diff options
Diffstat (limited to 'tools/bpf')
28 files changed, 2215 insertions, 275 deletions
diff --git a/tools/bpf/Makefile b/tools/bpf/Makefile index 5535650800ab..f897eeeb0b4f 100644 --- a/tools/bpf/Makefile +++ b/tools/bpf/Makefile @@ -38,7 +38,7 @@ FEATURE_TESTS = libbfd disassembler-four-args FEATURE_DISPLAY = libbfd disassembler-four-args check_feat := 1 -NON_CHECK_FEAT_TARGETS := clean bpftool_clean +NON_CHECK_FEAT_TARGETS := clean bpftool_clean runqslower_clean ifdef MAKECMDGOALS ifeq ($(filter-out $(NON_CHECK_FEAT_TARGETS),$(MAKECMDGOALS)),) check_feat := 0 @@ -73,7 +73,7 @@ $(OUTPUT)%.lex.o: $(OUTPUT)%.lex.c PROGS = $(OUTPUT)bpf_jit_disasm $(OUTPUT)bpf_dbg $(OUTPUT)bpf_asm -all: $(PROGS) bpftool +all: $(PROGS) bpftool runqslower $(OUTPUT)bpf_jit_disasm: CFLAGS += -DPACKAGE='bpf_jit_disasm' $(OUTPUT)bpf_jit_disasm: $(OUTPUT)bpf_jit_disasm.o @@ -89,7 +89,7 @@ $(OUTPUT)bpf_exp.lex.c: $(OUTPUT)bpf_exp.yacc.c $(OUTPUT)bpf_exp.yacc.o: $(OUTPUT)bpf_exp.yacc.c $(OUTPUT)bpf_exp.lex.o: $(OUTPUT)bpf_exp.lex.c -clean: bpftool_clean +clean: bpftool_clean runqslower_clean $(call QUIET_CLEAN, bpf-progs) $(Q)$(RM) -r -- $(OUTPUT)*.o $(OUTPUT)bpf_jit_disasm $(OUTPUT)bpf_dbg \ $(OUTPUT)bpf_asm $(OUTPUT)bpf_exp.yacc.* $(OUTPUT)bpf_exp.lex.* @@ -97,7 +97,7 @@ clean: bpftool_clean $(Q)$(RM) -- $(OUTPUT)FEATURE-DUMP.bpf $(Q)$(RM) -r -- $(OUTPUT)feature -install: $(PROGS) bpftool_install +install: $(PROGS) bpftool_install runqslower_install $(call QUIET_INSTALL, bpf_jit_disasm) $(Q)$(INSTALL) -m 0755 -d $(DESTDIR)$(prefix)/bin $(Q)$(INSTALL) $(OUTPUT)bpf_jit_disasm $(DESTDIR)$(prefix)/bin/bpf_jit_disasm @@ -115,4 +115,14 @@ bpftool_install: bpftool_clean: $(call descend,bpftool,clean) -.PHONY: all install clean bpftool bpftool_install bpftool_clean +runqslower: + $(call descend,runqslower) + +runqslower_install: + $(call descend,runqslower,install) + +runqslower_clean: + $(call descend,runqslower,clean) + +.PHONY: all install clean bpftool bpftool_install bpftool_clean \ + runqslower runqslower_install runqslower_clean diff --git a/tools/bpf/bpftool/Documentation/bpftool-gen.rst b/tools/bpf/bpftool/Documentation/bpftool-gen.rst new file mode 100644 index 000000000000..94d91322895a --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-gen.rst @@ -0,0 +1,305 @@ +================ +bpftool-gen +================ +------------------------------------------------------------------------------- +tool for BPF code-generation +------------------------------------------------------------------------------- + +:Manual section: 8 + +SYNOPSIS +======== + + **bpftool** [*OPTIONS*] **gen** *COMMAND* + + *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] } + + *COMMAND* := { **skeleton | **help** } + +GEN COMMANDS +============= + +| **bpftool** **gen skeleton** *FILE* +| **bpftool** **gen help** + +DESCRIPTION +=========== + **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, derived from + object file name. I.e., if BPF object file name is + **example.o**, BPF object name will be **example**. The + following custom functions are provided in such case: + + - **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 help** + Print short help message. + +OPTIONS +======= + -h, --help + Print short generic help message (similar to **bpftool help**). + + -V, --version + Print version number (similar to **bpftool version**). + + -j, --json + Generate JSON output. For commands that cannot produce JSON, + this option has no effect. + + -p, --pretty + Generate human-readable JSON output. Implies **-j**. + + -d, --debug + Print all logs available from libbpf, including debug-level + information. + +EXAMPLES +======== +**$ cat example.c** +:: + + #include <stdbool.h> + #include <linux/ptrace.h> + #include <linux/bpf.h> + #include "bpf_helpers.h" + + const volatile int param1 = 42; + bool global_flag = true; + struct { int x; } data = {}; + + 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_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; + } + + 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. + +**$ bpftool gen skeleton example.o** +:: + + /* 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_user.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_user** +:: + + 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. + +SEE ALSO +======== + **bpf**\ (2), + **bpf-helpers**\ (7), + **bpftool**\ (8), + **bpftool-map**\ (8), + **bpftool-prog**\ (8), + **bpftool-cgroup**\ (8), + **bpftool-feature**\ (8), + **bpftool-net**\ (8), + **bpftool-perf**\ (8), + **bpftool-btf**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst index 1c0f7146aab0..cdeae8ae90ba 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-map.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst @@ -39,9 +39,9 @@ MAP COMMANDS | **bpftool** **map freeze** *MAP* | **bpftool** **map help** | -| *MAP* := { **id** *MAP_ID* | **pinned** *FILE* } +| *MAP* := { **id** *MAP_ID* | **pinned** *FILE* | **name** *MAP_NAME* } | *DATA* := { [**hex**] *BYTES* } -| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* } +| *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** @@ -55,8 +55,9 @@ DESCRIPTION =========== **bpftool map { show | list }** [*MAP*] Show information about loaded maps. If *MAP* is specified - show information only about given map, otherwise list all - maps currently loaded on the system. + 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). @@ -66,7 +67,8 @@ DESCRIPTION as *FILE*. **bpftool map dump** *MAP* - Dump all entries in a given *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*. diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index 7a374b3c851d..64ddf8a4c518 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -33,7 +33,7 @@ PROG COMMANDS | **bpftool** **prog help** | | *MAP* := { **id** *MAP_ID* | **pinned** *FILE* } -| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* } +| *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** | @@ -53,8 +53,10 @@ DESCRIPTION =========== **bpftool prog { show | list }** [*PROG*] Show information about loaded programs. If *PROG* is - specified show information only about given program, otherwise - list all programs currently loaded on the system. + 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). @@ -68,11 +70,15 @@ DESCRIPTION performed via the **kernel.bpf_stats_enabled** sysctl knob. **bpftool prog dump xlated** *PROG* [{ **file** *FILE* | **opcodes** | **visual** | **linum** }] - Dump eBPF instructions of the program from the kernel. By + 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*. @@ -80,15 +86,17 @@ DESCRIPTION built instead, and eBPF instructions will be presented with CFG in DOT format, on standard output. - If the prog has line_info available, the source line will + 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. diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst index 6a9c52ef84a9..34239fda69ed 