*] [**effective**] Iterate over all cgroups in *CGROUP_ROOT* and list all attached programs. If *CGROUP_ROOT* is not specified, bpftool uses cgroup v2 mountpoint. @@ -49,6 +54,10 @@ DESCRIPTION commands: it starts with absolute cgroup path, followed by program ID, attach type, attach flags and program name. + If **effective** is specified retrieve effective programs that + will execute for events within a cgroup. This includes + inherited along with attached ones. + **bpftool cgroup attach** *CGROUP* *ATTACH_TYPE* *PROG* [*ATTACH_FLAGS*] Attach program *PROG* to the cgroup *CGROUP* with attach type *ATTACH_TYPE* and optional *ATTACH_FLAGS*. @@ -85,7 +94,14 @@ DESCRIPTION **sendmsg4** call to sendto(2), sendmsg(2), sendmmsg(2) for an unconnected udp4 socket (since 4.18); **sendmsg6** call to sendto(2), sendmsg(2), sendmmsg(2) for an - unconnected udp6 socket (since 4.18). + unconnected udp6 socket (since 4.18); + **recvmsg4** call to recvfrom(2), recvmsg(2), recvmmsg(2) for + an unconnected udp4 socket (since 5.2); + **recvmsg6** call to recvfrom(2), recvmsg(2), recvmmsg(2) for + an unconnected udp6 socket (since 5.2); + **sysctl** sysctl access (since 5.2); + **getsockopt** call to getsockopt (since 5.3); + **setsockopt** call to setsockopt (since 5.3). **bpftool cgroup detach** *CGROUP* *ATTACH_TYPE* *PROG* Detach *PROG* from the cgroup *CGROUP* and attach type @@ -99,7 +115,7 @@ OPTIONS -h, --help Print short generic help message (similar to **bpftool help**). - -v, --version + -V, --version Print version number (similar to **bpftool version**). -j, --json @@ -112,6 +128,10 @@ OPTIONS -f, --bpffs Show file names of pinned programs. + -d, --debug + Print all logs available from libbpf, including debug-level + information. + EXAMPLES ======== | @@ -144,4 +164,5 @@ SEE ALSO **bpftool-map**\ (8), **bpftool-feature**\ (8), **bpftool-net**\ (8), - **bpftool-perf**\ (8) + **bpftool-perf**\ (8), + **bpftool-btf**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-feature.rst b/tools/bpf/bpftool/Documentation/bpftool-feature.rst index 82de03dd8f52..4d08f35034a2 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-feature.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-feature.rst @@ -63,7 +63,7 @@ OPTIONS -h, --help Print short generic help message (similar to **bpftool help**). - -v, --version + -V, --version Print version number (similar to **bpftool version**). -j, --json @@ -73,6 +73,10 @@ OPTIONS -p, --pretty Generate human-readable JSON output. Implies **-j**. + -d, --debug + Print all logs available from libbpf, including debug-level + information. + SEE ALSO ======== **bpf**\ (2), @@ -82,4 +86,5 @@ SEE ALSO **bpftool-map**\ (8), **bpftool-cgroup**\ (8), **bpftool-net**\ (8), - **bpftool-perf**\ (8) + **bpftool-perf**\ (8), + **bpftool-btf**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst index 5c984ffc9f01..1c0f7146aab0 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-map.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst @@ -36,6 +36,7 @@ MAP COMMANDS | **bpftool** **map pop** *MAP* | **bpftool** **map enqueue** *MAP* **value** *VALUE* | **bpftool** **map dequeue** *MAP* +| **bpftool** **map freeze** *MAP* | **bpftool** **map help** | | *MAP* := { **id** *MAP_ID* | **pinned** *FILE* } @@ -46,7 +47,7 @@ MAP COMMANDS | *TYPE* := { **hash** | **array** | **prog_array** | **perf_event_array** | **percpu_hash** | | **percpu_array** | **stack_trace** | **cgroup_array** | **lru_hash** | | **lru_percpu_hash** | **lpm_trie** | **array_of_maps** | **hash_of_maps** -| | **devmap** | **sockmap** | **cpumap** | **xskmap** | **sockhash** +| | **devmap** | **devmap_hash** | **sockmap** | **cpumap** | **xskmap** | **sockhash** | | **cgroup_storage** | **reuseport_sockarray** | **percpu_cgroup_storage** | | **queue** | **stack** } @@ -127,6 +128,14 @@ DESCRIPTION **bpftool map dequeue** *MAP* Dequeue and print **value** from the queue. + **bpftool map freeze** *MAP* + Freeze the map as read-only from user space. Entries from a + frozen map can not longer be updated or deleted with the + **bpf\ ()** system call. This operation is not reversible, + and the map remains immutable from user space until its + destruction. However, read and write permissions for BPF + programs to the map remain unchanged. + **bpftool map help** Print short help message. @@ -135,7 +144,7 @@ OPTIONS -h, --help Print short generic help message (similar to **bpftool help**). - -v, --version + -V, --version Print version number (similar to **bpftool version**). -j, --json @@ -152,6 +161,10 @@ OPTIONS Do not automatically attempt to mount any virtual file system (such as tracefs or BPF virtual file system) when necessary. + -d, --debug + Print all logs available from libbpf, including debug-level + information. + EXAMPLES ======== **# bpftool map show** @@ -258,4 +271,5 @@ SEE ALSO **bpftool-cgroup**\ (8), **bpftool-feature**\ (8), **bpftool-net**\ (8), - **bpftool-perf**\ (8) + **bpftool-perf**\ (8), + **bpftool-btf**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-net.rst b/tools/bpf/bpftool/Documentation/bpftool-net.rst index 779dab3650ee..8651b00b81ea 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-net.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-net.rst @@ -15,17 +15,22 @@ SYNOPSIS *OPTIONS* := { [{ **-j** | **--json** }] [{ **-p** | **--pretty** }] } *COMMANDS* := - { **show** | **list** } [ **dev** name ] | **help** + { **show** | **list** | **attach** | **detach** | **help** } NET COMMANDS ============ -| **bpftool** **net { show | list } [ dev name ]** +| **bpftool** **net { show | list }** [ **dev** *NAME* ] +| **bpftool** **net attach** *ATTACH_TYPE* *PROG* **dev** *NAME* [ **overwrite** ] +| **bpftool** **net detach** *ATTACH_TYPE* **dev** *NAME* | **bpftool** **net help** +| +| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* } +| *ATTACH_TYPE* := { **xdp** | **xdpgeneric** | **xdpdrv** | **xdpoffload** } DESCRIPTION =========== - **bpftool net { show | list } [ dev name ]** + **bpftool net { show | list }** [ **dev** *NAME* ] List bpf program attachments in the kernel networking subsystem. Currently, only device driver xdp attachments and tc filter @@ -47,6 +52,24 @@ DESCRIPTION all bpf programs attached to non clsact qdiscs, and finally all bpf programs attached to root and clsact qdisc. + **bpftool** **net attach** *ATTACH_TYPE* *PROG* **dev** *NAME* [ **overwrite** ] + Attach bpf program *PROG* to network interface *NAME* with + type specified by *ATTACH_TYPE*. Previously attached bpf program + can be replaced by the command used with **overwrite** option. + Currently, only XDP-related modes are supported for *ATTACH_TYPE*. + + *ATTACH_TYPE* can be of: + **xdp** - try native XDP and fallback to generic XDP if NIC driver does not support it; + **xdpgeneric** - Generic XDP. runs at generic XDP hook when packet already enters receive path as skb; + **xdpdrv** - Native XDP. runs earliest point in driver's receive path; + **xdpoffload** - Offload XDP. runs directly on NIC on each packet reception; + + **bpftool** **net detach** *ATTACH_TYPE* **dev** *NAME* + Detach bpf program attached to network interface *NAME* with + type specified by *ATTACH_TYPE*. To detach bpf program, same + *ATTACH_TYPE* previously used for attach must be specified. + Currently, only XDP-related modes are supported for *ATTACH_TYPE*. + **bpftool net help** Print short help message. @@ -55,7 +78,7 @@ OPTIONS -h, --help Print short generic help message (similar to **bpftool help**). - -v, --version + -V, --version Print version number (similar to **bpftool version**). -j, --json @@ -65,6 +88,10 @@ OPTIONS -p, --pretty Generate human-readable JSON output. Implies **-j**. + -d, --debug + Print all logs available from libbpf, including debug-level + information. + EXAMPLES ======== @@ -133,6 +160,34 @@ EXAMPLES } ] +| +| **# bpftool net attach xdpdrv id 16 dev enp6s0np0** +| **# bpftool net** + +:: + + xdp: + enp6s0np0(4) driver id 16 + +| +| **# bpftool net attach xdpdrv id 16 dev enp6s0np0** +| **# bpftool net attach xdpdrv id 20 dev enp6s0np0 overwrite** +| **# bpftool net** + +:: + + xdp: + enp6s0np0(4) driver id 20 + +| +| **# bpftool net attach xdpdrv id 16 dev enp6s0np0** +| **# bpftool net detach xdpdrv dev enp6s0np0** +| **# bpftool net** + +:: + + xdp: + SEE ALSO ======== @@ -143,4 +198,5 @@ SEE ALSO **bpftool-map**\ (8), **bpftool-cgroup**\ (8), **bpftool-feature**\ (8), - **bpftool-perf**\ (8) + **bpftool-perf**\ (8), + **bpftool-btf**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-perf.rst b/tools/bpf/bpftool/Documentation/bpftool-perf.rst index bca5590a80d0..e252bd0bc434 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-perf.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-perf.rst @@ -43,7 +43,7 @@ OPTIONS -h, --help Print short generic help message (similar to **bpftool help**). - -v, --version + -V, --version Print version number (similar to **bpftool version**). -j, --json @@ -53,6 +53,10 @@ OPTIONS -p, --pretty Generate human-readable JSON output. Implies **-j**. + -d, --debug + Print all logs available from libbpf, including debug-level + information. + EXAMPLES ======== @@ -85,4 +89,5 @@ SEE ALSO **bpftool-map**\ (8), **bpftool-cgroup**\ (8), **bpftool-feature**\ (8), - **bpftool-net**\ (8) + **bpftool-net**\ (8), + **bpftool-btf**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index 9386bd6e0396..7a374b3c851d 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -25,10 +25,11 @@ PROG COMMANDS | **bpftool** **prog dump xlated** *PROG* [{**file** *FILE* | **opcodes** | **visual** | **linum**}] | **bpftool** **prog dump jited** *PROG* [{**file** *FILE* | **opcodes** | **linum**}] | **bpftool** **prog pin** *PROG* *FILE* -| **bpftool** **prog { load | loadall }** *OBJ* *PATH* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*] +| **bpftool** **prog { load | loadall }** *OBJ* *PATH* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*] [**pinmaps** *MAP_DIR*] | **bpftool** **prog attach** *PROG* *ATTACH_TYPE* [*MAP*] | **bpftool** **prog detach** *PROG* *ATTACH_TYPE* [*MAP*] | **bpftool** **prog tracelog** +| **bpftool** **prog run** *PROG* **data_in** *FILE* [**data_out** *FILE* [**data_size_out** *L*]] [**ctx_in** *FILE* [**ctx_out** *FILE* [**ctx_size_out** *M*]]] [**repeat** *N*] | **bpftool** **prog help** | | *MAP* := { **id** *MAP_ID* | **pinned** *FILE* } @@ -39,7 +40,9 @@ PROG COMMANDS | **cgroup/sock** | **cgroup/dev** | **lwt_in** | **lwt_out** | **lwt_xmit** | | **lwt_seg6local** | **sockops** | **sk_skb** | **sk_msg** | **lirc_mode2** | | **cgroup/bind4** | **cgroup/bind6** | **cgroup/post_bind4** | **cgroup/post_bind6** | -| **cgroup/connect4** | **cgroup/connect6** | **cgroup/sendmsg4** | **cgroup/sendmsg6** +| **cgroup/connect4** | **cgroup/connect6** | **cgroup/sendmsg4** | **cgroup/sendmsg6** | +| **cgroup/recvmsg4** | **cgroup/recvmsg6** | **cgroup/sysctl** | +| **cgroup/getsockopt** | **cgroup/setsockopt** | } | *ATTACH_TYPE* := { | **msg_verdict** | **stream_verdict** | **stream_parser** | **flow_dissector** @@ -56,6 +59,14 @@ DESCRIPTION Output will start with program ID followed by program type and zero or more named attributes (depending on kernel version). + Since Linux 5.1 the kernel can collect statistics on BPF + programs (such as the total time spent running the program, + and the number of times it was run). If available, bpftool + shows such statistics. However, the kernel does not collect + them by defaults, as it slightly impacts performance on each + program run. Activation or deactivation of the feature is + performed via the **kernel.bpf_stats_enabled** sysctl knob. + **bpftool prog dump xlated** *PROG* [{ **file** *FILE* | **opcodes** | **visual** | **linum** }] Dump eBPF instructions of the program from the kernel. By default, eBPF will be disassembled and printed to standard @@ -136,6 +147,39 @@ DESCRIPTION streaming data from BPF programs to user space, one can use perf events (see also **bpftool-map**\ (8)). + **bpftool prog run** *PROG* **data_in** *FILE* [**data_out** *FILE* [**data_size_out** *L*]] [**ctx_in** *FILE* [**ctx_out** *FILE* [**ctx_size_out** *M*]]] [**repeat** *N*] + Run BPF program *PROG* in the kernel testing infrastructure + for BPF, meaning that the program works on the data and + context provided by the user, and not on actual packets or + monitored functions etc. Return value and duration for the + test run are printed out to the console. + + Input data is read from the *FILE* passed with **data_in**. + If this *FILE* is "**-**", input data is read from standard + input. Input context, if any, is read from *FILE* passed with + **ctx_in**. Again, "**-**" can be used to read from standard + input, but only if standard input is not already in use for + input data. If a *FILE* is passed with **data_out**, output + data is written to that file. Similarly, output context is + written to the *FILE* passed with **ctx_out**. For both + output flows, "**-**" can be used to print to the standard + output (as plain text, or JSON if relevant