diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-07 18:49:45 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-07 18:49:45 +0000 |
commit | 2c3c1048746a4622d8c89a29670120dc8fab93c4 (patch) | |
tree | 848558de17fb3008cdf4d861b01ac7781903ce39 /tools/bpf/bpftool | |
parent | Initial commit. (diff) | |
download | linux-2c3c1048746a4622d8c89a29670120dc8fab93c4.tar.xz linux-2c3c1048746a4622d8c89a29670120dc8fab93c4.zip |
Adding upstream version 6.1.76.upstream/6.1.76
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'tools/bpf/bpftool')
48 files changed, 20843 insertions, 0 deletions
diff --git a/tools/bpf/bpftool/.gitignore b/tools/bpf/bpftool/.gitignore new file mode 100644 index 000000000..a736f64dc --- /dev/null +++ b/tools/bpf/bpftool/.gitignore @@ -0,0 +1,10 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +*.d +/bootstrap/ +/bpftool +bpftool*.8 +FEATURE-DUMP.bpftool +feature +libbpf +/*.skel.h +/vmlinux.h diff --git a/tools/bpf/bpftool/Documentation/Makefile b/tools/bpf/bpftool/Documentation/Makefile new file mode 100644 index 000000000..ac8487dcf --- /dev/null +++ b/tools/bpf/bpftool/Documentation/Makefile @@ -0,0 +1,60 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +include ../../../scripts/Makefile.include + +INSTALL ?= install +RM ?= rm -f +RMDIR ?= rmdir --ignore-fail-on-non-empty + +ifeq ($(V),1) + Q = +else + Q = @ +endif + +prefix ?= /usr/local +mandir ?= $(prefix)/man +man8dir = $(mandir)/man8 + +MAN8_RST = $(wildcard bpftool*.rst) + +_DOC_MAN8 = $(patsubst %.rst,%.8,$(MAN8_RST)) +DOC_MAN8 = $(addprefix $(OUTPUT),$(_DOC_MAN8)) + +man: man8 +man8: $(DOC_MAN8) + +RST2MAN_DEP := $(shell command -v rst2man 2>/dev/null) +RST2MAN_OPTS += --verbose --strip-comments + +list_pages = $(sort $(basename $(filter-out $(1),$(MAN8_RST)))) +see_also = $(subst " ",, \ + "\n" \ + "SEE ALSO\n" \ + "========\n" \ + "\t**bpf**\ (2),\n" \ + "\t**bpf-helpers**\\ (7)" \ + $(foreach page,$(call list_pages,$(1)),",\n\t**$(page)**\\ (8)") \ + "\n") + +$(OUTPUT)%.8: %.rst +ifndef RST2MAN_DEP + $(error "rst2man not found, but required to generate man pages") +endif + $(QUIET_GEN)( cat $< ; printf "%b" $(call see_also,$<) ) | rst2man $(RST2MAN_OPTS) > $@ + +clean: + $(call QUIET_CLEAN, Documentation) + $(Q)$(RM) $(DOC_MAN8) + +install: man + $(call QUIET_INSTALL, Documentation-man) + $(Q)$(INSTALL) -d -m 755 $(DESTDIR)$(man8dir) + $(Q)$(INSTALL) -m 644 $(DOC_MAN8) $(DESTDIR)$(man8dir) + +uninstall: + $(call QUIET_UNINST, Documentation-man) + $(Q)$(RM) $(addprefix $(DESTDIR)$(man8dir)/,$(_DOC_MAN8)) + $(Q)$(RMDIR) $(DESTDIR)$(man8dir) + +.PHONY: man man8 clean install uninstall +.DEFAULT_GOAL := man diff --git a/tools/bpf/bpftool/Documentation/bpftool-btf.rst b/tools/bpf/bpftool/Documentation/bpftool-btf.rst new file mode 100644 index 000000000..342716f74 --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-btf.rst @@ -0,0 +1,268 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + +================ +bpftool-btf +================ +------------------------------------------------------------------------------- +tool for inspection of BTF data +------------------------------------------------------------------------------- + +:Manual section: 8 + +.. include:: substitutions.rst + +SYNOPSIS +======== + + **bpftool** [*OPTIONS*] **btf** *COMMAND* + + *OPTIONS* := { |COMMON_OPTIONS| | { **-B** | **--base-btf** } } + + *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. + + Since Linux 5.8 bpftool is able to discover information about + processes that hold open file descriptors (FDs) against BTF + objects. On such kernels bpftool will automatically emit this + information as well. + + **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 +======= + .. include:: common_options.rst + + -B, --base-btf *FILE* + Pass a base BTF object. Base BTF objects are typically used + with BTF objects for kernel modules. To avoid duplicating + all kernel symbols required by modules, BTF objects for + modules are "split", they are built incrementally on top of + the kernel (vmlinux) BTF object. So the base BTF reference + should usually point to the kernel BTF. + + When the main BTF object to process (for example, the + module BTF to dump) is passed as a *FILE*, bpftool attempts + to autodetect the path for the base object, and passing + this option is optional. When the main BTF object is passed + through other handles, this option becomes necessary. + +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** + +| +| **# bpftool btf dump file /sys/kernel/btf/i2c_smbus** +| (or) +| **# I2C_SMBUS_ID=$(bpftool btf show -p | jq '.[] | select(.name=="i2c_smbus").id')** +| **# bpftool btf dump id ${I2C_SMBUS_ID} -B /sys/kernel/btf/vmlinux** + +:: + + [104848] STRUCT 'i2c_smbus_alert' size=40 vlen=2 + 'alert' type_id=393 bits_offset=0 + 'ara' type_id=56050 bits_offset=256 + [104849] STRUCT 'alert_data' size=12 vlen=3 + 'addr' type_id=16 bits_offset=0 + 'type' type_id=56053 bits_offset=32 + 'data' type_id=7 bits_offset=64 + [104850] PTR '(anon)' type_id=104848 + [104851] PTR '(anon)' type_id=104849 + [104852] FUNC 'i2c_register_spd' type_id=84745 linkage=static + [104853] FUNC 'smbalert_driver_init' type_id=1213 linkage=static + [104854] FUNC_PROTO '(anon)' ret_type_id=18 vlen=1 + 'ara' type_id=56050 + [104855] FUNC 'i2c_handle_smbus_alert' type_id=104854 linkage=static + [104856] FUNC 'smbalert_remove' type_id=104854 linkage=static + [104857] FUNC_PROTO '(anon)' ret_type_id=18 vlen=2 + 'ara' type_id=56050 + 'id' type_id=56056 + [104858] FUNC 'smbalert_probe' type_id=104857 linkage=static + [104859] FUNC 'smbalert_work' type_id=9695 linkage=static + [104860] FUNC 'smbus_alert' type_id=71367 linkage=static + [104861] FUNC 'smbus_do_alert' type_id=84827 linkage=static diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst new file mode 100644 index 000000000..bd015ec98 --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst @@ -0,0 +1,157 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + +================ +bpftool-cgroup +================ +------------------------------------------------------------------------------- +tool for inspection and simple manipulation of eBPF progs +------------------------------------------------------------------------------- + +:Manual section: 8 + +.. include:: substitutions.rst + +SYNOPSIS +======== + + **bpftool** [*OPTIONS*] **cgroup** *COMMAND* + + *OPTIONS* := { |COMMON_OPTIONS| | { **-f** | **--bpffs** } } + + *COMMANDS* := + { **show** | **list** | **tree** | **attach** | **detach** | **help** } + +CGROUP COMMANDS +=============== + +| **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** +| +| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* } +| *ATTACH_TYPE* := { **cgroup_inet_ingress** | **cgroup_inet_egress** | +| **cgroup_inet_sock_create** | **cgroup_sock_ops** | +| **cgroup_device** | **cgroup_inet4_bind** | **cgroup_inet6_bind** | +| **cgroup_inet4_post_bind** | **cgroup_inet6_post_bind** | +| **cgroup_inet4_connect** | **cgroup_inet6_connect** | +| **cgroup_inet4_getpeername** | **cgroup_inet6_getpeername** | +| **cgroup_inet4_getsockname** | **cgroup_inet6_getsockname** | +| **cgroup_udp4_sendmsg** | **cgroup_udp6_sendmsg** | +| **cgroup_udp4_recvmsg** | **cgroup_udp6_recvmsg** | +| **cgroup_sysctl** | **cgroup_getsockopt** | **cgroup_setsockopt** | +| **cgroup_inet_sock_release** } +| *ATTACH_FLAGS* := { **multi** | **override** } + +DESCRIPTION +=========== + **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. + + 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. + + The output is similar to the output of cgroup show/list + 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*. + + *ATTACH_FLAGS* can be one of: **override** if a sub-cgroup installs + some bpf program, the program in this cgroup yields to sub-cgroup + program; **multi** if a sub-cgroup installs some bpf program, + that cgroup program gets run in addition to the program in this + cgroup. + + Only one program is allowed to be attached to a cgroup with + no attach flags or the **override** flag. Attaching another + program will release old program and attach the new one. + + Multiple programs are allowed to be attached to a cgroup with + **multi**. They are executed in FIFO order (those that were + attached first, run first). + + Non-default *ATTACH_FLAGS* are supported by kernel version 4.14 + and later. + + *ATTACH_TYPE* can be on of: + **ingress** ingress path of the inet socket (since 4.10); + **egress** egress path of the inet socket (since 4.10); + **sock_create** opening of an inet socket (since 4.10); + **sock_ops** various socket operations (since 4.12); + **device** device access (since 4.15); + **bind4** call to bind(2) for an inet4 socket (since 4.17); + **bind6** call to bind(2) for an inet6 socket (since 4.17); + **post_bind4** return from bind(2) for an inet4 socket (since 4.17); + **post_bind6** return from bind(2) for an inet6 socket (since 4.17); + **connect4** call to connect(2) for an inet4 socket (since 4.17); + **connect6** call to connect(2) for an inet6 socket (since 4.17); + **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); + **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); + **getpeername4** call to getpeername(2) for an inet4 socket (since 5.8); + **getpeername6** call to getpeername(2) for an inet6 socket (since 5.8); + **getsockname4** call to getsockname(2) for an inet4 socket (since 5.8); + **getsockname6** call to getsockname(2) for an inet6 socket (since 5.8). + **sock_release** closing an userspace inet socket (since 5.9). + + **bpftool cgroup detach** *CGROUP* *ATTACH_TYPE* *PROG* + Detach *PROG* from the cgroup *CGROUP* and attach type + *ATTACH_TYPE*. + + **bpftool prog help** + Print short help message. + +OPTIONS +======= + .. include:: common_options.rst + + -f, --bpffs + Show file names of pinned programs. + +EXAMPLES +======== +| +| **# mount -t bpf none /sys/fs/bpf/** +| **# mkdir /sys/fs/cgroup/test.slice** +| **# bpftool prog load ./device_cgroup.o /sys/fs/bpf/prog** +| **# bpftool cgroup attach /sys/fs/cgroup/test.slice/ device id 1 allow_multi** + +**# bpftool cgroup list /sys/fs/cgroup/test.slice/** + +:: + + ID AttachType AttachFlags Name + 1 device allow_multi bpf_prog1 + +| +| **# bpftool cgroup detach /sys/fs/cgroup/test.slice/ device id 1** +| **# bpftool cgroup list /sys/fs/cgroup/test.slice/** + +:: + + ID AttachType AttachFlags Name diff --git a/tools/bpf/bpftool/Documentation/bpftool-feature.rst b/tools/bpf/bpftool/Documentation/bpftool-feature.rst new file mode 100644 index 000000000..e44039f89 --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-feature.rst @@ -0,0 +1,90 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + +=============== +bpftool-feature +=============== +------------------------------------------------------------------------------- +tool for inspection of eBPF-related parameters for Linux kernel or net device +------------------------------------------------------------------------------- + +:Manual section: 8 + +.. include:: substitutions.rst + +SYNOPSIS +======== + + **bpftool** [*OPTIONS*] **feature** *COMMAND* + + *OPTIONS* := { |COMMON_OPTIONS| } + + *COMMANDS* := { **probe** | **help** } + +FEATURE COMMANDS +================ + +| **bpftool** **feature probe** [*COMPONENT*] [**full**] [**unprivileged**] [**macros** [**prefix** *PREFIX*]] +| **bpftool** **feature list_builtins** *GROUP* +| **bpftool** **feature help** +| +| *COMPONENT* := { **kernel** | **dev** *NAME* } +| *GROUP* := { **prog_types** | **map_types** | **attach_types** | **link_types** | **helpers** } + +DESCRIPTION +=========== + **bpftool feature probe** [**kernel**] [**full**] [**macros** [**prefix** *PREFIX*]] + Probe the running kernel and dump a number of eBPF-related + parameters, such as availability of the **bpf**\ () system call, + JIT status, eBPF program types availability, eBPF helper + functions availability, and more. + + By default, bpftool **does not run probes** for + **bpf_probe_write_user**\ () and **bpf_trace_printk**\() + helpers which print warnings to kernel logs. To enable them + and run all probes, the **full** keyword should be used. + + If the **macros** keyword (but not the **-j** option) is + passed, a subset of the output is dumped as a list of + **#define** macros that are ready to be included in a C + header file, for example. If, additionally, **prefix** is + used to define a *PREFIX*, the provided string will be used + as a prefix to the names of the macros: this can be used to + avoid conflicts on macro names when including the output of + this command as a header file. + + Keyword **kernel** can be omitted. If no probe target is + specified, probing the kernel is the default behaviour. + + When the **unprivileged** keyword is used, bpftool will dump + only the features available to a user who does not have the + **CAP_SYS_ADMIN** capability set. The features available in + that case usually represent a small subset of the parameters + supported by the system. Unprivileged users MUST use the + **unprivileged** keyword: This is to avoid misdetection if + bpftool is inadvertently run as non-root, for example. This + keyword is unavailable if bpftool was compiled without + libcap. + + **bpftool feature probe dev** *NAME* [**full**] [**macros** [**prefix** *PREFIX*]] + Probe network device for supported eBPF features and dump + results to the console. + + The keywords **full**, **macros** and **prefix** have the + same role as when probing the kernel. + + **bpftool feature list_builtins** *GROUP* + List items known to bpftool. These can be BPF program types + (**prog_types**), BPF map types (**map_types**), attach types + (**attach_types**), link types (**link_types**), or BPF helper + functions (**helpers**). The command does not probe the system, but + simply lists the elements that bpftool knows from compilation time, + as provided from libbpf (for all object types) or from the BPF UAPI + header (list of helpers). This can be used in scripts to iterate over + BPF types or helpers. + + **bpftool feature help** + Print short help message. + +OPTIONS +======= + .. include:: common_options.rst diff --git a/tools/bpf/bpftool/Documentation/bpftool-gen.rst b/tools/bpf/bpftool/Documentation/bpftool-gen.rst new file mode 100644 index 000000000..68454ef28 --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-gen.rst @@ -0,0 +1,446 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + +================ +bpftool-gen +================ +------------------------------------------------------------------------------- +tool for BPF code-generation +------------------------------------------------------------------------------- + +:Manual section: 8 + +.. include:: substitutions.rst + +SYNOPSIS +======== + + **bpftool** [*OPTIONS*] **gen** *COMMAND* + + *OPTIONS* := { |COMMON_OPTIONS| | { **-L** | **--use-loader** } } + + *COMMAND* := { **object** | **skeleton** | **help** } + +GEN COMMANDS +============= + +| **bpftool** **gen object** *OUTPUT_FILE* *INPUT_FILE* [*INPUT_FILE*...] +| **bpftool** **gen skeleton** *FILE* [**name** *OBJECT_NAME*] +| **bpftool** **gen subskeleton** *FILE* [**name** *OBJECT_NAME*] +| **bpftool** **gen min_core_btf** *INPUT* *OUTPUT* *OBJECT* [*OBJECT*...] +| **bpftool** **gen help** + +DESCRIPTION +=========== + **bpftool gen object** *OUTPUT_FILE* *INPUT_FILE* [*INPUT_FILE*...] + Statically link (combine) together one or more *INPUT_FILE*'s + into a single resulting *OUTPUT_FILE*. All the files involved + are BPF ELF object files. + + The rules of BPF static linking are mostly the same as for + user-space object files, but in addition to combining data + and instruction sections, .BTF and .BTF.ext (if present in + any of the input files) data are combined together. .BTF + data is deduplicated, so all the common types across + *INPUT_FILE*'s will only be represented once in the resulting + BTF information. + + BPF static linking allows to partition BPF source code into + individually compiled files that are then linked into + a single resulting BPF object file, which can be used to + generated BPF skeleton (with **gen skeleton** command) or + passed directly into **libbpf** (using **bpf_object__open()** + family of APIs). + + **bpftool gen skeleton** *FILE* + Generate BPF skeleton C header file for a given *FILE*. + + BPF skeleton is an alternative interface to existing libbpf + APIs for working with BPF objects. Skeleton code is intended + to significantly shorten and simplify code to load and work + with BPF programs from userspace side. Generated code is + tailored to specific input BPF object *FILE*, reflecting its + structure by listing out available maps, program, variables, + etc. Skeleton eliminates the need to lookup mentioned + components by name. Instead, if skeleton instantiation + succeeds, they are populated in skeleton structure as valid + libbpf types (e.g., **struct bpf_map** pointer) and can be + passed to existing generic libbpf APIs. + + In addition to simple and reliable access to maps and + programs, skeleton provides a storage for BPF links (**struct + bpf_link**) for each BPF program within BPF object. When + requested, supported BPF programs will be automatically + attached and resulting BPF links stored for further use by + user in pre-allocated fields in skeleton struct. For BPF + programs that can't be automatically attached by libbpf, + user can attach them manually, but store resulting BPF link + in per-program link field. All such set up links will be + automatically destroyed on BPF skeleton destruction. This + eliminates the need for users to manage links manually and + rely on libbpf support to detach programs and free up + resources. + + Another facility provided by BPF skeleton is an interface to + global variables of all supported kinds: mutable, read-only, + as well as extern ones. This interface allows to pre-setup + initial values of variables before BPF object is loaded and + verified by kernel. For non-read-only variables, the same + interface can be used to fetch values of global variables on + userspace side, even if they are modified by BPF code. + + During skeleton generation, contents of source BPF object + *FILE* is embedded within generated code and is thus not + necessary to keep around. This ensures skeleton and BPF + object file are matching 1-to-1 and always stay in sync. + Generated code is dual-licensed under LGPL-2.1 and + BSD-2-Clause licenses. + + It is a design goal and guarantee that skeleton interfaces + are interoperable with generic libbpf APIs. User should + always be able to use skeleton API to create and load BPF + object, and later use libbpf APIs to keep working with + specific maps, programs, etc. + + As part of skeleton, few custom functions are generated. + Each of them is prefixed with object name. Object name can + either be derived from object file name, i.e., if BPF object + file name is **example.o**, BPF object name will be + **example**. Object name can be also specified explicitly + through **name** *OBJECT_NAME* parameter. The following + custom functions are provided (assuming **example** as + the object name): + + - **example__open** and **example__open_opts**. + These functions are used to instantiate skeleton. It + corresponds to libbpf's **bpf_object__open**\ () API. + **_opts** variants accepts extra **bpf_object_open_opts** + options. + + - **example__load**. + This function creates maps, loads and verifies BPF + programs, initializes global data maps. It corresponds to + libppf's **bpf_object__load**\ () API. + + - **example__open_and_load** combines **example__open** and + **example__load** invocations in one commonly used + operation. + + - **example__attach** and **example__detach** + This pair of functions allow to attach and detach, + correspondingly, already loaded BPF object. Only BPF + programs of types supported by libbpf for auto-attachment + will be auto-attached and their corresponding BPF links + instantiated. For other BPF programs, user can manually + create a BPF link and assign it to corresponding fields in + skeleton struct. **example__detach** will detach both + links created automatically, as well as those populated by + user manually. + + - **example__destroy** + Detach and unload BPF programs, free up all the resources + used by skeleton and BPF object. + + If BPF object has global variables, corresponding structs + with memory layout corresponding to global data data section + layout will be created. Currently supported ones are: *.data*, + *.bss*, *.rodata*, and *.kconfig* structs/data sections. + These data sections/structs can be used to set up initial + values of variables, if set before **example__load**. + Afterwards, if target kernel supports memory-mapped BPF + arrays, same structs can be used to fetch and update + (non-read-only) data from userspace, with same simplicity + as for BPF side. + + **bpftool gen subskeleton** *FILE* + Generate BPF subskeleton C header file for a given *FILE*. + + Subskeletons are similar to skeletons, except they do not own + the corresponding maps, programs, or global variables. They + require that the object file used to generate them is already + loaded into a *bpf_object* by some other means. + + This functionality is useful when a library is included into a + larger BPF program. A subskeleton for the library would have + access to all objects and globals defined in it, without + having to know about the larger program. + + Consequently, there are only two functions defined + for subskeletons: + + - **example__open(bpf_object\*)** + Instantiates a subskeleton from an already opened (but not + necessarily loaded) **bpf_object**. + + - **example__destroy()** + Frees the storage for the subskeleton but *does not* unload + any BPF programs or maps. + + **bpftool** **gen min_core_btf** *INPUT* *OUTPUT* *OBJECT* [*OBJECT*...] + Generate a minimum BTF file as *OUTPUT*, derived from a given + *INPUT* BTF file, containing all needed BTF types so one, or + more, given eBPF objects CO-RE relocations may be satisfied. + + When kernels aren't compiled with CONFIG_DEBUG_INFO_BTF, + libbpf, when loading an eBPF object, has to rely on external + BTF files to be able to calculate CO-RE relocations. + + Usually, an external BTF file is built from existing kernel + DWARF data using pahole. It contains all the types used by + its respective kernel image and, because of that, is big. + + The min_core_btf feature builds smaller BTF files, customized + to one or multiple eBPF objects, so they can be distributed + together with an eBPF CO-RE based application, turning the + application portable to different kernel versions. + + Check examples bellow for more information how to use it. + + **bpftool gen help** + Print short help message. + +OPTIONS +======= + .. include:: common_options.rst + + -L, --use-loader + For skeletons, generate a "light" skeleton (also known as "loader" + skeleton). A light skeleton contains a loader eBPF program. It does + not use the majority of the libbpf infrastructure, and does not need + libelf. + +EXAMPLES +======== +**$ cat example1.bpf.c** + +:: + + #include <stdbool.h> + #include <linux/ptrace.h> + #include <linux/bpf.h> + #include <bpf/bpf_helpers.h> + + const volatile int param1 = 42; + bool global_flag = true; + struct { int x; } data = {}; + + SEC("raw_tp/sys_enter") + int handle_sys_enter(struct pt_regs *ctx) + { + static long my_static_var; + if (global_flag) + my_static_var++; + else + data.x += param1; + return 0; + } + +**$ cat example2.bpf.c** + +:: + + #include <linux/ptrace.h> + #include <linux/bpf.h> + #include <bpf/bpf_helpers.h> + + struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 128); + __type(key, int); + __type(value, long); + } my_map SEC(".maps"); + + SEC("raw_tp/sys_exit") + int handle_sys_exit(struct pt_regs *ctx) + { + int zero = 0; + bpf_map_lookup_elem(&my_map, &zero); + return 0; + } + +This is example BPF application with two BPF programs and a mix of BPF maps +and global variables. Source code is split across two source code files. + +**$ clang -target bpf -g example1.bpf.c -o example1.bpf.o** + +**$ clang -target bpf -g example2.bpf.c -o example2.bpf.o** + +**$ bpftool gen object example.bpf.o example1.bpf.o example2.bpf.o** + +This set of commands compiles *example1.bpf.c* and *example2.bpf.c* +individually and then statically links respective object files into the final +BPF ELF object file *example.bpf.o*. + +**$ bpftool gen skeleton example.bpf.o name example | tee example.skel.h** + +:: + + /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + + /* THIS FILE IS AUTOGENERATED! */ + #ifndef __EXAMPLE_SKEL_H__ + #define __EXAMPLE_SKEL_H__ + + #include <stdlib.h> + #include <bpf/libbpf.h> + + struct example { + struct bpf_object_skeleton *skeleton; + struct bpf_object *obj; + struct { + struct bpf_map *rodata; + struct bpf_map *data; + struct bpf_map *bss; + struct bpf_map *my_map; + } maps; + struct { + struct bpf_program *handle_sys_enter; + struct bpf_program *handle_sys_exit; + } progs; + struct { + struct bpf_link *handle_sys_enter; + struct bpf_link *handle_sys_exit; + } links; + struct example__bss { + struct { + int x; + } data; + } *bss; + struct example__data { + _Bool global_flag; + long int handle_sys_enter_my_static_var; + } *data; + struct example__rodata { + int param1; + } *rodata; + }; + + static void example__destroy(struct example *obj); + static inline struct example *example__open_opts( + const struct bpf_object_open_opts *opts); + static inline struct example *example__open(); + static inline int example__load(struct example *obj); + static inline struct example *example__open_and_load(); + static inline int example__attach(struct example *obj); + static inline void example__detach(struct example *obj); + + #endif /* __EXAMPLE_SKEL_H__ */ + +**$ cat example.c** + +:: + + #include "example.skel.h" + + int main() + { + struct example *skel; + int err = 0; + + skel = example__open(); + if (!skel) + goto cleanup; + + skel->rodata->param1 = 128; + + err = example__load(skel); + if (err) + goto cleanup; + + err = example__attach(skel); + if (err) + goto cleanup; + + /* all libbpf APIs are usable */ + printf("my_map name: %s\n", bpf_map__name(skel->maps.my_map)); + printf("sys_enter prog FD: %d\n", + bpf_program__fd(skel->progs.handle_sys_enter)); + + /* detach and re-attach sys_exit program */ + bpf_link__destroy(skel->links.handle_sys_exit); + skel->links.handle_sys_exit = + bpf_program__attach(skel->progs.handle_sys_exit); + + printf("my_static_var: %ld\n", + skel->bss->handle_sys_enter_my_static_var); + + cleanup: + example__destroy(skel); + return err; + } + +**# ./example** + +:: + + my_map name: my_map + sys_enter prog FD: 8 + my_static_var: 7 + +This is a stripped-out version of skeleton generated for above example code. + +min_core_btf +------------ + +**$ bpftool btf dump file 5.4.0-example.btf format raw** + +:: + + [1] INT 'long unsigned int' size=8 bits_offset=0 nr_bits=64 encoding=(none) + [2] CONST '(anon)' type_id=1 + [3] VOLATILE '(anon)' type_id=1 + [4] ARRAY '(anon)' type_id=1 index_type_id=21 nr_elems=2 + [5] PTR '(anon)' type_id=8 + [6] CONST '(anon)' type_id=5 + [7] INT 'char' size=1 bits_offset=0 nr_bits=8 encoding=(none) + [8] CONST '(anon)' type_id=7 + [9] INT 'unsigned int' size=4 bits_offset=0 nr_bits=32 encoding=(none) + <long output> + +**$ bpftool btf dump file one.bpf.o format raw** + +:: + + [1] PTR '(anon)' type_id=2 + [2] STRUCT 'trace_event_raw_sys_enter' size=64 vlen=4 + 'ent' type_id=3 bits_offset=0 + 'id' type_id=7 bits_offset=64 + 'args' type_id=9 bits_offset=128 + '__data' type_id=12 bits_offset=512 + [3] STRUCT 'trace_entry' size=8 vlen=4 + 'type' type_id=4 bits_offset=0 + 'flags' type_id=5 bits_offset=16 + 'preempt_count' type_id=5 bits_offset=24 + <long output> + +**$ bpftool gen min_core_btf 5.4.0-example.btf 5.4.0-smaller.btf one.bpf.o** + +**$ bpftool btf dump file 5.4.0-smaller.btf format raw** + +:: + + [1] TYPEDEF 'pid_t' type_id=6 + [2] STRUCT 'trace_event_raw_sys_enter' size=64 vlen=1 + 'args' type_id=4 bits_offset=128 + [3] STRUCT 'task_struct' size=9216 vlen=2 + 'pid' type_id=1 bits_offset=17920 + 'real_parent' type_id=7 bits_offset=18048 + [4] ARRAY '(anon)' type_id=5 index_type_id=8 nr_elems=6 + [5] INT 'long unsigned int' size=8 bits_offset=0 nr_bits=64 encoding=(none) + [6] TYPEDEF '__kernel_pid_t' type_id=8 + [7] PTR '(anon)' type_id=3 + [8] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED + <end> + +Now, the "5.4.0-smaller.btf" file may be used by libbpf as an external BTF file +when loading the "one.bpf.o" object into the "5.4.0-example" kernel. Note that +the generated BTF file won't allow other eBPF objects to be loaded, just the +ones given to min_core_btf. + +:: + + LIBBPF_OPTS(bpf_object_open_opts, opts, .btf_custom_path = "5.4.0-smaller.btf"); + struct bpf_object *obj; + + obj = bpf_object__open_file("one.bpf.o", &opts); + + ... diff --git a/tools/bpf/bpftool/Documentation/bpftool-iter.rst b/tools/bpf/bpftool/Documentation/bpftool-iter.rst new file mode 100644 index 000000000..84839d488 --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-iter.rst @@ -0,0 +1,76 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + +============ +bpftool-iter +============ +------------------------------------------------------------------------------- +tool to create BPF iterators +------------------------------------------------------------------------------- + +:Manual section: 8 + +.. include:: substitutions.rst + +SYNOPSIS +======== + + **bpftool** [*OPTIONS*] **iter** *COMMAND* + + *OPTIONS* := { |COMMON_OPTIONS| } + + *COMMANDS* := { **pin** | **help** } + +ITER COMMANDS +=================== + +| **bpftool** **iter pin** *OBJ* *PATH* [**map** *MAP*] +| **bpftool** **iter help** +| +| *OBJ* := /a/file/of/bpf_iter_target.o +| *MAP* := { **id** *MAP_ID* | **pinned** *FILE* } + +DESCRIPTION +=========== + **bpftool iter pin** *OBJ* *PATH* [**map** *MAP*] + A bpf iterator combines a kernel iterating of + particular kernel data (e.g., tasks, bpf_maps, etc.) + and a bpf program called for each kernel data object + (e.g., one task, one bpf_map, etc.). User space can + *read* kernel iterator output through *read()* syscall. + + The *pin* command creates a bpf iterator from *OBJ*, + and pin it to *PATH*. The *PATH* should be located + in *bpffs* mount. It must not contain a dot + character ('.'), which is reserved for future extensions + of *bpffs*. + + Map element bpf iterator requires an additional parameter + *MAP* so bpf program can iterate over map elements for + that map. User can have a bpf program in kernel to run + with each map element, do checking, filtering, aggregation, + etc. without copying data to user space. + + User can then *cat PATH* to see the bpf iterator output. + + **bpftool iter help** + Print short help message. + +OPTIONS +======= + .. include:: common_options.rst + +EXAMPLES +======== +**# bpftool iter pin bpf_iter_netlink.o /sys/fs/bpf/my_netlink** + +:: + + Create a file-based bpf iterator from bpf_iter_netlink.o and pin it + to /sys/fs/bpf/my_netlink + +**# bpftool iter pin bpf_iter_hashmap.o /sys/fs/bpf/my_hashmap map id 20** + +:: + + Create a file-based bpf iterator from bpf_iter_hashmap.o and map with + id 20, and pin it to /sys/fs/bpf/my_hashmap diff --git a/tools/bpf/bpftool/Documentation/bpftool-link.rst b/tools/bpf/bpftool/Documentation/bpftool-link.rst new file mode 100644 index 000000000..52a4eee4a --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-link.rst @@ -0,0 +1,112 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + +================ +bpftool-link +================ +------------------------------------------------------------------------------- +tool for inspection and simple manipulation of eBPF links +------------------------------------------------------------------------------- + +:Manual section: 8 + +.. include:: substitutions.rst + +SYNOPSIS +======== + + **bpftool** [*OPTIONS*] **link** *COMMAND* + + *OPTIONS* := { |COMMON_OPTIONS| | { **-f** | **--bpffs** } | { **-n** | **--nomount** } } + + *COMMANDS* := { **show** | **list** | **pin** | **help** } + +LINK COMMANDS +============= + +| **bpftool** **link { show | list }** [*LINK*] +| **bpftool** **link pin** *LINK* *FILE* +| **bpftool** **link detach** *LINK* +| **bpftool** **link help** +| +| *LINK* := { **id** *LINK_ID* | **pinned** *FILE* } + + +DESCRIPTION +=========== + **bpftool link { show | list }** [*LINK*] + Show information about active links. If *LINK* is + specified show information only about given link, + otherwise list all links currently active on the system. + + Output will start with link ID followed by link type and + zero or more named attributes, some of which depend on type + of link. + + Since Linux 5.8 bpftool is able to discover information about + processes that hold open file descriptors (FDs) against BPF + links. On such kernels bpftool will automatically emit this + information as well. + + **bpftool link pin** *LINK* *FILE* + Pin link *LINK* as *FILE*. + + Note: *FILE* must be located in *bpffs* mount. It must not + contain a dot character ('.'), which is reserved for future + extensions of *bpffs*. + + **bpftool link detach** *LINK* + Force-detach link *LINK*. BPF link and its underlying BPF + program will stay valid, but they will be detached from the + respective BPF hook and BPF link will transition into + a defunct state until last open file descriptor for that + link is closed. + + **bpftool link help** + Print short help message. + +OPTIONS +======= + .. include:: common_options.rst + + -f, --bpffs + When showing BPF links, show file names of pinned + links. + + -n, --nomount + Do not automatically attempt to mount any virtual file system + (such as tracefs or BPF virtual file system) when necessary. + +EXAMPLES +======== +**# bpftool link show** + +:: + + 10: cgroup prog 25 + cgroup_id 614 attach_type egress + pids test_progs(223) + +**# bpftool --json --pretty link show** + +:: + + [{ + "type": "cgroup", + "prog_id": 25, + "cgroup_id": 614, + "attach_type": "egress", + "pids": [{ + "pid": 223, + "comm": "test_progs" + } + ] + } + ] + +| +| **# bpftool link pin id 10 /sys/fs/bpf/link** +| **# ls -l /sys/fs/bpf/** + +:: + + -rw------- 1 root root 0 Apr 23 21:39 link diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst new file mode 100644 index 000000000..7f3b67a8b --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst @@ -0,0 +1,277 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + +================ +bpftool-map +================ +------------------------------------------------------------------------------- +tool for inspection and simple manipulation of eBPF maps +------------------------------------------------------------------------------- + +:Manual section: 8 + +.. include:: substitutions.rst + +SYNOPSIS +======== + + **bpftool** [*OPTIONS*] **map** *COMMAND* + + *OPTIONS* := { |COMMON_OPTIONS| | { **-f** | **--bpffs** } | { **-n** | **--nomount** } } + + *COMMANDS* := + { **show** | **list** | **create** | **dump** | **update** | **lookup** | **getnext** | + **delete** | **pin** | **help** } + +MAP COMMANDS +============= + +| **bpftool** **map** { **show** | **list** } [*MAP*] +| **bpftool** **map create** *FILE* **type** *TYPE* **key** *KEY_SIZE* **value** *VALUE_SIZE* \ +| **entries** *MAX_ENTRIES* **name** *NAME* [**flags** *FLAGS*] [**inner_map** *MAP*] \ +| [**dev** *NAME*] +| **bpftool** **map dump** *MAP* +| **bpftool** **map update** *MAP* [**key** *DATA*] [**value** *VALUE*] [*UPDATE_FLAGS*] +| **bpftool** **map lookup** *MAP* [**key** *DATA*] +| **bpftool** **map getnext** *MAP* [**key** *DATA*] +| **bpftool** **map delete** *MAP* **key** *DATA* +| **bpftool** **map pin** *MAP* *FILE* +| **bpftool** **map event_pipe** *MAP* [**cpu** *N* **index** *M*] +| **bpftool** **map peek** *MAP* +| **bpftool** **map push** *MAP* **value** *VALUE* +| **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* | **name** *MAP_NAME* } +| *DATA* := { [**hex**] *BYTES* } +| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* | **name** *PROG_NAME* } +| *VALUE* := { *DATA* | *MAP* | *PROG* } +| *UPDATE_FLAGS* := { **any** | **exist** | **noexist** } +| *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** | **devmap_hash** | **sockmap** | **cpumap** | **xskmap** | **sockhash** +| | **cgroup_storage** | **reuseport_sockarray** | **percpu_cgroup_storage** +| | **queue** | **stack** | **sk_storage** | **struct_ops** | **ringbuf** | **inode_storage** +| | **task_storage** | **bloom_filter** | **user_ringbuf** } + +DESCRIPTION +=========== + **bpftool map { show | list }** [*MAP*] + Show information about loaded maps. If *MAP* is specified + show information only about given maps, otherwise list all + maps currently loaded on the system. In case of **name**, + *MAP* may match several maps which will all be shown. + + Output will start with map ID followed by map type and + zero or more named attributes (depending on kernel version). + + Since Linux 5.8 bpftool is able to discover information about + processes that hold open file descriptors (FDs) against BPF + maps. On such kernels bpftool will automatically emit this + information as well. + + **bpftool map create** *FILE* **type** *TYPE* **key** *KEY_SIZE* **value** *VALUE_SIZE* **entries** *MAX_ENTRIES* **name** *NAME* [**flags** *FLAGS*] [**inner_map** *MAP*] [**dev** *NAME*] + Create a new map with given parameters and pin it to *bpffs* + as *FILE*. + + *FLAGS* should be an integer which is the combination of + desired flags, e.g. 1024 for **BPF_F_MMAPABLE** (see bpf.h + UAPI header for existing flags). + + To create maps of type array-of-maps or hash-of-maps, the + **inner_map** keyword must be used to pass an inner map. The + kernel needs it to collect metadata related to the inner maps + that the new map will work with. + + Keyword **dev** expects a network interface name, and is used + to request hardware offload for the map. + + **bpftool map dump** *MAP* + Dump all entries in a given *MAP*. In case of **name**, + *MAP* may match several maps which will all be dumped. + + **bpftool map update** *MAP* [**key** *DATA*] [**value** *VALUE*] [*UPDATE_FLAGS*] + Update map entry for a given *KEY*. + + *UPDATE_FLAGS* can be one of: **any** update existing entry + or add if doesn't exit; **exist** update only if entry already + exists; **noexist** update only if entry doesn't exist. + + If the **hex** keyword is provided in front of the bytes + sequence, the bytes are parsed as hexadecimal values, even if + no "0x" prefix is added. If the keyword is not provided, then + the bytes are parsed as decimal values, unless a "0x" prefix + (for hexadecimal) or a "0" prefix (for octal) is provided. + + **bpftool map lookup** *MAP* [**key** *DATA*] + Lookup **key** in the map. + + **bpftool map getnext** *MAP* [**key** *DATA*] + Get next key. If *key* is not specified, get first key. + + **bpftool map delete** *MAP* **key** *DATA* + Remove entry from the map. + + **bpftool map pin** *MAP* *FILE* + Pin map *MAP* as *FILE*. + + Note: *FILE* must be located in *bpffs* mount. It must not + contain a dot character ('.'), which is reserved for future + extensions of *bpffs*. + + **bpftool** **map event_pipe** *MAP* [**cpu** *N* **index** *M*] + Read events from a **BPF_MAP_TYPE_PERF_EVENT_ARRAY** map. + + Install perf rings into a perf event array map and dump + output of any **bpf_perf_event_output**\ () call in the kernel. + By default read the number of CPUs on the system and + install perf ring for each CPU in the corresponding index + in the array. + + If **cpu** and **index** are specified, install perf ring + for given **cpu** at **index** in the array (single ring). + + Note that installing a perf ring into an array will silently + replace any existing ring. Any other application will stop + receiving events if it installed its rings earlier. + + **bpftool map peek** *MAP* + Peek next value in the queue or stack. + + **bpftool map push** *MAP* **value** *VALUE* + Push *VALUE* onto the stack. + + **bpftool map pop** *MAP* + Pop and print value from the stack. + + **bpftool map enqueue** *MAP* **value** *VALUE* + Enqueue *VALUE* into the queue. + + **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. + +OPTIONS +======= + .. include:: common_options.rst + + -f, --bpffs + Show file names of pinned maps. + + -n, --nomount + Do not automatically attempt to mount any virtual file system + (such as tracefs or BPF virtual file system) when necessary. + +EXAMPLES +======== +**# bpftool map show** + +:: + + 10: hash name some_map flags 0x0 + key 4B value 8B max_entries 2048 memlock 167936B + pids systemd(1) + +The following three commands are equivalent: + +| +| **# bpftool map update id 10 key hex 20 c4 b7 00 value hex 0f ff ff ab 01 02 03 4c** +| **# bpftool map update id 10 key 0x20 0xc4 0xb7 0x00 value 0x0f 0xff 0xff 0xab 0x01 0x02 0x03 0x4c** +| **# bpftool map update id 10 key 32 196 183 0 value 15 255 255 171 1 2 3 76** + +**# bpftool map lookup id 10 key 0 1 2 3** + +:: + + key: 00 01 02 03 value: 00 01 02 03 04 05 06 07 + + +**# bpftool map dump id 10** + +:: + + key: 00 01 02 03 value: 00 01 02 03 04 05 06 07 + key: 0d 00 07 00 value: 02 00 00 00 01 02 03 04 + Found 2 elements + +**# bpftool map getnext id 10 key 0 1 2 3** + +:: + + key: + 00 01 02 03 + next key: + 0d 00 07 00 + +| +| **# mount -t bpf none /sys/fs/bpf/** +| **# bpftool map pin id 10 /sys/fs/bpf/map** +| **# bpftool map del pinned /sys/fs/bpf/map key 13 00 07 00** + +Note that map update can also be used in order to change the program references +hold by a program array map. This can be used, for example, to change the +programs used for tail-call jumps at runtime, without having to reload the +entry-point program. Below is an example for this use case: we load a program +defining a prog array map, and with a main function that contains a tail call +to other programs that can be used either to "process" packets or to "debug" +processing. Note that the prog array map MUST be pinned into the BPF virtual +file system for the map update to work successfully, as kernel flushes prog +array maps when they have no more references from user space (and the update +would be lost as soon as bpftool exits). + +| +| **# bpftool prog loadall tail_calls.o /sys/fs/bpf/foo type xdp** +| **# bpftool prog --bpffs** + +:: + + 545: xdp name main_func tag 674b4b5597193dc3 gpl + loaded_at 2018-12-12T15:02:58+0000 uid 0 + xlated 240B jited 257B memlock 4096B map_ids 294 + pinned /sys/fs/bpf/foo/xdp + 546: xdp name bpf_func_process tag e369a529024751fc gpl + loaded_at 2018-12-12T15:02:58+0000 uid 0 + xlated 200B jited 164B memlock 4096B + pinned /sys/fs/bpf/foo/process + 547: xdp name bpf_func_debug tag 0b597868bc7f0976 gpl + loaded_at 2018-12-12T15:02:58+0000 uid 0 + xlated 200B jited 164B memlock 4096B + pinned /sys/fs/bpf/foo/debug + +**# bpftool map** + +:: + + 294: prog_array name jmp_table flags 0x0 + key 4B value 4B max_entries 1 memlock 4096B + owner_prog_type xdp owner jited + +| +| **# bpftool map pin id 294 /sys/fs/bpf/bar** +| **# bpftool map dump pinned /sys/fs/bpf/bar** + +:: + + Found 0 elements + +| +| **# bpftool map update pinned /sys/fs/bpf/bar key 0 0 0 0 value pinned /sys/fs/bpf/foo/debug** +| **# bpftool map dump pinned /sys/fs/bpf/bar** + +:: + + key: 00 00 00 00 value: 22 02 00 00 + Found 1 element diff --git a/tools/bpf/bpftool/Documentation/bpftool-net.rst b/tools/bpf/bpftool/Documentation/bpftool-net.rst new file mode 100644 index 000000000..f4e0a5163 --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-net.rst @@ -0,0 +1,178 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + +================ +bpftool-net +================ +------------------------------------------------------------------------------- +tool for inspection of netdev/tc related bpf prog attachments +------------------------------------------------------------------------------- + +:Manual section: 8 + +.. include:: substitutions.rst + +SYNOPSIS +======== + + **bpftool** [*OPTIONS*] **net** *COMMAND* + + *OPTIONS* := { |COMMON_OPTIONS| } + + *COMMANDS* := + { **show** | **list** | **attach** | **detach** | **help** } + +NET COMMANDS +============ + +| **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* ] + List bpf program attachments in the kernel networking subsystem. + + Currently, only device driver xdp attachments and tc filter + classification/action attachments are implemented, i.e., for + program types **BPF_PROG_TYPE_SCHED_CLS**, + **BPF_PROG_TYPE_SCHED_ACT** and **BPF_PROG_TYPE_XDP**. + For programs attached to a particular cgroup, e.g., + **BPF_PROG_TYPE_CGROUP_SKB**, **BPF_PROG_TYPE_CGROUP_SOCK**, + **BPF_PROG_TYPE_SOCK_OPS** and **BPF_PROG_TYPE_CGROUP_SOCK_ADDR**, + users can use **bpftool cgroup** to dump cgroup attachments. + For sk_{filter, skb, msg, reuseport} and lwt/seg6 + bpf programs, users should consult other tools, e.g., iproute2. + + The current output will start with all xdp program attachments, followed by + all tc class/qdisc bpf program attachments. Both xdp programs and + tc programs are ordered based on ifindex number. If multiple bpf + programs attached to the same networking device through **tc filter**, + the order will be first all bpf programs attached to tc classes, then + 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. + +OPTIONS +======= + .. include:: common_options.rst + +EXAMPLES +======== + +| **# bpftool net** + +:: + + xdp: + eth0(2) driver id 198 + + tc: + eth0(2) htb name prefix_matcher.o:[cls_prefix_matcher_htb] id 111727 act [] + eth0(2) clsact/ingress fbflow_icmp id 130246 act [] + eth0(2) clsact/egress prefix_matcher.o:[cls_prefix_matcher_clsact] id 111726 + eth0(2) clsact/egress cls_fg_dscp id 108619 act [] + eth0(2) clsact/egress fbflow_egress id 130245 + +| +| **# bpftool -jp net** + +:: + + [{ + "xdp": [{ + "devname": "eth0", + "ifindex": 2, + "mode": "driver", + "id": 198 + } + ], + "tc": [{ + "devname": "eth0", + "ifindex": 2, + "kind": "htb", + "name": "prefix_matcher.o:[cls_prefix_matcher_htb]", + "id": 111727, + "act": [] + },{ + "devname": "eth0", + "ifindex": 2, + "kind": "clsact/ingress", + "name": "fbflow_icmp", + "id": 130246, + "act": [] + },{ + "devname": "eth0", + "ifindex": 2, + "kind": "clsact/egress", + "name": "prefix_matcher.o:[cls_prefix_matcher_clsact]", + "id": 111726, + },{ + "devname": "eth0", + "ifindex": 2, + "kind": "clsact/egress", + "name": "cls_fg_dscp", + "id": 108619, + "act": [] + },{ + "devname": "eth0", + "ifindex": 2, + "kind": "clsact/egress", + "name": "fbflow_egress", + "id": 130245, + } + ] + } + ] + +| +| **# 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: diff --git a/tools/bpf/bpftool/Documentation/bpftool-perf.rst b/tools/bpf/bpftool/Documentation/bpftool-perf.rst new file mode 100644 index 000000000..5fea633a8 --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-perf.rst @@ -0,0 +1,69 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + +================ +bpftool-perf +================ +------------------------------------------------------------------------------- +tool for inspection of perf related bpf prog attachments +------------------------------------------------------------------------------- + +:Manual section: 8 + +.. include:: substitutions.rst + +SYNOPSIS +======== + + **bpftool** [*OPTIONS*] **perf** *COMMAND* + + *OPTIONS* := { |COMMON_OPTIONS| } + + *COMMANDS* := + { **show** | **list** | **help** } + +PERF COMMANDS +============= + +| **bpftool** **perf** { **show** | **list** } +| **bpftool** **perf help** + +DESCRIPTION +=========== + **bpftool perf { show | list }** + List all raw_tracepoint, tracepoint, kprobe attachment in the system. + + Output will start with process id and file descriptor in that process, + followed by bpf program id, attachment information, and attachment point. + The attachment point for raw_tracepoint/tracepoint is the trace probe name. + The attachment point for k[ret]probe is either symbol name and offset, + or a kernel virtual address. + The attachment point for u[ret]probe is the file name and the file offset. + + **bpftool perf help** + Print short help message. + +OPTIONS +======= + .. include:: common_options.rst + +EXAMPLES +======== + +| **# bpftool perf** + +:: + + pid 21711 fd 5: prog_id 5 kprobe func __x64_sys_write offset 0 + pid 21765 fd 5: prog_id 7 kretprobe func __x64_sys_nanosleep offset 0 + pid 21767 fd 5: prog_id 8 tracepoint sys_enter_nanosleep + pid 21800 fd 5: prog_id 9 uprobe filename /home/yhs/a.out offset 1159 + +| +| **# bpftool -j perf** + +:: + + [{"pid":21711,"fd":5,"prog_id":5,"fd_type":"kprobe","func":"__x64_sys_write","offset":0}, \ + {"pid":21765,"fd":5,"prog_id":7,"fd_type":"kretprobe","func":"__x64_sys_nanosleep","offset":0}, \ + {"pid":21767,"fd":5,"prog_id":8,"fd_type":"tracepoint","tracepoint":"sys_enter_nanosleep"}, \ + {"pid":21800,"fd":5,"prog_id":9,"fd_type":"uprobe","filename":"/home/yhs/a.out","offset":1159}] diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst new file mode 100644 index 000000000..eb1b2a254 --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -0,0 +1,363 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + +================ +bpftool-prog +================ +------------------------------------------------------------------------------- +tool for inspection and simple manipulation of eBPF progs +------------------------------------------------------------------------------- + +:Manual section: 8 + +.. include:: substitutions.rst + +SYNOPSIS +======== + + **bpftool** [*OPTIONS*] **prog** *COMMAND* + + *OPTIONS* := { |COMMON_OPTIONS| | + { **-f** | **--bpffs** } | { **-m** | **--mapcompat** } | { **-n** | **--nomount** } | + { **-L** | **--use-loader** } } + + *COMMANDS* := + { **show** | **list** | **dump xlated** | **dump jited** | **pin** | **load** | + **loadall** | **help** } + +PROG COMMANDS +============= + +| **bpftool** **prog** { **show** | **list** } [*PROG*] +| **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*] [**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 profile** *PROG* [**duration** *DURATION*] *METRICs* +| **bpftool** **prog help** +| +| *MAP* := { **id** *MAP_ID* | **pinned** *FILE* } +| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* | **name** *PROG_NAME* } +| *TYPE* := { +| **socket** | **kprobe** | **kretprobe** | **classifier** | **action** | +| **tracepoint** | **raw_tracepoint** | **xdp** | **perf_event** | **cgroup/skb** | +| **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/getpeername4** | **cgroup/getpeername6** | +| **cgroup/getsockname4** | **cgroup/getsockname6** | **cgroup/sendmsg4** | **cgroup/sendmsg6** | +| **cgroup/recvmsg4** | **cgroup/recvmsg6** | **cgroup/sysctl** | +| **cgroup/getsockopt** | **cgroup/setsockopt** | **cgroup/sock_release** | +| **struct_ops** | **fentry** | **fexit** | **freplace** | **sk_lookup** +| } +| *ATTACH_TYPE* := { +| **sk_msg_verdict** | **sk_skb_verdict** | **sk_skb_stream_verdict** | +| **sk_skb_stream_parser** | **flow_dissector** +| } +| *METRICs* := { +| **cycles** | **instructions** | **l1d_loads** | **llc_misses** | +| **itlb_misses** | **dtlb_misses** +| } + + +DESCRIPTION +=========== + **bpftool prog { show | list }** [*PROG*] + Show information about loaded programs. If *PROG* is + specified show information only about given programs, + otherwise list all programs currently loaded on the system. + In case of **tag** or **name**, *PROG* may match several + programs which will all be shown. + + 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. + + Since Linux 5.8 bpftool is able to discover information about + processes that hold open file descriptors (FDs) against BPF + programs. On such kernels bpftool will automatically emit this + information as well. + + **bpftool prog dump xlated** *PROG* [{ **file** *FILE* | **opcodes** | **visual** | **linum** }] + Dump eBPF instructions of the programs from the kernel. By + default, eBPF will be disassembled and printed to standard + output in human-readable format. In this case, **opcodes** + controls if raw opcodes should be printed as well. + + In case of **tag** or **name**, *PROG* may match several + programs which will all be dumped. However, if **file** or + **visual** is specified, *PROG* must match a single program. + + If **file** is specified, the binary image will instead be + written to *FILE*. + + If **visual** is specified, control flow graph (CFG) will be + built instead, and eBPF instructions will be presented with + CFG in DOT format, on standard output. + + If the programs have line_info available, the source line will + be displayed by default. If **linum** is specified, + the filename, line number and line column will also be + displayed on top of the source line. + + **bpftool prog dump jited** *PROG* [{ **file** *FILE* | **opcodes** | **linum** }] + Dump jited image (host machine code) of the program. + + If *FILE* is specified image will be written to a file, + otherwise it will be disassembled and printed to stdout. + *PROG* must match a single program when **file** is specified. + + **opcodes** controls if raw opcodes will be printed. + + If the prog has line_info available, the source line will + be displayed by default. If **linum** is specified, + the filename, line number and line column will also be + displayed on top of the source line. + + **bpftool prog pin** *PROG* *FILE* + Pin program *PROG* as *FILE*. + + Note: *FILE* must be located in *bpffs* mount. It must not + contain a dot character ('.'), which is reserved for future + extensions of *bpffs*. + + **bpftool prog { load | loadall }** *OBJ* *PATH* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*] [**pinmaps** *MAP_DIR*] + Load bpf program(s) from binary *OBJ* and pin as *PATH*. + **bpftool prog load** pins only the first program from the + *OBJ* as *PATH*. **bpftool prog loadall** pins all programs + from the *OBJ* under *PATH* directory. + **type** is optional, if not specified program type will be + inferred from section names. + By default bpftool will create new maps as declared in the ELF + object being loaded. **map** parameter allows for the reuse + of existing maps. It can be specified multiple times, each + time for a different map. *IDX* refers to index of the map + to be replaced in the ELF file counting from 0, while *NAME* + allows to replace a map by name. *MAP* specifies the map to + use, referring to it by **id** or through a **pinned** file. + If **dev** *NAME* is specified program will be loaded onto + given networking device (offload). + Optional **pinmaps** argument can be provided to pin all + maps under *MAP_DIR* directory. + + Note: *PATH* must be located in *bpffs* mount. It must not + contain a dot character ('.'), which is reserved for future + extensions of *bpffs*. + + **bpftool prog attach** *PROG* *ATTACH_TYPE* [*MAP*] + Attach bpf program *PROG* (with type specified by + *ATTACH_TYPE*). Most *ATTACH_TYPEs* require a *MAP* + parameter, with the exception of *flow_dissector* which is + attached to current networking name space. + + **bpftool prog detach** *PROG* *ATTACH_TYPE* [*MAP*] + Detach bpf program *PROG* (with type specified by + *ATTACH_TYPE*). Most *ATTACH_TYPEs* require a *MAP* + parameter, with the exception of *flow_dissector* which is + detached from the current networking name space. + + **bpftool prog tracelog** + Dump the trace pipe of the system to the console (stdout). + Hit <Ctrl+C> to stop printing. BPF programs can write to this + trace pipe at runtime with the **bpf_trace_printk**\ () helper. + This should be used only for debugging purposes. For + 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 profile** *PROG* [**duration** *DURATION*] *METRICs* + Profile *METRICs* for bpf program *PROG* for *DURATION* + seconds or until user hits <Ctrl+C>. *DURATION* is optional. + If *DURATION* is not specified, the profiling will run up to + **UINT_MAX** seconds. + + **bpftool prog help** + Print short help message. + +OPTIONS +======= + .. include:: common_options.rst + + -f, --bpffs + When showing BPF programs, show file names of pinned + programs. + + -m, --mapcompat + Allow loading maps with unknown map definitions. + + -n, --nomount + Do not automatically attempt to mount any virtual file system + (such as tracefs or BPF virtual file system) when necessary. + + -L, --use-loader + Load program as a "loader" program. This is useful to debug + the generation of such programs. When this option is in + use, bpftool attempts to load the programs from the object + file into the kernel, but does not pin them (therefore, the + *PATH* must not be provided). + + When combined with the **-d**\ \|\ **--debug** option, + additional debug messages are generated, and the execution + of the loader program will use the **bpf_trace_printk**\ () + helper to log each step of loading BTF, creating the maps, + and loading the programs (see **bpftool prog tracelog** as + a way to dump those messages). + +EXAMPLES +======== +**# bpftool prog show** + +:: + + 10: xdp name some_prog tag 005a3d2123620c8b gpl run_time_ns 81632 run_cnt 10 + loaded_at 2017-09-29T20:11:00+0000 uid 0 + xlated 528B jited 370B memlock 4096B map_ids 10 + pids systemd(1) + +**# bpftool --json --pretty prog show** + +:: + + [{ + "id": 10, + "type": "xdp", + "tag": "005a3d2123620c8b", + "gpl_compatible": true, + "run_time_ns": 81632, + "run_cnt": 10, + "loaded_at": 1506715860, + "uid": 0, + "bytes_xlated": 