100644 --- a/tools/bpf/bpftool/Documentation/bpftool.rst +++ b/tools/bpf/bpftool/Documentation/bpftool.rst @@ -81,4 +81,5 @@ SEE ALSO **bpftool-feature**\ (8), **bpftool-net**\ (8), **bpftool-perf**\ (8), - **bpftool-btf**\ (8) + **bpftool-btf**\ (8), + **bpftool-gen**\ (8), diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index 39bc6f0f4f0b..c4e810335810 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -45,7 +45,7 @@ CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ \ -I$(srctree)/kernel/bpf/ \ -I$(srctree)/tools/include \ -I$(srctree)/tools/include/uapi \ - -I$(srctree)/tools/lib/bpf \ + -I$(srctree)/tools/lib \ -I$(srctree)/tools/perf CFLAGS += -DBPFTOOL_VERSION='"$(BPFTOOL_VERSION)"' ifneq ($(EXTRA_CFLAGS),) diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index 70493a6da206..754d8395e451 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -59,6 +59,21 @@ _bpftool_get_map_ids_for_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 | \ @@ -71,6 +86,12 @@ _bpftool_get_prog_tags() 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 | \ @@ -180,6 +201,52 @@ _bpftool_map_update_get_id() 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 @@ -251,7 +318,8 @@ _bpftool() # Completion depends on object and command in use case $object in prog) - # Complete id, only for subcommands that use prog (but no map) ids + # 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 @@ -259,12 +327,16 @@ _bpftool() _bpftool_get_prog_ids return 0 ;; + name) + _bpftool_get_prog_names + return 0 + ;; esac ;; esac - local PROG_TYPE='id pinned tag' - local MAP_TYPE='id pinned' + local PROG_TYPE='id pinned tag name' + local MAP_TYPE='id pinned name' case $command in show|list) [[ $prev != "$command" ]] && return 0 @@ -315,6 +387,9 @@ _bpftool() id) _bpftool_get_prog_ids ;; + name) + _bpftool_get_map_names + ;; pinned) _filedir ;; @@ -335,6 +410,9 @@ _bpftool() id) _bpftool_get_map_ids ;; + name) + _bpftool_get_map_names + ;; pinned) _filedir ;; @@ -399,6 +477,10 @@ _bpftool() _bpftool_get_map_ids return 0 ;; + name) + _bpftool_get_map_names + return 0 + ;; pinned|pinmaps) _filedir return 0 @@ -447,7 +529,7 @@ _bpftool() esac ;; map) - local MAP_TYPE='id pinned' + local MAP_TYPE='id pinned name' case $command in show|list|dump|peek|pop|dequeue|freeze) case $prev in @@ -473,6 +555,24 @@ _bpftool() esac return 0 ;; + name) + case "$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 ;; @@ -520,6 +620,10 @@ _bpftool() _bpftool_get_map_ids return 0 ;; + name) + _bpftool_get_map_names + return 0 + ;; key) COMPREPLY+=( $( compgen -W 'hex' -- "$cur" ) ) ;; @@ -545,6 +649,10 @@ _bpftool() _bpftool_map_update_get_id $command return 0 ;; + name) + _bpftool_map_update_get_name $command + return 0 + ;; key) COMPREPLY+=( $( compgen -W 'hex' -- "$cur" ) ) ;; @@ -553,13 +661,13 @@ _bpftool() # 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' + local MAP_TYPE='id pinned name' COMPREPLY+=( $( compgen -W "$MAP_TYPE" \ -- "$cur" ) ) return 0 ;; prog_array) - local PROG_TYPE='id pinned tag' + local PROG_TYPE='id pinned tag name' COMPREPLY+=( $( compgen -W "$PROG_TYPE" \ -- "$cur" ) ) return 0 @@ -621,6 +729,10 @@ _bpftool() _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 ;; @@ -644,8 +756,8 @@ _bpftool() esac ;; btf) - local PROG_TYPE='id pinned tag' - local MAP_TYPE='id pinned' + local PROG_TYPE='id pinned tag name' + local MAP_TYPE='id pinned name' case $command in dump) case $prev in @@ -676,6 +788,17 @@ _bpftool() 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" ) ) ;; @@ -716,6 +839,17 @@ _bpftool() ;; esac ;; + gen) + case $command in + skeleton) + _filedir + ;; + *) + [[ $prev == $object ]] && \ + COMPREPLY=( $( compgen -W 'skeleton help' -- "$cur" ) ) + ;; + esac + ;; cgroup) case $command in show|list|tree) @@ -735,7 +869,7 @@ _bpftool() connect6 sendmsg4 sendmsg6 recvmsg4 recvmsg6 sysctl \ getsockopt setsockopt' local ATTACH_FLAGS='multi override' - local PROG_TYPE='id pinned tag' + local PROG_TYPE='id pinned tag name' case $prev in $command) _filedir @@ -760,7 +894,7 @@ _bpftool() elif [[ "$command" == "attach" ]]; then # We have an attach type on the command line, # but it is not the previous word, or - # "id|pinned|tag" (we already checked for + # "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" @@ -786,7 +920,7 @@ _bpftool() esac ;; net) - local PROG_TYPE='id pinned tag' + local PROG_TYPE='id pinned tag name' local ATTACH_TYPES='xdp xdpgeneric xdpdrv xdpoffload' case $command in show|list) diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c index e5bc97b71ceb..b3745ed711ba 100644 --- a/tools/bpf/bpftool/btf.c +++ b/tools/bpf/bpftool/btf.c @@ -8,15 +8,15 @@ #include <stdio.h> #include <string.h> #include <unistd.h> -#include <bpf.h> -#include <libbpf.h> +#include <bpf/bpf.h> +#include <bpf/btf.h> +#include <bpf/libbpf.h> #include <linux/btf.h> #include <linux/hashtable.h> #include <sys/types.h> #include <sys/stat.h> #include <unistd.h> -#include "btf.h" #include "json_writer.h" #include "main.h" @@ -77,6 +77,20 @@ static const char *btf_var_linkage_str(__u32 linkage) } } +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) @@ -231,12 +245,17 @@ static int dump_btf_type(const struct btf *btf, __u32 id, printf(" fwd_kind=%s", fwd_kind); break; } - case BTF_KIND_FUNC: - if (json_output) + case BTF_KIND_FUNC: { + const char *linkage = btf_func_linkage_str(t); + + if (json_output) { jsonw_uint_field(w, "type_id", t->type); - else - printf(" type_id=%u", 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); @@ -370,6 +389,10 @@ static int dump_btf_c(const struct btf *btf, if (IS_ERR(d)) return PTR_ERR(d); + 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]); @@ -386,6 +409,10 @@ static int dump_btf_c(const struct btf *btf, } } + printf("#ifndef BPF_NO_PRESERVE_ACCESS_INDEX\n"); + printf("#pragma clang attribute pop\n"); + printf("#endif\n"); + done: btf_dump__free(d); return err; @@ -524,7 +551,7 @@ static int do_dump(int argc, char **argv) if (IS_ERR(btf)) { err = PTR_ERR(btf); btf = NULL; - p_err("failed to load BTF from %s: %s", + p_err("failed to load BTF from %s: %s", *argv, strerror(err)); goto done; } diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c index 397e5716ab6d..01cc52b834fa 100644 --- a/tools/bpf/bpftool/btf_dumper.c +++ b/tools/bpf/bpftool/btf_dumper.c @@ -8,8 +8,8 @@ #include <linux/bitops.h> #include <linux/btf.h> #include <linux/err.h> +#include <bpf/btf.h> -#include "btf.h" #include "json_writer.h" #include "main.h" diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c index 1ef45e55039e..62c6a1d7cd18 100644 --- a/tools/bpf/bpftool/cgroup.c +++ b/tools/bpf/bpftool/cgroup.c @@ -14,7 +14,7 @@ #include <sys/types.h> #include <unistd.h> -#include <bpf.h> +#include <bpf/bpf.h> #include "main.h" @@ -117,6 +117,25 @@ static int count_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type) 