option was + passed). If output keywords are omitted, output data and + context are discarded. Keywords **data_size_out** and + **ctx_size_out** are used to pass the size (in bytes) for the + output buffers to the kernel, although the default of 32 kB + should be more than enough for most cases. + + Keyword **repeat** is used to indicate the number of + consecutive runs to perform. Note that output data and + context printed to files correspond to the last of those + runs. The duration printed out at the end of the runs is an + average over all runs performed by the command. + + Not all program types support test run. Among those which do, + not all of them can take the **ctx_in**/**ctx_out** + arguments. bpftool does not perform checks on program types. + **bpftool prog help** Print short help message. @@ -144,7 +188,7 @@ OPTIONS -h, --help Print short generic help message (similar to **bpftool help**). - -v, --version + -V, --version Print version number (similar to **bpftool version**). -j, --json @@ -165,6 +209,11 @@ OPTIONS Do not automatically attempt to mount any virtual file system (such as tracefs or BPF virtual file system) when necessary. + -d, --debug + Print all logs available, even debug-level information. This + includes logs from libbpf as well as from the verifier, when + attempting to load programs. + EXAMPLES ======== **# bpftool prog show** @@ -262,4 +311,5 @@ SEE ALSO **bpftool-cgroup**\ (8), **bpftool-feature**\ (8), **bpftool-net**\ (8), - **bpftool-perf**\ (8) + **bpftool-perf**\ (8), + **bpftool-btf**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst index 4f2188845dd8..6a9c52ef84a9 100644 --- a/tools/bpf/bpftool/Documentation/bpftool.rst +++ b/tools/bpf/bpftool/Documentation/bpftool.rst @@ -49,7 +49,7 @@ OPTIONS -h, --help Print short help message (similar to **bpftool help**). - -v, --version + -V, --version Print version number (similar to **bpftool version**). -j, --json @@ -66,6 +66,10 @@ OPTIONS Do not automatically attempt to mount any virtual file system (such as tracefs or BPF virtual file system) when necessary. + -d, --debug + Print all logs available, even debug-level information. This + includes logs from libbpf as well as from the verifier, when + attempting to load programs. SEE ALSO ======== @@ -76,4 +80,5 @@ SEE ALSO **bpftool-cgroup**\ (8), **bpftool-feature**\ (8), **bpftool-net**\ (8), - **bpftool-perf**\ (8) + **bpftool-perf**\ (8), + **bpftool-btf**\ (8) diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index 4ad1f0894d53..39bc6f0f4f0b 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only include ../../scripts/Makefile.include include ../../scripts/utilities.mak @@ -16,27 +17,30 @@ endif BPF_DIR = $(srctree)/tools/lib/bpf/ ifneq ($(OUTPUT),) - BPF_PATH = $(OUTPUT) + LIBBPF_OUTPUT = $(OUTPUT)/libbpf/ + LIBBPF_PATH = $(LIBBPF_OUTPUT) else - BPF_PATH = $(BPF_DIR) + LIBBPF_PATH = $(BPF_DIR) endif -LIBBPF = $(BPF_PATH)libbpf.a +LIBBPF = $(LIBBPF_PATH)libbpf.a -BPFTOOL_VERSION := $(shell make --no-print-directory -sC ../../.. kernelversion) +BPFTOOL_VERSION := $(shell make -rR --no-print-directory -sC ../../.. kernelversion) $(LIBBPF): FORCE - $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(OUTPUT) $(OUTPUT)libbpf.a + $(if $(LIBBPF_OUTPUT),@mkdir -p $(LIBBPF_OUTPUT)) + $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_OUTPUT) $(LIBBPF_OUTPUT)libbpf.a $(LIBBPF)-clean: $(call QUIET_CLEAN, libbpf) - $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(OUTPUT) clean >/dev/null + $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_OUTPUT) clean >/dev/null prefix ?= /usr/local bash_compdir ?= /usr/share/bash-completion/completions CFLAGS += -O2 -CFLAGS += -W -Wall -Wextra -Wno-unused-parameter -Wshadow -Wno-missing-field-initializers +CFLAGS += -W -Wall -Wextra -Wno-unused-parameter -Wno-missing-field-initializers +CFLAGS += $(filter-out -Wswitch-enum,$(EXTRA_WARNINGS)) CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ \ -I$(srctree)/kernel/bpf/ \ -I$(srctree)/tools/include \ @@ -51,14 +55,14 @@ ifneq ($(EXTRA_LDFLAGS),) LDFLAGS += $(EXTRA_LDFLAGS) endif -LIBS = -lelf $(LIBBPF) +LIBS = $(LIBBPF) -lelf -lz INSTALL ?= install RM ?= rm -f FEATURE_USER = .bpftool -FEATURE_TESTS = libbfd disassembler-four-args reallocarray -FEATURE_DISPLAY = libbfd disassembler-four-args +FEATURE_TESTS = libbfd disassembler-four-args reallocarray zlib +FEATURE_DISPLAY = libbfd disassembler-four-args zlib check_feat := 1 NON_CHECK_FEAT_TARGETS := clean uninstall doc doc-clean doc-install doc-uninstall @@ -110,17 +114,21 @@ OBJS = $(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) $(OUTPUT)disasm.o $(OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c $(QUIET_CC)$(COMPILE.c) -MMD -o $@ $< +$(OUTPUT)feature.o: | zdep + $(OUTPUT)bpftool: $(OBJS) $(LIBBPF) - $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ $^ $(LIBS) + $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ $(OBJS) $(LIBS) $(OUTPUT)%.o: %.c $(QUIET_CC)$(COMPILE.c) -MMD -o $@ $< clean: $(LIBBPF)-clean $(call QUIET_CLEAN, bpftool) - $(Q)$(RM) $(OUTPUT)bpftool $(OUTPUT)*.o $(OUTPUT)*.d + $(Q)$(RM) -- $(OUTPUT)bpftool $(OUTPUT)*.o $(OUTPUT)*.d + $(Q)$(RM) -r -- $(OUTPUT)libbpf/ $(call QUIET_CLEAN, core-gen) - $(Q)$(RM) $(OUTPUT)FEATURE-DUMP.bpftool + $(Q)$(RM) -- $(OUTPUT)FEATURE-DUMP.bpftool + $(Q)$(RM) -r -- $(OUTPUT)feature/ install: $(OUTPUT)bpftool $(call QUIET_INSTALL, bpftool) @@ -131,8 +139,8 @@ install: $(OUTPUT)bpftool uninstall: $(call QUIET_UNINST, bpftool) - $(Q)$(RM) $(DESTDIR)$(prefix)/sbin/bpftool - $(Q)$(RM) $(DESTDIR)$(bash_compdir)/bpftool + $(Q)$(RM) -- $(DESTDIR)$(prefix)/sbin/bpftool + $(Q)$(RM) -- $(DESTDIR)$(bash_compdir)/bpftool doc: $(call descend,Documentation) @@ -148,6 +156,9 @@ doc-uninstall: FORCE: -.PHONY: all FORCE clean install uninstall +zdep: + @if [ "$(feature-zlib)" != "1" ]; then echo "No zlib found"; exit 1 ; fi + +.PHONY: all FORCE clean install uninstall zdep .PHONY: doc doc-clean doc-install doc-uninstall .DEFAULT_GOAL := all diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index b803827d01e8..70493a6da206 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -71,6 +71,12 @@ _bpftool_get_prog_tags() command sed -n 's/.*"tag": "\(.*\)",$/\1/p' )" -- "$cur" ) ) } +_bpftool_get_btf_ids() +{ + COMPREPLY+=( $( compgen -W "$( bpftool -jp btf 2>&1 | \ + command sed -n 's/.*"id": \(.*\),$/\1/p' )" -- "$cur" ) ) +} + _bpftool_get_obj_map_names() { local obj @@ -181,7 +187,7 @@ _bpftool() # Deal with options if [[ ${words[cword]} == -* ]]; then - local c='--version --json --pretty --bpffs --mapcompat' + local c='--version --json --pretty --bpffs --mapcompat --debug' COMPREPLY=( $( compgen -W "$c" -- "$cur" ) ) return 0 fi @@ -195,6 +201,10 @@ _bpftool() _bpftool_get_prog_tags return 0 ;; + dev) + _sysfs_get_netdevs + return 0 + ;; file|pinned) _filedir return 0 @@ -217,6 +227,7 @@ _bpftool() done cur=${words[cword]} prev=${words[cword - 1]} + pprev=${words[cword - 2]} local object=${words[1]} command=${words[2]} @@ -272,17 +283,17 @@ _bpftool() "$cur" ) ) return 0 ;; - *) - _bpftool_once_attr 'file' - if _bpftool_search_list 'xlated'; then - COMPREPLY+=( $( compgen -W 'opcodes visual linum' -- \ - "$cur" ) ) - else - COMPREPLY+=( $( compgen -W 'opcodes linum' -- \ - "$cur" ) ) - fi - return 0 - ;; + *) + _bpftool_once_attr 'file' + if _bpftool_search_list 'xlated'; then + COMPREPLY+=( $( compgen -W 'opcodes visual linum' -- \ + "$cur" ) ) + else + COMPREPLY+=( $( compgen -W 'opcodes linum' -- \ + "$cur" ) ) + fi + return 0 + ;; esac ;; pin) @@ -335,6 +346,13 @@ _bpftool() load|loadall) local obj + # Propose "load/loadall" to complete "bpftool prog load", + # or bash tries to complete "load" as a filename below. + if [[ ${#words[@]} -eq 3 ]]; then + COMPREPLY=( $( compgen -W "load loadall" -- "$cur" ) ) + return 0 + fi + if [[ ${#words[@]} -lt 6 ]]; then _filedir return 0 @@ -370,7 +388,10 @@ _bpftool() lirc_mode2 cgroup/bind4 cgroup/bind6 \ cgroup/connect4 cgroup/connect6 \ cgroup/sendmsg4 cgroup/sendmsg6 \ - cgroup/post_bind4 cgroup/post_bind6" -- \ + cgroup/recvmsg4 cgroup/recvmsg6 \ + cgroup/post_bind4 cgroup/post_bind6 \ + cgroup/sysctl cgroup/getsockopt \ + cgroup/setsockopt" -- \ "$cur" ) ) return 0 ;; @@ -382,10 +403,6 @@ _bpftool() _filedir return 0 ;; - dev) - _sysfs_get_netdevs - return 0 - ;; *) COMPREPLY=( $( compgen -W "map" -- "$cur" ) ) _bpftool_once_attr 'type' @@ -398,17 +415,41 @@ _bpftool() tracelog) return 0 ;; + run) + if [[ ${#words[@]} -lt 5 ]]; then + _filedir + return 0 + fi + case $prev in + id) + _bpftool_get_prog_ids + return 0 + ;; + data_in|data_out|ctx_in|ctx_out) + _filedir + return 0 + ;; + repeat|data_size_out|ctx_size_out) + return 0 + ;; + *) + _bpftool_once_attr 'data_in data_out data_size_out \ + ctx_in ctx_out ctx_size_out repeat' + return 0 + ;; + esac + ;; *) [[ $prev == $object ]] && \ - COMPREPLY=( $( compgen -W 'dump help pin attach detach load \ - show list tracelog' -- "$cur" ) ) + COMPREPLY=( $( compgen -W 'dump help pin attach detach \ + load loadall show list tracelog run' -- "$cur" ) ) ;; esac ;; map) local MAP_TYPE='id pinned' case $command in - show|list|dump|peek|pop|dequeue) + show|list|dump|peek|pop|dequeue|freeze) case $prev in $command) COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) ) @@ -448,8 +489,8 @@ _bpftool() perf_event_array percpu_hash percpu_array \ stack_trace cgroup_array lru_hash \ lru_percpu_hash lpm_trie array_of_maps \ - hash_of_maps devmap sockmap cpumap xskmap \ - sockhash cgroup_storage reuseport_sockarray \ + hash_of_maps devmap devmap_hash sockmap cpumap \ + xskmap sockhash cgroup_storage reuseport_sockarray \ percpu_cgroup_storage queue stack' -- \ "$cur" ) ) return 0 @@ -457,10 +498,6 @@ _bpftool() key|value|flags|name|entries) return 0 ;; - dev) - _sysfs_get_netdevs - return 0 - ;; *) _bpftool_once_attr 'type' _bpftool_once_attr 'key' @@ -601,25 +638,102 @@ _bpftool() [[ $prev == $object ]] && \ COMPREPLY=( $( compgen -W 'delete dump getnext help \ lookup pin event_pipe show list update create \ - peek push enqueue pop dequeue' -- \ + peek push enqueue pop dequeue freeze' -- \ "$cur" ) ) ;; esac ;; - cgroup) + btf) + local PROG_TYPE='id pinned tag' + local MAP_TYPE='id pinned' case $command in + dump) + case $prev in + $command) + COMPREPLY+=( $( compgen -W "id map prog file" -- \ + "$cur" ) ) + return 0 + ;; + prog) + COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) ) + return 0 + ;; + map) + COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) ) + return 0 + ;; + id) + case $pprev in + prog) + _bpftool_get_prog_ids + ;; + map) + _bpftool_get_map_ids + ;; + $command) + _bpftool_get_btf_ids + ;; + esac + return 0 + ;; + format) + COMPREPLY=( $( compgen -W "c raw" -- "$cur" ) ) + ;; + *) + # emit extra options + case ${words[3]} in + id|file) + _bpftool_once_attr 'format' + ;; + map|prog) + if [[ ${words[3]} == "map" ]] && [[ $cword == 6 ]]; then + COMPREPLY+=( $( compgen -W "key value kv all" -- "$cur" ) ) + fi + _bpftool_once_attr 'format' + ;; + *) + ;; + esac + return 0 + ;; + esac + ;; show|list) - _filedir + case $prev in + $command) + COMPREPLY+=( $( compgen -W "id" -- "$cur" ) ) + ;; + id) + _bpftool_get_btf_ids + ;; + esac return 0 ;; - tree) - _filedir + *) + [[ $prev == $object ]] && \ + COMPREPLY=( $( compgen -W 'dump help show list' \ + -- "$cur" ) ) + ;; + esac + ;; + cgroup) + case $command in + show|list|tree) + case $cword in + 3) + _filedir + ;; + 4) + COMPREPLY=( $( compgen -W 'effective' -- "$cur" ) ) + ;; + esac return 0 ;; attach|detach) local ATTACH_TYPES='ingress egress sock_create sock_ops \ device bind4 bind6 post_bind4 post_bind6 connect4 \ - connect6 sendmsg4 sendmsg6' + connect6 sendmsg4 sendmsg6 recvmsg4 recvmsg6 sysctl \ + getsockopt setsockopt' local ATTACH_FLAGS='multi override' local PROG_TYPE='id pinned tag' case $prev in @@ -629,7 +743,8 @@ _bpftool() ;; ingress|egress|sock_create|sock_ops|device|bind4|bind6|\ post_bind4|post_bind6|connect4|connect6|sendmsg4|\ - sendmsg6) + sendmsg6|recvmsg4|recvmsg6|sysctl|getsockopt|\ + setsockopt) COMPREPLY=( $( compgen -W "$PROG_TYPE" -- \ "$cur" ) ) return 0 @@ -671,18 +786,67 @@ _bpftool() esac ;; net) + local PROG_TYPE='id pinned tag' + local ATTACH_TYPES='xdp xdpgeneric xdpdrv xdpoffload' case $command in + show|list) + [[ $prev != "$command" ]] && return 0 + COMPREPLY=( $( compgen -W 'dev' -- "$cur" ) ) + return 0 + ;; + attach) + case $cword in + 3) + COMPREPLY=( $( compgen -W "$ATTACH_TYPES" -- "$cur" ) ) + return 0 + ;; + 4) + COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) ) + return 0 + ;; + 5) + case $prev in + id) + _bpftool_get_prog_ids + ;; + pinned) + _filedir + ;; + esac + return 0 + ;; + 6) + COMPREPLY=( $( compgen -W 'dev' -- "$cur" ) ) + return 0 + ;; + 8) + _bpftool_once_attr 'overwrite' + return 0 + ;; + esac + ;; + detach) + case $cword in + 3) + COMPREPLY=( $( compgen -W "$ATTACH_TYPES" -- "$cur" ) ) + return 0 + ;; + 4) + COMPREPLY=( $( compgen -W 'dev' -- "$cur" ) ) + return 0 + ;; + esac + ;; *) [[ $prev == $object ]] && \ COMPREPLY=( $( compgen -W 'help \ - show list' -- "$cur" ) ) + show list attach detach' -- "$cur" ) ) ;; esac ;; feature) case $command in probe) - [[ $prev == "dev" ]] && _sysfs_get_netdevs && return 0 [[ $prev == "prefix" ]] && return 0 if _bpftool_search_list 'macros'; then COMPREPLY+=( $( compgen -W 'prefix' -- "$cur" ) ) diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c new file mode 100644 index 000000000000..e5bc97b71ceb --- /dev/null +++ b/tools/bpf/bpftool/btf.c @@ -0,0 +1,949 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2019 Facebook */ + +#include <errno.h> +#include <fcntl.h> +#include <linux/err.h> +#include <stdbool.h> +#include <stdio.h> +#include <string.h> +#include <unistd.h> +#include <bpf.h> +#include <libbpf.h> +#include <linux/btf.h> +#include <linux/hashtable.