528, + "jited": true, + "bytes_jited": 370, + "bytes_memlock": 4096, + "map_ids": [10 + ], + "pids": [{ + "pid": 1, + "comm": "systemd" + } + ] + } + ] + +| +| **# bpftool prog dump xlated id 10 file /tmp/t** +| **$ ls -l /tmp/t** + +:: + + -rw------- 1 root root 560 Jul 22 01:42 /tmp/t + +**# bpftool prog dump jited tag 005a3d2123620c8b** + +:: + + 0: push %rbp + 1: mov %rsp,%rbp + 2: sub $0x228,%rsp + 3: sub $0x28,%rbp + 4: mov %rbx,0x0(%rbp) + +| +| **# mount -t bpf none /sys/fs/bpf/** +| **# bpftool prog pin id 10 /sys/fs/bpf/prog** +| **# bpftool prog load ./my_prog.o /sys/fs/bpf/prog2** +| **# ls -l /sys/fs/bpf/** + +:: + + -rw------- 1 root root 0 Jul 22 01:43 prog + -rw------- 1 root root 0 Jul 22 01:44 prog2 + +**# bpftool prog dump jited pinned /sys/fs/bpf/prog opcodes** + +:: + + 0: push %rbp + 55 + 1: mov %rsp,%rbp + 48 89 e5 + 4: sub $0x228,%rsp + 48 81 ec 28 02 00 00 + b: sub $0x28,%rbp + 48 83 ed 28 + f: mov %rbx,0x0(%rbp) + 48 89 5d 00 + +| +| **# bpftool prog load xdp1_kern.o /sys/fs/bpf/xdp1 type xdp map name rxcnt id 7** +| **# bpftool prog show pinned /sys/fs/bpf/xdp1** + +:: + + 9: xdp name xdp_prog1 tag 539ec6ce11b52f98 gpl + loaded_at 2018-06-25T16:17:31-0700 uid 0 + xlated 488B jited 336B memlock 4096B map_ids 7 + +**# rm /sys/fs/bpf/xdp1** + +| +| **# bpftool prog profile id 337 duration 10 cycles instructions llc_misses** + +:: + + 51397 run_cnt + 40176203 cycles (83.05%) + 42518139 instructions # 1.06 insns per cycle (83.39%) + 123 llc_misses # 2.89 LLC misses per million insns (83.15%) + +| +| Output below is for the trace logs. +| Run in separate terminals: +| **# bpftool prog tracelog** +| **# bpftool prog load -L -d file.o** + +:: + + bpftool-620059 [004] d... 2634685.517903: bpf_trace_printk: btf_load size 665 r=5 + bpftool-620059 [004] d... 2634685.517912: bpf_trace_printk: map_create sample_map idx 0 type 2 value_size 4 value_btf_id 0 r=6 + bpftool-620059 [004] d... 2634685.517997: bpf_trace_printk: prog_load sample insn_cnt 13 r=7 + bpftool-620059 [004] d... 2634685.517999: bpf_trace_printk: close(5) = 0 diff --git a/tools/bpf/bpftool/Documentation/bpftool-struct_ops.rst b/tools/bpf/bpftool/Documentation/bpftool-struct_ops.rst new file mode 100644 index 000000000..ee53a122c --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-struct_ops.rst @@ -0,0 +1,88 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + +================== +bpftool-struct_ops +================== +------------------------------------------------------------------------------- +tool to register/unregister/introspect BPF struct_ops +------------------------------------------------------------------------------- + +:Manual section: 8 + +.. include:: substitutions.rst + +SYNOPSIS +======== + + **bpftool** [*OPTIONS*] **struct_ops** *COMMAND* + + *OPTIONS* := { |COMMON_OPTIONS| } + + *COMMANDS* := + { **show** | **list** | **dump** | **register** | **unregister** | **help** } + +STRUCT_OPS COMMANDS +=================== + +| **bpftool** **struct_ops { show | list }** [*STRUCT_OPS_MAP*] +| **bpftool** **struct_ops dump** [*STRUCT_OPS_MAP*] +| **bpftool** **struct_ops register** *OBJ* +| **bpftool** **struct_ops unregister** *STRUCT_OPS_MAP* +| **bpftool** **struct_ops help** +| +| *STRUCT_OPS_MAP* := { **id** *STRUCT_OPS_MAP_ID* | **name** *STRUCT_OPS_MAP_NAME* } +| *OBJ* := /a/file/of/bpf_struct_ops.o + + +DESCRIPTION +=========== + **bpftool struct_ops { show | list }** [*STRUCT_OPS_MAP*] + Show brief information about the struct_ops in the system. + If *STRUCT_OPS_MAP* is specified, it shows information only + for the given struct_ops. Otherwise, it lists all struct_ops + currently existing in the system. + + Output will start with struct_ops map ID, followed by its map + name and its struct_ops's kernel type. + + **bpftool struct_ops dump** [*STRUCT_OPS_MAP*] + Dump details information about the struct_ops in the system. + If *STRUCT_OPS_MAP* is specified, it dumps information only + for the given struct_ops. Otherwise, it dumps all struct_ops + currently existing in the system. + + **bpftool struct_ops register** *OBJ* + Register bpf struct_ops from *OBJ*. All struct_ops under + the ELF section ".struct_ops" will be registered to + its kernel subsystem. + + **bpftool struct_ops unregister** *STRUCT_OPS_MAP* + Unregister the *STRUCT_OPS_MAP* from the kernel subsystem. + + **bpftool struct_ops help** + Print short help message. + +OPTIONS +======= + .. include:: common_options.rst + +EXAMPLES +======== +**# bpftool struct_ops show** + +:: + + 100: dctcp tcp_congestion_ops + 105: cubic tcp_congestion_ops + +**# bpftool struct_ops unregister id 105** + +:: + + Unregistered tcp_congestion_ops cubic id 105 + +**# bpftool struct_ops register bpf_cubic.o** + +:: + + Registered tcp_congestion_ops cubic id 110 diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst new file mode 100644 index 000000000..6965c94df --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool.rst @@ -0,0 +1,70 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + +================ +BPFTOOL +================ +------------------------------------------------------------------------------- +tool for inspection and simple manipulation of eBPF programs and maps +------------------------------------------------------------------------------- + +:Manual section: 8 + +.. include:: substitutions.rst + +SYNOPSIS +======== + + **bpftool** [*OPTIONS*] *OBJECT* { *COMMAND* | **help** } + + **bpftool** **batch file** *FILE* + + **bpftool** **version** + + *OBJECT* := { **map** | **program** | **link** | **cgroup** | **perf** | **net** | **feature** | + **btf** | **gen** | **struct_ops** | **iter** } + + *OPTIONS* := { { **-V** | **--version** } | |COMMON_OPTIONS| } + + *MAP-COMMANDS* := + { **show** | **list** | **create** | **dump** | **update** | **lookup** | **getnext** | + **delete** | **pin** | **event_pipe** | **help** } + + *PROG-COMMANDS* := { **show** | **list** | **dump jited** | **dump xlated** | **pin** | + **load** | **attach** | **detach** | **help** } + + *LINK-COMMANDS* := { **show** | **list** | **pin** | **detach** | **help** } + + *CGROUP-COMMANDS* := { **show** | **list** | **attach** | **detach** | **help** } + + *PERF-COMMANDS* := { **show** | **list** | **help** } + + *NET-COMMANDS* := { **show** | **list** | **help** } + + *FEATURE-COMMANDS* := { **probe** | **help** } + + *BTF-COMMANDS* := { **show** | **list** | **dump** | **help** } + + *GEN-COMMANDS* := { **object** | **skeleton** | **min_core_btf** | **help** } + + *STRUCT-OPS-COMMANDS* := { **show** | **list** | **dump** | **register** | **unregister** | **help** } + + *ITER-COMMANDS* := { **pin** | **help** } + +DESCRIPTION +=========== + *bpftool* allows for inspection and simple modification of BPF objects + on the system. + + Note that format of the output of all tools is not guaranteed to be + stable and should not be depended upon. + +OPTIONS +======= + .. include:: common_options.rst + + -m, --mapcompat + Allow loading maps with unknown map definitions. + + -n, --nomount + Do not automatically attempt to mount any virtual file system + (such as tracefs or BPF virtual file system) when necessary. diff --git a/tools/bpf/bpftool/Documentation/common_options.rst b/tools/bpf/bpftool/Documentation/common_options.rst new file mode 100644 index 000000000..4107a586b --- /dev/null +++ b/tools/bpf/bpftool/Documentation/common_options.rst @@ -0,0 +1,34 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + +-h, --help + Print short help message (similar to **bpftool help**). + +-V, --version + Print bpftool's version number (similar to **bpftool version**), the + number of the libbpf version in use, and optional features that were + included when bpftool was compiled. Optional features include linking + against libbfd to provide the disassembler for JIT-ted programs + (**bpftool prog dump jited**) and usage of BPF skeletons (some + features like **bpftool prog profile** or showing pids associated to + BPF objects may rely on it). + +-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, even debug-level information. This includes + logs from libbpf as well as from the verifier, when attempting to + load programs. + +-l, --legacy + Use legacy libbpf mode which has more relaxed BPF program + requirements. By default, bpftool has more strict requirements + about section names, changes pinning logic and doesn't support + some of the older non-BTF map declarations. + + See https://github.com/libbpf/libbpf/wiki/Libbpf:-the-road-to-v1.0 + for details. diff --git a/tools/bpf/bpftool/Documentation/substitutions.rst b/tools/bpf/bpftool/Documentation/substitutions.rst new file mode 100644 index 000000000..ccf1ffa06 --- /dev/null +++ b/tools/bpf/bpftool/Documentation/substitutions.rst @@ -0,0 +1,3 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + +.. |COMMON_OPTIONS| replace:: { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-d** | **--debug** } | { **-l** | **--legacy** } diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile new file mode 100644 index 000000000..a3794b341 --- /dev/null +++ b/tools/bpf/bpftool/Makefile @@ -0,0 +1,268 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +include ../../scripts/Makefile.include + +ifeq ($(srctree),) +srctree := $(patsubst %/,%,$(dir $(CURDIR))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +endif + +ifeq ($(V),1) + Q = +else + Q = @ +endif + +BPF_DIR = $(srctree)/tools/lib/bpf + +ifneq ($(OUTPUT),) + _OUTPUT := $(OUTPUT) +else + _OUTPUT := $(CURDIR)/ +endif +BOOTSTRAP_OUTPUT := $(_OUTPUT)bootstrap/ + +LIBBPF_OUTPUT := $(_OUTPUT)libbpf/ +LIBBPF_DESTDIR := $(LIBBPF_OUTPUT) +LIBBPF_INCLUDE := $(LIBBPF_DESTDIR)include +LIBBPF_HDRS_DIR := $(LIBBPF_INCLUDE)/bpf +LIBBPF := $(LIBBPF_OUTPUT)libbpf.a + +LIBBPF_BOOTSTRAP_OUTPUT := $(BOOTSTRAP_OUTPUT)libbpf/ +LIBBPF_BOOTSTRAP_DESTDIR := $(LIBBPF_BOOTSTRAP_OUTPUT) +LIBBPF_BOOTSTRAP_INCLUDE := $(LIBBPF_BOOTSTRAP_DESTDIR)include +LIBBPF_BOOTSTRAP_HDRS_DIR := $(LIBBPF_BOOTSTRAP_INCLUDE)/bpf +LIBBPF_BOOTSTRAP := $(LIBBPF_BOOTSTRAP_OUTPUT)libbpf.a + +# We need to copy hashmap.h, nlattr.h, relo_core.h and libbpf_internal.h +# which are not otherwise exported by libbpf, but still required by bpftool. +LIBBPF_INTERNAL_HDRS := $(addprefix $(LIBBPF_HDRS_DIR)/,hashmap.h nlattr.h relo_core.h libbpf_internal.h) +LIBBPF_BOOTSTRAP_INTERNAL_HDRS := $(addprefix $(LIBBPF_BOOTSTRAP_HDRS_DIR)/,hashmap.h relo_core.h libbpf_internal.h) + +$(LIBBPF_OUTPUT) $(BOOTSTRAP_OUTPUT) $(LIBBPF_BOOTSTRAP_OUTPUT) $(LIBBPF_HDRS_DIR) $(LIBBPF_BOOTSTRAP_HDRS_DIR): + $(QUIET_MKDIR)mkdir -p $@ + +$(LIBBPF): $(wildcard $(BPF_DIR)/*.[ch] $(BPF_DIR)/Makefile) | $(LIBBPF_OUTPUT) + $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_OUTPUT) \ + DESTDIR=$(LIBBPF_DESTDIR:/=) prefix= $(LIBBPF) install_headers + +$(LIBBPF_INTERNAL_HDRS): $(LIBBPF_HDRS_DIR)/%.h: $(BPF_DIR)/%.h | $(LIBBPF_HDRS_DIR) + $(call QUIET_INSTALL, $@) + $(Q)install -m 644 -t $(LIBBPF_HDRS_DIR) $< + +$(LIBBPF_BOOTSTRAP): $(wildcard $(BPF_DIR)/*.[ch] $(BPF_DIR)/Makefile) | $(LIBBPF_BOOTSTRAP_OUTPUT) + $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_BOOTSTRAP_OUTPUT) \ + DESTDIR=$(LIBBPF_BOOTSTRAP_DESTDIR:/=) prefix= \ + ARCH= CROSS_COMPILE= CC=$(HOSTCC) LD=$(HOSTLD) AR=$(HOSTAR) $@ install_headers + +$(LIBBPF_BOOTSTRAP_INTERNAL_HDRS): $(LIBBPF_BOOTSTRAP_HDRS_DIR)/%.h: $(BPF_DIR)/%.h | $(LIBBPF_BOOTSTRAP_HDRS_DIR) + $(call QUIET_INSTALL, $@) + $(Q)install -m 644 -t $(LIBBPF_BOOTSTRAP_HDRS_DIR) $< + +$(LIBBPF)-clean: FORCE | $(LIBBPF_OUTPUT) + $(call QUIET_CLEAN, libbpf) + $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_OUTPUT) clean >/dev/null + +$(LIBBPF_BOOTSTRAP)-clean: FORCE | $(LIBBPF_BOOTSTRAP_OUTPUT) + $(call QUIET_CLEAN, libbpf-bootstrap) + $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_BOOTSTRAP_OUTPUT) clean >/dev/null + +prefix ?= /usr/local +bash_compdir ?= /usr/share/bash-completion/completions + +CFLAGS += -O2 +CFLAGS += -W -Wall -Wextra -Wno-unused-parameter -Wno-missing-field-initializers +CFLAGS += $(filter-out -Wswitch-enum -Wnested-externs,$(EXTRA_WARNINGS)) +CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ \ + -I$(or $(OUTPUT),.) \ + -I$(LIBBPF_INCLUDE) \ + -I$(srctree)/kernel/bpf/ \ + -I$(srctree)/tools/include \ + -I$(srctree)/tools/include/uapi +ifneq ($(BPFTOOL_VERSION),) +CFLAGS += -DBPFTOOL_VERSION='"$(BPFTOOL_VERSION)"' +endif +ifneq ($(EXTRA_CFLAGS),) +CFLAGS += $(EXTRA_CFLAGS) +endif +ifneq ($(EXTRA_LDFLAGS),) +LDFLAGS += $(EXTRA_LDFLAGS) +endif + +INSTALL ?= install +RM ?= rm -f + +FEATURE_USER = .bpftool +FEATURE_TESTS = libbfd libbfd-liberty libbfd-liberty-z \ + disassembler-four-args disassembler-init-styled libcap \ + clang-bpf-co-re +FEATURE_DISPLAY = libbfd libbfd-liberty libbfd-liberty-z \ + libcap clang-bpf-co-re + +check_feat := 1 +NON_CHECK_FEAT_TARGETS := clean uninstall doc doc-clean doc-install doc-uninstall +ifdef MAKECMDGOALS +ifeq ($(filter-out $(NON_CHECK_FEAT_TARGETS),$(MAKECMDGOALS)),) + check_feat := 0 +endif +endif + +ifeq ($(check_feat),1) +ifeq ($(FEATURES_DUMP),) +include $(srctree)/tools/build/Makefile.feature +else +include $(FEATURES_DUMP) +endif +endif + +ifeq ($(feature-disassembler-four-args), 1) +CFLAGS += -DDISASM_FOUR_ARGS_SIGNATURE +endif +ifeq ($(feature-disassembler-init-styled), 1) + CFLAGS += -DDISASM_INIT_STYLED +endif + +LIBS = $(LIBBPF) -lelf -lz +LIBS_BOOTSTRAP = $(LIBBPF_BOOTSTRAP) -lelf -lz +ifeq ($(feature-libcap), 1) +CFLAGS += -DUSE_LIBCAP +LIBS += -lcap +endif + +include $(wildcard $(OUTPUT)*.d) + +all: $(OUTPUT)bpftool + +BFD_SRCS = jit_disasm.c + +SRCS = $(filter-out $(BFD_SRCS),$(wildcard *.c)) + +ifeq ($(feature-libbfd),1) + LIBS += -lbfd -ldl -lopcodes +else ifeq ($(feature-libbfd-liberty),1) + LIBS += -lbfd -ldl -lopcodes -liberty +else ifeq ($(feature-libbfd-liberty-z),1) + LIBS += -lbfd -ldl -lopcodes -liberty -lz +endif + +ifneq ($(filter -lbfd,$(LIBS)),) +CFLAGS += -DHAVE_LIBBFD_SUPPORT +SRCS += $(BFD_SRCS) +endif + +HOST_CFLAGS = $(subst -I$(LIBBPF_INCLUDE),-I$(LIBBPF_BOOTSTRAP_INCLUDE),\ + $(subst $(CLANG_CROSS_FLAGS),,$(CFLAGS))) + +BPFTOOL_BOOTSTRAP := $(BOOTSTRAP_OUTPUT)bpftool + +BOOTSTRAP_OBJS = $(addprefix $(BOOTSTRAP_OUTPUT),main.o common.o json_writer.o gen.o btf.o xlated_dumper.o btf_dumper.o disasm.o) +$(BOOTSTRAP_OBJS): $(LIBBPF_BOOTSTRAP) + +OBJS = $(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) $(OUTPUT)disasm.o +$(OBJS): $(LIBBPF) $(LIBBPF_INTERNAL_HDRS) + +VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux) \ + $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux) \ + ../../../vmlinux \ + /sys/kernel/btf/vmlinux \ + /boot/vmlinux-$(shell uname -r) +VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS)))) + +bootstrap: $(BPFTOOL_BOOTSTRAP) + +ifneq ($(VMLINUX_BTF)$(VMLINUX_H),) +ifeq ($(feature-clang-bpf-co-re),1) + +BUILD_BPF_SKELS := 1 + +$(OUTPUT)vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL_BOOTSTRAP) +ifeq ($(VMLINUX_H),) + $(QUIET_GEN)$(BPFTOOL_BOOTSTRAP) btf dump file $< format c > $@ +else + $(Q)cp "$(VMLINUX_H)" $@ +endif + +$(OUTPUT)%.bpf.o: skeleton/%.bpf.c $(OUTPUT)vmlinux.h $(LIBBPF_BOOTSTRAP) + $(QUIET_CLANG)$(CLANG) \ + -I$(or $(OUTPUT),.) \ + -I$(srctree)/tools/include/uapi/ \ + -I$(LIBBPF_BOOTSTRAP_INCLUDE) \ + -g -O2 -Wall -fno-stack-protector \ + -target bpf -c $< -o $@ + $(Q)$(LLVM_STRIP) -g $@ + +$(OUTPUT)%.skel.h: $(OUTPUT)%.bpf.o $(BPFTOOL_BOOTSTRAP) + $(QUIET_GEN)$(BPFTOOL_BOOTSTRAP) gen skeleton $< > $@ + +$(OUTPUT)prog.o: $(OUTPUT)profiler.skel.h + +$(OUTPUT)pids.o: $(OUTPUT)pid_iter.skel.h + +endif +endif + +CFLAGS += $(if $(BUILD_BPF_SKELS),,-DBPFTOOL_WITHOUT_SKELETONS) + +$(BOOTSTRAP_OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c + $(QUIET_CC)$(HOSTCC) $(HOST_CFLAGS) -c -MMD $< -o $@ + +$(OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c + $(QUIET_CC)$(CC) $(CFLAGS) -c -MMD $< -o $@ + +$(BPFTOOL_BOOTSTRAP): $(BOOTSTRAP_OBJS) $(LIBBPF_BOOTSTRAP) + $(QUIET_LINK)$(HOSTCC) $(HOST_CFLAGS) $(LDFLAGS) $(BOOTSTRAP_OBJS) $(LIBS_BOOTSTRAP) -o $@ + +$(OUTPUT)bpftool: $(OBJS) $(LIBBPF) + $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $(OBJS) $(LIBS) -o $@ + +$(BOOTSTRAP_OUTPUT)%.o: %.c $(LIBBPF_BOOTSTRAP_INTERNAL_HDRS) | $(BOOTSTRAP_OUTPUT) + $(QUIET_CC)$(HOSTCC) $(HOST_CFLAGS) -c -MMD $< -o $@ + +$(OUTPUT)%.o: %.c + $(QUIET_CC)$(CC) $(CFLAGS) -c -MMD $< -o $@ + +feature-detect-clean: + $(call QUIET_CLEAN, feature-detect) + $(Q)$(MAKE) -C $(srctree)/tools/build/feature/ clean >/dev/null + +clean: $(LIBBPF)-clean $(LIBBPF_BOOTSTRAP)-clean feature-detect-clean + $(call QUIET_CLEAN, bpftool) + $(Q)$(RM) -- $(OUTPUT)bpftool $(OUTPUT)*.o $(OUTPUT)*.d + $(Q)$(RM) -- $(OUTPUT)*.skel.h $(OUTPUT)vmlinux.h + $(Q)$(RM) -r -- $(LIBBPF_OUTPUT) $(BOOTSTRAP_OUTPUT) + $(call QUIET_CLEAN, core-gen) + $(Q)$(RM) -- $(OUTPUT)FEATURE-DUMP.bpftool + $(Q)$(RM) -r -- $(OUTPUT)feature/ + +install-bin: $(OUTPUT)bpftool + $(call QUIET_INSTALL, bpftool) + $(Q)$(INSTALL) -m 0755 -d $(DESTDIR)$(prefix)/sbin + $(Q)$(INSTALL) $(OUTPUT)bpftool $(DESTDIR)$(prefix)/sbin/bpftool + +install: install-bin + $(Q)$(INSTALL) -m 0755 -d $(DESTDIR)$(bash_compdir) + $(Q)$(INSTALL) -m 0644 bash-completion/bpftool $(DESTDIR)$(bash_compdir) + +uninstall: + $(call QUIET_UNINST, bpftool) + $(Q)$(RM) -- $(DESTDIR)$(prefix)/sbin/bpftool + $(Q)$(RM) -- $(DESTDIR)$(bash_compdir)/bpftool + +doc: + $(call descend,Documentation) + +doc-clean: + $(call descend,Documentation,clean) + +doc-install: + $(call descend,Documentation,install) + +doc-uninstall: + $(call descend,Documentation,uninstall) + +FORCE: + +.SECONDARY: +.PHONY: all FORCE bootstrap clean install-bin install uninstall +.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 new file mode 100644 index 000000000..dc1641e36 --- /dev/null +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -0,0 +1,1213 @@ +# bpftool(8) bash completion -*- shell-script -*- +# +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +# Copyright (C) 2017-2018 Netronome Systems, Inc. +# +# Author: Quentin Monnet <quentin.monnet@netronome.com> + +# Takes a list of words in argument; each one of them is added to COMPREPLY if +# it is not already present on the command line. Returns no value. +_bpftool_once_attr() +{ + local w idx found + for w in $*; do + found=0 + for (( idx=3; idx < ${#words[@]}-1; idx++ )); do + if [[ $w == ${words[idx]} ]]; then + found=1 + break + fi + done + [[ $found -eq 0 ]] && \ + COMPREPLY+=( $( compgen -W "$w" -- "$cur" ) ) + done +} + +# Takes a list of words as argument; if any of those words is present on the +# command line, return 0. Otherwise, return 1. +_bpftool_search_list() +{ + local w idx + for w in $*; do + for (( idx=3; idx < ${#words[@]}-1; idx++ )); do + [[ $w == ${words[idx]} ]] && return 0 + done + done + return 1 +} + +# Takes a list of words in argument; adds them all to COMPREPLY if none of them +# is already present on the command line. Returns no value. +_bpftool_one_of_list() +{ + _bpftool_search_list $* && return 1 + COMPREPLY+=( $( compgen -W "$*" -- "$cur" ) ) +} + +_bpftool_get_map_ids() +{ + COMPREPLY+=( $( compgen -W "$( bpftool -jp map 2>&1 | \ + command sed -n 's/.*"id": \(.*\),$/\1/p' )" -- "$cur" ) ) +} + +# Takes map type and adds matching map ids to the list of suggestions. +_bpftool_get_map_ids_for_type() +{ + local type="$1" + COMPREPLY+=( $( compgen -W "$( bpftool -jp map 2>&1 | \ + command grep -C2 "$type" | \ + command sed -n 's/.*"id": \(.*\),$/\1/p' )" -- "$cur" ) ) +} + +_bpftool_get_map_names() +{ + COMPREPLY+=( $( compgen -W "$( bpftool -jp map 2>&1 | \ + command sed -n 's/.*"name": \(.*\),$/\1/p' )" -- "$cur" ) ) +} + +# Takes map type and adds matching map names to the list of suggestions. +_bpftool_get_map_names_for_type() +{ + local type="$1" + COMPREPLY+=( $( compgen -W "$( bpftool -jp map 2>&1 | \ + command grep -C2 "$type" | \ + command sed -n 's/.*"name": \(.*\),$/\1/p' )" -- "$cur" ) ) +} + +_bpftool_get_prog_ids() +{ + COMPREPLY+=( $( compgen -W "$( bpftool -jp prog 2>&1 | \ + command sed -n 's/.*"id": \(.*\),$/\1/p' )" -- "$cur" ) ) +} + +_bpftool_get_prog_tags() +{ + COMPREPLY+=( $( compgen -W "$( bpftool -jp prog 2>&1 | \ + command sed -n 's/.*"tag": "\(.*\)",$/\1/p' )" -- "$cur" ) ) +} + +_bpftool_get_prog_names() +{ + COMPREPLY+=( $( compgen -W "$( bpftool -jp prog 2>&1 | \ + command sed -n 's/.*"name": "\(.*\)",$/\1/p' )" -- "$cur" ) ) +} + +_bpftool_get_btf_ids() +{ + COMPREPLY+=( $( compgen -W "$( bpftool -jp btf 2>&1 | \ + command sed -n 's/.*"id": \(.*\),$/\1/p' )" -- "$cur" ) ) +} + +_bpftool_get_link_ids() +{ + COMPREPLY+=( $( compgen -W "$( bpftool -jp link 2>&1 | \ + command sed -n 's/.*"id": \(.*\),$/\1/p' )" -- "$cur" ) ) +} + +_bpftool_get_obj_map_names() +{ + local obj + + obj=$1 + + maps=$(objdump -j maps -t $obj 2>/dev/null | \ + command awk '/g . maps/ {print $NF}') + + COMPREPLY+=( $( compgen -W "$maps" -- "$cur" ) ) +} + +_bpftool_get_obj_map_idxs() +{ + local obj + + obj=$1 + + nmaps=$(objdump -j maps -t $obj 2>/dev/null | grep -c 'g . maps') + + COMPREPLY+=( $( compgen -W "$(seq 0 $((nmaps - 1)))" -- "$cur" ) ) +} + +_sysfs_get_netdevs() +{ + COMPREPLY+=( $( compgen -W "$( ls /sys/class/net 2>/dev/null )" -- \ + "$cur" ) ) +} + +# Retrieve type of the map that we are operating on. +_bpftool_map_guess_map_type() +{ + local keyword ref + for (( idx=3; idx < ${#words[@]}-1; idx++ )); do + case "${words[$((idx-2))]}" in + lookup|update) + keyword=${words[$((idx-1))]} + ref=${words[$((idx))]} + ;; + push) + printf "stack" + return 0 + ;; + enqueue) + printf "queue" + return 0 + ;; + esac + done + [[ -z $ref ]] && return 0 + + local type + type=$(bpftool -jp map show $keyword $ref | \ + command sed -n 's/.*"type": "\(.*\)",$/\1/p') + [[ -n $type ]] && printf $type +} + +_bpftool_map_update_get_id() +{ + local command="$1" + + # Is it the map to update, or a map to insert into the map to update? + # Search for "value" keyword. + local idx value + for (( idx=7; idx < ${#words[@]}-1; idx++ )); do + if [[ ${words[idx]} == "value" ]]; then + value=1 + break + fi + done + if [[ $value -eq 0 ]]; then + case "$command" in + push) + _bpftool_get_map_ids_for_type stack + ;; + enqueue) + _bpftool_get_map_ids_for_type queue + ;; + *) + _bpftool_get_map_ids + ;; + esac + return 0 + fi + + # Id to complete is for a value. It can be either prog id or map id. This + # depends on the type of the map to update. + local type=$(_bpftool_map_guess_map_type) + case $type in + array_of_maps|hash_of_maps) + _bpftool_get_map_ids + return 0 + ;; + prog_array) + _bpftool_get_prog_ids + return 0 + ;; + *) + return 0 + ;; + esac +} + +_bpftool_map_update_get_name() +{ + local command="$1" + + # Is it the map to update, or a map to insert into the map to update? + # Search for "value" keyword. + local idx value + for (( idx=7; idx < ${#words[@]}-1; idx++ )); do + if [[ ${words[idx]} == "value" ]]; then + value=1 + break + fi + done + if [[ $value -eq 0 ]]; then + case "$command" in + push) + _bpftool_get_map_names_for_type stack + ;; + enqueue) + _bpftool_get_map_names_for_type queue + ;; + *) + _bpftool_get_map_names + ;; + esac + return 0 + fi + + # Name to complete is for a value. It can be either prog name or map name. This + # depends on the type of the map to update. + local type=$(_bpftool_map_guess_map_type) + case $type in + array_of_maps|hash_of_maps) + _bpftool_get_map_names + return 0 + ;; + prog_array) + _bpftool_get_prog_names + return 0 + ;; + *) + return 0 + ;; + esac +} + +_bpftool() +{ + local cur prev words objword + _init_completion || return + + # Deal with options + if [[ ${words[cword]} == -* ]]; then + local c='--version --json --pretty --bpffs --mapcompat --debug \ + --use-loader --base-btf --legacy' + COMPREPLY=( $( compgen -W "$c" -- "$cur" ) ) + return 0 + fi + + # Deal with simplest keywords + case $prev in + help|hex|opcodes|visual|linum) + return 0 + ;; + tag) + _bpftool_get_prog_tags + return 0 + ;; + dev) + _sysfs_get_netdevs + return 0 + ;; + file|pinned|-B|--base-btf) + _filedir + return 0 + ;; + batch) + COMPREPLY=( $( compgen -W 'file' -- "$cur" ) ) + return 0 + ;; + esac + + # Remove all options so completions don't have to deal with them. + local i + for (( i=1; i < ${#words[@]}; )); do + if [[ ${words[i]::1} == - ]] && + [[ ${words[i]} != "-B" ]] && [[ ${words[i]} != "--base-btf" ]]; then + words=( "${words[@]:0:i}" "${words[@]:i+1}" ) + [[ $i -le $cword ]] && cword=$(( cword - 1 )) + else + i=$(( ++i )) + fi + done + cur=${words[cword]} + prev=${words[cword - 1]} + pprev=${words[cword - 2]} + + local object=${words[1]} command=${words[2]} + + if [[ -z $object || $cword -eq 1 ]]; then + case $cur in + *) + COMPREPLY=( $( compgen -W "$( bpftool help 2>&1 | \ + command sed \ + -e '/OBJECT := /!d' \ + -e 's/.*{//' \ + -e 's/}.*//' \ + -e 's/|//g' )" -- "$cur" ) ) + COMPREPLY+=( $( compgen -W 'batch help' -- "$cur" ) ) + return 0 + ;; + esac + fi + + [[ $command == help ]] && return 0 + + # Completion depends on object and command in use + case $object in + prog) + # Complete id and name, only for subcommands that use prog (but no + # map) ids/names. + case $command in + show|list|dump|pin) + case $prev in + id) + _bpftool_get_prog_ids + return 0 + ;; + name) + _bpftool_get_prog_names + return 0 + ;; + esac + ;; + esac + + local PROG_TYPE='id pinned tag name' + local MAP_TYPE='id pinned name' + local METRIC_TYPE='cycles instructions l1d_loads llc_misses \ + itlb_misses dtlb_misses' + case $command in + show|list) + [[ $prev != "$command" ]] && return 0 + COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) ) + return 0 + ;; + dump) + case $prev in + $command) + COMPREPLY+=( $( compgen -W "xlated jited" -- \ + "$cur" ) ) + return 0 + ;; + xlated|jited) + COMPREPLY=( $( compgen -W "$PROG_TYPE" -- \ + "$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 + ;; + esac + ;; + pin) + if [[ $prev == "$command" ]]; then + COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) ) + else + _filedir + fi + return 0 + ;; + attach|detach) + case $cword in + 3) + COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) ) + return 0 + ;; + 4) + case $prev in + id) + _bpftool_get_prog_ids + ;; + name) + _bpftool_get_prog_names + ;; + pinned) + _filedir + ;; + esac + return 0 + ;; + 5) + local BPFTOOL_PROG_ATTACH_TYPES='sk_msg_verdict \ + sk_skb_verdict sk_skb_stream_verdict sk_skb_stream_parser \ + flow_dissector' + COMPREPLY=( $( compgen -W "$BPFTOOL_PROG_ATTACH_TYPES" -- "$cur" ) ) + return 0 + ;; + 6) + COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) ) + return 0 + ;; + 7) + case $prev in + id) + _bpftool_get_map_ids + ;; + name) + _bpftool_get_map_names + ;; + pinned) + _filedir + ;; + esac + return 0 + ;; + esac + ;; + 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 [[ ${#words[@]} -lt 6 ]]; then + _filedir + return 0 + fi + + obj=${words[3]} + + if [[ ${words[-4]} == "map" ]]; then + COMPREPLY=( $( compgen -W "id pinned" -- "$cur" ) ) + return 0 + fi + if [[ ${words[-3]} == "map" ]]; then + if [[ ${words[-2]} == "idx" ]]; then + _bpftool_get_obj_map_idxs $obj + elif [[ ${words[-2]} == "name" ]]; then + _bpftool_get_obj_map_names $obj + fi + return 0 + fi + if [[ ${words[-2]} == "map" ]]; then + COMPREPLY=( $( compgen -W "idx name" -- "$cur" ) ) + return 0 + fi + + case $prev in + type) + local BPFTOOL_PROG_LOAD_TYPES='socket kprobe \ + kretprobe classifier flow_dissector \ + action tracepoint raw_tracepoint \ + xdp perf_event cgroup/skb cgroup/sock \ + cgroup/dev lwt_in lwt_out lwt_xmit \ + lwt_seg6local sockops sk_skb sk_msg \ + lirc_mode2 cgroup/bind4 cgroup/bind6 \ + cgroup/connect4 cgroup/connect6 \ + cgroup/getpeername4 cgroup/getpeername6 \ + cgroup/getsockname4 cgroup/getsockname6 \ + cgroup/sendmsg4 cgroup/sendmsg6 \ + cgroup/recvmsg4 cgroup/recvmsg6 \ + cgroup/post_bind4 cgroup/post_bind6 \ + cgroup/sysctl cgroup/getsockopt \ + cgroup/setsockopt cgroup/sock_release struct_ops \ + fentry fexit freplace sk_lookup' + COMPREPLY=( $( compgen -W "$BPFTOOL_PROG_LOAD_TYPES" -- "$cur" ) ) + return 0 + ;; + id) + _bpftool_get_map_ids + return 0 + ;; + name) + _bpftool_get_map_names + return 0 + ;; + pinned|pinmaps) + _filedir + return 0 + ;; + *) + COMPREPLY=( $( compgen -W "map" -- "$cur" ) ) + _bpftool_once_attr 'type' + _bpftool_once_attr 'dev' + _bpftool_once_attr 'pinmaps' + return 0 + ;; + esac + ;; + tracelog) + return 0 + ;; + profile) + case $cword in + 3) + COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) ) + return 0 + ;; + 4) + case $prev in + id) + _bpftool_get_prog_ids + ;; + name) + _bpftool_get_prog_names + ;; + pinned) + _filedir + ;; + esac + return 0 + ;; + 5) + COMPREPLY=( $( compgen -W "$METRIC_TYPE duration" -- "$cur" ) ) + return 0 + ;; + 6) + case $prev in + duration) + return 0 + ;; + *) + COMPREPLY=( $( compgen -W "$METRIC_TYPE" -- "$cur" ) ) + return 0 + ;; + esac + return 0 + ;; + *) + COMPREPLY=( $( compgen -W "$METRIC_TYPE" -- "$cur" ) ) + return 0 + ;; + esac + ;; + run) + if [[ ${#words[@]} -eq 4 ]]; then + COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) ) + return 0 + fi + case $prev in + id) + _bpftool_get_prog_ids + return 0 + ;; + name) + _bpftool_get_prog_names + 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=( $( compgen -W 'dump help pin attach detach \ + load loadall show list tracelog run profile' -- "$cur" ) ) + ;; + esac + ;; + struct_ops) + local STRUCT_OPS_TYPE='id name' + case $command in + show|list|dump|unregister) + case $prev in + $command) + COMPREPLY=( $( compgen -W "$STRUCT_OPS_TYPE" -- "$cur" ) ) + ;; + id) + _bpftool_get_map_ids_for_type struct_ops + ;; + name) + _bpftool_get_map_names_for_type struct_ops + ;; + esac + return 0 + ;; + register) + _filedir + return 0 + ;; + *) + [[ $prev == $object ]] && \ + COMPREPLY=( $( compgen -W 'register unregister show list dump help' \ + -- "$cur" ) ) + ;; + esac + ;; + iter) + case $command in + pin) + case $prev in + $command) + _filedir + ;; + id) + _bpftool_get_map_ids + ;; + name) + _bpftool_get_map_names + ;; + pinned) + _filedir + ;; + *) + _bpftool_one_of_list $MAP_TYPE + ;; + esac + return 0 + ;; + *) + [[ $prev == $object ]] && \ + COMPREPLY=( $( compgen -W 'pin help' \ + -- "$cur" ) ) + ;; + esac + ;; + map) + local MAP_TYPE='id pinned name' + case $command in + show|list|dump|peek|pop|dequeue|freeze) + case $prev in + $command) + COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) ) + return 0 + ;; + id) + case "$command" in + peek) + _bpftool_get_map_ids_for_type stack + _bpftool_get_map_ids_for_type queue + ;; + pop) + _bpftool_get_map_ids_for_type stack + ;; + dequeue) + _bpftool_get_map_ids_for_type queue + ;; + *) + _bpftool_get_map_ids + ;; + esac + return 0 + ;; + name) + case "$command" in + peek) + _bpftool_get_map_names_for_type stack + _bpftool_get_map_names_for_type queue + ;; + pop) + _bpftool_get_map_names_for_type stack + ;; + dequeue) + _bpftool_get_map_names_for_type queue + ;; + *) + _bpftool_get_map_names + ;; + esac + return 0 + ;; + *) + return 0 + ;; + esac + ;; + create) + case $prev in + $command) + _filedir + return 0 + ;; + type) + local BPFTOOL_MAP_CREATE_TYPES="$(bpftool feature list_builtins map_types 2>/dev/null | \ + grep -v '^unspec$')" + COMPREPLY=( $( compgen -W "$BPFTOOL_MAP_CREATE_TYPES" -- "$cur" ) ) + return 0 + ;; + key|value|flags|entries) + return 0 + ;; + inner_map) + COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) ) + return 0 + ;; + id) + _bpftool_get_map_ids + ;; + name) + case $pprev in + inner_map) + _bpftool_get_map_names + ;; + *) + return 0 + ;; + esac + ;; + *) + _bpftool_once_attr 'type' + _bpftool_once_attr 'key' + _bpftool_once_attr 'value' + _bpftool_once_attr 'entries' + _bpftool_once_attr 'name' + _bpftool_once_attr 'flags' + if _bpftool_search_list 'array_of_maps' 'hash_of_maps'; then + _bpftool_once_attr 'inner_map' + fi + _bpftool_once_attr 'dev' + return 0 + ;; + esac + ;; + lookup|getnext|delete) + case $prev in + $command) + COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) ) + return 0 + ;; + id) + _bpftool_get_map_ids + return 0 + ;; + name) + _bpftool_get_map_names + return 0 + ;; + key) + COMPREPLY+=( $( compgen -W 'hex' -- "$cur" ) ) + ;; + *) + case $(_bpftool_map_guess_map_type) in + queue|stack) + return 0 + ;; + esac + + _bpftool_once_attr 'key' + return 0 + ;; + esac + ;; + update|push|enqueue) + case $prev in + $command) + COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) ) + return 0 + ;; + id) + _bpftool_map_update_get_id $command + return 0 + ;; + name) + _bpftool_map_update_get_name $command + return 0 + ;; + key) + COMPREPLY+=( $( compgen -W 'hex' -- "$cur" ) ) + ;; + value) + # We can have bytes, or references to a prog or a + # map, depending on the type of the map to update. + case "$(_bpftool_map_guess_map_type)" in + array_of_maps|hash_of_maps) + local MAP_TYPE='id pinned name' + COMPREPLY+=( $( compgen -W "$MAP_TYPE" \ + -- "$cur" ) ) + return 0 + ;; + prog_array) + local PROG_TYPE='id pinned tag name' + COMPREPLY+=( $( compgen -W "$PROG_TYPE" \ + -- "$cur" ) ) + return 0 + ;; + *) + COMPREPLY+=( $( compgen -W 'hex' \ + -- "$cur" ) ) + return 0 + ;; + esac + return 0 + ;; + *) + case $(_bpftool_map_guess_map_type) in + queue|stack) + _bpftool_once_attr 'value' + return 0; + ;; + esac + + _bpftool_once_attr 'key' + local UPDATE_FLAGS='any exist noexist' + for (( idx=3; idx < ${#words[@]}-1; idx++ )); do + if [[ ${words[idx]} == 'value' ]]; then + # 'value' is present, but is not the last + # word i.e. we can now have UPDATE_FLAGS. + _bpftool_one_of_list "$UPDATE_FLAGS" + return 0 + fi + done + for (( idx=3; idx < ${#words[@]}-1; idx++ )); do + if [[ ${words[idx]} == 'key' ]]; then + # 'key' is present, but is not the last + # word i.e. we can now have 'value'. + _bpftool_once_attr 'value' + return 0 + fi + done + + return 0 + ;; + esac + ;; + pin) + case $prev in + $command) + COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) ) + ;; + id) + _bpftool_get_map_ids + ;; + name) + _bpftool_get_map_names + ;; + esac + return 0 + ;; + event_pipe) + case $prev in + $command) + COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) ) + return 0 + ;; + id) + _bpftool_get_map_ids_for_type perf_event_array + return 0 + ;; + name) + _bpftool_get_map_names_for_type perf_event_array + return 0 + ;; + cpu) + return 0 + ;; + index) + return 0 + ;; + *) + _bpftool_once_attr 'cpu' + _bpftool_once_attr 'index' + return 0 + ;; + esac + ;; + *) + [[ $prev == $object ]] && \ + COMPREPLY=( $( compgen -W 'delete dump getnext help \ + lookup pin event_pipe show list update create \ + peek push enqueue pop dequeue freeze' -- \ + "$cur" ) ) + ;; + esac + ;; + btf) + local PROG_TYPE='id pinned tag name' + local MAP_TYPE='id pinned name' + 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 + ;; + name) + case $pprev in + prog) + _bpftool_get_prog_names + ;; + map) + _bpftool_get_map_names + ;; + 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) + case $prev in + $command) + COMPREPLY+=( $( compgen -W "id" -- "$cur" ) ) + ;; + id) + _bpftool_get_btf_ids + ;; + esac + return 0 + ;; + *) + [[ $prev == $object ]] && \ + COMPREPLY=( $( compgen -W 'dump help show list' \ + -- "$cur" ) ) + ;; + esac + ;; + gen) + case $command in + object) + _filedir + return 0 + ;; + skeleton) + case $prev in + $command) + _filedir + return 0 + ;; + *) + _bpftool_once_attr 'name' + return 0 + ;; + esac + ;; + subskeleton) + case $prev in + $command) + _filedir + return 0 + ;; + *) + _bpftool_once_attr 'name' + return 0 + ;; + esac + ;; + min_core_btf) + _filedir + return 0 + ;; + *) + [[ $prev == $object ]] && \ + COMPREPLY=( $( compgen -W 'object skeleton subskeleton help min_core_btf' -- "$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 BPFTOOL_CGROUP_ATTACH_TYPES="$(bpftool feature list_builtins attach_types 2>/dev/null | \ + grep '^cgroup_')" + local ATTACH_FLAGS='multi override' + local PROG_TYPE='id pinned tag name' + # Check for $prev = $command first + if [ $prev = $command ]; then + _filedir + return 0 + # Then check for attach type. This is done outside of the + # "case $prev in" to avoid writing the whole list of attach + # types again as pattern to match (where we cannot reuse + # our variable). + elif [[ $BPFTOOL_CGROUP_ATTACH_TYPES =~ $prev ]]; then + COMPREPLY=( $( compgen -W "$PROG_TYPE" -- \ + "$cur" ) ) + return 0 + fi + # case/esac for the other cases + case $prev in + id) + _bpftool_get_prog_ids + return 0 + ;; + *) + if ! _bpftool_search_list "$BPFTOOL_CGROUP_ATTACH_TYPES"; then + COMPREPLY=( $( compgen -W \ + "$BPFTOOL_CGROUP_ATTACH_TYPES" -- "$cur" ) ) + elif [[ "$command" == "attach" ]]; then + # We have an attach type on the command line, + # but it is not the previous word, or + # "id|pinned|tag|name" (we already checked for + # that). This should only leave the case when + # we need attach flags for "attach" commamnd. + _bpftool_one_of_list "$ATTACH_FLAGS" + fi + return 0 + ;; + esac + ;; + *) + [[ $prev == $object ]] && \ + COMPREPLY=( $( compgen -W 'help attach detach \ + show list tree' -- "$cur" ) ) + ;; + esac + ;; + perf) + case $command in + *) + [[ $prev == $object ]] && \ + COMPREPLY=( $( compgen -W 'help \ + show list' -- "$cur" ) ) + ;; + esac + ;; + net) + local PROG_TYPE='id pinned tag name' + 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 + ;; + name) + _bpftool_get_prog_names + ;; + 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=( $( compgen -W 'help \ + show list attach detach' -- "$cur" ) ) + ;; + esac + ;; + feature) + case $command in + probe) + [[ $prev == "prefix" ]] && return 0 + if _bpftool_search_list 'macros'; then + _bpftool_once_attr 'prefix' + else + COMPREPLY+=( $( compgen -W 'macros' -- "$cur" ) ) + fi + _bpftool_one_of_list 'kernel dev' + _bpftool_once_attr 'full unprivileged' + return 0 + ;; + list_builtins) + [[ $prev != "$command" ]] && return 0 + COMPREPLY=( $( compgen -W 'prog_types map_types \ + attach_types link_types helpers' -- "$cur" ) ) + ;; + *) + [[ $prev == $object ]] && \ + COMPREPLY=( $( compgen -W 'help list_builtins probe' -- "$cur" ) ) + ;; + esac + ;; + link) + case $command in + show|list|pin|detach) + case $prev in + id) + _bpftool_get_link_ids + return 0 + ;; + esac + ;; + esac + + local LINK_TYPE='id pinned' + case $command in + show|list) + [[ $prev != "$command" ]] && return 0 + COMPREPLY=( $( compgen -W "$LINK_TYPE" -- "$cur" ) ) + return 0 + ;; + pin|detach) + if [[ $prev == "$command" ]]; then + COMPREPLY=( $( compgen -W "$LINK_TYPE" -- "$cur" ) ) + else + _filedir + fi + return 0 + ;; + *) + [[ $prev == $object ]] && \ + COMPREPLY=( $( compgen -W 'help pin show list' -- "$cur" ) ) + ;; + esac + ;; + esac +} && +complete -F _bpftool bpftool + +# ex: ts=4 sw=4 et filetype=sh diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c new file mode 100644 index 000000000..68a70ac03 --- /dev/null +++ b/tools/bpf/bpftool/btf.c @@ -0,0 +1,1095 @@ +// 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 <linux/btf.h> +#include <sys/types.h> +#include <sys/stat.h> + +#include <bpf/bpf.h> +#include <bpf/btf.h> +#include <bpf/hashmap.h> +#include <bpf/libbpf.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", + [BTF_KIND_FLOAT] = "FLOAT", + [BTF_KIND_DECL_TAG] = "DECL_TAG", + [BTF_KIND_TYPE_TAG] = "TYPE_TAG", + [BTF_KIND_ENUM64] = "ENUM64", +}; + +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"; + case BTF_VAR_GLOBAL_EXTERN: + return "extern"; + default: + return "(unknown)"; + } +} + +static const char *btf_func_linkage_str(const struct btf_type *t) +{ + switch (btf_vlen(t)) { + case BTF_FUNC_STATIC: + return "static"; + case BTF_FUNC_GLOBAL: + return "global"; + case BTF_FUNC_EXTERN: + return "extern"; + 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 btf_kind_safe(int kind) +{ + return kind <= BTF_KIND_MAX ? kind : BTF_KIND_UNKN; +} + +static int dump_btf_type(const struct btf *btf, __u32 id, + const struct btf_type *t) +{ + json_writer_t *w = json_wtr; + int kind = btf_kind(t); + + if (json_output) { + jsonw_start_object(w); + jsonw_uint_field(w, "id", id); + jsonw_string_field(w, "kind", btf_kind_str[btf_kind_safe(kind)]); + jsonw_string_field(w, "name", btf_str(btf, t->name_off)); + } else { + printf("[%u] %s '%s'", id, btf_kind_str[btf_kind_safe(kind)], + btf_str(btf, t->name_off)); + } + + switch (kind) { + 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: + case BTF_KIND_TYPE_TAG: + 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); + const char *encoding; + int i; + + encoding = btf_kflag(t) ? "SIGNED" : "UNSIGNED"; + if (json_output) { + jsonw_string_field(w, "encoding", encoding); + jsonw_uint_field(w, "size", t->size); + jsonw_uint_field(w, "vlen", vlen); + jsonw_name(w, "values"); + jsonw_start_array(w); + } else { + printf(" encoding=%s size=%u vlen=%u", encoding, 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); + if (btf_kflag(t)) + jsonw_int_field(w, "val", v->val); + else + jsonw_uint_field(w, "val", v->val); + jsonw_end_object(w); + } else { + if (btf_kflag(t)) + printf("\n\t'%s' val=%d", name, v->val); + else + printf("\n\t'%s' val=%u", name, v->val); + } + } + if (json_output) + jsonw_end_array(w); + break; + } + case BTF_KIND_ENUM64: { + const struct btf_enum64 *v = btf_enum64(t); + __u16 vlen = btf_vlen(t); + const char *encoding; + int i; + + encoding = btf_kflag(t) ? "SIGNED" : "UNSIGNED"; + if (json_output) { + jsonw_string_field(w, "encoding", encoding); + jsonw_uint_field(w, "size", t->size); + jsonw_uint_field(w, "vlen", vlen); + jsonw_name(w, "values"); + jsonw_start_array(w); + } else { + printf(" encoding=%s size=%u vlen=%u", encoding, t->size, vlen); + } + for (i = 0; i < vlen; i++, v++) { + const char *name = btf_str(btf, v->name_off); + __u64 val = ((__u64)v->val_hi32 << 32) | v->val_lo32; + + if (json_output) { + jsonw_start_object(w); + jsonw_string_field(w, "name", name); + if (btf_kflag(t)) + jsonw_int_field(w, "val", val); + else + jsonw_uint_field(w, "val", val); + jsonw_end_object(w); + } else { + if (btf_kflag(t)) + printf("\n\t'%s' val=%lldLL", name, + (unsigned long long)val); + else + printf("\n\t'%s' val=%lluULL", name, + (unsigned long long)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: { + const char *linkage = btf_func_linkage_str(t); + + 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_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); + const struct btf_type *vt; + __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 (v->type < btf__type_cnt(btf)) { + vt = btf__type_by_id(btf, v->type); + printf(" (%s '%s')", + btf_kind_str[btf_kind_safe(btf_kind(vt))], + btf_str(btf, vt->name_off)); + } + } + } + if (json_output) + jsonw_end_array(w); + break; + } + case BTF_KIND_FLOAT: { + if (json_output) + jsonw_uint_field(w, "size", t->size); + else + printf(" size=%u", t->size); + break; + } + case BTF_KIND_DECL_TAG: { + const struct btf_decl_tag *tag = (const void *)(t + 1); + + if (json_output) { + jsonw_uint_field(w, "type_id", t->type); + jsonw_int_field(w, "component_idx", tag->component_idx); + } else { + printf(" type_id=%u component_idx=%d", t->type, tag->component_idx); + } + 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 { + const struct btf *base; + int cnt = btf__type_cnt(btf); + int start_id = 1; + + base = btf__base_btf(btf); + if (base) + start_id = btf__type_cnt(base); + + for (i = start_id; 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, btf_dump_printf, NULL, NULL); + err = libbpf_get_error(d); + if (err) + return err; + + printf("#ifndef __VMLINUX_H__\n"); + printf("#define __VMLINUX_H__\n"); + printf("\n"); + printf("#ifndef BPF_NO_PRESERVE_ACCESS_INDEX\n"); + printf("#pragma clang attribute push (__attribute__((preserve_access_index)), apply_to = record)\n"); + printf("#endif\n\n"); + + 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__type_cnt(btf); + + for (i = 1; i < cnt; i++) { + err = btf_dump__dump_type(d, i); + if (err) + goto done; + } + } + + printf("#ifndef BPF_NO_PRESERVE_ACCESS_INDEX\n"); + printf("#pragma clang attribute pop\n"); + printf("#endif\n"); + printf("\n"); + printf("#endif /* __VMLINUX_H__ */\n"); + +done: + btf_dump__free(d); + return err; +} + +static const char sysfs_vmlinux[] = "/sys/kernel/btf/vmlinux"; + +static struct btf *get_vmlinux_btf_from_sysfs(void) +{ + struct btf *base; + + base = btf__parse(sysfs_vmlinux, NULL); + if (libbpf_get_error(base)) { + p_err("failed to parse vmlinux BTF at '%s': %ld\n", + sysfs_vmlinux, libbpf_get_error(base)); + base = NULL; + } + + return base; +} + +#define BTF_NAME_BUFF_LEN 64 + +static bool btf_is_kernel_module(__u32 btf_id) +{ + struct bpf_btf_info btf_info = {}; + char btf_name[BTF_NAME_BUFF_LEN]; + int btf_fd; + __u32 len; + int err; + + btf_fd = bpf_btf_get_fd_by_id(btf_id); + if (btf_fd < 0) { + p_err("can't get BTF object by id (%u): %s", btf_id, strerror(errno)); + return false; + } + + len = sizeof(btf_info); + btf_info.name = ptr_to_u64(btf_name); + btf_info.name_len = sizeof(btf_name); + err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len); + close(btf_fd); + if (err) { + p_err("can't get BTF (ID %u) object info: %s", btf_id, strerror(errno)); + return false; + } + + return btf_info.kernel_btf && strncmp(btf_name, "vmlinux", sizeof(btf_name)) != 0; +} + +static int do_dump(int argc, char **argv) +{ + struct btf *btf = NULL, *base = 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")) { + const char sysfs_prefix[] = "/sys/kernel/btf/"; + + if (!base_btf && + strncmp(*argv, sysfs_prefix, sizeof(sysfs_prefix) - 1) == 0 && + strcmp(*argv, sysfs_vmlinux) != 0) + base = get_vmlinux_btf_from_sysfs(); + + btf = btf__parse_split(*argv, base ?: base_btf); + err = libbpf_get_error(btf); + if (!btf) { + p_err("failed to load BTF from %s: %s", + *argv, strerror(errno)); + 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"); + err = -EINVAL; + 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); + err = -EINVAL; + goto done; + } + NEXT_ARG(); + } else { + p_err("unrecognized option: '%s'", *argv); + err = -EINVAL; + goto done; + } + } + + if (!btf) { + if (!base_btf && btf_is_kernel_module(btf_id)) { + p_info("Warning: valid base BTF was not specified with -B option, falling back to standard base BTF (%s)", + sysfs_vmlinux); + base_btf = get_vmlinux_btf_from_sysfs(); + } + + btf = btf__load_from_kernel_by_id_split(btf_id, base_btf); + err = libbpf_get_error(btf); + if (!btf) { + p_err("get btf by id (%u): %s", btf_id, strerror(errno)); + 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); + btf__free(base); + 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 int +build_btf_type_table(struct hashmap *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", + }; + __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; + + err = hashmap__append(tab, u32_as_hash_field(btf_id), + u32_as_hash_field(id)); + if (err) { + p_err("failed to append entry to hashmap for BTF ID %u, object ID %u: %s", + btf_id, id, strerror(-err)); + goto err_free; + } + } + + return 0; + +err_free: + hashmap__free(tab); + return err; +} + +static int +build_btf_tables(struct hashmap *btf_prog_table, + struct hashmap *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) { + hashmap__free(btf_prog_table); + return err; + } + + return 0; +} + +static void +show_btf_plain(struct bpf_btf_info *info, int fd, + struct hashmap *btf_prog_table, + struct hashmap *btf_map_table) +{ + struct hashmap_entry *entry; + const char *name = u64_to_ptr(info->name); + int n; + + printf("%u: ", info->id); + if (info->kernel_btf) + printf("name [%s] ", name); + else if (name && name[0]) + printf("name %s ", name); + else + printf("name <anon> "); + printf("size %uB", info->btf_size); + + n = 0; + hashmap__for_each_key_entry(btf_prog_table, entry, + u32_as_hash_field(info->id)) { + printf("%s%u", n++ == 0 ? " prog_ids " : ",", + hash_field_as_u32(entry->value)); + } + + n = 0; + hashmap__for_each_key_entry(btf_map_table, entry, + u32_as_hash_field(info->id)) { + printf("%s%u", n++ == 0 ? " map_ids " : ",", + hash_field_as_u32(entry->value)); + } + + emit_obj_refs_plain(refs_table, info->id, "\n\tpids "); + + printf("\n"); +} + +static void +show_btf_json(struct bpf_btf_info *info, int fd, + struct hashmap *btf_prog_table, + struct hashmap *btf_map_table) +{ + struct hashmap_entry *entry; + const char *name = u64_to_ptr(info->name); + + 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 */ + hashmap__for_each_key_entry(btf_prog_table, entry, + u32_as_hash_field(info->id)) { + jsonw_uint(json_wtr, hash_field_as_u32(entry->value)); + } + jsonw_end_array(json_wtr); /* prog_ids */ + + jsonw_name(json_wtr, "map_ids"); + jsonw_start_array(json_wtr); /* map_ids */ + hashmap__for_each_key_entry(btf_map_table, entry, + u32_as_hash_field(info->id)) { + jsonw_uint(json_wtr, hash_field_as_u32(entry->value)); + } + jsonw_end_array(json_wtr); /* map_ids */ + + emit_obj_refs_json(refs_table, info->id, json_wtr); /* pids */ + + jsonw_bool_field(json_wtr, "kernel", info->kernel_btf); + + if (name && name[0]) + jsonw_string_field(json_wtr, "name", name); + + jsonw_end_object(json_wtr); /* btf object */ +} + +static int +show_btf(int fd, struct hashmap *btf_prog_table, + struct hashmap *btf_map_table) +{ + struct bpf_btf_info info; + __u32 len = sizeof(info); + char name[64]; + int err; + + memset(&info, 0, sizeof(info)); + 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 kernel support emitting BTF object name, pass name pointer */ + if (info.name_len) { + memset(&info, 0, sizeof(info)); + info.name_len = sizeof(name); + info.name = ptr_to_u64(name); + len = sizeof(info); + + 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 hashmap *btf_prog_table; + struct hashmap *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(); + } + + btf_prog_table = hashmap__new(hash_fn_for_key_as_id, + equal_fn_for_key_as_id, NULL); + btf_map_table = hashmap__new(hash_fn_for_key_as_id, + equal_fn_for_key_as_id, NULL); + if (IS_ERR(btf_prog_table) || IS_ERR(btf_map_table)) { + hashmap__free(btf_prog_table); + hashmap__free(btf_map_table); + if (fd >= 0) + close(fd); + p_err("failed to create hashmap for object references"); + return -1; + } + err = build_btf_tables(btf_prog_table, btf_map_table); + if (err) { + if (fd >= 0) + close(fd); + return err; + } + build_obj_refs_table(&refs_table, BPF_OBJ_BTF); + + 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: + hashmap__free(btf_prog_table); + hashmap__free(btf_map_table); + delete_obj_refs_table(refs_table); + + return err; +} + +static int do_help(int argc, char **argv) +{ + if (json_output) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %1$s %2$s { show | list } [id BTF_ID]\n" + " %1$s %2$s dump BTF_SRC [format FORMAT]\n" + " %1$s %2$s 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" + " {-B|--base-btf} }\n" + "", + bin_name, "btf"); + + 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 new file mode 100644 index 000000000..19924b6ce --- /dev/null +++ b/tools/bpf/bpftool/btf_dumper.c @@ -0,0 +1,823 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (c) 2018 Facebook */ + +#include <ctype.h> +#include <stdio.h> /* for (FILE *) used by json_writer */ +#include <string.h> +#include <unistd.h> +#include <asm/byteorder.h> +#include <linux/bitops.h> +#include <linux/btf.h> +#include <linux/err.h> +#include <bpf/btf.h> +#include <bpf/bpf.h> + +#include "json_writer.h" +#include "main.h" + +#define BITS_PER_BYTE_MASK (BITS_PER_BYTE - 1) +#define BITS_PER_BYTE_MASKED(bits) ((bits) & BITS_PER_BYTE_MASK) +#define BITS_ROUNDDOWN_BYTES(bits) ((bits) >> 3) +#define BITS_ROUNDUP_BYTES(bits) \ + (BITS_ROUNDDOWN_BYTES(bits) + !!BITS_PER_BYTE_MASKED(bits)) + +static int btf_dumper_do_type(const struct btf_dumper *d, __u32 type_id, + __u8 bit_offset, const void *data); + +static int btf_dump_func(const struct btf *btf, char *func_sig, + const struct btf_type *func_proto, + const struct btf_type *func, int pos, int size); + +static int dump_prog_id_as_func_ptr(const struct btf_dumper *d, + const struct btf_type *func_proto, + __u32 prog_id) +{ + const struct btf_type *func_type; + int prog_fd = -1, func_sig_len; + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + const char *prog_name = NULL; + struct btf *prog_btf = NULL; + struct bpf_func_info finfo; + __u32 finfo_rec_size; + char prog_str[1024]; + int err; + + /* Get the ptr's func_proto */ + func_sig_len = btf_dump_func(d->btf, prog_str, func_proto, NULL, 0, + sizeof(prog_str)); + if (func_sig_len == -1) + return -1; + + if (!prog_id) + goto print; + + /* Get the bpf_prog's name. Obtain from func_info. */ + prog_fd = bpf_prog_get_fd_by_id(prog_id); + if (prog_fd < 0) + goto print; + + err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + if (err) + goto print; + + if (!info.btf_id || !info.nr_func_info) + goto print; + + finfo_rec_size = info.func_info_rec_size; + memset(&info, 0, sizeof(info)); + info.nr_func_info = 1; + info.func_info_rec_size = finfo_rec_size; + info.func_info = ptr_to_u64(&finfo); + + err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + if (err) + goto print; + + prog_btf = btf__load_from_kernel_by_id(info.btf_id); + if (libbpf_get_error(prog_btf)) + goto print; + func_type = btf__type_by_id(prog_btf, finfo.type_id); + if (!func_type || !btf_is_func(func_type)) + goto print; + + prog_name = btf__name_by_offset(prog_btf, func_type->name_off); + +print: + if (!prog_id) + snprintf(&prog_str[func_sig_len], + sizeof(prog_str) - func_sig_len, " 0"); + else if (prog_name) + snprintf(&prog_str[func_sig_len], + sizeof(prog_str) - func_sig_len, + " %s/prog_id:%u", prog_name, prog_id); + else + snprintf(&prog_str[func_sig_len], + sizeof(prog_str) - func_sig_len, + " <unknown_prog_name>/prog_id:%u", prog_id); + + prog_str[sizeof(prog_str) - 1] = '\0'; + jsonw_string(d->jw, prog_str); + btf__free(prog_btf); + if (prog_fd >= 0) + close(prog_fd); + return 0; +} + +static void btf_dumper_ptr(const struct btf_dumper *d, + const struct btf_type *t, + const void *data) +{ + unsigned long value = *(unsigned long *)data; + const struct btf_type *ptr_type; + __s32 ptr_type_id; + + if (!d->prog_id_as_func_ptr || value > UINT32_MAX) + goto print_ptr_value; + + ptr_type_id = btf__resolve_type(d->btf, t->type); + if (ptr_type_id < 0) + goto print_ptr_value; + ptr_type = btf__type_by_id(d->btf, ptr_type_id); + if (!ptr_type || !btf_is_func_proto(ptr_type)) + goto print_ptr_value; + + if (!dump_prog_id_as_func_ptr(d, ptr_type, value)) + return; + +print_ptr_value: + if (d->is_plain_text) + jsonw_printf(d->jw, "%p", (void *)value); + else + jsonw_printf(d->jw, "%lu", value); +} + +static int btf_dumper_modifier(const struct btf_dumper *d, __u32 type_id, + __u8 bit_offset, const void *data) +{ + int actual_type_id; + + actual_type_id = btf__resolve_type(d->btf, type_id); + if (actual_type_id < 0) + return actual_type_id; + + return btf_dumper_do_type(d, actual_type_id, bit_offset, data); +} + +static int btf_dumper_enum(const struct btf_dumper *d, + const struct btf_type *t, + const void *data) +{ + const struct btf_enum *enums = btf_enum(t); + __s64 value; + __u16 i; + + switch (t->size) { + case 8: + value = *(__s64 *)data; + break; + case 4: + value = *(__s32 *)data; + break; + case 2: + value = *(__s16 *)data; + break; + case 1: + value = *(__s8 *)data; + break; + default: + return -EINVAL; + } + + for (i = 0; i < btf_vlen(t); i++) { + if (value == enums[i].val) { + jsonw_string(d->jw, + btf__name_by_offset(d->btf, + enums[i].name_off)); + return 0; + } + } + + jsonw_int(d->jw, value); + return 0; +} + +static int btf_dumper_enum64(const struct btf_dumper *d, + const struct btf_type *t, + const void *data) +{ + const struct btf_enum64 *enums = btf_enum64(t); + __u32 val_lo32, val_hi32; + __u64 value; + __u16 i; + + value = *(__u64 *)data; + val_lo32 = (__u32)value; + val_hi32 = value >> 32; + + for (i = 0; i < btf_vlen(t); i++) { + if (val_lo32 == enums[i].val_lo32 && val_hi32 == enums[i].val_hi32) { + jsonw_string(d->jw, + btf__name_by_offset(d->btf, + enums[i].name_off)); + return 0; + } + } + + jsonw_int(d->jw, value); + return 0; +} + +static bool is_str_array(const struct btf *btf, const struct btf_array *arr, + const char *s) +{ + const struct btf_type *elem_type; + const char *end_s; + + if (!arr->nelems) + return false; + + elem_type = btf__type_by_id(btf, arr->type); + /* Not skipping typedef. typedef to char does not count as + * a string now. + */ + while (elem_type && btf_is_mod(elem_type)) + elem_type = btf__type_by_id(btf, elem_type->type); + + if (!elem_type || !btf_is_int(elem_type) || elem_type->size != 1) + return false; + + if (btf_int_encoding(elem_type) != BTF_INT_CHAR && + strcmp("char", btf__name_by_offset(btf, elem_type->name_off))) + return false; + + end_s = s + arr->nelems; + while (s < end_s) { + if (!