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_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type, int level) { @@ -161,6 +180,7 @@ static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type, static int do_show(int argc, char **argv) { enum bpf_attach_type type; + int has_attached_progs; const char *path; int cgroup_fd; int ret = -1; @@ -192,6 +212,16 @@ static int do_show(int argc, char **argv) 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 @@ -212,6 +242,7 @@ static int do_show(int argc, char **argv) if (json_output) jsonw_end_array(json_wtr); +exit_cgroup: close(cgroup_fd); exit: return ret; @@ -228,7 +259,7 @@ static int do_show_tree_fn(const char *fpath, const struct stat *sb, int typeflag, struct FTW *ftw) { enum bpf_attach_type type; - bool skip = true; + int has_attached_progs; int cgroup_fd; if (typeflag != FTW_D) @@ -240,22 +271,13 @@ static int do_show_tree_fn(const char *fpath, const struct stat *sb, return SHOW_TREE_FN_ERR; } - for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) { - int count = count_attached_bpf_progs(cgroup_fd, type); - - if (count < 0 && errno != EINVAL) { - p_err("can't query bpf programs attached to %s: %s", - fpath, strerror(errno)); - close(cgroup_fd); - return SHOW_TREE_FN_ERR; - } - if (count > 0) { - skip = false; - break; - } - } - - if (skip) { + 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; } diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index 88264abaa738..b75b8ec5469c 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -20,8 +20,8 @@ #include <sys/stat.h> #include <sys/vfs.h> -#include <bpf.h> -#include <libbpf.h> /* libbpf_num_possible_cpus */ +#include <bpf/bpf.h> +#include <bpf/libbpf.h> /* libbpf_num_possible_cpus */ #include "main.h" diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c index 03bdc5b3ac49..446ba891f1e2 100644 --- a/tools/bpf/bpftool/feature.c +++ b/tools/bpf/bpftool/feature.c @@ -12,8 +12,8 @@ #include <linux/filter.h> #include <linux/limits.h> -#include <bpf.h> -#include <libbpf.h> +#include <bpf/bpf.h> +#include <bpf/libbpf.h> #include <zlib.h> #include "main.h" @@ -572,6 +572,18 @@ probe_helpers_for_progtype(enum bpf_prog_type prog_type, bool supported_type, printf("\n"); } +static void +probe_large_insn_limit(const char *define_prefix, __u32 ifindex) +{ + bool res; + + res = bpf_probe_large_insn_limit(ifindex); + print_bool_feature("have_large_insn_limit", + "Large program size limit", + "HAVE_LARGE_INSN_LIMIT", + res, define_prefix); +} + static int do_probe(int argc, char **argv) { enum probe_component target = COMPONENT_UNSPEC; @@ -724,6 +736,12 @@ static int do_probe(int argc, char **argv) probe_helpers_for_progtype(i, supported_types[i], define_prefix, ifindex); + print_end_then_start_section("misc", + "Scanning miscellaneous eBPF features...", + "/*** eBPF misc features ***/", + define_prefix); + probe_large_insn_limit(define_prefix, ifindex); + exit_close_json: if (json_output) { /* End current "section" of probes */ diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c new file mode 100644 index 000000000000..f8113b3646f5 --- /dev/null +++ b/tools/bpf/bpftool/gen.c @@ -0,0 +1,609 @@ +// 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 <sys/types.h> +#include <sys/stat.h> +#include <sys/mman.h> +#include <unistd.h> +#include <bpf/btf.h> + +#include "bpf/libbpf_internal.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_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) +{ + int i; + + sprintf(guard, "__%s_SKEL_H__", obj_name); + for (i = 0; guard[i]; i++) + guard[i] = toupper(guard[i]); +} + +static const char *get_map_ident(const struct bpf_map *map) +{ + const char *name = bpf_map__name(map); + + if (!bpf_map__is_internal(map)) + return name; + + if (str_has_suffix(name, ".data")) + return "data"; + else if (str_has_suffix(name, ".rodata")) + return "rodata"; + else if (str_has_suffix(name, ".bss")) + return "bss"; + else if (str_has_suffix(name, ".kconfig")) + return "kconfig"; + else + return NULL; +} + +static void codegen_btf_dump_printf(void *ct, 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); + const char *sec_ident; + char var_ident[256]; + + if (strcmp(sec_name, ".data") == 0) + sec_ident = "data"; + else if (strcmp(sec_name, ".bss") == 0) + sec_ident = "bss"; + else if (strcmp(sec_name, ".rodata") == 0) + sec_ident = "rodata"; + else if (strcmp(sec_name, ".kconfig") == 0) + sec_ident = "kconfig"; + else + return 0; + + 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, + ); + int need_off = sec_var->offset, align_off, align; + __u32 var_type_id = var->type; + const struct btf_type *t; + + t = btf__type_by_id(btf, var_type_id); + while (btf_is_mod(t)) { + var_type_id = t->type; + t = btf__type_by_id(btf, var_type_id); + } + + 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; + } + + 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 int codegen_datasecs(struct bpf_object *obj, const char *obj_name) +{ + struct btf *btf = bpf_object__btf(obj); + int n = btf__get_nr_types(btf); + struct btf_dump *d; + int i, err = 0; + + d = btf_dump__new(btf, NULL, NULL, codegen_btf_dump_printf); + if (IS_ERR(d)) + return PTR_ERR(d); + + for (i = 1; i <= n; i++) { + const struct btf_type *t = btf__type_by_id(btf, i); + + if (!btf_is_datasec(t)) + continue; + + err = codegen_datasec_def(obj, btf, d, t, obj_name); + if (err) + goto out; + } +out: + btf_dump__free(d); + return err; +} + +static int 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) + return -ENOMEM; + 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'", + src - template - 1, template); + return -EINVAL; + } + } + + 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); + return -EINVAL; + } + } + /* 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); + return n; +} + +static int do_skeleton(int argc, char **argv) +{ + char header_guard[MAX_OBJ_NAME_LEN + sizeof("__SKEL_H__")]; + size_t i, 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, *ident; + struct bpf_program *prog; + int fd, len, err = -1; + struct bpf_map *map; + struct btf *btf; + struct stat st; + + if (!REQ_ARGS(1)) { + usage(); + return -1; + } + file = GET_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; + } + get_obj_name(obj_name, file); + opts.object_name = obj_name; + obj = bpf_object__open_mem(obj_data, file_sz, &opts); + if (IS_ERR(obj)) { + obj = NULL; + p_err("failed to open BPF object file: %ld", PTR_ERR(obj)); + goto out; + } + + bpf_object__for_each_map(map, obj) { + ident = get_map_ident(map); + if (!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); + 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$s \n\ + \n\ + #include <stdlib.h> \n\ + #include <bpf/libbpf.h> \n\ + \n\ + struct %1$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) { + ident = get_map_ident(map); + if (!