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> + +#include "btf.h" +#include "json_writer.h" +#include "main.h" + +static const char * const btf_kind_str[NR_BTF_KINDS] = { + [BTF_KIND_UNKN] = "UNKNOWN", + [BTF_KIND_INT] = "INT", + [BTF_KIND_PTR] = "PTR", + [BTF_KIND_ARRAY] = "ARRAY", + [BTF_KIND_STRUCT] = "STRUCT", + [BTF_KIND_UNION] = "UNION", + [BTF_KIND_ENUM] = "ENUM", + [BTF_KIND_FWD] = "FWD", + [BTF_KIND_TYPEDEF] = "TYPEDEF", + [BTF_KIND_VOLATILE] = "VOLATILE", + [BTF_KIND_CONST] = "CONST", + [BTF_KIND_RESTRICT] = "RESTRICT", + [BTF_KIND_FUNC] = "FUNC", + [BTF_KIND_FUNC_PROTO] = "FUNC_PROTO", + [BTF_KIND_VAR] = "VAR", + [BTF_KIND_DATASEC] = "DATASEC", +}; + +struct btf_attach_table { + DECLARE_HASHTABLE(table, 16); +}; + +struct btf_attach_point { + __u32 obj_id; + __u32 btf_id; + struct hlist_node hash; +}; + +static const char *btf_int_enc_str(__u8 encoding) +{ + switch (encoding) { + case 0: + return "(none)"; + case BTF_INT_SIGNED: + return "SIGNED"; + case BTF_INT_CHAR: + return "CHAR"; + case BTF_INT_BOOL: + return "BOOL"; + default: + return "UNKN"; + } +} + +static const char *btf_var_linkage_str(__u32 linkage) +{ + switch (linkage) { + case BTF_VAR_STATIC: + return "static"; + case BTF_VAR_GLOBAL_ALLOCATED: + return "global-alloc"; + default: + return "(unknown)"; + } +} + +static const char *btf_str(const struct btf *btf, __u32 off) +{ + if (!off) + return "(anon)"; + return btf__name_by_offset(btf, off) ? : "(invalid)"; +} + +static int dump_btf_type(const struct btf *btf, __u32 id, + const struct btf_type *t) +{ + json_writer_t *w = json_wtr; + int kind, safe_kind; + + kind = BTF_INFO_KIND(t->info); + safe_kind = kind <= BTF_KIND_MAX ? kind : BTF_KIND_UNKN; + + if (json_output) { + jsonw_start_object(w); + jsonw_uint_field(w, "id", id); + jsonw_string_field(w, "kind", btf_kind_str[safe_kind]); + jsonw_string_field(w, "name", btf_str(btf, t->name_off)); + } else { + printf("[%u] %s '%s'", id, btf_kind_str[safe_kind], + btf_str(btf, t->name_off)); + } + + switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_INT: { + __u32 v = *(__u32 *)(t + 1); + const char *enc; + + enc = btf_int_enc_str(BTF_INT_ENCODING(v)); + + if (json_output) { + jsonw_uint_field(w, "size", t->size); + jsonw_uint_field(w, "bits_offset", BTF_INT_OFFSET(v)); + jsonw_uint_field(w, "nr_bits", BTF_INT_BITS(v)); + jsonw_string_field(w, "encoding", enc); + } else { + printf(" size=%u bits_offset=%u nr_bits=%u encoding=%s", + t->size, BTF_INT_OFFSET(v), BTF_INT_BITS(v), + enc); + } + break; + } + case BTF_KIND_PTR: + case BTF_KIND_CONST: + case BTF_KIND_VOLATILE: + case BTF_KIND_RESTRICT: + case BTF_KIND_TYPEDEF: + if (json_output) + jsonw_uint_field(w, "type_id", t->type); + else + printf(" type_id=%u", t->type); + break; + case BTF_KIND_ARRAY: { + const struct btf_array *arr = (const void *)(t + 1); + + if (json_output) { + jsonw_uint_field(w, "type_id", arr->type); + jsonw_uint_field(w, "index_type_id", arr->index_type); + jsonw_uint_field(w, "nr_elems", arr->nelems); + } else { + printf(" type_id=%u index_type_id=%u nr_elems=%u", + arr->type, arr->index_type, arr->nelems); + } + break; + } + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: { + const struct btf_member *m = (const void *)(t + 1); + __u16 vlen = BTF_INFO_VLEN(t->info); + int i; + + if (json_output) { + jsonw_uint_field(w, "size", t->size); + jsonw_uint_field(w, "vlen", vlen); + jsonw_name(w, "members"); + jsonw_start_array(w); + } else { + printf(" size=%u vlen=%u", t->size, vlen); + } + for (i = 0; i < vlen; i++, m++) { + const char *name = btf_str(btf, m->name_off); + __u32 bit_off, bit_sz; + + if (BTF_INFO_KFLAG(t->info)) { + bit_off = BTF_MEMBER_BIT_OFFSET(m->offset); + bit_sz = BTF_MEMBER_BITFIELD_SIZE(m->offset); + } else { + bit_off = m->offset; + bit_sz = 0; + } + + if (json_output) { + jsonw_start_object(w); + jsonw_string_field(w, "name", name); + jsonw_uint_field(w, "type_id", m->type); + jsonw_uint_field(w, "bits_offset", bit_off); + if (bit_sz) { + jsonw_uint_field(w, "bitfield_size", + bit_sz); + } + jsonw_end_object(w); + } else { + printf("\n\t'%s' type_id=%u bits_offset=%u", + name, m->type, bit_off); + if (bit_sz) + printf(" bitfield_size=%u", bit_sz); + } + } + if (json_output) + jsonw_end_array(w); + break; + } + case BTF_KIND_ENUM: { + const struct btf_enum *v = (const void *)(t + 1); + __u16 vlen = BTF_INFO_VLEN(t->info); + int i; + + if (json_output) { + jsonw_uint_field(w, "size", t->size); + jsonw_uint_field(w, "vlen", vlen); + jsonw_name(w, "values"); + jsonw_start_array(w); + } else { + printf(" size=%u vlen=%u", t->size, vlen); + } + for (i = 0; i < vlen; i++, v++) { + const char *name = btf_str(btf, v->name_off); + + if (json_output) { + jsonw_start_object(w); + jsonw_string_field(w, "name", name); + jsonw_uint_field(w, "val", v->val); + jsonw_end_object(w); + } else { + printf("\n\t'%s' val=%u", name, v->val); + } + } + if (json_output) + jsonw_end_array(w); + break; + } + case BTF_KIND_FWD: { + const char *fwd_kind = BTF_INFO_KFLAG(t->info) ? "union" + : "struct"; + + if (json_output) + jsonw_string_field(w, "fwd_kind", fwd_kind); + else + printf(" fwd_kind=%s", fwd_kind); + break; + } + case BTF_KIND_FUNC: + if (json_output) + jsonw_uint_field(w, "type_id", t->type); + else + printf(" type_id=%u", t->type); + break; + case BTF_KIND_FUNC_PROTO: { + const struct btf_param *p = (const void *)(t + 1); + __u16 vlen = BTF_INFO_VLEN(t->info); + int i; + + if (json_output) { + jsonw_uint_field(w, "ret_type_id", t->type); + jsonw_uint_field(w, "vlen", vlen); + jsonw_name(w, "params"); + jsonw_start_array(w); + } else { + printf(" ret_type_id=%u vlen=%u", t->type, vlen); + } + for (i = 0; i < vlen; i++, p++) { + const char *name = btf_str(btf, p->name_off); + + if (json_output) { + jsonw_start_object(w); + jsonw_string_field(w, "name", name); + jsonw_uint_field(w, "type_id", p->type); + jsonw_end_object(w); + } else { + printf("\n\t'%s' type_id=%u", name, p->type); + } + } + if (json_output) + jsonw_end_array(w); + break; + } + case BTF_KIND_VAR: { + const struct btf_var *v = (const void *)(t + 1); + const char *linkage; + + linkage = btf_var_linkage_str(v->linkage); + + if (json_output) { + jsonw_uint_field(w, "type_id", t->type); + jsonw_string_field(w, "linkage", linkage); + } else { + printf(" type_id=%u, linkage=%s", t->type, linkage); + } + break; + } + case BTF_KIND_DATASEC: { + const struct btf_var_secinfo *v = (const void *)(t+1); + __u16 vlen = BTF_INFO_VLEN(t->info); + int i; + + if (json_output) { + jsonw_uint_field(w, "size", t->size); + jsonw_uint_field(w, "vlen", vlen); + jsonw_name(w, "vars"); + jsonw_start_array(w); + } else { + printf(" size=%u vlen=%u", t->size, vlen); + } + for (i = 0; i < vlen; i++, v++) { + if (json_output) { + jsonw_start_object(w); + jsonw_uint_field(w, "type_id", v->type); + jsonw_uint_field(w, "offset", v->offset); + jsonw_uint_field(w, "size", v->size); + jsonw_end_object(w); + } else { + printf("\n\ttype_id=%u offset=%u size=%u", + v->type, v->offset, v->size); + } + } + if (json_output) + jsonw_end_array(w); + break; + } + default: + break; + } + + if (json_output) + jsonw_end_object(json_wtr); + else + printf("\n"); + + return 0; +} + +static int dump_btf_raw(const struct btf *btf, + __u32 *root_type_ids, int root_type_cnt) +{ + const struct btf_type *t; + int i; + + if (json_output) { + jsonw_start_object(json_wtr); + jsonw_name(json_wtr, "types"); + jsonw_start_array(json_wtr); + } + + if (root_type_cnt) { + for (i = 0; i < root_type_cnt; i++) { + t = btf__type_by_id(btf, root_type_ids[i]); + dump_btf_type(btf, root_type_ids[i], t); + } + } else { + int cnt = btf__get_nr_types(btf); + + for (i = 1; i <= cnt; i++) { + t = btf__type_by_id(btf, i); + dump_btf_type(btf, i, t); + } + } + + if (json_output) { + jsonw_end_array(json_wtr); + jsonw_end_object(json_wtr); + } + return 0; +} + +static void __printf(2, 0) btf_dump_printf(void *ctx, + const char *fmt, va_list args) +{ + vfprintf(stdout, fmt, args); +} + +static int dump_btf_c(const struct btf *btf, + __u32 *root_type_ids, int root_type_cnt) +{ + struct btf_dump *d; + int err = 0, i; + + d = btf_dump__new(btf, NULL, NULL, btf_dump_printf); + if (IS_ERR(d)) + return PTR_ERR(d); + + if (root_type_cnt) { + for (i = 0; i < root_type_cnt; i++) { + err = btf_dump__dump_type(d, root_type_ids[i]); + if (err) + goto done; + } + } else { + int cnt = btf__get_nr_types(btf); + + for (i = 1; i <= cnt; i++) { + err = btf_dump__dump_type(d, i); + if (err) + goto done; + } + } + +done: + btf_dump__free(d); + return err; +} + +static struct btf *btf__parse_raw(const char *file) +{ + struct btf *btf; + struct stat st; + __u8 *buf; + FILE *f; + + if (stat(file, &st)) + return NULL; + + f = fopen(file, "rb"); + if (!f) + return NULL; + + buf = malloc(st.st_size); + if (!buf) { + btf = ERR_PTR(-ENOMEM); + goto exit_close; + } + + if ((size_t) st.st_size != fread(buf, 1, st.st_size, f)) { + btf = ERR_PTR(-EINVAL); + goto exit_free; + } + + btf = btf__new(buf, st.st_size); + +exit_free: + free(buf); +exit_close: + fclose(f); + return btf; +} + +static bool is_btf_raw(const char *file) +{ + __u16 magic = 0; + int fd, nb_read; + + fd = open(file, O_RDONLY); + if (fd < 0) + return false; + + nb_read = read(fd, &magic, sizeof(magic)); + close(fd); + return nb_read == sizeof(magic) && magic == BTF_MAGIC; +} + +static int do_dump(int argc, char **argv) +{ + struct btf *btf = NULL; + __u32 root_type_ids[2]; + int root_type_cnt = 0; + bool dump_c = false; + __u32 btf_id = -1; + const char *src; + int fd = -1; + int err; + + if (!REQ_ARGS(2)) { + usage(); + return -1; + } + src = GET_ARG(); + + if (is_prefix(src, "map")) { + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + + if (!REQ_ARGS(2)) { + usage(); + return -1; + } + + fd = map_parse_fd_and_info(&argc, &argv, &info, &len); + if (fd < 0) + return -1; + + btf_id = info.btf_id; + if (argc && is_prefix(*argv, "key")) { + root_type_ids[root_type_cnt++] = info.btf_key_type_id; + NEXT_ARG(); + } else if (argc && is_prefix(*argv, "value")) { + root_type_ids[root_type_cnt++] = info.btf_value_type_id; + NEXT_ARG(); + } else if (argc && is_prefix(*argv, "all")) { + NEXT_ARG(); + } else if (argc && is_prefix(*argv, "kv")) { + root_type_ids[root_type_cnt++] = info.btf_key_type_id; + root_type_ids[root_type_cnt++] = info.btf_value_type_id; + NEXT_ARG(); + } else { + root_type_ids[root_type_cnt++] = info.btf_key_type_id; + root_type_ids[root_type_cnt++] = info.btf_value_type_id; + } + } else if (is_prefix(src, "prog")) { + struct bpf_prog_info info = {}; + __u32 len = sizeof(info); + + if (!REQ_ARGS(2)) { + usage(); + return -1; + } + + fd = prog_parse_fd(&argc, &argv); + if (fd < 0) + return -1; + + err = bpf_obj_get_info_by_fd(fd, &info, &len); + if (err) { + p_err("can't get prog info: %s", strerror(errno)); + goto done; + } + + btf_id = info.btf_id; + } else if (is_prefix(src, "id")) { + char *endptr; + + btf_id = strtoul(*argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as ID", *argv); + return -1; + } + NEXT_ARG(); + } else if (is_prefix(src, "file")) { + if (is_btf_raw(*argv)) + btf = btf__parse_raw(*argv); + else + btf = btf__parse_elf(*argv, NULL); + + if (IS_ERR(btf)) { + err = PTR_ERR(btf); + btf = NULL; + p_err("failed to load BTF from %s: %s", + *argv, strerror(err)); + goto done; + } + NEXT_ARG(); + } else { + err = -1; + p_err("unrecognized BTF source specifier: '%s'", src); + goto done; + } + + while (argc) { + if (is_prefix(*argv, "format")) { + NEXT_ARG(); + if (argc < 1) { + p_err("expecting value for 'format' option\n"); + goto done; + } + if (strcmp(*argv, "c") == 0) { + dump_c = true; + } else if (strcmp(*argv, "raw") == 0) { + dump_c = false; + } else { + p_err("unrecognized format specifier: '%s', possible values: raw, c", + *argv); + goto done; + } + NEXT_ARG(); + } else { + p_err("unrecognized option: '%s'", *argv); + goto done; + } + } + + if (!btf) { + err = btf__get_from_id(btf_id, &btf); + if (err) { + p_err("get btf by id (%u): %s", btf_id, strerror(err)); + goto done; + } + if (!btf) { + err = ENOENT; + p_err("can't find btf with ID (%u)", btf_id); + goto done; + } + } + + if (dump_c) { + if (json_output) { + p_err("JSON output for C-syntax dump is not supported"); + err = -ENOTSUP; + goto done; + } + err = dump_btf_c(btf, root_type_ids, root_type_cnt); + } else { + err = dump_btf_raw(btf, root_type_ids, root_type_cnt); + } + +done: + close(fd); + btf__free(btf); + return err; +} + +static int btf_parse_fd(int *argc, char ***argv) +{ + unsigned int id; + char *endptr; + int fd; + + if (!is_prefix(*argv[0], "id")) { + p_err("expected 'id', got: '%s'?", **argv); + return -1; + } + NEXT_ARGP(); + + id = strtoul(**argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as ID", **argv); + return -1; + } + NEXT_ARGP(); + + fd = bpf_btf_get_fd_by_id(id); + if (fd < 0) + p_err("can't get BTF object by id (%u): %s", + id, strerror(errno)); + + return fd; +} + +static void delete_btf_table(struct btf_attach_table *tab) +{ + struct btf_attach_point *obj; + struct hlist_node *tmp; + + unsigned int bkt; + + hash_for_each_safe(tab->table, bkt, tmp, obj, hash) { + hash_del(&obj->hash); + free(obj); + } +} + +static int +build_btf_type_table(struct btf_attach_table *tab, enum bpf_obj_type type, + void *info, __u32 *len) +{ + static const char * const names[] = { + [BPF_OBJ_UNKNOWN] = "unknown", + [BPF_OBJ_PROG] = "prog", + [BPF_OBJ_MAP] = "map", + }; + struct btf_attach_point *obj_node; + __u32 btf_id, id = 0; + int err; + int fd; + + while (true) { + switch (type) { + case BPF_OBJ_PROG: + err = bpf_prog_get_next_id(id, &id); + break; + case BPF_OBJ_MAP: + err = bpf_map_get_next_id(id, &id); + break; + default: + err = -1; + p_err("unexpected object type: %d", type); + goto err_free; + } + if (err) { + if (errno == ENOENT) { + err = 0; + break; + } + p_err("can't get next %s: %s%s", names[type], + strerror(errno), + errno == EINVAL ? " -- kernel too old?" : ""); + goto err_free; + } + + switch (type) { + case BPF_OBJ_PROG: + fd = bpf_prog_get_fd_by_id(id); + break; + case BPF_OBJ_MAP: + fd = bpf_map_get_fd_by_id(id); + break; + default: + err = -1; + p_err("unexpected object type: %d", type); + goto err_free; + } + if (fd < 0) { + if (errno == ENOENT) + continue; + p_err("can't get %s by id (%u): %s", names[type], id, + strerror(errno)); + err = -1; + goto err_free; + } + + memset(info, 0, *len); + err = bpf_obj_get_info_by_fd(fd, info, len); + close(fd); + if (err) { + p_err("can't get %s info: %s", names[type], + strerror(errno)); + goto err_free; + } + + switch (type) { + case BPF_OBJ_PROG: + btf_id = ((struct bpf_prog_info *)info)->btf_id; + break; + case BPF_OBJ_MAP: + btf_id = ((struct bpf_map_info *)info)->btf_id; + break; + default: + err = -1; + p_err("unexpected object type: %d", type); + goto err_free; + } + if (!btf_id) + continue; + + obj_node = calloc(1, sizeof(*obj_node)); + if (!obj_node) { + p_err("failed to allocate memory: %s", strerror(errno)); + goto err_free; + } + + obj_node->obj_id = id; + obj_node->btf_id = btf_id; + hash_add(tab->table, &obj_node->hash, obj_node->btf_id); + } + + return 0; + +err_free: + delete_btf_table(tab); + return err; +} + +static int +build_btf_tables(struct btf_attach_table *btf_prog_table, + struct btf_attach_table *btf_map_table) +{ + struct bpf_prog_info prog_info; + __u32 prog_len = sizeof(prog_info); + struct bpf_map_info map_info; + __u32 map_len = sizeof(map_info); + int err = 0; + + err = build_btf_type_table(btf_prog_table, BPF_OBJ_PROG, &prog_info, + &prog_len); + if (err) + return err; + + err = build_btf_type_table(btf_map_table, BPF_OBJ_MAP, &map_info, + &map_len); + if (err) { + delete_btf_table(btf_prog_table); + return err; + } + + return 0; +} + +static void +show_btf_plain(struct bpf_btf_info *info, int fd, + struct btf_attach_table *btf_prog_table, + struct btf_attach_table *btf_map_table) +{ + struct btf_attach_point *obj; + int n; + + printf("%u: ", info->id); + printf("size %uB", info->btf_size); + + n = 0; + hash_for_each_possible(btf_prog_table->table, obj, hash, info->id) { + if (obj->btf_id == info->id) + printf("%s%u", n++ == 0 ? " prog_ids " : ",", + obj->obj_id); + } + + n = 0; + hash_for_each_possible(btf_map_table->table, obj, hash, info->id) { + if (obj->btf_id == info->id) + printf("%s%u", n++ == 0 ? " map_ids " : ",", + obj->obj_id); + } + + printf("\n"); +} + +static void +show_btf_json(struct bpf_btf_info *info, int fd, + struct btf_attach_table *btf_prog_table, + struct btf_attach_table *btf_map_table) +{ + struct btf_attach_point *obj; + + jsonw_start_object(json_wtr); /* btf object */ + jsonw_uint_field(json_wtr, "id", info->id); + jsonw_uint_field(json_wtr, "size", info->btf_size); + + jsonw_name(json_wtr, "prog_ids"); + jsonw_start_array(json_wtr); /* prog_ids */ + hash_for_each_possible(btf_prog_table->table, obj, hash, + info->id) { + if (obj->btf_id == info->id) + jsonw_uint(json_wtr, obj->obj_id); + } + jsonw_end_array(json_wtr); /* prog_ids */ + + jsonw_name(json_wtr, "map_ids"); + jsonw_start_array(json_wtr); /* map_ids */ + hash_for_each_possible(btf_map_table->table, obj, hash, + info->id) { + if (obj->btf_id == info->id) + jsonw_uint(json_wtr, obj->obj_id); + } + jsonw_end_array(json_wtr); /* map_ids */ + jsonw_end_object(json_wtr); /* btf object */ +} + +static int +show_btf(int fd, struct btf_attach_table *btf_prog_table, + struct btf_attach_table *btf_map_table) +{ + struct bpf_btf_info info = {}; + __u32 len = sizeof(info); + int err; + + err = bpf_obj_get_info_by_fd(fd, &info, &len); + if (err) { + p_err("can't get BTF object info: %s", strerror(errno)); + return -1; + } + + if (json_output) + show_btf_json(&info, fd, btf_prog_table, btf_map_table); + else + show_btf_plain(&info, fd, btf_prog_table, btf_map_table); + + return 0; +} + +static int do_show(int argc, char **argv) +{ + struct btf_attach_table btf_prog_table; + struct btf_attach_table btf_map_table; + int err, fd = -1; + __u32 id = 0; + + if (argc == 2) { + fd = btf_parse_fd(&argc, &argv); + if (fd < 0) + return -1; + } + + if (argc) { + if (fd >= 0) + close(fd); + return BAD_ARG(); + } + + hash_init(btf_prog_table.table); + hash_init(btf_map_table.table); + err = build_btf_tables(&btf_prog_table, &btf_map_table); + if (err) { + if (fd >= 0) + close(fd); + return err; + } + + if (fd >= 0) { + err = show_btf(fd, &btf_prog_table, &btf_map_table); + close(fd); + goto exit_free; + } + + if (json_output) + jsonw_start_array(json_wtr); /* root array */ + + while (true) { + err = bpf_btf_get_next_id(id, &id); + if (err) { + if (errno == ENOENT) { + err = 0; + break; + } + p_err("can't get next BTF object: %s%s", + strerror(errno), + errno == EINVAL ? " -- kernel too old?" : ""); + err = -1; + break; + } + + fd = bpf_btf_get_fd_by_id(id); + if (fd < 0) { + if (errno == ENOENT) + continue; + p_err("can't get BTF object by id (%u): %s", + id, strerror(errno)); + err = -1; + break; + } + + err = show_btf(fd, &btf_prog_table, &btf_map_table); + close(fd); + if (err) + break; + } + + if (json_output) + jsonw_end_array(json_wtr); /* root array */ + +exit_free: + delete_btf_table(&btf_prog_table); + delete_btf_table(&btf_map_table); + + return err; +} + +static int do_help(int argc, char **argv) +{ + if (json_output) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %s btf { show | list } [id BTF_ID]\n" + " %s btf dump BTF_SRC [format FORMAT]\n" + " %s btf help\n" + "\n" + " BTF_SRC := { id BTF_ID | prog PROG | map MAP [{key | value | kv | all}] | file FILE }\n" + " FORMAT := { raw | c }\n" + " " HELP_SPEC_MAP "\n" + " " HELP_SPEC_PROGRAM "\n" + " " HELP_SPEC_OPTIONS "\n" + "", + bin_name, bin_name, bin_name); + + return 0; +} + +static const struct cmd cmds[] = { + { "show", do_show }, + { "list", do_show }, + { "help", do_help }, + { "dump", do_dump }, + { 0 } +}; + +int do_btf(int argc, char **argv) +{ + return cmd_select(cmds, argc, argv, do_help); +} diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c index e63bce0755eb..d66131f69689 100644 --- a/tools/bpf/bpftool/btf_dumper.c +++ b/tools/bpf/bpftool/btf_dumper.c @@ -26,9 +26,9 @@ static void btf_dumper_ptr(const void *data, json_writer_t *jw, bool is_plain_text) { if (is_plain_text) - jsonw_printf(jw, "%p", *(unsigned long *)data); + jsonw_printf(jw, "%p", data); else - jsonw_printf(jw, "%u", *(unsigned long *)data); + jsonw_printf(jw, "%lu", *(unsigned long *)data); } static int btf_dumper_modifier(const struct btf_dumper *d, __u32 type_id, @@ -216,7 +216,7 @@ static int btf_dumper_int(const struct btf_type *t, __u8 bit_offset, switch (BTF_INT_ENCODING(*int_type)) { case 0: if (BTF_INT_BITS(*int_type) == 64) - jsonw_printf(jw, "%lu", *(__u64 *)data); + jsonw_printf(jw, "%llu", *(__u64 *)data); else if (BTF_INT_BITS(*int_type) == 32) jsonw_printf(jw, "%u", *(__u32 *)data); else if (BTF_INT_BITS(*int_type) == 16) @@ -229,7 +229,7 @@ static int btf_dumper_int(const struct btf_type *t, __u8 bit_offset, break; case BTF_INT_SIGNED: if (BTF_INT_BITS(*int_type) == 64) - jsonw_printf(jw, "%ld", *(long long *)data); + jsonw_printf(jw, "%lld", *(long long *)data); else if (BTF_INT_BITS(*int_type) == 32) jsonw_printf(jw, "%d", *(int *)data); else if (BTF_INT_BITS(*int_type) == 16) @@ -309,6 +309,48 @@ static int btf_dumper_struct(const struct btf_dumper *d, __u32 type_id, return ret; } +static int btf_dumper_var(const struct btf_dumper *d, __u32 type_id, + __u8 bit_offset, const void *data) +{ + const struct btf_type *t = btf__type_by_id(d->btf, type_id); + int ret; + + jsonw_start_object(d->jw); + jsonw_name(d->jw, btf__name_by_offset(d->btf, t->name_off)); + ret = btf_dumper_do_type(d, t->type, bit_offset, data); + jsonw_end_object(d->jw); + + return ret; +} + +static int btf_dumper_datasec(const struct btf_dumper *d, __u32 type_id, + const void *data) +{ + struct btf_var_secinfo *vsi; + const struct btf_type *t; + int ret = 0, i, vlen; + + t = btf__type_by_id(d->btf, type_id); + if (!t) + return -EINVAL; + + vlen = BTF_INFO_VLEN(t->info); + vsi = (struct btf_var_secinfo *)(t + 1); + + jsonw_start_object(d->jw); + jsonw_name(d->jw, btf__name_by_offset(d->btf, t->name_off)); + jsonw_start_array(d->jw); + for (i = 0; i < vlen; i++) { + ret = btf_dumper_do_type(d, vsi[i].type, 0, data + vsi[i].offset); + if (ret) + break; + } + jsonw_end_array(d->jw); + jsonw_end_object(d->jw); + + return ret; +} + static int btf_dumper_do_type(const struct btf_dumper *d, __u32 type_id, __u8 bit_offset, const void *data) { @@ -341,6 +383,10 @@ static int btf_dumper_do_type(const struct btf_dumper *d, __u32 type_id, case BTF_KIND_CONST: case BTF_KIND_RESTRICT: return btf_dumper_modifier(d, type_id, bit_offset, data); + case BTF_KIND_VAR: + return btf_dumper_var(d, type_id, bit_offset, data); + case BTF_KIND_DATASEC: + return btf_dumper_datasec(d, type_id, data); default: jsonw_printf(d->jw, "(unsupported-kind"); return -EINVAL; @@ -377,6 +423,7 @@ static int __btf_dumper_type_only(const struct btf *btf, __u32 type_id, { const struct btf_type *proto_type; const struct btf_array *array; + const struct btf_var *var; const struct btf_type *t; if (!type_id) { @@ -440,6 +487,18 @@ static int __btf_dumper_type_only(const struct btf *btf, __u32 type_id, if (pos == -1) return -1; break; + case BTF_KIND_VAR: + var = (struct btf_var *)(t + 1); + if (var->linkage == BTF_VAR_STATIC) + BTF_PRINT_ARG("static "); + BTF_PRINT_TYPE(t->type); + BTF_PRINT_ARG(" %s", + btf__name_by_offset(btf, t->name_off)); + break; + case BTF_KIND_DATASEC: + BTF_PRINT_ARG("section (\"%s\") ", + btf__name_by_offset(btf, t->name_off)); + break; case BTF_KIND_UNKN: default: return -1; diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c index 4b5c8da2a7c0..1ef45e55039e 100644 --- a/tools/bpf/bpftool/cgroup.c +++ b/tools/bpf/bpftool/cgroup.c @@ -25,7 +25,11 @@ " ATTACH_TYPE := { ingress | egress | sock_create |\n" \ " sock_ops | device | bind4 | bind6 |\n" \ " post_bind4 | post_bind6 | connect4 |\n" \ - " connect6 | sendmsg4 | sendmsg6 }" + " connect6 | sendmsg4 | sendmsg6 |\n" \ + " recvmsg4 | recvmsg6 | sysctl |\n" \ + " getsockopt | setsockopt }" + +static unsigned int query_flags; static const char * const attach_type_strings[] = { [BPF_CGROUP_INET_INGRESS] = "ingress", @@ -41,6 +45,11 @@ static const char * const attach_type_strings[] = { [BPF_CGROUP_INET6_POST_BIND] = "post_bind6", [BPF_CGROUP_UDP4_SENDMSG] = "sendmsg4", [BPF_CGROUP_UDP6_SENDMSG] = "sendmsg6", + [BPF_CGROUP_SYSCTL] = "sysctl", + [BPF_CGROUP_UDP4_RECVMSG] = "recvmsg4", + [BPF_CGROUP_UDP6_RECVMSG] = "recvmsg6", + [BPF_CGROUP_GETSOCKOPT] = "getsockopt", + [BPF_CGROUP_SETSOCKOPT] = "setsockopt", [__MAX_BPF_ATTACH_TYPE] = NULL, }; @@ -100,7 +109,8 @@ static int count_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type) __u32 prog_cnt = 0; int ret; - ret = bpf_prog_query(cgroup_fd, type, 0, NULL, NULL, &prog_cnt); + ret = bpf_prog_query(cgroup_fd, type, query_flags, NULL, + NULL, &prog_cnt); if (ret) return -1; @@ -110,16 +120,16 @@ static int count_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type) static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type, int level) { + const char *attach_flags_str; __u32 prog_ids[1024] = {0}; - char *attach_flags_str; __u32 prog_cnt, iter; __u32 attach_flags; char buf[32]; int ret; prog_cnt = ARRAY_SIZE(prog_ids); - ret = bpf_prog_query(cgroup_fd, type, 0, &attach_flags, prog_ids, - &prog_cnt); + ret = bpf_prog_query(cgroup_fd, type, query_flags, &attach_flags, + prog_ids, &prog_cnt); if (ret) return ret; @@ -151,20 +161,34 @@ static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type, static int do_show(int argc, char **argv) { enum bpf_attach_type type; + const char *path; int cgroup_fd; int ret = -1; - if (argc < 1) { - p_err("too few parameters for cgroup show"); - goto exit; - } else if (argc > 1) { - p_err("too many parameters for cgroup show"); - goto exit; + query_flags = 0; + + if (!REQ_ARGS(1)) + return -1; + path = GET_ARG(); + + while (argc) { + if (is_prefix(*argv, "effective")) { + if (query_flags & BPF_F_QUERY_EFFECTIVE) { + p_err("duplicated argument: %s", *argv); + return -1; + } + query_flags |= BPF_F_QUERY_EFFECTIVE; + NEXT_ARG(); + } else { + p_err("expected no more arguments, 'effective', got: '%s'?", + *argv); + return -1; + } } - cgroup_fd = open(argv[0], O_RDONLY); + cgroup_fd = open(path, O_RDONLY); if (cgroup_fd < 0) { - p_err("can't open cgroup %s", argv[1]); + p_err("can't open cgroup %s", path); goto exit; } @@ -248,6 +272,13 @@ static int do_show_tree_fn(const char *fpath, const struct stat *sb, for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) show_attached_bpf_progs(cgroup_fd, type, ftw->level); + if (errno == EINVAL) + /* Last attach type does not support query. + * Do not report an error for this, especially because batch + * mode would stop processing commands. + */ + errno = 0; + if (json_output) { jsonw_end_array(json_wtr); jsonw_end_object(json_wtr); @@ -280,26 +311,37 @@ static char *find_cgroup_root(void) static int do_show_tree(int argc, char **argv) { - char *cgroup_root; + char *cgroup_root, *cgroup_alloced = NULL; int ret; - switch (argc) { - case 0: - cgroup_root = find_cgroup_root(); - if (!cgroup_root) { + query_flags = 0; + + if (!argc) { + cgroup_alloced = find_cgroup_root(); + if (!cgroup_alloced) { p_err("cgroup v2 isn't mounted"); return -1; } - break; - case 1: - cgroup_root = argv[0]; - break; - default: - p_err("too many parameters for cgroup tree"); - return -1; + cgroup_root = cgroup_alloced; + } else { + cgroup_root = GET_ARG(); + + while (argc) { + if (is_prefix(*argv, "effective")) { + if (query_flags & BPF_F_QUERY_EFFECTIVE) { + p_err("duplicated argument: %s", *argv); + return -1; + } + query_flags |= BPF_F_QUERY_EFFECTIVE; + NEXT_ARG(); + } else { + p_err("expected no more arguments, 'effective', got: '%s'?", + *argv); + return -1; + } + } } - if (json_output) jsonw_start_array(json_wtr); else @@ -324,8 +366,7 @@ static int do_show_tree(int argc, char **argv) if (json_output) jsonw_end_array(json_wtr); - if (argc == 0) - free(cgroup_root); + free(cgroup_alloced); return ret; } @@ -345,7 +386,7 @@ static int do_attach(int argc, char **argv) cgroup_fd = open(argv[0], O_RDONLY); if (cgroup_fd < 0) { - p_err("can't open cgroup %s", argv[1]); + p_err("can't open cgroup %s", argv[0]); goto exit; } @@ -403,7 +444,7 @@ static int do_detach(int argc, char **argv) cgroup_fd = open(argv[0], O_RDONLY); if (cgroup_fd < 0) { - p_err("can't open cgroup %s", argv[1]); + p_err("can't open cgroup %s", argv[0]); goto exit; } @@ -445,8 +486,8 @@ static int do_help(int argc, char **argv) } fprintf(stderr, - "Usage: %s %s { show | list } CGROUP\n" - " %s %s tree [CGROUP_ROOT]\n" + "Usage: %s %s { show | list } CGROUP [**effective**]\n" + " %s %s tree [CGROUP_ROOT] [**effective**]\n" " %s %s attach CGROUP ATTACH_TYPE PROG [ATTACH_FLAGS]\n" " %s %s detach CGROUP ATTACH_TYPE PROG\n" " %s %s help\n" diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index f7261fad45c1..88264abaa738 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -21,6 +21,7 @@ #include <sys/vfs.h> #include <bpf.h> +#include <libbpf.h> /* libbpf_num_possible_cpus */ #include "main.h" @@ -28,7 +29,7 @@ #define BPF_FS_MAGIC 0xcafe4a11 #endif -void __printf(1, 2) p_err(const char *fmt, ...) +void p_err(const char *fmt, ...) { va_list ap; @@ -46,7 +47,7 @@ void __printf(1, 2) p_err(const char *fmt, ...) va_end(ap); } -void __printf(1, 2) p_info(const char *fmt, ...) +void p_info(const char *fmt, ...) { va_list ap; @@ -203,7 +204,11 @@ int do_pin_fd(int fd, const char *name) if (err) return err; - return bpf_obj_pin(fd, name); + err = bpf_obj_pin(fd, name); + if (err) + p_err("can't pin the object (%s): %s", name, strerror(errno)); + + return err; } int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32)) @@ -236,7 +241,7 @@ int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32)) fd = get_fd_by_id(id); if (fd < 0) { - p_err("can't get prog by id (%u): %s", id, strerror(errno)); + p_err("can't open object by id (%u): %s", id, strerror(errno)); return -1; } @@ -439,57 +444,13 @@ unsigned int get_page_size(void) unsigned int get_possible_cpus(void) { - static unsigned int result; - char buf[128]; - long int n; - char *ptr; - int fd; - - if (result) - return result; - - fd = open("/sys/devices/system/cpu/possible", O_RDONLY); - if (fd < 0) { - p_err("can't open sysfs possible cpus"); - exit(-1); - } - - n = read(fd, buf, sizeof(buf)); - if (n < 2) { - p_err("can't read sysfs possible cpus"); - exit(-1); - } - close(fd); + int cpus = libbpf_num_possible_cpus(); - if (n == sizeof(buf)) { - p_err("read sysfs possible cpus overflow"); + if (cpus < 0) { + p_err("Can't get # of possible cpus: %s", strerror(-cpus)); exit(-1); } - - ptr = buf; - n = 0; - while (*ptr && *ptr != '\n') { - unsigned int a, b; - - if (sscanf(ptr, "%u-%u", &a, &b) == 2) { - n += b - a + 1; - - ptr = strchr(ptr, '-') + 1; - } else if (sscanf(ptr, "%u", &a) == 1) { - n++; - } else { - assert(0); - } - - while (isdigit(*ptr)) - ptr++; - if (*ptr == ',') - ptr++; - } - - result = n; - - return result; + return cpus; } static char * diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c index d672d9086fff..03bdc5b3ac49 100644 --- a/tools/bpf/bpftool/feature.c +++ b/tools/bpf/bpftool/feature.c @@ -14,6 +14,7 @@ #include <bpf.h> #include <libbpf.h> +#include <zlib.h> #include "main.h" @@ -284,34 +285,32 @@ static void probe_jit_limit(void) } } -static char *get_kernel_config_option(FILE *fd, const char *option) +static bool read_next_kernel_config_option(gzFile file, char *buf, size_t n, + char **value) { - size_t line_n = 0, optlen = strlen(option); - char *res, *strval, *line = NULL; - ssize_t n; + char *sep; - rewind(fd); - while ((n = getline(&line, &line_n, fd)) > 0) { - if (strncmp(line, option, optlen)) + while (gzgets(file, buf, n)) { + if (strncmp(buf, "CONFIG_", 7)) continue; - /* Check we have at least '=', value, and '\n' */ - if (strlen(line) < optlen + 3) - continue; - if (*(line + optlen) != '=') + + sep = strchr(buf, '='); + if (!sep) continue; /* Trim ending '\n' */ - line[strlen(line) - 1] = '\0'; + buf[strlen(buf) - 1] = '\0'; + + /* Split on '=' and ensure that a value is present. */ + *sep = '\0'; + if (!sep[1]) + continue; - /* Copy and return config option value */ - strval = line + optlen + 1; - res = strdup(strval); - free(line); - return res; + *value = sep + 1; + return true; } - free(line); - return NULL; + return false; } static void probe_kernel_image_config(void) @@ -386,59 +385,61 @@ static void probe_kernel_image_config(void) /* test_bpf module for BPF tests */ "CONFIG_TEST_BPF", }; - char *value, *buf = NULL; + char *values[ARRAY_SIZE(options)] = { }; struct utsname utsn; char path[PATH_MAX]; - size_t i, n; - ssize_t ret; - FILE *fd; + gzFile file = NULL; + char buf[4096]; + char *value; + size_t i; - if (uname(&utsn)) - goto no_config; + if (!uname(&utsn)) { + snprintf(path, sizeof(path), "/boot/config-%s", utsn.release); - snprintf(path, sizeof(path), "/boot/config-%s", utsn.release); + /* gzopen also accepts uncompressed files. */ + file = gzopen(path, "r"); + } - fd = fopen(path, "r"); - if (!fd && errno == ENOENT) { - /* Some distributions put the config file at /proc/config, give - * it a try. - * Sometimes it is also at /proc/config.gz but we do not try - * this one for now, it would require linking against libz. + if (!file) { + /* Some distributions build with CONFIG_IKCONFIG=y and put the + * config file at /proc/config.gz. */ - fd = fopen("/proc/config", "r"); + file = gzopen("/proc/config.gz", "r"); } - if (!fd) { + if (!file) { p_info("skipping kernel config, can't open file: %s", strerror(errno)); - goto no_config; + goto end_parse; } /* Sanity checks */ - ret = getline(&buf, &n, fd); - ret = getline(&buf, &n, fd); - if (!buf || !ret) { + if (!gzgets(file, buf, sizeof(buf)) || + !gzgets(file, buf, sizeof(buf))) { p_info("skipping kernel config, can't read from file: %s", strerror(errno)); - free(buf); - goto no_config; + goto end_parse; } if (strcmp(buf, "# Automatically generated file; DO NOT EDIT.\n")) { p_info("skipping kernel config, can't find correct file"); - free(buf); - goto no_config; + goto end_parse; } - free(buf); - for (i = 0; i < ARRAY_SIZE(options); i++) { - value = get_kernel_config_option(fd, options[i]); - print_kernel_option(options[i], value); - free(value); + while (read_next_kernel_config_option(file, buf, sizeof(buf), &value)) { + for (i = 0; i < ARRAY_SIZE(options); i++) { + if (values[i] || strcmp(buf, options[i])) + continue; + + values[i] = strdup(value); + } } - fclose(fd); - return; -no_config: - for (i = 0; i < ARRAY_SIZE(options); i++) - print_kernel_option(options[i], NULL); +end_parse: + if (file) + gzclose(file); + + for (i = 0; i < ARRAY_SIZE(options); i++) { + print_kernel_option(options[i], values[i]); + free(values[i]); + } } static bool probe_bpf_syscall(const char *define_prefix) diff --git a/tools/bpf/bpftool/jit_disasm.c b/tools/bpf/bpftool/jit_disasm.c index 3ef3093560ba..bfed711258ce 100644 --- a/tools/bpf/bpftool/jit_disasm.c +++ b/tools/bpf/bpftool/jit_disasm.c @@ -11,6 +11,8 @@ * Licensed under the GNU General Public License, version 2.0 (GPLv2) */ +#define _GNU_SOURCE +#include <stdio.h> #include <stdarg.h> #include <stdint.h> #include <stdio.h> @@ -44,11 +46,13 @@ static int fprintf_json(void *out, const char *fmt, ...) char *s; va_start(ap, fmt); + if (vasprintf(&s, fmt, ap) < 0) + return -1; + va_end(ap); + if (!oper_count) { int i; - s = va_arg(ap, char *); - /* Strip trailing spaces */ i = strlen(s) - 1; while (s[i] == ' ') @@ -61,11 +65,10 @@ static int fprintf_json(void *out, const char *fmt, ...) } else if (!strcmp(fmt, ",")) { /* Skip */ } else { - s = va_arg(ap, char *); jsonw_string(json_wtr, s); oper_count++; } - va_end(ap); + free(s); return 0; } diff --git a/tools/bpf/bpftool/json_writer.c b/tools/bpf/bpftool/json_writer.c index 6046dcab51cc..86501cd3c763 100644 --- a/tools/bpf/bpftool/json_writer.c +++ b/tools/bpf/bpftool/json_writer.c @@ -15,7 +15,6 @@ #include <malloc.h> #include <inttypes.h> #include <stdint.h> -#include <linux/compiler.h> #include "json_writer.h" @@ -153,8 +152,7 @@ void jsonw_name(json_writer_t *self, const char *name) putc(' ', self->out); } -void __printf(2, 0) -jsonw_vprintf_enquote(json_writer_t *self, const char *fmt, va_list ap) +void jsonw_vprintf_enquote(json_writer_t *self, const char *fmt, va_list ap) { jsonw_eor(self); putc('"', self->out); @@ -162,7 +160,7 @@ jsonw_vprintf_enquote(json_writer_t *self, const char *fmt, va_list ap) putc('"', self->out); } -void __printf(2, 3) jsonw_printf(json_writer_t *self, const char *fmt, ...) +void jsonw_printf(json_writer_t *self, const char *fmt, ...) { va_list ap; diff --git a/tools/bpf/bpftool/json_writer.h b/tools/bpf/bpftool/json_writer.h index cb9a1993681c..35cf1f00f96c 100644 --- a/tools/bpf/bpftool/json_writer.h +++ b/tools/bpf/bpftool/json_writer.h @@ -14,6 +14,7 @@ #include <stdbool.h> #include <stdint.h> #include <stdarg.h> +#include <linux/compiler.h> /* Opaque class structure */ typedef struct json_writer json_writer_t; @@ -30,8 +31,9 @@ void jsonw_pretty(json_writer_t *self, bool on); void jsonw_name(json_writer_t *self, const char *name); /* Add value */ -void jsonw_vprintf_enquote(json_writer_t *self, const char *fmt, va_list ap); -void jsonw_printf(json_writer_t *self, const char *fmt, ...); +void __printf(2, 0) jsonw_vprintf_enquote(json_writer_t *self, const char *fmt, + va_list ap); +void __printf(2, 3) jsonw_printf(json_writer_t *self, const char *fmt, ...); void jsonw_string(json_writer_t *self, const char *value); void jsonw_bool(json_writer_t *self, bool value); void jsonw_float(json_writer_t *self, double number); diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index a9d5e9e6a732..4764581ff9ea 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -10,6 +10,7 @@ #include <string.h> #include <bpf.h> +#include <libbpf.h> #include "main.h" @@ -25,7 +26,8 @@ bool pretty_output; bool json_output; bool show_pinned; bool block_mount; -int bpf_flags; +bool verifier_logs; +bool relaxed_maps; struct pinned_obj_table prog_table; struct pinned_obj_table map_table; @@ -56,7 +58,7 @@ static int do_help(int argc, char **argv) " %s batch file FILE\n" " %s version\n" "\n" - " OBJECT := { prog | map | cgroup | perf | net | feature }\n" + " OBJECT := { prog | map | cgroup | perf | net | feature | btf }\n" " " HELP_SPEC_OPTIONS "\n" "", bin_name, bin_name, bin_name); @@ -77,6 +79,13 @@ static int do_version(int argc, char **argv) return 0; } +static int __printf(2, 0) +print_all_levels(__maybe_unused enum libbpf_print_level level, + const char *format, va_list args) +{ + return vfprintf(stderr, format, args); +} + int cmd_select(const struct cmd *cmds, int argc, char **argv, int (*help)(int argc, char **argv)) { @@ -108,6 +117,35 @@ bool is_prefix(const char *pfx, const char *str) return !memcmp(str, pfx, strlen(pfx)); } +/* Last argument MUST be NULL pointer */ +int detect_common_prefix(const char *arg, ...) +{ + unsigned int count = 0; + const char *ref; + char msg[256]; + va_list ap; + + snprintf(msg, sizeof(msg), "ambiguous prefix: '%s' could be '", arg); + va_start(ap, arg); + while ((ref = va_arg(ap, const char *))) { + if (!is_prefix(arg, ref)) + continue; + count++; + if (count > 1) + strncat(msg, "' or '", sizeof(msg) - strlen(msg) - 1); + strncat(msg, ref, sizeof(msg) - strlen(msg) - 1); + } + va_end(ap); + strncat(msg, "'", sizeof(msg) - strlen(msg) - 1); + + if (count >= 2) { + p_err("%s", msg); + return -1; + } + + return 0; +} + void fprint_hex(FILE *f, void *arg, unsigned int n, const char *sep) { unsigned char *data = arg; @@ -188,6 +226,7 @@ static const struct cmd cmds[] = { { "perf", do_perf }, { "net", do_net }, { "feature", do_feature }, + { "btf", do_btf }, { "version", do_version }, { 0 } }; @@ -316,6 +355,7 @@ int main(int argc, char **argv) { "bpffs", no_argument, NULL, 'f' }, { "mapcompat", no_argument, NULL, 'm' }, { "nomount", no_argument, NULL, 'n' }, + { "debug", no_argument, NULL, 'd' }, { 0 } }; int opt, ret; @@ -331,7 +371,7 @@ int main(int argc, char **argv) hash_init(map_table.table); opterr = 0; - while ((opt = getopt_long(argc, argv, "Vhpjfmn", + while ((opt = getopt_long(argc, argv, "Vhpjfmnd", options, NULL)) >= 0) { switch (opt) { case 'V': @@ -356,11 +396,15 @@ int main(int argc, char **argv) show_pinned = true; break; case 'm': - bpf_flags = MAPS_RELAX_COMPAT; + relaxed_maps = true; break; case 'n': block_mount = true; break; + case 'd': + libbpf_set_print(print_all_levels); + verifier_logs = true; + break; default: p_err("unrecognized option '%s'", argv[optind - 1]); if (json_output) diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index d7dd84d3c660..2899095f8254 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -73,6 +73,9 @@ static const char * const prog_type_name[] = { [BPF_PROG_TYPE_LIRC_MODE2] = "lirc_mode2", [BPF_PROG_TYPE_SK_REUSEPORT] = "sk_reuseport", [BPF_PROG_TYPE_FLOW_DISSECTOR] = "flow_dissector", + [BPF_PROG_TYPE_CGROUP_SYSCTL] = "cgroup_sysctl", + [BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE] = "raw_tracepoint_writable", + [BPF_PROG_TYPE_CGROUP_SOCKOPT] = "cgroup_sockopt", }; extern const char * const map_type_name[]; @@ -90,14 +93,16 @@ extern json_writer_t *json_wtr; extern bool json_output; extern bool show_pinned; extern bool block_mount; -extern int bpf_flags; +extern bool verifier_logs; +extern bool relaxed_maps; extern struct pinned_obj_table prog_table; extern struct pinned_obj_table map_table; -void p_err(const char *fmt, ...); -void p_info(const char *fmt, ...); +void __printf(1, 2) p_err(const char *fmt, ...); +void __printf(1, 2) p_info(const char *fmt, ...); bool is_prefix(const char *pfx, const char *str); +int detect_common_prefix(const char *arg, ...); void fprint_hex(FILE *f, void *arg, unsigned int n, const char *sep); void usage(void) __noreturn; @@ -149,6 +154,7 @@ int do_perf(int argc, char **arg); int do_net(int argc, char **arg); int do_tracelog(int argc, char **arg); int do_feature(int argc, char **argv); +int do_btf(int argc, char **argv); int parse_u32_arg(int *argc, char ***argv, __u32 *val, const char *what); int prog_parse_fd(int *argc, char ***argv); diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index e0c650d91784..de61d73b9030 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -37,6 +37,7 @@ const char * const map_type_name[] = { [BPF_MAP_TYPE_ARRAY_OF_MAPS] = "array_of_maps", [BPF_MAP_TYPE_HASH_OF_MAPS] = "hash_of_maps", [BPF_MAP_TYPE_DEVMAP] = "devmap", + [BPF_MAP_TYPE_DEVMAP_HASH] = "devmap_hash", [BPF_MAP_TYPE_SOCKMAP] = "sockmap", [BPF_MAP_TYPE_CPUMAP] = "cpumap", [BPF_MAP_TYPE_XSKMAP] = "xskmap", @@ -46,6 +47,7 @@ const char * const map_type_name[] = { [BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE] = "percpu_cgroup_storage", [BPF_MAP_TYPE_QUEUE] = "queue", [BPF_MAP_TYPE_STACK] = "stack", + [BPF_MAP_TYPE_SK_STORAGE] = "sk_storage", }; const size_t map_type_name_size = ARRAY_SIZE(map_type_name); @@ -153,11 +155,13 @@ static int do_dump_btf(const struct btf_dumper *d, /* start of key-value pair */ jsonw_start_object(d->jw); - jsonw_name(d->jw, "key"); + if (map_info->btf_key_type_id) { + jsonw_name(d->jw, "key"); - ret = btf_dumper_type(d, map_info->btf_key_type_id, key); - if (ret) - goto err_end_obj; + ret = btf_dumper_type(d, map_info->btf_key_type_id, key); + if (ret) + goto err_end_obj; + } if (!map_is_per_cpu(map_info->type)) { jsonw_name(d->jw, "value"); @@ -259,20 +263,20 @@ static void print_entry_json(struct bpf_map_info *info, unsigned char *key, } static void print_entry_error(struct bpf_map_info *info, unsigned char *key, - const char *value) + const char *error_msg) { - int value_size = strlen(value); + int msg_size = strlen(error_msg); bool single_line, break_names; - break_names = info->key_size > 16 || value_size > 16; - single_line = info->key_size + value_size <= 24 && !break_names; + break_names = info->key_size > 16 || msg_size > 16; + single_line = info->key_size + msg_size <= 24 && !break_names; printf("key:%c", break_names ? '\n' : ' '); fprint_hex(stdout, key, info->key_size, " "); printf(single_line ? " " : "\n"); - printf("value:%c%s", break_names ? '\n' : ' ', value); + printf("value:%c%s", break_names ? '\n' : ' ', error_msg); printf("\n"); } @@ -296,11 +300,7 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key, if (info->value_size) { printf("value:%c", break_names ? '\n' : ' '); - if (value) - fprint_hex(stdout, value, info->value_size, - " "); - else - printf("<no entry>"); + fprint_hex(stdout, value, info->value_size, " "); } printf("\n"); @@ -319,11 +319,8 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key, for (i = 0; i < n; i++) { printf("value (CPU %02d):%c", i, info->value_size > 16 ? '\n' : ' '); - if (value) - fprint_hex(stdout, value + i * step, - info->value_size, " "); - else - printf("<no entry>"); + fprint_hex(stdout, value + i * step, + info->value_size, " "); printf("\n"); } } @@ -484,9 +481,11 @@ static int parse_elem(char **argv, struct bpf_map_info *info, static int show_map_close_json(int fd, struct bpf_map_info *info) { - char *memlock; + char *memlock, *frozen_str; + int frozen = 0; memlock = get_fdinfo(fd, "memlock"); + frozen_str = get_fdinfo(fd, "frozen"); jsonw_start_object(json_wtr); @@ -536,6 +535,15 @@ static int show_map_close_json(int fd, struct bpf_map_info *info) } close(fd); + if (frozen_str) { + frozen = atoi(frozen_str); + free(frozen_str); + } + jsonw_int_field(json_wtr, "frozen", frozen); + + if (info->btf_id) + jsonw_int_field(json_wtr, "btf_id", info->btf_id); + if (!hash_empty(map_table.table)) { struct pinned_obj *obj; @@ -555,9 +563,11 @@ static int show_map_close_json(int fd, struct bpf_map_info *info) static int show_map_close_plain(int fd, struct bpf_map_info *info) { - char *memlock; + char *memlock, *frozen_str; + int frozen = 0; memlock = get_fdinfo(fd, "memlock"); + frozen_str = get_fdinfo(fd, "frozen"); printf("%u: ", info->id); if (info->type < ARRAY_SIZE(map_type_name)) @@ -602,15 +612,33 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info) } close(fd); - printf("\n"); if (!hash_empty(map_table.table)) { struct pinned_obj *obj; hash_for_each_possible(map_table.table, obj, hash, info->id) { if (obj->id == info->id) - printf("\tpinned %s\n", obj->path); + printf("\n\tpinned %s", obj->path); } } + printf("\n"); + + if (frozen_str) { + frozen = atoi(frozen_str); + free(frozen_str); + } + + if (!info->btf_id && !frozen) + return 0; + + printf("\t"); + + if (info->btf_id) + printf("btf_id %d", info->btf_id); + + if (frozen) + printf("%sfrozen", info->btf_id ? " " : ""); + + printf("\n"); return 0; } @@ -713,18 +741,25 @@ static int dump_map_elem(int fd, void *key, void *value, return 0; if (json_output) { + jsonw_start_object(json_wtr); jsonw_name(json_wtr, "key"); print_hex_data_json(key, map_info->key_size); jsonw_name(json_wtr, "value"); jsonw_start_object(json_wtr); jsonw_string_field(json_wtr, "error", strerror(lookup_errno)); jsonw_end_object(json_wtr); + jsonw_end_object(json_wtr); } else { - if (errno == ENOENT) - print_entry_plain(map_info, key, NULL); - else - print_entry_error(map_info, key, - strerror(lookup_errno)); + const char *msg = NULL; + + if (lookup_errno == ENOENT) + msg = "<no entry>"; + else if (lookup_errno == ENOSPC && + map_info->type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) + msg = "<cannot read>"; + + print_entry_error(map_info, key, + msg ? : strerror(lookup_errno)); } return 0; @@ -778,6 +813,10 @@ static int do_dump(int argc, char **argv) } } + if (info.type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY && + info.value_size != 8) + p_info("Warning: cannot read values from %s map with value_size != 8", + map_type_name[info.type]); while (true) { err = bpf_map_get_next_key(fd, prev_key, key); if (err) { @@ -1151,6 +1190,9 @@ static int do_create(int argc, char **argv) return -1; } NEXT_ARG(); + } else { + p_err("unknown arg %s", *argv); + return -1; } } @@ -1220,6 +1262,35 @@ exit_free: return err; } +static int do_freeze(int argc, char **argv) +{ + int err, fd; + + if (!REQ_ARGS(2)) + return -1; + + fd = map_parse_fd(&argc, &argv); + if (fd < 0) + return -1; + + if (argc) { + close(fd); + return BAD_ARG(); + } + + err = bpf_map_freeze(fd); + close(fd); + if (err) { + p_err("failed to freeze map: %s", strerror(errno)); + return err; + } + + if (json_output) + jsonw_null(json_wtr); + + return 0; +} + static int do_help(int argc, char **argv) { if (json_output) { @@ -1244,6 +1315,7 @@ static int do_help(int argc, char **argv) " %s %s pop MAP\n" " %s %s enqueue MAP value VALUE\n" " %s %s dequeue MAP\n" + " %s %s freeze MAP\n" " %s %s help\n" "\n" " " HELP_SPEC_MAP "\n" @@ -1254,7 +1326,7 @@ static int do_help(int argc, char **argv) " TYPE := { hash | array | prog_array | perf_event_array | percpu_hash |\n" " percpu_array | stack_trace | cgroup_array | lru_hash |\n" " lru_percpu_hash | lpm_trie | array_of_maps | hash_of_maps |\n" - " devmap | sockmap | cpumap | xskmap | sockhash |\n" + " devmap | devmap_hash | sockmap | cpumap | xskmap | sockhash |\n" " cgroup_storage | reuseport_sockarray | percpu_cgroup_storage }\n" " " HELP_SPEC_OPTIONS "\n" "", @@ -1262,7 +1334,8 @@ static int do_help(int argc, char **argv) bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], - bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2]); + bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], + bin_name, argv[-2]); return 0; } @@ -1284,6 +1357,7 @@ static const struct cmd cmds[] = { { "enqueue", do_update }, { "pop", do_pop_dequeue }, { "dequeue", do_pop_dequeue }, + { "freeze", do_freeze }, { 0 } }; diff --git a/tools/bpf/bpftool/map_perf_ring.c b/tools/bpf/bpftool/map_perf_ring.c index 0507dfaf7a8f..4c5531d1a450 100644 --- a/tools/bpf/bpftool/map_perf_ring.c +++ b/tools/bpf/bpftool/map_perf_ring.c @@ -28,7 +28,7 @@ #define MMAP_PAGE_CNT 16 -static bool stop; +static volatile bool stop; struct event_ring_info { int fd; @@ -44,32 +44,44 @@ struct perf_event_sample { unsigned char data[]; }; +struct perf_event_lost { + struct perf_event_header header; + __u64 id; + __u64 lost; +}; + static void int_exit(int signo) { fprintf(stderr, "Stopping...\n"); stop = true; } +struct event_pipe_ctx { + bool all_cpus; + int cpu; + int idx; +}; + static enum bpf_perf_event_ret -print_bpf_output(struct perf_event_header *event, void *private_data) +print_bpf_output(void *private_data, int cpu, struct perf_event_header *event) { - struct perf_event_sample *e = container_of(event, struct perf_event_sample, + struct perf_event_sample *e = container_of(event, + struct perf_event_sample, header); - struct event_ring_info *ring = private_data; - struct { - struct perf_event_header header; - __u64 id; - __u64 lost; - } *lost = (typeof(lost))event; + struct perf_event_lost *lost = container_of(event, + struct perf_event_lost, + header); + struct event_pipe_ctx *ctx = private_data; + int idx = ctx->all_cpus ? cpu : ctx->idx; if (json_output) { jsonw_start_object(json_wtr); jsonw_name(json_wtr, "type"); jsonw_uint(json_wtr, e->header.type); jsonw_name(json_wtr, "cpu"); - jsonw_uint(json_wtr, ring->cpu); + jsonw_uint(json_wtr, cpu); jsonw_name(json_wtr, "index"); - jsonw_uint(json_wtr, ring->key); + jsonw_uint(json_wtr, idx); if (e->header.type == PERF_RECORD_SAMPLE) { jsonw_name(json_wtr, "timestamp"); jsonw_uint(json_wtr, e->time); @@ -89,7 +101,7 @@ print_bpf_output(struct perf_event_header *event, void *private_data) if (e->header.type == PERF_RECORD_SAMPLE) { printf("== @%lld.