*s) + return true; + if (*s <= 0x1f || *s >= 0x7f) + return false; + s++; + } + + /* '\0' is not found */ + return false; +} + +static int btf_dumper_array(const struct btf_dumper *d, __u32 type_id, + const void *data) +{ + const struct btf_type *t = btf__type_by_id(d->btf, type_id); + struct btf_array *arr = (struct btf_array *)(t + 1); + long long elem_size; + int ret = 0; + __u32 i; + + if (is_str_array(d->btf, arr, data)) { + jsonw_string(d->jw, data); + return 0; + } + + elem_size = btf__resolve_size(d->btf, arr->type); + if (elem_size < 0) + return elem_size; + + jsonw_start_array(d->jw); + for (i = 0; i < arr->nelems; i++) { + ret = btf_dumper_do_type(d, arr->type, 0, + data + i * elem_size); + if (ret) + break; + } + + jsonw_end_array(d->jw); + return ret; +} + +static void btf_int128_print(json_writer_t *jw, const void *data, + bool is_plain_text) +{ + /* data points to a __int128 number. + * Suppose + * int128_num = *(__int128 *)data; + * The below formulas shows what upper_num and lower_num represents: + * upper_num = int128_num >> 64; + * lower_num = int128_num & 0xffffffffFFFFFFFFULL; + */ + __u64 upper_num, lower_num; + +#ifdef __BIG_ENDIAN_BITFIELD + upper_num = *(__u64 *)data; + lower_num = *(__u64 *)(data + 8); +#else + upper_num = *(__u64 *)(data + 8); + lower_num = *(__u64 *)data; +#endif + + if (is_plain_text) { + if (upper_num == 0) + jsonw_printf(jw, "0x%llx", lower_num); + else + jsonw_printf(jw, "0x%llx%016llx", upper_num, lower_num); + } else { + if (upper_num == 0) + jsonw_printf(jw, "\"0x%llx\"", lower_num); + else + jsonw_printf(jw, "\"0x%llx%016llx\"", upper_num, lower_num); + } +} + +static void btf_int128_shift(__u64 *print_num, __u16 left_shift_bits, + __u16 right_shift_bits) +{ + __u64 upper_num, lower_num; + +#ifdef __BIG_ENDIAN_BITFIELD + upper_num = print_num[0]; + lower_num = print_num[1]; +#else + upper_num = print_num[1]; + lower_num = print_num[0]; +#endif + + /* shake out un-needed bits by shift/or operations */ + if (left_shift_bits >= 64) { + upper_num = lower_num << (left_shift_bits - 64); + lower_num = 0; + } else { + upper_num = (upper_num << left_shift_bits) | + (lower_num >> (64 - left_shift_bits)); + lower_num = lower_num << left_shift_bits; + } + + if (right_shift_bits >= 64) { + lower_num = upper_num >> (right_shift_bits - 64); + upper_num = 0; + } else { + lower_num = (lower_num >> right_shift_bits) | + (upper_num << (64 - right_shift_bits)); + upper_num = upper_num >> right_shift_bits; + } + +#ifdef __BIG_ENDIAN_BITFIELD + print_num[0] = upper_num; + print_num[1] = lower_num; +#else + print_num[0] = lower_num; + print_num[1] = upper_num; +#endif +} + +static void btf_dumper_bitfield(__u32 nr_bits, __u8 bit_offset, + const void *data, json_writer_t *jw, + bool is_plain_text) +{ + int left_shift_bits, right_shift_bits; + __u64 print_num[2] = {}; + int bytes_to_copy; + int bits_to_copy; + + bits_to_copy = bit_offset + nr_bits; + bytes_to_copy = BITS_ROUNDUP_BYTES(bits_to_copy); + + memcpy(print_num, data, bytes_to_copy); +#if defined(__BIG_ENDIAN_BITFIELD) + left_shift_bits = bit_offset; +#elif defined(__LITTLE_ENDIAN_BITFIELD) + left_shift_bits = 128 - bits_to_copy; +#else +#error neither big nor little endian +#endif + right_shift_bits = 128 - nr_bits; + + btf_int128_shift(print_num, left_shift_bits, right_shift_bits); + btf_int128_print(jw, print_num, is_plain_text); +} + + +static void btf_dumper_int_bits(__u32 int_type, __u8 bit_offset, + const void *data, json_writer_t *jw, + bool is_plain_text) +{ + int nr_bits = BTF_INT_BITS(int_type); + int total_bits_offset; + + /* bits_offset is at most 7. + * BTF_INT_OFFSET() cannot exceed 128 bits. + */ + total_bits_offset = bit_offset + BTF_INT_OFFSET(int_type); + data += BITS_ROUNDDOWN_BYTES(total_bits_offset); + bit_offset = BITS_PER_BYTE_MASKED(total_bits_offset); + btf_dumper_bitfield(nr_bits, bit_offset, data, jw, + is_plain_text); +} + +static int btf_dumper_int(const struct btf_type *t, __u8 bit_offset, + const void *data, json_writer_t *jw, + bool is_plain_text) +{ + __u32 *int_type; + __u32 nr_bits; + + int_type = (__u32 *)(t + 1); + nr_bits = BTF_INT_BITS(*int_type); + /* if this is bit field */ + if (bit_offset || BTF_INT_OFFSET(*int_type) || + BITS_PER_BYTE_MASKED(nr_bits)) { + btf_dumper_int_bits(*int_type, bit_offset, data, jw, + is_plain_text); + return 0; + } + + if (nr_bits == 128) { + btf_int128_print(jw, data, is_plain_text); + return 0; + } + + switch (BTF_INT_ENCODING(*int_type)) { + case 0: + if (BTF_INT_BITS(*int_type) == 64) + 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) + jsonw_printf(jw, "%hu", *(__u16 *)data); + else if (BTF_INT_BITS(*int_type) == 8) + jsonw_printf(jw, "%hhu", *(__u8 *)data); + else + btf_dumper_int_bits(*int_type, bit_offset, data, jw, + is_plain_text); + break; + case BTF_INT_SIGNED: + if (BTF_INT_BITS(*int_type) == 64) + 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) + jsonw_printf(jw, "%hd", *(short *)data); + else if (BTF_INT_BITS(*int_type) == 8) + jsonw_printf(jw, "%hhd", *(char *)data); + else + btf_dumper_int_bits(*int_type, bit_offset, data, jw, + is_plain_text); + break; + case BTF_INT_CHAR: + if (isprint(*(char *)data)) + jsonw_printf(jw, "\"%c\"", *(char *)data); + else + if (is_plain_text) + jsonw_printf(jw, "0x%hhx", *(char *)data); + else + jsonw_printf(jw, "\"\\u00%02hhx\"", + *(char *)data); + break; + case BTF_INT_BOOL: + jsonw_bool(jw, *(bool *)data); + break; + default: + /* shouldn't happen */ + return -EINVAL; + } + + return 0; +} + +static int btf_dumper_struct(const struct btf_dumper *d, __u32 type_id, + const void *data) +{ + const struct btf_type *t; + struct btf_member *m; + const void *data_off; + int kind_flag; + int ret = 0; + int i, vlen; + + t = btf__type_by_id(d->btf, type_id); + if (!t) + return -EINVAL; + + kind_flag = BTF_INFO_KFLAG(t->info); + vlen = BTF_INFO_VLEN(t->info); + jsonw_start_object(d->jw); + m = (struct btf_member *)(t + 1); + + for (i = 0; i < vlen; i++) { + __u32 bit_offset = m[i].offset; + __u32 bitfield_size = 0; + + if (kind_flag) { + bitfield_size = BTF_MEMBER_BITFIELD_SIZE(bit_offset); + bit_offset = BTF_MEMBER_BIT_OFFSET(bit_offset); + } + + jsonw_name(d->jw, btf__name_by_offset(d->btf, m[i].name_off)); + data_off = data + BITS_ROUNDDOWN_BYTES(bit_offset); + if (bitfield_size) { + btf_dumper_bitfield(bitfield_size, + BITS_PER_BYTE_MASKED(bit_offset), + data_off, d->jw, d->is_plain_text); + } else { + ret = btf_dumper_do_type(d, m[i].type, + BITS_PER_BYTE_MASKED(bit_offset), + data_off); + if (ret) + break; + } + } + + jsonw_end_object(d->jw); + + 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) +{ + const struct btf_type *t = btf__type_by_id(d->btf, type_id); + + switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_INT: + return btf_dumper_int(t, bit_offset, data, d->jw, + d->is_plain_text); + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + return btf_dumper_struct(d, type_id, data); + case BTF_KIND_ARRAY: + return btf_dumper_array(d, type_id, data); + case BTF_KIND_ENUM: + return btf_dumper_enum(d, t, data); + case BTF_KIND_ENUM64: + return btf_dumper_enum64(d, t, data); + case BTF_KIND_PTR: + btf_dumper_ptr(d, t, data); + return 0; + case BTF_KIND_UNKN: + jsonw_printf(d->jw, "(unknown)"); + return 0; + case BTF_KIND_FWD: + /* map key or value can't be forward */ + jsonw_printf(d->jw, "(fwd-kind-invalid)"); + return -EINVAL; + case BTF_KIND_TYPEDEF: + case BTF_KIND_VOLATILE: + 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; + } +} + +int btf_dumper_type(const struct btf_dumper *d, __u32 type_id, + const void *data) +{ + return btf_dumper_do_type(d, type_id, 0, data); +} + +#define BTF_PRINT_ARG(...) \ + do { \ + pos += snprintf(func_sig + pos, size - pos, \ + __VA_ARGS__); \ + if (pos >= size) \ + return -1; \ + } while (0) +#define BTF_PRINT_TYPE(type) \ + do { \ + pos = __btf_dumper_type_only(btf, type, func_sig, \ + pos, size); \ + if (pos == -1) \ + return -1; \ + } while (0) + +static int __btf_dumper_type_only(const struct btf *btf, __u32 type_id, + char *func_sig, int pos, int size) +{ + const struct btf_type *proto_type; + const struct btf_array *array; + const struct btf_var *var; + const struct btf_type *t; + + if (!type_id) { + BTF_PRINT_ARG("void "); + return pos; + } + + t = btf__type_by_id(btf, type_id); + + switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_INT: + case BTF_KIND_TYPEDEF: + case BTF_KIND_FLOAT: + BTF_PRINT_ARG("%s ", btf__name_by_offset(btf, t->name_off)); + break; + case BTF_KIND_STRUCT: + BTF_PRINT_ARG("struct %s ", + btf__name_by_offset(btf, t->name_off)); + break; + case BTF_KIND_UNION: + BTF_PRINT_ARG("union %s ", + btf__name_by_offset(btf, t->name_off)); + break; + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + BTF_PRINT_ARG("enum %s ", + btf__name_by_offset(btf, t->name_off)); + break; + case BTF_KIND_ARRAY: + array = (struct btf_array *)(t + 1); + BTF_PRINT_TYPE(array->type); + BTF_PRINT_ARG("[%d]", array->nelems); + break; + case BTF_KIND_PTR: + BTF_PRINT_TYPE(t->type); + BTF_PRINT_ARG("* "); + break; + case BTF_KIND_FWD: + BTF_PRINT_ARG("%s %s ", + BTF_INFO_KFLAG(t->info) ? "union" : "struct", + btf__name_by_offset(btf, t->name_off)); + break; + case BTF_KIND_VOLATILE: + BTF_PRINT_ARG("volatile "); + BTF_PRINT_TYPE(t->type); + break; + case BTF_KIND_CONST: + BTF_PRINT_ARG("const "); + BTF_PRINT_TYPE(t->type); + break; + case BTF_KIND_RESTRICT: + BTF_PRINT_ARG("restrict "); + BTF_PRINT_TYPE(t->type); + break; + case BTF_KIND_FUNC_PROTO: + pos = btf_dump_func(btf, func_sig, t, NULL, pos, size); + if (pos == -1) + return -1; + break; + case BTF_KIND_FUNC: + proto_type = btf__type_by_id(btf, t->type); + pos = btf_dump_func(btf, func_sig, proto_type, t, pos, size); + 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; + } + + return pos; +} + +static int btf_dump_func(const struct btf *btf, char *func_sig, + const struct btf_type *func_proto, + const struct btf_type *func, int pos, int size) +{ + int i, vlen; + + BTF_PRINT_TYPE(func_proto->type); + if (func) + BTF_PRINT_ARG("%s(", btf__name_by_offset(btf, func->name_off)); + else + BTF_PRINT_ARG("("); + vlen = BTF_INFO_VLEN(func_proto->info); + for (i = 0; i < vlen; i++) { + struct btf_param *arg = &((struct btf_param *)(func_proto + 1))[i]; + + if (i) + BTF_PRINT_ARG(", "); + if (arg->type) { + BTF_PRINT_TYPE(arg->type); + if (arg->name_off) + BTF_PRINT_ARG("%s", + btf__name_by_offset(btf, arg->name_off)); + else if (pos && func_sig[pos - 1] == ' ') + /* Remove unnecessary space for + * FUNC_PROTO that does not have + * arg->name_off + */ + func_sig[--pos] = '\0'; + } else { + BTF_PRINT_ARG("..."); + } + } + BTF_PRINT_ARG(")"); + + return pos; +} + +void btf_dumper_type_only(const struct btf *btf, __u32 type_id, char *func_sig, + int size) +{ + int err; + + func_sig[0] = '\0'; + if (!btf) + return; + + err = __btf_dumper_type_only(btf, type_id, func_sig, 0, size); + if (err < 0) + func_sig[0] = '\0'; +} + +static const char *ltrim(const char *s) +{ + while (isspace(*s)) + s++; + + return s; +} + +void btf_dump_linfo_plain(const struct btf *btf, + const struct bpf_line_info *linfo, + const char *prefix, bool linum) +{ + const char *line = btf__name_by_offset(btf, linfo->line_off); + + if (!line) + return; + line = ltrim(line); + + if (!prefix) + prefix = ""; + + if (linum) { + const char *file = btf__name_by_offset(btf, linfo->file_name_off); + + /* More forgiving on file because linum option is + * expected to provide more info than the already + * available src line. + */ + if (!file) + file = ""; + + printf("%s%s [file:%s line_num:%u line_col:%u]\n", + prefix, line, file, + BPF_LINE_INFO_LINE_NUM(linfo->line_col), + BPF_LINE_INFO_LINE_COL(linfo->line_col)); + } else { + printf("%s%s\n", prefix, line); + } +} + +void btf_dump_linfo_json(const struct btf *btf, + const struct bpf_line_info *linfo, bool linum) +{ + const char *line = btf__name_by_offset(btf, linfo->line_off); + + if (line) + jsonw_string_field(json_wtr, "src", ltrim(line)); + + if (linum) { + const char *file = btf__name_by_offset(btf, linfo->file_name_off); + + if (file) + jsonw_string_field(json_wtr, "file", file); + + if (BPF_LINE_INFO_LINE_NUM(linfo->line_col)) + jsonw_int_field(json_wtr, "line_num", + BPF_LINE_INFO_LINE_NUM(linfo->line_col)); + + if (BPF_LINE_INFO_LINE_COL(linfo->line_col)) + jsonw_int_field(json_wtr, "line_col", + BPF_LINE_INFO_LINE_COL(linfo->line_col)); + } +} diff --git a/tools/bpf/bpftool/cfg.c b/tools/bpf/bpftool/cfg.c new file mode 100644 index 000000000..1951219a9 --- /dev/null +++ b/tools/bpf/bpftool/cfg.c @@ -0,0 +1,485 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2018 Netronome Systems, Inc. */ + +#include <linux/list.h> +#include <stdlib.h> +#include <string.h> + +#include "cfg.h" +#include "main.h" +#include "xlated_dumper.h" + +struct cfg { + struct list_head funcs; + int func_num; +}; + +struct func_node { + struct list_head l; + struct list_head bbs; + struct bpf_insn *start; + struct bpf_insn *end; + int idx; + int bb_num; +}; + +struct bb_node { + struct list_head l; + struct list_head e_prevs; + struct list_head e_succs; + struct bpf_insn *head; + struct bpf_insn *tail; + int idx; +}; + +#define EDGE_FLAG_EMPTY 0x0 +#define EDGE_FLAG_FALLTHROUGH 0x1 +#define EDGE_FLAG_JUMP 0x2 +struct edge_node { + struct list_head l; + struct bb_node *src; + struct bb_node *dst; + int flags; +}; + +#define ENTRY_BLOCK_INDEX 0 +#define EXIT_BLOCK_INDEX 1 +#define NUM_FIXED_BLOCKS 2 +#define func_prev(func) list_prev_entry(func, l) +#define func_next(func) list_next_entry(func, l) +#define bb_prev(bb) list_prev_entry(bb, l) +#define bb_next(bb) list_next_entry(bb, l) +#define entry_bb(func) func_first_bb(func) +#define exit_bb(func) func_last_bb(func) +#define cfg_first_func(cfg) \ + list_first_entry(&cfg->funcs, struct func_node, l) +#define cfg_last_func(cfg) \ + list_last_entry(&cfg->funcs, struct func_node, l) +#define func_first_bb(func) \ + list_first_entry(&func->bbs, struct bb_node, l) +#define func_last_bb(func) \ + list_last_entry(&func->bbs, struct bb_node, l) + +static struct func_node *cfg_append_func(struct cfg *cfg, struct bpf_insn *insn) +{ + struct func_node *new_func, *func; + + list_for_each_entry(func, &cfg->funcs, l) { + if (func->start == insn) + return func; + else if (func->start > insn) + break; + } + + func = func_prev(func); + new_func = calloc(1, sizeof(*new_func)); + if (!new_func) { + p_err("OOM when allocating FUNC node"); + return NULL; + } + new_func->start = insn; + new_func->idx = cfg->func_num; + list_add(&new_func->l, &func->l); + cfg->func_num++; + + return new_func; +} + +static struct bb_node *func_append_bb(struct func_node *func, + struct bpf_insn *insn) +{ + struct bb_node *new_bb, *bb; + + list_for_each_entry(bb, &func->bbs, l) { + if (bb->head == insn) + return bb; + else if (bb->head > insn) + break; + } + + bb = bb_prev(bb); + new_bb = calloc(1, sizeof(*new_bb)); + if (!new_bb) { + p_err("OOM when allocating BB node"); + return NULL; + } + new_bb->head = insn; + INIT_LIST_HEAD(&new_bb->e_prevs); + INIT_LIST_HEAD(&new_bb->e_succs); + list_add(&new_bb->l, &bb->l); + + return new_bb; +} + +static struct bb_node *func_insert_dummy_bb(struct list_head *after) +{ + struct bb_node *bb; + + bb = calloc(1, sizeof(*bb)); + if (!bb) { + p_err("OOM when allocating BB node"); + return NULL; + } + + INIT_LIST_HEAD(&bb->e_prevs); + INIT_LIST_HEAD(&bb->e_succs); + list_add(&bb->l, after); + + return bb; +} + +static bool cfg_partition_funcs(struct cfg *cfg, struct bpf_insn *cur, + struct bpf_insn *end) +{ + struct func_node *func, *last_func; + + func = cfg_append_func(cfg, cur); + if (!func) + return true; + + for (; cur < end; cur++) { + if (cur->code != (BPF_JMP | BPF_CALL)) + continue; + if (cur->src_reg != BPF_PSEUDO_CALL) + continue; + func = cfg_append_func(cfg, cur + cur->off + 1); + if (!func) + return true; + } + + last_func = cfg_last_func(cfg); + last_func->end = end - 1; + func = cfg_first_func(cfg); + list_for_each_entry_from(func, &last_func->l, l) { + func->end = func_next(func)->start - 1; + } + + return false; +} + +static bool is_jmp_insn(__u8 code) +{ + return BPF_CLASS(code) == BPF_JMP || BPF_CLASS(code) == BPF_JMP32; +} + +static bool func_partition_bb_head(struct func_node *func) +{ + struct bpf_insn *cur, *end; + struct bb_node *bb; + + cur = func->start; + end = func->end; + INIT_LIST_HEAD(&func->bbs); + bb = func_append_bb(func, cur); + if (!bb) + return true; + + for (; cur <= end; cur++) { + if (is_jmp_insn(cur->code)) { + __u8 opcode = BPF_OP(cur->code); + + if (opcode == BPF_EXIT || opcode == BPF_CALL) + continue; + + bb = func_append_bb(func, cur + cur->off + 1); + if (!bb) + return true; + + if (opcode != BPF_JA) { + bb = func_append_bb(func, cur + 1); + if (!bb) + return true; + } + } + } + + return false; +} + +static void func_partition_bb_tail(struct func_node *func) +{ + unsigned int bb_idx = NUM_FIXED_BLOCKS; + struct bb_node *bb, *last; + + last = func_last_bb(func); + last->tail = func->end; + bb = func_first_bb(func); + list_for_each_entry_from(bb, &last->l, l) { + bb->tail = bb_next(bb)->head - 1; + bb->idx = bb_idx++; + } + + last->idx = bb_idx++; + func->bb_num = bb_idx; +} + +static bool func_add_special_bb(struct func_node *func) +{ + struct bb_node *bb; + + bb = func_insert_dummy_bb(&func->bbs); + if (!bb) + return true; + bb->idx = ENTRY_BLOCK_INDEX; + + bb = func_insert_dummy_bb(&func_last_bb(func)->l); + if (!bb) + return true; + bb->idx = EXIT_BLOCK_INDEX; + + return false; +} + +static bool func_partition_bb(struct func_node *func) +{ + if (func_partition_bb_head(func)) + return true; + + func_partition_bb_tail(func); + + return false; +} + +static struct bb_node *func_search_bb_with_head(struct func_node *func, + struct bpf_insn *insn) +{ + struct bb_node *bb; + + list_for_each_entry(bb, &func->bbs, l) { + if (bb->head == insn) + return bb; + } + + return NULL; +} + +static struct edge_node *new_edge(struct bb_node *src, struct bb_node *dst, + int flags) +{ + struct edge_node *e; + + e = calloc(1, sizeof(*e)); + if (!e) { + p_err("OOM when allocating edge node"); + return NULL; + } + + if (src) + e->src = src; + if (dst) + e->dst = dst; + + e->flags |= flags; + + return e; +} + +static bool func_add_bb_edges(struct func_node *func) +{ + struct bpf_insn *insn; + struct edge_node *e; + struct bb_node *bb; + + bb = entry_bb(func); + e = new_edge(bb, bb_next(bb), EDGE_FLAG_FALLTHROUGH); + if (!e) + return true; + list_add_tail(&e->l, &bb->e_succs); + + bb = exit_bb(func); + e = new_edge(bb_prev(bb), bb, EDGE_FLAG_FALLTHROUGH); + if (!e) + return true; + list_add_tail(&e->l, &bb->e_prevs); + + bb = entry_bb(func); + bb = bb_next(bb); + list_for_each_entry_from(bb, &exit_bb(func)->l, l) { + e = new_edge(bb, NULL, EDGE_FLAG_EMPTY); + if (!e) + return true; + e->src = bb; + + insn = bb->tail; + if (!is_jmp_insn(insn->code) || + BPF_OP(insn->code) == BPF_EXIT) { + e->dst = bb_next(bb); + e->flags |= EDGE_FLAG_FALLTHROUGH; + list_add_tail(&e->l, &bb->e_succs); + continue; + } else if (BPF_OP(insn->code) == BPF_JA) { + e->dst = func_search_bb_with_head(func, + insn + insn->off + 1); + e->flags |= EDGE_FLAG_JUMP; + list_add_tail(&e->l, &bb->e_succs); + continue; + } + + e->dst = bb_next(bb); + e->flags |= EDGE_FLAG_FALLTHROUGH; + list_add_tail(&e->l, &bb->e_succs); + + e = new_edge(bb, NULL, EDGE_FLAG_JUMP); + if (!e) + return true; + e->src = bb; + e->dst = func_search_bb_with_head(func, insn + insn->off + 1); + list_add_tail(&e->l, &bb->e_succs); + } + + return false; +} + +static bool cfg_build(struct cfg *cfg, struct bpf_insn *insn, unsigned int len) +{ + int cnt = len / sizeof(*insn); + struct func_node *func; + + INIT_LIST_HEAD(&cfg->funcs); + + if (cfg_partition_funcs(cfg, insn, insn + cnt)) + return true; + + list_for_each_entry(func, &cfg->funcs, l) { + if (func_partition_bb(func) || func_add_special_bb(func)) + return true; + + if (func_add_bb_edges(func)) + return true; + } + + return false; +} + +static void cfg_destroy(struct cfg *cfg) +{ + struct func_node *func, *func2; + + list_for_each_entry_safe(func, func2, &cfg->funcs, l) { + struct bb_node *bb, *bb2; + + list_for_each_entry_safe(bb, bb2, &func->bbs, l) { + struct edge_node *e, *e2; + + list_for_each_entry_safe(e, e2, &bb->e_prevs, l) { + list_del(&e->l); + free(e); + } + + list_for_each_entry_safe(e, e2, &bb->e_succs, l) { + list_del(&e->l); + free(e); + } + + list_del(&bb->l); + free(bb); + } + + list_del(&func->l); + free(func); + } +} + +static void draw_bb_node(struct func_node *func, struct bb_node *bb) +{ + const char *shape; + + if (bb->idx == ENTRY_BLOCK_INDEX || bb->idx == EXIT_BLOCK_INDEX) + shape = "Mdiamond"; + else + shape = "record"; + + printf("\tfn_%d_bb_%d [shape=%s,style=filled,label=\"", + func->idx, bb->idx, shape); + + if (bb->idx == ENTRY_BLOCK_INDEX) { + printf("ENTRY"); + } else if (bb->idx == EXIT_BLOCK_INDEX) { + printf("EXIT"); + } else { + unsigned int start_idx; + struct dump_data dd = {}; + + printf("{"); + kernel_syms_load(&dd); + start_idx = bb->head - func->start; + dump_xlated_for_graph(&dd, bb->head, bb->tail, start_idx); + kernel_syms_destroy(&dd); + printf("}"); + } + + printf("\"];\n\n"); +} + +static void draw_bb_succ_edges(struct func_node *func, struct bb_node *bb) +{ + const char *style = "\"solid,bold\""; + const char *color = "black"; + int func_idx = func->idx; + struct edge_node *e; + int weight = 10; + + if (list_empty(&bb->e_succs)) + return; + + list_for_each_entry(e, &bb->e_succs, l) { + printf("\tfn_%d_bb_%d:s -> fn_%d_bb_%d:n [style=%s, color=%s, weight=%d, constraint=true", + func_idx, e->src->idx, func_idx, e->dst->idx, + style, color, weight); + printf("];\n"); + } +} + +static void func_output_bb_def(struct func_node *func) +{ + struct bb_node *bb; + + list_for_each_entry(bb, &func->bbs, l) { + draw_bb_node(func, bb); + } +} + +static void func_output_edges(struct func_node *func) +{ + int func_idx = func->idx; + struct bb_node *bb; + + list_for_each_entry(bb, &func->bbs, l) { + draw_bb_succ_edges(func, bb); + } + + /* Add an invisible edge from ENTRY to EXIT, this is to + * improve the graph layout. + */ + printf("\tfn_%d_bb_%d:s -> fn_%d_bb_%d:n [style=\"invis\", constraint=true];\n", + func_idx, ENTRY_BLOCK_INDEX, func_idx, EXIT_BLOCK_INDEX); +} + +static void cfg_dump(struct cfg *cfg) +{ + struct func_node *func; + + printf("digraph \"DOT graph for eBPF program\" {\n"); + list_for_each_entry(func, &cfg->funcs, l) { + printf("subgraph \"cluster_%d\" {\n\tstyle=\"dashed\";\n\tcolor=\"black\";\n\tlabel=\"func_%d ()\";\n", + func->idx, func->idx); + func_output_bb_def(func); + func_output_edges(func); + printf("}\n"); + } + printf("}\n"); +} + +void dump_xlated_cfg(void *buf, unsigned int len) +{ + struct bpf_insn *insn = buf; + struct cfg cfg; + + memset(&cfg, 0, sizeof(cfg)); + if (cfg_build(&cfg, insn, len)) + return; + + cfg_dump(&cfg); + + cfg_destroy(&cfg); +} diff --git a/tools/bpf/bpftool/cfg.h b/tools/bpf/bpftool/cfg.h new file mode 100644 index 000000000..e144257ea --- /dev/null +++ b/tools/bpf/bpftool/cfg.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* Copyright (C) 2018 Netronome Systems, Inc. */ + +#ifndef __BPF_TOOL_CFG_H +#define __BPF_TOOL_CFG_H + +void dump_xlated_cfg(void *buf, unsigned int len); + +#endif /* __BPF_TOOL_CFG_H */ diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c new file mode 100644 index 000000000..b46a998d8 --- /dev/null +++ b/tools/bpf/bpftool/cgroup.c @@ -0,0 +1,655 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +// Copyright (C) 2017 Facebook +// Author: Roman Gushchin <guro@fb.com> + +#define _XOPEN_SOURCE 500 +#include <errno.h> +#include <fcntl.h> +#include <ftw.h> +#include <mntent.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <unistd.h> + +#include <bpf/bpf.h> +#include <bpf/btf.h> + +#include "main.h" + +#define HELP_SPEC_ATTACH_FLAGS \ + "ATTACH_FLAGS := { multi | override }" + +#define HELP_SPEC_ATTACH_TYPES \ + " ATTACH_TYPE := { cgroup_inet_ingress | cgroup_inet_egress |\n" \ + " cgroup_inet_sock_create | cgroup_sock_ops |\n" \ + " cgroup_device | cgroup_inet4_bind |\n" \ + " cgroup_inet6_bind | cgroup_inet4_post_bind |\n" \ + " cgroup_inet6_post_bind | cgroup_inet4_connect |\n" \ + " cgroup_inet6_connect | cgroup_inet4_getpeername |\n" \ + " cgroup_inet6_getpeername | cgroup_inet4_getsockname |\n" \ + " cgroup_inet6_getsockname | cgroup_udp4_sendmsg |\n" \ + " cgroup_udp6_sendmsg | cgroup_udp4_recvmsg |\n" \ + " cgroup_udp6_recvmsg | cgroup_sysctl |\n" \ + " cgroup_getsockopt | cgroup_setsockopt |\n" \ + " cgroup_inet_sock_release }" + +static unsigned int query_flags; +static struct btf *btf_vmlinux; +static __u32 btf_vmlinux_id; + +static enum bpf_attach_type parse_attach_type(const char *str) +{ + const char *attach_type_str; + enum bpf_attach_type type; + + for (type = 0; ; type++) { + attach_type_str = libbpf_bpf_attach_type_str(type); + if (!attach_type_str) + break; + if (!strcmp(str, attach_type_str)) + return type; + } + + /* Also check traditionally used attach type strings. For these we keep + * allowing prefixed usage. + */ + for (type = 0; ; type++) { + attach_type_str = bpf_attach_type_input_str(type); + if (!attach_type_str) + break; + if (is_prefix(str, attach_type_str)) + return type; + } + + return __MAX_BPF_ATTACH_TYPE; +} + +static void guess_vmlinux_btf_id(__u32 attach_btf_obj_id) +{ + struct bpf_btf_info btf_info = {}; + __u32 btf_len = sizeof(btf_info); + char name[16] = {}; + int err; + int fd; + + btf_info.name = ptr_to_u64(name); + btf_info.name_len = sizeof(name); + + fd = bpf_btf_get_fd_by_id(attach_btf_obj_id); + if (fd < 0) + return; + + err = bpf_obj_get_info_by_fd(fd, &btf_info, &btf_len); + if (err) + goto out; + + if (btf_info.kernel_btf && strncmp(name, "vmlinux", sizeof(name)) == 0) + btf_vmlinux_id = btf_info.id; + +out: + close(fd); +} + +static int show_bpf_prog(int id, enum bpf_attach_type attach_type, + const char *attach_flags_str, + int level) +{ + char prog_name[MAX_PROG_FULL_NAME]; + const char *attach_btf_name = NULL; + struct bpf_prog_info info = {}; + const char *attach_type_str; + __u32 info_len = sizeof(info); + int prog_fd; + + prog_fd = bpf_prog_get_fd_by_id(id); + if (prog_fd < 0) + return -1; + + if (bpf_obj_get_info_by_fd(prog_fd, &info, &info_len)) { + close(prog_fd); + return -1; + } + + attach_type_str = libbpf_bpf_attach_type_str(attach_type); + + if (btf_vmlinux) { + if (!btf_vmlinux_id) + guess_vmlinux_btf_id(info.attach_btf_obj_id); + + if (btf_vmlinux_id == info.attach_btf_obj_id && + info.attach_btf_id < btf__type_cnt(btf_vmlinux)) { + const struct btf_type *t = + btf__type_by_id(btf_vmlinux, info.attach_btf_id); + attach_btf_name = + btf__name_by_offset(btf_vmlinux, t->name_off); + } + } + + get_prog_full_name(&info, prog_fd, prog_name, sizeof(prog_name)); + if (json_output) { + jsonw_start_object(json_wtr); + jsonw_uint_field(json_wtr, "id", info.id); + if (attach_type_str) + jsonw_string_field(json_wtr, "attach_type", attach_type_str); + else + jsonw_uint_field(json_wtr, "attach_type", attach_type); + if (!(query_flags & BPF_F_QUERY_EFFECTIVE)) + jsonw_string_field(json_wtr, "attach_flags", attach_flags_str); + jsonw_string_field(json_wtr, "name", prog_name); + if (attach_btf_name) + jsonw_string_field(json_wtr, "attach_btf_name", attach_btf_name); + jsonw_uint_field(json_wtr, "attach_btf_obj_id", info.attach_btf_obj_id); + jsonw_uint_field(json_wtr, "attach_btf_id", info.attach_btf_id); + jsonw_end_object(json_wtr); + } else { + printf("%s%-8u ", level ? " " : "", info.id); + if (attach_type_str) + printf("%-15s", attach_type_str); + else + printf("type %-10u", attach_type); + if (query_flags & BPF_F_QUERY_EFFECTIVE) + printf(" %-15s", prog_name); + else + printf(" %-15s %-15s", attach_flags_str, prog_name); + if (attach_btf_name) + printf(" %-15s", attach_btf_name); + else if (info.attach_btf_id) + printf(" attach_btf_obj_id=%d attach_btf_id=%d", + info.attach_btf_obj_id, info.attach_btf_id); + printf("\n"); + } + + close(prog_fd); + return 0; +} + +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, query_flags, NULL, + NULL, &prog_cnt); + if (ret) + return -1; + + return prog_cnt; +} + +static int cgroup_has_attached_progs(int cgroup_fd) +{ + enum bpf_attach_type type; + bool no_prog = true; + + for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) { + int count = count_attached_bpf_progs(cgroup_fd, type); + + if (count < 0 && errno != EINVAL) + return -1; + + if (count > 0) { + no_prog = false; + break; + } + } + + return no_prog ? 0 : 1; +} + +static int show_effective_bpf_progs(int cgroup_fd, enum bpf_attach_type type, + int level) +{ + LIBBPF_OPTS(bpf_prog_query_opts, p); + __u32 prog_ids[1024] = {0}; + __u32 iter; + int ret; + + p.query_flags = query_flags; + p.prog_cnt = ARRAY_SIZE(prog_ids); + p.prog_ids = prog_ids; + + ret = bpf_prog_query_opts(cgroup_fd, type, &p); + if (ret) + return ret; + + if (p.prog_cnt == 0) + return 0; + + for (iter = 0; iter < p.prog_cnt; iter++) + show_bpf_prog(prog_ids[iter], type, NULL, level); + + return 0; +} + +static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type, + int level) +{ + LIBBPF_OPTS(bpf_prog_query_opts, p); + __u32 prog_attach_flags[1024] = {0}; + const char *attach_flags_str; + __u32 prog_ids[1024] = {0}; + char buf[32]; + __u32 iter; + int ret; + + p.query_flags = query_flags; + p.prog_cnt = ARRAY_SIZE(prog_ids); + p.prog_ids = prog_ids; + p.prog_attach_flags = prog_attach_flags; + + ret = bpf_prog_query_opts(cgroup_fd, type, &p); + if (ret) + return ret; + + if (p.prog_cnt == 0) + return 0; + + for (iter = 0; iter < p.prog_cnt; iter++) { + __u32 attach_flags; + + attach_flags = prog_attach_flags[iter] ?: p.attach_flags; + + switch (attach_flags) { + case BPF_F_ALLOW_MULTI: + attach_flags_str = "multi"; + break; + case BPF_F_ALLOW_OVERRIDE: + attach_flags_str = "override"; + break; + case 0: + attach_flags_str = ""; + break; + default: + snprintf(buf, sizeof(buf), "unknown(%x)", attach_flags); + attach_flags_str = buf; + } + + show_bpf_prog(prog_ids[iter], type, + attach_flags_str, level); + } + + return 0; +} + +static int show_bpf_progs(int cgroup_fd, enum bpf_attach_type type, + int level) +{ + return query_flags & BPF_F_QUERY_EFFECTIVE ? + show_effective_bpf_progs(cgroup_fd, type, level) : + show_attached_bpf_progs(cgroup_fd, type, level); +} + +static int do_show(int argc, char **argv) +{ + enum bpf_attach_type type; + int has_attached_progs; + const char *path; + int cgroup_fd; + int ret = -1; + + 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(path, O_RDONLY); + if (cgroup_fd < 0) { + p_err("can't open cgroup %s", path); + goto exit; + } + + has_attached_progs = cgroup_has_attached_progs(cgroup_fd); + if (has_attached_progs < 0) { + p_err("can't query bpf programs attached to %s: %s", + path, strerror(errno)); + goto exit_cgroup; + } else if (!has_attached_progs) { + ret = 0; + goto exit_cgroup; + } + + if (json_output) + jsonw_start_array(json_wtr); + else if (query_flags & BPF_F_QUERY_EFFECTIVE) + printf("%-8s %-15s %-15s\n", "ID", "AttachType", "Name"); + else + printf("%-8s %-15s %-15s %-15s\n", "ID", "AttachType", + "AttachFlags", "Name"); + + btf_vmlinux = libbpf_find_kernel_btf(); + for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) { + /* + * Not all attach types may be supported, so it's expected, + * that some requests will fail. + * If we were able to get the show for at least one + * attach type, let's return 0. + */ + if (show_bpf_progs(cgroup_fd, type, 0) == 0) + ret = 0; + } + + if (json_output) + jsonw_end_array(json_wtr); + +exit_cgroup: + close(cgroup_fd); +exit: + return ret; +} + +/* + * To distinguish nftw() errors and do_show_tree_fn() errors + * and avoid duplicating error messages, let's return -2 + * from do_show_tree_fn() in case of error. + */ +#define NFTW_ERR -1 +#define SHOW_TREE_FN_ERR -2 +static int do_show_tree_fn(const char *fpath, const struct stat *sb, + int typeflag, struct FTW *ftw) +{ + enum bpf_attach_type type; + int has_attached_progs; + int cgroup_fd; + + if (typeflag != FTW_D) + return 0; + + cgroup_fd = open(fpath, O_RDONLY); + if (cgroup_fd < 0) { + p_err("can't open cgroup %s: %s", fpath, strerror(errno)); + return SHOW_TREE_FN_ERR; + } + + has_attached_progs = cgroup_has_attached_progs(cgroup_fd); + if (has_attached_progs < 0) { + p_err("can't query bpf programs attached to %s: %s", + fpath, strerror(errno)); + close(cgroup_fd); + return SHOW_TREE_FN_ERR; + } else if (!has_attached_progs) { + close(cgroup_fd); + return 0; + } + + if (json_output) { + jsonw_start_object(json_wtr); + jsonw_string_field(json_wtr, "cgroup", fpath); + jsonw_name(json_wtr, "programs"); + jsonw_start_array(json_wtr); + } else { + printf("%s\n", fpath); + } + + btf_vmlinux = libbpf_find_kernel_btf(); + for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) + show_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); + } + + close(cgroup_fd); + + return 0; +} + +static char *find_cgroup_root(void) +{ + struct mntent *mnt; + FILE *f; + + f = fopen("/proc/mounts", "r"); + if (f == NULL) + return NULL; + + while ((mnt = getmntent(f))) { + if (strcmp(mnt->mnt_type, "cgroup2") == 0) { + fclose(f); + return strdup(mnt->mnt_dir); + } + } + + fclose(f); + return NULL; +} + +static int do_show_tree(int argc, char **argv) +{ + char *cgroup_root, *cgroup_alloced = NULL; + int ret; + + query_flags = 0; + + if (!argc) { + cgroup_alloced = find_cgroup_root(); + if (!cgroup_alloced) { + p_err("cgroup v2 isn't mounted"); + 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 if (query_flags & BPF_F_QUERY_EFFECTIVE) + printf("%s\n" + "%-8s %-15s %-15s\n", + "CgroupPath", + "ID", "AttachType", "Name"); + else + printf("%s\n" + "%-8s %-15s %-15s %-15s\n", + "CgroupPath", + "ID", "AttachType", "AttachFlags", "Name"); + + switch (nftw(cgroup_root, do_show_tree_fn, 1024, FTW_MOUNT)) { + case NFTW_ERR: + p_err("can't iterate over %s: %s", cgroup_root, + strerror(errno)); + ret = -1; + break; + case SHOW_TREE_FN_ERR: + ret = -1; + break; + default: + ret = 0; + } + + if (json_output) + jsonw_end_array(json_wtr); + + free(cgroup_alloced); + + return ret; +} + +static int do_attach(int argc, char **argv) +{ + enum bpf_attach_type attach_type; + int cgroup_fd, prog_fd; + int attach_flags = 0; + int ret = -1; + int i; + + if (argc < 4) { + p_err("too few parameters for cgroup attach"); + goto exit; + } + + cgroup_fd = open(argv[0], O_RDONLY); + if (cgroup_fd < 0) { + p_err("can't open cgroup %s", argv[0]); + goto exit; + } + + attach_type = parse_attach_type(argv[1]); + if (attach_type == __MAX_BPF_ATTACH_TYPE) { + p_err("invalid attach type"); + goto exit_cgroup; + } + + argc -= 2; + argv = &argv[2]; + prog_fd = prog_parse_fd(&argc, &argv); + if (prog_fd < 0) + goto exit_cgroup; + + for (i = 0; i < argc; i++) { + if (is_prefix(argv[i], "multi")) { + attach_flags |= BPF_F_ALLOW_MULTI; + } else if (is_prefix(argv[i], "override")) { + attach_flags |= BPF_F_ALLOW_OVERRIDE; + } else { + p_err("unknown option: %s", argv[i]); + goto exit_cgroup; + } + } + + if (bpf_prog_attach(prog_fd, cgroup_fd, attach_type, attach_flags)) { + p_err("failed to attach program"); + goto exit_prog; + } + + if (json_output) + jsonw_null(json_wtr); + + ret = 0; + +exit_prog: + close(prog_fd); +exit_cgroup: + close(cgroup_fd); +exit: + return ret; +} + +static int do_detach(int argc, char **argv) +{ + enum bpf_attach_type attach_type; + int prog_fd, cgroup_fd; + int ret = -1; + + if (argc < 4) { + p_err("too few parameters for cgroup detach"); + goto exit; + } + + cgroup_fd = open(argv[0], O_RDONLY); + if (cgroup_fd < 0) { + p_err("can't open cgroup %s", argv[0]); + goto exit; + } + + attach_type = parse_attach_type(argv[1]); + if (attach_type == __MAX_BPF_ATTACH_TYPE) { + p_err("invalid attach type"); + goto exit_cgroup; + } + + argc -= 2; + argv = &argv[2]; + prog_fd = prog_parse_fd(&argc, &argv); + if (prog_fd < 0) + goto exit_cgroup; + + if (bpf_prog_detach2(prog_fd, cgroup_fd, attach_type)) { + p_err("failed to detach program"); + goto exit_prog; + } + + if (json_output) + jsonw_null(json_wtr); + + ret = 0; + +exit_prog: + close(prog_fd); +exit_cgroup: + close(cgroup_fd); +exit: + return ret; +} + +static int do_help(int argc, char **argv) +{ + if (json_output) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %1$s %2$s { show | list } CGROUP [**effective**]\n" + " %1$s %2$s tree [CGROUP_ROOT] [**effective**]\n" + " %1$s %2$s attach CGROUP ATTACH_TYPE PROG [ATTACH_FLAGS]\n" + " %1$s %2$s detach CGROUP ATTACH_TYPE PROG\n" + " %1$s %2$s help\n" + "\n" + HELP_SPEC_ATTACH_TYPES "\n" + " " HELP_SPEC_ATTACH_FLAGS "\n" + " " HELP_SPEC_PROGRAM "\n" + " " HELP_SPEC_OPTIONS " |\n" + " {-f|--bpffs} }\n" + "", + bin_name, argv[-2]); + + return 0; +} + +static const struct cmd cmds[] = { + { "show", do_show }, + { "list", do_show }, + { "tree", do_show_tree }, + { "attach", do_attach }, + { "detach", do_detach }, + { "help", do_help }, + { 0 } +}; + +int do_cgroup(int argc, char **argv) +{ + return cmd_select(cmds, argc, argv, do_help); +} diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c new file mode 100644 index 000000000..e7a11cff7 --- /dev/null +++ b/tools/bpf/bpftool/common.c @@ -0,0 +1,1088 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2017-2018 Netronome Systems, Inc. */ + +#define _GNU_SOURCE +#include <ctype.h> +#include <errno.h> +#include <fcntl.h> +#include <ftw.h> +#include <libgen.h> +#include <mntent.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <net/if.h> +#include <sys/mount.h> +#include <sys/resource.h> +#include <sys/stat.h> +#include <sys/vfs.h> + +#include <linux/filter.h> +#include <linux/limits.h> +#include <linux/magic.h> +#include <linux/unistd.h> + +#include <bpf/bpf.h> +#include <bpf/hashmap.h> +#include <bpf/libbpf.h> /* libbpf_num_possible_cpus */ +#include <bpf/btf.h> + +#include "main.h" + +#ifndef BPF_FS_MAGIC +#define BPF_FS_MAGIC 0xcafe4a11 +#endif + +void p_err(const char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + if (json_output) { + jsonw_start_object(json_wtr); + jsonw_name(json_wtr, "error"); + jsonw_vprintf_enquote(json_wtr, fmt, ap); + jsonw_end_object(json_wtr); + } else { + fprintf(stderr, "Error: "); + vfprintf(stderr, fmt, ap); + fprintf(stderr, "\n"); + } + va_end(ap); +} + +void p_info(const char *fmt, ...) +{ + va_list ap; + + if (json_output) + return; + + va_start(ap, fmt); + vfprintf(stderr, fmt, ap); + fprintf(stderr, "\n"); + va_end(ap); +} + +static bool is_bpffs(char *path) +{ + struct statfs st_fs; + + if (statfs(path, &st_fs) < 0) + return false; + + return (unsigned long)st_fs.f_type == BPF_FS_MAGIC; +} + +/* Probe whether kernel switched from memlock-based (RLIMIT_MEMLOCK) to + * memcg-based memory accounting for BPF maps and programs. This was done in + * commit 97306be45fbe ("Merge branch 'switch to memcg-based memory + * accounting'"), in Linux 5.11. + * + * Libbpf also offers to probe for memcg-based accounting vs rlimit, but does + * so by checking for the availability of a given BPF helper and this has + * failed on some kernels with backports in the past, see commit 6b4384ff1088 + * ("Revert "bpftool: Use libbpf 1.0 API mode instead of RLIMIT_MEMLOCK""). + * Instead, we can probe by lowering the process-based rlimit to 0, trying to + * load a BPF object, and resetting the rlimit. If the load succeeds then + * memcg-based accounting is supported. + * + * This would be too dangerous to do in the library, because multithreaded + * applications might attempt to load items while the rlimit is at 0. Given + * that bpftool is single-threaded, this is fine to do here. + */ +static bool known_to_need_rlimit(void) +{ + struct rlimit rlim_init, rlim_cur_zero = {}; + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + size_t insn_cnt = ARRAY_SIZE(insns); + union bpf_attr attr; + int prog_fd, err; + + memset(&attr, 0, sizeof(attr)); + attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; + attr.insns = ptr_to_u64(insns); + attr.insn_cnt = insn_cnt; + attr.license = ptr_to_u64("GPL"); + + if (getrlimit(RLIMIT_MEMLOCK, &rlim_init)) + return false; + + /* Drop the soft limit to zero. We maintain the hard limit to its + * current value, because lowering it would be a permanent operation + * for unprivileged users. + */ + rlim_cur_zero.rlim_max = rlim_init.rlim_max; + if (setrlimit(RLIMIT_MEMLOCK, &rlim_cur_zero)) + return false; + + /* Do not use bpf_prog_load() from libbpf here, because it calls + * bump_rlimit_memlock(), interfering with the current probe. + */ + prog_fd = syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr)); + err = errno; + + /* reset soft rlimit to its initial value */ + setrlimit(RLIMIT_MEMLOCK, &rlim_init); + + if (prog_fd < 0) + return err == EPERM; + + close(prog_fd); + return false; +} + +void set_max_rlimit(void) +{ + struct rlimit rinf = { RLIM_INFINITY, RLIM_INFINITY }; + + if (known_to_need_rlimit()) + setrlimit(RLIMIT_MEMLOCK, &rinf); +} + +static int +mnt_fs(const char *target, const char *type, char *buff, size_t bufflen) +{ + bool bind_done = false; + + while (mount("", target, "none", MS_PRIVATE | MS_REC, NULL)) { + if (errno != EINVAL || bind_done) { + snprintf(buff, bufflen, + "mount --make-private %s failed: %s", + target, strerror(errno)); + return -1; + } + + if (mount(target, target, "none", MS_BIND, NULL)) { + snprintf(buff, bufflen, + "mount --bind %s %s failed: %s", + target, target, strerror(errno)); + return -1; + } + + bind_done = true; + } + + if (mount(type, target, type, 0, "mode=0700")) { + snprintf(buff, bufflen, "mount -t %s %s %s failed: %s", + type, type, target, strerror(errno)); + return -1; + } + + return 0; +} + +int mount_tracefs(const char *target) +{ + char err_str[ERR_MAX_LEN]; + int err; + + err = mnt_fs(target, "tracefs", err_str, ERR_MAX_LEN); + if (err) { + err_str[ERR_MAX_LEN - 1] = '\0'; + p_err("can't mount tracefs: %s", err_str); + } + + return err; +} + +int open_obj_pinned(const char *path, bool quiet) +{ + char *pname; + int fd = -1; + + pname = strdup(path); + if (!pname) { + if (!quiet) + p_err("mem alloc failed"); + goto out_ret; + } + + fd = bpf_obj_get(pname); + if (fd < 0) { + if (!quiet) + p_err("bpf obj get (%s): %s", pname, + errno == EACCES && !is_bpffs(dirname(pname)) ? + "directory not in bpf file system (bpffs)" : + strerror(errno)); + goto out_free; + } + +out_free: + free(pname); +out_ret: + return fd; +} + +int open_obj_pinned_any(const char *path, enum bpf_obj_type exp_type) +{ + enum bpf_obj_type type; + int fd; + + fd = open_obj_pinned(path, false); + if (fd < 0) + return -1; + + type = get_fd_type(fd); + if (type < 0) { + close(fd); + return type; + } + if (type != exp_type) { + p_err("incorrect object type: %s", get_fd_type_name(type)); + close(fd); + return -1; + } + + return fd; +} + +int mount_bpffs_for_pin(const char *name) +{ + char err_str[ERR_MAX_LEN]; + char *file; + char *dir; + int err = 0; + + file = malloc(strlen(name) + 1); + if (!file) { + p_err("mem alloc failed"); + return -1; + } + + strcpy(file, name); + dir = dirname(file); + + if (is_bpffs(dir)) + /* nothing to do if already mounted */ + goto out_free; + + if (block_mount) { + p_err("no BPF file system found, not mounting it due to --nomount option"); + err = -1; + goto out_free; + } + + err = mnt_fs(dir, "bpf", err_str, ERR_MAX_LEN); + if (err) { + err_str[ERR_MAX_LEN - 1] = '\0'; + p_err("can't mount BPF file system to pin the object (%s): %s", + name, err_str); + } + +out_free: + free(file); + return err; +} + +int do_pin_fd(int fd, const char *name) +{ + int err; + + err = mount_bpffs_for_pin(name); + if (err) + return err; + + 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)(int *, char ***)) +{ + int err; + int fd; + + if (!REQ_ARGS(3)) + return -EINVAL; + + fd = get_fd(&argc, &argv); + if (fd < 0) + return fd; + + err = do_pin_fd(fd, *argv); + + close(fd); + return err; +} + +const char *get_fd_type_name(enum bpf_obj_type type) +{ + static const char * const names[] = { + [BPF_OBJ_UNKNOWN] = "unknown", + [BPF_OBJ_PROG] = "prog", + [BPF_OBJ_MAP] = "map", + [BPF_OBJ_LINK] = "link", + }; + + if (type < 0 || type >= ARRAY_SIZE(names) || !names[type]) + return names[BPF_OBJ_UNKNOWN]; + + return names[type]; +} + +void get_prog_full_name(const struct bpf_prog_info *prog_info, int prog_fd, + char *name_buff, size_t buff_len) +{ + const char *prog_name = prog_info->name; + const struct btf_type *func_type; + const struct bpf_func_info finfo = {}; + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + struct btf *prog_btf = NULL; + + if (buff_len <= BPF_OBJ_NAME_LEN || + strlen(prog_info->name) < BPF_OBJ_NAME_LEN - 1) + goto copy_name; + + if (!prog_info->btf_id || prog_info->nr_func_info == 0) + goto copy_name; + + info.nr_func_info = 1; + info.func_info_rec_size = prog_info->func_info_rec_size; + if (info.func_info_rec_size > sizeof(finfo)) + info.func_info_rec_size = sizeof(finfo); + info.func_info = ptr_to_u64(&finfo); + + if (bpf_obj_get_info_by_fd(prog_fd, &info, &info_len)) + goto copy_name; + + prog_btf = btf__load_from_kernel_by_id(info.btf_id); + if (!prog_btf) + goto copy_name; + + func_type = btf__type_by_id(prog_btf, finfo.type_id); + if (!func_type || !btf_is_func(func_type)) + goto copy_name; + + prog_name = btf__name_by_offset(prog_btf, func_type->name_off); + +copy_name: + snprintf(name_buff, buff_len, "%s", prog_name); + + if (prog_btf) + btf__free(prog_btf); +} + +int get_fd_type(int fd) +{ + char path[PATH_MAX]; + char buf[512]; + ssize_t n; + + snprintf(path, sizeof(path), "/proc/self/fd/%d", fd); + + n = readlink(path, buf, sizeof(buf)); + if (n < 0) { + p_err("can't read link type: %s", strerror(errno)); + return -1; + } + if (n == sizeof(path)) { + p_err("can't read link type: path too long!"); + return -1; + } + + if (strstr(buf, "bpf-map")) + return BPF_OBJ_MAP; + else if (strstr(buf, "bpf-prog")) + return BPF_OBJ_PROG; + else if (strstr(buf, "bpf-link")) + return BPF_OBJ_LINK; + + return BPF_OBJ_UNKNOWN; +} + +char *get_fdinfo(int fd, const char *key) +{ + char path[PATH_MAX]; + char *line = NULL; + size_t line_n = 0; + ssize_t n; + FILE *fdi; + + snprintf(path, sizeof(path), "/proc/self/fdinfo/%d", fd); + + fdi = fopen(path, "r"); + if (!fdi) + return NULL; + + while ((n = getline(&line, &line_n, fdi)) > 0) { + char *value; + int len; + + if (!strstr(line, key)) + continue; + + fclose(fdi); + + value = strchr(line, '\t'); + if (!value || !value[1]) { + free(line); + return NULL; + } + value++; + + len = strlen(value); + memmove(line, value, len); + line[len - 1] = '\0'; + + return line; + } + + free(line); + fclose(fdi); + return NULL; +} + +void print_data_json(uint8_t *data, size_t len) +{ + unsigned int i; + + jsonw_start_array(json_wtr); + for (i = 0; i < len; i++) + jsonw_printf(json_wtr, "%d", data[i]); + jsonw_end_array(json_wtr); +} + +void print_hex_data_json(uint8_t *data, size_t len) +{ + unsigned int i; + + jsonw_start_array(json_wtr); + for (i = 0; i < len; i++) + jsonw_printf(json_wtr, "\"0x%02hhx\"", data[i]); + jsonw_end_array(json_wtr); +} + +/* extra params for nftw cb */ +static struct hashmap *build_fn_table; +static enum bpf_obj_type build_fn_type; + +static int do_build_table_cb(const char *fpath, const struct stat *sb, + int typeflag, struct FTW *ftwbuf) +{ + struct bpf_prog_info pinned_info; + __u32 len = sizeof(pinned_info); + enum bpf_obj_type objtype; + int fd, err = 0; + char *path; + + if (typeflag != FTW_F) + goto out_ret; + + fd = open_obj_pinned(fpath, true); + if (fd < 0) + goto out_ret; + + objtype = get_fd_type(fd); + if (objtype != build_fn_type) + goto out_close; + + memset(&pinned_info, 0, sizeof(pinned_info)); + if (bpf_obj_get_info_by_fd(fd, &pinned_info, &len)) + goto out_close; + + path = strdup(fpath); + if (!path) { + err = -1; + goto out_close; + } + + err = hashmap__append(build_fn_table, u32_as_hash_field(pinned_info.id), path); + if (err) { + p_err("failed to append entry to hashmap for ID %u, path '%s': %s", + pinned_info.id, path, strerror(errno)); + free(path); + goto out_close; + } + +out_close: + close(fd); +out_ret: + return err; +} + +int build_pinned_obj_table(struct hashmap *tab, + enum bpf_obj_type type) +{ + struct mntent *mntent = NULL; + FILE *mntfile = NULL; + int flags = FTW_PHYS; + int nopenfd = 16; + int err = 0; + + mntfile = setmntent("/proc/mounts", "r"); + if (!mntfile) + return -1; + + build_fn_table = tab; + build_fn_type = type; + + while ((mntent = getmntent(mntfile))) { + char *path = mntent->mnt_dir; + + if (strncmp(mntent->mnt_type, "bpf", 3) != 0) + continue; + err = nftw(path, do_build_table_cb, nopenfd, flags); + if (err) + break; + } + fclose(mntfile); + return err; +} + +void delete_pinned_obj_table(struct hashmap *map) +{ + struct hashmap_entry *entry; + size_t bkt; + + if (!map) + return; + + hashmap__for_each_entry(map, entry, bkt) + free(entry->value); + + hashmap__free(map); +} + +unsigned int get_page_size(void) +{ + static int result; + + if (!result) + result = getpagesize(); + return result; +} + +unsigned int get_possible_cpus(void) +{ + int cpus = libbpf_num_possible_cpus(); + + if (cpus < 0) { + p_err("Can't get # of possible cpus: %s", strerror(-cpus)); + exit(-1); + } + return cpus; +} + +static char * +ifindex_to_name_ns(__u32 ifindex, __u32 ns_dev, __u32 ns_ino, char *buf) +{ + struct stat st; + int err; + + err = stat("/proc/self/ns/net", &st); + if (err) { + p_err("Can't stat /proc/self: %s", strerror(errno)); + return NULL; + } + + if (st.st_dev != ns_dev || st.st_ino != ns_ino) + return NULL; + + return if_indextoname(ifindex, buf); +} + +static int read_sysfs_hex_int(char *path) +{ + char vendor_id_buf[8]; + int len; + int fd; + + fd = open(path, O_RDONLY); + if (fd < 0) { + p_err("Can't open %s: %s", path, strerror(errno)); + return -1; + } + + len = read(fd, vendor_id_buf, sizeof(vendor_id_buf)); + close(fd); + if (len < 0) { + p_err("Can't read %s: %s", path, strerror(errno)); + return -1; + } + if (len >= (int)sizeof(vendor_id_buf)) { + p_err("Value in %s too long", path); + return -1; + } + + vendor_id_buf[len] = 0; + + return strtol(vendor_id_buf, NULL, 0); +} + +static int read_sysfs_netdev_hex_int(char *devname, const char *entry_name) +{ + char full_path[64]; + + snprintf(full_path, sizeof(full_path), "/sys/class/net/%s/device/%s", + devname, entry_name); + + return read_sysfs_hex_int(full_path); +} + +const char * +ifindex_to_bfd_params(__u32 ifindex, __u64 ns_dev, __u64 ns_ino, + const char **opt) +{ + char devname[IF_NAMESIZE]; + int vendor_id; + int device_id; + + if (!ifindex_to_name_ns(ifindex, ns_dev, ns_ino, devname)) { + p_err("Can't get net device name for ifindex %d: %s", ifindex, + strerror(errno)); + return NULL; + } + + vendor_id = read_sysfs_netdev_hex_int(devname, "vendor"); + if (vendor_id < 0) { + p_err("Can't get device vendor id for %s", devname); + return NULL; + } + + switch (vendor_id) { + case 0x19ee: + device_id = read_sysfs_netdev_hex_int(devname, "device"); + if (device_id != 0x4000 && + device_id != 0x6000 && + device_id != 0x6003) + p_info("Unknown NFP device ID, assuming it is NFP-6xxx arch"); + *opt = "ctx4"; + return "NFP-6xxx"; + default: + p_err("Can't get bfd arch name for device vendor id 0x%04x", + vendor_id); + return NULL; + } +} + +void print_dev_plain(__u32 ifindex, __u64 ns_dev, __u64 ns_inode) +{ + char name[IF_NAMESIZE]; + + if (!ifindex) + return; + + printf(" offloaded_to "); + if (ifindex_to_name_ns(ifindex, ns_dev, ns_inode, name)) + printf("%s", name); + else + printf("ifindex %u ns_dev %llu ns_ino %llu", + ifindex, ns_dev, ns_inode); +} + +void print_dev_json(__u32 ifindex, __u64 ns_dev, __u64 ns_inode) +{ + char name[IF_NAMESIZE]; + + if (!ifindex) + return; + + jsonw_name(json_wtr, "dev"); + jsonw_start_object(json_wtr); + jsonw_uint_field(json_wtr, "ifindex", ifindex); + jsonw_uint_field(json_wtr, "ns_dev", ns_dev); + jsonw_uint_field(json_wtr, "ns_inode", ns_inode); + if (ifindex_to_name_ns(ifindex, ns_dev, ns_inode, name)) + jsonw_string_field(json_wtr, "ifname", name); + jsonw_end_object(json_wtr); +} + +int parse_u32_arg(int *argc, char ***argv, __u32 *val, const char *what) +{ + char *endptr; + + NEXT_ARGP(); + + if (*val) { + p_err("%s already specified", what); + return -1; + } + + *val = strtoul(**argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as %s", **argv, what); + return -1; + } + NEXT_ARGP(); + + return 0; +} + +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); +} + +static int prog_fd_by_nametag(void *nametag, int **fds, bool tag) +{ + char prog_name[MAX_PROG_FULL_NAME]; + unsigned int id = 0; + int fd, nb_fds = 0; + void *tmp; + int err; + + while (true) { + struct bpf_prog_info info = {}; + __u32 len = sizeof(info); + + err = bpf_prog_get_next_id(id, &id); + if (err) { + if (errno != ENOENT) { + p_err("%s", strerror(errno)); + goto err_close_fds; + } + return nb_fds; + } + + fd = bpf_prog_get_fd_by_id(id); + if (fd < 0) { + p_err("can't get prog by id (%u): %s", + id, strerror(errno)); + goto err_close_fds; + } + + err = bpf_obj_get_info_by_fd(fd, &info, &len); + if (err) { + p_err("can't get prog info (%u): %s", + id, strerror(errno)); + goto err_close_fd; + } + + if (tag && memcmp(nametag, info.tag, BPF_TAG_SIZE)) { + close(fd); + continue; + } + + if (!tag) { + get_prog_full_name(&info, fd, prog_name, + sizeof(prog_name)); + if (strncmp(nametag, prog_name, sizeof(prog_name))) { + close(fd); + continue; + } + } + + if (nb_fds > 0) { + tmp = realloc(*fds, (nb_fds + 1) * sizeof(int)); + if (!tmp) { + p_err("failed to realloc"); + goto err_close_fd; + } + *fds = tmp; + } + (*fds)[nb_fds++] = fd; + } + +err_close_fd: + close(fd); +err_close_fds: + while (--nb_fds >= 0) + close((*fds)[nb_fds]); + return -1; +} + +int prog_parse_fds(int *argc, char ***argv, int **fds) +{ + if (is_prefix(**argv, "id")) { + unsigned int id; + char *endptr; + + NEXT_ARGP(); + + id = strtoul(**argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as ID", **argv); + return -1; + } + NEXT_ARGP(); + + (*fds)[0] = bpf_prog_get_fd_by_id(id); + if ((*fds)[0] < 0) { + p_err("get by id (%u): %s", id, strerror(errno)); + return -1; + } + return 1; + } else if (is_prefix(**argv, "tag")) { + unsigned char tag[BPF_TAG_SIZE]; + + NEXT_ARGP(); + + if (sscanf(**argv, BPF_TAG_FMT, tag, tag + 1, tag + 2, + tag + 3, tag + 4, tag + 5, tag + 6, tag + 7) + != BPF_TAG_SIZE) { + p_err("can't parse tag"); + return -1; + } + NEXT_ARGP(); + + return prog_fd_by_nametag(tag, fds, true); + } else if (is_prefix(**argv, "name")) { + char *name; + + NEXT_ARGP(); + + name = **argv; + if (strlen(name) > MAX_PROG_FULL_NAME - 1) { + p_err("can't parse name"); + return -1; + } + NEXT_ARGP(); + + return prog_fd_by_nametag(name, fds, false); + } else if (is_prefix(**argv, "pinned")) { + char *path; + + NEXT_ARGP(); + + path = **argv; + NEXT_ARGP(); + + (*fds)[0] = open_obj_pinned_any(path, BPF_OBJ_PROG); + if ((*fds)[0] < 0) + return -1; + return 1; + } + + p_err("expected 'id', 'tag', 'name' or 'pinned', got: '%s'?", **argv); + return -1; +} + +int prog_parse_fd(int *argc, char ***argv) +{ + int *fds = NULL; + int nb_fds, fd; + + fds = malloc(sizeof(int)); + if (!fds) { + p_err("mem alloc failed"); + return -1; + } + nb_fds = prog_parse_fds(argc, argv, &fds); + if (nb_fds != 1) { + if (nb_fds > 1) { + p_err("several programs match this handle"); + while (nb_fds--) + close(fds[nb_fds]); + } + fd = -1; + goto exit_free; + } + + fd = fds[0]; +exit_free: + free(fds); + return fd; +} + +static int map_fd_by_name(char *name, int **fds) +{ + unsigned int id = 0; + int fd, nb_fds = 0; + void *tmp; + int err; + + while (true) { + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + + err = bpf_map_get_next_id(id, &id); + if (err) { + if (errno != ENOENT) { + p_err("%s", strerror(errno)); + goto err_close_fds; + } + return nb_fds; + } + + fd = bpf_map_get_fd_by_id(id); + if (fd < 0) { + p_err("can't get map by id (%u): %s", + id, strerror(errno)); + goto err_close_fds; + } + + err = bpf_obj_get_info_by_fd(fd, &info, &len); + if (err) { + p_err("can't get map info (%u): %s", + id, strerror(errno)); + goto err_close_fd; + } + + if (strncmp(name, info.name, BPF_OBJ_NAME_LEN)) { + close(fd); + continue; + } + + if (nb_fds > 0) { + tmp = realloc(*fds, (nb_fds + 1) * sizeof(int)); + if (!tmp) { + p_err("failed to realloc"); + goto err_close_fd; + } + *fds = tmp; + } + (*fds)[nb_fds++] = fd; + } + +err_close_fd: + close(fd); +err_close_fds: + while (--nb_fds >= 0) + close((*fds)[nb_fds]); + return -1; +} + +int map_parse_fds(int *argc, char ***argv, int **fds) +{ + if (is_prefix(**argv, "id")) { + unsigned int id; + char *endptr; + + NEXT_ARGP(); + + id = strtoul(**argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as ID", **argv); + return -1; + } + NEXT_ARGP(); + + (*fds)[0] = bpf_map_get_fd_by_id(id); + if ((*fds)[0] < 0) { + p_err("get map by id (%u): %s", id, strerror(errno)); + return -1; + } + return 1; + } else if (is_prefix(**argv, "name")) { + char *name; + + NEXT_ARGP(); + + name = **argv; + if (strlen(name) > BPF_OBJ_NAME_LEN - 1) { + p_err("can't parse name"); + return -1; + } + NEXT_ARGP(); + + return map_fd_by_name(name, fds); + } else if (is_prefix(**argv, "pinned")) { + char *path; + + NEXT_ARGP(); + + path = **argv; + NEXT_ARGP(); + + (*fds)[0] = open_obj_pinned_any(path, BPF_OBJ_MAP); + if ((*fds)[0] < 0) + return -1; + return 1; + } + + p_err("expected 'id', 'name' or 'pinned', got: '%s'?", **argv); + return -1; +} + +int map_parse_fd(int *argc, char ***argv) +{ + int *fds = NULL; + int nb_fds, fd; + + fds = malloc(sizeof(int)); + if (!fds) { + p_err("mem alloc failed"); + return -1; + } + nb_fds = map_parse_fds(argc, argv, &fds); + if (nb_fds != 1) { + if (nb_fds > 1) { + p_err("several maps match this handle"); + while (nb_fds--) + close(fds[nb_fds]); + } + fd = -1; + goto exit_free; + } + + fd = fds[0]; +exit_free: + free(fds); + return fd; +} + +int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len) +{ + int err; + int fd; + + fd = map_parse_fd(argc, argv); + if (fd < 0) + return -1; + + err = bpf_obj_get_info_by_fd(fd, info, info_len); + if (err) { + p_err("can't get map info: %s", strerror(errno)); + close(fd); + return err; + } + + return fd; +} + +size_t hash_fn_for_key_as_id(const void *key, void *ctx) +{ + return (size_t)key; +} + +bool equal_fn_for_key_as_id(const void *k1, const void *k2, void *ctx) +{ + return k1 == k2; +} + +const char *bpf_attach_type_input_str(enum bpf_attach_type t) +{ + switch (t) { + case BPF_CGROUP_INET_INGRESS: return "ingress"; + case BPF_CGROUP_INET_EGRESS: return "egress"; + case