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"); + printf("\tstruct {\n"); + bpf_object__for_each_program(prog, obj) { + 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; + } + + codegen("\ + \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$s *obj; \n\ + \n\ + obj = (typeof(obj))calloc(1, sizeof(*obj)); \n\ + if (!obj) \n\ + return NULL; \n\ + if (%1$s__create_skeleton(obj)) \n\ + goto err; \n\ + if (bpf_object__open_skeleton(obj->skeleton, opts)) \n\ + goto err; \n\ + \n\ + return obj; \n\ + err: \n\ + %1$s__destroy(obj); \n\ + return NULL; \n\ + } \n\ + \n\ + static inline struct %1$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$s *obj; \n\ + \n\ + obj = %1$s__open(); \n\ + if (!obj) \n\ + return NULL; \n\ + if (%1$s__load(obj)) { \n\ + %1$s__destroy(obj); \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\ + return bpf_object__detach_skeleton(obj->skeleton); \n\ + } \n\ + ", + obj_name + ); + + codegen("\ + \n\ + \n\ + static inline int \n\ + %1$s__create_skeleton(struct %1$s *obj) \n\ + { \n\ + struct bpf_object_skeleton *s; \n\ + \n\ + s = (typeof(s))calloc(1, sizeof(*s)); \n\ + if (!s) \n\ + return -1; \n\ + obj->skeleton = s; \n\ + \n\ + s->sz = sizeof(*s); \n\ + s->name = \"%1$s\"; \n\ + s->obj = &obj->obj; \n\ + ", + obj_name + ); + if (map_cnt) { + codegen("\ + \n\ + \n\ + /* maps */ \n\ + s->map_cnt = %zu; \n\ + s->map_skel_sz = sizeof(*s->maps); \n\ + s->maps = (typeof(s->maps))calloc(s->map_cnt, s->map_skel_sz);\n\ + if (!s->maps) \n\ + goto err; \n\ + ", + map_cnt + ); + i = 0; + bpf_object__for_each_map(map, obj) { + ident = get_map_ident(map); + + if (!ident) + continue; + + codegen("\ + \n\ + \n\ + s->maps[%zu].name = \"%s\"; \n\ + s->maps[%zu].map = &obj->maps.%s; \n\ + ", + i, bpf_map__name(map), i, ident); + /* memory-mapped internal maps */ + if (bpf_map__is_internal(map) && + (bpf_map__def(map)->map_flags & BPF_F_MMAPABLE)) { + printf("\ts->maps[%zu].mmaped = (void **)&obj->%s;\n", + i, ident); + } + i++; + } + } + if (prog_cnt) { + codegen("\ + \n\ + \n\ + /* programs */ \n\ + s->prog_cnt = %zu; \n\ + s->prog_skel_sz = sizeof(*s->progs); \n\ + s->progs = (typeof(s->progs))calloc(s->prog_cnt, s->prog_skel_sz);\n\ + if (!s->progs) \n\ + goto err; \n\ + ", + prog_cnt + ); + i = 0; + bpf_object__for_each_program(prog, obj) { + codegen("\ + \n\ + \n\ + s->progs[%1$zu].name = \"%2$s\"; \n\ + s->progs[%1$zu].prog = &obj->progs.%2$s;\n\ + s->progs[%1$zu].link = &obj->links.%2$s;\n\ + ", + i, bpf_program__name(prog)); + i++; + } + } + codegen("\ + \n\ + \n\ + s->data_sz = %d; \n\ + s->data = (void *)\"\\ \n\ + ", + file_sz); + + /* embed contents of BPF object file */ + for (i = 0, len = 0; i < file_sz; i++) { + int w = obj_data[i] ? 4 : 2; + + len += w; + if (len > 78) { + printf("\\\n"); + len = w; + } + if (!obj_data[i]) + printf("\\0"); + else + printf("\\x%02x", (unsigned char)obj_data[i]); + } + + codegen("\ + \n\ + \"; \n\ + \n\ + return 0; \n\ + err: \n\ + bpf_object__destroy_skeleton(s); \n\ + return -1; \n\ + } \n\ + \n\ + #endif /* %s */ \n\ + ", + header_guard); + err = 0; +out: + bpf_object__close(obj); + if (obj_data) + munmap(obj_data, mmap_sz); + close(fd); + return err; +} + +static int do_help(int argc, char **argv) +{ + if (json_output) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %1$s gen skeleton FILE\n" + " %1$s gen help\n" + "\n" + " " HELP_SPEC_OPTIONS "\n" + "", + bin_name); + + return 0; +} + +static const struct cmd cmds[] = { + { "skeleton", do_skeleton }, + { "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/jit_disasm.c b/tools/bpf/bpftool/jit_disasm.c index bfed711258ce..f7f5885aa3ba 100644 --- a/tools/bpf/bpftool/jit_disasm.c +++ b/tools/bpf/bpftool/jit_disasm.c @@ -24,7 +24,7 @@ #include <dis-asm.h> #include <sys/stat.h> #include <limits.h> -#include <libbpf.h> +#include <bpf/libbpf.h> #include "json_writer.h" #include "main.h" diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index 4764581ff9ea..6d41bbfc6459 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -9,8 +9,8 @@ #include <stdlib.h> #include <string.h> -#include <bpf.h> -#include <libbpf.h> +#include <bpf/bpf.h> +#include <bpf/libbpf.h> #include "main.h" @@ -58,7 +58,7 @@ static int do_help(int argc, char **argv) " %s batch file FILE\n" " %s version\n" "\n" - " OBJECT := { prog | map | cgroup | perf | net | feature | btf }\n" + " OBJECT := { prog | map | cgroup | perf | net | feature | btf | gen }\n" " " HELP_SPEC_OPTIONS "\n" "", bin_name, bin_name, bin_name); @@ -227,6 +227,7 @@ static const struct cmd cmds[] = { { "net", do_net }, { "feature", do_feature }, { "btf", do_btf }, + { "gen", do_gen }, { "version", do_version }, { 0 } }; diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 2899095f8254..4e75b58d3989 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -42,12 +42,12 @@ #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 }" + "PROG := { id PROG_ID | pinned FILE | tag PROG_TAG | name PROG_NAME }" #define HELP_SPEC_OPTIONS \ "OPTIONS := { {-j|--json} [{-p|--pretty}] | {-f|--bpffs} |\n" \ "\t {-m|--mapcompat} | {-n|--nomount} }" #define HELP_SPEC_MAP \ - "MAP := { id MAP_ID | pinned FILE }" + "MAP := { id MAP_ID | pinned FILE | name MAP_NAME }" static const char * const prog_type_name[] = { [BPF_PROG_TYPE_UNSPEC] = "unspec", @@ -155,6 +155,7 @@ int do_net(int argc, char **arg); int do_tracelog(int argc, char **arg); int do_feature(int argc, char **argv); int do_btf(int argc, char **argv); +int do_gen(int argc, char **argv); int parse_u32_arg(int *argc, char ***argv, __u32 *val, const char *what); int prog_parse_fd(int *argc, char ***argv); diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index de61d73b9030..e6c85680b34d 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -15,9 +15,9 @@ #include <sys/types.h> #include <sys/stat.h> -#include <bpf.h> +#include <bpf/bpf.h> +#include <bpf/btf.h> -#include "btf.h" #include "json_writer.h" #include "main.h" @@ -48,6 +48,7 @@ const char * const map_type_name[] = { [BPF_MAP_TYPE_QUEUE] = "queue", [BPF_MAP_TYPE_STACK] = "stack", [BPF_MAP_TYPE_SK_STORAGE] = "sk_storage", + [BPF_MAP_TYPE_STRUCT_OPS] = "struct_ops", }; const size_t map_type_name_size = ARRAY_SIZE(map_type_name); @@ -91,10 +92,66 @@ static void *alloc_value(struct bpf_map_info *info) return malloc(info->value_size); } -int map_parse_fd(int *argc, char ***argv) +static int map_fd_by_name(char *name, int **fds) { - int fd; + 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; +} + +static int map_parse_fds(int *argc, char ***argv, int **fds) +{ if (is_prefix(**argv, "id")) { unsigned int id; char *endptr; @@ -108,10 +165,25 @@ int map_parse_fd(int *argc, char ***argv) } NEXT_ARGP(); - fd = bpf_map_get_fd_by_id(id); - if (fd < 0) + (*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 fd; + 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; @@ -120,13 +192,43 @@ int map_parse_fd(int *argc, char ***argv) path = **argv; NEXT_ARGP(); - return