%09lld CPU: %d index: %d =====\n", e->time / 1000000000ULL, e->time % 1000000000ULL, - ring->cpu, ring->key); + cpu, idx); fprint_hex(stdout, e->data, e->size, " "); printf("\n"); } else if (e->header.type == PERF_RECORD_LOST) { @@ -103,87 +115,25 @@ print_bpf_output(struct perf_event_header *event, void *private_data) return LIBBPF_PERF_EVENT_CONT; } -static void -perf_event_read(struct event_ring_info *ring, void **buf, size_t *buf_len) -{ - enum bpf_perf_event_ret ret; - - ret = bpf_perf_event_read_simple(ring->mem, - MMAP_PAGE_CNT * get_page_size(), - get_page_size(), buf, buf_len, - print_bpf_output, ring); - if (ret != LIBBPF_PERF_EVENT_CONT) { - fprintf(stderr, "perf read loop failed with %d\n", ret); - stop = true; - } -} - -static int perf_mmap_size(void) -{ - return get_page_size() * (MMAP_PAGE_CNT + 1); -} - -static void *perf_event_mmap(int fd) -{ - int mmap_size = perf_mmap_size(); - void *base; - - base = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); - if (base == MAP_FAILED) { - p_err("event mmap failed: %s\n", strerror(errno)); - return NULL; - } - - return base; -} - -static void perf_event_unmap(void *mem) -{ - if (munmap(mem, perf_mmap_size())) - fprintf(stderr, "Can't unmap ring memory!\n"); -} - -static int bpf_perf_event_open(int map_fd, int key, int cpu) +int do_event_pipe(int argc, char **argv) { - struct perf_event_attr attr = { + struct perf_event_attr perf_attr = { .sample_type = PERF_SAMPLE_RAW | PERF_SAMPLE_TIME, .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_BPF_OUTPUT, + .sample_period = 1, + .wakeup_events = 1, }; - int pmu_fd; - - pmu_fd = sys_perf_event_open(&attr, -1, cpu, -1, 0); - if (pmu_fd < 0) { - p_err("failed to open perf event %d for CPU %d", key, cpu); - return -1; - } - - if (bpf_map_update_elem(map_fd, &key, &pmu_fd, BPF_ANY)) { - p_err("failed to update map for event %d for CPU %d", key, cpu); - goto err_close; - } - if (ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0)) { - p_err("failed to enable event %d for CPU %d", key, cpu); - goto err_close; - } - - return pmu_fd; - -err_close: - close(pmu_fd); - return -1; -} - -int do_event_pipe(int argc, char **argv) -{ - int i, nfds, map_fd, index = -1, cpu = -1; struct bpf_map_info map_info = {}; - struct event_ring_info *rings; - size_t tmp_buf_sz = 0; - void *tmp_buf = NULL; - struct pollfd *pfds; + struct perf_buffer_raw_opts opts = {}; + struct event_pipe_ctx ctx = { + .all_cpus = true, + .cpu = -1, + .idx = -1, + }; + struct perf_buffer *pb; __u32 map_info_len; - bool do_all = true; + int err, map_fd; map_info_len = sizeof(map_info); map_fd = map_parse_fd_and_info(&argc, &argv, &map_info, &map_info_len); @@ -205,9 +155,9 @@ int do_event_pipe(int argc, char **argv) char *endptr; NEXT_ARG(); - cpu = strtoul(*argv, &endptr, 0); + ctx.cpu = strtoul(*argv, &endptr, 0); if (*endptr) { - p_err("can't parse %s as CPU ID", **argv); + p_err("can't parse %s as CPU ID", *argv); goto err_close_map; } @@ -216,9 +166,9 @@ int do_event_pipe(int argc, char **argv) char *endptr; NEXT_ARG(); - index = strtoul(*argv, &endptr, 0); + ctx.idx = strtoul(*argv, &endptr, 0); if (*endptr) { - p_err("can't parse %s as index", **argv); + p_err("can't parse %s as index", *argv); goto err_close_map; } @@ -228,45 +178,32 @@ int do_event_pipe(int argc, char **argv) goto err_close_map; } - do_all = false; + ctx.all_cpus = false; } - if (!do_all) { - if (index == -1 || cpu == -1) { + if (!ctx.all_cpus) { + if (ctx.idx == -1 || ctx.cpu == -1) { p_err("cpu and index must be specified together"); goto err_close_map; } - - nfds = 1; } else { - nfds = min(get_possible_cpus(), map_info.max_entries); - cpu = 0; - index = 0; + ctx.cpu = 0; + ctx.idx = 0; } - rings = calloc(nfds, sizeof(rings[0])); - if (!rings) + opts.attr = &perf_attr; + opts.event_cb = print_bpf_output; + opts.ctx = &ctx; + opts.cpu_cnt = ctx.all_cpus ? 0 : 1; + opts.cpus = &ctx.cpu; + opts.map_keys = &ctx.idx; + + pb = perf_buffer__new_raw(map_fd, MMAP_PAGE_CNT, &opts); + err = libbpf_get_error(pb); + if (err) { + p_err("failed to create perf buffer: %s (%d)", + strerror(err), err); goto err_close_map; - - pfds = calloc(nfds, sizeof(pfds[0])); - if (!pfds) - goto err_free_rings; - - for (i = 0; i < nfds; i++) { - rings[i].cpu = cpu + i; - rings[i].key = index + i; - - rings[i].fd = bpf_perf_event_open(map_fd, rings[i].key, - rings[i].cpu); - if (rings[i].fd < 0) - goto err_close_fds_prev; - - rings[i].mem = perf_event_mmap(rings[i].fd); - if (!rings[i].mem) - goto err_close_fds_current; - - pfds[i].fd = rings[i].fd; - pfds[i].events = POLLIN; } signal(SIGINT, int_exit); @@ -277,34 +214,24 @@ int do_event_pipe(int argc, char **argv) jsonw_start_array(json_wtr); while (!stop) { - poll(pfds, nfds, 200); - for (i = 0; i < nfds; i++) - perf_event_read(&rings[i], &tmp_buf, &tmp_buf_sz); + err = perf_buffer__poll(pb, 200); + if (err < 0 && err != -EINTR) { + p_err("perf buffer polling failed: %s (%d)", + strerror(err), err); + goto err_close_pb; + } } - free(tmp_buf); if (json_output) jsonw_end_array(json_wtr); - for (i = 0; i < nfds; i++) { - perf_event_unmap(rings[i].mem); - close(rings[i].fd); - } - free(pfds); - free(rings); + perf_buffer__free(pb); close(map_fd); return 0; -err_close_fds_prev: - while (i--) { - perf_event_unmap(rings[i].mem); -err_close_fds_current: - close(rings[i].fd); - } - free(pfds); -err_free_rings: - free(rings); +err_close_pb: + perf_buffer__free(pb); err_close_map: close(map_fd); return -1; diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c index db0e7de49d49..4f52d3151616 100644 --- a/tools/bpf/bpftool/net.c +++ b/tools/bpf/bpftool/net.c @@ -3,6 +3,7 @@ #define _GNU_SOURCE #include <errno.h> +#include <fcntl.h> #include <stdlib.h> #include <string.h> #include <unistd.h> @@ -12,6 +13,8 @@ #include <linux/rtnetlink.h> #include <linux/tc_act/tc_bpf.h> #include <sys/socket.h> +#include <sys/stat.h> +#include <sys/types.h> #include <bpf.h> #include <nlattr.h> @@ -48,6 +51,39 @@ struct bpf_filter_t { int ifindex; }; +struct bpf_attach_info { + __u32 flow_dissector_id; +}; + +enum net_attach_type { + NET_ATTACH_TYPE_XDP, + NET_ATTACH_TYPE_XDP_GENERIC, + NET_ATTACH_TYPE_XDP_DRIVER, + NET_ATTACH_TYPE_XDP_OFFLOAD, +}; + +static const char * const attach_type_strings[] = { + [NET_ATTACH_TYPE_XDP] = "xdp", + [NET_ATTACH_TYPE_XDP_GENERIC] = "xdpgeneric", + [NET_ATTACH_TYPE_XDP_DRIVER] = "xdpdrv", + [NET_ATTACH_TYPE_XDP_OFFLOAD] = "xdpoffload", +}; + +const size_t net_attach_type_size = ARRAY_SIZE(attach_type_strings); + +static enum net_attach_type parse_attach_type(const char *str) +{ + enum net_attach_type type; + + for (type = 0; type < net_attach_type_size; type++) { + if (attach_type_strings[type] && + is_prefix(str, attach_type_strings[type])) + return type; + } + + return net_attach_type_size; +} + static int dump_link_nlmsg(void *cookie, void *msg, struct nlattr **tb) { struct bpf_netdev_t *netinfo = cookie; @@ -180,25 +216,190 @@ out: return 0; } +static int query_flow_dissector(struct bpf_attach_info *attach_info) +{ + __u32 attach_flags; + __u32 prog_ids[1]; + __u32 prog_cnt; + int err; + int fd; + + fd = open("/proc/self/ns/net", O_RDONLY); + if (fd < 0) { + p_err("can't open /proc/self/ns/net: %s", + strerror(errno)); + return -1; + } + prog_cnt = ARRAY_SIZE(prog_ids); + err = bpf_prog_query(fd, BPF_FLOW_DISSECTOR, 0, + &attach_flags, prog_ids, &prog_cnt); + close(fd); + if (err) { + if (errno == EINVAL) { + /* Older kernel's don't support querying + * flow dissector programs. + */ + errno = 0; + return 0; + } + p_err("can't query prog: %s", strerror(errno)); + return -1; + } + + if (prog_cnt == 1) + attach_info->flow_dissector_id = prog_ids[0]; + + return 0; +} + +static int net_parse_dev(int *argc, char ***argv) +{ + int ifindex; + + if (is_prefix(**argv, "dev")) { + NEXT_ARGP(); + + ifindex = if_nametoindex(**argv); + if (!ifindex) + p_err("invalid devname %s", **argv); + + NEXT_ARGP(); + } else { + p_err("expected 'dev', got: '%s'?", **argv); + return -1; + } + + return ifindex; +} + +static int do_attach_detach_xdp(int progfd, enum net_attach_type attach_type, + int ifindex, bool overwrite) +{ + __u32 flags = 0; + + if (!overwrite) + flags = XDP_FLAGS_UPDATE_IF_NOEXIST; + if (attach_type == NET_ATTACH_TYPE_XDP_GENERIC) + flags |= XDP_FLAGS_SKB_MODE; + if (attach_type == NET_ATTACH_TYPE_XDP_DRIVER) + flags |= XDP_FLAGS_DRV_MODE; + if (attach_type == NET_ATTACH_TYPE_XDP_OFFLOAD) + flags |= XDP_FLAGS_HW_MODE; + + return bpf_set_link_xdp_fd(ifindex, progfd, flags); +} + +static int do_attach(int argc, char **argv) +{ + enum net_attach_type attach_type; + int progfd, ifindex, err = 0; + bool overwrite = false; + + /* parse attach args */ + if (!REQ_ARGS(5)) + return -EINVAL; + + attach_type = parse_attach_type(*argv); + if (attach_type == net_attach_type_size) { + p_err("invalid net attach/detach type: %s", *argv); + return -EINVAL; + } + NEXT_ARG(); + + progfd = prog_parse_fd(&argc, &argv); + if (progfd < 0) + return -EINVAL; + + ifindex = net_parse_dev(&argc, &argv); + if (ifindex < 1) { + close(progfd); + return -EINVAL; + } + + if (argc) { + if (is_prefix(*argv, "overwrite")) { + overwrite = true; + } else { + p_err("expected 'overwrite', got: '%s'?", *argv); + close(progfd); + return -EINVAL; + } + } + + /* attach xdp prog */ + if (is_prefix("xdp", attach_type_strings[attach_type])) + err = do_attach_detach_xdp(progfd, attach_type, ifindex, + overwrite); + + if (err < 0) { + p_err("interface %s attach failed: %s", + attach_type_strings[attach_type], strerror(-err)); + return err; + } + + if (json_output) + jsonw_null(json_wtr); + + return 0; +} + +static int do_detach(int argc, char **argv) +{ + enum net_attach_type attach_type; + int progfd, ifindex, err = 0; + + /* parse detach args */ + if (!REQ_ARGS(3)) + return -EINVAL; + + attach_type = parse_attach_type(*argv); + if (attach_type == net_attach_type_size) { + p_err("invalid net attach/detach type: %s", *argv); + return -EINVAL; + } + NEXT_ARG(); + + ifindex = net_parse_dev(&argc, &argv); + if (ifindex < 1) + return -EINVAL; + + /* detach xdp prog */ + progfd = -1; + if (is_prefix("xdp", attach_type_strings[attach_type])) + err = do_attach_detach_xdp(progfd, attach_type, ifindex, NULL); + + if (err < 0) { + p_err("interface %s detach failed: %s", + attach_type_strings[attach_type], strerror(-err)); + return err; + } + + if (json_output) + jsonw_null(json_wtr); + + return 0; +} + static int do_show(int argc, char **argv) { + struct bpf_attach_info attach_info = {}; int i, sock, ret, filter_idx = -1; struct bpf_netdev_t dev_array; unsigned int nl_pid; char err_buf[256]; if (argc == 2) { - if (strcmp(argv[0], "dev") != 0) - usage(); - filter_idx = if_nametoindex(argv[1]); - if (filter_idx == 0) { - fprintf(stderr, "invalid dev name %s\n", argv[1]); + filter_idx = net_parse_dev(&argc, &argv); + if (filter_idx < 1) return -1; - } } else if (argc != 0) { usage(); } + ret = query_flow_dissector(&attach_info); + if (ret) + return -1; + sock = libbpf_netlink_open(&nl_pid); if (sock < 0) { fprintf(stderr, "failed to open netlink sock\n"); @@ -227,6 +428,12 @@ static int do_show(int argc, char **argv) } NET_END_ARRAY("\n"); } + + NET_START_ARRAY("flow_dissector", "%s:\n"); + if (attach_info.flow_dissector_id > 0) + NET_DUMP_UINT("id", "id %u", attach_info.flow_dissector_id); + NET_END_ARRAY("\n"); + NET_END_OBJECT; if (json_output) jsonw_end_array(json_wtr); @@ -251,13 +458,20 @@ static int do_help(int argc, char **argv) fprintf(stderr, "Usage: %s %s { show | list } [dev <devname>]\n" + " %s %s attach ATTACH_TYPE PROG dev <devname> [ overwrite ]\n" + " %s %s detach ATTACH_TYPE dev <devname>\n" " %s %s help\n" + "\n" + " " HELP_SPEC_PROGRAM "\n" + " ATTACH_TYPE := { xdp | xdpgeneric | xdpdrv | xdpoffload }\n" + "\n" "Note: Only xdp and tc attachments are supported now.\n" " For progs attached to cgroups, use \"bpftool cgroup\"\n" " to dump program attachments. For program types\n" " sk_{filter,skb,msg,reuseport} and lwt/seg6, please\n" " consult iproute2.