BPF_CGROUP_INET_SOCK_CREATE: return "sock_create"; + case BPF_CGROUP_INET_SOCK_RELEASE: return "sock_release"; + case BPF_CGROUP_SOCK_OPS: return "sock_ops"; + case BPF_CGROUP_DEVICE: return "device"; + case BPF_CGROUP_INET4_BIND: return "bind4"; + case BPF_CGROUP_INET6_BIND: return "bind6"; + case BPF_CGROUP_INET4_CONNECT: return "connect4"; + case BPF_CGROUP_INET6_CONNECT: return "connect6"; + case BPF_CGROUP_INET4_POST_BIND: return "post_bind4"; + case BPF_CGROUP_INET6_POST_BIND: return "post_bind6"; + case BPF_CGROUP_INET4_GETPEERNAME: return "getpeername4"; + case BPF_CGROUP_INET6_GETPEERNAME: return "getpeername6"; + case BPF_CGROUP_INET4_GETSOCKNAME: return "getsockname4"; + case BPF_CGROUP_INET6_GETSOCKNAME: return "getsockname6"; + case BPF_CGROUP_UDP4_SENDMSG: return "sendmsg4"; + case BPF_CGROUP_UDP6_SENDMSG: return "sendmsg6"; + case BPF_CGROUP_SYSCTL: return "sysctl"; + case BPF_CGROUP_UDP4_RECVMSG: return "recvmsg4"; + case BPF_CGROUP_UDP6_RECVMSG: return "recvmsg6"; + case BPF_CGROUP_GETSOCKOPT: return "getsockopt"; + case BPF_CGROUP_SETSOCKOPT: return "setsockopt"; + case BPF_TRACE_RAW_TP: return "raw_tp"; + case BPF_TRACE_FENTRY: return "fentry"; + case BPF_TRACE_FEXIT: return "fexit"; + case BPF_MODIFY_RETURN: return "mod_ret"; + case BPF_SK_REUSEPORT_SELECT: return "sk_skb_reuseport_select"; + case BPF_SK_REUSEPORT_SELECT_OR_MIGRATE: return "sk_skb_reuseport_select_or_migrate"; + default: return libbpf_bpf_attach_type_str(t); + } +} diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c new file mode 100644 index 000000000..4460399bc --- /dev/null +++ b/tools/bpf/bpftool/feature.c @@ -0,0 +1,1344 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (c) 2019 Netronome Systems, Inc. */ + +#include <ctype.h> +#include <errno.h> +#include <fcntl.h> +#include <string.h> +#include <unistd.h> +#include <net/if.h> +#ifdef USE_LIBCAP +#include <sys/capability.h> +#endif +#include <sys/utsname.h> +#include <sys/vfs.h> + +#include <linux/filter.h> +#include <linux/limits.h> + +#include <bpf/bpf.h> +#include <bpf/libbpf.h> +#include <zlib.h> + +#include "main.h" + +#ifndef PROC_SUPER_MAGIC +# define PROC_SUPER_MAGIC 0x9fa0 +#endif + +enum probe_component { + COMPONENT_UNSPEC, + COMPONENT_KERNEL, + COMPONENT_DEVICE, +}; + +#define BPF_HELPER_MAKE_ENTRY(name) [BPF_FUNC_ ## name] = "bpf_" # name +static const char * const helper_name[] = { + __BPF_FUNC_MAPPER(BPF_HELPER_MAKE_ENTRY) +}; + +#undef BPF_HELPER_MAKE_ENTRY + +static bool full_mode; +#ifdef USE_LIBCAP +static bool run_as_unprivileged; +#endif + +/* Miscellaneous utility functions */ + +static bool grep(const char *buffer, const char *pattern) +{ + return !!strstr(buffer, pattern); +} + +static bool check_procfs(void) +{ + struct statfs st_fs; + + if (statfs("/proc", &st_fs) < 0) + return false; + if ((unsigned long)st_fs.f_type != PROC_SUPER_MAGIC) + return false; + + return true; +} + +static void uppercase(char *str, size_t len) +{ + size_t i; + + for (i = 0; i < len && str[i] != '\0'; i++) + str[i] = toupper(str[i]); +} + +/* Printing utility functions */ + +static void +print_bool_feature(const char *feat_name, const char *plain_name, + const char *define_name, bool res, const char *define_prefix) +{ + if (json_output) + jsonw_bool_field(json_wtr, feat_name, res); + else if (define_prefix) + printf("#define %s%sHAVE_%s\n", define_prefix, + res ? "" : "NO_", define_name); + else + printf("%s is %savailable\n", plain_name, res ? "" : "NOT "); +} + +static void print_kernel_option(const char *name, const char *value, + const char *define_prefix) +{ + char *endptr; + int res; + + if (json_output) { + if (!value) { + jsonw_null_field(json_wtr, name); + return; + } + errno = 0; + res = strtol(value, &endptr, 0); + if (!errno && *endptr == '\n') + jsonw_int_field(json_wtr, name, res); + else + jsonw_string_field(json_wtr, name, value); + } else if (define_prefix) { + if (value) + printf("#define %s%s %s\n", define_prefix, + name, value); + else + printf("/* %s%s is not set */\n", define_prefix, name); + } else { + if (value) + printf("%s is set to %s\n", name, value); + else + printf("%s is not set\n", name); + } +} + +static void +print_start_section(const char *json_title, const char *plain_title, + const char *define_comment, const char *define_prefix) +{ + if (json_output) { + jsonw_name(json_wtr, json_title); + jsonw_start_object(json_wtr); + } else if (define_prefix) { + printf("%s\n", define_comment); + } else { + printf("%s\n", plain_title); + } +} + +static void print_end_section(void) +{ + if (json_output) + jsonw_end_object(json_wtr); + else + printf("\n"); +} + +/* Probing functions */ + +static int get_vendor_id(int ifindex) +{ + char ifname[IF_NAMESIZE], path[64], buf[8]; + ssize_t len; + int fd; + + if (!if_indextoname(ifindex, ifname)) + return -1; + + snprintf(path, sizeof(path), "/sys/class/net/%s/device/vendor", ifname); + + fd = open(path, O_RDONLY | O_CLOEXEC); + if (fd < 0) + return -1; + + len = read(fd, buf, sizeof(buf)); + close(fd); + if (len < 0) + return -1; + if (len >= (ssize_t)sizeof(buf)) + return -1; + buf[len] = '\0'; + + return strtol(buf, NULL, 0); +} + +static long read_procfs(const char *path) +{ + char *endptr, *line = NULL; + size_t len = 0; + FILE *fd; + long res; + + fd = fopen(path, "r"); + if (!fd) + return -1; + + res = getline(&line, &len, fd); + fclose(fd); + if (res < 0) + return -1; + + errno = 0; + res = strtol(line, &endptr, 10); + if (errno || *line == '\0' || *endptr != '\n') + res = -1; + free(line); + + return res; +} + +static void probe_unprivileged_disabled(void) +{ + long res; + + /* No support for C-style ouptut */ + + res = read_procfs("/proc/sys/kernel/unprivileged_bpf_disabled"); + if (json_output) { + jsonw_int_field(json_wtr, "unprivileged_bpf_disabled", res); + } else { + switch (res) { + case 0: + printf("bpf() syscall for unprivileged users is enabled\n"); + break; + case 1: + printf("bpf() syscall restricted to privileged users (without recovery)\n"); + break; + case 2: + printf("bpf() syscall restricted to privileged users (admin can change)\n"); + break; + case -1: + printf("Unable to retrieve required privileges for bpf() syscall\n"); + break; + default: + printf("bpf() syscall restriction has unknown value %ld\n", res); + } + } +} + +static void probe_jit_enable(void) +{ + long res; + + /* No support for C-style ouptut */ + + res = read_procfs("/proc/sys/net/core/bpf_jit_enable"); + if (json_output) { + jsonw_int_field(json_wtr, "bpf_jit_enable", res); + } else { + switch (res) { + case 0: + printf("JIT compiler is disabled\n"); + break; + case 1: + printf("JIT compiler is enabled\n"); + break; + case 2: + printf("JIT compiler is enabled with debugging traces in kernel logs\n"); + break; + case -1: + printf("Unable to retrieve JIT-compiler status\n"); + break; + default: + printf("JIT-compiler status has unknown value %ld\n", + res); + } + } +} + +static void probe_jit_harden(void) +{ + long res; + + /* No support for C-style ouptut */ + + res = read_procfs("/proc/sys/net/core/bpf_jit_harden"); + if (json_output) { + jsonw_int_field(json_wtr, "bpf_jit_harden", res); + } else { + switch (res) { + case 0: + printf("JIT compiler hardening is disabled\n"); + break; + case 1: + printf("JIT compiler hardening is enabled for unprivileged users\n"); + break; + case 2: + printf("JIT compiler hardening is enabled for all users\n"); + break; + case -1: + printf("Unable to retrieve JIT hardening status\n"); + break; + default: + printf("JIT hardening status has unknown value %ld\n", + res); + } + } +} + +static void probe_jit_kallsyms(void) +{ + long res; + + /* No support for C-style ouptut */ + + res = read_procfs("/proc/sys/net/core/bpf_jit_kallsyms"); + if (json_output) { + jsonw_int_field(json_wtr, "bpf_jit_kallsyms", res); + } else { + switch (res) { + case 0: + printf("JIT compiler kallsyms exports are disabled\n"); + break; + case 1: + printf("JIT compiler kallsyms exports are enabled for root\n"); + break; + case -1: + printf("Unable to retrieve JIT kallsyms export status\n"); + break; + default: + printf("JIT kallsyms exports status has unknown value %ld\n", res); + } + } +} + +static void probe_jit_limit(void) +{ + long res; + + /* No support for C-style ouptut */ + + res = read_procfs("/proc/sys/net/core/bpf_jit_limit"); + if (json_output) { + jsonw_int_field(json_wtr, "bpf_jit_limit", res); + } else { + switch (res) { + case -1: + printf("Unable to retrieve global memory limit for JIT compiler for unprivileged users\n"); + break; + default: + printf("Global memory limit for JIT compiler for unprivileged users is %ld bytes\n", res); + } + } +} + +static bool read_next_kernel_config_option(gzFile file, char *buf, size_t n, + char **value) +{ + char *sep; + + while (gzgets(file, buf, n)) { + if (strncmp(buf, "CONFIG_", 7)) + continue; + + sep = strchr(buf, '='); + if (!sep) + continue; + + /* Trim ending '\n' */ + buf[strlen(buf) - 1] = '\0'; + + /* Split on '=' and ensure that a value is present. */ + *sep = '\0'; + if (!sep[1]) + continue; + + *value = sep + 1; + return true; + } + + return false; +} + +static void probe_kernel_image_config(const char *define_prefix) +{ + static const struct { + const char * const name; + bool macro_dump; + } options[] = { + /* Enable BPF */ + { "CONFIG_BPF", }, + /* Enable bpf() syscall */ + { "CONFIG_BPF_SYSCALL", }, + /* Does selected architecture support eBPF JIT compiler */ + { "CONFIG_HAVE_EBPF_JIT", }, + /* Compile eBPF JIT compiler */ + { "CONFIG_BPF_JIT", }, + /* Avoid compiling eBPF interpreter (use JIT only) */ + { "CONFIG_BPF_JIT_ALWAYS_ON", }, + /* Kernel BTF debug information available */ + { "CONFIG_DEBUG_INFO_BTF", }, + /* Kernel module BTF debug information available */ + { "CONFIG_DEBUG_INFO_BTF_MODULES", }, + + /* cgroups */ + { "CONFIG_CGROUPS", }, + /* BPF programs attached to cgroups */ + { "CONFIG_CGROUP_BPF", }, + /* bpf_get_cgroup_classid() helper */ + { "CONFIG_CGROUP_NET_CLASSID", }, + /* bpf_skb_{,ancestor_}cgroup_id() helpers */ + { "CONFIG_SOCK_CGROUP_DATA", }, + + /* Tracing: attach BPF to kprobes, tracepoints, etc. */ + { "CONFIG_BPF_EVENTS", }, + /* Kprobes */ + { "CONFIG_KPROBE_EVENTS", }, + /* Uprobes */ + { "CONFIG_UPROBE_EVENTS", }, + /* Tracepoints */ + { "CONFIG_TRACING", }, + /* Syscall tracepoints */ + { "CONFIG_FTRACE_SYSCALLS", }, + /* bpf_override_return() helper support for selected arch */ + { "CONFIG_FUNCTION_ERROR_INJECTION", }, + /* bpf_override_return() helper */ + { "CONFIG_BPF_KPROBE_OVERRIDE", }, + + /* Network */ + { "CONFIG_NET", }, + /* AF_XDP sockets */ + { "CONFIG_XDP_SOCKETS", }, + /* BPF_PROG_TYPE_LWT_* and related helpers */ + { "CONFIG_LWTUNNEL_BPF", }, + /* BPF_PROG_TYPE_SCHED_ACT, TC (traffic control) actions */ + { "CONFIG_NET_ACT_BPF", }, + /* BPF_PROG_TYPE_SCHED_CLS, TC filters */ + { "CONFIG_NET_CLS_BPF", }, + /* TC clsact qdisc */ + { "CONFIG_NET_CLS_ACT", }, + /* Ingress filtering with TC */ + { "CONFIG_NET_SCH_INGRESS", }, + /* bpf_skb_get_xfrm_state() helper */ + { "CONFIG_XFRM", }, + /* bpf_get_route_realm() helper */ + { "CONFIG_IP_ROUTE_CLASSID", }, + /* BPF_PROG_TYPE_LWT_SEG6_LOCAL and related helpers */ + { "CONFIG_IPV6_SEG6_BPF", }, + /* BPF_PROG_TYPE_LIRC_MODE2 and related helpers */ + { "CONFIG_BPF_LIRC_MODE2", }, + /* BPF stream parser and BPF socket maps */ + { "CONFIG_BPF_STREAM_PARSER", }, + /* xt_bpf module for passing BPF programs to netfilter */ + { "CONFIG_NETFILTER_XT_MATCH_BPF", }, + /* bpfilter back-end for iptables */ + { "CONFIG_BPFILTER", }, + /* bpftilter module with "user mode helper" */ + { "CONFIG_BPFILTER_UMH", }, + + /* test_bpf module for BPF tests */ + { "CONFIG_TEST_BPF", }, + + /* Misc configs useful in BPF C programs */ + /* jiffies <-> sec conversion for bpf_jiffies64() helper */ + { "CONFIG_HZ", true, } + }; + char *values[ARRAY_SIZE(options)] = { }; + struct utsname utsn; + char path[PATH_MAX]; + gzFile file = NULL; + char buf[4096]; + char *value; + size_t i; + + if (!uname(&utsn)) { + snprintf(path, sizeof(path), "/boot/config-%s", utsn.release); + + /* gzopen also accepts uncompressed files. */ + file = gzopen(path, "r"); + } + + if (!file) { + /* Some distributions build with CONFIG_IKCONFIG=y and put the + * config file at /proc/config.gz. + */ + file = gzopen("/proc/config.gz", "r"); + } + if (!file) { + p_info("skipping kernel config, can't open file: %s", + strerror(errno)); + goto end_parse; + } + /* Sanity checks */ + if (!gzgets(file, buf, sizeof(buf)) || + !gzgets(file, buf, sizeof(buf))) { + p_info("skipping kernel config, can't read from file: %s", + strerror(errno)); + goto end_parse; + } + if (strcmp(buf, "# Automatically generated file; DO NOT EDIT.\n")) { + p_info("skipping kernel config, can't find correct file"); + goto end_parse; + } + + while (read_next_kernel_config_option(file, buf, sizeof(buf), &value)) { + for (i = 0; i < ARRAY_SIZE(options); i++) { + if ((define_prefix && !options[i].macro_dump) || + values[i] || strcmp(buf, options[i].name)) + continue; + + values[i] = strdup(value); + } + } + +end_parse: + if (file) + gzclose(file); + + for (i = 0; i < ARRAY_SIZE(options); i++) { + if (define_prefix && !options[i].macro_dump) + continue; + print_kernel_option(options[i].name, values[i], define_prefix); + free(values[i]); + } +} + +static bool probe_bpf_syscall(const char *define_prefix) +{ + bool res; + + bpf_prog_load(BPF_PROG_TYPE_UNSPEC, NULL, NULL, NULL, 0, NULL); + res = (errno != ENOSYS); + + print_bool_feature("have_bpf_syscall", + "bpf() syscall", + "BPF_SYSCALL", + res, define_prefix); + + return res; +} + +static bool +probe_prog_load_ifindex(enum bpf_prog_type prog_type, + const struct bpf_insn *insns, size_t insns_cnt, + char *log_buf, size_t log_buf_sz, + __u32 ifindex) +{ + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .log_buf = log_buf, + .log_size = log_buf_sz, + .log_level = log_buf ? 1 : 0, + .prog_ifindex = ifindex, + ); + int fd; + + errno = 0; + fd = bpf_prog_load(prog_type, NULL, "GPL", insns, insns_cnt, &opts); + if (fd >= 0) + close(fd); + + return fd >= 0 && errno != EINVAL && errno != EOPNOTSUPP; +} + +static bool probe_prog_type_ifindex(enum bpf_prog_type prog_type, __u32 ifindex) +{ + /* nfp returns -EINVAL on exit(0) with TC offload */ + struct bpf_insn insns[2] = { + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_EXIT_INSN() + }; + + return probe_prog_load_ifindex(prog_type, insns, ARRAY_SIZE(insns), + NULL, 0, ifindex); +} + +static void +probe_prog_type(enum bpf_prog_type prog_type, const char *prog_type_str, + bool *supported_types, const char *define_prefix, __u32 ifindex) +{ + char feat_name[128], plain_desc[128], define_name[128]; + const char *plain_comment = "eBPF program_type "; + size_t maxlen; + bool res; + + if (ifindex) { + switch (prog_type) { + case BPF_PROG_TYPE_SCHED_CLS: + case BPF_PROG_TYPE_XDP: + break; + default: + return; + } + + res = probe_prog_type_ifindex(prog_type, ifindex); + } else { + res = libbpf_probe_bpf_prog_type(prog_type, NULL) > 0; + } + +#ifdef USE_LIBCAP + /* Probe may succeed even if program load fails, for unprivileged users + * check that we did not fail because of insufficient permissions + */ + if (run_as_unprivileged && errno == EPERM) + res = false; +#endif + + supported_types[prog_type] |= res; + + maxlen = sizeof(plain_desc) - strlen(plain_comment) - 1; + if (strlen(prog_type_str) > maxlen) { + p_info("program type name too long"); + return; + } + + sprintf(feat_name, "have_%s_prog_type", prog_type_str); + sprintf(define_name, "%s_prog_type", prog_type_str); + uppercase(define_name, sizeof(define_name)); + sprintf(plain_desc, "%s%s", plain_comment, prog_type_str); + print_bool_feature(feat_name, plain_desc, define_name, res, + define_prefix); +} + +static bool probe_map_type_ifindex(enum bpf_map_type map_type, __u32 ifindex) +{ + LIBBPF_OPTS(bpf_map_create_opts, opts); + int key_size, value_size, max_entries; + int fd; + + opts.map_ifindex = ifindex; + + key_size = sizeof(__u32); + value_size = sizeof(__u32); + max_entries = 1; + + fd = bpf_map_create(map_type, NULL, key_size, value_size, max_entries, + &opts); + if (fd >= 0) + close(fd); + + return fd >= 0; +} + +static void +probe_map_type(enum bpf_map_type map_type, char const *map_type_str, + const char *define_prefix, __u32 ifindex) +{ + char feat_name[128], plain_desc[128], define_name[128]; + const char *plain_comment = "eBPF map_type "; + size_t maxlen; + bool res; + + if (ifindex) { + switch (map_type) { + case BPF_MAP_TYPE_HASH: + case BPF_MAP_TYPE_ARRAY: + break; + default: + return; + } + + res = probe_map_type_ifindex(map_type, ifindex); + } else { + res = libbpf_probe_bpf_map_type(map_type, NULL) > 0; + } + + /* Probe result depends on the success of map creation, no additional + * check required for unprivileged users + */ + + maxlen = sizeof(plain_desc) - strlen(plain_comment) - 1; + if (strlen(map_type_str) > maxlen) { + p_info("map type name too long"); + return; + } + + sprintf(feat_name, "have_%s_map_type", map_type_str); + sprintf(define_name, "%s_map_type", map_type_str); + uppercase(define_name, sizeof(define_name)); + sprintf(plain_desc, "%s%s", plain_comment, map_type_str); + print_bool_feature(feat_name, plain_desc, define_name, res, + define_prefix); +} + +static bool +probe_helper_ifindex(enum bpf_func_id id, enum bpf_prog_type prog_type, + __u32 ifindex) +{ + struct bpf_insn insns[2] = { + BPF_EMIT_CALL(id), + BPF_EXIT_INSN() + }; + char buf[4096] = {}; + bool res; + + probe_prog_load_ifindex(prog_type, insns, ARRAY_SIZE(insns), buf, + sizeof(buf), ifindex); + res = !grep(buf, "invalid func ") && !grep(buf, "unknown func "); + + switch (get_vendor_id(ifindex)) { + case 0x19ee: /* Netronome specific */ + res = res && !grep(buf, "not supported by FW") && + !grep(buf, "unsupported function id"); + break; + default: + break; + } + + return res; +} + +static bool +probe_helper_for_progtype(enum bpf_prog_type prog_type, bool supported_type, + const char *define_prefix, unsigned int id, + const char *ptype_name, __u32 ifindex) +{ + bool res = false; + + if (supported_type) { + if (ifindex) + res = probe_helper_ifindex(id, prog_type, ifindex); + else + res = libbpf_probe_bpf_helper(prog_type, id, NULL) > 0; +#ifdef USE_LIBCAP + /* Probe may succeed even if program load fails, for + * unprivileged users check that we did not fail because of + * insufficient permissions + */ + if (run_as_unprivileged && errno == EPERM) + res = false; +#endif + } + + if (json_output) { + if (res) + jsonw_string(json_wtr, helper_name[id]); + } else if (define_prefix) { + printf("#define %sBPF__PROG_TYPE_%s__HELPER_%s %s\n", + define_prefix, ptype_name, helper_name[id], + res ? "1" : "0"); + } else { + if (res) + printf("\n\t- %s", helper_name[id]); + } + + return res; +} + +static void +probe_helpers_for_progtype(enum bpf_prog_type prog_type, + const char *prog_type_str, bool supported_type, + const char *define_prefix, __u32 ifindex) +{ + char feat_name[128]; + unsigned int id; + bool probe_res = false; + + if (ifindex) + /* Only test helpers for offload-able program types */ + switch (prog_type) { + case BPF_PROG_TYPE_SCHED_CLS: + case BPF_PROG_TYPE_XDP: + break; + default: + return; + } + + if (json_output) { + sprintf(feat_name, "%s_available_helpers", prog_type_str); + jsonw_name(json_wtr, feat_name); + jsonw_start_array(json_wtr); + } else if (!define_prefix) { + printf("eBPF helpers supported for program type %s:", + prog_type_str); + } + + for (id = 1; id < ARRAY_SIZE(helper_name); id++) { + /* Skip helper functions which emit dmesg messages when not in + * the full mode. + */ + switch (id) { + case BPF_FUNC_trace_printk: + case BPF_FUNC_trace_vprintk: + case BPF_FUNC_probe_write_user: + if (!full_mode) + continue; + /* fallthrough */ + default: + probe_res |= probe_helper_for_progtype(prog_type, supported_type, + define_prefix, id, prog_type_str, + ifindex); + } + } + + if (json_output) + jsonw_end_array(json_wtr); + else if (!define_prefix) { + printf("\n"); + if (!probe_res) { + if (!supported_type) + printf("\tProgram type not supported\n"); + else + printf("\tCould not determine which helpers are available\n"); + } + } + + +} + +static void +probe_misc_feature(struct bpf_insn *insns, size_t len, + const char *define_prefix, __u32 ifindex, + const char *feat_name, const char *plain_name, + const char *define_name) +{ + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .prog_ifindex = ifindex, + ); + bool res; + int fd; + + errno = 0; + fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", + insns, len, &opts); + res = fd >= 0 || !errno; + + if (fd >= 0) + close(fd); + + print_bool_feature(feat_name, plain_name, define_name, res, + define_prefix); +} + +/* + * Probe for availability of kernel commit (5.3): + * + * c04c0d2b968a ("bpf: increase complexity limit and maximum program size") + */ +static void probe_large_insn_limit(const char *define_prefix, __u32 ifindex) +{ + struct bpf_insn insns[BPF_MAXINSNS + 1]; + int i; + + for (i = 0; i < BPF_MAXINSNS; i++) + insns[i] = BPF_MOV64_IMM(BPF_REG_0, 1); + insns[BPF_MAXINSNS] = BPF_EXIT_INSN(); + + probe_misc_feature(insns, ARRAY_SIZE(insns), + define_prefix, ifindex, + "have_large_insn_limit", + "Large program size limit", + "LARGE_INSN_LIMIT"); +} + +/* + * Probe for bounded loop support introduced in commit 2589726d12a1 + * ("bpf: introduce bounded loops"). + */ +static void +probe_bounded_loops(const char *define_prefix, __u32 ifindex) +{ + struct bpf_insn insns[4] = { + BPF_MOV64_IMM(BPF_REG_0, 10), + BPF_ALU64_IMM(BPF_SUB, BPF_REG_0, 1), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, -2), + BPF_EXIT_INSN() + }; + + probe_misc_feature(insns, ARRAY_SIZE(insns), + define_prefix, ifindex, + "have_bounded_loops", + "Bounded loop support", + "BOUNDED_LOOPS"); +} + +/* + * Probe for the v2 instruction set extension introduced in commit 92b31a9af73b + * ("bpf: add BPF_J{LT,LE,SLT,SLE} instructions"). + */ +static void +probe_v2_isa_extension(const char *define_prefix, __u32 ifindex) +{ + struct bpf_insn insns[4] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 0, 1), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN() + }; + + probe_misc_feature(insns, ARRAY_SIZE(insns), + define_prefix, ifindex, + "have_v2_isa_extension", + "ISA extension v2", + "V2_ISA_EXTENSION"); +} + +/* + * Probe for the v3 instruction set extension introduced in commit 092ed0968bb6 + * ("bpf: verifier support JMP32"). + */ +static void +probe_v3_isa_extension(const char *define_prefix, __u32 ifindex) +{ + struct bpf_insn insns[4] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP32_IMM(BPF_JLT, BPF_REG_0, 0, 1), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN() + }; + + probe_misc_feature(insns, ARRAY_SIZE(insns), + define_prefix, ifindex, + "have_v3_isa_extension", + "ISA extension v3", + "V3_ISA_EXTENSION"); +} + +static void +section_system_config(enum probe_component target, const char *define_prefix) +{ + switch (target) { + case COMPONENT_KERNEL: + case COMPONENT_UNSPEC: + print_start_section("system_config", + "Scanning system configuration...", + "/*** Misc kernel config items ***/", + define_prefix); + if (!define_prefix) { + if (check_procfs()) { + probe_unprivileged_disabled(); + probe_jit_enable(); + probe_jit_harden(); + probe_jit_kallsyms(); + probe_jit_limit(); + } else { + p_info("/* procfs not mounted, skipping related probes */"); + } + } + probe_kernel_image_config(define_prefix); + print_end_section(); + break; + default: + break; + } +} + +static bool section_syscall_config(const char *define_prefix) +{ + bool res; + + print_start_section("syscall_config", + "Scanning system call availability...", + "/*** System call availability ***/", + define_prefix); + res = probe_bpf_syscall(define_prefix); + print_end_section(); + + return res; +} + +static void +section_program_types(bool *supported_types, const char *define_prefix, + __u32 ifindex) +{ + unsigned int prog_type = BPF_PROG_TYPE_UNSPEC; + const char *prog_type_str; + + print_start_section("program_types", + "Scanning eBPF program types...", + "/*** eBPF program types ***/", + define_prefix); + + while (true) { + prog_type++; + prog_type_str = libbpf_bpf_prog_type_str(prog_type); + /* libbpf will return NULL for variants unknown to it. */ + if (!prog_type_str) + break; + + probe_prog_type(prog_type, prog_type_str, supported_types, define_prefix, + ifindex); + } + + print_end_section(); +} + +static void section_map_types(const char *define_prefix, __u32 ifindex) +{ + unsigned int map_type = BPF_MAP_TYPE_UNSPEC; + const char *map_type_str; + + print_start_section("map_types", + "Scanning eBPF map types...", + "/*** eBPF map types ***/", + define_prefix); + + while (true) { + map_type++; + map_type_str = libbpf_bpf_map_type_str(map_type); + /* libbpf will return NULL for variants unknown to it. */ + if (!map_type_str) + break; + + probe_map_type(map_type, map_type_str, define_prefix, ifindex); + } + + print_end_section(); +} + +static void +section_helpers(bool *supported_types, const char *define_prefix, __u32 ifindex) +{ + unsigned int prog_type = BPF_PROG_TYPE_UNSPEC; + const char *prog_type_str; + + print_start_section("helpers", + "Scanning eBPF helper functions...", + "/*** eBPF helper functions ***/", + define_prefix); + + if (define_prefix) + printf("/*\n" + " * Use %sHAVE_PROG_TYPE_HELPER(prog_type_name, helper_name)\n" + " * to determine if <helper_name> is available for <prog_type_name>,\n" + " * e.g.\n" + " * #if %sHAVE_PROG_TYPE_HELPER(xdp, bpf_redirect)\n" + " * // do stuff with this helper\n" + " * #elif\n" + " * // use a workaround\n" + " * #endif\n" + " */\n" + "#define %sHAVE_PROG_TYPE_HELPER(prog_type, helper) \\\n" + " %sBPF__PROG_TYPE_ ## prog_type ## __HELPER_ ## helper\n", + define_prefix, define_prefix, define_prefix, + define_prefix); + while (true) { + prog_type++; + prog_type_str = libbpf_bpf_prog_type_str(prog_type); + /* libbpf will return NULL for variants unknown to it. */ + if (!prog_type_str) + break; + + probe_helpers_for_progtype(prog_type, prog_type_str, + supported_types[prog_type], + define_prefix, + ifindex); + } + + print_end_section(); +} + +static void section_misc(const char *define_prefix, __u32 ifindex) +{ + print_start_section("misc", + "Scanning miscellaneous eBPF features...", + "/*** eBPF misc features ***/", + define_prefix); + probe_large_insn_limit(define_prefix, ifindex); + probe_bounded_loops(define_prefix, ifindex); + probe_v2_isa_extension(define_prefix, ifindex); + probe_v3_isa_extension(define_prefix, ifindex); + print_end_section(); +} + +#ifdef USE_LIBCAP +#define capability(c) { c, false, #c } +#define capability_msg(a, i) a[i].set ? "" : a[i].name, a[i].set ? "" : ", " +#endif + +static int handle_perms(void) +{ +#ifdef USE_LIBCAP + struct { + cap_value_t cap; + bool set; + char name[14]; /* strlen("CAP_SYS_ADMIN") */ + } bpf_caps[] = { + capability(CAP_SYS_ADMIN), +#ifdef CAP_BPF + capability(CAP_BPF), + capability(CAP_NET_ADMIN), + capability(CAP_PERFMON), +#endif + }; + cap_value_t cap_list[ARRAY_SIZE(bpf_caps)]; + unsigned int i, nb_bpf_caps = 0; + bool cap_sys_admin_only = true; + cap_flag_value_t val; + int res = -1; + cap_t caps; + + caps = cap_get_proc(); + if (!caps) { + p_err("failed to get capabilities for process: %s", + strerror(errno)); + return -1; + } + +#ifdef CAP_BPF + if (CAP_IS_SUPPORTED(CAP_BPF)) + cap_sys_admin_only = false; +#endif + + for (i = 0; i < ARRAY_SIZE(bpf_caps); i++) { + const char *cap_name = bpf_caps[i].name; + cap_value_t cap = bpf_caps[i].cap; + + if (cap_get_flag(caps, cap, CAP_EFFECTIVE, &val)) { + p_err("bug: failed to retrieve %s status: %s", cap_name, + strerror(errno)); + goto exit_free; + } + + if (val == CAP_SET) { + bpf_caps[i].set = true; + cap_list[nb_bpf_caps++] = cap; + } + + if (cap_sys_admin_only) + /* System does not know about CAP_BPF, meaning that + * CAP_SYS_ADMIN is the only capability required. We + * just checked it, break. + */ + break; + } + + if ((run_as_unprivileged && !nb_bpf_caps) || + (!run_as_unprivileged && nb_bpf_caps == ARRAY_SIZE(bpf_caps)) || + (!run_as_unprivileged && cap_sys_admin_only && nb_bpf_caps)) { + /* We are all good, exit now */ + res = 0; + goto exit_free; + } + + if (!run_as_unprivileged) { + if (cap_sys_admin_only) + p_err("missing %s, required for full feature probing; run as root or use 'unprivileged'", + bpf_caps[0].name); + else + p_err("missing %s%s%s%s%s%s%s%srequired for full feature probing; run as root or use 'unprivileged'", + capability_msg(bpf_caps, 0), +#ifdef CAP_BPF + capability_msg(bpf_caps, 1), + capability_msg(bpf_caps, 2), + capability_msg(bpf_caps, 3) +#else + "", "", "", "", "", "" +#endif /* CAP_BPF */ + ); + goto exit_free; + } + + /* if (run_as_unprivileged && nb_bpf_caps > 0), drop capabilities. */ + if (cap_set_flag(caps, CAP_EFFECTIVE, nb_bpf_caps, cap_list, + CAP_CLEAR)) { + p_err("bug: failed to clear capabilities: %s", strerror(errno)); + goto exit_free; + } + + if (cap_set_proc(caps)) { + p_err("failed to drop capabilities: %s", strerror(errno)); + goto exit_free; + } + + res = 0; + +exit_free: + if (cap_free(caps) && !res) { + p_err("failed to clear storage object for capabilities: %s", + strerror(errno)); + res = -1; + } + + return res; +#else + /* Detection assumes user has specific privileges. + * We do not use libcap so let's approximate, and restrict usage to + * root user only. + */ + if (geteuid()) { + p_err("full feature probing requires root privileges"); + return -1; + } + + return 0; +#endif /* USE_LIBCAP */ +} + +static int do_probe(int argc, char **argv) +{ + enum probe_component target = COMPONENT_UNSPEC; + const char *define_prefix = NULL; + bool supported_types[128] = {}; + __u32 ifindex = 0; + char *ifname; + + set_max_rlimit(); + + while (argc) { + if (is_prefix(*argv, "kernel")) { + if (target != COMPONENT_UNSPEC) { + p_err("component to probe already specified"); + return -1; + } + target = COMPONENT_KERNEL; + NEXT_ARG(); + } else if (is_prefix(*argv, "dev")) { + NEXT_ARG(); + + if (target != COMPONENT_UNSPEC || ifindex) { + p_err("component to probe already specified"); + return -1; + } + if (!REQ_ARGS(1)) + return -1; + + target = COMPONENT_DEVICE; + ifname = GET_ARG(); + ifindex = if_nametoindex(ifname); + if (!ifindex) { + p_err("unrecognized netdevice '%s': %s", ifname, + strerror(errno)); + return -1; + } + } else if (is_prefix(*argv, "full")) { + full_mode = true; + NEXT_ARG(); + } else if (is_prefix(*argv, "macros") && !define_prefix) { + define_prefix = ""; + NEXT_ARG(); + } else if (is_prefix(*argv, "prefix")) { + if (!define_prefix) { + p_err("'prefix' argument can only be use after 'macros'"); + return -1; + } + if (strcmp(define_prefix, "")) { + p_err("'prefix' already defined"); + return -1; + } + NEXT_ARG(); + + if (!REQ_ARGS(1)) + return -1; + define_prefix = GET_ARG(); + } else if (is_prefix(*argv, "unprivileged")) { +#ifdef USE_LIBCAP + run_as_unprivileged = true; + NEXT_ARG(); +#else + p_err("unprivileged run not supported, recompile bpftool with libcap"); + return -1; +#endif + } else { + p_err("expected no more arguments, 'kernel', 'dev', 'macros' or 'prefix', got: '%s'?", + *argv); + return -1; + } + } + + /* Full feature detection requires specific privileges. + * Let's approximate, and warn if user is not root. + */ + if (handle_perms()) + return -1; + + if (json_output) { + define_prefix = NULL; + jsonw_start_object(json_wtr); + } + + section_system_config(target, define_prefix); + if (!section_syscall_config(define_prefix)) + /* bpf() syscall unavailable, don't probe other BPF features */ + goto exit_close_json; + section_program_types(supported_types, define_prefix, ifindex); + section_map_types(define_prefix, ifindex); + section_helpers(supported_types, define_prefix, ifindex); + section_misc(define_prefix, ifindex); + +exit_close_json: + if (json_output) + /* End root object */ + jsonw_end_object(json_wtr); + + return 0; +} + +static const char *get_helper_name(unsigned int id) +{ + if (id >= ARRAY_SIZE(helper_name)) + return NULL; + + return helper_name[id]; +} + +static int do_list_builtins(int argc, char **argv) +{ + const char *(*get_name)(unsigned int id); + unsigned int id = 0; + + if (argc < 1) + usage(); + + if (is_prefix(*argv, "prog_types")) { + get_name = (const char *(*)(unsigned int))libbpf_bpf_prog_type_str; + } else if (is_prefix(*argv, "map_types")) { + get_name = (const char *(*)(unsigned int))libbpf_bpf_map_type_str; + } else if (is_prefix(*argv, "attach_types")) { + get_name = (const char *(*)(unsigned int))libbpf_bpf_attach_type_str; + } else if (is_prefix(*argv, "link_types")) { + get_name = (const char *(*)(unsigned int))libbpf_bpf_link_type_str; + } else if (is_prefix(*argv, "helpers")) { + get_name = get_helper_name; + } else { + p_err("expected 'prog_types', 'map_types', 'attach_types', 'link_types' or 'helpers', got: %s", *argv); + return -1; + } + + if (json_output) + jsonw_start_array(json_wtr); /* root array */ + + while (true) { + const char *name; + + name = get_name(id++); + if (!name) + break; + if (json_output) + jsonw_string(json_wtr, name); + else + printf("%s\n", name); + } + + if (json_output) + jsonw_end_array(json_wtr); /* root array */ + + return 0; +} + +static int do_help(int argc, char **argv) +{ + if (json_output) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %1$s %2$s probe [COMPONENT] [full] [unprivileged] [macros [prefix PREFIX]]\n" + " %1$s %2$s list_builtins GROUP\n" + " %1$s %2$s help\n" + "\n" + " COMPONENT := { kernel | dev NAME }\n" + " GROUP := { prog_types | map_types | attach_types | link_types | helpers }\n" + " " HELP_SPEC_OPTIONS " }\n" + "", + bin_name, argv[-2]); + + return 0; +} + +static const struct cmd cmds[] = { + { "probe", do_probe }, + { "list_builtins", do_list_builtins }, + { "help", do_help }, + { 0 } +}; + +int do_feature(int argc, char **argv) +{ + return cmd_select(cmds, argc, argv, do_help); +} diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c new file mode 100644 index 000000000..cf8b4e525 --- /dev/null +++ b/tools/bpf/bpftool/gen.c @@ -0,0 +1,2340 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2019 Facebook */ + +#ifndef _GNU_SOURCE +#define _GNU_SOURCE +#endif +#include <ctype.h> +#include <errno.h> +#include <fcntl.h> +#include <linux/err.h> +#include <stdbool.h> +#include <stdio.h> +#include <string.h> +#include <unistd.h> +#include <bpf/bpf.h> +#include <bpf/libbpf.h> +#include <bpf/libbpf_internal.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <sys/mman.h> +#include <bpf/btf.h> + +#include "json_writer.h" +#include "main.h" + +#define MAX_OBJ_NAME_LEN 64 + +static void sanitize_identifier(char *name) +{ + int i; + + for (i = 0; name[i]; i++) + if (!isalnum(name[i]) && name[i] != '_') + name[i] = '_'; +} + +static bool str_has_prefix(const char *str, const char *prefix) +{ + return strncmp(str, prefix, strlen(prefix)) == 0; +} + +static bool str_has_suffix(const char *str, const char *suffix) +{ + size_t i, n1 = strlen(str), n2 = strlen(suffix); + + if (n1 < n2) + return false; + + for (i = 0; i < n2; i++) { + if (str[n1 - i - 1] != suffix[n2 - i - 1]) + return false; + } + + return true; +} + +static void get_obj_name(char *name, const char *file) +{ + /* Using basename() GNU version which doesn't modify arg. */ + strncpy(name, basename(file), MAX_OBJ_NAME_LEN - 1); + name[MAX_OBJ_NAME_LEN - 1] = '\0'; + if (str_has_suffix(name, ".o")) + name[strlen(name) - 2] = '\0'; + sanitize_identifier(name); +} + +static void get_header_guard(char *guard, const char *obj_name, const char *suffix) +{ + int i; + + sprintf(guard, "__%s_%s__", obj_name, suffix); + for (i = 0; guard[i]; i++) + guard[i] = toupper(guard[i]); +} + +static bool get_map_ident(const struct bpf_map *map, char *buf, size_t buf_sz) +{ + static const char *sfxs[] = { ".data", ".rodata", ".bss", ".kconfig" }; + const char *name = bpf_map__name(map); + int i, n; + + if (!bpf_map__is_internal(map)) { + snprintf(buf, buf_sz, "%s", name); + return true; + } + + for (i = 0, n = ARRAY_SIZE(sfxs); i < n; i++) { + const char *sfx = sfxs[i], *p; + + p = strstr(name, sfx); + if (p) { + snprintf(buf, buf_sz, "%s", p + 1); + sanitize_identifier(buf); + return true; + } + } + + return false; +} + +static bool get_datasec_ident(const char *sec_name, char *buf, size_t buf_sz) +{ + static const char *pfxs[] = { ".data", ".rodata", ".bss", ".kconfig" }; + int i, n; + + for (i = 0, n = ARRAY_SIZE(pfxs); i < n; i++) { + const char *pfx = pfxs[i]; + + if (str_has_prefix(sec_name, pfx)) { + snprintf(buf, buf_sz, "%s", sec_name + 1); + sanitize_identifier(buf); + return true; + } + } + + return false; +} + +static void codegen_btf_dump_printf(void *ctx, const char *fmt, va_list args) +{ + vprintf(fmt, args); +} + +static int codegen_datasec_def(struct bpf_object *obj, + struct btf *btf, + struct btf_dump *d, + const struct btf_type *sec, + const char *obj_name) +{ + const char *sec_name = btf__name_by_offset(btf, sec->name_off); + const struct btf_var_secinfo *sec_var = btf_var_secinfos(sec); + int i, err, off = 0, pad_cnt = 0, vlen = btf_vlen(sec); + char var_ident[256], sec_ident[256]; + bool strip_mods = false; + + if (!get_datasec_ident(sec_name, sec_ident, sizeof(sec_ident))) + return 0; + + if (strcmp(sec_name, ".kconfig") != 0) + strip_mods = true; + + printf(" struct %s__%s {\n", obj_name, sec_ident); + for (i = 0; i < vlen; i++, sec_var++) { + const struct btf_type *var = btf__type_by_id(btf, sec_var->type); + const char *var_name = btf__name_by_offset(btf, var->name_off); + DECLARE_LIBBPF_OPTS(btf_dump_emit_type_decl_opts, opts, + .field_name = var_ident, + .indent_level = 2, + .strip_mods = strip_mods, + ); + int need_off = sec_var->offset, align_off, align; + __u32 var_type_id = var->type; + + /* static variables are not exposed through BPF skeleton */ + if (btf_var(var)->linkage == BTF_VAR_STATIC) + continue; + + if (off > need_off) { + p_err("Something is wrong for %s's variable #%d: need offset %d, already at %d.\n", + sec_name, i, need_off, off); + return -EINVAL; + } + + align = btf__align_of(btf, var->type); + if (align <= 0) { + p_err("Failed to determine alignment of variable '%s': %d", + var_name, align); + return -EINVAL; + } + /* Assume 32-bit architectures when generating data section + * struct memory layout. Given bpftool can't know which target + * host architecture it's emitting skeleton for, we need to be + * conservative and assume 32-bit one to ensure enough padding + * bytes are generated for pointer and long types. This will + * still work correctly for 64-bit architectures, because in + * the worst case we'll generate unnecessary padding field, + * which on 64-bit architectures is not strictly necessary and + * would be handled by natural 8-byte alignment. But it still + * will be a correct memory layout, based on recorded offsets + * in BTF. + */ + if (align > 4) + align = 4; + + align_off = (off + align - 1) / align * align; + if (align_off != need_off) { + printf("\t\tchar __pad%d[%d];\n", + pad_cnt, need_off - off); + pad_cnt++; + } + + /* sanitize variable name, e.g., for static vars inside + * a function, it's name is '<function name>.<variable name>', + * which we'll turn into a '<function name>_<variable name>' + */ + var_ident[0] = '\0'; + strncat(var_ident, var_name, sizeof(var_ident) - 1); + sanitize_identifier(var_ident); + + printf("\t\t"); + err = btf_dump__emit_type_decl(d, var_type_id, &opts); + if (err) + return err; + printf(";\n"); + + off = sec_var->offset + sec_var->size; + } + printf(" } *%s;\n", sec_ident); + return 0; +} + +static const struct btf_type *find_type_for_map(struct btf *btf, const char *map_ident) +{ + int n = btf__type_cnt(btf), i; + char sec_ident[256]; + + for (i = 1; i < n; i++) { + const struct btf_type *t = btf__type_by_id(btf, i); + const char *name; + + if (!btf_is_datasec(t)) + continue; + + name = btf__str_by_offset(btf, t->name_off); + if (!get_datasec_ident(name, sec_ident, sizeof(sec_ident))) + continue; + + if (strcmp(sec_ident, map_ident) == 0) + return t; + } + return NULL; +} + +static bool is_internal_mmapable_map(const struct bpf_map *map, char *buf, size_t sz) +{ + if (!bpf_map__is_internal(map) || !(bpf_map__map_flags(map) & BPF_F_MMAPABLE)) + return false; + + if (!get_map_ident(map, buf, sz)) + return false; + + return true; +} + +static int codegen_datasecs(struct bpf_object *obj, const char *obj_name) +{ + struct btf *btf = bpf_object__btf(obj); + struct btf_dump *d; + struct bpf_map *map; + const struct btf_type *sec; + char map_ident[256]; + int err = 0; + + d = btf_dump__new(btf, codegen_btf_dump_printf, NULL, NULL); + err = libbpf_get_error(d); + if (err) + return err; + + bpf_object__for_each_map(map, obj) { + /* only generate definitions for memory-mapped internal maps */ + if (!is_internal_mmapable_map(map, map_ident, sizeof(map_ident))) + continue; + + sec = find_type_for_map(btf, map_ident); + + /* In some cases (e.g., sections like .rodata.cst16 containing + * compiler allocated string constants only) there will be + * special internal maps with no corresponding DATASEC BTF + * type. In such case, generate empty structs for each such + * map. It will still be memory-mapped and its contents + * accessible from user-space through BPF skeleton. + */ + if (!sec) { + printf(" struct %s__%s {\n", obj_name, map_ident); + printf(" } *%s;\n", map_ident); + } else { + err = codegen_datasec_def(obj, btf, d, sec, obj_name); + if (err) + goto out; + } + } + + +out: + btf_dump__free(d); + return err; +} + +static bool btf_is_ptr_to_func_proto(const struct btf *btf, + const struct btf_type *v) +{ + return btf_is_ptr(v) && btf_is_func_proto(btf__type_by_id(btf, v->type)); +} + +static int codegen_subskel_datasecs(struct bpf_object *obj, const char *obj_name) +{ + struct btf *btf = bpf_object__btf(obj); + struct btf_dump *d; + struct bpf_map *map; + const struct btf_type *sec, *var; + const struct btf_var_secinfo *sec_var; + int i, err = 0, vlen; + char map_ident[256], sec_ident[256]; + bool strip_mods = false, needs_typeof = false; + const char *sec_name, *var_name; + __u32 var_type_id; + + d = btf_dump__new(btf, codegen_btf_dump_printf, NULL, NULL); + if (!d) + return -errno; + + bpf_object__for_each_map(map, obj) { + /* only generate definitions for memory-mapped internal maps */ + if (!is_internal_mmapable_map(map, map_ident, sizeof(map_ident))) + continue; + + sec = find_type_for_map(btf, map_ident); + if (!sec) + continue; + + sec_name = btf__name_by_offset(btf, sec->name_off); + if (!get_datasec_ident(sec_name, sec_ident, sizeof(sec_ident))) + continue; + + strip_mods = strcmp(sec_name, ".kconfig") != 0; + printf(" struct %s__%s {\n", obj_name, sec_ident); + + sec_var = btf_var_secinfos(sec); + vlen = btf_vlen(sec); + for (i = 0; i < vlen; i++, sec_var++) { + DECLARE_LIBBPF_OPTS(btf_dump_emit_type_decl_opts, opts, + .indent_level = 2, + .strip_mods = strip_mods, + /* we'll print the name separately */ + .field_name = "", + ); + + var = btf__type_by_id(btf, sec_var->type); + var_name = btf__name_by_offset(btf, var->name_off); + var_type_id = var->type; + + /* static variables are not exposed through BPF skeleton */ + if (btf_var(var)->linkage == BTF_VAR_STATIC) + continue; + + /* The datasec member has KIND_VAR but we want the + * underlying type of the variable (e.g. KIND_INT). + */ + var = skip_mods_and_typedefs(btf, var->type, NULL); + + printf("\t\t"); + /* Func and array members require special handling. + * Instead of producing `typename *var`, they produce + * `typeof(typename) *var`. This allows us to keep a + * similar syntax where the identifier is just prefixed + * by *, allowing us to ignore C declaration minutiae. + */ + needs_typeof = btf_is_array(var) || btf_is_ptr_to_func_proto(btf, var); + if (needs_typeof) + printf("typeof("); + + err = btf_dump__emit_type_decl(d, var_type_id, &opts); + if (err) + goto out; + + if (needs_typeof) + printf(")"); + + printf(" *%s;\n", var_name); + } + printf(" } %s;\n", sec_ident); + } + +out: + btf_dump__free(d); + return err; +} + +static void codegen(const char *template, ...) +{ + const char *src, *end; + int skip_tabs = 0, n; + char *s, *dst; + va_list args; + char c; + + n = strlen(template); + s = malloc(n + 1); + if (!s) + exit(-1); + src = template; + dst = s; + + /* find out "baseline" indentation to skip */ + while ((c = *src++)) { + if (c == '\t') { + skip_tabs++; + } else if (c == '\n') { + break; + } else { + p_err("unrecognized character at pos %td in template '%s': '%c'", + src - template - 1, template, c); + free(s); + exit(-1); + } + } + + while (*src) { + /* skip baseline indentation tabs */ + for (n = skip_tabs; n > 0; n--, src++) { + if (*src != '\t') { + p_err("not enough tabs at pos %td in template '%s'", + src - template - 1, template); + free(s); + exit(-1); + } + } + /* trim trailing whitespace */ + end = strchrnul(src, '\n'); + for (n = end - src; n > 0 && isspace(src[n - 1]); n--) + ; + memcpy(dst, src, n); + dst += n; + if (*end) + *dst++ = '\n'; + src = *end ? end + 1 : end; + } + *dst++ = '\0'; + + /* print out using adjusted template */ + va_start(args, template); + n = vprintf(s, args); + va_end(args); + + free(s); +} + +static void print_hex(const char *data, int data_sz) +{ + int i, len; + + for (i = 0, len = 0; i < data_sz; i++) { + int w = data[i] ? 4 : 2; + + len += w; + if (len > 78) { + printf("\\\n"); + len = w; + } + if (!data[i]) + printf("\\0"); + else + printf("\\x%02x", (unsigned char)data[i]); + } +} + +static size_t bpf_map_mmap_sz(const struct bpf_map *map) +{ + long page_sz = sysconf(_SC_PAGE_SIZE); + size_t map_sz; + + map_sz = (size_t)roundup(bpf_map__value_size(map), 8) * bpf_map__max_entries(map); + map_sz = roundup(map_sz, page_sz); + return map_sz; +} + +/* Emit type size asserts for all top-level fields in memory-mapped internal maps. */ +static void codegen_asserts(struct bpf_object *obj, const char *obj_name) +{ + struct btf *btf = bpf_object__btf(obj); + struct bpf_map *map; + struct btf_var_secinfo *sec_var; + int i, vlen; + const struct btf_type *sec; + char map_ident[256], var_ident[256]; + + if (!btf) + return; + + codegen("\ + \n\ + __attribute__((unused)) static void \n\ + %1$s__assert(struct %1$s *s __attribute__((unused))) \n\ + { \n\ + #ifdef __cplusplus \n\ + #define _Static_assert static_assert \n\ + #endif \n\ + ", obj_name); + + bpf_object__for_each_map(map, obj) { + if (!is_internal_mmapable_map(map, map_ident, sizeof(map_ident))) + continue; + + sec = find_type_for_map(btf, map_ident); + if (!sec) { + /* best effort, couldn't find the type for this map */ + continue; + } + + sec_var = btf_var_secinfos(sec); + vlen = btf_vlen(sec); + + for (i = 0; i < vlen; i++, sec_var++) { + const struct btf_type *var = btf__type_by_id(btf, sec_var->type); + const char *var_name = btf__name_by_offset(btf, var->name_off); + long var_size; + + /* static variables are not exposed through BPF skeleton */ + if (btf_var(var)->linkage == BTF_VAR_STATIC) + continue; + + var_size = btf__resolve_size(btf, var->type); + if (var_size < 0) + continue; + + var_ident[0] = '\0'; + strncat(var_ident, var_name, sizeof(var_ident) - 1); + sanitize_identifier(var_ident); + + printf("\t_Static_assert(sizeof(s->%s->%s) == %ld, \"unexpected size of '%s'\");\n", + map_ident, var_ident, var_size, var_ident); + } + } + codegen("\ + \n\ + #ifdef __cplusplus \n\ + #undef _Static_assert \n\ + #endif \n\ + } \n\ + "); +} + +static void codegen_attach_detach(struct bpf_object *obj, const char *obj_name) +{ + struct bpf_program *prog; + + bpf_object__for_each_program(prog, obj) { + const char *tp_name; + + codegen("\ + \n\ + \n\ + static inline int \n\ + %1$s__%2$s__attach(struct %1$s *skel) \n\ + { \n\ + int prog_fd = skel->progs.%2$s.prog_fd; \n\ + ", obj_name, bpf_program__name(prog)); + + switch (bpf_program__type(prog)) { + case BPF_PROG_TYPE_RAW_TRACEPOINT: + tp_name = strchr(bpf_program__section_name(prog), '/') + 1; + printf("\tint fd = skel_raw_tracepoint_open(\"%s\", prog_fd);\n", tp_name); + break; + case BPF_PROG_TYPE_TRACING: + case BPF_PROG_TYPE_LSM: + if (bpf_program__expected_attach_type(prog) == BPF_TRACE_ITER) + printf("\tint fd = skel_link_create(prog_fd, 0, BPF_TRACE_ITER);\n"); + else + printf("\tint fd = skel_raw_tracepoint_open(NULL, prog_fd);\n"); + break; + default: + printf("\tint fd = ((void)prog_fd, 0); /* auto-attach not supported */\n"); + break; + } + codegen("\ + \n\ + \n\ + if (fd > 0) \n\ + skel->links.%1$s_fd = fd; \n\ + return fd; \n\ + } \n\ + ", bpf_program__name(prog)); + } + + codegen("\ + \n\ + \n\ + static inline int \n\ + %1$s__attach(struct %1$s *skel) \n\ + { \n\ + int ret = 0; \n\ + \n\ + ", obj_name); + + bpf_object__for_each_program(prog, obj) { + codegen("\ + \n\ + ret = ret < 0 ? ret : %1$s__%2$s__attach(skel); \n\ + ", obj_name, bpf_program__name(prog)); + } + + codegen("\ + \n\ + return ret < 0 ? ret : 0; \n\ + } \n\ + \n\ + static inline void \n\ + %1$s__detach(struct %1$s *skel) \n\ + { \n\ + ", obj_name); + + bpf_object__for_each_program(prog, obj) { + codegen("\ + \n\ + skel_closenz(skel->links.%1$s_fd); \n\ + ", bpf_program__name(prog)); + } + + codegen("\ + \n\ + } \n\ + "); +} + +static void codegen_destroy(struct bpf_object *obj, const char *obj_name) +{ + struct bpf_program *prog; + struct bpf_map *map; + char ident[256]; + + codegen("\ + \n\ + static void \n\ + %1$s__destroy(struct %1$s *skel) \n\ + { \n\ + if (!skel) \n\ + return; \n\ + %1$s__detach(skel); \n\ + ", + obj_name); + + bpf_object__for_each_program(prog, obj) { + codegen("\ + \n\ + skel_closenz(skel->progs.%1$s.prog_fd); \n\ + ", bpf_program__name(prog)); + } + + bpf_object__for_each_map(map, obj) { + if (!get_map_ident(map, ident, sizeof(ident))) + continue; + if (bpf_map__is_internal(map) && + (bpf_map__map_flags(map) & BPF_F_MMAPABLE)) + printf("\tskel_free_map_data(skel->%1$s, skel->maps.%1$s.initial_value, %2$zd);\n", + ident, bpf_map_mmap_sz(map)); + codegen("\ + \n\ + skel_closenz(skel->maps.%1$s.map_fd); \n\ + ", ident); + } + codegen("\ + \n\ + skel_free(skel); \n\ + } \n\ + ", + obj_name); +} + +static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *header_guard) +{ + DECLARE_LIBBPF_OPTS(gen_loader_opts, opts); + struct bpf_map *map; + char ident[256]; + int err = 0; + + err = bpf_object__gen_loader(obj, &opts); + if (err) + return err; + + err = bpf_object__load(obj); + if (err) { + p_err("failed to load object file"); + goto out; + } + /* If there was no error during load then gen_loader_opts + * are populated with the loader program. + */ + + /* finish generating 'struct skel' */ + codegen("\ + \n\ + }; \n\ + ", obj_name); + + + codegen_attach_detach(obj, obj_name); + + codegen_destroy(obj, obj_name); + + codegen("\ + \n\ + static inline struct %1$s * \n\ + %1$s__open(void) \n\ + { \n\ + struct %1$s *skel; \n\ + \n\ + skel = skel_alloc(sizeof(*skel)); \n\ + if (!skel) \n\ + goto cleanup; \n\ + skel->ctx.sz = (void *)&skel->links - (void *)skel; \n\ + ", + obj_name, opts.data_sz); + bpf_object__for_each_map(map, obj) { + const void *mmap_data = NULL; + size_t mmap_size = 0; + + if (!is_internal_mmapable_map(map, ident, sizeof(ident))) + continue; + + codegen("\ + \n\ + skel->%1$s = skel_prep_map_data((void *)\"\\ \n\ + ", ident); + mmap_data = bpf_map__initial_value(map, &mmap_size); + print_hex(mmap_data, mmap_size); + codegen("\ + \n\ + \", %1$zd, %2$zd); \n\ + if (!skel->%3$s) \n\ + goto cleanup; \n\ + skel->maps.%3$s.initial_value = (__u64) (long) skel->%3$s;\n\ + ", bpf_map_mmap_sz(map), mmap_size, ident); + } + codegen("\ + \n\ + return skel; \n\ + cleanup: \n\ + %1$s__destroy(skel); \n\ + return NULL; \n\ + } \n\ + \n\ + static inline int \n\ + %1$s__load(struct %1$s *skel) \n\ + { \n\ + struct bpf_load_and_run_opts opts = {}; \n\ + int err; \n\ + \n\ + opts.ctx = (struct bpf_loader_ctx *)skel; \n\ + opts.data_sz = %2$d; \n\ + opts.data = (void *)\"\\ \n\ + ", + obj_name, opts.data_sz); + print_hex(opts.data, opts.data_sz); + codegen("\ + \n\ + \"; \n\ + "); + + codegen("\ + \n\ + opts.insns_sz = %d; \n\ + opts.insns = (void *)\"\\ \n\ + ", + opts.insns_sz); + print_hex(opts.insns, opts.insns_sz); + codegen("\ + \n\ + \"; \n\ + err = bpf_load_and_run(&opts); \n\ + if (err < 0) \n\ + return err; \n\ + ", obj_name); + bpf_object__for_each_map(map, obj) { + const char *mmap_flags; + + if (!is_internal_mmapable_map(map, ident, sizeof(ident))) + continue; + + if (bpf_map__map_flags(map) & BPF_F_RDONLY_PROG) + mmap_flags = "PROT_READ"; + else + mmap_flags = "PROT_READ | PROT_WRITE"; + + codegen("\ + \n\ + skel->%1$s = skel_finalize_map_data(&skel->maps.%1$s.initial_value, \n\ + %2$zd, %3$s, skel->maps.%1$s.map_fd);\n\ + if (!skel->%1$s) \n\ + return -ENOMEM; \n\ + ", + ident, bpf_map_mmap_sz(map), mmap_flags); + } + codegen("\ + \n\ + return 0; \n\ + } \n\ + \n\ + static inline struct %1$s * \n\ + %1$s__open_and_load(void) \n\ + { \n\ + struct %1$s *skel; \n\ + \n\ + skel = %1$s__open(); \n\ + if (!skel) \n\ + return NULL; \n\ + if (%1$s__load(skel)) { \n\ + %1$s__destroy(skel); \n\ + return NULL; \n\ + } \n\ + return skel; \n\ + } \n\ + \n\ + ", obj_name); + + codegen_asserts(obj, obj_name); + + codegen("\ + \n\ + \n\ + #endif /* %s */ \n\ + ", + header_guard); + err = 0; +out: + return err; +} + +static void +codegen_maps_skeleton(struct bpf_object *obj, size_t map_cnt, bool mmaped) +{ + struct bpf_map *map; + char ident[256]; + size_t i; + + if (!map_cnt) + return; + + codegen("\ + \n\ + \n\ + /* maps */ \n\ + s->map_cnt = %zu; \n\ + s->map_skel_sz = sizeof(*s->maps); \n\ + s->maps = (struct bpf_map_skeleton *)calloc(s->map_cnt, s->map_skel_sz);\n\ + if (!s->maps) { \n\ + err = -ENOMEM; \n\ + goto err; \n\ + } \n\ + ", + map_cnt + ); + i = 0; + bpf_object__for_each_map(map, obj) { + if (!get_map_ident(map, ident, sizeof(ident))) + continue; + + codegen("\ + \n\ + \n\ + s->maps[%zu].name = \"%s\"; \n\ + s->maps[%zu].map = &obj->maps.%s; \n\ + ", + i, bpf_map__name(map), i, ident); + /* memory-mapped internal maps */ + if (mmaped && is_internal_mmapable_map(map, ident, sizeof(ident))) { + printf("\ts->maps[%zu].mmaped = (void **)&obj->%s;\n", + i, ident); + } + i++; + } +} + +static void +codegen_progs_skeleton(struct bpf_object *obj, size_t prog_cnt, bool populate_links) +{ + struct bpf_program *prog; + int i; + + if (!prog_cnt) + return; + + codegen("\ + \n\ + \n\ + /* programs */ \n\ + s->prog_cnt = %zu; \n\ + s->prog_skel_sz = sizeof(*s->progs); \n\ + s->progs = (struct bpf_prog_skeleton *)calloc(s->prog_cnt, s->prog_skel_sz);\n\ + if (!s->progs) { \n\ + err = -ENOMEM; \n\ + goto err; \n\ + } \n\ + ", + prog_cnt + ); + i = 0; + bpf_object__for_each_program(prog, obj) { + codegen("\ + \n\ + \n\ + s->progs[%1$zu].name = \"%2$s\"; \n\ + s->progs[%1$zu].prog = &obj->progs.%2$s;\n\ + ", + i, bpf_program__name(prog)); + + if (populate_links) { + codegen("\ + \n\ + s->progs[%1$zu].link = &obj->links.