open_obj_pinned_any(path, BPF_OBJ_MAP); + (*fds)[0] = open_obj_pinned_any(path, BPF_OBJ_MAP); + if ((*fds)[0] < 0) + return -1; + return 1; } - p_err("expected 'id' or 'pinned', got: '%s'?", **argv); + 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; @@ -150,6 +252,7 @@ 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; /* start of key-value pair */ @@ -163,9 +266,12 @@ static int do_dump_btf(const struct btf_dumper *d, 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, map_info->btf_value_type_id, value); + ret = btf_dumper_type(d, value_id, value); } else { unsigned int i, n, step; @@ -177,8 +283,7 @@ static int do_dump_btf(const struct btf_dumper *d, jsonw_start_object(d->jw); jsonw_int_field(d->jw, "cpu", i); jsonw_name(d->jw, "value"); - ret = btf_dumper_type(d, map_info->btf_value_type_id, - value + i * step); + ret = btf_dumper_type(d, value_id, value + i * step); jsonw_end_object(d->jw); if (ret) break; @@ -479,6 +584,21 @@ static int parse_elem(char **argv, struct bpf_map_info *info, return -1; } +static void show_map_header_json(struct bpf_map_info *info, json_writer_t *wtr) +{ + jsonw_uint_field(wtr, "id", info->id); + if (info->type < ARRAY_SIZE(map_type_name)) + jsonw_string_field(wtr, "type", map_type_name[info->type]); + 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; @@ -489,18 +609,7 @@ static int show_map_close_json(int fd, struct bpf_map_info *info) jsonw_start_object(json_wtr); - jsonw_uint_field(json_wtr, "id", info->id); - if (info->type < ARRAY_SIZE(map_type_name)) - jsonw_string_field(json_wtr, "type", - map_type_name[info->type]); - else - jsonw_uint_field(json_wtr, "type", info->type); - - if (*info->name) - jsonw_string_field(json_wtr, "name", info->name); - - jsonw_name(json_wtr, "flags"); - jsonw_printf(json_wtr, "%d", info->map_flags); + show_map_header_json(info, json_wtr); print_dev_json(info->ifindex, info->netns_dev, info->netns_ino); @@ -561,14 +670,8 @@ static int show_map_close_json(int fd, struct bpf_map_info *info) return 0; } -static int show_map_close_plain(int fd, struct bpf_map_info *info) +static void show_map_header_plain(struct bpf_map_info *info) { - char *memlock, *frozen_str; - int frozen = 0; - - memlock = get_fdinfo(fd, "memlock"); - frozen_str = get_fdinfo(fd, "frozen"); - printf("%u: ", info->id); if (info->type < ARRAY_SIZE(map_type_name)) printf("%s ", map_type_name[info->type]); @@ -581,6 +684,17 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info) 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); @@ -642,6 +756,50 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info) 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 = {}; @@ -653,16 +811,8 @@ static int do_show(int argc, char **argv) if (show_pinned) build_pinned_obj_table(&map_table, BPF_OBJ_MAP); - if (argc == 2) { - fd = map_parse_fd_and_info(&argc, &argv, &info, &len); - if (fd < 0) - return -1; - - if (json_output) - return show_map_close_json(fd, &info); - else - return show_map_close_plain(fd, &info); - } + if (argc == 2) + return do_show_subset(argc, argv); if (argc) return BAD_ARG(); @@ -765,26 +915,75 @@ static int dump_map_elem(int fd, void *key, void *value, return 0; } -static int do_dump(int argc, char **argv) +static int maps_have_btf(int *fds, int nb_fds) { struct bpf_map_info info = {}; - void *key, *value, *prev_key; - unsigned int num_elems = 0; __u32 len = sizeof(info); - json_writer_t *btf_wtr; + 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 struct btf *get_map_kv_btf(const struct bpf_map_info *info) +{ struct btf *btf = NULL; - int err; - int fd; - if (argc != 2) - usage(); + if (info->btf_vmlinux_value_type_id) { + if (!btf_vmlinux) { + btf_vmlinux = libbpf_find_kernel_btf(); + if (IS_ERR(btf_vmlinux)) + p_err("failed to get kernel btf"); + } + return btf_vmlinux; + } else if (info->btf_value_type_id) { + int err; + + err = btf__get_from_id(info->btf_id, &btf); + if (err || !btf) { + p_err("failed to get btf"); + btf = err ? ERR_PTR(err) : ERR_PTR(-ESRCH); + } + } - fd = map_parse_fd_and_info(&argc, &argv, &info, &len); - if (fd < 0) - return -1; + return btf; +} - key = malloc(info.key_size); - value = alloc_value(&info); +static void free_map_kv_btf(struct btf *btf) +{ + if (!IS_ERR(btf) && btf != btf_vmlinux) + btf__free(btf); +} + +static void free_btf_vmlinux(void) +{ + if (!IS_ERR(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; @@ -793,30 +992,27 @@ static int do_dump(int argc, char **argv) prev_key = NULL; - err = btf__get_from_id(info.btf_id, &btf); - if (err) { - p_err("failed to get btf"); - goto exit_free; - } + if (wtr) { + btf = get_map_kv_btf(info); + if (IS_ERR(btf)) { + err = PTR_ERR(btf); + goto exit_free; + } - if (json_output) - jsonw_start_array(json_wtr); - else - if (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; - } else { - jsonw_start_array(btf_wtr); - } + 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) + if (info->type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY && + info->value_size != 8) p_info("Warning: cannot read values from %s map with value_size != 8", - map_type_name[info.type]); + map_type_name[info->type]); while (true) { err = bpf_map_get_next_key(fd, prev_key, key); if (err) { @@ -824,15 +1020,14 @@ static int do_dump(int argc, char **argv) err = 0; break; } - num_elems += dump_map_elem(fd, key, value, &info, btf, btf_wtr); + num_elems += dump_map_elem(fd, key, value, info, btf, wtr); prev_key = key; } - if (json_output) - jsonw_end_array(json_wtr); - else if (btf) { - jsonw_end_array(btf_wtr); - jsonw_destroy(&btf_wtr); + 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" : ""); @@ -842,11 +1037,78 @@ exit_free: free(key); free(value); close(fd); - btf__free(btf); + 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; diff --git a/tools/bpf/bpftool/map_perf_ring.c b/tools/bpf/bpftool/map_perf_ring.c index 4c5531d1a450..d9b29c17fbb8 100644 --- a/tools/bpf/bpftool/map_perf_ring.c +++ b/tools/bpf/bpftool/map_perf_ring.c @@ -6,7 +6,7 @@ */ #include <errno.h> #include <fcntl.h> -#include <libbpf.h> +#include <bpf/libbpf.h> #include <poll.h> #include <signal.h> #include <stdbool.h> @@ -21,7 +21,7 @@ #include <sys/mman.h> #include <sys/syscall.h> -#include <bpf.h> +#include <bpf/bpf.h> #include <perf-sys.h> #include "main.h" diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c index 4f52d3151616..c5e3895b7c8b 100644 --- a/tools/bpf/bpftool/net.c +++ b/tools/bpf/bpftool/net.c @@ -7,7 +7,8 @@ #include <stdlib.h> #include <string.h> #include <unistd.h> -#include <libbpf.h> +#include <bpf/bpf.h> +#include <bpf/libbpf.h> #include <net/if.h> #include <linux/if.h> #include <linux/rtnetlink.h> @@ -16,8 +17,8 @@ #include <sys/stat.h> #include <sys/types.h> -#include <bpf.h> -#include <nlattr.h> +#include "bpf/nlattr.h" +#include "bpf/libbpf_internal.h" #include "main.h" #include "netlink_dumper.h" diff --git a/tools/bpf/bpftool/netlink_dumper.c