\n", - bin_name, argv[-2], bin_name, argv[-2]); + bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], + bin_name, argv[-2]); return 0; } @@ -265,6 +479,8 @@ static int do_help(int argc, char **argv) static const struct cmd cmds[] = { { "show", do_show }, { "list", do_show }, + { "attach", do_attach }, + { "detach", do_detach }, { "help", do_help }, { 0 } }; diff --git a/tools/bpf/bpftool/perf.c b/tools/bpf/bpftool/perf.c index f2a545e667c4..b2046f33e23f 100644 --- a/tools/bpf/bpftool/perf.c +++ b/tools/bpf/bpftool/perf.c @@ -104,6 +104,8 @@ static void print_perf_json(int pid, int fd, __u32 prog_id, __u32 fd_type, jsonw_string_field(json_wtr, "filename", buf); jsonw_lluint_field(json_wtr, "offset", probe_offset); break; + default: + break; } jsonw_end_object(json_wtr); } @@ -140,6 +142,8 @@ static void print_perf_plain(int pid, int fd, __u32 prog_id, __u32 fd_type, printf("uretprobe filename %s offset %llu\n", buf, probe_offset); break; + default: + break; } } diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index d2be5a06c339..4535c863d2cd 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -15,6 +15,7 @@ #include <sys/stat.h> #include <linux/err.h> +#include <linux/sizes.h> #include <bpf.h> #include <btf.h> @@ -249,6 +250,9 @@ static void print_prog_json(struct bpf_prog_info *info, int fd) if (info->nr_map_ids) show_prog_maps(fd, info->nr_map_ids); + if (info->btf_id) + jsonw_int_field(json_wtr, "btf_id", info->btf_id); + if (!hash_empty(prog_table.table)) { struct pinned_obj *obj; @@ -319,6 +323,9 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd) } } + if (info->btf_id) + printf("\n\tbtf_id %d", info->btf_id); + printf("\n"); } @@ -356,7 +363,9 @@ static int do_show(int argc, char **argv) if (fd < 0) return -1; - return show_prog(fd); + err = show_prog(fd); + close(fd); + return err; } if (argc) @@ -742,12 +751,352 @@ static int do_detach(int argc, char **argv) return 0; } +static int check_single_stdin(char *file_data_in, char *file_ctx_in) +{ + if (file_data_in && file_ctx_in && + !strcmp(file_data_in, "-") && !strcmp(file_ctx_in, "-")) { + p_err("cannot use standard input for both data_in and ctx_in"); + return -1; + } + + return 0; +} + +static int get_run_data(const char *fname, void **data_ptr, unsigned int *size) +{ + size_t block_size = 256; + size_t buf_size = block_size; + size_t nb_read = 0; + void *tmp; + FILE *f; + + if (!fname) { + *data_ptr = NULL; + *size = 0; + return 0; + } + + if (!strcmp(fname, "-")) + f = stdin; + else + f = fopen(fname, "r"); + if (!f) { + p_err("failed to open %s: %s", fname, strerror(errno)); + return -1; + } + + *data_ptr = malloc(block_size); + if (!*data_ptr) { + p_err("failed to allocate memory for data_in/ctx_in: %s", + strerror(errno)); + goto err_fclose; + } + + while ((nb_read += fread(*data_ptr + nb_read, 1, block_size, f))) { + if (feof(f)) + break; + if (ferror(f)) { + p_err("failed to read data_in/ctx_in from %s: %s", + fname, strerror(errno)); + goto err_free; + } + if (nb_read > buf_size - block_size) { + if (buf_size == UINT32_MAX) { + p_err("data_in/ctx_in is too long (max: %d)", + UINT32_MAX); + goto err_free; + } + /* No space for fread()-ing next chunk; realloc() */ + buf_size *= 2; + tmp = realloc(*data_ptr, buf_size); + if (!tmp) { + p_err("failed to reallocate data_in/ctx_in: %s", + strerror(errno)); + goto err_free; + } + *data_ptr = tmp; + } + } + if (f != stdin) + fclose(f); + + *size = nb_read; + return 0; + +err_free: + free(*data_ptr); + *data_ptr = NULL; +err_fclose: + if (f != stdin) + fclose(f); + return -1; +} + +static void hex_print(void *data, unsigned int size, FILE *f) +{ + size_t i, j; + char c; + + for (i = 0; i < size; i += 16) { + /* Row offset */ + fprintf(f, "%07zx\t", i); + + /* Hexadecimal values */ + for (j = i; j < i + 16 && j < size; j++) + fprintf(f, "%02x%s", *(uint8_t *)(data + j), + j % 2 ? " " : ""); + for (; j < i + 16; j++) + fprintf(f, " %s", j % 2 ? " " : ""); + + /* ASCII values (if relevant), '.' otherwise */ + fprintf(f, "| "); + for (j = i; j < i + 16 && j < size; j++) { + c = *(char *)(data + j); + if (c < ' ' || c > '~') + c = '.'; + fprintf(f, "%c%s", c, j == i + 7 ? " " : ""); + } + + fprintf(f, "\n"); + } +} + +static int +print_run_output(void *data, unsigned int size, const char *fname, + const char *json_key) +{ + size_t nb_written; + FILE *f; + + if (!fname) + return 0; + + if (!strcmp(fname, "-")) { + f = stdout; + if (json_output) { + jsonw_name(json_wtr, json_key); + print_data_json(data, size); + } else { + hex_print(data, size, f); + } + return 0; + } + + f = fopen(fname, "w"); + if (!f) { + p_err("failed to open %s: %s", fname, strerror(errno)); + return -1; + } + + nb_written = fwrite(data, 1, size, f); + fclose(f); + if (nb_written != size) { + p_err("failed to write output data/ctx: %s", strerror(errno)); + return -1; + } + + return 0; +} + +static int alloc_run_data(void **data_ptr, unsigned int size_out) +{ + *data_ptr = calloc(size_out, 1); + if (!*data_ptr) { + p_err("failed to allocate memory for output data/ctx: %s", + strerror(errno)); + return -1; + } + + return 0; +} + +static int do_run(int argc, char **argv) +{ + char *data_fname_in = NULL, *data_fname_out = NULL; + char *ctx_fname_in = NULL, *ctx_fname_out = NULL; + struct bpf_prog_test_run_attr test_attr = {0}; + const unsigned int default_size = SZ_32K; + void *data_in = NULL, *data_out = NULL; + void *ctx_in = NULL, *ctx_out = NULL; + unsigned int repeat = 1; + int fd, err; + + if (!REQ_ARGS(4)) + return -1; + + fd = prog_parse_fd(&argc, &argv); + if (fd < 0) + return -1; + + while (argc) { + if (detect_common_prefix(*argv, "data_in", "data_out", + "data_size_out", NULL)) + return -1; + if (detect_common_prefix(*argv, "ctx_in", "ctx_out", + "ctx_size_out", NULL)) + return -1; + + if (is_prefix(*argv, "data_in")) { + NEXT_ARG(); + if (!REQ_ARGS(1)) + return -1; + + data_fname_in = GET_ARG(); + if (check_single_stdin(data_fname_in, ctx_fname_in)) + return -1; + } else if (is_prefix(*argv, "data_out")) { + NEXT_ARG(); + if (!REQ_ARGS(1)) + return -1; + + data_fname_out = GET_ARG(); + } else if (is_prefix(*argv, "data_size_out")) { + char *endptr; + + NEXT_ARG(); + if (!REQ_ARGS(1)) + return -1; + + test_attr.data_size_out = strtoul(*argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as output data size", + *argv); + return -1; + } + NEXT_ARG(); + } else if (is_prefix(*argv, "ctx_in")) { + NEXT_ARG(); + if (!REQ_ARGS(1)) + return -1; + + ctx_fname_in = GET_ARG(); + if (check_single_stdin(data_fname_in, ctx_fname_in)) + return -1; + } else if (is_prefix(*argv, "ctx_out")) { + NEXT_ARG(); + if (!REQ_ARGS(1)) + return -1; + + ctx_fname_out = GET_ARG(); + } else if (is_prefix(*argv, "ctx_size_out")) { + char *endptr; + + NEXT_ARG(); + if (!REQ_ARGS(1)) + return -1; + + test_attr.ctx_size_out = strtoul(*argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as output context size", + *argv); + return -1; + } + NEXT_ARG(); + } else if (is_prefix(*argv, "repeat")) { + char *endptr; + + NEXT_ARG(); + if (!REQ_ARGS(1)) + return -1; + + repeat = strtoul(*argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as repeat number", + *argv); + return -1; + } + NEXT_ARG(); + } else { + p_err("expected no more arguments, 'data_in', 'data_out', 'data_size_out', 'ctx_in', 'ctx_out', 'ctx_size_out' or 'repeat', got: '%s'?", + *argv); + return -1; + } + } + + err = get_run_data(data_fname_in, &data_in, &test_attr.data_size_in); + if (err) + return -1; + + if (data_in) { + if (!test_attr.data_size_out) + test_attr.data_size_out = default_size; + err = alloc_run_data(&data_out, test_attr.data_size_out); + if (err) + goto free_data_in; + } + + err = get_run_data(ctx_fname_in, &ctx_in, &test_attr.ctx_size_in); + if (err) + goto free_data_out; + + if (ctx_in) { + if (!test_attr.ctx_size_out) + test_attr.ctx_size_out = default_size; + err = alloc_run_data(&ctx_out, test_attr.ctx_size_out); + if (err) + goto free_ctx_in; + } + + test_attr.prog_fd = fd; + test_attr.repeat = repeat; + test_attr.data_in = data_in; + test_attr.data_out = data_out; + test_attr.ctx_in = ctx_in; + test_attr.ctx_out = ctx_out; + + err = bpf_prog_test_run_xattr(&test_attr); + if (err) { + p_err("failed to run program: %s", strerror(errno)); + goto free_ctx_out; + } + + err = 0; + + if (json_output) + jsonw_start_object(json_wtr); /* root */ + + /* Do not exit on errors occurring when printing output data/context, + * we still want to print return value and duration for program run. + */ + if (test_attr.data_size_out) + err += print_run_output(test_attr.data_out, + test_attr.data_size_out, + data_fname_out, "data_out"); + if (test_attr.ctx_size_out) + err += print_run_output(test_attr.ctx_out, + test_attr.ctx_size_out, + ctx_fname_out, "ctx_out"); + + if (json_output) { + jsonw_uint_field(json_wtr, "retval", test_attr.retval); + jsonw_uint_field(json_wtr, "duration", test_attr.duration); + jsonw_end_object(json_wtr); /* root */ + } else { + fprintf(stdout, "Return value: %u, duration%s: %uns\n", + test_attr.retval, + repeat > 1 ? " (average)" : "", test_attr.duration); + } + +free_ctx_out: + free(ctx_out); +free_ctx_in: + free(ctx_in); +free_data_out: + free(data_out); +free_data_in: + free(data_in); + + return err; +} + static int load_with_options(int argc, char **argv, bool first_prog_only) { + enum bpf_prog_type common_prog_type = BPF_PROG_TYPE_UNSPEC; + DECLARE_LIBBPF_OPTS(bpf_object_open_opts, open_opts, + .relaxed_maps = relaxed_maps, + ); + struct bpf_object_load_attr load_attr = { 0 }; enum bpf_attach_type expected_attach_type; - struct bpf_object_open_attr attr = { - .prog_type = BPF_PROG_TYPE_UNSPEC, - }; struct map_replace *map_replace = NULL; struct bpf_program *prog = NULL, *pos; unsigned int old_map_fds = 0; @@ -757,11 +1106,13 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) const char *pinfile; unsigned int i, j; __u32 ifindex = 0; + const char *file; int idx, err; + if (!REQ_ARGS(2)) return -1; - attr.file = GET_ARG(); + file = GET_ARG(); pinfile = GET_ARG(); while (argc) { @@ -770,7 +1121,7 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) NEXT_ARG(); - if (attr.prog_type != BPF_PROG_TYPE_UNSPEC) { + if (common_prog_type != BPF_PROG_TYPE_UNSPEC) { p_err("program type already specified"); goto err_free_reuse_maps; } @@ -787,7 +1138,7 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) strcat(type, *argv); strcat(type, "/"); - err = libbpf_prog_type_by_name(type, &attr.prog_type, + err = libbpf_prog_type_by_name(type, &common_prog_type, &expected_attach_type); free(type); if (err < 0) @@ -873,16 +1224,18 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) } } - obj = __bpf_object__open_xattr(&attr, bpf_flags); + set_max_rlimit(); + + obj = bpf_object__open_file(file, &open_opts); if (IS_ERR_OR_NULL(obj)) { p_err("failed to open object file"); goto err_free_reuse_maps; } bpf_object__for_each_program(pos, obj) { - enum bpf_prog_type prog_type = attr.prog_type; + enum bpf_prog_type prog_type = common_prog_type; - if (attr.prog_type == BPF_PROG_TYPE_UNSPEC) { + if (prog_type == BPF_PROG_TYPE_UNSPEC) { const char *sec_name = bpf_program__title(pos, false); err = libbpf_prog_type_by_name(sec_name, &prog_type, @@ -952,9 +1305,12 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) goto err_close_obj; } - set_max_rlimit(); + load_attr.obj = obj; + if (verifier_logs) + /* log_level1 + log_level2 + stats, but not stable UAPI */ + load_attr.log_level = 1 + 2 + 4; - err = bpf_object__load(obj); + err = bpf_object__load_xattr(&load_attr); if (err) { p_err("failed to load object file"); goto err_close_obj; @@ -1045,6 +1401,11 @@ static int do_help(int argc, char **argv) " [pinmaps MAP_DIR]\n" " %s %s attach PROG ATTACH_TYPE [MAP]\n" " %s %s detach PROG ATTACH_TYPE [MAP]\n" + " %s %s run PROG \\\n" + " data_in FILE \\\n" + " [data_out FILE [data_size_out L]] \\\n" + " [ctx_in FILE [ctx_out FILE [ctx_size_out M]]] \\\n" + " [repeat N]\n" " %s %s tracelog\n" " %s %s help\n" "\n" @@ -1054,17 +1415,20 @@ static int do_help(int argc, char **argv) " tracepoint | raw_tracepoint | xdp | perf_event | cgroup/skb |\n" " cgroup/sock | cgroup/dev | lwt_in | lwt_out | lwt_xmit |\n" " lwt_seg6local | sockops | sk_skb | sk_msg | lirc_mode2 |\n" - " sk_reuseport | flow_dissector |\n" + " sk_reuseport | flow_dissector | cgroup/sysctl |\n" " cgroup/bind4 | cgroup/bind6 | cgroup/post_bind4 |\n" " cgroup/post_bind6 | cgroup/connect4 | cgroup/connect6 |\n" - " cgroup/sendmsg4 | cgroup/sendmsg6 }\n" + " cgroup/sendmsg4 | cgroup/sendmsg6 | cgroup/recvmsg4 |\n" + " cgroup/recvmsg6 | cgroup/getsockopt |\n" + " cgroup/setsockopt }\n" " ATTACH_TYPE := { msg_verdict | stream_verdict | stream_parser |\n" " flow_dissector }\n" " " HELP_SPEC_OPTIONS "\n" "", bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], - bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2]); + bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], + bin_name, argv[-2]); return 0; } @@ -1080,6 +1444,7 @@ static const struct cmd cmds[] = { { "attach", do_attach }, { "detach", do_detach }, { "tracelog", do_tracelog }, + { "run", do_run }, { 0 } }; diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c index 7073dbe1ff27..494d7ae3614d 100644 --- a/tools/bpf/bpftool/xlated_dumper.c +++ b/tools/bpf/bpftool/xlated_dumper.c @@ -31,9 +31,7 @@ void kernel_syms_load(struct dump_data *dd) if (!fp) return; - while (!feof(fp)) { - if (!fgets(buff, sizeof(buff), fp)) - break; + while (fgets(buff, sizeof(buff), fp)) { tmp = reallocarray(dd->sym_mapping, dd->sym_count + 1, sizeof(*dd->sym_mapping)); if (!tmp) { @@ -195,6 +193,9 @@ static const char *print_imm(void *private_data, if (insn->src_reg == BPF_PSEUDO_MAP_FD) snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), "map[id:%u]", insn->imm); + else if (insn->src_reg == BPF_PSEUDO_MAP_VALUE) + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "map[id:%u][0]+%u", insn->imm, (insn + 1)->imm); else snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), "0x%llx", (unsigned long long)full_imm); |