%2$s;\n\ + ", + i, bpf_program__name(prog)); + } + i++; + } +} + +static int do_skeleton(int argc, char **argv) +{ + char header_guard[MAX_OBJ_NAME_LEN + sizeof("__SKEL_H__")]; + size_t map_cnt = 0, prog_cnt = 0, file_sz, mmap_sz; + DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts); + char obj_name[MAX_OBJ_NAME_LEN] = "", *obj_data; + struct bpf_object *obj = NULL; + const char *file; + char ident[256]; + struct bpf_program *prog; + int fd, err = -1; + struct bpf_map *map; + struct btf *btf; + struct stat st; + + if (!REQ_ARGS(1)) { + usage(); + return -1; + } + file = GET_ARG(); + + while (argc) { + if (!REQ_ARGS(2)) + return -1; + + if (is_prefix(*argv, "name")) { + NEXT_ARG(); + + if (obj_name[0] != '\0') { + p_err("object name already specified"); + return -1; + } + + strncpy(obj_name, *argv, MAX_OBJ_NAME_LEN - 1); + obj_name[MAX_OBJ_NAME_LEN - 1] = '\0'; + } else { + p_err("unknown arg %s", *argv); + return -1; + } + + NEXT_ARG(); + } + + if (argc) { + p_err("extra unknown arguments"); + return -1; + } + + if (stat(file, &st)) { + p_err("failed to stat() %s: %s", file, strerror(errno)); + return -1; + } + file_sz = st.st_size; + mmap_sz = roundup(file_sz, sysconf(_SC_PAGE_SIZE)); + fd = open(file, O_RDONLY); + if (fd < 0) { + p_err("failed to open() %s: %s", file, strerror(errno)); + return -1; + } + obj_data = mmap(NULL, mmap_sz, PROT_READ, MAP_PRIVATE, fd, 0); + if (obj_data == MAP_FAILED) { + obj_data = NULL; + p_err("failed to mmap() %s: %s", file, strerror(errno)); + goto out; + } + if (obj_name[0] == '\0') + get_obj_name(obj_name, file); + opts.object_name = obj_name; + if (verifier_logs) + /* log_level1 + log_level2 + stats, but not stable UAPI */ + opts.kernel_log_level = 1 + 2 + 4; + obj = bpf_object__open_mem(obj_data, file_sz, &opts); + err = libbpf_get_error(obj); + if (err) { + char err_buf[256]; + + libbpf_strerror(err, err_buf, sizeof(err_buf)); + p_err("failed to open BPF object file: %s", err_buf); + obj = NULL; + goto out; + } + + bpf_object__for_each_map(map, obj) { + if (!get_map_ident(map, ident, sizeof(ident))) { + p_err("ignoring unrecognized internal map '%s'...", + bpf_map__name(map)); + continue; + } + map_cnt++; + } + bpf_object__for_each_program(prog, obj) { + prog_cnt++; + } + + get_header_guard(header_guard, obj_name, "SKEL_H"); + if (use_loader) { + codegen("\ + \n\ + /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ \n\ + /* THIS FILE IS AUTOGENERATED BY BPFTOOL! */ \n\ + #ifndef %2$s \n\ + #define %2$s \n\ + \n\ + #include <bpf/skel_internal.h> \n\ + \n\ + struct %1$s { \n\ + struct bpf_loader_ctx ctx; \n\ + ", + obj_name, header_guard + ); + } else { + codegen("\ + \n\ + /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ \n\ + \n\ + /* THIS FILE IS AUTOGENERATED BY BPFTOOL! */ \n\ + #ifndef %2$s \n\ + #define %2$s \n\ + \n\ + #include <errno.h> \n\ + #include <stdlib.h> \n\ + #include <bpf/libbpf.h> \n\ + \n\ + struct %1$s { \n\ + struct bpf_object_skeleton *skeleton; \n\ + struct bpf_object *obj; \n\ + ", + obj_name, header_guard + ); + } + + if (map_cnt) { + printf("\tstruct {\n"); + bpf_object__for_each_map(map, obj) { + if (!get_map_ident(map, ident, sizeof(ident))) + continue; + if (use_loader) + printf("\t\tstruct bpf_map_desc %s;\n", ident); + else + printf("\t\tstruct bpf_map *%s;\n", ident); + } + printf("\t} maps;\n"); + } + + if (prog_cnt) { + printf("\tstruct {\n"); + bpf_object__for_each_program(prog, obj) { + if (use_loader) + printf("\t\tstruct bpf_prog_desc %s;\n", + bpf_program__name(prog)); + else + printf("\t\tstruct bpf_program *%s;\n", + bpf_program__name(prog)); + } + printf("\t} progs;\n"); + printf("\tstruct {\n"); + bpf_object__for_each_program(prog, obj) { + if (use_loader) + printf("\t\tint %s_fd;\n", + bpf_program__name(prog)); + else + printf("\t\tstruct bpf_link *%s;\n", + bpf_program__name(prog)); + } + printf("\t} links;\n"); + } + + btf = bpf_object__btf(obj); + if (btf) { + err = codegen_datasecs(obj, obj_name); + if (err) + goto out; + } + if (use_loader) { + err = gen_trace(obj, obj_name, header_guard); + goto out; + } + + codegen("\ + \n\ + \n\ + #ifdef __cplusplus \n\ + static inline struct %1$s *open(const struct bpf_object_open_opts *opts = nullptr);\n\ + static inline struct %1$s *open_and_load(); \n\ + static inline int load(struct %1$s *skel); \n\ + static inline int attach(struct %1$s *skel); \n\ + static inline void detach(struct %1$s *skel); \n\ + static inline void destroy(struct %1$s *skel); \n\ + static inline const void *elf_bytes(size_t *sz); \n\ + #endif /* __cplusplus */ \n\ + }; \n\ + \n\ + static void \n\ + %1$s__destroy(struct %1$s *obj) \n\ + { \n\ + if (!obj) \n\ + return; \n\ + if (obj->skeleton) \n\ + bpf_object__destroy_skeleton(obj->skeleton);\n\ + free(obj); \n\ + } \n\ + \n\ + static inline int \n\ + %1$s__create_skeleton(struct %1$s *obj); \n\ + \n\ + static inline struct %1$s * \n\ + %1$s__open_opts(const struct bpf_object_open_opts *opts) \n\ + { \n\ + struct %1$s *obj; \n\ + int err; \n\ + \n\ + obj = (struct %1$s *)calloc(1, sizeof(*obj)); \n\ + if (!obj) { \n\ + errno = ENOMEM; \n\ + return NULL; \n\ + } \n\ + \n\ + err = %1$s__create_skeleton(obj); \n\ + if (err) \n\ + goto err_out; \n\ + \n\ + err = bpf_object__open_skeleton(obj->skeleton, opts);\n\ + if (err) \n\ + goto err_out; \n\ + \n\ + return obj; \n\ + err_out: \n\ + %1$s__destroy(obj); \n\ + errno = -err; \n\ + return NULL; \n\ + } \n\ + \n\ + static inline struct %1$s * \n\ + %1$s__open(void) \n\ + { \n\ + return %1$s__open_opts(NULL); \n\ + } \n\ + \n\ + static inline int \n\ + %1$s__load(struct %1$s *obj) \n\ + { \n\ + return bpf_object__load_skeleton(obj->skeleton); \n\ + } \n\ + \n\ + static inline struct %1$s * \n\ + %1$s__open_and_load(void) \n\ + { \n\ + struct %1$s *obj; \n\ + int err; \n\ + \n\ + obj = %1$s__open(); \n\ + if (!obj) \n\ + return NULL; \n\ + err = %1$s__load(obj); \n\ + if (err) { \n\ + %1$s__destroy(obj); \n\ + errno = -err; \n\ + return NULL; \n\ + } \n\ + return obj; \n\ + } \n\ + \n\ + static inline int \n\ + %1$s__attach(struct %1$s *obj) \n\ + { \n\ + return bpf_object__attach_skeleton(obj->skeleton); \n\ + } \n\ + \n\ + static inline void \n\ + %1$s__detach(struct %1$s *obj) \n\ + { \n\ + bpf_object__detach_skeleton(obj->skeleton); \n\ + } \n\ + ", + obj_name + ); + + codegen("\ + \n\ + \n\ + static inline const void *%1$s__elf_bytes(size_t *sz); \n\ + \n\ + static inline int \n\ + %1$s__create_skeleton(struct %1$s *obj) \n\ + { \n\ + struct bpf_object_skeleton *s; \n\ + int err; \n\ + \n\ + s = (struct bpf_object_skeleton *)calloc(1, sizeof(*s));\n\ + if (!s) { \n\ + err = -ENOMEM; \n\ + goto err; \n\ + } \n\ + \n\ + s->sz = sizeof(*s); \n\ + s->name = \"%1$s\"; \n\ + s->obj = &obj->obj; \n\ + ", + obj_name + ); + + codegen_maps_skeleton(obj, map_cnt, true /*mmaped*/); + codegen_progs_skeleton(obj, prog_cnt, true /*populate_links*/); + + codegen("\ + \n\ + \n\ + s->data = (void *)%2$s__elf_bytes(&s->data_sz); \n\ + \n\ + obj->skeleton = s; \n\ + return 0; \n\ + err: \n\ + bpf_object__destroy_skeleton(s); \n\ + return err; \n\ + } \n\ + \n\ + static inline const void *%2$s__elf_bytes(size_t *sz) \n\ + { \n\ + *sz = %1$d; \n\ + return (const void *)\"\\ \n\ + " + , file_sz, obj_name); + + /* embed contents of BPF object file */ + print_hex(obj_data, file_sz); + + codegen("\ + \n\ + \"; \n\ + } \n\ + \n\ + #ifdef __cplusplus \n\ + struct %1$s *%1$s::open(const struct bpf_object_open_opts *opts) { return %1$s__open_opts(opts); }\n\ + struct %1$s *%1$s::open_and_load() { return %1$s__open_and_load(); } \n\ + int %1$s::load(struct %1$s *skel) { return %1$s__load(skel); } \n\ + int %1$s::attach(struct %1$s *skel) { return %1$s__attach(skel); } \n\ + void %1$s::detach(struct %1$s *skel) { %1$s__detach(skel); } \n\ + void %1$s::destroy(struct %1$s *skel) { %1$s__destroy(skel); } \n\ + const void *%1$s::elf_bytes(size_t *sz) { return %1$s__elf_bytes(sz); } \n\ + #endif /* __cplusplus */ \n\ + \n\ + ", + obj_name); + + codegen_asserts(obj, obj_name); + + codegen("\ + \n\ + \n\ + #endif /* %1$s */ \n\ + ", + header_guard); + err = 0; +out: + bpf_object__close(obj); + if (obj_data) + munmap(obj_data, mmap_sz); + close(fd); + return err; +} + +/* Subskeletons are like skeletons, except they don't own the bpf_object, + * associated maps, links, etc. Instead, they know about the existence of + * variables, maps, programs and are able to find their locations + * _at runtime_ from an already loaded bpf_object. + * + * This allows for library-like BPF objects to have userspace counterparts + * with access to their own items without having to know anything about the + * final BPF object that the library was linked into. + */ +static int do_subskeleton(int argc, char **argv) +{ + char header_guard[MAX_OBJ_NAME_LEN + sizeof("__SUBSKEL_H__")]; + size_t i, len, file_sz, map_cnt = 0, prog_cnt = 0, mmap_sz, var_cnt = 0, var_idx = 0; + DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts); + char obj_name[MAX_OBJ_NAME_LEN] = "", *obj_data; + struct bpf_object *obj = NULL; + const char *file, *var_name; + char ident[256]; + int fd, err = -1, map_type_id; + const struct bpf_map *map; + struct bpf_program *prog; + struct btf *btf; + const struct btf_type *map_type, *var_type; + const struct btf_var_secinfo *var; + struct stat st; + + if (!REQ_ARGS(1)) { + usage(); + return -1; + } + file = GET_ARG(); + + while (argc) { + if (!REQ_ARGS(2)) + return -1; + + if (is_prefix(*argv, "name")) { + NEXT_ARG(); + + if (obj_name[0] != '\0') { + p_err("object name already specified"); + return -1; + } + + strncpy(obj_name, *argv, MAX_OBJ_NAME_LEN - 1); + obj_name[MAX_OBJ_NAME_LEN - 1] = '\0'; + } else { + p_err("unknown arg %s", *argv); + return -1; + } + + NEXT_ARG(); + } + + if (argc) { + p_err("extra unknown arguments"); + return -1; + } + + if (use_loader) { + p_err("cannot use loader for subskeletons"); + return -1; + } + + if (stat(file, &st)) { + p_err("failed to stat() %s: %s", file, strerror(errno)); + return -1; + } + file_sz = st.st_size; + mmap_sz = roundup(file_sz, sysconf(_SC_PAGE_SIZE)); + fd = open(file, O_RDONLY); + if (fd < 0) { + p_err("failed to open() %s: %s", file, strerror(errno)); + return -1; + } + obj_data = mmap(NULL, mmap_sz, PROT_READ, MAP_PRIVATE, fd, 0); + if (obj_data == MAP_FAILED) { + obj_data = NULL; + p_err("failed to mmap() %s: %s", file, strerror(errno)); + goto out; + } + if (obj_name[0] == '\0') + get_obj_name(obj_name, file); + + /* The empty object name allows us to use bpf_map__name and produce + * ELF section names out of it. (".data" instead of "obj.data") + */ + opts.object_name = ""; + obj = bpf_object__open_mem(obj_data, file_sz, &opts); + if (!obj) { + char err_buf[256]; + + libbpf_strerror(errno, err_buf, sizeof(err_buf)); + p_err("failed to open BPF object file: %s", err_buf); + obj = NULL; + goto out; + } + + btf = bpf_object__btf(obj); + if (!btf) { + err = -1; + p_err("need btf type information for %s", obj_name); + goto out; + } + + bpf_object__for_each_program(prog, obj) { + prog_cnt++; + } + + /* First, count how many variables we have to find. + * We need this in advance so the subskel can allocate the right + * amount of storage. + */ + bpf_object__for_each_map(map, obj) { + if (!get_map_ident(map, ident, sizeof(ident))) + continue; + + /* Also count all maps that have a name */ + map_cnt++; + + if (!is_internal_mmapable_map(map, ident, sizeof(ident))) + continue; + + map_type_id = bpf_map__btf_value_type_id(map); + if (map_type_id <= 0) { + err = map_type_id; + goto out; + } + map_type = btf__type_by_id(btf, map_type_id); + + var = btf_var_secinfos(map_type); + len = btf_vlen(map_type); + for (i = 0; i < len; i++, var++) { + var_type = btf__type_by_id(btf, var->type); + + if (btf_var(var_type)->linkage == BTF_VAR_STATIC) + continue; + + var_cnt++; + } + } + + get_header_guard(header_guard, obj_name, "SUBSKEL_H"); + codegen("\ + \n\ + /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ \n\ + \n\ + /* THIS FILE IS AUTOGENERATED! */ \n\ + #ifndef %2$s \n\ + #define %2$s \n\ + \n\ + #include <errno.h> \n\ + #include <stdlib.h> \n\ + #include <bpf/libbpf.h> \n\ + \n\ + struct %1$s { \n\ + struct bpf_object *obj; \n\ + struct bpf_object_subskeleton *subskel; \n\ + ", obj_name, header_guard); + + if (map_cnt) { + printf("\tstruct {\n"); + bpf_object__for_each_map(map, obj) { + if (!get_map_ident(map, ident, sizeof(ident))) + continue; + printf("\t\tstruct bpf_map *%s;\n", ident); + } + printf("\t} maps;\n"); + } + + if (prog_cnt) { + printf("\tstruct {\n"); + bpf_object__for_each_program(prog, obj) { + printf("\t\tstruct bpf_program *%s;\n", + bpf_program__name(prog)); + } + printf("\t} progs;\n"); + } + + err = codegen_subskel_datasecs(obj, obj_name); + if (err) + goto out; + + /* emit code that will allocate enough storage for all symbols */ + codegen("\ + \n\ + \n\ + #ifdef __cplusplus \n\ + static inline struct %1$s *open(const struct bpf_object *src);\n\ + static inline void destroy(struct %1$s *skel); \n\ + #endif /* __cplusplus */ \n\ + }; \n\ + \n\ + static inline void \n\ + %1$s__destroy(struct %1$s *skel) \n\ + { \n\ + if (!skel) \n\ + return; \n\ + if (skel->subskel) \n\ + bpf_object__destroy_subskeleton(skel->subskel);\n\ + free(skel); \n\ + } \n\ + \n\ + static inline struct %1$s * \n\ + %1$s__open(const struct bpf_object *src) \n\ + { \n\ + struct %1$s *obj; \n\ + struct bpf_object_subskeleton *s; \n\ + int err; \n\ + \n\ + obj = (struct %1$s *)calloc(1, sizeof(*obj)); \n\ + if (!obj) { \n\ + err = -ENOMEM; \n\ + goto err; \n\ + } \n\ + s = (struct bpf_object_subskeleton *)calloc(1, sizeof(*s));\n\ + if (!s) { \n\ + err = -ENOMEM; \n\ + goto err; \n\ + } \n\ + s->sz = sizeof(*s); \n\ + s->obj = src; \n\ + s->var_skel_sz = sizeof(*s->vars); \n\ + obj->subskel = s; \n\ + \n\ + /* vars */ \n\ + s->var_cnt = %2$d; \n\ + s->vars = (struct bpf_var_skeleton *)calloc(%2$d, sizeof(*s->vars));\n\ + if (!s->vars) { \n\ + err = -ENOMEM; \n\ + goto err; \n\ + } \n\ + ", + obj_name, var_cnt + ); + + /* walk through each symbol and emit the runtime representation */ + bpf_object__for_each_map(map, obj) { + if (!is_internal_mmapable_map(map, ident, sizeof(ident))) + continue; + + map_type_id = bpf_map__btf_value_type_id(map); + if (map_type_id <= 0) + /* skip over internal maps with no type*/ + continue; + + map_type = btf__type_by_id(btf, map_type_id); + var = btf_var_secinfos(map_type); + len = btf_vlen(map_type); + for (i = 0; i < len; i++, var++) { + var_type = btf__type_by_id(btf, var->type); + var_name = btf__name_by_offset(btf, var_type->name_off); + + if (btf_var(var_type)->linkage == BTF_VAR_STATIC) + continue; + + /* Note that we use the dot prefix in .data as the + * field access operator i.e. maps%s becomes maps.data + */ + codegen("\ + \n\ + \n\ + s->vars[%3$d].name = \"%1$s\"; \n\ + s->vars[%3$d].map = &obj->maps.%2$s; \n\ + s->vars[%3$d].addr = (void **) &obj->%2$s.%1$s;\n\ + ", var_name, ident, var_idx); + + var_idx++; + } + } + + codegen_maps_skeleton(obj, map_cnt, false /*mmaped*/); + codegen_progs_skeleton(obj, prog_cnt, false /*links*/); + + codegen("\ + \n\ + \n\ + err = bpf_object__open_subskeleton(s); \n\ + if (err) \n\ + goto err; \n\ + \n\ + return obj; \n\ + err: \n\ + %1$s__destroy(obj); \n\ + errno = -err; \n\ + return NULL; \n\ + } \n\ + \n\ + #ifdef __cplusplus \n\ + struct %1$s *%1$s::open(const struct bpf_object *src) { return %1$s__open(src); }\n\ + void %1$s::destroy(struct %1$s *skel) { %1$s__destroy(skel); }\n\ + #endif /* __cplusplus */ \n\ + \n\ + #endif /* %2$s */ \n\ + ", + obj_name, header_guard); + err = 0; +out: + bpf_object__close(obj); + if (obj_data) + munmap(obj_data, mmap_sz); + close(fd); + return err; +} + +static int do_object(int argc, char **argv) +{ + struct bpf_linker *linker; + const char *output_file, *file; + int err = 0; + + if (!REQ_ARGS(2)) { + usage(); + return -1; + } + + output_file = GET_ARG(); + + linker = bpf_linker__new(output_file, NULL); + if (!linker) { + p_err("failed to create BPF linker instance"); + return -1; + } + + while (argc) { + file = GET_ARG(); + + err = bpf_linker__add_file(linker, file, NULL); + if (err) { + p_err("failed to link '%s': %s (%d)", file, strerror(errno), errno); + goto out; + } + } + + err = bpf_linker__finalize(linker); + if (err) { + p_err("failed to finalize ELF file: %s (%d)", strerror(errno), errno); + goto out; + } + + err = 0; +out: + bpf_linker__free(linker); + return err; +} + +static int do_help(int argc, char **argv) +{ + if (json_output) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %1$s %2$s object OUTPUT_FILE INPUT_FILE [INPUT_FILE...]\n" + " %1$s %2$s skeleton FILE [name OBJECT_NAME]\n" + " %1$s %2$s subskeleton FILE [name OBJECT_NAME]\n" + " %1$s %2$s min_core_btf INPUT OUTPUT OBJECT [OBJECT...]\n" + " %1$s %2$s help\n" + "\n" + " " HELP_SPEC_OPTIONS " |\n" + " {-L|--use-loader} }\n" + "", + bin_name, "gen"); + + return 0; +} + +static int btf_save_raw(const struct btf *btf, const char *path) +{ + const void *data; + FILE *f = NULL; + __u32 data_sz; + int err = 0; + + data = btf__raw_data(btf, &data_sz); + if (!data) + return -ENOMEM; + + f = fopen(path, "wb"); + if (!f) + return -errno; + + if (fwrite(data, 1, data_sz, f) != data_sz) + err = -errno; + + fclose(f); + return err; +} + +struct btfgen_info { + struct btf *src_btf; + struct btf *marked_btf; /* btf structure used to mark used types */ +}; + +static size_t btfgen_hash_fn(const void *key, void *ctx) +{ + return (size_t)key; +} + +static bool btfgen_equal_fn(const void *k1, const void *k2, void *ctx) +{ + return k1 == k2; +} + +static void *u32_as_hash_key(__u32 x) +{ + return (void *)(uintptr_t)x; +} + +static void btfgen_free_info(struct btfgen_info *info) +{ + if (!info) + return; + + btf__free(info->src_btf); + btf__free(info->marked_btf); + + free(info); +} + +static struct btfgen_info * +btfgen_new_info(const char *targ_btf_path) +{ + struct btfgen_info *info; + int err; + + info = calloc(1, sizeof(*info)); + if (!info) + return NULL; + + info->src_btf = btf__parse(targ_btf_path, NULL); + if (!info->src_btf) { + err = -errno; + p_err("failed parsing '%s' BTF file: %s", targ_btf_path, strerror(errno)); + goto err_out; + } + + info->marked_btf = btf__parse(targ_btf_path, NULL); + if (!info->marked_btf) { + err = -errno; + p_err("failed parsing '%s' BTF file: %s", targ_btf_path, strerror(errno)); + goto err_out; + } + + return info; + +err_out: + btfgen_free_info(info); + errno = -err; + return NULL; +} + +#define MARKED UINT32_MAX + +static void btfgen_mark_member(struct btfgen_info *info, int type_id, int idx) +{ + const struct btf_type *t = btf__type_by_id(info->marked_btf, type_id); + struct btf_member *m = btf_members(t) + idx; + + m->name_off = MARKED; +} + +static int +btfgen_mark_type(struct btfgen_info *info, unsigned int type_id, bool follow_pointers) +{ + const struct btf_type *btf_type = btf__type_by_id(info->src_btf, type_id); + struct btf_type *cloned_type; + struct btf_param *param; + struct btf_array *array; + int err, i; + + if (type_id == 0) + return 0; + + /* mark type on cloned BTF as used */ + cloned_type = (struct btf_type *) btf__type_by_id(info->marked_btf, type_id); + cloned_type->name_off = MARKED; + + /* recursively mark other types needed by it */ + switch (btf_kind(btf_type)) { + case BTF_KIND_UNKN: + case BTF_KIND_INT: + case BTF_KIND_FLOAT: + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + break; + case BTF_KIND_PTR: + if (follow_pointers) { + err = btfgen_mark_type(info, btf_type->type, follow_pointers); + if (err) + return err; + } + break; + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + case BTF_KIND_VOLATILE: + case BTF_KIND_TYPEDEF: + err = btfgen_mark_type(info, btf_type->type, follow_pointers); + if (err) + return err; + break; + case BTF_KIND_ARRAY: + array = btf_array(btf_type); + + /* mark array type */ + err = btfgen_mark_type(info, array->type, follow_pointers); + /* mark array's index type */ + err = err ? : btfgen_mark_type(info, array->index_type, follow_pointers); + if (err) + return err; + break; + case BTF_KIND_FUNC_PROTO: + /* mark ret type */ + err = btfgen_mark_type(info, btf_type->type, follow_pointers); + if (err) + return err; + + /* mark parameters types */ + param = btf_params(btf_type); + for (i = 0; i < btf_vlen(btf_type); i++) { + err = btfgen_mark_type(info, param->type, follow_pointers); + if (err) + return err; + param++; + } + break; + /* tells if some other type needs to be handled */ + default: + p_err("unsupported kind: %s (%d)", btf_kind_str(btf_type), type_id); + return -EINVAL; + } + + return 0; +} + +static int btfgen_record_field_relo(struct btfgen_info *info, struct bpf_core_spec *targ_spec) +{ + struct btf *btf = info->src_btf; + const struct btf_type *btf_type; + struct btf_member *btf_member; + struct btf_array *array; + unsigned int type_id = targ_spec->root_type_id; + int idx, err; + + /* mark root type */ + btf_type = btf__type_by_id(btf, type_id); + err = btfgen_mark_type(info, type_id, false); + if (err) + return err; + + /* mark types for complex types (arrays, unions, structures) */ + for (int i = 1; i < targ_spec->raw_len; i++) { + /* skip typedefs and mods */ + while (btf_is_mod(btf_type) || btf_is_typedef(btf_type)) { + type_id = btf_type->type; + btf_type = btf__type_by_id(btf, type_id); + } + + switch (btf_kind(btf_type)) { + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + idx = targ_spec->raw_spec[i]; + btf_member = btf_members(btf_type) + idx; + + /* mark member */ + btfgen_mark_member(info, type_id, idx); + + /* mark member's type */ + type_id = btf_member->type; + btf_type = btf__type_by_id(btf, type_id); + err = btfgen_mark_type(info, type_id, false); + if (err) + return err; + break; + case BTF_KIND_ARRAY: + array = btf_array(btf_type); + type_id = array->type; + btf_type = btf__type_by_id(btf, type_id); + break; + default: + p_err("unsupported kind: %s (%d)", + btf_kind_str(btf_type), btf_type->type); + return -EINVAL; + } + } + + return 0; +} + +/* Mark types, members, and member types. Compared to btfgen_record_field_relo, + * this function does not rely on the target spec for inferring members, but + * uses the associated BTF. + * + * The `behind_ptr` argument is used to stop marking of composite types reached + * through a pointer. This way, we can keep BTF size in check while providing + * reasonable match semantics. + */ +static int btfgen_mark_type_match(struct btfgen_info *info, __u32 type_id, bool behind_ptr) +{ + const struct btf_type *btf_type; + struct btf *btf = info->src_btf; + struct btf_type *cloned_type; + int i, err; + + if (type_id == 0) + return 0; + + btf_type = btf__type_by_id(btf, type_id); + /* mark type on cloned BTF as used */ + cloned_type = (struct btf_type *)btf__type_by_id(info->marked_btf, type_id); + cloned_type->name_off = MARKED; + + switch (btf_kind(btf_type)) { + case BTF_KIND_UNKN: + case BTF_KIND_INT: + case BTF_KIND_FLOAT: + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + break; + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: { + struct btf_member *m = btf_members(btf_type); + __u16 vlen = btf_vlen(btf_type); + + if (behind_ptr) + break; + + for (i = 0; i < vlen; i++, m++) { + /* mark member */ + btfgen_mark_member(info, type_id, i); + + /* mark member's type */ + err = btfgen_mark_type_match(info, m->type, false); + if (err) + return err; + } + break; + } + case BTF_KIND_CONST: + case BTF_KIND_FWD: + case BTF_KIND_RESTRICT: + case BTF_KIND_TYPEDEF: + case BTF_KIND_VOLATILE: + return btfgen_mark_type_match(info, btf_type->type, behind_ptr); + case BTF_KIND_PTR: + return btfgen_mark_type_match(info, btf_type->type, true); + case BTF_KIND_ARRAY: { + struct btf_array *array; + + array = btf_array(btf_type); + /* mark array type */ + err = btfgen_mark_type_match(info, array->type, false); + /* mark array's index type */ + err = err ? : btfgen_mark_type_match(info, array->index_type, false); + if (err) + return err; + break; + } + case BTF_KIND_FUNC_PROTO: { + __u16 vlen = btf_vlen(btf_type); + struct btf_param *param; + + /* mark ret type */ + err = btfgen_mark_type_match(info, btf_type->type, false); + if (err) + return err; + + /* mark parameters types */ + param = btf_params(btf_type); + for (i = 0; i < vlen; i++) { + err = btfgen_mark_type_match(info, param->type, false); + if (err) + return err; + param++; + } + break; + } + /* tells if some other type needs to be handled */ + default: + p_err("unsupported kind: %s (%d)", btf_kind_str(btf_type), type_id); + return -EINVAL; + } + + return 0; +} + +/* Mark types, members, and member types. Compared to btfgen_record_field_relo, + * this function does not rely on the target spec for inferring members, but + * uses the associated BTF. + */ +static int btfgen_record_type_match_relo(struct btfgen_info *info, struct bpf_core_spec *targ_spec) +{ + return btfgen_mark_type_match(info, targ_spec->root_type_id, false); +} + +static int btfgen_record_type_relo(struct btfgen_info *info, struct bpf_core_spec *targ_spec) +{ + return btfgen_mark_type(info, targ_spec->root_type_id, true); +} + +static int btfgen_record_enumval_relo(struct btfgen_info *info, struct bpf_core_spec *targ_spec) +{ + return btfgen_mark_type(info, targ_spec->root_type_id, false); +} + +static int btfgen_record_reloc(struct btfgen_info *info, struct bpf_core_spec *res) +{ + switch (res->relo_kind) { + case BPF_CORE_FIELD_BYTE_OFFSET: + case BPF_CORE_FIELD_BYTE_SIZE: + case BPF_CORE_FIELD_EXISTS: + case BPF_CORE_FIELD_SIGNED: + case BPF_CORE_FIELD_LSHIFT_U64: + case BPF_CORE_FIELD_RSHIFT_U64: + return btfgen_record_field_relo(info, res); + case BPF_CORE_TYPE_ID_LOCAL: /* BPF_CORE_TYPE_ID_LOCAL doesn't require kernel BTF */ + return 0; + case BPF_CORE_TYPE_ID_TARGET: + case BPF_CORE_TYPE_EXISTS: + case BPF_CORE_TYPE_SIZE: + return btfgen_record_type_relo(info, res); + case BPF_CORE_TYPE_MATCHES: + return btfgen_record_type_match_relo(info, res); + case BPF_CORE_ENUMVAL_EXISTS: + case BPF_CORE_ENUMVAL_VALUE: + return btfgen_record_enumval_relo(info, res); + default: + return -EINVAL; + } +} + +static struct bpf_core_cand_list * +btfgen_find_cands(const struct btf *local_btf, const struct btf *targ_btf, __u32 local_id) +{ + const struct btf_type *local_type; + struct bpf_core_cand_list *cands = NULL; + struct bpf_core_cand local_cand = {}; + size_t local_essent_len; + const char *local_name; + int err; + + local_cand.btf = local_btf; + local_cand.id = local_id; + + local_type = btf__type_by_id(local_btf, local_id); + if (!local_type) { + err = -EINVAL; + goto err_out; + } + + local_name = btf__name_by_offset(local_btf, local_type->name_off); + if (!local_name) { + err = -EINVAL; + goto err_out; + } + local_essent_len = bpf_core_essential_name_len(local_name); + + cands = calloc(1, sizeof(*cands)); + if (!cands) + return NULL; + + err = bpf_core_add_cands(&local_cand, local_essent_len, targ_btf, "vmlinux", 1, cands); + if (err) + goto err_out; + + return cands; + +err_out: + bpf_core_free_cands(cands); + errno = -err; + return NULL; +} + +/* Record relocation information for a single BPF object */ +static int btfgen_record_obj(struct btfgen_info *info, const char *obj_path) +{ + const struct btf_ext_info_sec *sec; + const struct bpf_core_relo *relo; + const struct btf_ext_info *seg; + struct hashmap_entry *entry; + struct hashmap *cand_cache = NULL; + struct btf_ext *btf_ext = NULL; + unsigned int relo_idx; + struct btf *btf = NULL; + size_t i; + int err; + + btf = btf__parse(obj_path, &btf_ext); + if (!btf) { + err = -errno; + p_err("failed to parse BPF object '%s': %s", obj_path, strerror(errno)); + return err; + } + + if (!btf_ext) { + p_err("failed to parse BPF object '%s': section %s not found", + obj_path, BTF_EXT_ELF_SEC); + err = -EINVAL; + goto out; + } + + if (btf_ext->core_relo_info.len == 0) { + err = 0; + goto out; + } + + cand_cache = hashmap__new(btfgen_hash_fn, btfgen_equal_fn, NULL); + if (IS_ERR(cand_cache)) { + err = PTR_ERR(cand_cache); + goto out; + } + + seg = &btf_ext->core_relo_info; + for_each_btf_ext_sec(seg, sec) { + for_each_btf_ext_rec(seg, sec, relo_idx, relo) { + struct bpf_core_spec specs_scratch[3] = {}; + struct bpf_core_relo_res targ_res = {}; + struct bpf_core_cand_list *cands = NULL; + const void *type_key = u32_as_hash_key(relo->type_id); + const char *sec_name = btf__name_by_offset(btf, sec->sec_name_off); + + if (relo->kind != BPF_CORE_TYPE_ID_LOCAL && + !hashmap__find(cand_cache, type_key, (void **)&cands)) { + cands = btfgen_find_cands(btf, info->src_btf, relo->type_id); + if (!cands) { + err = -errno; + goto out; + } + + err = hashmap__set(cand_cache, type_key, cands, NULL, NULL); + if (err) + goto out; + } + + err = bpf_core_calc_relo_insn(sec_name, relo, relo_idx, btf, cands, + specs_scratch, &targ_res); + if (err) + goto out; + + /* specs_scratch[2] is the target spec */ + err = btfgen_record_reloc(info, &specs_scratch[2]); + if (err) + goto out; + } + } + +out: + btf__free(btf); + btf_ext__free(btf_ext); + + if (!IS_ERR_OR_NULL(cand_cache)) { + hashmap__for_each_entry(cand_cache, entry, i) { + bpf_core_free_cands(entry->value); + } + hashmap__free(cand_cache); + } + + return err; +} + +static int btfgen_remap_id(__u32 *type_id, void *ctx) +{ + unsigned int *ids = ctx; + + *type_id = ids[*type_id]; + + return 0; +} + +/* Generate BTF from relocation information previously recorded */ +static struct btf *btfgen_get_btf(struct btfgen_info *info) +{ + struct btf *btf_new = NULL; + unsigned int *ids = NULL; + unsigned int i, n = btf__type_cnt(info->marked_btf); + int err = 0; + + btf_new = btf__new_empty(); + if (!btf_new) { + err = -errno; + goto err_out; + } + + ids = calloc(n, sizeof(*ids)); + if (!ids) { + err = -errno; + goto err_out; + } + + /* first pass: add all marked types to btf_new and add their new ids to the ids map */ + for (i = 1; i < n; i++) { + const struct btf_type *cloned_type, *type; + const char *name; + int new_id; + + cloned_type = btf__type_by_id(info->marked_btf, i); + + if (cloned_type->name_off != MARKED) + continue; + + type = btf__type_by_id(info->src_btf, i); + + /* add members for struct and union */ + if (btf_is_composite(type)) { + struct btf_member *cloned_m, *m; + unsigned short vlen; + int idx_src; + + name = btf__str_by_offset(info->src_btf, type->name_off); + + if (btf_is_struct(type)) + err = btf__add_struct(btf_new, name, type->size); + else + err = btf__add_union(btf_new, name, type->size); + + if (err < 0) + goto err_out; + new_id = err; + + cloned_m = btf_members(cloned_type); + m = btf_members(type); + vlen = btf_vlen(cloned_type); + for (idx_src = 0; idx_src < vlen; idx_src++, cloned_m++, m++) { + /* add only members that are marked as used */ + if (cloned_m->name_off != MARKED) + continue; + + name = btf__str_by_offset(info->src_btf, m->name_off); + err = btf__add_field(btf_new, name, m->type, + btf_member_bit_offset(cloned_type, idx_src), + btf_member_bitfield_size(cloned_type, idx_src)); + if (err < 0) + goto err_out; + } + } else { + err = btf__add_type(btf_new, info->src_btf, type); + if (err < 0) + goto err_out; + new_id = err; + } + + /* add ID mapping */ + ids[i] = new_id; + } + + /* second pass: fix up type ids */ + for (i = 1; i < btf__type_cnt(btf_new); i++) { + struct btf_type *btf_type = (struct btf_type *) btf__type_by_id(btf_new, i); + + err = btf_type_visit_type_ids(btf_type, btfgen_remap_id, ids); + if (err) + goto err_out; + } + + free(ids); + return btf_new; + +err_out: + btf__free(btf_new); + free(ids); + errno = -err; + return NULL; +} + +/* Create minimized BTF file for a set of BPF objects. + * + * The BTFGen algorithm is divided in two main parts: (1) collect the + * BTF types that are involved in relocations and (2) generate the BTF + * object using the collected types. + * + * In order to collect the types involved in the relocations, we parse + * the BTF and BTF.ext sections of the BPF objects and use + * bpf_core_calc_relo_insn() to get the target specification, this + * indicates how the types and fields are used in a relocation. + * + * Types are recorded in different ways according to the kind of the + * relocation. For field-based relocations only the members that are + * actually used are saved in order to reduce the size of the generated + * BTF file. For type-based relocations empty struct / unions are + * generated and for enum-based relocations the whole type is saved. + * + * The second part of the algorithm generates the BTF object. It creates + * an empty BTF object and fills it with the types recorded in the + * previous step. This function takes care of only adding the structure + * and union members that were marked as used and it also fixes up the + * type IDs on the generated BTF object. + */ +static int minimize_btf(const char *src_btf, const char *dst_btf, const char *objspaths[]) +{ + struct btfgen_info *info; + struct btf *btf_new = NULL; + int err, i; + + info = btfgen_new_info(src_btf); + if (!info) { + err = -errno; + p_err("failed to allocate info structure: %s", strerror(errno)); + goto out; + } + + for (i = 0; objspaths[i] != NULL; i++) { + err = btfgen_record_obj(info, objspaths[i]); + if (err) { + p_err("error recording relocations for %s: %s", objspaths[i], + strerror(errno)); + goto out; + } + } + + btf_new = btfgen_get_btf(info); + if (!btf_new) { + err = -errno; + p_err("error generating BTF: %s", strerror(errno)); + goto out; + } + + err = btf_save_raw(btf_new, dst_btf); + if (err) { + p_err("error saving btf file: %s", strerror(errno)); + goto out; + } + +out: + btf__free(btf_new); + btfgen_free_info(info); + + return err; +} + +static int do_min_core_btf(int argc, char **argv) +{ + const char *input, *output, **objs; + int i, err; + + if (!REQ_ARGS(3)) { + usage(); + return -1; + } + + input = GET_ARG(); + output = GET_ARG(); + + objs = (const char **) calloc(argc + 1, sizeof(*objs)); + if (!objs) { + p_err("failed to allocate array for object names"); + return -ENOMEM; + } + + i = 0; + while (argc) + objs[i++] = GET_ARG(); + + err = minimize_btf(input, output, objs); + free(objs); + return err; +} + +static const struct cmd cmds[] = { + { "object", do_object }, + { "skeleton", do_skeleton }, + { "subskeleton", do_subskeleton }, + { "min_core_btf", do_min_core_btf}, + { "help", do_help }, + { 0 } +}; + +int do_gen(int argc, char **argv) +{ + return cmd_select(cmds, argc, argv, do_help); +} diff --git a/tools/bpf/bpftool/iter.c b/tools/bpf/bpftool/iter.c new file mode 100644 index 000000000..f88fdc820 --- /dev/null +++ b/tools/bpf/bpftool/iter.c @@ -0,0 +1,119 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +// Copyright (C) 2020 Facebook + +#define _GNU_SOURCE +#include <unistd.h> +#include <linux/err.h> +#include <bpf/libbpf.h> + +#include "main.h" + +static int do_pin(int argc, char **argv) +{ + DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, iter_opts); + union bpf_iter_link_info linfo; + const char *objfile, *path; + struct bpf_program *prog; + struct bpf_object *obj; + struct bpf_link *link; + int err = -1, map_fd = -1; + + if (!REQ_ARGS(2)) + usage(); + + objfile = GET_ARG(); + path = GET_ARG(); + + /* optional arguments */ + if (argc) { + if (is_prefix(*argv, "map")) { + NEXT_ARG(); + + if (!REQ_ARGS(2)) { + p_err("incorrect map spec"); + return -1; + } + + map_fd = map_parse_fd(&argc, &argv); + if (map_fd < 0) + return -1; + + memset(&linfo, 0, sizeof(linfo)); + linfo.map.map_fd = map_fd; + iter_opts.link_info = &linfo; + iter_opts.link_info_len = sizeof(linfo); + } + } + + obj = bpf_object__open(objfile); + err = libbpf_get_error(obj); + if (err) { + p_err("can't open objfile %s", objfile); + goto close_map_fd; + } + + err = bpf_object__load(obj); + if (err) { + p_err("can't load objfile %s", objfile); + goto close_obj; + } + + prog = bpf_object__next_program(obj, NULL); + if (!prog) { + p_err("can't find bpf program in objfile %s", objfile); + goto close_obj; + } + + link = bpf_program__attach_iter(prog, &iter_opts); + err = libbpf_get_error(link); + if (err) { + p_err("attach_iter failed for program %s", + bpf_program__name(prog)); + goto close_obj; + } + + err = mount_bpffs_for_pin(path); + if (err) + goto close_link; + + err = bpf_link__pin(link, path); + if (err) { + p_err("pin_iter failed for program %s to path %s", + bpf_program__name(prog), path); + goto close_link; + } + +close_link: + bpf_link__destroy(link); +close_obj: + bpf_object__close(obj); +close_map_fd: + if (map_fd >= 0) + close(map_fd); + return err; +} + +static int do_help(int argc, char **argv) +{ + fprintf(stderr, + "Usage: %1$s %2$s pin OBJ PATH [map MAP]\n" + " %1$s %2$s help\n" + "\n" + " " HELP_SPEC_MAP "\n" + " " HELP_SPEC_OPTIONS " }\n" + "", + bin_name, "iter"); + + return 0; +} + +static const struct cmd cmds[] = { + { "help", do_help }, + { "pin", do_pin }, + { 0 } +}; + +int do_iter(int argc, char **argv) +{ + return cmd_select(cmds, argc, argv, do_help); +} diff --git a/tools/bpf/bpftool/jit_disasm.c b/tools/bpf/bpftool/jit_disasm.c new file mode 100644 index 000000000..aaf99a016 --- /dev/null +++ b/tools/bpf/bpftool/jit_disasm.c @@ -0,0 +1,234 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* + * Based on: + * + * Minimal BPF JIT image disassembler + * + * Disassembles BPF JIT compiler emitted opcodes back to asm insn's for + * debugging or verification purposes. + * + * Copyright 2013 Daniel Borkmann <daniel@iogearbox.net> + * Licensed under the GNU General Public License, version 2.0 (GPLv2) + */ + +#define _GNU_SOURCE +#include <stdio.h> +#include <stdarg.h> +#include <stdint.h> +#include <stdlib.h> +#include <assert.h> +#include <unistd.h> +#include <string.h> +#include <bfd.h> +#include <dis-asm.h> +#include <sys/stat.h> +#include <limits.h> +#include <bpf/libbpf.h> +#include <tools/dis-asm-compat.h> + +#include "json_writer.h" +#include "main.h" + +static void get_exec_path(char *tpath, size_t size) +{ + const char *path = "/proc/self/exe"; + ssize_t len; + + len = readlink(path, tpath, size - 1); + assert(len > 0); + tpath[len] = 0; +} + +static int oper_count; +static int printf_json(void *out, const char *fmt, va_list ap) +{ + char *s; + int err; + + err = vasprintf(&s, fmt, ap); + if (err < 0) + return -1; + + if (!oper_count) { + int i; + + /* Strip trailing spaces */ + i = strlen(s) - 1; + while (s[i] == ' ') + s[i--] = '\0'; + + jsonw_string_field(json_wtr, "operation", s); + jsonw_name(json_wtr, "operands"); + jsonw_start_array(json_wtr); + oper_count++; + } else if (!strcmp(fmt, ",")) { + /* Skip */ + } else { + jsonw_string(json_wtr, s); + oper_count++; + } + free(s); + return 0; +} + +static int fprintf_json(void *out, const char *fmt, ...) +{ + va_list ap; + int r; + + va_start(ap, fmt); + r = printf_json(out, fmt, ap); + va_end(ap); + + return r; +} + +static int fprintf_json_styled(void *out, + enum disassembler_style style __maybe_unused, + const char *fmt, ...) +{ + va_list ap; + int r; + + va_start(ap, fmt); + r = printf_json(out, fmt, ap); + va_end(ap); + + return r; +} + +void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes, + const char *arch, const char *disassembler_options, + const struct btf *btf, + const struct bpf_prog_linfo *prog_linfo, + __u64 func_ksym, unsigned int func_idx, + bool linum) +{ + const struct bpf_line_info *linfo = NULL; + disassembler_ftype disassemble; + struct disassemble_info info; + unsigned int nr_skip = 0; + int count, i, pc = 0; + char tpath[PATH_MAX]; + bfd *bfdf; + + if (!len) + return; + + memset(tpath, 0, sizeof(tpath)); + get_exec_path(tpath, sizeof(tpath)); + + bfdf = bfd_openr(tpath, NULL); + assert(bfdf); + assert(bfd_check_format(bfdf, bfd_object)); + + if (json_output) + init_disassemble_info_compat(&info, stdout, + (fprintf_ftype) fprintf_json, + fprintf_json_styled); + else + init_disassemble_info_compat(&info, stdout, + (fprintf_ftype) fprintf, + fprintf_styled); + + /* Update architecture info for offload. */ + if (arch) { + const bfd_arch_info_type *inf = bfd_scan_arch(arch); + + if (inf) { + bfdf->arch_info = inf; + } else { + p_err("No libbfd support for %s", arch); + return; + } + } + + info.arch = bfd_get_arch(bfdf); + info.mach = bfd_get_mach(bfdf); + if (disassembler_options) + info.disassembler_options = disassembler_options; + info.buffer = image; + info.buffer_length = len; + + disassemble_init_for_target(&info); + +#ifdef DISASM_FOUR_ARGS_SIGNATURE + disassemble = disassembler(info.arch, + bfd_big_endian(bfdf), + info.mach, + bfdf); +#else + disassemble = disassembler(bfdf); +#endif + assert(disassemble); + + if (json_output) + jsonw_start_array(json_wtr); + do { + if (prog_linfo) { + linfo = bpf_prog_linfo__lfind_addr_func(prog_linfo, + func_ksym + pc, + func_idx, + nr_skip); + if (linfo) + nr_skip++; + } + + if (json_output) { + jsonw_start_object(json_wtr); + oper_count = 0; + if (linfo) + btf_dump_linfo_json(btf, linfo, linum); + jsonw_name(json_wtr, "pc"); + jsonw_printf(json_wtr, "\"0x%x\"", pc); + } else { + if (linfo) + btf_dump_linfo_plain(btf, linfo, "; ", + linum); + printf("%4x:\t", pc); + } + + count = disassemble(pc, &info); + if (json_output) { + /* Operand array, was started in fprintf_json. Before + * that, make sure we have a _null_ value if no operand + * other than operation code was present. + */ + if (oper_count == 1) + jsonw_null(json_wtr); + jsonw_end_array(json_wtr); + } + + if (opcodes) { + if (json_output) { + jsonw_name(json_wtr, "opcodes"); + jsonw_start_array(json_wtr); + for (i = 0; i < count; ++i) + jsonw_printf(json_wtr, "\"0x%02hhx\"", + (uint8_t)image[pc + i]); + jsonw_end_array(json_wtr); + } else { + printf("\n\t"); + for (i = 0; i < count; ++i) + printf("%02x ", + (uint8_t)image[pc + i]); + } + } + if (json_output) + jsonw_end_object(json_wtr); + else + printf("\n"); + + pc += count; + } while (count > 0 && pc < len); + if (json_output) + jsonw_end_array(json_wtr); + + bfd_close(bfdf); +} + +int disasm_init(void) +{ + bfd_init(); + return 0; +} diff --git a/tools/bpf/bpftool/json_writer.c b/tools/bpf/bpftool/json_writer.c new file mode 100644 index 000000000..bca5dd0a5 --- /dev/null +++ b/tools/bpf/bpftool/json_writer.c @@ -0,0 +1,355 @@ +// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-2-Clause) +/* + * Simple streaming JSON writer + * + * This takes care of the annoying bits of JSON syntax like the commas + * after elements + * + * Authors: Stephen Hemminger <stephen@networkplumber.org> + */ + +#include <stdio.h> +#include <stdbool.h> +#include <stdarg.h> +#include <assert.h> +#include <malloc.h> +#include <inttypes.h> +#include <stdint.h> + +#include "json_writer.h" + +struct json_writer { + FILE *out; /* output file */ + unsigned depth; /* nesting */ + bool pretty; /* optional whitepace */ + char sep; /* either nul or comma */ +}; + +/* indentation for pretty print */ +static void jsonw_indent(json_writer_t *self) +{ + unsigned i; + for (i = 0; i < self->depth; ++i) + fputs(" ", self->out); +} + +/* end current line and indent if pretty printing */ +static void jsonw_eol(json_writer_t *self) +{ + if (!self->pretty) + return; + + putc('\n', self->out); + jsonw_indent(self); +} + +/* If current object is not empty print a comma */ +static void jsonw_eor(json_writer_t *self) +{ + if (self->sep != '\0') + putc(self->sep, self->out); + self->sep = ','; +} + + +/* Output JSON encoded string */ +/* Handles C escapes, does not do Unicode */ +static void jsonw_puts(json_writer_t *self, const char *str) +{ + putc('"', self->out); + for (; *str; ++str) + switch (*str) { + case '\t': + fputs("\\t", self->out); + break; + case '\n': + fputs("\\n", self->out); + break; + case '\r': + fputs("\\r", self->out); + break; + case '\f': + fputs("\\f", self->out); + break; + case '\b': + fputs("\\b", self->out); + break; + case '\\': + fputs("\\n", self->out); + break; + case '"': + fputs("\\\"", self->out); + break; + default: + putc(*str, self->out); + } + putc('"', self->out); +} + +/* Create a new JSON stream */ +json_writer_t *jsonw_new(FILE *f) +{ + json_writer_t *self = malloc(sizeof(*self)); + if (self) { + self->out = f; + self->depth = 0; + self->pretty = false; + self->sep = '\0'; + } + return self; +} + +/* End output to JSON stream */ +void jsonw_destroy(json_writer_t **self_p) +{ + json_writer_t *self = *self_p; + + assert(self->depth == 0); + fputs("\n", self->out); + fflush(self->out); + free(self); + *self_p = NULL; +} + +void jsonw_pretty(json_writer_t *self, bool on) +{ + self->pretty = on; +} + +void jsonw_reset(json_writer_t *self) +{ + assert(self->depth == 0); + self->sep = '\0'; +} + +/* Basic blocks */ +static void jsonw_begin(json_writer_t *self, int c) +{ + jsonw_eor(self); + putc(c, self->out); + ++self->depth; + self->sep = '\0'; +} + +static void jsonw_end(json_writer_t *self, int c) +{ + assert(self->depth > 0); + + --self->depth; + if (self->sep != '\0') + jsonw_eol(self); + putc(c, self->out); + self->sep = ','; +} + + +/* Add a JSON property name */ +void jsonw_name(json_writer_t *self, const char *name) +{ + jsonw_eor(self); + jsonw_eol(self); + self->sep = '\0'; + jsonw_puts(self, name); + putc(':', self->out); + if (self->pretty) + putc(' ', self->out); +} + +void jsonw_vprintf_enquote(json_writer_t *self, const char *fmt, va_list ap) +{ + jsonw_eor(self); + putc('"', self->out); + vfprintf(self->out, fmt, ap); + putc('"', self->out); +} + +void jsonw_printf(json_writer_t *self, const char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + jsonw_eor(self); + vfprintf(self->out, fmt, ap); + va_end(ap); +} + +/* Collections */ +void jsonw_start_object(json_writer_t *self) +{ + jsonw_begin(self, '{'); +} + +void jsonw_end_object(json_writer_t *self) +{ + jsonw_end(self, '}'); +} + +void jsonw_start_array(json_writer_t *self) +{ + jsonw_begin(self, '['); +} + +void jsonw_end_array(json_writer_t *self) +{ + jsonw_end(self, ']'); +} + +/* JSON value types */ +void jsonw_string(json_writer_t *self, const char *value) +{ + jsonw_eor(self); + jsonw_puts(self, value); +} + +void jsonw_bool(json_writer_t *self, bool val) +{ + jsonw_printf(self, "%s", val ? "true" : "false"); +} + +void jsonw_null(json_writer_t *self) +{ + jsonw_printf(self, "null"); +} + +void jsonw_float_fmt(json_writer_t *self, const char *fmt, double num) +{ + jsonw_printf(self, fmt, num); +} + +#ifdef notused +void jsonw_float(json_writer_t *self, double num) +{ + jsonw_printf(self, "%g", num); +} +#endif + +void jsonw_hu(json_writer_t *self, unsigned short num) +{ + jsonw_printf(self, "%hu", num); +} + +void jsonw_uint(json_writer_t *self, uint64_t num) +{ + jsonw_printf(self, "%"PRIu64, num); +} + +void jsonw_lluint(json_writer_t *self, unsigned long long int num) +{ + jsonw_printf(self, "%llu", num); +} + +void jsonw_int(json_writer_t *self, int64_t num) +{ + jsonw_printf(self, "%"PRId64, num); +} + +/* Basic name/value objects */ +void jsonw_string_field(json_writer_t *self, const char *prop, const char *val) +{ + jsonw_name(self, prop); + jsonw_string(self, val); +} + +void jsonw_bool_field(json_writer_t *self, const char *prop, bool val) +{ + jsonw_name(self, prop); + jsonw_bool(self, val); +} + +#ifdef notused +void jsonw_float_field(json_writer_t *self, const char *prop, double val) +{ + jsonw_name(self, prop); + jsonw_float(self, val); +} +#endif + +void jsonw_float_field_fmt(json_writer_t *self, + const char *prop, + const char *fmt, + double val) +{ + jsonw_name(self, prop); + jsonw_float_fmt(self, fmt, val); +} + +void jsonw_uint_field(json_writer_t *self, const char *prop, uint64_t num) +{ + jsonw_name(self, prop); + jsonw_uint(self, num); +} + +void jsonw_hu_field(json_writer_t *self, const char *prop, unsigned short num) +{ + jsonw_name(self, prop); + jsonw_hu(self, num); +} + +void jsonw_lluint_field(json_writer_t *self, + const char *prop, + unsigned long long int num) +{ + jsonw_name(self, prop); + jsonw_lluint(self, num); +} + +void jsonw_int_field(json_writer_t *self, const char *prop, int64_t num) +{ + jsonw_name(self, prop); + jsonw_int(self, num); +} + +void jsonw_null_field(json_writer_t *self, const char *prop) +{ + jsonw_name(self, prop); + jsonw_null(self); +} + +#ifdef TEST +int main(int argc, char **argv) +{ + json_writer_t *wr = jsonw_new(stdout); + + jsonw_start_object(wr); + jsonw_pretty(wr, true); + jsonw_name(wr, "Vyatta"); + jsonw_start_object(wr); + jsonw_string_field(wr, "url", "http://vyatta.com"); + jsonw_uint_field(wr, "downloads", 2000000ul); + jsonw_float_field(wr, "stock", 8.16); + + jsonw_name(wr, "ARGV"); + jsonw_start_array(wr); + while (--argc) + jsonw_string(wr, *++argv); + jsonw_end_array(wr); + + jsonw_name(wr, "empty"); + jsonw_start_array(wr); + jsonw_end_array(wr); + + jsonw_name(wr, "NIL"); + jsonw_start_object(wr); + jsonw_end_object(wr); + + jsonw_null_field(wr, "my_null"); + + jsonw_name(wr, "special chars"); + jsonw_start_array(wr); + jsonw_string_field(wr, "slash", "/"); + jsonw_string_field(wr, "newline", "\n"); + jsonw_string_field(wr, "tab", "\t"); + jsonw_string_field(wr, "ff", "\f"); + jsonw_string_field(wr, "quote", "\""); + jsonw_string_field(wr, "tick", "\'"); + jsonw_string_field(wr, "backslash", "\\"); + jsonw_end_array(wr); + + jsonw_end_object(wr); + + jsonw_end_object(wr); + jsonw_destroy(&wr); + return 0; +} + +#endif diff --git a/tools/bpf/bpftool/json_writer.h b/tools/bpf/bpftool/json_writer.h new file mode 100644 index 000000000..8ace65cdb --- /dev/null +++ b/tools/bpf/bpftool/json_writer.h @@ -0,0 +1,73 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Simple streaming JSON writer + * + * This takes care of the annoying bits of JSON syntax like the commas + * after elements + * + * Authors: Stephen Hemminger <stephen@networkplumber.org> + */ + +#ifndef _JSON_WRITER_H_ +#define _JSON_WRITER_H_ + +#include <stdbool.h> +#include <stdint.h> +#include <stdarg.h> +#include <linux/compiler.h> + +/* Opaque class structure */ +typedef struct json_writer json_writer_t; + +/* Create a new JSON stream */ +json_writer_t *jsonw_new(FILE *f); +/* End output to JSON stream */ +void jsonw_destroy(json_writer_t **self_p); + +/* Cause output to have pretty whitespace */ +void jsonw_pretty(json_writer_t *self, bool on); + +/* Reset separator to create new JSON */ +void jsonw_reset(json_writer_t *self); + +/* Add property name */ +void jsonw_name(json_writer_t *self, const char *name); + +/* Add value */ +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); +void jsonw_float_fmt(json_writer_t *self, const char *fmt, double num); +void jsonw_uint(json_writer_t *self, uint64_t number); +void jsonw_hu(json_writer_t *self, unsigned short number); +void jsonw_int(json_writer_t *self, int64_t number); +void jsonw_null(json_writer_t *self); +void jsonw_lluint(json_writer_t *self, unsigned long long int num); + +/* Useful Combinations of name and value */ +void jsonw_string_field(json_writer_t *self, const char *prop, const char *val); +void jsonw_bool_field(json_writer_t *self, const char *prop, bool value); +void jsonw_float_field(json_writer_t *self, const char *prop, double num); +void jsonw_uint_field(json_writer_t *self, const char *prop, uint64_t num); +void jsonw_hu_field(json_writer_t *self, const char *prop, unsigned short num); +void jsonw_int_field(json_writer_t *self, const char *prop, int64_t num); +void jsonw_null_field(json_writer_t *self, const char *prop); +void jsonw_lluint_field(json_writer_t *self, const char *prop, + unsigned long long int num); +void jsonw_float_field_fmt(json_writer_t *self, const char *prop, + const char *fmt, double val); + +/* Collections */ +void jsonw_start_object(json_writer_t *self); +void jsonw_end_object(json_writer_t *self); + +void jsonw_start_array(json_writer_t *self); +void jsonw_end_array(json_writer_t *self); + +/* Override default exception handling */ +typedef void (jsonw_err_handler_fn)(const char *); + +#endif /* _JSON_WRITER_H_ */ diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c new file mode 100644 index 000000000..286363970 --- /dev/null +++ b/tools/bpf/bpftool/link.c @@ -0,0 +1,495 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2020 Facebook */ + +#include <errno.h> +#include <linux/err.h> +#include <net/if.h> +#include <stdio.h> +#include <unistd.h> + +#include <bpf/bpf.h> +#include <bpf/hashmap.h> + +#include "json_writer.h" +#include "main.h" + +static struct hashmap *link_table; + +static int link_parse_fd(int *argc, char ***argv) +{ + int fd; + + if (is_prefix(**argv, "id")) { + unsigned int id; + char *endptr; + + NEXT_ARGP(); + + id = strtoul(**argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as ID", **argv); + return -1; + } + NEXT_ARGP(); + + fd = bpf_link_get_fd_by_id(id); + if (fd < 0) + p_err("failed to get link with ID %d: %s", id, strerror(errno)); + return fd; + } else if (is_prefix(**argv, "pinned")) { + char *path; + + NEXT_ARGP(); + + path = **argv; + NEXT_ARGP(); + + return open_obj_pinned_any(path, BPF_OBJ_LINK); + } + + p_err("expected 'id' or 'pinned', got: '%s'?", **argv); + return -1; +} + +static void +show_link_header_json(struct bpf_link_info *info, json_writer_t *wtr) +{ + const char *link_type_str; + + jsonw_uint_field(wtr, "id", info->id); + link_type_str = libbpf_bpf_link_type_str(info->type); + if (link_type_str) + jsonw_string_field(wtr, "type", link_type_str); + else + jsonw_uint_field(wtr, "type", info->type); + + jsonw_uint_field(json_wtr, "prog_id", info->prog_id); +} + +static void show_link_attach_type_json(__u32 attach_type, json_writer_t *wtr) +{ + const char *attach_type_str; + + attach_type_str = libbpf_bpf_attach_type_str(attach_type); + if (attach_type_str) + jsonw_string_field(wtr, "attach_type", attach_type_str); + else + jsonw_uint_field(wtr, "attach_type", attach_type); +} + +static bool is_iter_map_target(const char *target_name) +{ + return strcmp(target_name, "bpf_map_elem") == 0 || + strcmp(target_name, "bpf_sk_storage_map") == 0; +} + +static bool is_iter_cgroup_target(const char *target_name) +{ + return strcmp(target_name, "cgroup") == 0; +} + +static const char *cgroup_order_string(__u32 order) +{ + switch (order) { + case BPF_CGROUP_ITER_ORDER_UNSPEC: + return "order_unspec"; + case BPF_CGROUP_ITER_SELF_ONLY: + return "self_only"; + case BPF_CGROUP_ITER_DESCENDANTS_PRE: + return "descendants_pre"; + case BPF_CGROUP_ITER_DESCENDANTS_POST: + return "descendants_post"; + case BPF_CGROUP_ITER_ANCESTORS_UP: + return "ancestors_up"; + default: /* won't happen */ + return "unknown"; + } +} + +static bool is_iter_task_target(const char *target_name) +{ + return strcmp(target_name, "task") == 0 || + strcmp(target_name, "task_file") == 0 || + strcmp(target_name, "task_vma") == 0; +} + +static void show_iter_json(struct bpf_link_info *info, json_writer_t *wtr) +{ + const char *target_name = u64_to_ptr(info->iter.target_name); + + jsonw_string_field(wtr, "target_name", target_name); + + if (is_iter_map_target(target_name)) + jsonw_uint_field(wtr, "map_id", info->iter.map.map_id); + else if (is_iter_task_target(target_name)) { + if (info->iter.task.tid) + jsonw_uint_field(wtr, "tid", info->iter.task.tid); + else if (info->iter.task.pid) + jsonw_uint_field(wtr, "pid", info->iter.task.pid); + } + + if (is_iter_cgroup_target(target_name)) { + jsonw_lluint_field(wtr, "cgroup_id", info->iter.cgroup.cgroup_id); + jsonw_string_field(wtr, "order", + cgroup_order_string(info->iter.cgroup.order)); + } +} + +static int get_prog_info(int prog_id, struct bpf_prog_info *info) +{ + __u32 len = sizeof(*info); + int err, prog_fd; + + prog_fd = bpf_prog_get_fd_by_id(prog_id); + if (prog_fd < 0) + return prog_fd; + + memset(info, 0, sizeof(*info)); + err = bpf_obj_get_info_by_fd(prog_fd, info, &len); + if (err) + p_err("can't get prog info: %s", strerror(errno)); + close(prog_fd); + return err; +} + +static int show_link_close_json(int fd, struct bpf_link_info *info) +{ + struct bpf_prog_info prog_info; + const char *prog_type_str; + int err; + + jsonw_start_object(json_wtr); + + show_link_header_json(info, json_wtr); + + switch (info->type) { + case BPF_LINK_TYPE_RAW_TRACEPOINT: + jsonw_string_field(json_wtr, "tp_name", + u64_to_ptr(info->raw_tracepoint.tp_name)); + break; + case BPF_LINK_TYPE_TRACING: + err = get_prog_info(info->prog_id, &prog_info); + if (err) + return err; + + prog_type_str = libbpf_bpf_prog_type_str(prog_info.type); + /* libbpf will return NULL for variants unknown to it. */ + if (prog_type_str) + jsonw_string_field(json_wtr, "prog_type", prog_type_str); + else + jsonw_uint_field(json_wtr, "prog_type", prog_info.type); + + show_link_attach_type_json(info->tracing.attach_type, + json_wtr); + break; + case BPF_LINK_TYPE_CGROUP: + jsonw_lluint_field(json_wtr, "cgroup_id", + info->cgroup.cgroup_id); + show_link_attach_type_json(info->cgroup.attach_type, json_wtr); + break; + case BPF_LINK_TYPE_ITER: + show_iter_json(info, json_wtr); + break; + case BPF_LINK_TYPE_NETNS: + jsonw_uint_field(json_wtr, "netns_ino", + info->netns.netns_ino); + show_link_attach_type_json(info->netns.attach_type, json_wtr); + break; + default: + break; + } + + if (!hashmap__empty(link_table)) { + struct hashmap_entry *entry; + + jsonw_name(json_wtr, "pinned"); + jsonw_start_array(json_wtr); + hashmap__for_each_key_entry(link_table, entry, + u32_as_hash_field(info->id)) + jsonw_string(json_wtr, entry->value); + jsonw_end_array(json_wtr); + } + + emit_obj_refs_json(refs_table, info->id, json_wtr); + + jsonw_end_object(json_wtr); + + return 0; +} + +static void show_link_header_plain(struct bpf_link_info *info) +{ + const char *link_type_str; + + printf("%u: ", info->id); + link_type_str = libbpf_bpf_link_type_str(info->type); + if (link_type_str) + printf("%s ", link_type_str); + else + printf("type %u ", info->type); + + printf("prog %u ", info->prog_id); +} + +static void show_link_attach_type_plain(__u32 attach_type) +{ + const char *attach_type_str; + + attach_type_str = libbpf_bpf_attach_type_str(attach_type); + if (attach_type_str) + printf("attach_type %s ", attach_type_str); + else + printf("attach_type %u ", attach_type); +} + +static void show_iter_plain(struct bpf_link_info *info) +{ + const char *target_name = u64_to_ptr(info->iter.target_name); + + printf("target_name %s ", target_name); + + if (is_iter_map_target(target_name)) + printf("map_id %u ", info->iter.map.map_id); + else if (is_iter_task_target(target_name)) { + if (info->iter.task.tid) + printf("tid %u ", info->iter.task.tid); + else if (info->iter.task.pid) + printf("pid %u ", info->iter.task.pid); + } + + if (is_iter_cgroup_target(target_name)) { + printf("cgroup_id %llu ", info->iter.cgroup.cgroup_id); + printf("order %s ", + cgroup_order_string(info->iter.cgroup.order)); + } +} + +static int show_link_close_plain(int fd, struct bpf_link_info *info) +{ + struct bpf_prog_info prog_info; + const char *prog_type_str; + int err; + + show_link_header_plain(info); + + switch (info->type) { + case BPF_LINK_TYPE_RAW_TRACEPOINT: + printf("\n\ttp '%s' ", + (const char *)u64_to_ptr(info->raw_tracepoint.tp_name)); + break; + case BPF_LINK_TYPE_TRACING: + err = get_prog_info(info->prog_id, &prog_info); + if (err) + return err; + + prog_type_str = libbpf_bpf_prog_type_str(prog_info.type); + /* libbpf will return NULL for variants unknown to it. */ + if (prog_type_str) + printf("\n\tprog_type %s ", prog_type_str); + else + printf("\n\tprog_type %u ", prog_info.type); + + show_link_attach_type_plain(info->tracing.attach_type); + break; + case BPF_LINK_TYPE_CGROUP: + printf("\n\tcgroup_id %zu ", (size_t)info->cgroup.cgroup_id); + show_link_attach_type_plain(info->cgroup.attach_type); + break; + case BPF_LINK_TYPE_ITER: + show_iter_plain(info); + break; + case BPF_LINK_TYPE_NETNS: + printf("\n\tnetns_ino %u ", info->netns.netns_ino); + show_link_attach_type_plain(info->netns.attach_type); + break; + default: + break; + } + + if (!hashmap__empty(link_table)) { + struct hashmap_entry *entry; + + hashmap__for_each_key_entry(link_table, entry, + u32_as_hash_field(info->id)) + printf("\n\tpinned %s", (char *)entry->value); + } + emit_obj_refs_plain(refs_table, info->id, "\n\tpids "); + + printf("\n"); + + return 0; +} + +static int do_show_link(int fd) +{ + struct bpf_link_info info; + __u32 len = sizeof(info); + char buf[256]; + int err; + + memset(&info, 0, sizeof(info)); +again: + err = bpf_obj_get_info_by_fd(fd, &info, &len); + if (err) { + p_err("can't get link info: %s", + strerror(errno)); + close(fd); + return err; + } + if (info.type == BPF_LINK_TYPE_RAW_TRACEPOINT && + !info.raw_tracepoint.tp_name) { + info.raw_tracepoint.tp_name = (unsigned long)&buf; + info.raw_tracepoint.tp_name_len = sizeof(buf); + goto again; + } + if (info.type == BPF_LINK_TYPE_ITER && + !info.iter.target_name) { + info.iter.target_name = (unsigned long)&buf; + info.iter.target_name_len = sizeof(buf); + goto again; + } + + if (json_output) + show_link_close_json(fd, &info); + else + show_link_close_plain(fd, &info); + + close(fd); + return 0; +} + +static int do_show(int argc, char **argv) +{ + __u32 id = 0; + int err, fd; + + if (show_pinned) { + link_table = hashmap__new(hash_fn_for_key_as_id, + equal_fn_for_key_as_id, NULL); + if (IS_ERR(link_table)) { + p_err("failed to create hashmap for pinned paths"); + return -1; + } + build_pinned_obj_table(link_table, BPF_OBJ_LINK); + } + build_obj_refs_table(&refs_table, BPF_OBJ_LINK); + + if (argc == 2) { + fd = link_parse_fd(&argc, &argv); + if (fd < 0) + return fd; + return do_show_link(fd); + } + + if (argc) + return BAD_ARG(); + + if (json_output) + jsonw_start_array(json_wtr); + while (true) { + err = bpf_link_get_next_id(id, &id); + if (err) { + if (errno == ENOENT) + break; + p_err("can't get next link: %s%s", strerror(errno), + errno == EINVAL ? " -- kernel too old?" : ""); + break; + } + + fd = bpf_link_get_fd_by_id(id); + if (fd < 0) { + if (errno == ENOENT) + continue; + p_err("can't get link by id (%u): %s", + id, strerror(errno)); + break; + } + + err = do_show_link(fd); + if (err) + break; + } + if (json_output) + jsonw_end_array(json_wtr); + + delete_obj_refs_table(refs_table); + + if (show_pinned) + delete_pinned_obj_table(link_table); + + return errno == ENOENT ? 