b/tools/bpf/bpftool/netlink_dumper.c index 550a0f537eed..5f65140b003b 100644 --- a/tools/bpf/bpftool/netlink_dumper.c +++ b/tools/bpf/bpftool/netlink_dumper.c @@ -3,11 +3,11 @@ #include <stdlib.h> #include <string.h> -#include <libbpf.h> +#include <bpf/libbpf.h> #include <linux/rtnetlink.h> #include <linux/tc_act/tc_bpf.h> -#include <nlattr.h> +#include "bpf/nlattr.h" #include "main.h" #include "netlink_dumper.h" diff --git a/tools/bpf/bpftool/perf.c b/tools/bpf/bpftool/perf.c index b2046f33e23f..3341aa14acda 100644 --- a/tools/bpf/bpftool/perf.c +++ b/tools/bpf/bpftool/perf.c @@ -13,7 +13,7 @@ #include <unistd.h> #include <ftw.h> -#include <bpf.h> +#include <bpf/bpf.h> #include "main.h" diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 2ce9c5ba1934..a3521deca869 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -17,14 +17,19 @@ #include <linux/err.h> #include <linux/sizes.h> -#include <bpf.h> -#include <btf.h> -#include <libbpf.h> +#include <bpf/bpf.h> +#include <bpf/btf.h> +#include <bpf/libbpf.h> #include "cfg.h" #include "main.h" #include "xlated_dumper.h" +enum dump_mode { + DUMP_JITED, + DUMP_XLATED, +}; + static const char * const attach_type_strings[] = { [BPF_SK_SKB_STREAM_PARSER] = "stream_parser", [BPF_SK_SKB_STREAM_VERDICT] = "stream_verdict", @@ -77,11 +82,12 @@ static void print_boot_time(__u64 nsecs, char *buf, unsigned int size) strftime(buf, size, "%FT%T%z", &load_tm); } -static int prog_fd_by_tag(unsigned char *tag) +static int prog_fd_by_nametag(void *nametag, int **fds, bool tag) { unsigned int id = 0; + int fd, nb_fds = 0; + void *tmp; int err; - int fd; while (true) { struct bpf_prog_info info = {}; @@ -89,36 +95,54 @@ static int prog_fd_by_tag(unsigned char *tag) err = bpf_prog_get_next_id(id, &id); if (err) { - p_err("%s", strerror(errno)); - return -1; + 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)); - return -1; + 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)); - close(fd); - return -1; + goto err_close_fd; } - if (!memcmp(tag, info.tag, BPF_TAG_SIZE)) - return fd; + if ((tag && memcmp(nametag, info.tag, BPF_TAG_SIZE)) || + (!tag && strncmp(nametag, info.name, BPF_OBJ_NAME_LEN))) { + close(fd); + continue; + } - close(fd); + 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_fd(int *argc, char ***argv) +static int prog_parse_fds(int *argc, char ***argv, int **fds) { - int fd; - if (is_prefix(**argv, "id")) { unsigned int id; char *endptr; @@ -132,10 +156,12 @@ int prog_parse_fd(int *argc, char ***argv) } NEXT_ARGP(); - fd = bpf_prog_get_fd_by_id(id); - if (fd < 0) + (*fds)[0] = bpf_prog_get_fd_by_id(id); + if ((*fds)[0] < 0) { p_err("get by id (%u): %s", id, strerror(errno)); - return fd; + return -1; + } + return 1; } else if (is_prefix(**argv, "tag")) { unsigned char tag[BPF_TAG_SIZE]; @@ -149,7 +175,20 @@ int prog_parse_fd(int *argc, char ***argv) } NEXT_ARGP(); - return prog_fd_by_tag(tag); + return prog_fd_by_nametag(tag, fds, true); + } 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 prog_fd_by_nametag(name, fds, false); } else if (is_prefix(**argv, "pinned")) { char *path; @@ -158,13 +197,43 @@ int prog_parse_fd(int *argc, char ***argv) path = **argv; NEXT_ARGP(); - return open_obj_pinned_any(path, BPF_OBJ_PROG); + (*fds)[0] = open_obj_pinned_any(path, BPF_OBJ_PROG); + if ((*fds)[0] < 0) + return -1; + return 1; } - p_err("expected 'id', 'tag' or 'pinned', got: '%s'?", **argv); + 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 void show_prog_maps(int fd, u32 num_maps) { struct bpf_prog_info info = {}; @@ -194,11 +263,8 @@ static void show_prog_maps(int fd, u32 num_maps) } } -static void print_prog_json(struct bpf_prog_info *info, int fd) +static void print_prog_header_json(struct bpf_prog_info *info) { - char *memlock; - - jsonw_start_object(json_wtr); jsonw_uint_field(json_wtr, "id", info->id); if (info->type < ARRAY_SIZE(prog_type_name)) jsonw_string_field(json_wtr, "type", @@ -219,7 +285,14 @@ static void print_prog_json(struct bpf_prog_info *info, int fd) jsonw_uint_field(json_wtr, "run_time_ns", info->run_time_ns); jsonw_uint_field(json_wtr, "run_cnt", info->run_cnt); } +} +static void print_prog_json(struct bpf_prog_info *info, int fd) +{ + char *memlock; + + jsonw_start_object(json_wtr); + print_prog_header_json(info); print_dev_json(info->ifindex, info->netns_dev, info->netns_ino); if (info->load_time) { @@ -268,10 +341,8 @@ static void print_prog_json(struct bpf_prog_info *info, int fd) jsonw_end_object(json_wtr); } -static void print_prog_plain(struct bpf_prog_info *info, int fd) +static void print_prog_header_plain(struct bpf_prog_info *info) { - char *memlock; - printf("%u: ", info->id); if (info->type < ARRAY_SIZE(prog_type_name)) printf("%s ", prog_type_name[info->type]); @@ -289,6 +360,13 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd) printf(" run_time_ns %lld run_cnt %lld", info->run_time_ns, info->run_cnt); printf("\n"); +} + +static void print_prog_plain(struct bpf_prog_info *info, int fd) +{ + char *memlock; + + print_prog_header_plain(info); if (info->load_time) { char buf[32]; @@ -349,6 +427,40 @@ static int show_prog(int 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; @@ -358,15 +470,8 @@ static int do_show(int argc, char **argv) if (show_pinned) build_pinned_obj_table(&prog_table, BPF_OBJ_PROG); - if (argc == 2) { - fd = prog_parse_fd(&argc, &argv); - if (fd < 0) - return -1; - - err = show_prog(fd); - close(fd); - return err; - } + if (argc == 2) + return do_show_subset(argc, argv); if (argc) return BAD_ARG(); @@ -408,101 +513,32 @@ static int do_show(int argc, char **argv) return err; } -static int do_dump(int argc, char **argv) +static int +prog_dump(struct bpf_prog_info *info, enum dump_mode mode, + char *filepath, bool opcodes, bool visual, bool linum) { - struct bpf_prog_info_linear *info_linear; struct bpf_prog_linfo *prog_linfo = NULL; - enum {DUMP_JITED, DUMP_XLATED} mode; const char *disasm_opt = NULL; - struct bpf_prog_info *info; struct dump_data dd = {}; void *func_info = NULL; struct btf *btf = NULL; - char *filepath = NULL; - bool opcodes = false; - bool visual = false; char func_sig[1024]; unsigned char *buf; - bool linum = false; __u32 member_len; - __u64 arrays; ssize_t n; int fd; - 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(); - - fd = prog_parse_fd(&argc, &argv); - if (fd < 0) - return -1; - - if (is_prefix(*argv, "file")) { - NEXT_ARG(); - if (!argc) { - p_err("expected file path"); - return -1; - } - - filepath = *argv; - NEXT_ARG(); - } else if (is_prefix(*argv, "opcodes")) { - opcodes = true; - NEXT_ARG(); - } else if (is_prefix(*argv, "visual")) { - visual = true; - NEXT_ARG(); - } else if (is_prefix(*argv, "linum")) { - linum = true; - NEXT_ARG(); - } - - if (argc) { - usage(); - return -1; - } - - if (mode == DUMP_JITED) - arrays = 1UL << BPF_PROG_INFO_JITED_INSNS; - else - arrays = 1UL << BPF_PROG_INFO_XLATED_INSNS; - - arrays |= 1UL << BPF_PROG_INFO_JITED_KSYMS; - arrays |= 1UL << BPF_PROG_INFO_JITED_FUNC_LENS; - arrays |= 1UL << BPF_PROG_INFO_FUNC_INFO; - arrays |= 1UL << BPF_PROG_INFO_LINE_INFO; - arrays |= 1UL << BPF_PROG_INFO_JITED_LINE_INFO; - - info_linear = bpf_program__get_prog_info_linear(fd, arrays); - close(fd); - if (IS_ERR_OR_NULL(info_linear)) { - p_err("can't get prog info: %s", strerror(errno)); - return -1; - } - - info = &info_linear->info; if (mode == DUMP_JITED) { if (info->jited_prog_len == 0 || !info->jited_prog_insns) { p_info("no instructions returned"); - goto err_free; + return -1; } buf = (unsigned char *)(info->jited_prog_insns); member_len = info->jited_prog_len; } else { /* DUMP_XLATED */ if (info->xlated_prog_len == 0) { p_err("error retrieving insn dump: kernel.kptr_restrict set?"); - goto err_free; + return -1; } buf = (unsigned char *)info->xlated_prog_insns; member_len = info->xlated_prog_len; @@ -510,7 +546,7 @@ static int do_dump(int argc, char **argv) if (info->btf_id && btf__get_from_id(info->btf_id, &btf)) { p_err("failed to get btf"); - goto err_free; + return -1; } func_info = (void *)info->func_info; @@ -526,7 +562,7 @@ static int do_dump(int argc, char **argv) if (fd < 0) { p_err("can't open file %s: %s", filepath, strerror(errno)); - goto err_free; + return -1; } n = write(fd, buf, member_len); @@ -534,7 +570,7 @@ static int do_dump(int argc, char **argv) if (n != member_len) { p_err("error writing output file: %s", n < 0 ? strerror(errno) : "short write"); - goto err_free; + return -1; } if (json_output) @@ -548,7 +584,7 @@ static int do_dump(int argc, char **argv) info->netns_ino, &disasm_opt); if (!name) - goto err_free; + return -1; } if (info->nr_jited_func_lens && info->jited_func_lens) { @@ -643,12 +679,130 @@ static int do_dump(int argc, char **argv) kernel_syms_destroy(&dd); } - free(info_linear); return 0; +} -err_free: - free(info_linear); - return -1; +static int do_dump(int argc, char **argv) +{ + struct bpf_prog_info_linear *info_linear; + char *filepath = NULL; + bool opcodes = false; + bool visual = false; + enum dump_mode mode; + bool linum = false; + int *fds = NULL; + int nb_fds, i = 0; + int err = -1; + __u64 arrays; + + 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 (mode == DUMP_JITED) + arrays = 1UL << BPF_PROG_INFO_JITED_INSNS; + else + arrays = 1UL << BPF_PROG_INFO_XLATED_INSNS; + + arrays |= 1UL << BPF_PROG_INFO_JITED_KSYMS; + arrays |= 1UL << BPF_PROG_INFO_JITED_FUNC_LENS; + arrays |= 1UL << BPF_PROG_INFO_FUNC_INFO; + arrays |= 1UL << BPF_PROG_INFO_LINE_INFO; + arrays |= 1UL << BPF_PROG_INFO_JITED_LINE_INFO; + + if (json_output && nb_fds > 1) + jsonw_start_array(json_wtr); /* root array */ + for (i = 0; i < nb_fds; i++) { + info_linear = bpf_program__get_prog_info_linear(fds[i], arrays); + if (IS_ERR_OR_NULL(info_linear)) { + 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_linear->info); + jsonw_name(json_wtr, "insns"); + } else if (nb_fds > 1) { + print_prog_header_plain(&info_linear->info); + } + + err = prog_dump(&info_linear->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"); + + free(info_linear); + 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(fds); + return err; } static int do_pin(int argc, char **argv) diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c index 5b91ee65a080..8608cd68cdd0 100644 --- a/tools/bpf/bpftool/xlated_dumper.c +++ b/tools/bpf/bpftool/xlated_dumper.c @@ -7,7 +7,7 @@ #include <stdlib.h> #include <string.h> #include <sys/types.h> -#include <libbpf.h> +#include <bpf/libbpf.h> #include "disasm.h" #include "json_writer.h" diff --git a/tools/bpf/runqslower/.gitignore b/tools/bpf/runqslower/.gitignore new file mode 100644 index 000000000000..90a456a2a72f --- /dev/null +++ b/tools/bpf/runqslower/.gitignore @@ -0,0 +1 @@ +/.output diff --git a/tools/bpf/runqslower/Makefile b/tools/bpf/runqslower/Makefile new file mode 100644 index 000000000000..0c021352beed --- /dev/null +++ b/tools/bpf/runqslower/Makefile @@ -0,0 +1,84 @@ +# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +OUTPUT := .output +CLANG ?= clang +LLC ?= llc +LLVM_STRIP ?= llvm-strip +DEFAULT_BPFTOOL := $(OUTPUT)/sbin/bpftool +BPFTOOL ?= $(DEFAULT_BPFTOOL) +LIBBPF_SRC := $(abspath ../../lib/bpf) +BPFOBJ := $(OUTPUT)/libbpf.a +BPF_INCLUDE := $(OUTPUT) +INCLUDES := -I$(BPF_INCLUDE) -I$(OUTPUT) -I$(abspath ../../lib) +CFLAGS := -g -Wall + +# Try to detect best kernel BTF source +KERNEL_REL := $(shell uname -r) +VMLINUX_BTF_PATHS := /sys/kernel/btf/vmlinux /boot/vmlinux-$(KERNEL_REL) +VMLINUX_BTF_PATH := $(or $(VMLINUX_BTF),$(firstword \ + $(wildcard $(VMLINUX_BTF_PATHS)))) + +abs_out := $(abspath $(OUTPUT)) +ifeq ($(V),1) +Q = +msg = +else +Q = @ +msg = @printf ' %-8s %s%s\n' "$(1)" "$(notdir $(2))" "$(if $(3), $(3))"; +MAKEFLAGS += --no-print-directory +submake_extras := feature_display=0 +endif + +.DELETE_ON_ERROR: + +.PHONY: all clean runqslower +all: runqslower + +runqslower: $(OUTPUT)/runqslower + +clean: + $(call msg,CLEAN) + $(Q)rm -rf $(OUTPUT) runqslower + +$(OUTPUT)/runqslower: $(OUTPUT)/runqslower.o $(BPFOBJ) + $(call msg,BINARY,$@) + $(Q)$(CC) $(CFLAGS) -lelf -lz $^ -o $@ + +$(OUTPUT)/runqslower.o: runqslower.h $(OUTPUT)/runqslower.skel.h \ + $(OUTPUT)/runqslower.bpf.o + +$(OUTPUT)/runqslower.bpf.o: $(OUTPUT)/vmlinux.h runqslower.h + +$(OUTPUT)/%.skel.h: $(OUTPUT)/%.bpf.o | $(BPFTOOL) + $(call msg,GEN-SKEL,$@) + $(Q)$(BPFTOOL) gen skeleton $< > $@ + +$(OUTPUT)/%.bpf.o: %.bpf.c $(BPFOBJ) | $(OUTPUT) + $(call msg,BPF,$@) + $(Q)$(CLANG) -g -O2 -target bpf $(INCLUDES) \ + -c $(filter %.c,$^) -o $@ && \ + $(LLVM_STRIP) -g $@ + +$(OUTPUT)/%.o: %.c | $(OUTPUT) + $(call msg,CC,$@) + $(Q)$(CC) $(CFLAGS) $(INCLUDES) -c $(filter %.c,$^) -o $@ + +$(OUTPUT): + $(call msg,MKDIR,$@) + $(Q)mkdir -p $(OUTPUT) + +$(OUTPUT)/vmlinux.h: $(VMLINUX_BTF_PATH) | $(OUTPUT) $(BPFTOOL) + $(call msg,GEN,$@) + $(Q)if [ ! -e "$(VMLINUX_BTF_PATH)" ] ; then \ + echo "Couldn't find kernel BTF; set VMLINUX_BTF to" \ + "specify its location." >&2; \ + exit 1;\ + fi + $(Q)$(BPFTOOL) btf dump file $(VMLINUX_BTF_PATH) format c > $@ + +$(BPFOBJ): | $(OUTPUT) + $(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) \ + OUTPUT=$(abspath $(dir $@))/ $(abspath $@) + +$(DEFAULT_BPFTOOL): + $(Q)$(MAKE) $(submake_extras) -C ../bpftool \ + prefix= OUTPUT=$(abs_out)/ DESTDIR=$(abs_out) install diff --git a/tools/bpf/runqslower/runqslower.bpf.c b/tools/bpf/runqslower/runqslower.bpf.c new file mode 100644 index 000000000000..48a39f72fadf --- /dev/null +++ b/tools/bpf/runqslower/runqslower.bpf.