0 : -1; +} + +static int do_pin(int argc, char **argv) +{ + int err; + + err = do_pin_any(argc, argv, link_parse_fd); + if (!err && json_output) + jsonw_null(json_wtr); + return err; +} + +static int do_detach(int argc, char **argv) +{ + int err, fd; + + if (argc != 2) { + p_err("link specifier is invalid or missing\n"); + return 1; + } + + fd = link_parse_fd(&argc, &argv); + if (fd < 0) + return 1; + + err = bpf_link_detach(fd); + if (err) + err = -errno; + close(fd); + if (err) { + p_err("failed link detach: %s", strerror(-err)); + return 1; + } + + if (json_output) + jsonw_null(json_wtr); + + return 0; +} + +static int do_help(int argc, char **argv) +{ + if (json_output) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %1$s %2$s { show | list } [LINK]\n" + " %1$s %2$s pin LINK FILE\n" + " %1$s %2$s detach LINK\n" + " %1$s %2$s help\n" + "\n" + " " HELP_SPEC_LINK "\n" + " " HELP_SPEC_OPTIONS " |\n" + " {-f|--bpffs} | {-n|--nomount} }\n" + "", + bin_name, argv[-2]); + + return 0; +} + +static const struct cmd cmds[] = { + { "show", do_show }, + { "list", do_show }, + { "help", do_help }, + { "pin", do_pin }, + { "detach", do_detach }, + { 0 } +}; + +int do_link(int argc, char **argv) +{ + return cmd_select(cmds, argc, argv, do_help); +} diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c new file mode 100644 index 000000000..ccd7457f9 --- /dev/null +++ b/tools/bpf/bpftool/main.c @@ -0,0 +1,539 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2017-2018 Netronome Systems, Inc. */ + +#include <ctype.h> +#include <errno.h> +#include <getopt.h> +#include <linux/bpf.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> + +#include <bpf/bpf.h> +#include <bpf/btf.h> +#include <bpf/hashmap.h> +#include <bpf/libbpf.h> + +#include "main.h" + +#define BATCH_LINE_LEN_MAX 65536 +#define BATCH_ARG_NB_MAX 4096 + +const char *bin_name; +static int last_argc; +static char **last_argv; +static int (*last_do_help)(int argc, char **argv); +json_writer_t *json_wtr; +bool pretty_output; +bool json_output; +bool show_pinned; +bool block_mount; +bool verifier_logs; +bool relaxed_maps; +bool use_loader; +bool legacy_libbpf; +struct btf *base_btf; +struct hashmap *refs_table; + +static void __noreturn clean_and_exit(int i) +{ + if (json_output) + jsonw_destroy(&json_wtr); + + exit(i); +} + +void usage(void) +{ + last_do_help(last_argc - 1, last_argv + 1); + + clean_and_exit(-1); +} + +static int do_help(int argc, char **argv) +{ + if (json_output) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %s [OPTIONS] OBJECT { COMMAND | help }\n" + " %s batch file FILE\n" + " %s version\n" + "\n" + " OBJECT := { prog | map | link | cgroup | perf | net | feature | btf | gen | struct_ops | iter }\n" + " " HELP_SPEC_OPTIONS " |\n" + " {-V|--version} }\n" + "", + bin_name, bin_name, bin_name); + + return 0; +} + +#ifndef BPFTOOL_VERSION +/* bpftool's major and minor version numbers are aligned on libbpf's. There is + * an offset of 6 for the version number, because bpftool's version was higher + * than libbpf's when we adopted this scheme. The patch number remains at 0 + * for now. Set BPFTOOL_VERSION to override. + */ +#define BPFTOOL_MAJOR_VERSION (LIBBPF_MAJOR_VERSION + 6) +#define BPFTOOL_MINOR_VERSION LIBBPF_MINOR_VERSION +#define BPFTOOL_PATCH_VERSION 0 +#endif + +static int do_version(int argc, char **argv) +{ +#ifdef HAVE_LIBBFD_SUPPORT + const bool has_libbfd = true; +#else + const bool has_libbfd = false; +#endif +#ifdef BPFTOOL_WITHOUT_SKELETONS + const bool has_skeletons = false; +#else + const bool has_skeletons = true; +#endif + + if (json_output) { + jsonw_start_object(json_wtr); /* root object */ + + jsonw_name(json_wtr, "version"); +#ifdef BPFTOOL_VERSION + jsonw_printf(json_wtr, "\"%s\"", BPFTOOL_VERSION); +#else + jsonw_printf(json_wtr, "\"%d.%d.%d\"", BPFTOOL_MAJOR_VERSION, + BPFTOOL_MINOR_VERSION, BPFTOOL_PATCH_VERSION); +#endif + jsonw_name(json_wtr, "libbpf_version"); + jsonw_printf(json_wtr, "\"%d.%d\"", + libbpf_major_version(), libbpf_minor_version()); + + jsonw_name(json_wtr, "features"); + jsonw_start_object(json_wtr); /* features */ + jsonw_bool_field(json_wtr, "libbfd", has_libbfd); + jsonw_bool_field(json_wtr, "libbpf_strict", !legacy_libbpf); + jsonw_bool_field(json_wtr, "skeletons", has_skeletons); + jsonw_end_object(json_wtr); /* features */ + + jsonw_end_object(json_wtr); /* root object */ + } else { + unsigned int nb_features = 0; + +#ifdef BPFTOOL_VERSION + printf("%s v%s\n", bin_name, BPFTOOL_VERSION); +#else + printf("%s v%d.%d.%d\n", bin_name, BPFTOOL_MAJOR_VERSION, + BPFTOOL_MINOR_VERSION, BPFTOOL_PATCH_VERSION); +#endif + printf("using libbpf %s\n", libbpf_version_string()); + printf("features:"); + if (has_libbfd) { + printf(" libbfd"); + nb_features++; + } + if (!legacy_libbpf) { + printf("%s libbpf_strict", nb_features++ ? "," : ""); + nb_features++; + } + if (has_skeletons) + printf("%s skeletons", nb_features++ ? "," : ""); + printf("\n"); + } + return 0; +} + +int cmd_select(const struct cmd *cmds, int argc, char **argv, + int (*help)(int argc, char **argv)) +{ + unsigned int i; + + last_argc = argc; + last_argv = argv; + last_do_help = help; + + if (argc < 1 && cmds[0].func) + return cmds[0].func(argc, argv); + + for (i = 0; cmds[i].cmd; i++) { + if (is_prefix(*argv, cmds[i].cmd)) { + if (!cmds[i].func) { + p_err("command '%s' is not supported in bootstrap mode", + cmds[i].cmd); + return -1; + } + return cmds[i].func(argc - 1, argv + 1); + } + } + + help(argc - 1, argv + 1); + + return -1; +} + +bool is_prefix(const char *pfx, const char *str) +{ + if (!pfx) + return false; + if (strlen(str) < strlen(pfx)) + return false; + + 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; + unsigned int i; + + for (i = 0; i < n; i++) { + const char *pfx = ""; + + if (!i) + /* nothing */; + else if (!(i % 16)) + fprintf(f, "\n"); + else if (!(i % 8)) + fprintf(f, " "); + else + pfx = sep; + + fprintf(f, "%s%02hhx", i ? pfx : "", data[i]); + } +} + +/* Split command line into argument vector. */ +static int make_args(char *line, char *n_argv[], int maxargs, int cmd_nb) +{ + static const char ws[] = " \t\r\n"; + char *cp = line; + int n_argc = 0; + + while (*cp) { + /* Skip leading whitespace. */ + cp += strspn(cp, ws); + + if (*cp == '\0') + break; + + if (n_argc >= (maxargs - 1)) { + p_err("too many arguments to command %d", cmd_nb); + return -1; + } + + /* Word begins with quote. */ + if (*cp == '\'' || *cp == '"') { + char quote = *cp++; + + n_argv[n_argc++] = cp; + /* Find ending quote. */ + cp = strchr(cp, quote); + if (!cp) { + p_err("unterminated quoted string in command %d", + cmd_nb); + return -1; + } + } else { + n_argv[n_argc++] = cp; + + /* Find end of word. */ + cp += strcspn(cp, ws); + if (*cp == '\0') + break; + } + + /* Separate words. */ + *cp++ = 0; + } + n_argv[n_argc] = NULL; + + return n_argc; +} + +static int do_batch(int argc, char **argv); + +static const struct cmd cmds[] = { + { "help", do_help }, + { "batch", do_batch }, + { "prog", do_prog }, + { "map", do_map }, + { "link", do_link }, + { "cgroup", do_cgroup }, + { "perf", do_perf }, + { "net", do_net }, + { "feature", do_feature }, + { "btf", do_btf }, + { "gen", do_gen }, + { "struct_ops", do_struct_ops }, + { "iter", do_iter }, + { "version", do_version }, + { 0 } +}; + +static int do_batch(int argc, char **argv) +{ + char buf[BATCH_LINE_LEN_MAX], contline[BATCH_LINE_LEN_MAX]; + char *n_argv[BATCH_ARG_NB_MAX]; + unsigned int lines = 0; + int n_argc; + FILE *fp; + char *cp; + int err = 0; + int i; + + if (argc < 2) { + p_err("too few parameters for batch"); + return -1; + } else if (!is_prefix(*argv, "file")) { + p_err("expected 'file', got: %s", *argv); + return -1; + } else if (argc > 2) { + p_err("too many parameters for batch"); + return -1; + } + NEXT_ARG(); + + if (!strcmp(*argv, "-")) + fp = stdin; + else + fp = fopen(*argv, "r"); + if (!fp) { + p_err("Can't open file (%s): %s", *argv, strerror(errno)); + return -1; + } + + if (json_output) + jsonw_start_array(json_wtr); + while (fgets(buf, sizeof(buf), fp)) { + cp = strchr(buf, '#'); + if (cp) + *cp = '\0'; + + if (strlen(buf) == sizeof(buf) - 1) { + errno = E2BIG; + break; + } + + /* Append continuation lines if any (coming after a line ending + * with '\' in the batch file). + */ + while ((cp = strstr(buf, "\\\n")) != NULL) { + if (!fgets(contline, sizeof(contline), fp) || + strlen(contline) == 0) { + p_err("missing continuation line on command %d", + lines); + err = -1; + goto err_close; + } + + cp = strchr(contline, '#'); + if (cp) + *cp = '\0'; + + if (strlen(buf) + strlen(contline) + 1 > sizeof(buf)) { + p_err("command %d is too long", lines); + err = -1; + goto err_close; + } + buf[strlen(buf) - 2] = '\0'; + strcat(buf, contline); + } + + n_argc = make_args(buf, n_argv, BATCH_ARG_NB_MAX, lines); + if (!n_argc) + continue; + if (n_argc < 0) { + err = n_argc; + goto err_close; + } + + if (json_output) { + jsonw_start_object(json_wtr); + jsonw_name(json_wtr, "command"); + jsonw_start_array(json_wtr); + for (i = 0; i < n_argc; i++) + jsonw_string(json_wtr, n_argv[i]); + jsonw_end_array(json_wtr); + jsonw_name(json_wtr, "output"); + } + + err = cmd_select(cmds, n_argc, n_argv, do_help); + + if (json_output) + jsonw_end_object(json_wtr); + + if (err) + goto err_close; + + lines++; + } + + if (errno && errno != ENOENT) { + p_err("reading batch file failed: %s", strerror(errno)); + err = -1; + } else { + if (!json_output) + printf("processed %d commands\n", lines); + } +err_close: + if (fp != stdin) + fclose(fp); + + if (json_output) + jsonw_end_array(json_wtr); + + return err; +} + +int main(int argc, char **argv) +{ + static const struct option options[] = { + { "json", no_argument, NULL, 'j' }, + { "help", no_argument, NULL, 'h' }, + { "pretty", no_argument, NULL, 'p' }, + { "version", no_argument, NULL, 'V' }, + { "bpffs", no_argument, NULL, 'f' }, + { "mapcompat", no_argument, NULL, 'm' }, + { "nomount", no_argument, NULL, 'n' }, + { "debug", no_argument, NULL, 'd' }, + { "use-loader", no_argument, NULL, 'L' }, + { "base-btf", required_argument, NULL, 'B' }, + { "legacy", no_argument, NULL, 'l' }, + { 0 } + }; + bool version_requested = false; + int opt, ret; + + setlinebuf(stdout); + +#ifdef USE_LIBCAP + /* Libcap < 2.63 hooks before main() to compute the number of + * capabilities of the running kernel, and doing so it calls prctl() + * which may fail and set errno to non-zero. + * Let's reset errno to make sure this does not interfere with the + * batch mode. + */ + errno = 0; +#endif + + last_do_help = do_help; + pretty_output = false; + json_output = false; + show_pinned = false; + block_mount = false; + bin_name = argv[0]; + + opterr = 0; + while ((opt = getopt_long(argc, argv, "VhpjfLmndB:l", + options, NULL)) >= 0) { + switch (opt) { + case 'V': + version_requested = true; + break; + case 'h': + return do_help(argc, argv); + case 'p': + pretty_output = true; + /* fall through */ + case 'j': + if (!json_output) { + json_wtr = jsonw_new(stdout); + if (!json_wtr) { + p_err("failed to create JSON writer"); + return -1; + } + json_output = true; + } + jsonw_pretty(json_wtr, pretty_output); + break; + case 'f': + show_pinned = true; + break; + case 'm': + relaxed_maps = true; + break; + case 'n': + block_mount = true; + break; + case 'd': + libbpf_set_print(print_all_levels); + verifier_logs = true; + break; + case 'B': + base_btf = btf__parse(optarg, NULL); + if (libbpf_get_error(base_btf)) { + p_err("failed to parse base BTF at '%s': %ld\n", + optarg, libbpf_get_error(base_btf)); + base_btf = NULL; + return -1; + } + break; + case 'L': + use_loader = true; + break; + case 'l': + legacy_libbpf = true; + break; + default: + p_err("unrecognized option '%s'", argv[optind - 1]); + if (json_output) + clean_and_exit(-1); + else + usage(); + } + } + + if (!legacy_libbpf) { + /* Allow legacy map definitions for skeleton generation. + * It will still be rejected if users use LIBBPF_STRICT_ALL + * mode for loading generated skeleton. + */ + libbpf_set_strict_mode(LIBBPF_STRICT_ALL & ~LIBBPF_STRICT_MAP_DEFINITIONS); + } + + argc -= optind; + argv += optind; + if (argc < 0) + usage(); + + if (version_requested) + return do_version(argc, argv); + + ret = cmd_select(cmds, argc, argv, do_help); + + if (json_output) + jsonw_destroy(&json_wtr); + + btf__free(base_btf); + + return ret; +} diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h new file mode 100644 index 000000000..5e5060c2a --- /dev/null +++ b/tools/bpf/bpftool/main.h @@ -0,0 +1,275 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* Copyright (C) 2017-2018 Netronome Systems, Inc. */ + +#ifndef __BPF_TOOL_H +#define __BPF_TOOL_H + +/* BFD and kernel.h both define GCC_VERSION, differently */ +#undef GCC_VERSION +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <linux/bpf.h> +#include <linux/compiler.h> +#include <linux/kernel.h> + +#include <bpf/hashmap.h> +#include <bpf/libbpf.h> + +#include "json_writer.h" + +/* Make sure we do not use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + +static inline __u64 ptr_to_u64(const void *ptr) +{ + return (__u64)(unsigned long)ptr; +} + +static inline void *u64_to_ptr(__u64 ptr) +{ + return (void *)(unsigned long)ptr; +} + +#define NEXT_ARG() ({ argc--; argv++; if (argc < 0) usage(); }) +#define NEXT_ARGP() ({ (*argc)--; (*argv)++; if (*argc < 0) usage(); }) +#define BAD_ARG() ({ p_err("what is '%s'?", *argv); -1; }) +#define GET_ARG() ({ argc--; *argv++; }) +#define REQ_ARGS(cnt) \ + ({ \ + int _cnt = (cnt); \ + bool _res; \ + \ + if (argc < _cnt) { \ + p_err("'%s' needs at least %d arguments, %d found", \ + argv[-1], _cnt, argc); \ + _res = false; \ + } else { \ + _res = true; \ + } \ + _res; \ + }) + +#define ERR_MAX_LEN 1024 + +#define BPF_TAG_FMT "%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx" + +#define HELP_SPEC_PROGRAM \ + "PROG := { id PROG_ID | pinned FILE | tag PROG_TAG | name PROG_NAME }" +#define HELP_SPEC_OPTIONS \ + "OPTIONS := { {-j|--json} [{-p|--pretty}] | {-d|--debug} | {-l|--legacy}" +#define HELP_SPEC_MAP \ + "MAP := { id MAP_ID | pinned FILE | name MAP_NAME }" +#define HELP_SPEC_LINK \ + "LINK := { id LINK_ID | pinned FILE }" + +/* keep in sync with the definition in skeleton/pid_iter.bpf.c */ +enum bpf_obj_type { + BPF_OBJ_UNKNOWN, + BPF_OBJ_PROG, + BPF_OBJ_MAP, + BPF_OBJ_LINK, + BPF_OBJ_BTF, +}; + +extern const char *bin_name; + +extern json_writer_t *json_wtr; +extern bool json_output; +extern bool show_pinned; +extern bool show_pids; +extern bool block_mount; +extern bool verifier_logs; +extern bool relaxed_maps; +extern bool use_loader; +extern bool legacy_libbpf; +extern struct btf *base_btf; +extern struct hashmap *refs_table; + +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; + +void set_max_rlimit(void); + +int mount_tracefs(const char *target); + +struct obj_ref { + int pid; + char comm[16]; +}; + +struct obj_refs { + int ref_cnt; + bool has_bpf_cookie; + struct obj_ref *refs; + __u64 bpf_cookie; +}; + +struct btf; +struct bpf_line_info; + +int build_pinned_obj_table(struct hashmap *table, + enum bpf_obj_type type); +void delete_pinned_obj_table(struct hashmap *table); +__weak int build_obj_refs_table(struct hashmap **table, + enum bpf_obj_type type); +__weak void delete_obj_refs_table(struct hashmap *table); +__weak void emit_obj_refs_json(struct hashmap *table, __u32 id, + json_writer_t *json_wtr); +__weak void emit_obj_refs_plain(struct hashmap *table, __u32 id, + const char *prefix); +void print_dev_plain(__u32 ifindex, __u64 ns_dev, __u64 ns_inode); +void print_dev_json(__u32 ifindex, __u64 ns_dev, __u64 ns_inode); + +struct cmd { + const char *cmd; + int (*func)(int argc, char **argv); +}; + +int cmd_select(const struct cmd *cmds, int argc, char **argv, + int (*help)(int argc, char **argv)); + +#define MAX_PROG_FULL_NAME 128 +void get_prog_full_name(const struct bpf_prog_info *prog_info, int prog_fd, + char *name_buff, size_t buff_len); + +int get_fd_type(int fd); +const char *get_fd_type_name(enum bpf_obj_type type); +char *get_fdinfo(int fd, const char *key); +int open_obj_pinned(const char *path, bool quiet); +int open_obj_pinned_any(const char *path, enum bpf_obj_type exp_type); +int mount_bpffs_for_pin(const char *name); +int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(int *, char ***)); +int do_pin_fd(int fd, const char *name); + +/* commands available in bootstrap mode */ +int do_gen(int argc, char **argv); +int do_btf(int argc, char **argv); + +/* non-bootstrap only commands */ +int do_prog(int argc, char **arg) __weak; +int do_map(int argc, char **arg) __weak; +int do_link(int argc, char **arg) __weak; +int do_event_pipe(int argc, char **argv) __weak; +int do_cgroup(int argc, char **arg) __weak; +int do_perf(int argc, char **arg) __weak; +int do_net(int argc, char **arg) __weak; +int do_tracelog(int argc, char **arg) __weak; +int do_feature(int argc, char **argv) __weak; +int do_struct_ops(int argc, char **argv) __weak; +int do_iter(int argc, char **argv) __weak; + +int parse_u32_arg(int *argc, char ***argv, __u32 *val, const char *what); +int prog_parse_fd(int *argc, char ***argv); +int prog_parse_fds(int *argc, char ***argv, int **fds); +int map_parse_fd(int *argc, char ***argv); +int map_parse_fds(int *argc, char ***argv, int **fds); +int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len); + +struct bpf_prog_linfo; +#ifdef HAVE_LIBBFD_SUPPORT +void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes, + const char *arch, const char *disassembler_options, + const struct btf *btf, + const struct bpf_prog_linfo *prog_linfo, + __u64 func_ksym, unsigned int func_idx, + bool linum); +int disasm_init(void); +#else +static inline +void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes, + const char *arch, const char *disassembler_options, + const struct btf *btf, + const struct bpf_prog_linfo *prog_linfo, + __u64 func_ksym, unsigned int func_idx, + bool linum) +{ +} +static inline int disasm_init(void) +{ + p_err("No libbfd support"); + return -1; +} +#endif +void print_data_json(uint8_t *data, size_t len); +void print_hex_data_json(uint8_t *data, size_t len); + +unsigned int get_page_size(void); +unsigned int get_possible_cpus(void); +const char * +ifindex_to_bfd_params(__u32 ifindex, __u64 ns_dev, __u64 ns_ino, + const char **opt); + +struct btf_dumper { + const struct btf *btf; + json_writer_t *jw; + bool is_plain_text; + bool prog_id_as_func_ptr; +}; + +/* btf_dumper_type - print data along with type information + * @d: an instance containing context for dumping types + * @type_id: index in btf->types array. this points to the type to be dumped + * @data: pointer the actual data, i.e. the values to be printed + * + * Returns zero on success and negative error code otherwise + */ +int btf_dumper_type(const struct btf_dumper *d, __u32 type_id, + const void *data); +void btf_dumper_type_only(const struct btf *btf, __u32 func_type_id, + char *func_only, int size); + +void btf_dump_linfo_plain(const struct btf *btf, + const struct bpf_line_info *linfo, + const char *prefix, bool linum); +void btf_dump_linfo_json(const struct btf *btf, + const struct bpf_line_info *linfo, bool linum); + +struct nlattr; +struct ifinfomsg; +struct tcmsg; +int do_xdp_dump(struct ifinfomsg *ifinfo, struct nlattr **tb); +int do_filter_dump(struct tcmsg *ifinfo, struct nlattr **tb, const char *kind, + const char *devname, int ifindex); + +int print_all_levels(__maybe_unused enum libbpf_print_level level, + const char *format, va_list args); + +size_t hash_fn_for_key_as_id(const void *key, void *ctx); +bool equal_fn_for_key_as_id(const void *k1, const void *k2, void *ctx); + +/* bpf_attach_type_input_str - convert the provided attach type value into a + * textual representation that we accept for input purposes. + * + * This function is similar in nature to libbpf_bpf_attach_type_str, but + * recognizes some attach type names that have been used by the program in the + * past and which do not follow the string inference scheme that libbpf uses. + * These textual representations should only be used for user input. + * + * @t: The attach type + * Returns a pointer to a static string identifying the attach type. NULL is + * returned for unknown bpf_attach_type values. + */ +const char *bpf_attach_type_input_str(enum bpf_attach_type t); + +static inline void *u32_as_hash_field(__u32 x) +{ + return (void *)(uintptr_t)x; +} + +static inline __u32 hash_field_as_u32(const void *x) +{ + return (__u32)(uintptr_t)x; +} + +static inline bool hashmap__empty(struct hashmap *map) +{ + return map ? hashmap__size(map) == 0 : true; +} + +#endif diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c new file mode 100644 index 000000000..9a6ca9f31 --- /dev/null +++ b/tools/bpf/bpftool/map.c @@ -0,0 +1,1495 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2017-2018 Netronome Systems, Inc. */ + +#include <assert.h> +#include <errno.h> +#include <fcntl.h> +#include <linux/err.h> +#include <linux/kernel.h> +#include <net/if.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <sys/types.h> +#include <sys/stat.h> + +#include <bpf/bpf.h> +#include <bpf/btf.h> +#include <bpf/hashmap.h> + +#include "json_writer.h" +#include "main.h" + +static struct hashmap *map_table; + +static bool map_is_per_cpu(__u32 type) +{ + return type == BPF_MAP_TYPE_PERCPU_HASH || + type == BPF_MAP_TYPE_PERCPU_ARRAY || + type == BPF_MAP_TYPE_LRU_PERCPU_HASH || + type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE; +} + +static bool map_is_map_of_maps(__u32 type) +{ + return type == BPF_MAP_TYPE_ARRAY_OF_MAPS || + type == BPF_MAP_TYPE_HASH_OF_MAPS; +} + +static bool map_is_map_of_progs(__u32 type) +{ + return type == BPF_MAP_TYPE_PROG_ARRAY; +} + +static int map_type_from_str(const char *type) +{ + const char *map_type_str; + unsigned int i; + + for (i = 0; ; i++) { + map_type_str = libbpf_bpf_map_type_str(i); + if (!map_type_str) + break; + + /* Don't allow prefixing in case of possible future shadowing */ + if (!strcmp(map_type_str, type)) + return i; + } + return -1; +} + +static void *alloc_value(struct bpf_map_info *info) +{ + if (map_is_per_cpu(info->type)) + return malloc(round_up(info->value_size, 8) * + get_possible_cpus()); + else + return malloc(info->value_size); +} + +static int do_dump_btf(const struct btf_dumper *d, + struct bpf_map_info *map_info, void *key, + void *value) +{ + __u32 value_id; + int ret = 0; + + /* start of key-value pair */ + jsonw_start_object(d->jw); + + 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; + } + + value_id = map_info->btf_vmlinux_value_type_id ? + : map_info->btf_value_type_id; + + if (!map_is_per_cpu(map_info->type)) { + jsonw_name(d->jw, "value"); + ret = btf_dumper_type(d, value_id, value); + } else { + unsigned int i, n, step; + + jsonw_name(d->jw, "values"); + jsonw_start_array(d->jw); + n = get_possible_cpus(); + step = round_up(map_info->value_size, 8); + for (i = 0; i < n; i++) { + jsonw_start_object(d->jw); + jsonw_int_field(d->jw, "cpu", i); + jsonw_name(d->jw, "value"); + ret = btf_dumper_type(d, value_id, value + i * step); + jsonw_end_object(d->jw); + if (ret) + break; + } + jsonw_end_array(d->jw); + } + +err_end_obj: + /* end of key-value pair */ + jsonw_end_object(d->jw); + + return ret; +} + +static json_writer_t *get_btf_writer(void) +{ + json_writer_t *jw = jsonw_new(stdout); + + if (!jw) + return NULL; + jsonw_pretty(jw, true); + + return jw; +} + +static void print_entry_json(struct bpf_map_info *info, unsigned char *key, + unsigned char *value, struct btf *btf) +{ + jsonw_start_object(json_wtr); + + if (!map_is_per_cpu(info->type)) { + jsonw_name(json_wtr, "key"); + print_hex_data_json(key, info->key_size); + jsonw_name(json_wtr, "value"); + print_hex_data_json(value, info->value_size); + if (btf) { + struct btf_dumper d = { + .btf = btf, + .jw = json_wtr, + .is_plain_text = false, + }; + + jsonw_name(json_wtr, "formatted"); + do_dump_btf(&d, info, key, value); + } + } else { + unsigned int i, n, step; + + n = get_possible_cpus(); + step = round_up(info->value_size, 8); + + jsonw_name(json_wtr, "key"); + print_hex_data_json(key, info->key_size); + + jsonw_name(json_wtr, "values"); + jsonw_start_array(json_wtr); + for (i = 0; i < n; i++) { + jsonw_start_object(json_wtr); + + jsonw_int_field(json_wtr, "cpu", i); + + jsonw_name(json_wtr, "value"); + print_hex_data_json(value + i * step, + info->value_size); + + jsonw_end_object(json_wtr); + } + jsonw_end_array(json_wtr); + if (btf) { + struct btf_dumper d = { + .btf = btf, + .jw = json_wtr, + .is_plain_text = false, + }; + + jsonw_name(json_wtr, "formatted"); + do_dump_btf(&d, info, key, value); + } + } + + jsonw_end_object(json_wtr); +} + +static void +print_entry_error_msg(struct bpf_map_info *info, unsigned char *key, + const char *error_msg) +{ + int msg_size = strlen(error_msg); + bool single_line, 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' : ' ', error_msg); + + printf("\n"); +} + +static void +print_entry_error(struct bpf_map_info *map_info, void *key, int lookup_errno) +{ + /* For prog_array maps or arrays of maps, failure to lookup the value + * means there is no entry for that key. Do not print an error message + * in that case. + */ + if ((map_is_map_of_maps(map_info->type) || + map_is_map_of_progs(map_info->type)) && lookup_errno == ENOENT) + return; + + if (json_output) { + jsonw_start_object(json_wtr); /* entry */ + jsonw_name(json_wtr, "key"); + print_hex_data_json(key, map_info->key_size); + jsonw_name(json_wtr, "value"); + jsonw_start_object(json_wtr); /* error */ + jsonw_string_field(json_wtr, "error", strerror(lookup_errno)); + jsonw_end_object(json_wtr); /* error */ + jsonw_end_object(json_wtr); /* entry */ + } else { + 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_msg(map_info, key, + msg ? : strerror(lookup_errno)); + } +} + +static void print_entry_plain(struct bpf_map_info *info, unsigned char *key, + unsigned char *value) +{ + if (!map_is_per_cpu(info->type)) { + bool single_line, break_names; + + break_names = info->key_size > 16 || info->value_size > 16; + single_line = info->key_size + info->value_size <= 24 && + !break_names; + + if (info->key_size) { + printf("key:%c", break_names ? '\n' : ' '); + fprint_hex(stdout, key, info->key_size, " "); + + printf(single_line ? " " : "\n"); + } + + if (info->value_size) { + printf("value:%c", break_names ? '\n' : ' '); + fprint_hex(stdout, value, info->value_size, " "); + } + + printf("\n"); + } else { + unsigned int i, n, step; + + n = get_possible_cpus(); + step = round_up(info->value_size, 8); + + if (info->key_size) { + printf("key:\n"); + fprint_hex(stdout, key, info->key_size, " "); + printf("\n"); + } + if (info->value_size) { + for (i = 0; i < n; i++) { + printf("value (CPU %02d):%c", + i, info->value_size > 16 ? '\n' : ' '); + fprint_hex(stdout, value + i * step, + info->value_size, " "); + printf("\n"); + } + } + } +} + +static char **parse_bytes(char **argv, const char *name, unsigned char *val, + unsigned int n) +{ + unsigned int i = 0, base = 0; + char *endptr; + + if (is_prefix(*argv, "hex")) { + base = 16; + argv++; + } + + while (i < n && argv[i]) { + val[i] = strtoul(argv[i], &endptr, base); + if (*endptr) { + p_err("error parsing byte: %s", argv[i]); + return NULL; + } + i++; + } + + if (i != n) { + p_err("%s expected %d bytes got %d", name, n, i); + return NULL; + } + + return argv + i; +} + +/* on per cpu maps we must copy the provided value on all value instances */ +static void fill_per_cpu_value(struct bpf_map_info *info, void *value) +{ + unsigned int i, n, step; + + if (!map_is_per_cpu(info->type)) + return; + + n = get_possible_cpus(); + step = round_up(info->value_size, 8); + for (i = 1; i < n; i++) + memcpy(value + i * step, value, info->value_size); +} + +static int parse_elem(char **argv, struct bpf_map_info *info, + void *key, void *value, __u32 key_size, __u32 value_size, + __u32 *flags, __u32 **value_fd) +{ + if (!*argv) { + if (!key && !value) + return 0; + p_err("did not find %s", key ? "key" : "value"); + return -1; + } + + if (is_prefix(*argv, "key")) { + if (!key) { + if (key_size) + p_err("duplicate key"); + else + p_err("unnecessary key"); + return -1; + } + + argv = parse_bytes(argv + 1, "key", key, key_size); + if (!argv) + return -1; + + return parse_elem(argv, info, NULL, value, key_size, value_size, + flags, value_fd); + } else if (is_prefix(*argv, "value")) { + int fd; + + if (!value) { + if (value_size) + p_err("duplicate value"); + else + p_err("unnecessary value"); + return -1; + } + + argv++; + + if (map_is_map_of_maps(info->type)) { + int argc = 2; + + if (value_size != 4) { + p_err("value smaller than 4B for map in map?"); + return -1; + } + if (!argv[0] || !argv[1]) { + p_err("not enough value arguments for map in map"); + return -1; + } + + fd = map_parse_fd(&argc, &argv); + if (fd < 0) + return -1; + + *value_fd = value; + **value_fd = fd; + } else if (map_is_map_of_progs(info->type)) { + int argc = 2; + + if (value_size != 4) { + p_err("value smaller than 4B for map of progs?"); + return -1; + } + if (!argv[0] || !argv[1]) { + p_err("not enough value arguments for map of progs"); + return -1; + } + if (is_prefix(*argv, "id")) + p_info("Warning: updating program array via MAP_ID, make sure this map is kept open\n" + " by some process or pinned otherwise update will be lost"); + + fd = prog_parse_fd(&argc, &argv); + if (fd < 0) + return -1; + + *value_fd = value; + **value_fd = fd; + } else { + argv = parse_bytes(argv, "value", value, value_size); + if (!argv) + return -1; + + fill_per_cpu_value(info, value); + } + + return parse_elem(argv, info, key, NULL, key_size, value_size, + flags, NULL); + } else if (is_prefix(*argv, "any") || is_prefix(*argv, "noexist") || + is_prefix(*argv, "exist")) { + if (!flags) { + p_err("flags specified multiple times: %s", *argv); + return -1; + } + + if (is_prefix(*argv, "any")) + *flags = BPF_ANY; + else if (is_prefix(*argv, "noexist")) + *flags = BPF_NOEXIST; + else if (is_prefix(*argv, "exist")) + *flags = BPF_EXIST; + + return parse_elem(argv + 1, info, key, value, key_size, + value_size, NULL, value_fd); + } + + p_err("expected key or value, got: %s", *argv); + return -1; +} + +static void show_map_header_json(struct bpf_map_info *info, json_writer_t *wtr) +{ + const char *map_type_str; + + jsonw_uint_field(wtr, "id", info->id); + map_type_str = libbpf_bpf_map_type_str(info->type); + if (map_type_str) + jsonw_string_field(wtr, "type", map_type_str); + else + jsonw_uint_field(wtr, "type", info->type); + + if (*info->name) + jsonw_string_field(wtr, "name", info->name); + + jsonw_name(wtr, "flags"); + jsonw_printf(wtr, "%d", info->map_flags); +} + +static int show_map_close_json(int fd, struct bpf_map_info *info) +{ + char *memlock, *frozen_str; + int frozen = 0; + + memlock = get_fdinfo(fd, "memlock"); + frozen_str = get_fdinfo(fd, "frozen"); + + jsonw_start_object(json_wtr); + + show_map_header_json(info, json_wtr); + + print_dev_json(info->ifindex, info->netns_dev, info->netns_ino); + + jsonw_uint_field(json_wtr, "bytes_key", info->key_size); + jsonw_uint_field(json_wtr, "bytes_value", info->value_size); + jsonw_uint_field(json_wtr, "max_entries", info->max_entries); + + if (memlock) + jsonw_int_field(json_wtr, "bytes_memlock", atoll(memlock)); + free(memlock); + + if (info->type == BPF_MAP_TYPE_PROG_ARRAY) { + char *owner_prog_type = get_fdinfo(fd, "owner_prog_type"); + char *owner_jited = get_fdinfo(fd, "owner_jited"); + + if (owner_prog_type) { + unsigned int prog_type = atoi(owner_prog_type); + const char *prog_type_str; + + prog_type_str = libbpf_bpf_prog_type_str(prog_type); + if (prog_type_str) + jsonw_string_field(json_wtr, "owner_prog_type", + prog_type_str); + else + jsonw_uint_field(json_wtr, "owner_prog_type", + prog_type); + } + if (owner_jited) + jsonw_bool_field(json_wtr, "owner_jited", + !!atoi(owner_jited)); + + free(owner_prog_type); + free(owner_jited); + } + 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 (!hashmap__empty(map_table)) { + struct hashmap_entry *entry; + + jsonw_name(json_wtr, "pinned"); + jsonw_start_array(json_wtr); + hashmap__for_each_key_entry(map_table, entry, + u32_as_hash_field(info->id)) + jsonw_string(json_wtr, entry->value); + jsonw_end_array(json_wtr); + } + + emit_obj_refs_json(refs_table, info->id, json_wtr); + + jsonw_end_object(json_wtr); + + return 0; +} + +static void show_map_header_plain(struct bpf_map_info *info) +{ + const char *map_type_str; + + printf("%u: ", info->id); + + map_type_str = libbpf_bpf_map_type_str(info->type); + if (map_type_str) + printf("%s ", map_type_str); + else + printf("type %u ", info->type); + + if (*info->name) + printf("name %s ", info->name); + + printf("flags 0x%x", info->map_flags); + print_dev_plain(info->ifindex, info->netns_dev, info->netns_ino); + printf("\n"); +} + +static int show_map_close_plain(int fd, struct bpf_map_info *info) +{ + char *memlock, *frozen_str; + int frozen = 0; + + memlock = get_fdinfo(fd, "memlock"); + frozen_str = get_fdinfo(fd, "frozen"); + + show_map_header_plain(info); + printf("\tkey %uB value %uB max_entries %u", + info->key_size, info->value_size, info->max_entries); + + if (memlock) + printf(" memlock %sB", memlock); + free(memlock); + + if (info->type == BPF_MAP_TYPE_PROG_ARRAY) { + char *owner_prog_type = get_fdinfo(fd, "owner_prog_type"); + char *owner_jited = get_fdinfo(fd, "owner_jited"); + + if (owner_prog_type || owner_jited) + printf("\n\t"); + if (owner_prog_type) { + unsigned int prog_type = atoi(owner_prog_type); + const char *prog_type_str; + + prog_type_str = libbpf_bpf_prog_type_str(prog_type); + if (prog_type_str) + printf("owner_prog_type %s ", prog_type_str); + else + printf("owner_prog_type %d ", prog_type); + } + if (owner_jited) + printf("owner%s jited", + atoi(owner_jited) ? "" : " not"); + + free(owner_prog_type); + free(owner_jited); + } + close(fd); + + if (!hashmap__empty(map_table)) { + struct hashmap_entry *entry; + + hashmap__for_each_key_entry(map_table, entry, + u32_as_hash_field(info->id)) + printf("\n\tpinned %s", (char *)entry->value); + } + + if (frozen_str) { + frozen = atoi(frozen_str); + free(frozen_str); + } + + if (info->btf_id || frozen) + printf("\n\t"); + + if (info->btf_id) + printf("btf_id %d", info->btf_id); + + if (frozen) + printf("%sfrozen", info->btf_id ? " " : ""); + + emit_obj_refs_plain(refs_table, info->id, "\n\tpids "); + + printf("\n"); + return 0; +} + +static int do_show_subset(int argc, char **argv) +{ + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + int *fds = NULL; + int nb_fds, i; + int err = -1; + + fds = malloc(sizeof(int)); + if (!fds) { + p_err("mem alloc failed"); + return -1; + } + nb_fds = map_parse_fds(&argc, &argv, &fds); + if (nb_fds < 1) + goto exit_free; + + if (json_output && nb_fds > 1) + jsonw_start_array(json_wtr); /* root array */ + for (i = 0; i < nb_fds; i++) { + err = bpf_obj_get_info_by_fd(fds[i], &info, &len); + if (err) { + p_err("can't get map info: %s", + strerror(errno)); + for (; i < nb_fds; i++) + close(fds[i]); + break; + } + + if (json_output) + show_map_close_json(fds[i], &info); + else + show_map_close_plain(fds[i], &info); + + close(fds[i]); + } + if (json_output && nb_fds > 1) + jsonw_end_array(json_wtr); /* root array */ + +exit_free: + free(fds); + return err; +} + +static int do_show(int argc, char **argv) +{ + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + __u32 id = 0; + int err; + int fd; + + if (show_pinned) { + map_table = hashmap__new(hash_fn_for_key_as_id, + equal_fn_for_key_as_id, NULL); + if (IS_ERR(map_table)) { + p_err("failed to create hashmap for pinned paths"); + return -1; + } + build_pinned_obj_table(map_table, BPF_OBJ_MAP); + } + build_obj_refs_table(&refs_table, BPF_OBJ_MAP); + + if (argc == 2) + return do_show_subset(argc, argv); + + if (argc) + return BAD_ARG(); + + if (json_output) + jsonw_start_array(json_wtr); + while (true) { + err = bpf_map_get_next_id(id, &id); + if (err) { + if (errno == ENOENT) + break; + p_err("can't get next map: %s%s", strerror(errno), + errno == EINVAL ? " -- kernel too old?" : ""); + break; + } + + fd = bpf_map_get_fd_by_id(id); + if (fd < 0) { + if (errno == ENOENT) + continue; + p_err("can't get map by id (%u): %s", + id, strerror(errno)); + break; + } + + err = bpf_obj_get_info_by_fd(fd, &info, &len); + if (err) { + p_err("can't get map info: %s", strerror(errno)); + close(fd); + break; + } + + if (json_output) + show_map_close_json(fd, &info); + else + show_map_close_plain(fd, &info); + } + if (json_output) + jsonw_end_array(json_wtr); + + delete_obj_refs_table(refs_table); + + if (show_pinned) + delete_pinned_obj_table(map_table); + + return errno == ENOENT ? 0 : -1; +} + +static int dump_map_elem(int fd, void *key, void *value, + struct bpf_map_info *map_info, struct btf *btf, + json_writer_t *btf_wtr) +{ + if (bpf_map_lookup_elem(fd, key, value)) { + print_entry_error(map_info, key, errno); + return -1; + } + + if (json_output) { + print_entry_json(map_info, key, value, btf); + } else if (btf) { + struct btf_dumper d = { + .btf = btf, + .jw = btf_wtr, + .is_plain_text = true, + }; + + do_dump_btf(&d, map_info, key, value); + } else { + print_entry_plain(map_info, key, value); + } + + return 0; +} + +static int maps_have_btf(int *fds, int nb_fds) +{ + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + int err, i; + + for (i = 0; i < nb_fds; i++) { + err = bpf_obj_get_info_by_fd(fds[i], &info, &len); + if (err) { + p_err("can't get map info: %s", strerror(errno)); + return -1; + } + + if (!info.btf_id) + return 0; + } + + return 1; +} + +static struct btf *btf_vmlinux; + +static int get_map_kv_btf(const struct bpf_map_info *info, struct btf **btf) +{ + int err = 0; + + if (info->btf_vmlinux_value_type_id) { + if (!btf_vmlinux) { + btf_vmlinux = libbpf_find_kernel_btf(); + err = libbpf_get_error(btf_vmlinux); + if (err) { + p_err("failed to get kernel btf"); + return err; + } + } + *btf = btf_vmlinux; + } else if (info->btf_value_type_id) { + *btf = btf__load_from_kernel_by_id(info->btf_id); + err = libbpf_get_error(*btf); + if (err) + p_err("failed to get btf"); + } else { + *btf = NULL; + } + + return err; +} + +static void free_map_kv_btf(struct btf *btf) +{ + if (!libbpf_get_error(btf) && btf != btf_vmlinux) + btf__free(btf); +} + +static void free_btf_vmlinux(void) +{ + if (!libbpf_get_error(btf_vmlinux)) + btf__free(btf_vmlinux); +} + +static int +map_dump(int fd, struct bpf_map_info *info, json_writer_t *wtr, + bool show_header) +{ + void *key, *value, *prev_key; + unsigned int num_elems = 0; + struct btf *btf = NULL; + int err; + + key = malloc(info->key_size); + value = alloc_value(info); + if (!key || !value) { + p_err("mem alloc failed"); + err = -1; + goto exit_free; + } + + prev_key = NULL; + + if (wtr) { + err = get_map_kv_btf(info, &btf); + if (err) { + goto exit_free; + } + + if (show_header) { + jsonw_start_object(wtr); /* map object */ + show_map_header_json(info, wtr); + jsonw_name(wtr, "elements"); + } + jsonw_start_array(wtr); /* elements */ + } else if (show_header) { + show_map_header_plain(info); + } + + if (info->type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY && + info->value_size != 8) { + const char *map_type_str; + + map_type_str = libbpf_bpf_map_type_str(info->type); + p_info("Warning: cannot read values from %s map with value_size != 8", + map_type_str); + } + while (true) { + err = bpf_map_get_next_key(fd, prev_key, key); + if (err) { + if (errno == ENOENT) + err = 0; + break; + } + if (!dump_map_elem(fd, key, value, info, btf, wtr)) + num_elems++; + prev_key = key; + } + + if (wtr) { + jsonw_end_array(wtr); /* elements */ + if (show_header) + jsonw_end_object(wtr); /* map object */ + } else { + printf("Found %u element%s\n", num_elems, + num_elems != 1 ? "s" : ""); + } + +exit_free: + free(key); + free(value); + close(fd); + free_map_kv_btf(btf); + + return err; +} + +static int do_dump(int argc, char **argv) +{ + json_writer_t *wtr = NULL, *btf_wtr = NULL; + struct bpf_map_info info = {}; + int nb_fds, i = 0; + __u32 len = sizeof(info); + int *fds = NULL; + int err = -1; + + if (argc != 2) + usage(); + + fds = malloc(sizeof(int)); + if (!fds) { + p_err("mem alloc failed"); + return -1; + } + nb_fds = map_parse_fds(&argc, &argv, &fds); + if (nb_fds < 1) + goto exit_free; + + if (json_output) { + wtr = json_wtr; + } else { + int do_plain_btf; + + do_plain_btf = maps_have_btf(fds, nb_fds); + if (do_plain_btf < 0) + goto exit_close; + + if (do_plain_btf) { + btf_wtr = get_btf_writer(); + wtr = btf_wtr; + if (!btf_wtr) + p_info("failed to create json writer for btf. falling back to plain output"); + } + } + + if (wtr && nb_fds > 1) + jsonw_start_array(wtr); /* root array */ + for (i = 0; i < nb_fds; i++) { + if (bpf_obj_get_info_by_fd(fds[i], &info, &len)) { + p_err("can't get map info: %s", strerror(errno)); + break; + } + err = map_dump(fds[i], &info, wtr, nb_fds > 1); + if (!wtr && i != nb_fds - 1) + printf("\n"); + + if (err) + break; + close(fds[i]); + } + if (wtr && nb_fds > 1) + jsonw_end_array(wtr); /* root array */ + + if (btf_wtr) + jsonw_destroy(&btf_wtr); +exit_close: + for (; i < nb_fds; i++) + close(fds[i]); +exit_free: + free(fds); + free_btf_vmlinux(); + return err; +} + +static int alloc_key_value(struct bpf_map_info *info, void **key, void **value) +{ + *key = NULL; + *value = NULL; + + if (info->key_size) { + *key = malloc(info->key_size); + if (!*key) { + p_err("key mem alloc failed"); + return -1; + } + } + + if (info->value_size) { + *value = alloc_value(info); + if (!*value) { + p_err("value mem alloc failed"); + free(*key); + *key = NULL; + return -1; + } + } + + return 0; +} + +static int do_update(int argc, char **argv) +{ + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + __u32 *value_fd = NULL; + __u32 flags = BPF_ANY; + void *key, *value; + int fd, err; + + if (argc < 2) + usage(); + + fd = map_parse_fd_and_info(&argc, &argv, &info, &len); + if (fd < 0) + return -1; + + err = alloc_key_value(&info, &key, &value); + if (err) + goto exit_free; + + err = parse_elem(argv, &info, key, value, info.key_size, + info.value_size, &flags, &value_fd); + if (err) + goto exit_free; + + err = bpf_map_update_elem(fd, key, value, flags); + if (err) { + p_err("update failed: %s", strerror(errno)); + goto exit_free; + } + +exit_free: + if (value_fd) + close(*value_fd); + free(key); + free(value); + close(fd); + + if (!err && json_output) + jsonw_null(json_wtr); + return err; +} + +static void print_key_value(struct bpf_map_info *info, void *key, + void *value) +{ + json_writer_t *btf_wtr; + struct btf *btf; + + if (get_map_kv_btf(info, &btf)) + return; + + if (json_output) { + print_entry_json(info, key, value, btf); + } else if (btf) { + /* if here json_wtr wouldn't have been initialised, + * so let's create separate writer for btf + */ + btf_wtr = get_btf_writer(); + if (!btf_wtr) { + p_info("failed to create json writer for btf. falling back to plain output"); + btf__free(btf); + btf = NULL; + print_entry_plain(info, key, value); + } else { + struct btf_dumper d = { + .btf = btf, + .jw = btf_wtr, + .is_plain_text = true, + }; + + do_dump_btf(&d, info, key, value); + jsonw_destroy(&btf_wtr); + } + } else { + print_entry_plain(info, key, value); + } + btf__free(btf); +} + +static int do_lookup(int argc, char **argv) +{ + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + void *key, *value; + int err; + int fd; + + if (argc < 2) + usage(); + + fd = map_parse_fd_and_info(&argc, &argv, &info, &len); + if (fd < 0) + return -1; + + err = alloc_key_value(&info, &key, &value); + if (err) + goto exit_free; + + err = parse_elem(argv, &info, key, NULL, info.key_size, 0, NULL, NULL); + if (err) + goto exit_free; + + err = bpf_map_lookup_elem(fd, key, value); + if (err) { + if (errno == ENOENT) { + if (json_output) { + jsonw_null(json_wtr); + } else { + printf("key:\n"); + fprint_hex(stdout, key, info.key_size, " "); + printf("\n\nNot found\n"); + } + } else { + p_err("lookup failed: %s", strerror(errno)); + } + + goto exit_free; + } + + /* here means bpf_map_lookup_elem() succeeded */ + print_key_value(&info, key, value); + +exit_free: + free(key); + free(value); + close(fd); + + return err; +} + +static int do_getnext(int argc, char **argv) +{ + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + void *key, *nextkey; + int err; + int fd; + + if (argc < 2) + usage(); + + fd = map_parse_fd_and_info(&argc, &argv, &info, &len); + if (fd < 0) + return -1; + + key = malloc(info.key_size); + nextkey = malloc(info.key_size); + if (!key || !nextkey) { + p_err("mem alloc failed"); + err = -1; + goto exit_free; + } + + if (argc) { + err = parse_elem(argv, &info, key, NULL, info.key_size, 0, + NULL, NULL); + if (err) + goto exit_free; + } else { + free(key); + key = NULL; + } + + err = bpf_map_get_next_key(fd, key, nextkey); + if (err) { + p_err("can't get next key: %s", strerror(errno)); + goto exit_free; + } + + if (json_output) { + jsonw_start_object(json_wtr); + if (key) { + jsonw_name(json_wtr, "key"); + print_hex_data_json(key, info.key_size); + } else { + jsonw_null_field(json_wtr, "key"); + } + jsonw_name(json_wtr, "next_key"); + print_hex_data_json(nextkey, info.key_size); + jsonw_end_object(json_wtr); + } else { + if (key) { + printf("key:\n"); + fprint_hex(stdout, key, info.key_size, " "); + printf("\n"); + } else { + printf("key: None\n"); + } + printf("next key:\n"); + fprint_hex(stdout, nextkey, info.key_size, " "); + printf("\n"); + } + +exit_free: + free(nextkey); + free(key); + close(fd); + + return err; +} + +static int do_delete(int argc, char **argv) +{ + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + void *key; + int err; + int fd; + + if (argc < 2) + usage(); + + fd = map_parse_fd_and_info(&argc, &argv, &info, &len); + if (fd < 0) + return -1; + + key = malloc(info.key_size); + if (!key) { + p_err("mem alloc failed"); + err = -1; + goto exit_free; + } + + err = parse_elem(argv, &info, key, NULL, info.key_size, 0, NULL, NULL); + if (err) + goto exit_free; + + err = bpf_map_delete_elem(fd, key); + if (err) + p_err("delete failed: %s", strerror(errno)); + +exit_free: + free(key); + close(fd); + + if (!err && json_output) + jsonw_null(json_wtr); + return err; +} + +static int do_pin(int argc, char **argv) +{ + int err; + + err = do_pin_any(argc, argv, map_parse_fd); + if (!err && json_output) + jsonw_null(json_wtr); + return err; +} + +static int do_create(int argc, char **argv) +{ + LIBBPF_OPTS(bpf_map_create_opts, attr); + enum bpf_map_type map_type = BPF_MAP_TYPE_UNSPEC; + __u32 key_size = 0, value_size = 0, max_entries = 0; + const char *map_name = NULL; + const char *pinfile; + int err = -1, fd; + + if (!REQ_ARGS(7)) + return -1; + pinfile = GET_ARG(); + + while (argc) { + if (!REQ_ARGS(2)) + return -1; + + if (is_prefix(*argv, "type")) { + NEXT_ARG(); + + if (map_type) { + p_err("map type already specified"); + goto exit; + } + + map_type = map_type_from_str(*argv); + if ((int)map_type < 0) { + p_err("unrecognized map type: %s", *argv); + goto exit; + } + NEXT_ARG(); + } else if (is_prefix(*argv, "name")) { + NEXT_ARG(); + map_name = GET_ARG(); + } else if (is_prefix(*argv, "key")) { + if (parse_u32_arg(&argc, &argv, &key_size, + "key size")) + goto exit; + } else if (is_prefix(*argv, "value")) { + if (parse_u32_arg(&argc, &argv, &value_size, + "value size")) + goto exit; + } else if (is_prefix(*argv, "entries")) { + if (parse_u32_arg(&argc, &argv, &max_entries, + "max entries")) + goto exit; + } else if (is_prefix(*argv, "flags")) { + if (parse_u32_arg(&argc, &argv, &attr.map_flags, + "flags")) + goto exit; + } else if (is_prefix(*argv, "dev")) { + NEXT_ARG(); + + if (attr.map_ifindex) { + p_err("offload device already specified"); + goto exit; + } + + attr.map_ifindex = if_nametoindex(*argv); + if (!attr.map_ifindex) { + p_err("unrecognized netdevice '%s': %s", + *argv, strerror(errno)); + goto exit; + } + NEXT_ARG(); + } else if (is_prefix(*argv, "inner_map")) { + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + int inner_map_fd; + + NEXT_ARG(); + if (!REQ_ARGS(2)) + usage(); + inner_map_fd = map_parse_fd_and_info(&argc, &argv, + &info, &len); + if (inner_map_fd < 0) + return -1; + attr.inner_map_fd = inner_map_fd; + } else { + p_err("unknown arg %s", *argv); + goto exit; + } + } + + if (!map_name) { + p_err("map name not specified"); + goto exit; + } + + set_max_rlimit(); + + fd = bpf_map_create(map_type, map_name, key_size, value_size, max_entries, &attr); + if (fd < 0) { + p_err("map create failed: %s", strerror(errno)); + goto exit; + } + + err = do_pin_fd(fd, pinfile); + close(fd); + if (err) + goto exit; + + if (json_output) + jsonw_null(json_wtr); + +exit: + if (attr.inner_map_fd > 0) + close(attr.inner_map_fd); + + return err; +} + +static int do_pop_dequeue(int argc, char **argv) +{ + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + void *key, *value; + int err; + int fd; + + if (argc < 2) + usage(); + + fd = map_parse_fd_and_info(&argc, &argv, &info, &len); + if (fd < 0) + return -1; + + err = alloc_key_value(&info, &key, &value); + if (err) + goto exit_free; + + err = bpf_map_lookup_and_delete_elem(fd, key, value); + if (err) { + if (errno == ENOENT) { + if (json_output) + jsonw_null(json_wtr); + else + printf("Error: empty map\n"); + } else { + p_err("pop failed: %s", strerror(errno)); + } + + goto exit_free; + } + + print_key_value(&info, key, value); + +exit_free: + free(key); + free(value); + close(fd); + + 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) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %1$s %2$s { show | list } [MAP]\n" + " %1$s %2$s create FILE type TYPE key KEY_SIZE value VALUE_SIZE \\\n" + " entries MAX_ENTRIES name NAME [flags FLAGS] \\\n" + " [inner_map MAP] [dev NAME]\n" + " %1$s %2$s dump MAP\n" + " %1$s %2$s update MAP [key DATA] [value VALUE] [UPDATE_FLAGS]\n" + " %1$s %2$s lookup MAP [key DATA]\n" + " %1$s %2$s getnext MAP [key DATA]\n" + " %1$s %2$s delete MAP key DATA\n" + " %1$s %2$s pin MAP FILE\n" + " %1$s %2$s event_pipe MAP [cpu N index M]\n" + " %1$s %2$s peek MAP\n" + " %1$s %2$s push MAP value VALUE\n" + " %1$s %2$s pop MAP\n" + " %1$s %2$s enqueue MAP value VALUE\n" + " %1$s %2$s dequeue MAP\n" + " %1$s %2$s freeze MAP\n" + " %1$s %2$s help\n" + "\n" + " " HELP_SPEC_MAP "\n" + " DATA := { [hex] BYTES }\n" + " " HELP_SPEC_PROGRAM "\n" + " VALUE := { DATA | MAP | PROG }\n" + " UPDATE_FLAGS := { any | exist | noexist }\n" + " 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 | devmap_hash | sockmap | cpumap | xskmap | sockhash |\n" + " cgroup_storage | reuseport_sockarray | percpu_cgroup_storage |\n" + " queue | stack | sk_storage | struct_ops | ringbuf | inode_storage |\n" + " task_storage | bloom_filter | user_ringbuf }\n" + " " HELP_SPEC_OPTIONS " |\n" + " {-f|--bpffs} | {-n|--nomount} }\n" + "", + bin_name, argv[-2]); + + return 0; +} + +static const struct cmd cmds[] = { + { "show", do_show }, + { "list", do_show }, + { "help", do_help }, + { "dump", do_dump }, + { "update", do_update }, + { "lookup", do_lookup }, + { "getnext", do_getnext }, + { "delete", do_delete }, + { "pin", do_pin }, + { "event_pipe", do_event_pipe }, + { "create", do_create }, + { "peek", do_lookup }, + { "push", do_update }, + { "enqueue", do_update }, + { "pop", do_pop_dequeue }, + { "dequeue", do_pop_dequeue }, + { "freeze", do_freeze }, + { 0 } +}; + +int do_map(int argc, char **argv) +{ + return cmd_select(cmds, argc, argv, do_help); +} diff --git a/tools/bpf/bpftool/map_perf_ring.c b/tools/bpf/bpftool/map_perf_ring.c new file mode 100644 index 000000000..21d7d447e --- /dev/null +++ b/tools/bpf/bpftool/map_perf_ring.c @@ -0,0 +1,226 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2018 Netronome Systems, Inc. */ +/* This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <errno.h> +#include <fcntl.h> +#include <bpf/libbpf.h> +#include <poll.h> +#include <signal.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <time.h> +#include <unistd.h> +#include <linux/bpf.h> +#include <linux/perf_event.h> +#include <sys/ioctl.h> +#include <sys/mman.h> +#include <sys/syscall.h> + +#include <bpf/bpf.h> + +#include "main.h" + +#define MMAP_PAGE_CNT 16 + +static volatile bool stop; + +struct perf_event_sample { + struct perf_event_header header; + __u64 time; + __u32 size; + 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(void *private_data, int cpu, struct perf_event_header *event) +{ + struct perf_event_sample *e = container_of(event, + struct perf_event_sample, + header); + 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, cpu); + jsonw_name(json_wtr, "index"); + jsonw_uint(json_wtr, idx); + if (e->header.type == PERF_RECORD_SAMPLE) { + jsonw_name(json_wtr, "timestamp"); + jsonw_uint(json_wtr, e->time); + jsonw_name(json_wtr, "data"); + print_data_json(e->data, e->size); + } else if (e->header.type == PERF_RECORD_LOST) { + jsonw_name(json_wtr, "lost"); + jsonw_start_object(json_wtr); + jsonw_name(json_wtr, "id"); + jsonw_uint(json_wtr, lost->id); + jsonw_name(json_wtr, "count"); + jsonw_uint(json_wtr, lost->lost); + jsonw_end_object(json_wtr); + } + jsonw_end_object(json_wtr); + } else { + if (e->header.type == PERF_RECORD_SAMPLE) { + printf("== @%lld.%09lld CPU: %d index: %d =====\n", + e->time / 1000000000ULL, e->time % 1000000000ULL, + cpu, idx); + fprint_hex(stdout, e->data, e->size, " "); + printf("\n"); + } else if (e->header.type == PERF_RECORD_LOST) { + printf("lost %lld events\n", lost->lost); + } else { + printf("unknown event type=%d size=%d\n", + e->header.type, e->header.size); + } + } + + return LIBBPF_PERF_EVENT_CONT; +} + +int do_event_pipe(int argc, char **argv) +{ + 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, + }; + struct bpf_map_info map_info = {}; + LIBBPF_OPTS(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; + int err, map_fd; + + map_info_len = sizeof(map_info); + map_fd = map_parse_fd_and_info(&argc, &argv, &map_info, &map_info_len); + if (map_fd < 0) + return -1; + + if (map_info.type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) { + p_err("map is not a perf event array"); + goto err_close_map; + } + + while (argc) { + if (argc < 2) { + BAD_ARG(); + goto err_close_map; + } + + if (is_prefix(*argv, "cpu")) { + char *endptr; + + NEXT_ARG(); + ctx.cpu = strtoul(*argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as CPU ID", *argv); + goto err_close_map; + } + + NEXT_ARG(); + } else if (is_prefix(*argv, "index")) { + char *endptr; + + NEXT_ARG(); + ctx.idx = strtoul(*argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as index", *argv); + goto err_close_map; + } + + NEXT_ARG(); + } else { + BAD_ARG(); + goto err_close_map; + } + + ctx.all_cpus = false; + } + + if (!ctx.all_cpus) { + if (ctx.idx == -1 || ctx.cpu == -1) { + p_err("cpu and index must be specified together"); + goto err_close_map; + } + } else { + ctx.cpu = 0; + ctx.idx = 0; + } + + 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, &perf_attr, + print_bpf_output, &ctx, &opts); + if (!pb) { + p_err("failed to create perf buffer: %s (%d)", + strerror(errno), errno); + goto err_close_map; + } + + signal(SIGINT, int_exit); + signal(SIGHUP, int_exit); + signal(SIGTERM, int_exit); + + if (json_output) + jsonw_start_array(json_wtr); + + while (!stop) { + err = perf_buffer__poll(pb, 200); + if (err < 0 && err != -EINTR) { + p_err("perf buffer polling failed: %s (%d)", + strerror(errno), errno); + goto err_close_pb; + } + } + + if (json_output) + jsonw_end_array(json_wtr); + + perf_buffer__free(pb); + close(map_fd); + + return 0; + +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 new file mode 100644 index 000000000..526a332c4 --- /dev/null +++ b/tools/bpf/bpftool/net.c @@ -0,0 +1,757 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +// Copyright (C) 2018 Facebook + +#define _GNU_SOURCE +#include <errno.h> +#include <fcntl.h> +#include <stdlib.h> +#include <string.h> +#include <time.h> +#include <unistd.h> +#include <bpf/bpf.h> +#include <bpf/libbpf.h> +#include <net/if.h> +#include <linux/rtnetlink.h> +#include <linux/socket.h> +#include <linux/tc_act/tc_bpf.h> +#include <sys/socket.h> +#include <sys/stat.h> +#include <sys/types.h> + +#include "bpf/nlattr.h" +#include "main.h" +#include "netlink_dumper.h" + +#ifndef SOL_NETLINK +#define SOL_NETLINK 270 +#endif + +struct ip_devname_ifindex { + char devname[64]; + int ifindex; +}; + +struct bpf_netdev_t { + struct ip_devname_ifindex *devices; + int used_len; + int array_len; + int filter_idx; +}; + +struct tc_kind_handle { + char kind[64]; + int handle; +}; + +struct bpf_tcinfo_t { + struct tc_kind_handle *handle_array; + int used_len; + int array_len; + bool is_qdisc; +}; + +struct bpf_filter_t { + const char *kind; + const char *devname; + 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; +} + +typedef int (*dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb); + +typedef int (*__dump_nlmsg_t)(struct nlmsghdr *nlmsg, dump_nlmsg_t, void *cookie); + +static int netlink_open(__u32 *nl_pid) +{ + struct sockaddr_nl sa; + socklen_t addrlen; + int one = 1, ret; + int sock; + + memset(&sa, 0, sizeof(sa)); + sa.nl_family = AF_NETLINK; + + sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE); + if (sock < 0) + return -errno; + + if (setsockopt(sock, SOL_NETLINK, NETLINK_EXT_ACK, + &one, sizeof(one)) < 0) { + p_err("Netlink error reporting not supported"); + } + + if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) { + ret = -errno; + goto cleanup; + } + + addrlen = sizeof(sa); + if (getsockname(sock, (struct sockaddr *)&sa, &addrlen) < 0) { + ret = -errno; + goto cleanup; + } + + if (addrlen != sizeof(sa)) { + ret = -LIBBPF_ERRNO__INTERNAL; + goto cleanup; + } + + *nl_pid = sa.nl_pid; + return sock; + +cleanup: + close(sock); + return ret; +} + +static int netlink_recv(int sock, __u32 nl_pid, __u32 seq, + __dump_nlmsg_t _fn, dump_nlmsg_t fn, + void *cookie) +{ + bool multipart = true; + struct nlmsgerr *err; + struct nlmsghdr *nh; + char buf[4096]; + int len, ret; + + while (multipart) { + multipart = false; + len = recv(sock, buf, sizeof(buf), 0); + if (len < 0) { + ret = -errno; + goto done; + } + + if (len == 0) + break; + + for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, (unsigned int)len); + nh = NLMSG_NEXT(nh, len)) { + if (nh->nlmsg_pid != nl_pid) { + ret = -LIBBPF_ERRNO__WRNGPID; + goto done; + } + if (nh->nlmsg_seq != seq) { + ret = -LIBBPF_ERRNO__INVSEQ; + goto done; + } + if (nh->nlmsg_flags & NLM_F_MULTI) + multipart = true; + switch (nh->nlmsg_type) { + case NLMSG_ERROR: + err = (struct nlmsgerr *)NLMSG_DATA(nh); + if (!err->error) + continue; + ret = err->error; + libbpf_nla_dump_errormsg(nh); + goto done; + case NLMSG_DONE: + return 0; + default: + break; + } + if (_fn) { + ret = _fn(nh, fn, cookie); + if (ret) + return ret; + } + } + } + ret = 0; +done: + return ret; +} + +static int __dump_class_nlmsg(struct nlmsghdr *nlh, + dump_nlmsg_t dump_class_nlmsg, + void *cookie) +{ + struct nlattr *tb[TCA_MAX + 1], *attr; + struct tcmsg *t = NLMSG_DATA(nlh); + int len; + + len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t)); + attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t))); + if (libbpf_nla_parse(tb, TCA_MAX, attr, len, NULL) != 0) + return -LIBBPF_ERRNO__NLPARSE; + + return dump_class_nlmsg(cookie, t, tb); +} + +static int netlink_get_class(int sock, unsigned int nl_pid, int ifindex, + dump_nlmsg_t dump_class_nlmsg, void *cookie) +{ + struct { + struct nlmsghdr nlh; + struct tcmsg t; + } req = { + .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)), + .nlh.nlmsg_type = RTM_GETTCLASS, + .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, + .t.tcm_family = AF_UNSPEC, + .t.tcm_ifindex = ifindex, + }; + int seq = time(NULL); + + req.nlh.nlmsg_seq = seq; + if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0) + return -errno; + + return netlink_recv(sock, nl_pid, seq, __dump_class_nlmsg, + dump_class_nlmsg, cookie); +} + +static int __dump_qdisc_nlmsg(struct nlmsghdr *nlh, + dump_nlmsg_t dump_qdisc_nlmsg, + void *cookie) +{ + struct nlattr *tb[TCA_MAX + 1], *attr; + struct tcmsg *t = NLMSG_DATA(nlh); + int len; + + len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t)); + attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t))); + if (libbpf_nla_parse(tb, TCA_MAX, attr, len, NULL) != 0) + return -LIBBPF_ERRNO__NLPARSE; + + return dump_qdisc_nlmsg(cookie, t, tb); +} + +static int netlink_get_qdisc(int sock, unsigned int nl_pid, int ifindex, + dump_nlmsg_t dump_qdisc_nlmsg, void *cookie) +{ + struct { + struct nlmsghdr nlh; + struct tcmsg t; + } req = { + .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)), + .nlh.nlmsg_type = RTM_GETQDISC, + .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, + .t.tcm_family = AF_UNSPEC, + .t.tcm_ifindex = ifindex, + }; + int seq = time(NULL); + + req.nlh.nlmsg_seq = seq; + if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0) + return -errno; + + return netlink_recv(sock, nl_pid, seq, __dump_qdisc_nlmsg, + dump_qdisc_nlmsg, cookie); +} + +static int __dump_filter_nlmsg(struct nlmsghdr *nlh, + dump_nlmsg_t dump_filter_nlmsg, + void *cookie) +{ + struct nlattr *tb[TCA_MAX + 1], *attr; + struct tcmsg *t = NLMSG_DATA(nlh); + int len; + + len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t)); + attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t))); + if (libbpf_nla_parse(tb, TCA_MAX, attr, len, NULL) != 0) + return -LIBBPF_ERRNO__NLPARSE; + + return dump_filter_nlmsg(cookie, t, tb); +} + +static int netlink_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle, + dump_nlmsg_t dump_filter_nlmsg, void *cookie) +{ + struct { + struct nlmsghdr nlh; + struct tcmsg t; + } req = { + .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)), + .nlh.nlmsg_type = RTM_GETTFILTER, + .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, + .t.tcm_family = AF_UNSPEC, + .t.tcm_ifindex = ifindex, + .t.tcm_parent = handle, + }; + int seq = time(NULL); + + req.nlh.nlmsg_seq = seq; + if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0) + return -errno; + + return netlink_recv(sock, nl_pid, seq, __dump_filter_nlmsg, + dump_filter_nlmsg, cookie); +} + +static int __dump_link_nlmsg(struct nlmsghdr *nlh, + dump_nlmsg_t dump_link_nlmsg, void *cookie) +{ + struct nlattr *tb[IFLA_MAX + 1], *attr; + struct ifinfomsg *ifi = NLMSG_DATA(nlh); + int len; + + len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*ifi)); + attr = (struct nlattr *) ((void *) ifi + NLMSG_ALIGN(sizeof(*ifi))); + if (libbpf_nla_parse(tb, IFLA_MAX, attr, len, NULL) != 0) + return -LIBBPF_ERRNO__NLPARSE; + + return dump_link_nlmsg(cookie, ifi, tb); +} + +static int netlink_get_link(int sock, unsigned int nl_pid, + dump_nlmsg_t dump_link_nlmsg, void *cookie) +{ + struct { + struct nlmsghdr nlh; + struct ifinfomsg ifm; + } req = { + .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)), + .nlh.nlmsg_type = RTM_GETLINK, + .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, + .ifm.ifi_family = AF_PACKET, + }; + int seq = time(NULL); + + req.nlh.nlmsg_seq = seq; + if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0) + return -errno; + + return netlink_recv(sock, nl_pid, seq, __dump_link_nlmsg, + dump_link_nlmsg, cookie); +} + +static int dump_link_nlmsg(void *cookie, void *msg, struct nlattr **tb) +{ + struct bpf_netdev_t *netinfo = cookie; + struct ifinfomsg *ifinfo = msg; + + if (netinfo->filter_idx > 0 && netinfo->filter_idx != ifinfo->ifi_index) + return 0; + + if (netinfo->used_len == netinfo->array_len) { + netinfo->devices = realloc(netinfo->devices, + (netinfo->array_len + 16) * + sizeof(struct ip_devname_ifindex)); + if (!netinfo->devices) + return -ENOMEM; + + netinfo->array_len += 16; + } + netinfo->devices[netinfo->used_len].ifindex = ifinfo->ifi_index; + snprintf(netinfo->devices[netinfo->used_len].devname, + sizeof(netinfo->devices[netinfo->used_len].devname), + "%s", + tb[IFLA_IFNAME] + ? libbpf_nla_getattr_str(tb[IFLA_IFNAME]) + : ""); + netinfo->used_len++; + + return do_xdp_dump(ifinfo, tb); +} + +static int dump_class_qdisc_nlmsg(void *cookie, void *msg, struct nlattr **tb) +{ + struct bpf_tcinfo_t *tcinfo = cookie; + struct tcmsg *info = msg; + + if (tcinfo->is_qdisc) { + /* skip clsact qdisc */ + if (tb[TCA_KIND] && + strcmp(libbpf_nla_data(tb[TCA_KIND]), "clsact") == 0) + return 0; + if (info->tcm_handle == 0) + return 0; + } + + if (tcinfo->used_len == tcinfo->array_len) { + tcinfo->handle_array = realloc(tcinfo->handle_array, + (tcinfo->array_len + 16) * sizeof(struct tc_kind_handle)); + if (!tcinfo->handle_array) + return -ENOMEM; + + tcinfo->array_len += 16; + } + tcinfo->handle_array[tcinfo->used_len].handle = info->tcm_handle; + snprintf(tcinfo->handle_array[tcinfo->used_len].kind, + sizeof(tcinfo->handle_array[tcinfo->used_len].kind), + "%s", + tb[TCA_KIND] + ? libbpf_nla_getattr_str(tb[TCA_KIND]) + : "unknown"); + tcinfo->used_len++; + + return 0; +} + +static int dump_filter_nlmsg(void *cookie, void *msg, struct nlattr **tb) +{ + const struct bpf_filter_t *filter_info = cookie; + + return do_filter_dump((struct tcmsg *)msg, tb, filter_info->kind, + filter_info->devname, filter_info->ifindex); +} + +static int show_dev_tc_bpf(int sock, unsigned int nl_pid, + struct ip_devname_ifindex *dev) +{ + struct bpf_filter_t filter_info; + struct bpf_tcinfo_t tcinfo; + int i, handle, ret = 0; + + tcinfo.handle_array = NULL; + tcinfo.used_len = 0; + tcinfo.array_len = 0; + + tcinfo.is_qdisc = false; + ret = netlink_get_class(sock, nl_pid, dev->ifindex, + dump_class_qdisc_nlmsg, &tcinfo); + if (ret) + goto out; + + tcinfo.is_qdisc = true; + ret = netlink_get_qdisc(sock, nl_pid, dev->ifindex, + dump_class_qdisc_nlmsg, &tcinfo); + if (ret) + goto out; + + filter_info.devname = dev->devname; + filter_info.ifindex = dev->ifindex; + for (i = 0; i < tcinfo.used_len; i++) { + filter_info.kind = tcinfo.handle_array[i].kind; + ret = netlink_get_filter(sock, nl_pid, dev->ifindex, + tcinfo.handle_array[i].handle, + dump_filter_nlmsg, &filter_info); + if (ret) + goto out; + } + + /* root, ingress and egress handle */ + handle = TC_H_ROOT; + filter_info.kind = "root"; + ret = netlink_get_filter(sock, nl_pid, dev->ifindex, handle, + dump_filter_nlmsg, &filter_info); + if (ret) + goto out; + + handle = TC_H_MAKE(TC_H_CLSACT, TC_H_MIN_INGRESS); + filter_info.kind = "clsact/ingress"; + ret = netlink_get_filter(sock, nl_pid, dev->ifindex, handle, + dump_filter_nlmsg, &filter_info); + if (ret) + goto out; + + handle = TC_H_MAKE(TC_H_CLSACT, TC_H_MIN_EGRESS); + filter_info.kind = "clsact/egress"; + ret = netlink_get_filter(sock, nl_pid, dev->ifindex, handle, + dump_filter_nlmsg, &filter_info); + if (ret) + goto out; + +out: + free(tcinfo.handle_array); + 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_xdp_attach(ifindex, progfd, flags, NULL); +} + +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) { + err = -EINVAL; + goto cleanup; + } + + if (argc) { + if (is_prefix(*argv, "overwrite")) { + overwrite = true; + } else { + p_err("expected 'overwrite', got: '%s'?", *argv); + err = -EINVAL; + goto cleanup; + } + } + + /* attach xdp prog */ + if (is_prefix("xdp", attach_type_strings[attach_type])) + err = do_attach_detach_xdp(progfd, attach_type, ifindex, + overwrite); + if (err) { + p_err("interface %s attach failed: %s", + attach_type_strings[attach_type], strerror(-err)); + goto cleanup; + } + + if (json_output) + jsonw_null(json_wtr); +cleanup: + close(progfd); + return err; +} + +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 = 0; + char err_buf[256]; + + if (argc == 2) { + 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 = netlink_open(&nl_pid); + if (sock < 0) { + fprintf(stderr, "failed to open netlink sock\n"); + return -1; + } + + dev_array.devices = NULL; + dev_array.used_len = 0; + dev_array.array_len = 0; + dev_array.filter_idx = filter_idx; + + if (json_output) + jsonw_start_array(json_wtr); + NET_START_OBJECT; + NET_START_ARRAY("xdp", "%s:\n"); + ret = netlink_get_link(sock, nl_pid, dump_link_nlmsg, &dev_array); + NET_END_ARRAY("\n"); + + if (!ret) { + NET_START_ARRAY("tc", "%s:\n"); + for (i = 0; i < dev_array.used_len; i++) { + ret = show_dev_tc_bpf(sock, nl_pid, + &dev_array.devices[i]); + if (ret) + break; + } + 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); + + if (ret) { + if (json_output) + jsonw_null(json_wtr); + libbpf_strerror(ret, err_buf, sizeof(err_buf)); + fprintf(stderr, "Error: %s\n", err_buf); + } + free(dev_array.devices); + close(sock); + return ret; +} + +static int do_help(int argc, char **argv) +{ + if (json_output) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %1$s %2$s { show | list } [dev <devname>]\n" + " %1$s %2$s attach ATTACH_TYPE PROG dev <devname> [ overwrite ]\n" + " %1$s %2$s detach ATTACH_TYPE dev <devname>\n" + " %1$s %2$s help\n" + "\n" + " " HELP_SPEC_PROGRAM "\n" + " ATTACH_TYPE := { xdp | xdpgeneric | xdpdrv | xdpoffload }\n" + " " HELP_SPEC_OPTIONS " }\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]); + + return 0; +} + +static const struct cmd cmds[] = { + { "show", do_show }, + { "list", do_show }, + { "attach", do_attach }, + { "detach", do_detach }, + { "help", do_help }, + { 0 } +}; + +int do_net(int argc, char **argv) +{ + return cmd_select(cmds, argc, argv, do_help); +} diff --git a/tools/bpf/bpftool/netlink_dumper.c b/tools/bpf/bpftool/netlink_dumper.c new file mode 100644 index 000000000..5f65140b0 --- /dev/null +++ b/tools/bpf/bpftool/netlink_dumper.c @@ -0,0 +1,178 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +// Copyright (C) 2018 Facebook + +#include <stdlib.h> +#include <string.h> +#include <bpf/libbpf.h> +#include <linux/rtnetlink.h> +#include <linux/tc_act/tc_bpf.h> + +#include "bpf/nlattr.h" +#include "main.h" +#include "netlink_dumper.h" + +static void xdp_dump_prog_id(struct nlattr **tb, int attr, + const char *mode, + bool new_json_object) +{ + if (!tb[attr]) + return; + + if (new_json_object) + NET_START_OBJECT + NET_DUMP_STR("mode", " %s", mode); + NET_DUMP_UINT("id", " id %u", libbpf_nla_getattr_u32(tb[attr])) + if (new_json_object) + NET_END_OBJECT +} + +static int do_xdp_dump_one(struct nlattr *attr, unsigned int ifindex, + const char *name) +{ + struct nlattr *tb[IFLA_XDP_MAX + 1]; + unsigned char mode; + + if (libbpf_nla_parse_nested(tb, IFLA_XDP_MAX, attr, NULL) < 0) + return -1; + + if (!tb[IFLA_XDP_ATTACHED]) + return 0; + + mode = libbpf_nla_getattr_u8(tb[IFLA_XDP_ATTACHED]); + if (mode == XDP_ATTACHED_NONE) + return 0; + + NET_START_OBJECT; + if (name) + NET_DUMP_STR("devname", "%s", name); + NET_DUMP_UINT("ifindex", "(%d)", ifindex); + + if (mode == XDP_ATTACHED_MULTI) { + if (json_output) { + jsonw_name(json_wtr, "multi_attachments"); + jsonw_start_array(json_wtr); + } + xdp_dump_prog_id(tb, IFLA_XDP_SKB_PROG_ID, "generic", true); + xdp_dump_prog_id(tb, IFLA_XDP_DRV_PROG_ID, "driver", true); + xdp_dump_prog_id(tb, IFLA_XDP_HW_PROG_ID, "offload", true); + if (json_output) + jsonw_end_array(json_wtr); + } else if (mode == XDP_ATTACHED_DRV) { + xdp_dump_prog_id(tb, IFLA_XDP_PROG_ID, "driver", false); + } else if (mode == XDP_ATTACHED_SKB) { + xdp_dump_prog_id(tb, IFLA_XDP_PROG_ID, "generic", false); + } else if (mode == XDP_ATTACHED_HW) { + xdp_dump_prog_id(tb, IFLA_XDP_PROG_ID, "offload", false); + } + + NET_END_OBJECT_FINAL; + return 0; +} + +int do_xdp_dump(struct ifinfomsg *ifinfo, struct nlattr **tb) +{ + if (!tb[IFLA_XDP]) + return 0; + + return do_xdp_dump_one(tb[IFLA_XDP], ifinfo->ifi_index, + libbpf_nla_getattr_str(tb[IFLA_IFNAME])); +} + +static int do_bpf_dump_one_act(struct nlattr *attr) +{ + struct nlattr *tb[TCA_ACT_BPF_MAX + 1]; + + if (libbpf_nla_parse_nested(tb, TCA_ACT_BPF_MAX, attr, NULL) < 0) + return -LIBBPF_ERRNO__NLPARSE; + + if (!tb[TCA_ACT_BPF_PARMS]) + return -LIBBPF_ERRNO__NLPARSE; + + NET_START_OBJECT_NESTED2; + if (tb[TCA_ACT_BPF_NAME]) + NET_DUMP_STR("name", "%s", + libbpf_nla_getattr_str(tb[TCA_ACT_BPF_NAME])); + if (tb[TCA_ACT_BPF_ID]) + NET_DUMP_UINT("id", " id %u", + libbpf_nla_getattr_u32(tb[TCA_ACT_BPF_ID])); + NET_END_OBJECT_NESTED; + return 0; +} + +static int do_dump_one_act(struct nlattr *attr) +{ + struct nlattr *tb[TCA_ACT_MAX + 1]; + + if (!attr) + return 0; + + if (libbpf_nla_parse_nested(tb, TCA_ACT_MAX, attr, NULL) < 0) + return -LIBBPF_ERRNO__NLPARSE; + + if (tb[TCA_ACT_KIND] && + strcmp(libbpf_nla_data(tb[TCA_ACT_KIND]), "bpf") == 0) + return do_bpf_dump_one_act(tb[TCA_ACT_OPTIONS]); + + return 0; +} + +static int do_bpf_act_dump(struct nlattr *attr) +{ + struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; + int act, ret; + + if (libbpf_nla_parse_nested(tb, TCA_ACT_MAX_PRIO, attr, NULL) < 0) + return -LIBBPF_ERRNO__NLPARSE; + + NET_START_ARRAY("act", " %s ["); + for (act = 0; act <= TCA_ACT_MAX_PRIO; act++) { + ret = do_dump_one_act(tb[act]); + if (ret) + break; + } + NET_END_ARRAY("] "); + + return ret; +} + +static int do_bpf_filter_dump(struct nlattr *attr) +{ + struct nlattr *tb[TCA_BPF_MAX + 1]; + int ret; + + if (libbpf_nla_parse_nested(tb, TCA_BPF_MAX, attr, NULL) < 0) + return -LIBBPF_ERRNO__NLPARSE; + + if (tb[TCA_BPF_NAME]) + NET_DUMP_STR("name", " %s", + libbpf_nla_getattr_str(tb[TCA_BPF_NAME])); + if (tb[TCA_BPF_ID]) + NET_DUMP_UINT("id", " id %u", + libbpf_nla_getattr_u32(tb[TCA_BPF_ID])); + if (tb[TCA_BPF_ACT]) { + ret = do_bpf_act_dump(tb[TCA_BPF_ACT]); + if (ret) + return ret; + } + + return 0; +} + +int do_filter_dump(struct tcmsg *info, struct nlattr **tb, const char *kind, + const char *devname, int ifindex) +{ + int ret = 0; + + if (tb[TCA_OPTIONS] && + strcmp(libbpf_nla_data(tb[TCA_KIND]), "bpf") == 0) { + NET_START_OBJECT; + if (devname[0] != '\0') + NET_DUMP_STR("devname", "%s", devname); + NET_DUMP_UINT("ifindex", "(%u)", ifindex); + NET_DUMP_STR("kind", " %s", kind); + ret = do_bpf_filter_dump(tb[TCA_OPTIONS]); + NET_END_OBJECT_FINAL; + } + + return ret; +} diff --git a/tools/bpf/bpftool/netlink_dumper.h b/tools/bpf/bpftool/netlink_dumper.h new file mode 100644 index 000000000..774af6c62 --- /dev/null +++ b/tools/bpf/bpftool/netlink_dumper.h @@ -0,0 +1,95 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +// Copyright (C) 2018 Facebook + +#ifndef _NETLINK_DUMPER_H_ +#define _NETLINK_DUMPER_H_ + +#define NET_START_OBJECT \ +{ \ + if (json_output) \ + jsonw_start_object(json_wtr); \ +} + +#define NET_START_OBJECT_NESTED(name) \ +{ \ + if (json_output) { \ + jsonw_name(json_wtr, name); \ + jsonw_start_object(json_wtr); \ + } else { \ + fprintf(stdout, "%s {", name); \ + } \ +} + +#define NET_START_OBJECT_NESTED2 \ +{ \ + if (json_output) \ + jsonw_start_object(json_wtr); \ + else \ + fprintf(stdout, "{"); \ +} + +#define NET_END_OBJECT_NESTED \ +{ \ + if (json_output) \ + jsonw_end_object(json_wtr); \ + else \ + fprintf(stdout, "}"); \ +} + +#define NET_END_OBJECT \ +{ \ + if (json_output) \ + jsonw_end_object(json_wtr); \ +} + +#define NET_END_OBJECT_FINAL \ +{ \ + if (json_output) \ + jsonw_end_object(json_wtr); \ + else \ + fprintf(stdout, "\n"); \ +} + +#define NET_START_ARRAY(name, fmt_str) \ +{ \ + if (json_output) { \ + jsonw_name(json_wtr, name); \ + jsonw_start_array(json_wtr); \ + } else { \ + fprintf(stdout, fmt_str, name); \ + } \ +} + +#define NET_END_ARRAY(endstr) \ +{ \ + if (json_output) \ + jsonw_end_array(json_wtr); \ + else \ + fprintf(stdout, "%s", endstr); \ +} + +#define NET_DUMP_UINT(name, fmt_str, val) \ +{ \ + if (json_output) \ + jsonw_uint_field(json_wtr, name, val); \ + else \ + fprintf(stdout, fmt_str, val); \ +} + +#define NET_DUMP_STR(name, fmt_str, str) \ +{ \ + if (json_output) \ + jsonw_string_field(json_wtr, name, str);\ + else \ + fprintf(stdout, fmt_str, str); \ +} + +#define NET_DUMP_STR_ONLY(str) \ +{ \ + if (json_output) \ + jsonw_string(json_wtr, str); \ + else \ + fprintf(stdout, "%s ", str); \ +} + +#endif diff --git a/tools/bpf/bpftool/perf.c b/tools/bpf/bpftool/perf.c new file mode 100644 index 000000000..226ec2c39 --- /dev/null +++ b/tools/bpf/bpftool/perf.c @@ -0,0 +1,256 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +// Copyright (C) 2018 Facebook +// Author: Yonghong Song <yhs@fb.com> + +#define _GNU_SOURCE +#include <ctype.h> +#include <errno.h> +#include <fcntl.h> +#include <stdlib.h> +#include <string.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <unistd.h> +#include <dirent.h> + +#include <bpf/bpf.h> + +#include "main.h" + +/* 0: undecided, 1: supported, 2: not supported */ +static int perf_query_supported; +static bool has_perf_query_support(void) +{ + __u64 probe_offset, probe_addr; + __u32 len, prog_id, fd_type; + char buf[256]; + int fd; + + if (perf_query_supported) + goto out; + + fd = open("/", O_RDONLY); + if (fd < 0) { + p_err("perf_query_support: cannot open directory \"/\" (%s)", + strerror(errno)); + goto out; + } + + /* the following query will fail as no bpf attachment, + * the expected errno is ENOTSUPP + */ + errno = 0; + len = sizeof(buf); + bpf_task_fd_query(getpid(), fd, 0, buf, &len, &prog_id, + &fd_type, &probe_offset, &probe_addr); + + if (errno == 524 /* ENOTSUPP */) { + perf_query_supported = 1; + goto close_fd; + } + + perf_query_supported = 2; + p_err("perf_query_support: %s", strerror(errno)); + fprintf(stderr, + "HINT: non root or kernel doesn't support TASK_FD_QUERY\n"); + +close_fd: + close(fd); +out: + return perf_query_supported == 1; +} + +static void print_perf_json(int pid, int fd, __u32 prog_id, __u32 fd_type, + char *buf, __u64 probe_offset, __u64 probe_addr) +{ + jsonw_start_object(json_wtr); + jsonw_int_field(json_wtr, "pid", pid); + jsonw_int_field(json_wtr, "fd", fd); + jsonw_uint_field(json_wtr, "prog_id", prog_id); + switch (fd_type) { + case BPF_FD_TYPE_RAW_TRACEPOINT: + jsonw_string_field(json_wtr, "fd_type", "raw_tracepoint"); + jsonw_string_field(json_wtr, "tracepoint", buf); + break; + case BPF_FD_TYPE_TRACEPOINT: + jsonw_string_field(json_wtr, "fd_type", "tracepoint"); + jsonw_string_field(json_wtr, "tracepoint", buf); + break; + case BPF_FD_TYPE_KPROBE: + jsonw_string_field(json_wtr, "fd_type", "kprobe"); + if (buf[0] != '\0') { + jsonw_string_field(json_wtr, "func", buf); + jsonw_lluint_field(json_wtr, "offset", probe_offset); + } else { + jsonw_lluint_field(json_wtr, "addr", probe_addr); + } + break; + case BPF_FD_TYPE_KRETPROBE: + jsonw_string_field(json_wtr, "fd_type", "kretprobe"); + if (buf[0] != '\0') { + jsonw_string_field(json_wtr, "func", buf); + jsonw_lluint_field(json_wtr, "offset", probe_offset); + } else { + jsonw_lluint_field(json_wtr, "addr", probe_addr); + } + break; + case BPF_FD_TYPE_UPROBE: + jsonw_string_field(json_wtr, "fd_type", "uprobe"); + jsonw_string_field(json_wtr, "filename", buf); + jsonw_lluint_field(json_wtr, "offset", probe_offset); + break; + case BPF_FD_TYPE_URETPROBE: + jsonw_string_field(json_wtr, "fd_type", "uretprobe"); + jsonw_string_field(json_wtr, "filename", buf); + jsonw_lluint_field(json_wtr, "offset", probe_offset); + break; + default: + break; + } + jsonw_end_object(json_wtr); +} + +static void print_perf_plain(int pid, int fd, __u32 prog_id, __u32 fd_type, + char *buf, __u64 probe_offset, __u64 probe_addr) +{ + printf("pid %d fd %d: prog_id %u ", pid, fd, prog_id); + switch (fd_type) { + case BPF_FD_TYPE_RAW_TRACEPOINT: + printf("raw_tracepoint %s\n", buf); + break; + case BPF_FD_TYPE_TRACEPOINT: + printf("tracepoint %s\n", buf); + break; + case BPF_FD_TYPE_KPROBE: + if (buf[0] != '\0') + printf("kprobe func %s offset %llu\n", buf, + probe_offset); + else + printf("kprobe addr %llu\n", probe_addr); + break; + case BPF_FD_TYPE_KRETPROBE: + if (buf[0] != '\0') + printf("kretprobe func %s offset %llu\n", buf, + probe_offset); + else + printf("kretprobe addr %llu\n", probe_addr); + break; + case BPF_FD_TYPE_UPROBE: + printf("uprobe filename %s offset %llu\n", buf, probe_offset); + break; + case BPF_FD_TYPE_URETPROBE: + printf("uretprobe filename %s offset %llu\n", buf, + probe_offset); + break; + default: + break; + } +} + +static int show_proc(void) +{ + struct dirent *proc_de, *pid_fd_de; + __u64 probe_offset, probe_addr; + __u32 len, prog_id, fd_type; + DIR *proc, *pid_fd; + int err, pid, fd; + const char *pch; + char buf[4096]; + + proc = opendir("/proc"); + if (!proc) + return -1; + + while ((proc_de = readdir(proc))) { + pid = 0; + pch = proc_de->d_name; + + /* pid should be all numbers */ + while (isdigit(*pch)) { + pid = pid * 10 + *pch - '0'; + pch++; + } + if (*pch != '\0') + continue; + + err = snprintf(buf, sizeof(buf), "/proc/%s/fd", proc_de->d_name); + if (err < 0 || err >= (int)sizeof(buf)) + continue; + + pid_fd = opendir(buf); + if (!pid_fd) + continue; + + while ((pid_fd_de = readdir(pid_fd))) { + fd = 0; + pch = pid_fd_de->d_name; + + /* fd should be all numbers */ + while (isdigit(*pch)) { + fd = fd * 10 + *pch - '0'; + pch++; + } + if (*pch != '\0') + continue; + + /* query (pid, fd) for potential perf events */ + len = sizeof(buf); + err = bpf_task_fd_query(pid, fd, 0, buf, &len, + &prog_id, &fd_type, + &probe_offset, &probe_addr); + if (err < 0) + continue; + + if (json_output) + print_perf_json(pid, fd, prog_id, fd_type, buf, + probe_offset, probe_addr); + else + print_perf_plain(pid, fd, prog_id, fd_type, buf, + probe_offset, probe_addr); + } + closedir(pid_fd); + } + closedir(proc); + return 0; +} + +static int do_show(int argc, char **argv) +{ + int err; + + if (!has_perf_query_support()) + return -1; + + if (json_output) + jsonw_start_array(json_wtr); + err = show_proc(); + if (json_output) + jsonw_end_array(json_wtr); + + return err; +} + +static int do_help(int argc, char **argv) +{ + fprintf(stderr, + "Usage: %1$s %2$s { show | list }\n" + " %1$s %2$s help }\n" + "\n" + " " HELP_SPEC_OPTIONS " }\n" + "", + bin_name, argv[-2]); + + return 0; +} + +static const struct cmd cmds[] = { + { "show", do_show }, + { "list", do_show }, + { "help", do_help }, + { 0 } +}; + +int do_perf(int argc, char **argv) +{ + return cmd_select(cmds, argc, argv, do_help); +} diff --git a/tools/bpf/bpftool/pids.c b/tools/bpf/bpftool/pids.c new file mode 100644 index 000000000..bb6c969a1 --- /dev/null +++ b/tools/bpf/bpftool/pids.c @@ -0,0 +1,256 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2020 Facebook */ +#include <errno.h> +#include <linux/err.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> + +#include <bpf/bpf.h> +#include <bpf/hashmap.h> + +#include "main.h" +#include "skeleton/pid_iter.h" + +#ifdef BPFTOOL_WITHOUT_SKELETONS + +int build_obj_refs_table(struct hashmap **map, enum bpf_obj_type type) +{ + return -ENOTSUP; +} +void delete_obj_refs_table(struct hashmap *map) {} +void emit_obj_refs_plain(struct hashmap *map, __u32 id, const char *prefix) {} +void emit_obj_refs_json(struct hashmap *map, __u32 id, json_writer_t *json_writer) {} + +#else /* BPFTOOL_WITHOUT_SKELETONS */ + +#include "pid_iter.skel.h" + +static void add_ref(struct hashmap *map, struct pid_iter_entry *e) +{ + struct hashmap_entry *entry; + struct obj_refs *refs; + struct obj_ref *ref; + int err, i; + void *tmp; + + hashmap__for_each_key_entry(map, entry, u32_as_hash_field(e->id)) { + refs = entry->value; + + for (i = 0; i < refs->ref_cnt; i++) { + if (refs->refs[i].pid == e->pid) + return; + } + + tmp = realloc(refs->refs, (refs->ref_cnt + 1) * sizeof(*ref)); + if (!tmp) { + p_err("failed to re-alloc memory for ID %u, PID %d, COMM %s...", + e->id, e->pid, e->comm); + return; + } + refs->refs = tmp; + ref = &refs->refs[refs->ref_cnt]; + ref->pid = e->pid; + memcpy(ref->comm, e->comm, sizeof(ref->comm)); + refs->ref_cnt++; + + return; + } + + /* new ref */ + refs = calloc(1, sizeof(*refs)); + if (!refs) { + p_err("failed to alloc memory for ID %u, PID %d, COMM %s...", + e->id, e->pid, e->comm); + return; + } + + refs->refs = malloc(sizeof(*refs->refs)); + if (!refs->refs) { + free(refs); + p_err("failed to alloc memory for ID %u, PID %d, COMM %s...", + e->id, e->pid, e->comm); + return; + } + ref = &refs->refs[0]; + ref->pid = e->pid; + memcpy(ref->comm, e->comm, sizeof(ref->comm)); + refs->ref_cnt = 1; + refs->has_bpf_cookie = e->has_bpf_cookie; + refs->bpf_cookie = e->bpf_cookie; + + err = hashmap__append(map, u32_as_hash_field(e->id), refs); + if (err) + p_err("failed to append entry to hashmap for ID %u: %s", + e->id, strerror(errno)); +} + +static int __printf(2, 0) +libbpf_print_none(__maybe_unused enum libbpf_print_level level, + __maybe_unused const char *format, + __maybe_unused va_list args) +{ + return 0; +} + +int build_obj_refs_table(struct hashmap **map, enum bpf_obj_type type) +{ + struct pid_iter_entry *e; + char buf[4096 / sizeof(*e) * sizeof(*e)]; + struct pid_iter_bpf *skel; + int err, ret, fd = -1, i; + libbpf_print_fn_t default_print; + + *map = hashmap__new(hash_fn_for_key_as_id, equal_fn_for_key_as_id, NULL); + if (IS_ERR(*map)) { + p_err("failed to create hashmap for PID references"); + return -1; + } + set_max_rlimit(); + + skel = pid_iter_bpf__open(); + if (!skel) { + p_err("failed to open PID iterator skeleton"); + return -1; + } + + skel->rodata->obj_type = type; + + /* we don't want output polluted with libbpf errors if bpf_iter is not + * supported + */ + default_print = libbpf_set_print(libbpf_print_none); + err = pid_iter_bpf__load(skel); + libbpf_set_print(default_print); + if (err) { + /* too bad, kernel doesn't support BPF iterators yet */ + err = 0; + goto out; + } + err = pid_iter_bpf__attach(skel); + if (err) { + /* if we loaded above successfully, attach has to succeed */ + p_err("failed to attach PID iterator: %d", err); + goto out; + } + + fd = bpf_iter_create(bpf_link__fd(skel->links.iter)); + if (fd < 0) { + err = -errno; + p_err("failed to create PID iterator session: %d", err); + goto out; + } + + while (true) { + ret = read(fd, buf, sizeof(buf)); + if (ret < 0) { + if (errno == EAGAIN) + continue; + err = -errno; + p_err("failed to read PID iterator output: %d", err); + goto out; + } + if (ret == 0) + break; + if (ret % sizeof(*e)) { + err = -EINVAL; + p_err("invalid PID iterator output format"); + goto out; + } + ret /= sizeof(*e); + + e = (void *)buf; + for (i = 0; i < ret; i++, e++) { + add_ref(*map, e); + } + } + err = 0; +out: + if (fd >= 0) + close(fd); + pid_iter_bpf__destroy(skel); + return err; +} + +void delete_obj_refs_table(struct hashmap *map) +{ + struct hashmap_entry *entry; + size_t bkt; + + if (!map) + return; + + hashmap__for_each_entry(map, entry, bkt) { + struct obj_refs *refs = entry->value; + + free(refs->refs); + free(refs); + } + + hashmap__free(map); +} + +void emit_obj_refs_json(struct hashmap *map, __u32 id, + json_writer_t *json_writer) +{ + struct hashmap_entry *entry; + + if (hashmap__empty(map)) + return; + + hashmap__for_each_key_entry(map, entry, u32_as_hash_field(id)) { + struct obj_refs *refs = entry->value; + int i; + + if (refs->ref_cnt == 0) + break; + + if (refs->has_bpf_cookie) + jsonw_lluint_field(json_writer, "bpf_cookie", refs->bpf_cookie); + + jsonw_name(json_writer, "pids"); + jsonw_start_array(json_writer); + for (i = 0; i < refs->ref_cnt; i++) { + struct obj_ref *ref = &refs->refs[i]; + + jsonw_start_object(json_writer); + jsonw_int_field(json_writer, "pid", ref->pid); + jsonw_string_field(json_writer, "comm", ref->comm); + jsonw_end_object(json_writer); + } + jsonw_end_array(json_writer); + break; + } +} + +void emit_obj_refs_plain(struct hashmap *map, __u32 id, const char *prefix) +{ + struct hashmap_entry *entry; + + if (hashmap__empty(map)) + return; + + hashmap__for_each_key_entry(map, entry, u32_as_hash_field(id)) { + struct obj_refs *refs = entry->value; + int i; + + if (refs->ref_cnt == 0) + break; + + if (refs->has_bpf_cookie) + printf("\n\tbpf_cookie %llu", (unsigned long long) refs->bpf_cookie); + + printf("%s", prefix); + for (i = 0; i < refs->ref_cnt; i++) { + struct obj_ref *ref = &refs->refs[i]; + + printf("%s%s(%d)", i == 0 ? "" : ", ", ref->comm, ref->pid); + } + break; + } +} + + +#endif diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c new file mode 100644 index 000000000..41c02b6f6 --- /dev/null +++ b/tools/bpf/bpftool/prog.c @@ -0,0 +1,2419 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2017-2018 Netronome Systems, Inc. */ + +#define _GNU_SOURCE +#include <errno.h> +#include <fcntl.h> +#include <signal.h> +#include <stdarg.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <time.h> +#include <unistd.h> +#include <net/if.h> +#include <sys/ioctl.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <sys/syscall.h> +#include <dirent.h> + +#include <linux/err.h> +#include <linux/perf_event.h> +#include <linux/sizes.h> + +#include <bpf/bpf.h> +#include <bpf/btf.h> +#include <bpf/hashmap.h> +#include <bpf/libbpf.h> +#include <bpf/libbpf_internal.h> +#include <bpf/skel_internal.h> + +#include "cfg.h" +#include "main.h" +#include "xlated_dumper.h" + +#define BPF_METADATA_PREFIX "bpf_metadata_" +#define BPF_METADATA_PREFIX_LEN (sizeof(BPF_METADATA_PREFIX) - 1) + +enum dump_mode { + DUMP_JITED, + DUMP_XLATED, +}; + +static const bool attach_types[] = { + [BPF_SK_SKB_STREAM_PARSER] = true, + [BPF_SK_SKB_STREAM_VERDICT] = true, + [BPF_SK_SKB_VERDICT] = true, + [BPF_SK_MSG_VERDICT] = true, + [BPF_FLOW_DISSECTOR] = true, + [__MAX_BPF_ATTACH_TYPE] = false, +}; + +/* Textual representations traditionally used by the program and kept around + * for the sake of backwards compatibility. + */ +static const char * const attach_type_strings[] = { + [BPF_SK_SKB_STREAM_PARSER] = "stream_parser", + [BPF_SK_SKB_STREAM_VERDICT] = "stream_verdict", + [BPF_SK_SKB_VERDICT] = "skb_verdict", + [BPF_SK_MSG_VERDICT] = "msg_verdict", + [__MAX_BPF_ATTACH_TYPE] = NULL, +}; + +static struct hashmap *prog_table; + +static enum bpf_attach_type parse_attach_type(const char *str) +{ + enum bpf_attach_type type; + + for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) { + if (attach_types[type]) { + const char *attach_type_str; + + attach_type_str = libbpf_bpf_attach_type_str(type); + if (!strcmp(str, attach_type_str)) + return type; + } + + if (attach_type_strings[type] && + is_prefix(str, attach_type_strings[type])) + return type; + } + + return __MAX_BPF_ATTACH_TYPE; +} + +static int prep_prog_info(struct bpf_prog_info *const info, enum dump_mode mode, + void **info_data, size_t *const info_data_sz) +{ + struct bpf_prog_info holder = {}; + size_t needed = 0; + void *ptr; + + if (mode == DUMP_JITED) { + holder.jited_prog_len = info->jited_prog_len; + needed += info->jited_prog_len; + } else { + holder.xlated_prog_len = info->xlated_prog_len; + needed += info->xlated_prog_len; + } + + holder.nr_jited_ksyms = info->nr_jited_ksyms; + needed += info->nr_jited_ksyms * sizeof(__u64); + + holder.nr_jited_func_lens = info->nr_jited_func_lens; + needed += info->nr_jited_func_lens * sizeof(__u32); + + holder.nr_func_info = info->nr_func_info; + holder.func_info_rec_size = info->func_info_rec_size; + needed += info->nr_func_info * info->func_info_rec_size; + + holder.nr_line_info = info->nr_line_info; + holder.line_info_rec_size = info->line_info_rec_size; + needed += info->nr_line_info * info->line_info_rec_size; + + holder.nr_jited_line_info = info->nr_jited_line_info; + holder.jited_line_info_rec_size = info->jited_line_info_rec_size; + needed += info->nr_jited_line_info * info->jited_line_info_rec_size; + + if (needed > *info_data_sz) { + ptr = realloc(*info_data, needed); + if (!ptr) + return -1; + + *info_data = ptr; + *info_data_sz = needed; + } + ptr = *info_data; + + if (mode == DUMP_JITED) { + holder.jited_prog_insns = ptr_to_u64(ptr); + ptr += holder.jited_prog_len; + } else { + holder.xlated_prog_insns = ptr_to_u64(ptr); + ptr += holder.xlated_prog_len; + } + + holder.jited_ksyms = ptr_to_u64(ptr); + ptr += holder.nr_jited_ksyms * sizeof(__u64); + + holder.jited_func_lens = ptr_to_u64(ptr); + ptr += holder.nr_jited_func_lens * sizeof(__u32); + + holder.func_info = ptr_to_u64(ptr); + ptr += holder.nr_func_info * holder.func_info_rec_size; + + holder.line_info = ptr_to_u64(ptr); + ptr += holder.nr_line_info * holder.line_info_rec_size; + + holder.jited_line_info = ptr_to_u64(ptr); + ptr += holder.nr_jited_line_info * holder.jited_line_info_rec_size; + + *info = holder; + return 0; +} + +static void print_boot_time(__u64 nsecs, char *buf, unsigned int size) +{ + struct timespec real_time_ts, boot_time_ts; + time_t wallclock_secs; + struct tm load_tm; + + buf[--size] = '\0'; + + if (clock_gettime(CLOCK_REALTIME, &real_time_ts) || + clock_gettime(CLOCK_BOOTTIME, &boot_time_ts)) { + perror("Can't read clocks"); + snprintf(buf, size, "%llu", nsecs / 1000000000); + return; + } + + wallclock_secs = (real_time_ts.tv_sec - boot_time_ts.tv_sec) + + (real_time_ts.tv_nsec - boot_time_ts.tv_nsec + nsecs) / + 1000000000; + + + if (!localtime_r(&wallclock_secs, &load_tm)) { + snprintf(buf, size, "%llu", nsecs / 1000000000); + return; + } + + if (json_output) + strftime(buf, size, "%s", &load_tm); + else + strftime(buf, size, "%FT%T%z", &load_tm); +} + +static void show_prog_maps(int fd, __u32 num_maps) +{ + struct bpf_prog_info info = {}; + __u32 len = sizeof(info); + __u32 map_ids[num_maps]; + unsigned int i; + int err; + + info.nr_map_ids = num_maps; + info.map_ids = ptr_to_u64(map_ids); + + err = bpf_obj_get_info_by_fd(fd, &info, &len); + if (err || !info.nr_map_ids) + return; + + if (json_output) { + jsonw_name(json_wtr, "map_ids"); + jsonw_start_array(json_wtr); + for (i = 0; i < info.nr_map_ids; i++) + jsonw_uint(json_wtr, map_ids[i]); + jsonw_end_array(json_wtr); + } else { + printf(" map_ids "); + for (i = 0; i < info.nr_map_ids; i++) + printf("%u%s", map_ids[i], + i == info.nr_map_ids - 1 ? "" : ","); + } +} + +static void *find_metadata(int prog_fd, struct bpf_map_info *map_info) +{ + struct bpf_prog_info prog_info; + __u32 prog_info_len; + __u32 map_info_len; + void *value = NULL; + __u32 *map_ids; + int nr_maps; + int key = 0; + int map_fd; + int ret; + __u32 i; + + memset(&prog_info, 0, sizeof(prog_info)); + prog_info_len = sizeof(prog_info); + ret = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &prog_info_len); + if (ret) + return NULL; + + if (!prog_info.nr_map_ids) + return NULL; + + map_ids = calloc(prog_info.nr_map_ids, sizeof(__u32)); + if (!map_ids) + return NULL; + + nr_maps = prog_info.nr_map_ids; + memset(&prog_info, 0, sizeof(prog_info)); + prog_info.nr_map_ids = nr_maps; + prog_info.map_ids = ptr_to_u64(map_ids); + prog_info_len = sizeof(prog_info); + + ret = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &prog_info_len); + if (ret) + goto free_map_ids; + + for (i = 0; i < prog_info.nr_map_ids; i++) { + map_fd = bpf_map_get_fd_by_id(map_ids[i]); + if (map_fd < 0) + goto free_map_ids; + + memset(map_info, 0, sizeof(*map_info)); + map_info_len = sizeof(*map_info); + ret = bpf_obj_get_info_by_fd(map_fd, map_info, &map_info_len); + if (ret < 0) { + close(map_fd); + goto free_map_ids; + } + + if (map_info->type != BPF_MAP_TYPE_ARRAY || + map_info->key_size != sizeof(int) || + map_info->max_entries != 1 || + !map_info->btf_value_type_id || + !strstr(map_info->name, ".rodata")) { + close(map_fd); + continue; + } + + value = malloc(map_info->value_size); + if (!value) { + close(map_fd); + goto free_map_ids; + } + + if (bpf_map_lookup_elem(map_fd, &key, value)) { + close(map_fd); + free(value); + value = NULL; + goto free_map_ids; + } + + close(map_fd); + break; + } + +free_map_ids: + free(map_ids); + return value; +} + +static bool has_metadata_prefix(const char *s) +{ + return strncmp(s, BPF_METADATA_PREFIX, BPF_METADATA_PREFIX_LEN) == 0; +} + +static void show_prog_metadata(int fd, __u32 num_maps) +{ + const struct btf_type *t_datasec, *t_var; + struct bpf_map_info map_info; + struct btf_var_secinfo *vsi; + bool printed_header = false; + unsigned int i, vlen; + void *value = NULL; + const char *name; + struct btf *btf; + int err; + + if (!num_maps) + return; + + memset(&map_info, 0, sizeof(map_info)); + value = find_metadata(fd, &map_info); + if (!value) + return; + + btf = btf__load_from_kernel_by_id(map_info.btf_id); + if (libbpf_get_error(btf)) + goto out_free; + + t_datasec = btf__type_by_id(btf, map_info.btf_value_type_id); + if (!btf_is_datasec(t_datasec)) + goto out_free; + + vlen = btf_vlen(t_datasec); + vsi = btf_var_secinfos(t_datasec); + + /* We don't proceed to check the kinds of the elements of the DATASEC. + * The verifier enforces them to be BTF_KIND_VAR. + */ + + if (json_output) { + struct btf_dumper d = { + .btf = btf, + .jw = json_wtr, + .is_plain_text = false, + }; + + for (i = 0; i < vlen; i++, vsi++) { + t_var = btf__type_by_id(btf, vsi->type); + name = btf__name_by_offset(btf, t_var->name_off); + + if (!has_metadata_prefix(name)) + continue; + + if (!printed_header) { + jsonw_name(json_wtr, "metadata"); + jsonw_start_object(json_wtr); + printed_header = true; + } + + jsonw_name(json_wtr, name + BPF_METADATA_PREFIX_LEN); + err = btf_dumper_type(&d, t_var->type, value + vsi->offset); + if (err) { + p_err("btf dump failed: %d", err); + break; + } + } + if (printed_header) + jsonw_end_object(json_wtr); + } else { + json_writer_t *btf_wtr; + struct btf_dumper d = { + .btf = btf, + .is_plain_text = true, + }; + + for (i = 0; i < vlen; i++, vsi++) { + t_var = btf__type_by_id(btf, vsi->type); + name = btf__name_by_offset(btf, t_var->name_off); + + if (!has_metadata_prefix(name)) + continue; + + if (!printed_header) { + printf("\tmetadata:"); + + btf_wtr = jsonw_new(stdout); + if (!btf_wtr) { + p_err("jsonw alloc failed"); + goto out_free; + } + d.jw = btf_wtr, + + printed_header = true; + } + + printf("\n\t\t%s = ", name + BPF_METADATA_PREFIX_LEN); + + jsonw_reset(btf_wtr); + err = btf_dumper_type(&d, t_var->type, value + vsi->offset); + if (err) { + p_err("btf dump failed: %d", err); + break; + } + } + if (printed_header) + jsonw_destroy(&btf_wtr); + } + +out_free: + btf__free(btf); + free(value); +} + +static void print_prog_header_json(struct bpf_prog_info *info, int fd) +{ + const char *prog_type_str; + char prog_name[MAX_PROG_FULL_NAME]; + + jsonw_uint_field(json_wtr, "id", info->id); + prog_type_str = libbpf_bpf_prog_type_str(info->type); + + if (prog_type_str) + jsonw_string_field(json_wtr, "type", prog_type_str); + else + jsonw_uint_field(json_wtr, "type", info->type); + + if (*info->name) { + get_prog_full_name(info, fd, prog_name, sizeof(prog_name)); + jsonw_string_field(json_wtr, "name", prog_name); + } + + jsonw_name(json_wtr, "tag"); + jsonw_printf(json_wtr, "\"" BPF_TAG_FMT "\"", + info->tag[0], info->tag[1], info->tag[2], info->tag[3], + info->tag[4], info->tag[5], info->tag[6], info->tag[7]); + + jsonw_bool_field(json_wtr, "gpl_compatible", info->gpl_compatible); + if (info->run_time_ns) { + jsonw_uint_field(json_wtr, "run_time_ns", info->run_time_ns); + jsonw_uint_field(json_wtr, "run_cnt", info->run_cnt); + } + if (info->recursion_misses) + jsonw_uint_field(json_wtr, "recursion_misses", info->recursion_misses); +} + +static void print_prog_json(struct bpf_prog_info *info, int fd) +{ + char *memlock; + + jsonw_start_object(json_wtr); + print_prog_header_json(info, fd); + print_dev_json(info->ifindex, info->netns_dev, info->netns_ino); + + if (info->load_time) { + char buf[32]; + + print_boot_time(info->load_time, buf, sizeof(buf)); + + /* Piggy back on load_time, since 0 uid is a valid one */ + jsonw_name(json_wtr, "loaded_at"); + jsonw_printf(json_wtr, "%s", buf); + jsonw_uint_field(json_wtr, "uid", info->created_by_uid); + } + + jsonw_uint_field(json_wtr, "bytes_xlated", info->xlated_prog_len); + + if (info->jited_prog_len) { + jsonw_bool_field(json_wtr, "jited", true); + jsonw_uint_field(json_wtr, "bytes_jited", info->jited_prog_len); + } else { + jsonw_bool_field(json_wtr, "jited", false); + } + + memlock = get_fdinfo(fd, "memlock"); + if (memlock) + jsonw_int_field(json_wtr, "bytes_memlock", atoll(memlock)); + free(memlock); + + 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 (!hashmap__empty(prog_table)) { + struct hashmap_entry *entry; + + jsonw_name(json_wtr, "pinned"); + jsonw_start_array(json_wtr); + hashmap__for_each_key_entry(prog_table, entry, + u32_as_hash_field(info->id)) + jsonw_string(json_wtr, entry->value); + jsonw_end_array(json_wtr); + } + + emit_obj_refs_json(refs_table, info->id, json_wtr); + + show_prog_metadata(fd, info->nr_map_ids); + + jsonw_end_object(json_wtr); +} + +static void print_prog_header_plain(struct bpf_prog_info *info, int fd) +{ + const char *prog_type_str; + char prog_name[MAX_PROG_FULL_NAME]; + + printf("%u: ", info->id); + prog_type_str = libbpf_bpf_prog_type_str(info->type); + if (prog_type_str) + printf("%s ", prog_type_str); + else + printf("type %u ", info->type); + + if (*info->name) { + get_prog_full_name(info, fd, prog_name, sizeof(prog_name)); + printf("name %s ", prog_name); + } + + printf("tag "); + fprint_hex(stdout, info->tag, BPF_TAG_SIZE, ""); + print_dev_plain(info->ifindex, info->netns_dev, info->netns_ino); + printf("%s", info->gpl_compatible ? " gpl" : ""); + if (info->run_time_ns) + printf(" run_time_ns %lld run_cnt %lld", + info->run_time_ns, info->run_cnt); + if (info->recursion_misses) + printf(" recursion_misses %lld", info->recursion_misses); + printf("\n"); +} + +static void print_prog_plain(struct bpf_prog_info *info, int fd) +{ + char *memlock; + + print_prog_header_plain(info, fd); + + if (info->load_time) { + char buf[32]; + + print_boot_time(info->load_time, buf, sizeof(buf)); + + /* Piggy back on load_time, since 0 uid is a valid one */ + printf("\tloaded_at %s uid %u\n", buf, info->created_by_uid); + } + + printf("\txlated %uB", info->xlated_prog_len); + + if (info->jited_prog_len) + printf(" jited %uB", info->jited_prog_len); + else + printf(" not jited"); + + memlock = get_fdinfo(fd, "memlock"); + if (memlock) + printf(" memlock %sB", memlock); + free(memlock); + + if (info->nr_map_ids) + show_prog_maps(fd, info->nr_map_ids); + + if (!hashmap__empty(prog_table)) { + struct hashmap_entry *entry; + + hashmap__for_each_key_entry(prog_table, entry, + u32_as_hash_field(info->id)) + printf("\n\tpinned %s", (char *)entry->value); + } + + if (info->btf_id) + printf("\n\tbtf_id %d", info->btf_id); + + emit_obj_refs_plain(refs_table, info->id, "\n\tpids "); + + printf("\n"); + + show_prog_metadata(fd, info->nr_map_ids); +} + +static int show_prog(int fd) +{ + struct bpf_prog_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 prog info: %s", strerror(errno)); + return -1; + } + + if (json_output) + print_prog_json(&info, fd); + else + print_prog_plain(&info, fd); + + return 0; +} + +static int do_show_subset(int argc, char **argv) +{ + int *fds = NULL; + int nb_fds, i; + int err = -1; + + fds = malloc(sizeof(int)); + if (!fds) { + p_err("mem alloc failed"); + return -1; + } + nb_fds = prog_parse_fds(&argc, &argv, &fds); + if (nb_fds < 1) + goto exit_free; + + if (json_output && nb_fds > 1) + jsonw_start_array(json_wtr); /* root array */ + for (i = 0; i < nb_fds; i++) { + err = show_prog(fds[i]); + if (err) { + for (; i < nb_fds; i++) + close(fds[i]); + break; + } + close(fds[i]); + } + if (json_output && nb_fds > 1) + jsonw_end_array(json_wtr); /* root array */ + +exit_free: + free(fds); + return err; +} + +static int do_show(int argc, char **argv) +{ + __u32 id = 0; + int err; + int fd; + + if (show_pinned) { + prog_table = hashmap__new(hash_fn_for_key_as_id, + equal_fn_for_key_as_id, NULL); + if (IS_ERR(prog_table)) { + p_err("failed to create hashmap for pinned paths"); + return -1; + } + build_pinned_obj_table(prog_table, BPF_OBJ_PROG); + } + build_obj_refs_table(&refs_table, BPF_OBJ_PROG); + + if (argc == 2) + return do_show_subset(argc, argv); + + if (argc) + return BAD_ARG(); + + if (json_output) + jsonw_start_array(json_wtr); + while (true) { + err = bpf_prog_get_next_id(id, &id); + if (err) { + if (errno == ENOENT) { + err = 0; + break; + } + p_err("can't get next program: %s%s", strerror(errno), + errno == EINVAL ? " -- kernel too old?" : ""); + err = -1; + break; + } + + fd = bpf_prog_get_fd_by_id(id); + if (fd < 0) { + if (errno == ENOENT) + continue; + p_err("can't get prog by id (%u): %s", + id, strerror(errno)); + err = -1; + break; + } + + err = show_prog(fd); + close(fd); + if (err) + break; + } + + if (json_output) + jsonw_end_array(json_wtr); + + delete_obj_refs_table(refs_table); + + if (show_pinned) + delete_pinned_obj_table(prog_table); + + return err; +} + +static int +prog_dump(struct bpf_prog_info *info, enum dump_mode mode, + char *filepath, bool opcodes, bool visual, bool linum) +{ + struct bpf_prog_linfo *prog_linfo = NULL; + const char *disasm_opt = NULL; + struct dump_data dd = {}; + void *func_info = NULL; + struct btf *btf = NULL; + char func_sig[1024]; + unsigned char *buf; + __u32 member_len; + int fd, err = -1; + ssize_t n; + + if (mode == DUMP_JITED) { + if (info->jited_prog_len == 0 || !info->jited_prog_insns) { + p_info("no instructions returned"); + return -1; + } + buf = u64_to_ptr(info->jited_prog_insns); + member_len = info->jited_prog_len; + } else { /* DUMP_XLATED */ + if (info->xlated_prog_len == 0 || !info->xlated_prog_insns) { + p_err("error retrieving insn dump: kernel.kptr_restrict set?"); + return -1; + } + buf = u64_to_ptr(info->xlated_prog_insns); + member_len = info->xlated_prog_len; + } + + if (info->btf_id) { + btf = btf__load_from_kernel_by_id(info->btf_id); + if (libbpf_get_error(btf)) { + p_err("failed to get btf"); + return -1; + } + } + + func_info = u64_to_ptr(info->func_info); + + if (info->nr_line_info) { + prog_linfo = bpf_prog_linfo__new(info); + if (!prog_linfo) + p_info("error in processing bpf_line_info. continue without it."); + } + + if (filepath) { + fd = open(filepath, O_WRONLY | O_CREAT | O_TRUNC, 0600); + if (fd < 0) { + p_err("can't open file %s: %s", filepath, + strerror(errno)); + goto exit_free; + } + + n = write(fd, buf, member_len); + close(fd); + if (n != (ssize_t)member_len) { + p_err("error writing output file: %s", + n < 0 ? strerror(errno) : "short write"); + goto exit_free; + } + + if (json_output) + jsonw_null(json_wtr); + } else if (mode == DUMP_JITED) { + const char *name = NULL; + + if (info->ifindex) { + name = ifindex_to_bfd_params(info->ifindex, + info->netns_dev, + info->netns_ino, + &disasm_opt); + if (!name) + goto exit_free; + } + + if (info->nr_jited_func_lens && info->jited_func_lens) { + struct kernel_sym *sym = NULL; + struct bpf_func_info *record; + char sym_name[SYM_MAX_NAME]; + unsigned char *img = buf; + __u64 *ksyms = NULL; + __u32 *lens; + __u32 i; + if (info->nr_jited_ksyms) { + kernel_syms_load(&dd); + ksyms = u64_to_ptr(info->jited_ksyms); + } + + if (json_output) + jsonw_start_array(json_wtr); + + lens = u64_to_ptr(info->jited_func_lens); + for (i = 0; i < info->nr_jited_func_lens; i++) { + if (ksyms) { + sym = kernel_syms_search(&dd, ksyms[i]); + if (sym) + sprintf(sym_name, "%s", sym->name); + else + sprintf(sym_name, "0x%016llx", ksyms[i]); + } else { + strcpy(sym_name, "unknown"); + } + + if (func_info) { + record = func_info + i * info->func_info_rec_size; + btf_dumper_type_only(btf, record->type_id, + func_sig, + sizeof(func_sig)); + } + + if (json_output) { + jsonw_start_object(json_wtr); + if (func_info && func_sig[0] != '\0') { + jsonw_name(json_wtr, "proto"); + jsonw_string(json_wtr, func_sig); + } + jsonw_name(json_wtr, "name"); + jsonw_string(json_wtr, sym_name); + jsonw_name(json_wtr, "insns"); + } else { + if (func_info && func_sig[0] != '\0') + printf("%s:\n", func_sig); + printf("%s:\n", sym_name); + } + + disasm_print_insn(img, lens[i], opcodes, + name, disasm_opt, btf, + prog_linfo, ksyms[i], i, + linum); + + img += lens[i]; + + if (json_output) + jsonw_end_object(json_wtr); + else + printf("\n"); + } + + if (json_output) + jsonw_end_array(json_wtr); + } else { + disasm_print_insn(buf, member_len, opcodes, name, + disasm_opt, btf, NULL, 0, 0, false); + } + } else if (visual) { + if (json_output) + jsonw_null(json_wtr); + else + dump_xlated_cfg(buf, member_len); + } else { + kernel_syms_load(&dd); + dd.nr_jited_ksyms = info->nr_jited_ksyms; + dd.jited_ksyms = u64_to_ptr(info->jited_ksyms); + dd.btf = btf; + dd.func_info = func_info; + dd.finfo_rec_size = info->func_info_rec_size; + dd.prog_linfo = prog_linfo; + + if (json_output) + dump_xlated_json(&dd, buf, member_len, opcodes, + linum); + else + dump_xlated_plain(&dd, buf, member_len, opcodes, + linum); + kernel_syms_destroy(&dd); + } + + err = 0; + +exit_free: + btf__free(btf); + bpf_prog_linfo__free(prog_linfo); + return err; +} + +static int do_dump(int argc, char **argv) +{ + struct bpf_prog_info info; + __u32 info_len = sizeof(info); + size_t info_data_sz = 0; + void *info_data = NULL; + char *filepath = NULL; + bool opcodes = false; + bool visual = false; + enum dump_mode mode; + bool linum = false; + int nb_fds, i = 0; + int *fds = NULL; + int err = -1; + + if (is_prefix(*argv, "jited")) { + if (disasm_init()) + return -1; + mode = DUMP_JITED; + } else if (is_prefix(*argv, "xlated")) { + mode = DUMP_XLATED; + } else { + p_err("expected 'xlated' or 'jited', got: %s", *argv); + return -1; + } + NEXT_ARG(); + + if (argc < 2) + usage(); + + fds = malloc(sizeof(int)); + if (!fds) { + p_err("mem alloc failed"); + return -1; + } + nb_fds = prog_parse_fds(&argc, &argv, &fds); + if (nb_fds < 1) + goto exit_free; + + if (is_prefix(*argv, "file")) { + NEXT_ARG(); + if (!argc) { + p_err("expected file path"); + goto exit_close; + } + if (nb_fds > 1) { + p_err("several programs matched"); + goto exit_close; + } + + filepath = *argv; + NEXT_ARG(); + } else if (is_prefix(*argv, "opcodes")) { + opcodes = true; + NEXT_ARG(); + } else if (is_prefix(*argv, "visual")) { + if (nb_fds > 1) { + p_err("several programs matched"); + goto exit_close; + } + + visual = true; + NEXT_ARG(); + } else if (is_prefix(*argv, "linum")) { + linum = true; + NEXT_ARG(); + } + + if (argc) { + usage(); + goto exit_close; + } + + if (json_output && nb_fds > 1) + jsonw_start_array(json_wtr); /* root array */ + for (i = 0; i < nb_fds; i++) { + memset(&info, 0, sizeof(info)); + + err = bpf_obj_get_info_by_fd(fds[i], &info, &info_len); + if (err) { + p_err("can't get prog info: %s", strerror(errno)); + break; + } + + err = prep_prog_info(&info, mode, &info_data, &info_data_sz); + if (err) { + p_err("can't grow prog info_data"); + break; + } + + err = bpf_obj_get_info_by_fd(fds[i], &info, &info_len); + if (err) { + p_err("can't get prog info: %s", strerror(errno)); + break; + } + + if (json_output && nb_fds > 1) { + jsonw_start_object(json_wtr); /* prog object */ + print_prog_header_json(&info, fds[i]); + jsonw_name(json_wtr, "insns"); + } else if (nb_fds > 1) { + print_prog_header_plain(&info, fds[i]); + } + + err = prog_dump(&info, mode, filepath, opcodes, visual, linum); + + if (json_output && nb_fds > 1) + jsonw_end_object(json_wtr); /* prog object */ + else if (i != nb_fds - 1 && nb_fds > 1) + printf("\n"); + + if (err) + break; + close(fds[i]); + } + if (json_output && nb_fds > 1) + jsonw_end_array(json_wtr); /* root array */ + +exit_close: + for (; i < nb_fds; i++) + close(fds[i]); +exit_free: + free(info_data); + free(fds); + return err; +} + +static int do_pin(int argc, char **argv) +{ + int err; + + err = do_pin_any(argc, argv, prog_parse_fd); + if (!err && json_output) + jsonw_null(json_wtr); + return err; +} + +struct map_replace { + int idx; + int fd; + char *name; +}; + +static int map_replace_compar(const void *p1, const void *p2) +{ + const struct map_replace *a = p1, *b = p2; + + return a->idx - b->idx; +} + +static int parse_attach_detach_args(int argc, char **argv, int *progfd, + enum bpf_attach_type *attach_type, + int *mapfd) +{ + if (!REQ_ARGS(3)) + return -EINVAL; + + *progfd = prog_parse_fd(&argc, &argv); + if (*progfd < 0) + return *progfd; + + *attach_type = parse_attach_type(*argv); + if (*attach_type == __MAX_BPF_ATTACH_TYPE) { + p_err("invalid attach/detach type"); + return -EINVAL; + } + + if (*attach_type == BPF_FLOW_DISSECTOR) { + *mapfd = 0; + return 0; + } + + NEXT_ARG(); + if (!REQ_ARGS(2)) + return -EINVAL; + + *mapfd = map_parse_fd(&argc, &argv); + if (*mapfd < 0) + return *mapfd; + + return 0; +} + +static int do_attach(int argc, char **argv) +{ + enum bpf_attach_type attach_type; + int err, progfd; + int mapfd; + + err = parse_attach_detach_args(argc, argv, + &progfd, &attach_type, &mapfd); + if (err) + return err; + + err = bpf_prog_attach(progfd, mapfd, attach_type, 0); + if (err) { + p_err("failed prog attach to map"); + return -EINVAL; + } + + if (json_output) + jsonw_null(json_wtr); + return 0; +} + +static int do_detach(int argc, char **argv) +{ + enum bpf_attach_type attach_type; + int err, progfd; + int mapfd; + + err = parse_attach_detach_args(argc, argv, + &progfd, &attach_type, &mapfd); + if (err) + return err; + + err = bpf_prog_detach2(progfd, mapfd, attach_type); + if (err) { + p_err("failed prog detach from map"); + return -EINVAL; + } + + if (json_output) + jsonw_null(json_wtr); + 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; + 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; + LIBBPF_OPTS(bpf_test_run_opts, test_attr); + + 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.