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include "runqslower.h" + +#define TASK_RUNNING 0 + +#define BPF_F_INDEX_MASK 0xffffffffULL +#define BPF_F_CURRENT_CPU BPF_F_INDEX_MASK + +const volatile __u64 min_us = 0; +const volatile pid_t targ_pid = 0; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 10240); + __type(key, u32); + __type(value, u64); +} start SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __uint(key_size, sizeof(u32)); + __uint(value_size, sizeof(u32)); +} events SEC(".maps"); + +/* record enqueue timestamp */ +__always_inline +static int trace_enqueue(u32 tgid, u32 pid) +{ + u64 ts; + + if (!pid || (targ_pid && targ_pid != pid)) + return 0; + + ts = bpf_ktime_get_ns(); + bpf_map_update_elem(&start, &pid, &ts, 0); + return 0; +} + +SEC("tp_btf/sched_wakeup") +int handle__sched_wakeup(u64 *ctx) +{ + /* TP_PROTO(struct task_struct *p) */ + struct task_struct *p = (void *)ctx[0]; + + return trace_enqueue(p->tgid, p->pid); +} + +SEC("tp_btf/sched_wakeup_new") +int handle__sched_wakeup_new(u64 *ctx) +{ + /* TP_PROTO(struct task_struct *p) */ + struct task_struct *p = (void *)ctx[0]; + + return trace_enqueue(p->tgid, p->pid); +} + +SEC("tp_btf/sched_switch") +int handle__sched_switch(u64 *ctx) +{ + /* TP_PROTO(bool preempt, struct task_struct *prev, + * struct task_struct *next) + */ + struct task_struct *prev = (struct task_struct *)ctx[1]; + struct task_struct *next = (struct task_struct *)ctx[2]; + struct event event = {}; + u64 *tsp, delta_us; + long state; + u32 pid; + + /* ivcsw: treat like an enqueue event and store timestamp */ + if (prev->state == TASK_RUNNING) + trace_enqueue(prev->tgid, prev->pid); + + pid = next->pid; + + /* fetch timestamp and calculate delta */ + tsp = bpf_map_lookup_elem(&start, &pid); + if (!tsp) + return 0; /* missed enqueue */ + + delta_us = (bpf_ktime_get_ns() - *tsp) / 1000; + if (min_us && delta_us <= min_us) + return 0; + + event.pid = pid; + event.delta_us = delta_us; + bpf_get_current_comm(&event.task, sizeof(event.task)); + + /* output */ + bpf_perf_event_output(ctx, &events, BPF_F_CURRENT_CPU, + &event, sizeof(event)); + + bpf_map_delete_elem(&start, &pid); + return 0; +} + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/bpf/runqslower/runqslower.c b/tools/bpf/runqslower/runqslower.c new file mode 100644 index 000000000000..d89715844952 --- /dev/null +++ b/tools/bpf/runqslower/runqslower.c @@ -0,0 +1,187 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +// Copyright (c) 2019 Facebook +#include <argp.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/resource.h> +#include <time.h> +#include <bpf/libbpf.h> +#include <bpf/bpf.h> +#include "runqslower.h" +#include "runqslower.skel.h" + +struct env { + pid_t pid; + __u64 min_us; + bool verbose; +} env = { + .min_us = 10000, +}; + +const char *argp_program_version = "runqslower 0.1"; +const char *argp_program_bug_address = "<bpf@vger.kernel.org>"; +const char argp_program_doc[] = +"runqslower Trace long process scheduling delays.\n" +" For Linux, uses eBPF, BPF CO-RE, libbpf, BTF.\n" +"\n" +"This script traces high scheduling delays between tasks being\n" +"ready to run and them running on CPU after that.\n" +"\n" +"USAGE: runqslower [-p PID] [min_us]\n" +"\n" +"EXAMPLES:\n" +" runqslower # trace run queue latency higher than 10000 us (default)\n" +" runqslower 1000 # trace run queue latency higher than 1000 us\n" +" runqslower -p 123 # trace pid 123 only\n"; + +static const struct argp_option opts[] = { + { "pid", 'p', "PID", 0, "Process PID to trace"}, + { "verbose", 'v', NULL, 0, "Verbose debug output" }, + {}, +}; + +static error_t parse_arg(int key, char *arg, struct argp_state *state) +{ + static int pos_args; + int pid; + long long min_us; + + switch (key) { + case 'v': + env.verbose = true; + break; + case 'p': + errno = 0; + pid = strtol(arg, NULL, 10); + if (errno || pid <= 0) { + fprintf(stderr, "Invalid PID: %s\n", arg); + argp_usage(state); + } + env.pid = pid; + break; + case ARGP_KEY_ARG: + if (pos_args++) { + fprintf(stderr, + "Unrecognized positional argument: %s\n", arg); + argp_usage(state); + } + errno = 0; + min_us = strtoll(arg, NULL, 10); + if (errno || min_us <= 0) { + fprintf(stderr, "Invalid delay (in us): %s\n", arg); + argp_usage(state); + } + env.min_us = min_us; + break; + default: + return ARGP_ERR_UNKNOWN; + } + return 0; +} + +int libbpf_print_fn(enum libbpf_print_level level, + const char *format, va_list args) +{ + if (level == LIBBPF_DEBUG && !env.verbose) + return 0; + return vfprintf(stderr, format, args); +} + +static int bump_memlock_rlimit(void) +{ + struct rlimit rlim_new = { + .rlim_cur = RLIM_INFINITY, + .rlim_max = RLIM_INFINITY, + }; + + return setrlimit(RLIMIT_MEMLOCK, &rlim_new); +} + +void handle_event(void *ctx, int cpu, void *data, __u32 data_sz) +{ + const struct event *e = data; + struct tm *tm; + char ts[32]; + time_t t; + + time(&t); + tm = localtime(&t); + strftime(ts, sizeof(ts), "%H:%M:%S", tm); + printf("%-8s %-16s %-6d %14llu\n", ts, e->task, e->pid, e->delta_us); +} + +void handle_lost_events(void *ctx, int cpu, __u64 lost_cnt) +{ + printf("Lost %llu events on CPU #%d!\n", lost_cnt, cpu); +} + +int main(int argc, char **argv) +{ + static const struct argp argp = { + .options = opts, + .parser = parse_arg, + .doc = argp_program_doc, + }; + struct perf_buffer_opts pb_opts; + struct perf_buffer *pb = NULL; + struct runqslower_bpf *obj; + int err; + + err = argp_parse(&argp, argc, argv, 0, NULL, NULL); + if (err) + return err; + + libbpf_set_print(libbpf_print_fn); + + err = bump_memlock_rlimit(); + if (err) { + fprintf(stderr, "failed to increase rlimit: %d", err); + return 1; + } + + obj = runqslower_bpf__open(); + if (!obj) { + fprintf(stderr, "failed to open and/or load BPF object\n"); + return 1; + } + + /* initialize global data (filtering options) */ + obj->rodata->targ_pid = env.pid; + obj->rodata->min_us = env.min_us; + + err = runqslower_bpf__load(obj); + if (err) { + fprintf(stderr, "failed to load BPF object: %d\n", err); + goto cleanup; + } + + err = runqslower_bpf__attach(obj); + if (err) { + fprintf(stderr, "failed to attach BPF programs\n"); + goto cleanup; + } + + printf("Tracing run queue latency higher than %llu us\n", env.min_us); + printf("%-8s %-16s %-6s %14s\n", "TIME", "COMM", "PID", "LAT(us)"); + + pb_opts.sample_cb = handle_event; + pb_opts.lost_cb = handle_lost_events; + pb = perf_buffer__new(bpf_map__fd(obj->maps.events), 64, &pb_opts); + err = libbpf_get_error(pb); + if (err) { + pb = NULL; + fprintf(stderr, "failed to open perf buffer: %d\n", err); + goto cleanup; + } + + while ((err = perf_buffer__poll(pb, 100)) >= 0) + ; + printf("Error polling perf buffer: %d\n", err); + +cleanup: + perf_buffer__free(pb); + runqslower_bpf__destroy(obj); + + return err != 0; +} diff --git a/tools/bpf/runqslower/runqslower.h b/tools/bpf/runqslower/runqslower.h new file mode 100644 index 000000000000..9db225425e5f --- /dev/null +++ b/tools/bpf/runqslower/runqslower.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +#ifndef __RUNQSLOWER_H +#define __RUNQSLOWER_H + +#define TASK_COMM_LEN 16 + +struct event { + char task[TASK_COMM_LEN]; + __u64 delta_us; + pid_t pid; +}; + +#endif /* __RUNQSLOWER_H */ |