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_opts(fd, &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 +get_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type, + enum bpf_attach_type *expected_attach_type) +{ + libbpf_print_fn_t print_backup; + int ret; + + ret = libbpf_prog_type_by_name(name, prog_type, expected_attach_type); + if (!ret) + return ret; + + /* libbpf_prog_type_by_name() failed, let's re-run with debug level */ + print_backup = libbpf_set_print(print_all_levels); + ret = libbpf_prog_type_by_name(name, prog_type, expected_attach_type); + libbpf_set_print(print_backup); + + return ret; +} + +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, + ); + enum bpf_attach_type expected_attach_type; + struct map_replace *map_replace = NULL; + struct bpf_program *prog = NULL, *pos; + unsigned int old_map_fds = 0; + const char *pinmaps = NULL; + struct bpf_object *obj; + struct bpf_map *map; + const char *pinfile; + unsigned int i, j; + __u32 ifindex = 0; + const char *file; + int idx, err; + + + if (!REQ_ARGS(2)) + return -1; + file = GET_ARG(); + pinfile = GET_ARG(); + + while (argc) { + if (is_prefix(*argv, "type")) { + NEXT_ARG(); + + if (common_prog_type != BPF_PROG_TYPE_UNSPEC) { + p_err("program type already specified"); + goto err_free_reuse_maps; + } + if (!REQ_ARGS(1)) + goto err_free_reuse_maps; + + err = libbpf_prog_type_by_name(*argv, &common_prog_type, + &expected_attach_type); + if (err < 0) { + /* Put a '/' at the end of type to appease libbpf */ + char *type = malloc(strlen(*argv) + 2); + + if (!type) { + p_err("mem alloc failed"); + goto err_free_reuse_maps; + } + *type = 0; + strcat(type, *argv); + strcat(type, "/"); + + err = get_prog_type_by_name(type, &common_prog_type, + &expected_attach_type); + free(type); + if (err < 0) + goto err_free_reuse_maps; + } + + NEXT_ARG(); + } else if (is_prefix(*argv, "map")) { + void *new_map_replace; + char *endptr, *name; + int fd; + + NEXT_ARG(); + + if (!REQ_ARGS(4)) + goto err_free_reuse_maps; + + if (is_prefix(*argv, "idx")) { + NEXT_ARG(); + + idx = strtoul(*argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as IDX", *argv); + goto err_free_reuse_maps; + } + name = NULL; + } else if (is_prefix(*argv, "name")) { + NEXT_ARG(); + + name = *argv; + idx = -1; + } else { + p_err("expected 'idx' or 'name', got: '%s'?", + *argv); + goto err_free_reuse_maps; + } + NEXT_ARG(); + + fd = map_parse_fd(&argc, &argv); + if (fd < 0) + goto err_free_reuse_maps; + + new_map_replace = libbpf_reallocarray(map_replace, + old_map_fds + 1, + sizeof(*map_replace)); + if (!new_map_replace) { + p_err("mem alloc failed"); + goto err_free_reuse_maps; + } + map_replace = new_map_replace; + + map_replace[old_map_fds].idx = idx; + map_replace[old_map_fds].name = name; + map_replace[old_map_fds].fd = fd; + old_map_fds++; + } else if (is_prefix(*argv, "dev")) { + NEXT_ARG(); + + if (ifindex) { + p_err("offload device already specified"); + goto err_free_reuse_maps; + } + if (!REQ_ARGS(1)) + goto err_free_reuse_maps; + + ifindex = if_nametoindex(*argv); + if (!ifindex) { + p_err("unrecognized netdevice '%s': %s", + *argv, strerror(errno)); + goto err_free_reuse_maps; + } + NEXT_ARG(); + } else if (is_prefix(*argv, "pinmaps")) { + NEXT_ARG(); + + if (!REQ_ARGS(1)) + goto err_free_reuse_maps; + + pinmaps = GET_ARG(); + } else { + p_err("expected no more arguments, 'type', 'map' or 'dev', got: '%s'?", + *argv); + goto err_free_reuse_maps; + } + } + + set_max_rlimit(); + + if (verifier_logs) + /* log_level1 + log_level2 + stats, but not stable UAPI */ + open_opts.kernel_log_level = 1 + 2 + 4; + + obj = bpf_object__open_file(file, &open_opts); + if (libbpf_get_error(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 = common_prog_type; + + if (prog_type == BPF_PROG_TYPE_UNSPEC) { + const char *sec_name = bpf_program__section_name(pos); + + err = get_prog_type_by_name(sec_name, &prog_type, + &expected_attach_type); + if (err < 0) + goto err_close_obj; + } + + bpf_program__set_ifindex(pos, ifindex); + bpf_program__set_type(pos, prog_type); + bpf_program__set_expected_attach_type(pos, expected_attach_type); + } + + qsort(map_replace, old_map_fds, sizeof(*map_replace), + map_replace_compar); + + /* After the sort maps by name will be first on the list, because they + * have idx == -1. Resolve them. + */ + j = 0; + while (j < old_map_fds && map_replace[j].name) { + i = 0; + bpf_object__for_each_map(map, obj) { + if (!strcmp(bpf_map__name(map), map_replace[j].name)) { + map_replace[j].idx = i; + break; + } + i++; + } + if (map_replace[j].idx == -1) { + p_err("unable to find map '%s'", map_replace[j].name); + goto err_close_obj; + } + j++; + } + /* Resort if any names were resolved */ + if (j) + qsort(map_replace, old_map_fds, sizeof(*map_replace), + map_replace_compar); + + /* Set ifindex and name reuse */ + j = 0; + idx = 0; + bpf_object__for_each_map(map, obj) { + if (bpf_map__type(map) != BPF_MAP_TYPE_PERF_EVENT_ARRAY) + bpf_map__set_ifindex(map, ifindex); + + if (j < old_map_fds && idx == map_replace[j].idx) { + err = bpf_map__reuse_fd(map, map_replace[j++].fd); + if (err) { + p_err("unable to set up map reuse: %d", err); + goto err_close_obj; + } + + /* Next reuse wants to apply to the same map */ + if (j < old_map_fds && map_replace[j].idx == idx) { + p_err("replacement for map idx %d specified more than once", + idx); + goto err_close_obj; + } + } + + idx++; + } + if (j < old_map_fds) { + p_err("map idx '%d' not used", map_replace[j].idx); + goto err_close_obj; + } + + err = bpf_object__load(obj); + if (err) { + p_err("failed to load object file"); + goto err_close_obj; + } + + err = mount_bpffs_for_pin(pinfile); + if (err) + goto err_close_obj; + + if (first_prog_only) { + prog = bpf_object__next_program(obj, NULL); + if (!prog) { + p_err("object file doesn't contain any bpf program"); + goto err_close_obj; + } + + err = bpf_obj_pin(bpf_program__fd(prog), pinfile); + if (err) { + p_err("failed to pin program %s", + bpf_program__section_name(prog)); + goto err_close_obj; + } + } else { + err = bpf_object__pin_programs(obj, pinfile); + if (err) { + p_err("failed to pin all programs"); + goto err_close_obj; + } + } + + if (pinmaps) { + err = bpf_object__pin_maps(obj, pinmaps); + if (err) { + p_err("failed to pin all maps"); + goto err_unpin; + } + } + + if (json_output) + jsonw_null(json_wtr); + + bpf_object__close(obj); + for (i = 0; i < old_map_fds; i++) + close(map_replace[i].fd); + free(map_replace); + + return 0; + +err_unpin: + if (first_prog_only) + unlink(pinfile); + else + bpf_object__unpin_programs(obj, pinfile); +err_close_obj: + if (!legacy_libbpf) { + p_info("Warning: bpftool is now running in libbpf strict mode and has more stringent requirements about BPF programs.\n" + "If it used to work for this object file but now doesn't, see --legacy option for more details.\n"); + } + + bpf_object__close(obj); +err_free_reuse_maps: + for (i = 0; i < old_map_fds; i++) + close(map_replace[i].fd); + free(map_replace); + return -1; +} + +static int count_open_fds(void) +{ + DIR *dp = opendir("/proc/self/fd"); + struct dirent *de; + int cnt = -3; + + if (!dp) + return -1; + + while ((de = readdir(dp))) + cnt++; + + closedir(dp); + return cnt; +} + +static int try_loader(struct gen_loader_opts *gen) +{ + struct bpf_load_and_run_opts opts = {}; + struct bpf_loader_ctx *ctx; + int ctx_sz = sizeof(*ctx) + 64 * max(sizeof(struct bpf_map_desc), + sizeof(struct bpf_prog_desc)); + int log_buf_sz = (1u << 24) - 1; + int err, fds_before, fd_delta; + char *log_buf = NULL; + + ctx = alloca(ctx_sz); + memset(ctx, 0, ctx_sz); + ctx->sz = ctx_sz; + if (verifier_logs) { + ctx->log_level = 1 + 2 + 4; + ctx->log_size = log_buf_sz; + log_buf = malloc(log_buf_sz); + if (!log_buf) + return -ENOMEM; + ctx->log_buf = (long) log_buf; + } + opts.ctx = ctx; + opts.data = gen->data; + opts.data_sz = gen->data_sz; + opts.insns = gen->insns; + opts.insns_sz = gen->insns_sz; + fds_before = count_open_fds(); + err = bpf_load_and_run(&opts); + fd_delta = count_open_fds() - fds_before; + if (err < 0 || verifier_logs) { + fprintf(stderr, "err %d\n%s\n%s", err, opts.errstr, log_buf); + if (fd_delta && err < 0) + fprintf(stderr, "loader prog leaked %d FDs\n", + fd_delta); + } + free(log_buf); + return err; +} + +static int do_loader(int argc, char **argv) +{ + DECLARE_LIBBPF_OPTS(bpf_object_open_opts, open_opts); + DECLARE_LIBBPF_OPTS(gen_loader_opts, gen); + struct bpf_object *obj; + const char *file; + int err = 0; + + if (!REQ_ARGS(1)) + return -1; + file = GET_ARG(); + + if (verifier_logs) + /* log_level1 + log_level2 + stats, but not stable UAPI */ + open_opts.kernel_log_level = 1 + 2 + 4; + + obj = bpf_object__open_file(file, &open_opts); + if (libbpf_get_error(obj)) { + p_err("failed to open object file"); + goto err_close_obj; + } + + err = bpf_object__gen_loader(obj, &gen); + if (err) + goto err_close_obj; + + err = bpf_object__load(obj); + if (err) { + p_err("failed to load object file"); + goto err_close_obj; + } + + if (verifier_logs) { + struct dump_data dd = {}; + + kernel_syms_load(&dd); + dump_xlated_plain(&dd, (void *)gen.insns, gen.insns_sz, false, false); + kernel_syms_destroy(&dd); + } + err = try_loader(&gen); +err_close_obj: + bpf_object__close(obj); + return err; +} + +static int do_load(int argc, char **argv) +{ + if (use_loader) + return do_loader(argc, argv); + return load_with_options(argc, argv, true); +} + +static int do_loadall(int argc, char **argv) +{ + return load_with_options(argc, argv, false); +} + +#ifdef BPFTOOL_WITHOUT_SKELETONS + +static int do_profile(int argc, char **argv) +{ + p_err("bpftool prog profile command is not supported. Please build bpftool with clang >= 10.0.0"); + return 0; +} + +#else /* BPFTOOL_WITHOUT_SKELETONS */ + +#include "profiler.skel.h" + +struct profile_metric { + const char *name; + struct bpf_perf_event_value val; + struct perf_event_attr attr; + bool selected; + + /* calculate ratios like instructions per cycle */ + const int ratio_metric; /* 0 for N/A, 1 for index 0 (cycles) */ + const char *ratio_desc; + const float ratio_mul; +} metrics[] = { + { + .name = "cycles", + .attr = { + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES, + .exclude_user = 1, + }, + }, + { + .name = "instructions", + .attr = { + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_INSTRUCTIONS, + .exclude_user = 1, + }, + .ratio_metric = 1, + .ratio_desc = "insns per cycle", + .ratio_mul = 1.0, + }, + { + .name = "l1d_loads", + .attr = { + .type = PERF_TYPE_HW_CACHE, + .config = + PERF_COUNT_HW_CACHE_L1D | + (PERF_COUNT_HW_CACHE_OP_READ << 8) | + (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16), + .exclude_user = 1, + }, + }, + { + .name = "llc_misses", + .attr = { + .type = PERF_TYPE_HW_CACHE, + .config = + PERF_COUNT_HW_CACHE_LL | + (PERF_COUNT_HW_CACHE_OP_READ << 8) | + (PERF_COUNT_HW_CACHE_RESULT_MISS << 16), + .exclude_user = 1 + }, + .ratio_metric = 2, + .ratio_desc = "LLC misses per million insns", + .ratio_mul = 1e6, + }, + { + .name = "itlb_misses", + .attr = { + .type = PERF_TYPE_HW_CACHE, + .config = + PERF_COUNT_HW_CACHE_ITLB | + (PERF_COUNT_HW_CACHE_OP_READ << 8) | + (PERF_COUNT_HW_CACHE_RESULT_MISS << 16), + .exclude_user = 1 + }, + .ratio_metric = 2, + .ratio_desc = "itlb misses per million insns", + .ratio_mul = 1e6, + }, + { + .name = "dtlb_misses", + .attr = { + .type = PERF_TYPE_HW_CACHE, + .config = + PERF_COUNT_HW_CACHE_DTLB | + (PERF_COUNT_HW_CACHE_OP_READ << 8) | + (PERF_COUNT_HW_CACHE_RESULT_MISS << 16), + .exclude_user = 1 + }, + .ratio_metric = 2, + .ratio_desc = "dtlb misses per million insns", + .ratio_mul = 1e6, + }, +}; + +static __u64 profile_total_count; + +#define MAX_NUM_PROFILE_METRICS 4 + +static int profile_parse_metrics(int argc, char **argv) +{ + unsigned int metric_cnt; + int selected_cnt = 0; + unsigned int i; + + metric_cnt = ARRAY_SIZE(metrics); + + while (argc > 0) { + for (i = 0; i < metric_cnt; i++) { + if (is_prefix(argv[0], metrics[i].name)) { + if (!metrics[i].selected) + selected_cnt++; + metrics[i].selected = true; + break; + } + } + if (i == metric_cnt) { + p_err("unknown metric %s", argv[0]); + return -1; + } + NEXT_ARG(); + } + if (selected_cnt > MAX_NUM_PROFILE_METRICS) { + p_err("too many (%d) metrics, please specify no more than %d metrics at at time", + selected_cnt, MAX_NUM_PROFILE_METRICS); + return -1; + } + return selected_cnt; +} + +static void profile_read_values(struct profiler_bpf *obj) +{ + __u32 m, cpu, num_cpu = obj->rodata->num_cpu; + int reading_map_fd, count_map_fd; + __u64 counts[num_cpu]; + __u32 key = 0; + int err; + + reading_map_fd = bpf_map__fd(obj->maps.accum_readings); + count_map_fd = bpf_map__fd(obj->maps.counts); + if (reading_map_fd < 0 || count_map_fd < 0) { + p_err("failed to get fd for map"); + return; + } + + err = bpf_map_lookup_elem(count_map_fd, &key, counts); + if (err) { + p_err("failed to read count_map: %s", strerror(errno)); + return; + } + + profile_total_count = 0; + for (cpu = 0; cpu < num_cpu; cpu++) + profile_total_count += counts[cpu]; + + for (m = 0; m < ARRAY_SIZE(metrics); m++) { + struct bpf_perf_event_value values[num_cpu]; + + if (!metrics[m].selected) + continue; + + err = bpf_map_lookup_elem(reading_map_fd, &key, values); + if (err) { + p_err("failed to read reading_map: %s", + strerror(errno)); + return; + } + for (cpu = 0; cpu < num_cpu; cpu++) { + metrics[m].val.counter += values[cpu].counter; + metrics[m].val.enabled += values[cpu].enabled; + metrics[m].val.running += values[cpu].running; + } + key++; + } +} + +static void profile_print_readings_json(void) +{ + __u32 m; + + jsonw_start_array(json_wtr); + for (m = 0; m < ARRAY_SIZE(metrics); m++) { + if (!metrics[m].selected) + continue; + jsonw_start_object(json_wtr); + jsonw_string_field(json_wtr, "metric", metrics[m].name); + jsonw_lluint_field(json_wtr, "run_cnt", profile_total_count); + jsonw_lluint_field(json_wtr, "value", metrics[m].val.counter); + jsonw_lluint_field(json_wtr, "enabled", metrics[m].val.enabled); + jsonw_lluint_field(json_wtr, "running", metrics[m].val.running); + + jsonw_end_object(json_wtr); + } + jsonw_end_array(json_wtr); +} + +static void profile_print_readings_plain(void) +{ + __u32 m; + + printf("\n%18llu %-20s\n", profile_total_count, "run_cnt"); + for (m = 0; m < ARRAY_SIZE(metrics); m++) { + struct bpf_perf_event_value *val = &metrics[m].val; + int r; + + if (!metrics[m].selected) + continue; + printf("%18llu %-20s", val->counter, metrics[m].name); + + r = metrics[m].ratio_metric - 1; + if (r >= 0 && metrics[r].selected && + metrics[r].val.counter > 0) { + printf("# %8.2f %-30s", + val->counter * metrics[m].ratio_mul / + metrics[r].val.counter, + metrics[m].ratio_desc); + } else { + printf("%-41s", ""); + } + + if (val->enabled > val->running) + printf("(%4.2f%%)", + val->running * 100.0 / val->enabled); + printf("\n"); + } +} + +static void profile_print_readings(void) +{ + if (json_output) + profile_print_readings_json(); + else + profile_print_readings_plain(); +} + +static char *profile_target_name(int tgt_fd) +{ + struct bpf_func_info func_info; + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + const struct btf_type *t; + __u32 func_info_rec_size; + struct btf *btf = NULL; + char *name = NULL; + int err; + + err = bpf_obj_get_info_by_fd(tgt_fd, &info, &info_len); + if (err) { + p_err("failed to bpf_obj_get_info_by_fd for prog FD %d", tgt_fd); + goto out; + } + + if (info.btf_id == 0) { + p_err("prog FD %d doesn't have valid btf", tgt_fd); + goto out; + } + + func_info_rec_size = info.func_info_rec_size; + if (info.nr_func_info == 0) { + p_err("bpf_obj_get_info_by_fd for prog FD %d found 0 func_info", tgt_fd); + goto out; + } + + memset(&info, 0, sizeof(info)); + info.nr_func_info = 1; + info.func_info_rec_size = func_info_rec_size; + info.func_info = ptr_to_u64(&func_info); + + err = bpf_obj_get_info_by_fd(tgt_fd, &info, &info_len); + if (err) { + p_err("failed to get func_info for prog FD %d", tgt_fd); + goto out; + } + + btf = btf__load_from_kernel_by_id(info.btf_id); + if (libbpf_get_error(btf)) { + p_err("failed to load btf for prog FD %d", tgt_fd); + goto out; + } + + t = btf__type_by_id(btf, func_info.type_id); + if (!t) { + p_err("btf %d doesn't have type %d", + info.btf_id, func_info.type_id); + goto out; + } + name = strdup(btf__name_by_offset(btf, t->name_off)); +out: + btf__free(btf); + return name; +} + +static struct profiler_bpf *profile_obj; +static int profile_tgt_fd = -1; +static char *profile_tgt_name; +static int *profile_perf_events; +static int profile_perf_event_cnt; + +static void profile_close_perf_events(struct profiler_bpf *obj) +{ + int i; + + for (i = profile_perf_event_cnt - 1; i >= 0; i--) + close(profile_perf_events[i]); + + free(profile_perf_events); + profile_perf_event_cnt = 0; +} + +static int profile_open_perf_event(int mid, int cpu, int map_fd) +{ + int pmu_fd; + + pmu_fd = syscall(__NR_perf_event_open, &metrics[mid].attr, + -1 /*pid*/, cpu, -1 /*group_fd*/, 0); + if (pmu_fd < 0) { + if (errno == ENODEV) { + p_info("cpu %d may be offline, skip %s profiling.", + cpu, metrics[mid].name); + profile_perf_event_cnt++; + return 0; + } + return -1; + } + + if (bpf_map_update_elem(map_fd, + &profile_perf_event_cnt, + &pmu_fd, BPF_ANY) || + ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0)) { + close(pmu_fd); + return -1; + } + + profile_perf_events[profile_perf_event_cnt++] = pmu_fd; + return 0; +} + +static int profile_open_perf_events(struct profiler_bpf *obj) +{ + unsigned int cpu, m; + int map_fd; + + profile_perf_events = calloc( + sizeof(int), obj->rodata->num_cpu * obj->rodata->num_metric); + if (!profile_perf_events) { + p_err("failed to allocate memory for perf_event array: %s", + strerror(errno)); + return -1; + } + map_fd = bpf_map__fd(obj->maps.events); + if (map_fd < 0) { + p_err("failed to get fd for events map"); + return -1; + } + + for (m = 0; m < ARRAY_SIZE(metrics); m++) { + if (!metrics[m].selected) + continue; + for (cpu = 0; cpu < obj->rodata->num_cpu; cpu++) { + if (profile_open_perf_event(m, cpu, map_fd)) { + p_err("failed to create event %s on cpu %d", + metrics[m].name, cpu); + return -1; + } + } + } + return 0; +} + +static void profile_print_and_cleanup(void) +{ + profile_close_perf_events(profile_obj); + profile_read_values(profile_obj); + profile_print_readings(); + profiler_bpf__destroy(profile_obj); + + close(profile_tgt_fd); + free(profile_tgt_name); +} + +static void int_exit(int signo) +{ + profile_print_and_cleanup(); + exit(0); +} + +static int do_profile(int argc, char **argv) +{ + int num_metric, num_cpu, err = -1; + struct bpf_program *prog; + unsigned long duration; + char *endptr; + + /* we at least need two args for the prog and one metric */ + if (!REQ_ARGS(3)) + return -EINVAL; + + /* parse target fd */ + profile_tgt_fd = prog_parse_fd(&argc, &argv); + if (profile_tgt_fd < 0) { + p_err("failed to parse fd"); + return -1; + } + + /* parse profiling optional duration */ + if (argc > 2 && is_prefix(argv[0], "duration")) { + NEXT_ARG(); + duration = strtoul(*argv, &endptr, 0); + if (*endptr) + usage(); + NEXT_ARG(); + } else { + duration = UINT_MAX; + } + + num_metric = profile_parse_metrics(argc, argv); + if (num_metric <= 0) + goto out; + + num_cpu = libbpf_num_possible_cpus(); + if (num_cpu <= 0) { + p_err("failed to identify number of CPUs"); + goto out; + } + + profile_obj = profiler_bpf__open(); + if (!profile_obj) { + p_err("failed to open and/or load BPF object"); + goto out; + } + + profile_obj->rodata->num_cpu = num_cpu; + profile_obj->rodata->num_metric = num_metric; + + /* adjust map sizes */ + bpf_map__set_max_entries(profile_obj->maps.events, num_metric * num_cpu); + bpf_map__set_max_entries(profile_obj->maps.fentry_readings, num_metric); + bpf_map__set_max_entries(profile_obj->maps.accum_readings, num_metric); + bpf_map__set_max_entries(profile_obj->maps.counts, 1); + + /* change target name */ + profile_tgt_name = profile_target_name(profile_tgt_fd); + if (!profile_tgt_name) + goto out; + + bpf_object__for_each_program(prog, profile_obj->obj) { + err = bpf_program__set_attach_target(prog, profile_tgt_fd, + profile_tgt_name); + if (err) { + p_err("failed to set attach target\n"); + goto out; + } + } + + set_max_rlimit(); + err = profiler_bpf__load(profile_obj); + if (err) { + p_err("failed to load profile_obj"); + goto out; + } + + err = profile_open_perf_events(profile_obj); + if (err) + goto out; + + err = profiler_bpf__attach(profile_obj); + if (err) { + p_err("failed to attach profile_obj"); + goto out; + } + signal(SIGINT, int_exit); + + sleep(duration); + profile_print_and_cleanup(); + return 0; + +out: + profile_close_perf_events(profile_obj); + if (profile_obj) + profiler_bpf__destroy(profile_obj); + close(profile_tgt_fd); + free(profile_tgt_name); + return err; +} + +#endif /* BPFTOOL_WITHOUT_SKELETONS */ + +static int do_help(int argc, char **argv) +{ + if (json_output) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %1$s %2$s { show | list } [PROG]\n" + " %1$s %2$s dump xlated PROG [{ file FILE | opcodes | visual | linum }]\n" + " %1$s %2$s dump jited PROG [{ file FILE | opcodes | linum }]\n" + " %1$s %2$s pin PROG FILE\n" + " %1$s %2$s { load | loadall } OBJ PATH \\\n" + " [type TYPE] [dev NAME] \\\n" + " [map { idx IDX | name NAME } MAP]\\\n" + " [pinmaps MAP_DIR]\n" + " %1$s %2$s attach PROG ATTACH_TYPE [MAP]\n" + " %1$s %2$s detach PROG ATTACH_TYPE [MAP]\n" + " %1$s %2$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" + " %1$s %2$s profile PROG [duration DURATION] METRICs\n" + " %1$s %2$s tracelog\n" + " %1$s %2$s help\n" + "\n" + " " HELP_SPEC_MAP "\n" + " " HELP_SPEC_PROGRAM "\n" + " TYPE := { socket | kprobe | kretprobe | classifier | action |\n" + " 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 | cgroup/sysctl |\n" + " cgroup/bind4 | cgroup/bind6 | cgroup/post_bind4 |\n" + " cgroup/post_bind6 | cgroup/connect4 | cgroup/connect6 |\n" + " cgroup/getpeername4 | cgroup/getpeername6 |\n" + " cgroup/getsockname4 | cgroup/getsockname6 | cgroup/sendmsg4 |\n" + " cgroup/sendmsg6 | cgroup/recvmsg4 | cgroup/recvmsg6 |\n" + " cgroup/getsockopt | cgroup/setsockopt | cgroup/sock_release |\n" + " struct_ops | fentry | fexit | freplace | sk_lookup }\n" + " ATTACH_TYPE := { sk_msg_verdict | sk_skb_verdict | sk_skb_stream_verdict |\n" + " sk_skb_stream_parser | flow_dissector }\n" + " METRIC := { cycles | instructions | l1d_loads | llc_misses | itlb_misses | dtlb_misses }\n" + " " HELP_SPEC_OPTIONS " |\n" + " {-f|--bpffs} | {-m|--mapcompat} | {-n|--nomount} |\n" + " {-L|--use-loader} }\n" + "", + bin_name, argv[-2]); + + return 0; +} + +static const struct cmd cmds[] = { + { "show", do_show }, + { "list", do_show }, + { "help", do_help }, + { "dump", do_dump }, + { "pin", do_pin }, + { "load", do_load }, + { "loadall", do_loadall }, + { "attach", do_attach }, + { "detach", do_detach }, + { "tracelog", do_tracelog }, + { "run", do_run }, + { "profile", do_profile }, + { 0 } +}; + +int do_prog(int argc, char **argv) +{ + return cmd_select(cmds, argc, argv, do_help); +} diff --git a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c new file mode 100644 index 000000000..26004f0c5 --- /dev/null +++ b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c @@ -0,0 +1,119 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (c) 2020 Facebook */ +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> +#include <bpf/bpf_tracing.h> +#include "pid_iter.h" + +/* keep in sync with the definition in main.h */ +enum bpf_obj_type { + BPF_OBJ_UNKNOWN, + BPF_OBJ_PROG, + BPF_OBJ_MAP, + BPF_OBJ_LINK, + BPF_OBJ_BTF, +}; + +struct bpf_perf_link___local { + struct bpf_link link; + struct file *perf_file; +} __attribute__((preserve_access_index)); + +struct perf_event___local { + u64 bpf_cookie; +} __attribute__((preserve_access_index)); + +enum bpf_link_type___local { + BPF_LINK_TYPE_PERF_EVENT___local = 7, +}; + +extern const void bpf_link_fops __ksym; +extern const void bpf_map_fops __ksym; +extern const void bpf_prog_fops __ksym; +extern const void btf_fops __ksym; + +const volatile enum bpf_obj_type obj_type = BPF_OBJ_UNKNOWN; + +static __always_inline __u32 get_obj_id(void *ent, enum bpf_obj_type type) +{ + switch (type) { + case BPF_OBJ_PROG: + return BPF_CORE_READ((struct bpf_prog *)ent, aux, id); + case BPF_OBJ_MAP: + return BPF_CORE_READ((struct bpf_map *)ent, id); + case BPF_OBJ_BTF: + return BPF_CORE_READ((struct btf *)ent, id); + case BPF_OBJ_LINK: + return BPF_CORE_READ((struct bpf_link *)ent, id); + default: + return 0; + } +} + +/* could be used only with BPF_LINK_TYPE_PERF_EVENT links */ +static __u64 get_bpf_cookie(struct bpf_link *link) +{ + struct bpf_perf_link___local *perf_link; + struct perf_event___local *event; + + perf_link = container_of(link, struct bpf_perf_link___local, link); + event = BPF_CORE_READ(perf_link, perf_file, private_data); + return BPF_CORE_READ(event, bpf_cookie); +} + +SEC("iter/task_file") +int iter(struct bpf_iter__task_file *ctx) +{ + struct file *file = ctx->file; + struct task_struct *task = ctx->task; + struct pid_iter_entry e; + const void *fops; + + if (!file || !task) + return 0; + + switch (obj_type) { + case BPF_OBJ_PROG: + fops = &bpf_prog_fops; + break; + case BPF_OBJ_MAP: + fops = &bpf_map_fops; + break; + case BPF_OBJ_BTF: + fops = &btf_fops; + break; + case BPF_OBJ_LINK: + fops = &bpf_link_fops; + break; + default: + return 0; + } + + if (file->f_op != fops) + return 0; + + __builtin_memset(&e, 0, sizeof(e)); + e.pid = task->tgid; + e.id = get_obj_id(file->private_data, obj_type); + + if (obj_type == BPF_OBJ_LINK && + bpf_core_enum_value_exists(enum bpf_link_type___local, + BPF_LINK_TYPE_PERF_EVENT___local)) { + struct bpf_link *link = (struct bpf_link *) file->private_data; + + if (link->type == bpf_core_enum_value(enum bpf_link_type___local, + BPF_LINK_TYPE_PERF_EVENT___local)) { + e.has_bpf_cookie = true; + e.bpf_cookie = get_bpf_cookie(link); + } + } + + bpf_probe_read_kernel_str(&e.comm, sizeof(e.comm), + task->group_leader->comm); + bpf_seq_write(ctx->meta->seq, &e, sizeof(e)); + + return 0; +} + +char LICENSE[] SEC("license") = "Dual BSD/GPL"; diff --git a/tools/bpf/bpftool/skeleton/pid_iter.h b/tools/bpf/bpftool/skeleton/pid_iter.h new file mode 100644 index 000000000..bbb570d4c --- /dev/null +++ b/tools/bpf/bpftool/skeleton/pid_iter.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* Copyright (c) 2020 Facebook */ +#ifndef __PID_ITER_H +#define __PID_ITER_H + +struct pid_iter_entry { + __u32 id; + int pid; + __u64 bpf_cookie; + bool has_bpf_cookie; + char comm[16]; +}; + +#endif diff --git a/tools/bpf/bpftool/skeleton/profiler.bpf.c b/tools/bpf/bpftool/skeleton/profiler.bpf.c new file mode 100644 index 000000000..2f80edc68 --- /dev/null +++ b/tools/bpf/bpftool/skeleton/profiler.bpf.c @@ -0,0 +1,125 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +// Copyright (c) 2020 Facebook +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +struct bpf_perf_event_value___local { + __u64 counter; + __u64 enabled; + __u64 running; +} __attribute__((preserve_access_index)); + +/* map of perf event fds, num_cpu * num_metric entries */ +struct { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __uint(key_size, sizeof(u32)); + __uint(value_size, sizeof(int)); +} events SEC(".maps"); + +/* readings at fentry */ +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(key_size, sizeof(u32)); + __uint(value_size, sizeof(struct bpf_perf_event_value___local)); +} fentry_readings SEC(".maps"); + +/* accumulated readings */ +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(key_size, sizeof(u32)); + __uint(value_size, sizeof(struct bpf_perf_event_value___local)); +} accum_readings SEC(".maps"); + +/* sample counts, one per cpu */ +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(key_size, sizeof(u32)); + __uint(value_size, sizeof(u64)); +} counts SEC(".maps"); + +const volatile __u32 num_cpu = 1; +const volatile __u32 num_metric = 1; +#define MAX_NUM_MATRICS 4 + +SEC("fentry/XXX") +int BPF_PROG(fentry_XXX) +{ + struct bpf_perf_event_value___local *ptrs[MAX_NUM_MATRICS]; + u32 key = bpf_get_smp_processor_id(); + u32 i; + + /* look up before reading, to reduce error */ + for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++) { + u32 flag = i; + + ptrs[i] = bpf_map_lookup_elem(&fentry_readings, &flag); + if (!ptrs[i]) + return 0; + } + + for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++) { + struct bpf_perf_event_value___local reading; + int err; + + err = bpf_perf_event_read_value(&events, key, (void *)&reading, + sizeof(reading)); + if (err) + return 0; + *(ptrs[i]) = reading; + key += num_cpu; + } + + return 0; +} + +static inline void +fexit_update_maps(u32 id, struct bpf_perf_event_value___local *after) +{ + struct bpf_perf_event_value___local *before, diff; + + before = bpf_map_lookup_elem(&fentry_readings, &id); + /* only account samples with a valid fentry_reading */ + if (before && before->counter) { + struct bpf_perf_event_value___local *accum; + + diff.counter = after->counter - before->counter; + diff.enabled = after->enabled - before->enabled; + diff.running = after->running - before->running; + + accum = bpf_map_lookup_elem(&accum_readings, &id); + if (accum) { + accum->counter += diff.counter; + accum->enabled += diff.enabled; + accum->running += diff.running; + } + } +} + +SEC("fexit/XXX") +int BPF_PROG(fexit_XXX) +{ + struct bpf_perf_event_value___local readings[MAX_NUM_MATRICS]; + u32 cpu = bpf_get_smp_processor_id(); + u32 i, zero = 0; + int err; + u64 *count; + + /* read all events before updating the maps, to reduce error */ + for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++) { + err = bpf_perf_event_read_value(&events, cpu + i * num_cpu, + (void *)(readings + i), + sizeof(*readings)); + if (err) + return 0; + } + count = bpf_map_lookup_elem(&counts, &zero); + if (count) { + *count += 1; + for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++) + fexit_update_maps(i, &readings[i]); + } + return 0; +} + +char LICENSE[] SEC("license") = "Dual BSD/GPL"; diff --git a/tools/bpf/bpftool/struct_ops.c b/tools/bpf/bpftool/struct_ops.c new file mode 100644 index 000000000..e08a6ff28 --- /dev/null +++ b/tools/bpf/bpftool/struct_ops.c @@ -0,0 +1,600 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2020 Facebook */ + +#include <errno.h> +#include <stdio.h> +#include <unistd.h> + +#include <linux/err.h> + +#include <bpf/bpf.h> +#include <bpf/btf.h> +#include <bpf/libbpf.h> + +#include "json_writer.h" +#include "main.h" + +#define STRUCT_OPS_VALUE_PREFIX "bpf_struct_ops_" + +static const struct btf_type *map_info_type; +static __u32 map_info_alloc_len; +static struct btf *btf_vmlinux; +static __s32 map_info_type_id; + +struct res { + unsigned int nr_maps; + unsigned int nr_errs; +}; + +static const struct btf *get_btf_vmlinux(void) +{ + if (btf_vmlinux) + return btf_vmlinux; + + btf_vmlinux = libbpf_find_kernel_btf(); + if (libbpf_get_error(btf_vmlinux)) + p_err("struct_ops requires kernel CONFIG_DEBUG_INFO_BTF=y"); + + return btf_vmlinux; +} + +static const char *get_kern_struct_ops_name(const struct bpf_map_info *info) +{ + const struct btf *kern_btf; + const struct btf_type *t; + const char *st_ops_name; + + kern_btf = get_btf_vmlinux(); + if (libbpf_get_error(kern_btf)) + return "<btf_vmlinux_not_found>"; + + t = btf__type_by_id(kern_btf, info->btf_vmlinux_value_type_id); + st_ops_name = btf__name_by_offset(kern_btf, t->name_off); + st_ops_name += strlen(STRUCT_OPS_VALUE_PREFIX); + + return st_ops_name; +} + +static __s32 get_map_info_type_id(void) +{ + const struct btf *kern_btf; + + if (map_info_type_id) + return map_info_type_id; + + kern_btf = get_btf_vmlinux(); + if (libbpf_get_error(kern_btf)) { + map_info_type_id = PTR_ERR(kern_btf); + return map_info_type_id; + } + + map_info_type_id = btf__find_by_name_kind(kern_btf, "bpf_map_info", + BTF_KIND_STRUCT); + if (map_info_type_id < 0) { + p_err("can't find bpf_map_info from btf_vmlinux"); + return map_info_type_id; + } + map_info_type = btf__type_by_id(kern_btf, map_info_type_id); + + /* Ensure map_info_alloc() has at least what the bpftool needs */ + map_info_alloc_len = map_info_type->size; + if (map_info_alloc_len < sizeof(struct bpf_map_info)) + map_info_alloc_len = sizeof(struct bpf_map_info); + + return map_info_type_id; +} + +/* If the subcmd needs to print out the bpf_map_info, + * it should always call map_info_alloc to allocate + * a bpf_map_info object instead of allocating it + * on the stack. + * + * map_info_alloc() will take the running kernel's btf + * into account. i.e. it will consider the + * sizeof(struct bpf_map_info) of the running kernel. + * + * It will enable the "struct_ops" cmd to print the latest + * "struct bpf_map_info". + * + * [ Recall that "struct_ops" requires the kernel's btf to + * be available ] + */ +static struct bpf_map_info *map_info_alloc(__u32 *alloc_len) +{ + struct bpf_map_info *info; + + if (get_map_info_type_id() < 0) + return NULL; + + info = calloc(1, map_info_alloc_len); + if (!info) + p_err("mem alloc failed"); + else + *alloc_len = map_info_alloc_len; + + return info; +} + +/* It iterates all struct_ops maps of the system. + * It returns the fd in "*res_fd" and map_info in "*info". + * In the very first iteration, info->id should be 0. + * An optional map "*name" filter can be specified. + * The filter can be made more flexible in the future. + * e.g. filter by kernel-struct-ops-name, regex-name, glob-name, ...etc. + * + * Return value: + * 1: A struct_ops map found. It is returned in "*res_fd" and "*info". + * The caller can continue to call get_next in the future. + * 0: No struct_ops map is returned. + * All struct_ops map has been found. + * -1: Error and the caller should abort the iteration. + */ +static int get_next_struct_ops_map(const char *name, int *res_fd, + struct bpf_map_info *info, __u32 info_len) +{ + __u32 id = info->id; + int err, fd; + + while (true) { + err = bpf_map_get_next_id(id, &id); + if (err) { + if (errno == ENOENT) + return 0; + p_err("can't get next map: %s", strerror(errno)); + return -1; + } + + fd = bpf_map_get_fd_by_id(id); + if (fd < 0) { + if (errno == ENOENT) + continue; + p_err("can't get map by id (%u): %s", + id, strerror(errno)); + return -1; + } + + err = bpf_obj_get_info_by_fd(fd, info, &info_len); + if (err) { + p_err("can't get map info: %s", strerror(errno)); + close(fd); + return -1; + } + + if (info->type == BPF_MAP_TYPE_STRUCT_OPS && + (!name || !strcmp(name, info->name))) { + *res_fd = fd; + return 1; + } + close(fd); + } +} + +static int cmd_retval(const struct res *res, bool must_have_one_map) +{ + if (res->nr_errs || (!res->nr_maps && must_have_one_map)) + return -1; + + return 0; +} + +/* "data" is the work_func private storage */ +typedef int (*work_func)(int fd, const struct bpf_map_info *info, void *data, + struct json_writer *wtr); + +/* Find all struct_ops map in the system. + * Filter out by "name" (if specified). + * Then call "func(fd, info, data, wtr)" on each struct_ops map found. + */ +static struct res do_search(const char *name, work_func func, void *data, + struct json_writer *wtr) +{ + struct bpf_map_info *info; + struct res res = {}; + __u32 info_len; + int fd, err; + + info = map_info_alloc(&info_len); + if (!info) { + res.nr_errs++; + return res; + } + + if (wtr) + jsonw_start_array(wtr); + while ((err = get_next_struct_ops_map(name, &fd, info, info_len)) == 1) { + res.nr_maps++; + err = func(fd, info, data, wtr); + if (err) + res.nr_errs++; + close(fd); + } + if (wtr) + jsonw_end_array(wtr); + + if (err) + res.nr_errs++; + + if (!wtr && name && !res.nr_errs && !res.nr_maps) + /* It is not printing empty []. + * Thus, needs to specifically say nothing found + * for "name" here. + */ + p_err("no struct_ops found for %s", name); + else if (!wtr && json_output && !res.nr_errs) + /* The "func()" above is not writing any json (i.e. !wtr + * test here). + * + * However, "-j" is enabled and there is no errs here, + * so call json_null() as the current convention of + * other cmds. + */ + jsonw_null(json_wtr); + + free(info); + return res; +} + +static struct res do_one_id(const char *id_str, work_func func, void *data, + struct json_writer *wtr) +{ + struct bpf_map_info *info; + struct res res = {}; + unsigned long id; + __u32 info_len; + char *endptr; + int fd; + + id = strtoul(id_str, &endptr, 0); + if (*endptr || !id || id > UINT32_MAX) { + p_err("invalid id %s", id_str); + res.nr_errs++; + return res; + } + + fd = bpf_map_get_fd_by_id(id); + if (fd < 0) { + p_err("can't get map by id (%lu): %s", id, strerror(errno)); + res.nr_errs++; + return res; + } + + info = map_info_alloc(&info_len); + if (!info) { + res.nr_errs++; + goto done; + } + + if (bpf_obj_get_info_by_fd(fd, info, &info_len)) { + p_err("can't get map info: %s", strerror(errno)); + res.nr_errs++; + goto done; + } + + if (info->type != BPF_MAP_TYPE_STRUCT_OPS) { + p_err("%s id %u is not a struct_ops map", info->name, info->id); + res.nr_errs++; + goto done; + } + + res.nr_maps++; + + if (func(fd, info, data, wtr)) + res.nr_errs++; + else if (!wtr && json_output) + /* The "func()" above is not writing any json (i.e. !wtr + * test here). + * + * However, "-j" is enabled and there is no errs here, + * so call json_null() as the current convention of + * other cmds. + */ + jsonw_null(json_wtr); + +done: + free(info); + close(fd); + + return res; +} + +static struct res do_work_on_struct_ops(const char *search_type, + const char *search_term, + work_func func, void *data, + struct json_writer *wtr) +{ + if (search_type) { + if (is_prefix(search_type, "id")) + return do_one_id(search_term, func, data, wtr); + else if (!is_prefix(search_type, "name")) + usage(); + } + + return do_search(search_term, func, data, wtr); +} + +static int __do_show(int fd, const struct bpf_map_info *info, void *data, + struct json_writer *wtr) +{ + if (wtr) { + jsonw_start_object(wtr); + jsonw_uint_field(wtr, "id", info->id); + jsonw_string_field(wtr, "name", info->name); + jsonw_string_field(wtr, "kernel_struct_ops", + get_kern_struct_ops_name(info)); + jsonw_end_object(wtr); + } else { + printf("%u: %-15s %-32s\n", info->id, info->name, + get_kern_struct_ops_name(info)); + } + + return 0; +} + +static int do_show(int argc, char **argv) +{ + const char *search_type = NULL, *search_term = NULL; + struct res res; + + if (argc && argc != 2) + usage(); + + if (argc == 2) { + search_type = GET_ARG(); + search_term = GET_ARG(); + } + + res = do_work_on_struct_ops(search_type, search_term, __do_show, + NULL, json_wtr); + + return cmd_retval(&res, !!search_term); +} + +static int __do_dump(int fd, const struct bpf_map_info *info, void *data, + struct json_writer *wtr) +{ + struct btf_dumper *d = (struct btf_dumper *)data; + const struct btf_type *struct_ops_type; + const struct btf *kern_btf = d->btf; + const char *struct_ops_name; + int zero = 0; + void *value; + + /* note: d->jw == wtr */ + + kern_btf = d->btf; + + /* The kernel supporting BPF_MAP_TYPE_STRUCT_OPS must have + * btf_vmlinux_value_type_id. + */ + struct_ops_type = btf__type_by_id(kern_btf, + info->btf_vmlinux_value_type_id); + struct_ops_name = btf__name_by_offset(kern_btf, + struct_ops_type->name_off); + value = calloc(1, info->value_size); + if (!value) { + p_err("mem alloc failed"); + return -1; + } + + if (bpf_map_lookup_elem(fd, &zero, value)) { + p_err("can't lookup struct_ops map %s id %u", + info->name, info->id); + free(value); + return -1; + } + + jsonw_start_object(wtr); + jsonw_name(wtr, "bpf_map_info"); + btf_dumper_type(d, map_info_type_id, (void *)info); + jsonw_end_object(wtr); + + jsonw_start_object(wtr); + jsonw_name(wtr, struct_ops_name); + btf_dumper_type(d, info->btf_vmlinux_value_type_id, value); + jsonw_end_object(wtr); + + free(value); + + return 0; +} + +static int do_dump(int argc, char **argv) +{ + const char *search_type = NULL, *search_term = NULL; + json_writer_t *wtr = json_wtr; + const struct btf *kern_btf; + struct btf_dumper d = {}; + struct res res; + + if (argc && argc != 2) + usage(); + + if (argc == 2) { + search_type = GET_ARG(); + search_term = GET_ARG(); + } + + kern_btf = get_btf_vmlinux(); + if (libbpf_get_error(kern_btf)) + return -1; + + if (!json_output) { + wtr = jsonw_new(stdout); + if (!wtr) { + p_err("can't create json writer"); + return -1; + } + jsonw_pretty(wtr, true); + } + + d.btf = kern_btf; + d.jw = wtr; + d.is_plain_text = !json_output; + d.prog_id_as_func_ptr = true; + + res = do_work_on_struct_ops(search_type, search_term, __do_dump, &d, + wtr); + + if (!json_output) + jsonw_destroy(&wtr); + + return cmd_retval(&res, !!search_term); +} + +static int __do_unregister(int fd, const struct bpf_map_info *info, void *data, + struct json_writer *wtr) +{ + int zero = 0; + + if (bpf_map_delete_elem(fd, &zero)) { + p_err("can't unload %s %s id %u: %s", + get_kern_struct_ops_name(info), info->name, + info->id, strerror(errno)); + return -1; + } + + p_info("Unregistered %s %s id %u", + get_kern_struct_ops_name(info), info->name, + info->id); + + return 0; +} + +static int do_unregister(int argc, char **argv) +{ + const char *search_type, *search_term; + struct res res; + + if (argc != 2) + usage(); + + search_type = GET_ARG(); + search_term = GET_ARG(); + + res = do_work_on_struct_ops(search_type, search_term, + __do_unregister, NULL, NULL); + + return cmd_retval(&res, true); +} + +static int do_register(int argc, char **argv) +{ + LIBBPF_OPTS(bpf_object_open_opts, open_opts); + struct bpf_map_info info = {}; + __u32 info_len = sizeof(info); + int nr_errs = 0, nr_maps = 0; + struct bpf_object *obj; + struct bpf_link *link; + struct bpf_map *map; + const char *file; + + if (argc != 1) + usage(); + + file = GET_ARG(); + + if (verifier_logs) + /* log_level1 + log_level2 + stats, but not stable UAPI */ + open_opts.kernel_log_level = 1 + 2 + 4; + + obj = bpf_object__open_file(file, &open_opts); + if (libbpf_get_error(obj)) + return -1; + + set_max_rlimit(); + + if (bpf_object__load(obj)) { + bpf_object__close(obj); + return -1; + } + + bpf_object__for_each_map(map, obj) { + if (bpf_map__type(map) != BPF_MAP_TYPE_STRUCT_OPS) + continue; + + link = bpf_map__attach_struct_ops(map); + if (libbpf_get_error(link)) { + p_err("can't register struct_ops %s: %s", + bpf_map__name(map), + strerror(-PTR_ERR(link))); + nr_errs++; + continue; + } + nr_maps++; + + bpf_link__disconnect(link); + bpf_link__destroy(link); + + if (!bpf_obj_get_info_by_fd(bpf_map__fd(map), &info, + &info_len)) + p_info("Registered %s %s id %u", + get_kern_struct_ops_name(&info), + bpf_map__name(map), + info.id); + else + /* Not p_err. The struct_ops was attached + * successfully. + */ + p_info("Registered %s but can't find id: %s", + bpf_map__name(map), strerror(errno)); + } + + bpf_object__close(obj); + + if (nr_errs) + return -1; + + if (!nr_maps) { + p_err("no struct_ops found in %s", file); + return -1; + } + + if (json_output) + jsonw_null(json_wtr); + + return 0; +} + +static int do_help(int argc, char **argv) +{ + if (json_output) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %1$s %2$s { show | list } [STRUCT_OPS_MAP]\n" + " %1$s %2$s dump [STRUCT_OPS_MAP]\n" + " %1$s %2$s register OBJ\n" + " %1$s %2$s unregister STRUCT_OPS_MAP\n" + " %1$s %2$s help\n" + "\n" + " STRUCT_OPS_MAP := [ id STRUCT_OPS_MAP_ID | name STRUCT_OPS_MAP_NAME ]\n" + " " HELP_SPEC_OPTIONS " }\n" + "", + bin_name, argv[-2]); + + return 0; +} + +static const struct cmd cmds[] = { + { "show", do_show }, + { "list", do_show }, + { "register", do_register }, + { "unregister", do_unregister }, + { "dump", do_dump }, + { "help", do_help }, + { 0 } +}; + +int do_struct_ops(int argc, char **argv) +{ + int err; + + err = cmd_select(cmds, argc, argv, do_help); + + if (!libbpf_get_error(btf_vmlinux)) + btf__free(btf_vmlinux); + + return err; +} diff --git a/tools/bpf/bpftool/tracelog.c b/tools/bpf/bpftool/tracelog.c new file mode 100644 index 000000000..bf1f02212 --- /dev/null +++ b/tools/bpf/bpftool/tracelog.c @@ -0,0 +1,166 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (c) 2015-2017 Daniel Borkmann */ +/* Copyright (c) 2018 Netronome Systems, Inc. */ + +#include <errno.h> +#include <limits.h> +#include <signal.h> +#include <stdio.h> +#include <string.h> +#include <unistd.h> +#include <linux/magic.h> +#include <fcntl.h> +#include <sys/vfs.h> + +#include "main.h" + +#ifndef TRACEFS_MAGIC +# define TRACEFS_MAGIC 0x74726163 +#endif + +#define _textify(x) #x +#define textify(x) _textify(x) + +FILE *trace_pipe_fd; +char *buff; + +static int validate_tracefs_mnt(const char *mnt, unsigned long magic) +{ + struct statfs st_fs; + + if (statfs(mnt, &st_fs) < 0) + return -ENOENT; + if ((unsigned long)st_fs.f_type != magic) + return -ENOENT; + + return 0; +} + +static bool +find_tracefs_mnt_single(unsigned long magic, char *mnt, const char *mntpt) +{ + size_t src_len; + + if (validate_tracefs_mnt(mntpt, magic)) + return false; + + src_len = strlen(mntpt); + if (src_len + 1 >= PATH_MAX) { + p_err("tracefs mount point name too long"); + return false; + } + + strcpy(mnt, mntpt); + return true; +} + +static bool get_tracefs_pipe(char *mnt) +{ + static const char * const known_mnts[] = { + "/sys/kernel/debug/tracing", + "/sys/kernel/tracing", + "/tracing", + "/trace", + }; + const char *pipe_name = "/trace_pipe"; + const char *fstype = "tracefs"; + char type[100], format[32]; + const char * const *ptr; + bool found = false; + FILE *fp; + + for (ptr = known_mnts; ptr < known_mnts + ARRAY_SIZE(known_mnts); ptr++) + if (find_tracefs_mnt_single(TRACEFS_MAGIC, mnt, *ptr)) + goto exit_found; + + fp = fopen("/proc/mounts", "r"); + if (!fp) + return false; + + /* Allow room for NULL terminating byte and pipe file name */ + snprintf(format, sizeof(format), "%%*s %%%zds %%99s %%*s %%*d %%*d\\n", + PATH_MAX - strlen(pipe_name) - 1); + while (fscanf(fp, format, mnt, type) == 2) + if (strcmp(type, fstype) == 0) { + found = true; + break; + } + fclose(fp); + + /* The string from fscanf() might be truncated, check mnt is valid */ + if (found && validate_tracefs_mnt(mnt, TRACEFS_MAGIC)) + goto exit_found; + + if (block_mount) + return false; + + p_info("could not find tracefs, attempting to mount it now"); + /* Most of the time, tracefs is automatically mounted by debugfs at + * /sys/kernel/debug/tracing when we try to access it. If we could not + * find it, it is likely that debugfs is not mounted. Let's give one + * attempt at mounting just tracefs at /sys/kernel/tracing. + */ + strcpy(mnt, known_mnts[1]); + if (mount_tracefs(mnt)) + return false; + +exit_found: + strcat(mnt, pipe_name); + return true; +} + +static void exit_tracelog(int signum) +{ + fclose(trace_pipe_fd); + free(buff); + + if (json_output) { + jsonw_end_array(json_wtr); + jsonw_destroy(&json_wtr); + } + + exit(0); +} + +int do_tracelog(int argc, char **argv) +{ + const struct sigaction act = { + .sa_handler = exit_tracelog + }; + char trace_pipe[PATH_MAX]; + size_t buff_len = 0; + + if (json_output) + jsonw_start_array(json_wtr); + + if (!get_tracefs_pipe(trace_pipe)) + return -1; + + trace_pipe_fd = fopen(trace_pipe, "r"); + if (!trace_pipe_fd) { + p_err("could not open trace pipe: %s", strerror(errno)); + return -1; + } + + sigaction(SIGHUP, &act, NULL); + sigaction(SIGINT, &act, NULL); + sigaction(SIGTERM, &act, NULL); + while (1) { + ssize_t ret; + + ret = getline(&buff, &buff_len, trace_pipe_fd); + if (ret <= 0) { + p_err("failed to read content from trace pipe: %s", + strerror(errno)); + break; + } + if (json_output) + jsonw_string(json_wtr, buff); + else + printf("%s", buff); + } + + fclose(trace_pipe_fd); + free(buff); + return -1; +} diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c new file mode 100644 index 000000000..d9386a1a4 --- /dev/null +++ b/tools/bpf/bpftool/xlated_dumper.c @@ -0,0 +1,387 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2018 Netronome Systems, Inc. */ + +#define _GNU_SOURCE +#include <stdarg.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/types.h> +#include <bpf/libbpf.h> +#include <bpf/libbpf_internal.h> + +#include "disasm.h" +#include "json_writer.h" +#include "main.h" +#include "xlated_dumper.h" + +static int kernel_syms_cmp(const void *sym_a, const void *sym_b) +{ + return ((struct kernel_sym *)sym_a)->address - + ((struct kernel_sym *)sym_b)->address; +} + +void kernel_syms_load(struct dump_data *dd) +{ + struct kernel_sym *sym; + char buff[256]; + void *tmp, *address; + FILE *fp; + + fp = fopen("/proc/kallsyms", "r"); + if (!fp) + return; + + while (fgets(buff, sizeof(buff), fp)) { + tmp = libbpf_reallocarray(dd->sym_mapping, dd->sym_count + 1, + sizeof(*dd->sym_mapping)); + if (!tmp) { +out: + free(dd->sym_mapping); + dd->sym_mapping = NULL; + fclose(fp); + return; + } + dd->sym_mapping = tmp; + sym = &dd->sym_mapping[dd->sym_count]; + if (sscanf(buff, "%p %*c %s", &address, sym->name) != 2) + continue; + sym->address = (unsigned long)address; + if (!strcmp(sym->name, "__bpf_call_base")) { + dd->address_call_base = sym->address; + /* sysctl kernel.kptr_restrict was set */ + if (!sym->address) + goto out; + } + if (sym->address) + dd->sym_count++; + } + + fclose(fp); + + qsort(dd->sym_mapping, dd->sym_count, + sizeof(*dd->sym_mapping), kernel_syms_cmp); +} + +void kernel_syms_destroy(struct dump_data *dd) +{ + free(dd->sym_mapping); +} + +struct kernel_sym *kernel_syms_search(struct dump_data *dd, + unsigned long key) +{ + struct kernel_sym sym = { + .address = key, + }; + + return dd->sym_mapping ? + bsearch(&sym, dd->sym_mapping, dd->sym_count, + sizeof(*dd->sym_mapping), kernel_syms_cmp) : NULL; +} + +static void __printf(2, 3) print_insn(void *private_data, const char *fmt, ...) +{ + va_list args; + + va_start(args, fmt); + vprintf(fmt, args); + va_end(args); +} + +static void __printf(2, 3) +print_insn_for_graph(void *private_data, const char *fmt, ...) +{ + char buf[64], *p; + va_list args; + + va_start(args, fmt); + vsnprintf(buf, sizeof(buf), fmt, args); + va_end(args); + + p = buf; + while (*p != '\0') { + if (*p == '\n') { + memmove(p + 3, p, strlen(buf) + 1 - (p - buf)); + /* Align each instruction dump row left. */ + *p++ = '\\'; + *p++ = 'l'; + /* Output multiline concatenation. */ + *p++ = '\\'; + } else if (*p == '<' || *p == '>' || *p == '|' || *p == '&') { + memmove(p + 1, p, strlen(buf) + 1 - (p - buf)); + /* Escape special character. */ + *p++ = '\\'; + } + + p++; + } + + printf("%s", buf); +} + +static void __printf(2, 3) +print_insn_json(void *private_data, const char *fmt, ...) +{ + unsigned int l = strlen(fmt); + char chomped_fmt[l]; + va_list args; + + va_start(args, fmt); + if (l > 0) { + strncpy(chomped_fmt, fmt, l - 1); + chomped_fmt[l - 1] = '\0'; + } + jsonw_vprintf_enquote(json_wtr, chomped_fmt, args); + va_end(args); +} + +static const char *print_call_pcrel(struct dump_data *dd, + struct kernel_sym *sym, + unsigned long address, + const struct bpf_insn *insn) +{ + if (!dd->nr_jited_ksyms) + /* Do not show address for interpreted programs */ + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "%+d", insn->off); + else if (sym) + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "%+d#%s", insn->off, sym->name); + else + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "%+d#0x%lx", insn->off, address); + return dd->scratch_buff; +} + +static const char *print_call_helper(struct dump_data *dd, + struct kernel_sym *sym, + unsigned long address) +{ + if (sym) + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "%s", sym->name); + else + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "0x%lx", address); + return dd->scratch_buff; +} + +static const char *print_call(void *private_data, + const struct bpf_insn *insn) +{ + struct dump_data *dd = private_data; + unsigned long address = dd->address_call_base + insn->imm; + struct kernel_sym *sym; + + if (insn->src_reg == BPF_PSEUDO_CALL && + (__u32) insn->imm < dd->nr_jited_ksyms && dd->jited_ksyms) + address = dd->jited_ksyms[insn->imm]; + + sym = kernel_syms_search(dd, address); + if (insn->src_reg == BPF_PSEUDO_CALL) + return print_call_pcrel(dd, sym, address, insn); + else + return print_call_helper(dd, sym, address); +} + +static const char *print_imm(void *private_data, + const struct bpf_insn *insn, + __u64 full_imm) +{ + struct dump_data *dd = 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 if (insn->src_reg == BPF_PSEUDO_MAP_IDX_VALUE) + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "map[idx:%u]+%u", insn->imm, (insn + 1)->imm); + else if (insn->src_reg == BPF_PSEUDO_FUNC) + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "subprog[%+d]", insn->imm); + else + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "0x%llx", (unsigned long long)full_imm); + return dd->scratch_buff; +} + +void dump_xlated_json(struct dump_data *dd, void *buf, unsigned int len, + bool opcodes, bool linum) +{ + const struct bpf_prog_linfo *prog_linfo = dd->prog_linfo; + const struct bpf_insn_cbs cbs = { + .cb_print = print_insn_json, + .cb_call = print_call, + .cb_imm = print_imm, + .private_data = dd, + }; + struct bpf_func_info *record; + struct bpf_insn *insn = buf; + struct btf *btf = dd->btf; + bool double_insn = false; + unsigned int nr_skip = 0; + char func_sig[1024]; + unsigned int i; + + jsonw_start_array(json_wtr); + record = dd->func_info; + for (i = 0; i < len / sizeof(*insn); i++) { + if (double_insn) { + double_insn = false; + continue; + } + double_insn = insn[i].code == (BPF_LD | BPF_IMM | BPF_DW); + + jsonw_start_object(json_wtr); + + if (btf && record) { + if (record->insn_off == i) { + btf_dumper_type_only(btf, record->type_id, + func_sig, + sizeof(func_sig)); + if (func_sig[0] != '\0') { + jsonw_name(json_wtr, "proto"); + jsonw_string(json_wtr, func_sig); + } + record = (void *)record + dd->finfo_rec_size; + } + } + + if (prog_linfo) { + const struct bpf_line_info *linfo; + + linfo = bpf_prog_linfo__lfind(prog_linfo, i, nr_skip); + if (linfo) { + btf_dump_linfo_json(btf, linfo, linum); + nr_skip++; + } + } + + jsonw_name(json_wtr, "disasm"); + print_bpf_insn(&cbs, insn + i, true); + + if (opcodes) { + jsonw_name(json_wtr, "opcodes"); + jsonw_start_object(json_wtr); + + jsonw_name(json_wtr, "code"); + jsonw_printf(json_wtr, "\"0x%02hhx\"", insn[i].code); + + jsonw_name(json_wtr, "src_reg"); + jsonw_printf(json_wtr, "\"0x%hhx\"", insn[i].src_reg); + + jsonw_name(json_wtr, "dst_reg"); + jsonw_printf(json_wtr, "\"0x%hhx\"", insn[i].dst_reg); + + jsonw_name(json_wtr, "off"); + print_hex_data_json((uint8_t *)(&insn[i].off), 2); + + jsonw_name(json_wtr, "imm"); + if (double_insn && i < len - 1) + print_hex_data_json((uint8_t *)(&insn[i].imm), + 12); + else + print_hex_data_json((uint8_t *)(&insn[i].imm), + 4); + jsonw_end_object(json_wtr); + } + jsonw_end_object(json_wtr); + } + jsonw_end_array(json_wtr); +} + +void dump_xlated_plain(struct dump_data *dd, void *buf, unsigned int len, + bool opcodes, bool linum) +{ + const struct bpf_prog_linfo *prog_linfo = dd->prog_linfo; + const struct bpf_insn_cbs cbs = { + .cb_print = print_insn, + .cb_call = print_call, + .cb_imm = print_imm, + .private_data = dd, + }; + struct bpf_func_info *record; + struct bpf_insn *insn = buf; + struct btf *btf = dd->btf; + unsigned int nr_skip = 0; + bool double_insn = false; + char func_sig[1024]; + unsigned int i; + + record = dd->func_info; + for (i = 0; i < len / sizeof(*insn); i++) { + if (double_insn) { + double_insn = false; + continue; + } + + if (btf && record) { + if (record->insn_off == i) { + btf_dumper_type_only(btf, record->type_id, + func_sig, + sizeof(func_sig)); + if (func_sig[0] != '\0') + printf("%s:\n", func_sig); + record = (void *)record + dd->finfo_rec_size; + } + } + + if (prog_linfo) { + const struct bpf_line_info *linfo; + + linfo = bpf_prog_linfo__lfind(prog_linfo, i, nr_skip); + if (linfo) { + btf_dump_linfo_plain(btf, linfo, "; ", + linum); + nr_skip++; + } + } + + double_insn = insn[i].code == (BPF_LD | BPF_IMM | BPF_DW); + + printf("% 4d: ", i); + print_bpf_insn(&cbs, insn + i, true); + + if (opcodes) { + printf(" "); + fprint_hex(stdout, insn + i, 8, " "); + if (double_insn && i < len - 1) { + printf(" "); + fprint_hex(stdout, insn + i + 1, 8, " "); + } + printf("\n"); + } + } +} + +void dump_xlated_for_graph(struct dump_data *dd, void *buf_start, void *buf_end, + unsigned int start_idx) +{ + const struct bpf_insn_cbs cbs = { + .cb_print = print_insn_for_graph, + .cb_call = print_call, + .cb_imm = print_imm, + .private_data = dd, + }; + struct bpf_insn *insn_start = buf_start; + struct bpf_insn *insn_end = buf_end; + struct bpf_insn *cur = insn_start; + bool double_insn = false; + + for (; cur <= insn_end; cur++) { + if (double_insn) { + double_insn = false; + continue; + } + double_insn = cur->code == (BPF_LD | BPF_IMM | BPF_DW); + + printf("% 4d: ", (int)(cur - insn_start + start_idx)); + print_bpf_insn(&cbs, cur, true); + if (cur != insn_end) + printf(" | "); + } +} diff --git a/tools/bpf/bpftool/xlated_dumper.h b/tools/bpf/bpftool/xlated_dumper.h new file mode 100644 index 000000000..54847e174 --- /dev/null +++ b/tools/bpf/bpftool/xlated_dumper.h @@ -0,0 +1,39 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* Copyright (C) 2018 Netronome Systems, Inc. */ + +#ifndef __BPF_TOOL_XLATED_DUMPER_H +#define __BPF_TOOL_XLATED_DUMPER_H + +#define SYM_MAX_NAME 256 + +struct bpf_prog_linfo; + +struct kernel_sym { + unsigned long address; + char name[SYM_MAX_NAME]; +}; + +struct dump_data { + unsigned long address_call_base; + struct kernel_sym *sym_mapping; + __u32 sym_count; + __u64 *jited_ksyms; + __u32 nr_jited_ksyms; + struct btf *btf; + void *func_info; + __u32 finfo_rec_size; + const struct bpf_prog_linfo *prog_linfo; + char scratch_buff[SYM_MAX_NAME + 8]; +}; + +void kernel_syms_load(struct dump_data *dd); +void kernel_syms_destroy(struct dump_data *dd); +struct kernel_sym *kernel_syms_search(struct dump_data *dd, unsigned long key); +void dump_xlated_json(struct dump_data *dd, void *buf, unsigned int len, + bool opcodes, bool linum); +void dump_xlated_plain(struct dump_data *dd, void *buf, unsigned int len, + bool opcodes, bool linum); +void dump_xlated_for_graph(struct dump_data *dd, void *buf, void *buf_end, + unsigned int start_index); + +#endif |